├── 1.Python Crash Course
    └── Python Crash Course.ipynb
├── 2.Intro to Pandas
    ├── 1.Creating a Dataframe.ipynb
    ├── 2.Displaying a Dataframe.ipynb
    ├── 3. Basic Attributes, Methods and Functions.ipynb
    ├── 4.Selecting One Column from a Dataframe.ipynb
    ├── 5.Selecting Two or More Columns from a Dataframe.ipynb
    ├── 6.Add New Column to a Dataframe.ipynb
    ├── 7.Operations on Dataframes.ipynb
    ├── 8.The value_counts() method.ipynb
    ├── 9.Sort a Dataframe with sort_values().ipynb
    └── StudentsPerformance.csv
├── 3.Pivot Table
    ├── 1.pivot() and pivot_table().ipynb
    ├── gdp.csv
    └── supermarket_sales.xlsx
├── 4.Data Visualization
    ├── 1.Dataset Overview and Making Pivot Table.ipynb
    ├── 2.Data Visualization with Pandas.ipynb
    ├── 3.Adding Matplotlib to Pandas.ipynb
    └── population_total.csv
├── Exercises
    ├── Intro to Pandas
    │   ├── Introduction to Pandas-Exercise.ipynb
    │   ├── Introduction to Pandas-Solution.ipynb
    │   └── bestsellers with categories.csv
    └── Merging and Concatenating DataFrames
    │   ├── IMDb movies.csv.zip
    │   ├── IMDb ratings.csv.zip
    │   ├── Merging and Concatenating DataFrames-Exercise.ipynb
    │   └── Merging and Concatenating DataFrames-Solution.ipynb
├── README.md
├── Web Scraping with Pandas.ipynb
├── loc vs iloc.ipynb
└── players_20.csv


/2.Intro to Pandas/1.Creating a Dataframe.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 2,
  6 |    "id": "7fa9cddf",
  7 |    "metadata": {},
  8 |    "outputs": [],
  9 |    "source": [
 10 |     "import pandas as pd\n",
 11 |     "import numpy as np"
 12 |    ]
 13 |   },
 14 |   {
 15 |    "cell_type": "markdown",
 16 |    "id": "81a09ffd",
 17 |    "metadata": {},
 18 |    "source": [
 19 |     "# Creating a dataframe from an array"
 20 |    ]
 21 |   },
 22 |   {
 23 |    "cell_type": "markdown",
 24 |    "id": "6db0cb3f",
 25 |    "metadata": {},
 26 |    "source": [
 27 |     "## Option 1"
 28 |    ]
 29 |   },
 30 |   {
 31 |    "cell_type": "code",
 32 |    "execution_count": 3,
 33 |    "id": "93d02bc5",
 34 |    "metadata": {},
 35 |    "outputs": [],
 36 |    "source": [
 37 |     "# creating an array\n",
 38 |     "data = np.array([[1, 4], [2, 5], [3, 6]])"
 39 |    ]
 40 |   },
 41 |   {
 42 |    "cell_type": "code",
 43 |    "execution_count": 4,
 44 |    "id": "b9be7874",
 45 |    "metadata": {},
 46 |    "outputs": [],
 47 |    "source": [
 48 |     "# creating a dataframe\n",
 49 |     "df = pd.DataFrame(data, index=['row1', 'row2', 'row3'],\n",
 50 |     "                 columns=['col1', 'col2'])"
 51 |    ]
 52 |   },
 53 |   {
 54 |    "cell_type": "code",
 55 |    "execution_count": 5,
 56 |    "id": "7787533c",
 57 |    "metadata": {},
 58 |    "outputs": [
 59 |     {
 60 |      "data": {
 61 |       "text/html": [
 62 |        "<div>\n",
 63 |        "<style scoped>\n",
 64 |        "    .dataframe tbody tr th:only-of-type {\n",
 65 |        "        vertical-align: middle;\n",
 66 |        "    }\n",
 67 |        "\n",
 68 |        "    .dataframe tbody tr th {\n",
 69 |        "        vertical-align: top;\n",
 70 |        "    }\n",
 71 |        "\n",
 72 |        "    .dataframe thead th {\n",
 73 |        "        text-align: right;\n",
 74 |        "    }\n",
 75 |        "</style>\n",
 76 |        "<table border=\"1\" class=\"dataframe\">\n",
 77 |        "  <thead>\n",
 78 |        "    <tr style=\"text-align: right;\">\n",
 79 |        "      <th></th>\n",
 80 |        "      <th>col1</th>\n",
 81 |        "      <th>col2</th>\n",
 82 |        "    </tr>\n",
 83 |        "  </thead>\n",
 84 |        "  <tbody>\n",
 85 |        "    <tr>\n",
 86 |        "      <th>row1</th>\n",
 87 |        "      <td>1</td>\n",
 88 |        "      <td>4</td>\n",
 89 |        "    </tr>\n",
 90 |        "    <tr>\n",
 91 |        "      <th>row2</th>\n",
 92 |        "      <td>2</td>\n",
 93 |        "      <td>5</td>\n",
 94 |        "    </tr>\n",
 95 |        "    <tr>\n",
 96 |        "      <th>row3</th>\n",
 97 |        "      <td>3</td>\n",
 98 |        "      <td>6</td>\n",
 99 |        "    </tr>\n",
100 |        "  </tbody>\n",
101 |        "</table>\n",
102 |        "</div>"
103 |       ],
104 |       "text/plain": [
105 |        "      col1  col2\n",
106 |        "row1     1     4\n",
107 |        "row2     2     5\n",
108 |        "row3     3     6"
109 |       ]
110 |      },
111 |      "execution_count": 5,
112 |      "metadata": {},
113 |      "output_type": "execute_result"
114 |     }
115 |    ],
116 |    "source": [
117 |     "# showing the datafrane\n",
118 |     "df"
119 |    ]
120 |   },
121 |   {
122 |    "cell_type": "markdown",
123 |    "id": "9a66d12d",
124 |    "metadata": {},
125 |    "source": [
126 |     "## Option 2"
127 |    ]
128 |   },
129 |   {
130 |    "cell_type": "code",
131 |    "execution_count": 6,
132 |    "id": "39caa078",
133 |    "metadata": {},
134 |    "outputs": [],
135 |    "source": [
136 |     "# creating an array with list shape\n",
137 |     "data = [[1, 4], [2, 5], [3, 6]]"
138 |    ]
139 |   },
140 |   {
141 |    "cell_type": "code",
142 |    "execution_count": 7,
143 |    "id": "dfca7ffa",
144 |    "metadata": {},
145 |    "outputs": [],
146 |    "source": [
147 |     "# creating a dataframe\n",
148 |     "df = pd.DataFrame(data, index=['row1', 'row2', 'row3'],\n",
149 |     "                 columns=['col1', 'col2'])"
150 |    ]
151 |   },
152 |   {
153 |    "cell_type": "code",
154 |    "execution_count": 8,
155 |    "id": "7c057728",
156 |    "metadata": {},
157 |    "outputs": [
158 |     {
159 |      "data": {
160 |       "text/html": [
161 |        "<div>\n",
162 |        "<style scoped>\n",
163 |        "    .dataframe tbody tr th:only-of-type {\n",
164 |        "        vertical-align: middle;\n",
165 |        "    }\n",
166 |        "\n",
167 |        "    .dataframe tbody tr th {\n",
168 |        "        vertical-align: top;\n",
169 |        "    }\n",
170 |        "\n",
171 |        "    .dataframe thead th {\n",
172 |        "        text-align: right;\n",
173 |        "    }\n",
174 |        "</style>\n",
175 |        "<table border=\"1\" class=\"dataframe\">\n",
176 |        "  <thead>\n",
177 |        "    <tr style=\"text-align: right;\">\n",
178 |        "      <th></th>\n",
179 |        "      <th>col1</th>\n",
180 |        "      <th>col2</th>\n",
181 |        "    </tr>\n",
182 |        "  </thead>\n",
183 |        "  <tbody>\n",
184 |        "    <tr>\n",
185 |        "      <th>row1</th>\n",
186 |        "      <td>1</td>\n",
187 |        "      <td>4</td>\n",
188 |        "    </tr>\n",
189 |        "    <tr>\n",
190 |        "      <th>row2</th>\n",
191 |        "      <td>2</td>\n",
192 |        "      <td>5</td>\n",
193 |        "    </tr>\n",
194 |        "    <tr>\n",
195 |        "      <th>row3</th>\n",
196 |        "      <td>3</td>\n",
197 |        "      <td>6</td>\n",
198 |        "    </tr>\n",
199 |        "  </tbody>\n",
200 |        "</table>\n",
201 |        "</div>"
202 |       ],
203 |       "text/plain": [
204 |        "      col1  col2\n",
205 |        "row1     1     4\n",
206 |        "row2     2     5\n",
207 |        "row3     3     6"
208 |       ]
209 |      },
210 |      "execution_count": 8,
211 |      "metadata": {},
212 |      "output_type": "execute_result"
213 |     }
214 |    ],
215 |    "source": [
216 |     "# showing the datafrane\n",
217 |     "df"
218 |    ]
219 |   },
220 |   {
221 |    "cell_type": "markdown",
222 |    "id": "d7ee2ed9",
223 |    "metadata": {},
224 |    "source": [
225 |     "# Creating a DataFrame from a dictionary"
226 |    ]
227 |   },
228 |   {
229 |    "cell_type": "code",
230 |    "execution_count": 9,
231 |    "id": "63bf85b8",
232 |    "metadata": {},
233 |    "outputs": [],
234 |    "source": [
235 |     "# lists used for this example\n",
236 |     "states = [\"California\", \"Texas\", \"Florida\", \"New York\"]\n",
237 |     "population = [39613493, 29730311, 21944577, 19299981]"
238 |    ]
239 |   },
240 |   {
241 |    "cell_type": "code",
242 |    "execution_count": 10,
243 |    "id": "b309ebe8",
244 |    "metadata": {},
245 |    "outputs": [],
246 |    "source": [
247 |     "# Storing lists within a dictionary\n",
248 |     "dict_states = {'States': states, 'Population': population}"
249 |    ]
250 |   },
251 |   {
252 |    "cell_type": "code",
253 |    "execution_count": 11,
254 |    "id": "4e774499",
255 |    "metadata": {
256 |     "scrolled": false
257 |    },
258 |    "outputs": [],
259 |    "source": [
260 |     "# Creating the dataframe\n",
261 |     "df_population = pd.DataFrame(dict_states)\n",
262 |     "# df_population = pd.DataFrame.from_dict(dict_states)"
263 |    ]
264 |   },
265 |   {
266 |    "cell_type": "code",
267 |    "execution_count": 12,
268 |    "id": "585c7ff6",
269 |    "metadata": {},
270 |    "outputs": [
271 |     {
272 |      "data": {
273 |       "text/html": [
274 |        "<div>\n",
275 |        "<style scoped>\n",
276 |        "    .dataframe tbody tr th:only-of-type {\n",
277 |        "        vertical-align: middle;\n",
278 |        "    }\n",
279 |        "\n",
280 |        "    .dataframe tbody tr th {\n",
281 |        "        vertical-align: top;\n",
282 |        "    }\n",
283 |        "\n",
284 |        "    .dataframe thead th {\n",
285 |        "        text-align: right;\n",
286 |        "    }\n",
287 |        "</style>\n",
288 |        "<table border=\"1\" class=\"dataframe\">\n",
289 |        "  <thead>\n",
290 |        "    <tr style=\"text-align: right;\">\n",
291 |        "      <th></th>\n",
292 |        "      <th>States</th>\n",
293 |        "      <th>Population</th>\n",
294 |        "    </tr>\n",
295 |        "  </thead>\n",
296 |        "  <tbody>\n",
297 |        "    <tr>\n",
298 |        "      <th>0</th>\n",
299 |        "      <td>California</td>\n",
300 |        "      <td>39613493</td>\n",
301 |        "    </tr>\n",
302 |        "    <tr>\n",
303 |        "      <th>1</th>\n",
304 |        "      <td>Texas</td>\n",
305 |        "      <td>29730311</td>\n",
306 |        "    </tr>\n",
307 |        "    <tr>\n",
308 |        "      <th>2</th>\n",
309 |        "      <td>Florida</td>\n",
310 |        "      <td>21944577</td>\n",
311 |        "    </tr>\n",
312 |        "    <tr>\n",
313 |        "      <th>3</th>\n",
314 |        "      <td>New York</td>\n",
315 |        "      <td>19299981</td>\n",
316 |        "    </tr>\n",
317 |        "  </tbody>\n",
318 |        "</table>\n",
319 |        "</div>"
320 |       ],
321 |       "text/plain": [
322 |        "       States  Population\n",
323 |        "0  California    39613493\n",
324 |        "1       Texas    29730311\n",
325 |        "2     Florida    21944577\n",
326 |        "3    New York    19299981"
327 |       ]
328 |      },
329 |      "execution_count": 12,
330 |      "metadata": {},
331 |      "output_type": "execute_result"
332 |     }
333 |    ],
334 |    "source": [
335 |     "# showing the datafrane\n",
336 |     "df_population"
337 |    ]
338 |   },
339 |   {
340 |    "cell_type": "markdown",
341 |    "id": "245b58bf",
342 |    "metadata": {},
343 |    "source": [
344 |     "# Creating a DataFrame from a csv file"
345 |    ]
346 |   },
347 |   {
348 |    "cell_type": "code",
349 |    "execution_count": 13,
350 |    "id": "5a3dcc1e",
351 |    "metadata": {},
352 |    "outputs": [],
353 |    "source": [
354 |     "# reading the csv file\n",
355 |     "df_exams = pd.read_csv('StudentsPerformance.csv')"
356 |    ]
357 |   },
358 |   {
359 |    "cell_type": "code",
360 |    "execution_count": 14,
361 |    "id": "585ed37d",
362 |    "metadata": {},
363 |    "outputs": [
364 |     {
365 |      "data": {
366 |       "text/html": [
367 |        "<div>\n",
368 |        "<style scoped>\n",
369 |        "    .dataframe tbody tr th:only-of-type {\n",
370 |        "        vertical-align: middle;\n",
371 |        "    }\n",
372 |        "\n",
373 |        "    .dataframe tbody tr th {\n",
374 |        "        vertical-align: top;\n",
375 |        "    }\n",
376 |        "\n",
377 |        "    .dataframe thead th {\n",
378 |        "        text-align: right;\n",
379 |        "    }\n",
380 |        "</style>\n",
381 |        "<table border=\"1\" class=\"dataframe\">\n",
382 |        "  <thead>\n",
383 |        "    <tr style=\"text-align: right;\">\n",
384 |        "      <th></th>\n",
385 |        "      <th>gender</th>\n",
386 |        "      <th>race/ethnicity</th>\n",
387 |        "      <th>parental level of education</th>\n",
388 |        "      <th>lunch</th>\n",
389 |        "      <th>test preparation course</th>\n",
390 |        "      <th>math score</th>\n",
391 |        "      <th>reading score</th>\n",
392 |        "      <th>writing score</th>\n",
393 |        "    </tr>\n",
394 |        "  </thead>\n",
395 |        "  <tbody>\n",
396 |        "    <tr>\n",
397 |        "      <th>0</th>\n",
398 |        "      <td>female</td>\n",
399 |        "      <td>group B</td>\n",
400 |        "      <td>bachelor's degree</td>\n",
401 |        "      <td>standard</td>\n",
402 |        "      <td>none</td>\n",
403 |        "      <td>72</td>\n",
404 |        "      <td>72</td>\n",
405 |        "      <td>74</td>\n",
406 |        "    </tr>\n",
407 |        "    <tr>\n",
408 |        "      <th>1</th>\n",
409 |        "      <td>female</td>\n",
410 |        "      <td>group C</td>\n",
411 |        "      <td>some college</td>\n",
412 |        "      <td>standard</td>\n",
413 |        "      <td>completed</td>\n",
414 |        "      <td>69</td>\n",
415 |        "      <td>90</td>\n",
416 |        "      <td>88</td>\n",
417 |        "    </tr>\n",
418 |        "    <tr>\n",
419 |        "      <th>2</th>\n",
420 |        "      <td>female</td>\n",
421 |        "      <td>group B</td>\n",
422 |        "      <td>master's degree</td>\n",
423 |        "      <td>standard</td>\n",
424 |        "      <td>none</td>\n",
425 |        "      <td>90</td>\n",
426 |        "      <td>95</td>\n",
427 |        "      <td>93</td>\n",
428 |        "    </tr>\n",
429 |        "    <tr>\n",
430 |        "      <th>3</th>\n",
431 |        "      <td>male</td>\n",
432 |        "      <td>group A</td>\n",
433 |        "      <td>associate's degree</td>\n",
434 |        "      <td>free/reduced</td>\n",
435 |        "      <td>none</td>\n",
436 |        "      <td>47</td>\n",
437 |        "      <td>57</td>\n",
438 |        "      <td>44</td>\n",
439 |        "    </tr>\n",
440 |        "    <tr>\n",
441 |        "      <th>4</th>\n",
442 |        "      <td>male</td>\n",
443 |        "      <td>group C</td>\n",
444 |        "      <td>some college</td>\n",
445 |        "      <td>standard</td>\n",
446 |        "      <td>none</td>\n",
447 |        "      <td>76</td>\n",
448 |        "      <td>78</td>\n",
449 |        "      <td>75</td>\n",
450 |        "    </tr>\n",
451 |        "    <tr>\n",
452 |        "      <th>...</th>\n",
453 |        "      <td>...</td>\n",
454 |        "      <td>...</td>\n",
455 |        "      <td>...</td>\n",
456 |        "      <td>...</td>\n",
457 |        "      <td>...</td>\n",
458 |        "      <td>...</td>\n",
459 |        "      <td>...</td>\n",
460 |        "      <td>...</td>\n",
461 |        "    </tr>\n",
462 |        "    <tr>\n",
463 |        "      <th>995</th>\n",
464 |        "      <td>female</td>\n",
465 |        "      <td>group E</td>\n",
466 |        "      <td>master's degree</td>\n",
467 |        "      <td>standard</td>\n",
468 |        "      <td>completed</td>\n",
469 |        "      <td>88</td>\n",
470 |        "      <td>99</td>\n",
471 |        "      <td>95</td>\n",
472 |        "    </tr>\n",
473 |        "    <tr>\n",
474 |        "      <th>996</th>\n",
475 |        "      <td>male</td>\n",
476 |        "      <td>group C</td>\n",
477 |        "      <td>high school</td>\n",
478 |        "      <td>free/reduced</td>\n",
479 |        "      <td>none</td>\n",
480 |        "      <td>62</td>\n",
481 |        "      <td>55</td>\n",
482 |        "      <td>55</td>\n",
483 |        "    </tr>\n",
484 |        "    <tr>\n",
485 |        "      <th>997</th>\n",
486 |        "      <td>female</td>\n",
487 |        "      <td>group C</td>\n",
488 |        "      <td>high school</td>\n",
489 |        "      <td>free/reduced</td>\n",
490 |        "      <td>completed</td>\n",
491 |        "      <td>59</td>\n",
492 |        "      <td>71</td>\n",
493 |        "      <td>65</td>\n",
494 |        "    </tr>\n",
495 |        "    <tr>\n",
496 |        "      <th>998</th>\n",
497 |        "      <td>female</td>\n",
498 |        "      <td>group D</td>\n",
499 |        "      <td>some college</td>\n",
500 |        "      <td>standard</td>\n",
501 |        "      <td>completed</td>\n",
502 |        "      <td>68</td>\n",
503 |        "      <td>78</td>\n",
504 |        "      <td>77</td>\n",
505 |        "    </tr>\n",
506 |        "    <tr>\n",
507 |        "      <th>999</th>\n",
508 |        "      <td>female</td>\n",
509 |        "      <td>group D</td>\n",
510 |        "      <td>some college</td>\n",
511 |        "      <td>free/reduced</td>\n",
512 |        "      <td>none</td>\n",
513 |        "      <td>77</td>\n",
514 |        "      <td>86</td>\n",
515 |        "      <td>86</td>\n",
516 |        "    </tr>\n",
517 |        "  </tbody>\n",
518 |        "</table>\n",
519 |        "<p>1000 rows × 8 columns</p>\n",
520 |        "</div>"
521 |       ],
522 |       "text/plain": [
523 |        "     gender race/ethnicity parental level of education         lunch  \\\n",
524 |        "0    female        group B           bachelor's degree      standard   \n",
525 |        "1    female        group C                some college      standard   \n",
526 |        "2    female        group B             master's degree      standard   \n",
527 |        "3      male        group A          associate's degree  free/reduced   \n",
528 |        "4      male        group C                some college      standard   \n",
529 |        "..      ...            ...                         ...           ...   \n",
530 |        "995  female        group E             master's degree      standard   \n",
531 |        "996    male        group C                 high school  free/reduced   \n",
532 |        "997  female        group C                 high school  free/reduced   \n",
533 |        "998  female        group D                some college      standard   \n",
534 |        "999  female        group D                some college  free/reduced   \n",
535 |        "\n",
536 |        "    test preparation course  math score  reading score  writing score  \n",
537 |        "0                      none          72             72             74  \n",
538 |        "1                 completed          69             90             88  \n",
539 |        "2                      none          90             95             93  \n",
540 |        "3                      none          47             57             44  \n",
541 |        "4                      none          76             78             75  \n",
542 |        "..                      ...         ...            ...            ...  \n",
543 |        "995               completed          88             99             95  \n",
544 |        "996                    none          62             55             55  \n",
545 |        "997               completed          59             71             65  \n",
546 |        "998               completed          68             78             77  \n",
547 |        "999                    none          77             86             86  \n",
548 |        "\n",
549 |        "[1000 rows x 8 columns]"
550 |       ]
551 |      },
552 |      "execution_count": 14,
553 |      "metadata": {},
554 |      "output_type": "execute_result"
555 |     }
556 |    ],
557 |    "source": [
558 |     "# show first 5 rows in a dataframe\n",
559 |     "df_exams"
560 |    ]
561 |   }
562 |  ],
563 |  "metadata": {
564 |   "kernelspec": {
565 |    "display_name": "Python 3",
566 |    "language": "python",
567 |    "name": "python3"
568 |   },
569 |   "language_info": {
570 |    "codemirror_mode": {
571 |     "name": "ipython",
572 |     "version": 3
573 |    },
574 |    "file_extension": ".py",
575 |    "mimetype": "text/x-python",
576 |    "name": "python",
577 |    "nbconvert_exporter": "python",
578 |    "pygments_lexer": "ipython3",
579 |    "version": "3.8.8"
580 |   },
581 |   "toc": {
582 |    "base_numbering": 1,
583 |    "nav_menu": {},
584 |    "number_sections": true,
585 |    "sideBar": true,
586 |    "skip_h1_title": false,
587 |    "title_cell": "Table of Contents",
588 |    "title_sidebar": "Contents",
589 |    "toc_cell": false,
590 |    "toc_position": {},
591 |    "toc_section_display": true,
592 |    "toc_window_display": false
593 |   }
594 |  },
595 |  "nbformat": 4,
596 |  "nbformat_minor": 5
597 | }
598 | 


--------------------------------------------------------------------------------
/2.Intro to Pandas/3. Basic Attributes, Methods and Functions.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 1,
  6 |    "id": "3cadeaac",
  7 |    "metadata": {},
  8 |    "outputs": [],
  9 |    "source": [
 10 |     "import pandas as pd"
 11 |    ]
 12 |   },
 13 |   {
 14 |    "cell_type": "code",
 15 |    "execution_count": 2,
 16 |    "id": "faf4a761",
 17 |    "metadata": {},
 18 |    "outputs": [],
 19 |    "source": [
 20 |     "# reading the csv file\n",
 21 |     "df_exams = pd.read_csv('StudentsPerformance.csv')"
 22 |    ]
 23 |   },
 24 |   {
 25 |    "cell_type": "code",
 26 |    "execution_count": 5,
 27 |    "id": "e6159fe8",
 28 |    "metadata": {},
 29 |    "outputs": [
 30 |     {
 31 |      "data": {
 32 |       "text/html": [
 33 |        "<div>\n",
 34 |        "<style scoped>\n",
 35 |        "    .dataframe tbody tr th:only-of-type {\n",
 36 |        "        vertical-align: middle;\n",
 37 |        "    }\n",
 38 |        "\n",
 39 |        "    .dataframe tbody tr th {\n",
 40 |        "        vertical-align: top;\n",
 41 |        "    }\n",
 42 |        "\n",
 43 |        "    .dataframe thead th {\n",
 44 |        "        text-align: right;\n",
 45 |        "    }\n",
 46 |        "</style>\n",
 47 |        "<table border=\"1\" class=\"dataframe\">\n",
 48 |        "  <thead>\n",
 49 |        "    <tr style=\"text-align: right;\">\n",
 50 |        "      <th></th>\n",
 51 |        "      <th>gender</th>\n",
 52 |        "      <th>race/ethnicity</th>\n",
 53 |        "      <th>parental level of education</th>\n",
 54 |        "      <th>lunch</th>\n",
 55 |        "      <th>test preparation course</th>\n",
 56 |        "      <th>math score</th>\n",
 57 |        "      <th>reading score</th>\n",
 58 |        "      <th>writing score</th>\n",
 59 |        "    </tr>\n",
 60 |        "  </thead>\n",
 61 |        "  <tbody>\n",
 62 |        "    <tr>\n",
 63 |        "      <th>0</th>\n",
 64 |        "      <td>female</td>\n",
 65 |        "      <td>group B</td>\n",
 66 |        "      <td>bachelor's degree</td>\n",
 67 |        "      <td>standard</td>\n",
 68 |        "      <td>none</td>\n",
 69 |        "      <td>72</td>\n",
 70 |        "      <td>72</td>\n",
 71 |        "      <td>74</td>\n",
 72 |        "    </tr>\n",
 73 |        "    <tr>\n",
 74 |        "      <th>1</th>\n",
 75 |        "      <td>female</td>\n",
 76 |        "      <td>group C</td>\n",
 77 |        "      <td>some college</td>\n",
 78 |        "      <td>standard</td>\n",
 79 |        "      <td>completed</td>\n",
 80 |        "      <td>69</td>\n",
 81 |        "      <td>90</td>\n",
 82 |        "      <td>88</td>\n",
 83 |        "    </tr>\n",
 84 |        "    <tr>\n",
 85 |        "      <th>2</th>\n",
 86 |        "      <td>female</td>\n",
 87 |        "      <td>group B</td>\n",
 88 |        "      <td>master's degree</td>\n",
 89 |        "      <td>standard</td>\n",
 90 |        "      <td>none</td>\n",
 91 |        "      <td>90</td>\n",
 92 |        "      <td>95</td>\n",
 93 |        "      <td>93</td>\n",
 94 |        "    </tr>\n",
 95 |        "    <tr>\n",
 96 |        "      <th>3</th>\n",
 97 |        "      <td>male</td>\n",
 98 |        "      <td>group A</td>\n",
 99 |        "      <td>associate's degree</td>\n",
100 |        "      <td>free/reduced</td>\n",
101 |        "      <td>none</td>\n",
102 |        "      <td>47</td>\n",
103 |        "      <td>57</td>\n",
104 |        "      <td>44</td>\n",
105 |        "    </tr>\n",
106 |        "    <tr>\n",
107 |        "      <th>4</th>\n",
108 |        "      <td>male</td>\n",
109 |        "      <td>group C</td>\n",
110 |        "      <td>some college</td>\n",
111 |        "      <td>standard</td>\n",
112 |        "      <td>none</td>\n",
113 |        "      <td>76</td>\n",
114 |        "      <td>78</td>\n",
115 |        "      <td>75</td>\n",
116 |        "    </tr>\n",
117 |        "    <tr>\n",
118 |        "      <th>...</th>\n",
119 |        "      <td>...</td>\n",
120 |        "      <td>...</td>\n",
121 |        "      <td>...</td>\n",
122 |        "      <td>...</td>\n",
123 |        "      <td>...</td>\n",
124 |        "      <td>...</td>\n",
125 |        "      <td>...</td>\n",
126 |        "      <td>...</td>\n",
127 |        "    </tr>\n",
128 |        "    <tr>\n",
129 |        "      <th>995</th>\n",
130 |        "      <td>female</td>\n",
131 |        "      <td>group E</td>\n",
132 |        "      <td>master's degree</td>\n",
133 |        "      <td>standard</td>\n",
134 |        "      <td>completed</td>\n",
135 |        "      <td>88</td>\n",
136 |        "      <td>99</td>\n",
137 |        "      <td>95</td>\n",
138 |        "    </tr>\n",
139 |        "    <tr>\n",
140 |        "      <th>996</th>\n",
141 |        "      <td>male</td>\n",
142 |        "      <td>group C</td>\n",
143 |        "      <td>high school</td>\n",
144 |        "      <td>free/reduced</td>\n",
145 |        "      <td>none</td>\n",
146 |        "      <td>62</td>\n",
147 |        "      <td>55</td>\n",
148 |        "      <td>55</td>\n",
149 |        "    </tr>\n",
150 |        "    <tr>\n",
151 |        "      <th>997</th>\n",
152 |        "      <td>female</td>\n",
153 |        "      <td>group C</td>\n",
154 |        "      <td>high school</td>\n",
155 |        "      <td>free/reduced</td>\n",
156 |        "      <td>completed</td>\n",
157 |        "      <td>59</td>\n",
158 |        "      <td>71</td>\n",
159 |        "      <td>65</td>\n",
160 |        "    </tr>\n",
161 |        "    <tr>\n",
162 |        "      <th>998</th>\n",
163 |        "      <td>female</td>\n",
164 |        "      <td>group D</td>\n",
165 |        "      <td>some college</td>\n",
166 |        "      <td>standard</td>\n",
167 |        "      <td>completed</td>\n",
168 |        "      <td>68</td>\n",
169 |        "      <td>78</td>\n",
170 |        "      <td>77</td>\n",
171 |        "    </tr>\n",
172 |        "    <tr>\n",
173 |        "      <th>999</th>\n",
174 |        "      <td>female</td>\n",
175 |        "      <td>group D</td>\n",
176 |        "      <td>some college</td>\n",
177 |        "      <td>free/reduced</td>\n",
178 |        "      <td>none</td>\n",
179 |        "      <td>77</td>\n",
180 |        "      <td>86</td>\n",
181 |        "      <td>86</td>\n",
182 |        "    </tr>\n",
183 |        "  </tbody>\n",
184 |        "</table>\n",
185 |        "<p>1000 rows × 8 columns</p>\n",
186 |        "</div>"
187 |       ],
188 |       "text/plain": [
189 |        "     gender race/ethnicity parental level of education         lunch  \\\n",
190 |        "0    female        group B           bachelor's degree      standard   \n",
191 |        "1    female        group C                some college      standard   \n",
192 |        "2    female        group B             master's degree      standard   \n",
193 |        "3      male        group A          associate's degree  free/reduced   \n",
194 |        "4      male        group C                some college      standard   \n",
195 |        "..      ...            ...                         ...           ...   \n",
196 |        "995  female        group E             master's degree      standard   \n",
197 |        "996    male        group C                 high school  free/reduced   \n",
198 |        "997  female        group C                 high school  free/reduced   \n",
199 |        "998  female        group D                some college      standard   \n",
200 |        "999  female        group D                some college  free/reduced   \n",
201 |        "\n",
202 |        "    test preparation course  math score  reading score  writing score  \n",
203 |        "0                      none          72             72             74  \n",
204 |        "1                 completed          69             90             88  \n",
205 |        "2                      none          90             95             93  \n",
206 |        "3                      none          47             57             44  \n",
207 |        "4                      none          76             78             75  \n",
208 |        "..                      ...         ...            ...            ...  \n",
209 |        "995               completed          88             99             95  \n",
210 |        "996                    none          62             55             55  \n",
211 |        "997               completed          59             71             65  \n",
212 |        "998               completed          68             78             77  \n",
213 |        "999                    none          77             86             86  \n",
214 |        "\n",
215 |        "[1000 rows x 8 columns]"
216 |       ]
217 |      },
218 |      "execution_count": 5,
219 |      "metadata": {},
220 |      "output_type": "execute_result"
221 |     }
222 |    ],
223 |    "source": [
224 |     "# showing the dataframe\n",
225 |     "df_exams"
226 |    ]
227 |   },
228 |   {
229 |    "cell_type": "markdown",
230 |    "id": "63bf386f",
231 |    "metadata": {},
232 |    "source": [
233 |     "# Attributes"
234 |    ]
235 |   },
236 |   {
237 |    "cell_type": "code",
238 |    "execution_count": 6,
239 |    "id": "8889cc6c",
240 |    "metadata": {},
241 |    "outputs": [
242 |     {
243 |      "data": {
244 |       "text/plain": [
245 |        "(1000, 8)"
246 |       ]
247 |      },
248 |      "execution_count": 6,
249 |      "metadata": {},
250 |      "output_type": "execute_result"
251 |     }
252 |    ],
253 |    "source": [
254 |     "# getting access to the shape attribute\n",
255 |     "df_exams.shape"
256 |    ]
257 |   },
258 |   {
259 |    "cell_type": "code",
260 |    "execution_count": 8,
261 |    "id": "c1d18854",
262 |    "metadata": {},
263 |    "outputs": [
264 |     {
265 |      "data": {
266 |       "text/plain": [
267 |        "RangeIndex(start=0, stop=1000, step=1)"
268 |       ]
269 |      },
270 |      "execution_count": 8,
271 |      "metadata": {},
272 |      "output_type": "execute_result"
273 |     }
274 |    ],
275 |    "source": [
276 |     "# getting access to the index attribute\n",
277 |     "df_exams.index"
278 |    ]
279 |   },
280 |   {
281 |    "cell_type": "code",
282 |    "execution_count": 9,
283 |    "id": "002ebb03",
284 |    "metadata": {},
285 |    "outputs": [
286 |     {
287 |      "data": {
288 |       "text/plain": [
289 |        "Index(['gender', 'race/ethnicity', 'parental level of education', 'lunch',\n",
290 |        "       'test preparation course', 'math score', 'reading score',\n",
291 |        "       'writing score'],\n",
292 |        "      dtype='object')"
293 |       ]
294 |      },
295 |      "execution_count": 9,
296 |      "metadata": {},
297 |      "output_type": "execute_result"
298 |     }
299 |    ],
300 |    "source": [
301 |     "# getting access to the column attribute\n",
302 |     "df_exams.columns"
303 |    ]
304 |   },
305 |   {
306 |    "cell_type": "code",
307 |    "execution_count": 12,
308 |    "id": "1928828c",
309 |    "metadata": {},
310 |    "outputs": [
311 |     {
312 |      "data": {
313 |       "text/plain": [
314 |        "gender                         object\n",
315 |        "race/ethnicity                 object\n",
316 |        "parental level of education    object\n",
317 |        "lunch                          object\n",
318 |        "test preparation course        object\n",
319 |        "math score                      int64\n",
320 |        "reading score                   int64\n",
321 |        "writing score                   int64\n",
322 |        "dtype: object"
323 |       ]
324 |      },
325 |      "execution_count": 12,
326 |      "metadata": {},
327 |      "output_type": "execute_result"
328 |     }
329 |    ],
330 |    "source": [
331 |     "# data types of each column\n",
332 |     "df_exams.dtypes"
333 |    ]
334 |   },
335 |   {
336 |    "cell_type": "markdown",
337 |    "id": "3ee3d60a",
338 |    "metadata": {},
339 |    "source": [
340 |     "# Methods"
341 |    ]
342 |   },
343 |   {
344 |    "cell_type": "code",
345 |    "execution_count": 10,
346 |    "id": "d6ff61f9",
347 |    "metadata": {},
348 |    "outputs": [
349 |     {
350 |      "data": {
351 |       "text/html": [
352 |        "<div>\n",
353 |        "<style scoped>\n",
354 |        "    .dataframe tbody tr th:only-of-type {\n",
355 |        "        vertical-align: middle;\n",
356 |        "    }\n",
357 |        "\n",
358 |        "    .dataframe tbody tr th {\n",
359 |        "        vertical-align: top;\n",
360 |        "    }\n",
361 |        "\n",
362 |        "    .dataframe thead th {\n",
363 |        "        text-align: right;\n",
364 |        "    }\n",
365 |        "</style>\n",
366 |        "<table border=\"1\" class=\"dataframe\">\n",
367 |        "  <thead>\n",
368 |        "    <tr style=\"text-align: right;\">\n",
369 |        "      <th></th>\n",
370 |        "      <th>gender</th>\n",
371 |        "      <th>race/ethnicity</th>\n",
372 |        "      <th>parental level of education</th>\n",
373 |        "      <th>lunch</th>\n",
374 |        "      <th>test preparation course</th>\n",
375 |        "      <th>math score</th>\n",
376 |        "      <th>reading score</th>\n",
377 |        "      <th>writing score</th>\n",
378 |        "    </tr>\n",
379 |        "  </thead>\n",
380 |        "  <tbody>\n",
381 |        "    <tr>\n",
382 |        "      <th>0</th>\n",
383 |        "      <td>female</td>\n",
384 |        "      <td>group B</td>\n",
385 |        "      <td>bachelor's degree</td>\n",
386 |        "      <td>standard</td>\n",
387 |        "      <td>none</td>\n",
388 |        "      <td>72</td>\n",
389 |        "      <td>72</td>\n",
390 |        "      <td>74</td>\n",
391 |        "    </tr>\n",
392 |        "    <tr>\n",
393 |        "      <th>1</th>\n",
394 |        "      <td>female</td>\n",
395 |        "      <td>group C</td>\n",
396 |        "      <td>some college</td>\n",
397 |        "      <td>standard</td>\n",
398 |        "      <td>completed</td>\n",
399 |        "      <td>69</td>\n",
400 |        "      <td>90</td>\n",
401 |        "      <td>88</td>\n",
402 |        "    </tr>\n",
403 |        "    <tr>\n",
404 |        "      <th>2</th>\n",
405 |        "      <td>female</td>\n",
406 |        "      <td>group B</td>\n",
407 |        "      <td>master's degree</td>\n",
408 |        "      <td>standard</td>\n",
409 |        "      <td>none</td>\n",
410 |        "      <td>90</td>\n",
411 |        "      <td>95</td>\n",
412 |        "      <td>93</td>\n",
413 |        "    </tr>\n",
414 |        "    <tr>\n",
415 |        "      <th>3</th>\n",
416 |        "      <td>male</td>\n",
417 |        "      <td>group A</td>\n",
418 |        "      <td>associate's degree</td>\n",
419 |        "      <td>free/reduced</td>\n",
420 |        "      <td>none</td>\n",
421 |        "      <td>47</td>\n",
422 |        "      <td>57</td>\n",
423 |        "      <td>44</td>\n",
424 |        "    </tr>\n",
425 |        "    <tr>\n",
426 |        "      <th>4</th>\n",
427 |        "      <td>male</td>\n",
428 |        "      <td>group C</td>\n",
429 |        "      <td>some college</td>\n",
430 |        "      <td>standard</td>\n",
431 |        "      <td>none</td>\n",
432 |        "      <td>76</td>\n",
433 |        "      <td>78</td>\n",
434 |        "      <td>75</td>\n",
435 |        "    </tr>\n",
436 |        "  </tbody>\n",
437 |        "</table>\n",
438 |        "</div>"
439 |       ],
440 |       "text/plain": [
441 |        "   gender race/ethnicity parental level of education         lunch  \\\n",
442 |        "0  female        group B           bachelor's degree      standard   \n",
443 |        "1  female        group C                some college      standard   \n",
444 |        "2  female        group B             master's degree      standard   \n",
445 |        "3    male        group A          associate's degree  free/reduced   \n",
446 |        "4    male        group C                some college      standard   \n",
447 |        "\n",
448 |        "  test preparation course  math score  reading score  writing score  \n",
449 |        "0                    none          72             72             74  \n",
450 |        "1               completed          69             90             88  \n",
451 |        "2                    none          90             95             93  \n",
452 |        "3                    none          47             57             44  \n",
453 |        "4                    none          76             78             75  "
454 |       ]
455 |      },
456 |      "execution_count": 10,
457 |      "metadata": {},
458 |      "output_type": "execute_result"
459 |     }
460 |    ],
461 |    "source": [
462 |     "# showing the first 5 columns\n",
463 |     "df_exams.head()"
464 |    ]
465 |   },
466 |   {
467 |    "cell_type": "code",
468 |    "execution_count": 15,
469 |    "id": "7852fee9",
470 |    "metadata": {},
471 |    "outputs": [
472 |     {
473 |      "name": "stdout",
474 |      "output_type": "stream",
475 |      "text": [
476 |       "<class 'pandas.core.frame.DataFrame'>\n",
477 |       "RangeIndex: 1000 entries, 0 to 999\n",
478 |       "Data columns (total 8 columns):\n",
479 |       " #   Column                       Non-Null Count  Dtype \n",
480 |       "---  ------                       --------------  ----- \n",
481 |       " 0   gender                       1000 non-null   object\n",
482 |       " 1   race/ethnicity               1000 non-null   object\n",
483 |       " 2   parental level of education  1000 non-null   object\n",
484 |       " 3   lunch                        1000 non-null   object\n",
485 |       " 4   test preparation course      1000 non-null   object\n",
486 |       " 5   math score                   1000 non-null   int64 \n",
487 |       " 6   reading score                1000 non-null   int64 \n",
488 |       " 7   writing score                1000 non-null   int64 \n",
489 |       "dtypes: int64(3), object(5)\n",
490 |       "memory usage: 62.6+ KB\n"
491 |      ]
492 |     }
493 |    ],
494 |    "source": [
495 |     "# showing the info of the dataframe\n",
496 |     "df_exams.info()"
497 |    ]
498 |   },
499 |   {
500 |    "cell_type": "code",
501 |    "execution_count": 16,
502 |    "id": "7e44a628",
503 |    "metadata": {},
504 |    "outputs": [
505 |     {
506 |      "data": {
507 |       "text/html": [
508 |        "<div>\n",
509 |        "<style scoped>\n",
510 |        "    .dataframe tbody tr th:only-of-type {\n",
511 |        "        vertical-align: middle;\n",
512 |        "    }\n",
513 |        "\n",
514 |        "    .dataframe tbody tr th {\n",
515 |        "        vertical-align: top;\n",
516 |        "    }\n",
517 |        "\n",
518 |        "    .dataframe thead th {\n",
519 |        "        text-align: right;\n",
520 |        "    }\n",
521 |        "</style>\n",
522 |        "<table border=\"1\" class=\"dataframe\">\n",
523 |        "  <thead>\n",
524 |        "    <tr style=\"text-align: right;\">\n",
525 |        "      <th></th>\n",
526 |        "      <th>math score</th>\n",
527 |        "      <th>reading score</th>\n",
528 |        "      <th>writing score</th>\n",
529 |        "    </tr>\n",
530 |        "  </thead>\n",
531 |        "  <tbody>\n",
532 |        "    <tr>\n",
533 |        "      <th>count</th>\n",
534 |        "      <td>1000.00000</td>\n",
535 |        "      <td>1000.000000</td>\n",
536 |        "      <td>1000.000000</td>\n",
537 |        "    </tr>\n",
538 |        "    <tr>\n",
539 |        "      <th>mean</th>\n",
540 |        "      <td>66.08900</td>\n",
541 |        "      <td>69.169000</td>\n",
542 |        "      <td>68.054000</td>\n",
543 |        "    </tr>\n",
544 |        "    <tr>\n",
545 |        "      <th>std</th>\n",
546 |        "      <td>15.16308</td>\n",
547 |        "      <td>14.600192</td>\n",
548 |        "      <td>15.195657</td>\n",
549 |        "    </tr>\n",
550 |        "    <tr>\n",
551 |        "      <th>min</th>\n",
552 |        "      <td>0.00000</td>\n",
553 |        "      <td>17.000000</td>\n",
554 |        "      <td>10.000000</td>\n",
555 |        "    </tr>\n",
556 |        "    <tr>\n",
557 |        "      <th>25%</th>\n",
558 |        "      <td>57.00000</td>\n",
559 |        "      <td>59.000000</td>\n",
560 |        "      <td>57.750000</td>\n",
561 |        "    </tr>\n",
562 |        "    <tr>\n",
563 |        "      <th>50%</th>\n",
564 |        "      <td>66.00000</td>\n",
565 |        "      <td>70.000000</td>\n",
566 |        "      <td>69.000000</td>\n",
567 |        "    </tr>\n",
568 |        "    <tr>\n",
569 |        "      <th>75%</th>\n",
570 |        "      <td>77.00000</td>\n",
571 |        "      <td>79.000000</td>\n",
572 |        "      <td>79.000000</td>\n",
573 |        "    </tr>\n",
574 |        "    <tr>\n",
575 |        "      <th>max</th>\n",
576 |        "      <td>100.00000</td>\n",
577 |        "      <td>100.000000</td>\n",
578 |        "      <td>100.000000</td>\n",
579 |        "    </tr>\n",
580 |        "  </tbody>\n",
581 |        "</table>\n",
582 |        "</div>"
583 |       ],
584 |       "text/plain": [
585 |        "       math score  reading score  writing score\n",
586 |        "count  1000.00000    1000.000000    1000.000000\n",
587 |        "mean     66.08900      69.169000      68.054000\n",
588 |        "std      15.16308      14.600192      15.195657\n",
589 |        "min       0.00000      17.000000      10.000000\n",
590 |        "25%      57.00000      59.000000      57.750000\n",
591 |        "50%      66.00000      70.000000      69.000000\n",
592 |        "75%      77.00000      79.000000      79.000000\n",
593 |        "max     100.00000     100.000000     100.000000"
594 |       ]
595 |      },
596 |      "execution_count": 16,
597 |      "metadata": {},
598 |      "output_type": "execute_result"
599 |     }
600 |    ],
601 |    "source": [
602 |     "# describing basic statistics of the dataframe\n",
603 |     "df_exams.describe()"
604 |    ]
605 |   },
606 |   {
607 |    "cell_type": "markdown",
608 |    "id": "22a32e4e",
609 |    "metadata": {},
610 |    "source": [
611 |     "# Functions"
612 |    ]
613 |   },
614 |   {
615 |    "cell_type": "code",
616 |    "execution_count": 17,
617 |    "id": "a71af478",
618 |    "metadata": {},
619 |    "outputs": [
620 |     {
621 |      "data": {
622 |       "text/plain": [
623 |        "1000"
624 |       ]
625 |      },
626 |      "execution_count": 17,
627 |      "metadata": {},
628 |      "output_type": "execute_result"
629 |     }
630 |    ],
631 |    "source": [
632 |     "# obtaining the length of the dataframe (number of rows)\n",
633 |     "len(df_exams)"
634 |    ]
635 |   },
636 |   {
637 |    "cell_type": "code",
638 |    "execution_count": 22,
639 |    "id": "595fcbde",
640 |    "metadata": {
641 |     "scrolled": true
642 |    },
643 |    "outputs": [
644 |     {
645 |      "data": {
646 |       "text/plain": [
647 |        "999"
648 |       ]
649 |      },
650 |      "execution_count": 22,
651 |      "metadata": {},
652 |      "output_type": "execute_result"
653 |     }
654 |    ],
655 |    "source": [
656 |     "# obtaining the highest index of the dataframe\n",
657 |     "max(df_exams.index)"
658 |    ]
659 |   },
660 |   {
661 |    "cell_type": "code",
662 |    "execution_count": 26,
663 |    "id": "7aba282f",
664 |    "metadata": {},
665 |    "outputs": [
666 |     {
667 |      "data": {
668 |       "text/plain": [
669 |        "0"
670 |       ]
671 |      },
672 |      "execution_count": 26,
673 |      "metadata": {},
674 |      "output_type": "execute_result"
675 |     }
676 |    ],
677 |    "source": [
678 |     "# obtaining the lowest index of the dataframe\n",
679 |     "min(df_exams.index)"
680 |    ]
681 |   },
682 |   {
683 |    "cell_type": "code",
684 |    "execution_count": 27,
685 |    "id": "8ce53edc",
686 |    "metadata": {},
687 |    "outputs": [
688 |     {
689 |      "data": {
690 |       "text/plain": [
691 |        "pandas.core.frame.DataFrame"
692 |       ]
693 |      },
694 |      "execution_count": 27,
695 |      "metadata": {},
696 |      "output_type": "execute_result"
697 |     }
698 |    ],
699 |    "source": [
700 |     "# obtaining the data type\n",
701 |     "type(df_exams)"
702 |    ]
703 |   },
704 |   {
705 |    "cell_type": "code",
706 |    "execution_count": 28,
707 |    "id": "224775a3",
708 |    "metadata": {},
709 |    "outputs": [
710 |     {
711 |      "data": {
712 |       "text/html": [
713 |        "<div>\n",
714 |        "<style scoped>\n",
715 |        "    .dataframe tbody tr th:only-of-type {\n",
716 |        "        vertical-align: middle;\n",
717 |        "    }\n",
718 |        "\n",
719 |        "    .dataframe tbody tr th {\n",
720 |        "        vertical-align: top;\n",
721 |        "    }\n",
722 |        "\n",
723 |        "    .dataframe thead th {\n",
724 |        "        text-align: right;\n",
725 |        "    }\n",
726 |        "</style>\n",
727 |        "<table border=\"1\" class=\"dataframe\">\n",
728 |        "  <thead>\n",
729 |        "    <tr style=\"text-align: right;\">\n",
730 |        "      <th></th>\n",
731 |        "      <th>gender</th>\n",
732 |        "      <th>race/ethnicity</th>\n",
733 |        "      <th>parental level of education</th>\n",
734 |        "      <th>lunch</th>\n",
735 |        "      <th>test preparation course</th>\n",
736 |        "      <th>math score</th>\n",
737 |        "      <th>reading score</th>\n",
738 |        "      <th>writing score</th>\n",
739 |        "    </tr>\n",
740 |        "  </thead>\n",
741 |        "  <tbody>\n",
742 |        "    <tr>\n",
743 |        "      <th>0</th>\n",
744 |        "      <td>female</td>\n",
745 |        "      <td>group B</td>\n",
746 |        "      <td>bachelor's degree</td>\n",
747 |        "      <td>standard</td>\n",
748 |        "      <td>none</td>\n",
749 |        "      <td>72</td>\n",
750 |        "      <td>72</td>\n",
751 |        "      <td>74</td>\n",
752 |        "    </tr>\n",
753 |        "    <tr>\n",
754 |        "      <th>1</th>\n",
755 |        "      <td>female</td>\n",
756 |        "      <td>group C</td>\n",
757 |        "      <td>some college</td>\n",
758 |        "      <td>standard</td>\n",
759 |        "      <td>completed</td>\n",
760 |        "      <td>69</td>\n",
761 |        "      <td>90</td>\n",
762 |        "      <td>88</td>\n",
763 |        "    </tr>\n",
764 |        "    <tr>\n",
765 |        "      <th>2</th>\n",
766 |        "      <td>female</td>\n",
767 |        "      <td>group B</td>\n",
768 |        "      <td>master's degree</td>\n",
769 |        "      <td>standard</td>\n",
770 |        "      <td>none</td>\n",
771 |        "      <td>90</td>\n",
772 |        "      <td>95</td>\n",
773 |        "      <td>93</td>\n",
774 |        "    </tr>\n",
775 |        "    <tr>\n",
776 |        "      <th>3</th>\n",
777 |        "      <td>male</td>\n",
778 |        "      <td>group A</td>\n",
779 |        "      <td>associate's degree</td>\n",
780 |        "      <td>free/reduced</td>\n",
781 |        "      <td>none</td>\n",
782 |        "      <td>47</td>\n",
783 |        "      <td>57</td>\n",
784 |        "      <td>44</td>\n",
785 |        "    </tr>\n",
786 |        "    <tr>\n",
787 |        "      <th>4</th>\n",
788 |        "      <td>male</td>\n",
789 |        "      <td>group C</td>\n",
790 |        "      <td>some college</td>\n",
791 |        "      <td>standard</td>\n",
792 |        "      <td>none</td>\n",
793 |        "      <td>76</td>\n",
794 |        "      <td>78</td>\n",
795 |        "      <td>75</td>\n",
796 |        "    </tr>\n",
797 |        "    <tr>\n",
798 |        "      <th>...</th>\n",
799 |        "      <td>...</td>\n",
800 |        "      <td>...</td>\n",
801 |        "      <td>...</td>\n",
802 |        "      <td>...</td>\n",
803 |        "      <td>...</td>\n",
804 |        "      <td>...</td>\n",
805 |        "      <td>...</td>\n",
806 |        "      <td>...</td>\n",
807 |        "    </tr>\n",
808 |        "    <tr>\n",
809 |        "      <th>995</th>\n",
810 |        "      <td>female</td>\n",
811 |        "      <td>group E</td>\n",
812 |        "      <td>master's degree</td>\n",
813 |        "      <td>standard</td>\n",
814 |        "      <td>completed</td>\n",
815 |        "      <td>88</td>\n",
816 |        "      <td>99</td>\n",
817 |        "      <td>95</td>\n",
818 |        "    </tr>\n",
819 |        "    <tr>\n",
820 |        "      <th>996</th>\n",
821 |        "      <td>male</td>\n",
822 |        "      <td>group C</td>\n",
823 |        "      <td>high school</td>\n",
824 |        "      <td>free/reduced</td>\n",
825 |        "      <td>none</td>\n",
826 |        "      <td>62</td>\n",
827 |        "      <td>55</td>\n",
828 |        "      <td>55</td>\n",
829 |        "    </tr>\n",
830 |        "    <tr>\n",
831 |        "      <th>997</th>\n",
832 |        "      <td>female</td>\n",
833 |        "      <td>group C</td>\n",
834 |        "      <td>high school</td>\n",
835 |        "      <td>free/reduced</td>\n",
836 |        "      <td>completed</td>\n",
837 |        "      <td>59</td>\n",
838 |        "      <td>71</td>\n",
839 |        "      <td>65</td>\n",
840 |        "    </tr>\n",
841 |        "    <tr>\n",
842 |        "      <th>998</th>\n",
843 |        "      <td>female</td>\n",
844 |        "      <td>group D</td>\n",
845 |        "      <td>some college</td>\n",
846 |        "      <td>standard</td>\n",
847 |        "      <td>completed</td>\n",
848 |        "      <td>68</td>\n",
849 |        "      <td>78</td>\n",
850 |        "      <td>77</td>\n",
851 |        "    </tr>\n",
852 |        "    <tr>\n",
853 |        "      <th>999</th>\n",
854 |        "      <td>female</td>\n",
855 |        "      <td>group D</td>\n",
856 |        "      <td>some college</td>\n",
857 |        "      <td>free/reduced</td>\n",
858 |        "      <td>none</td>\n",
859 |        "      <td>77</td>\n",
860 |        "      <td>86</td>\n",
861 |        "      <td>86</td>\n",
862 |        "    </tr>\n",
863 |        "  </tbody>\n",
864 |        "</table>\n",
865 |        "<p>1000 rows × 8 columns</p>\n",
866 |        "</div>"
867 |       ],
868 |       "text/plain": [
869 |        "     gender race/ethnicity parental level of education         lunch  \\\n",
870 |        "0    female        group B           bachelor's degree      standard   \n",
871 |        "1    female        group C                some college      standard   \n",
872 |        "2    female        group B             master's degree      standard   \n",
873 |        "3      male        group A          associate's degree  free/reduced   \n",
874 |        "4      male        group C                some college      standard   \n",
875 |        "..      ...            ...                         ...           ...   \n",
876 |        "995  female        group E             master's degree      standard   \n",
877 |        "996    male        group C                 high school  free/reduced   \n",
878 |        "997  female        group C                 high school  free/reduced   \n",
879 |        "998  female        group D                some college      standard   \n",
880 |        "999  female        group D                some college  free/reduced   \n",
881 |        "\n",
882 |        "    test preparation course  math score  reading score  writing score  \n",
883 |        "0                      none          72             72             74  \n",
884 |        "1                 completed          69             90             88  \n",
885 |        "2                      none          90             95             93  \n",
886 |        "3                      none          47             57             44  \n",
887 |        "4                      none          76             78             75  \n",
888 |        "..                      ...         ...            ...            ...  \n",
889 |        "995               completed          88             99             95  \n",
890 |        "996                    none          62             55             55  \n",
891 |        "997               completed          59             71             65  \n",
892 |        "998               completed          68             78             77  \n",
893 |        "999                    none          77             86             86  \n",
894 |        "\n",
895 |        "[1000 rows x 8 columns]"
896 |       ]
897 |      },
898 |      "execution_count": 28,
899 |      "metadata": {},
900 |      "output_type": "execute_result"
901 |     }
902 |    ],
903 |    "source": [
904 |     "# rounding the values of the dataset\n",
905 |     "round(df_exams, 2)"
906 |    ]
907 |   }
908 |  ],
909 |  "metadata": {
910 |   "kernelspec": {
911 |    "display_name": "Python 3",
912 |    "language": "python",
913 |    "name": "python3"
914 |   },
915 |   "language_info": {
916 |    "codemirror_mode": {
917 |     "name": "ipython",
918 |     "version": 3
919 |    },
920 |    "file_extension": ".py",
921 |    "mimetype": "text/x-python",
922 |    "name": "python",
923 |    "nbconvert_exporter": "python",
924 |    "pygments_lexer": "ipython3",
925 |    "version": "3.8.8"
926 |   },
927 |   "toc": {
928 |    "base_numbering": 1,
929 |    "nav_menu": {},
930 |    "number_sections": true,
931 |    "sideBar": true,
932 |    "skip_h1_title": false,
933 |    "title_cell": "Table of Contents",
934 |    "title_sidebar": "Contents",
935 |    "toc_cell": false,
936 |    "toc_position": {},
937 |    "toc_section_display": true,
938 |    "toc_window_display": false
939 |   }
940 |  },
941 |  "nbformat": 4,
942 |  "nbformat_minor": 5
943 | }
944 | 


--------------------------------------------------------------------------------
/2.Intro to Pandas/4.Selecting One Column from a Dataframe.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 1,
  6 |    "id": "4e3fdade",
  7 |    "metadata": {},
  8 |    "outputs": [],
  9 |    "source": [
 10 |     "import pandas as pd"
 11 |    ]
 12 |   },
 13 |   {
 14 |    "cell_type": "code",
 15 |    "execution_count": 2,
 16 |    "id": "9dfaf0d2",
 17 |    "metadata": {
 18 |     "scrolled": false
 19 |    },
 20 |    "outputs": [
 21 |     {
 22 |      "data": {
 23 |       "text/html": [
 24 |        "<div>\n",
 25 |        "<style scoped>\n",
 26 |        "    .dataframe tbody tr th:only-of-type {\n",
 27 |        "        vertical-align: middle;\n",
 28 |        "    }\n",
 29 |        "\n",
 30 |        "    .dataframe tbody tr th {\n",
 31 |        "        vertical-align: top;\n",
 32 |        "    }\n",
 33 |        "\n",
 34 |        "    .dataframe thead th {\n",
 35 |        "        text-align: right;\n",
 36 |        "    }\n",
 37 |        "</style>\n",
 38 |        "<table border=\"1\" class=\"dataframe\">\n",
 39 |        "  <thead>\n",
 40 |        "    <tr style=\"text-align: right;\">\n",
 41 |        "      <th></th>\n",
 42 |        "      <th>gender</th>\n",
 43 |        "      <th>race/ethnicity</th>\n",
 44 |        "      <th>parental level of education</th>\n",
 45 |        "      <th>lunch</th>\n",
 46 |        "      <th>test preparation course</th>\n",
 47 |        "      <th>math score</th>\n",
 48 |        "      <th>reading score</th>\n",
 49 |        "      <th>writing score</th>\n",
 50 |        "    </tr>\n",
 51 |        "  </thead>\n",
 52 |        "  <tbody>\n",
 53 |        "    <tr>\n",
 54 |        "      <th>0</th>\n",
 55 |        "      <td>female</td>\n",
 56 |        "      <td>group B</td>\n",
 57 |        "      <td>bachelor's degree</td>\n",
 58 |        "      <td>standard</td>\n",
 59 |        "      <td>none</td>\n",
 60 |        "      <td>72</td>\n",
 61 |        "      <td>72</td>\n",
 62 |        "      <td>74</td>\n",
 63 |        "    </tr>\n",
 64 |        "    <tr>\n",
 65 |        "      <th>1</th>\n",
 66 |        "      <td>female</td>\n",
 67 |        "      <td>group C</td>\n",
 68 |        "      <td>some college</td>\n",
 69 |        "      <td>standard</td>\n",
 70 |        "      <td>completed</td>\n",
 71 |        "      <td>69</td>\n",
 72 |        "      <td>90</td>\n",
 73 |        "      <td>88</td>\n",
 74 |        "    </tr>\n",
 75 |        "    <tr>\n",
 76 |        "      <th>2</th>\n",
 77 |        "      <td>female</td>\n",
 78 |        "      <td>group B</td>\n",
 79 |        "      <td>master's degree</td>\n",
 80 |        "      <td>standard</td>\n",
 81 |        "      <td>none</td>\n",
 82 |        "      <td>90</td>\n",
 83 |        "      <td>95</td>\n",
 84 |        "      <td>93</td>\n",
 85 |        "    </tr>\n",
 86 |        "    <tr>\n",
 87 |        "      <th>3</th>\n",
 88 |        "      <td>male</td>\n",
 89 |        "      <td>group A</td>\n",
 90 |        "      <td>associate's degree</td>\n",
 91 |        "      <td>free/reduced</td>\n",
 92 |        "      <td>none</td>\n",
 93 |        "      <td>47</td>\n",
 94 |        "      <td>57</td>\n",
 95 |        "      <td>44</td>\n",
 96 |        "    </tr>\n",
 97 |        "    <tr>\n",
 98 |        "      <th>4</th>\n",
 99 |        "      <td>male</td>\n",
100 |        "      <td>group C</td>\n",
101 |        "      <td>some college</td>\n",
102 |        "      <td>standard</td>\n",
103 |        "      <td>none</td>\n",
104 |        "      <td>76</td>\n",
105 |        "      <td>78</td>\n",
106 |        "      <td>75</td>\n",
107 |        "    </tr>\n",
108 |        "  </tbody>\n",
109 |        "</table>\n",
110 |        "</div>"
111 |       ],
112 |       "text/plain": [
113 |        "   gender race/ethnicity parental level of education         lunch  \\\n",
114 |        "0  female        group B           bachelor's degree      standard   \n",
115 |        "1  female        group C                some college      standard   \n",
116 |        "2  female        group B             master's degree      standard   \n",
117 |        "3    male        group A          associate's degree  free/reduced   \n",
118 |        "4    male        group C                some college      standard   \n",
119 |        "\n",
120 |        "  test preparation course  math score  reading score  writing score  \n",
121 |        "0                    none          72             72             74  \n",
122 |        "1               completed          69             90             88  \n",
123 |        "2                    none          90             95             93  \n",
124 |        "3                    none          47             57             44  \n",
125 |        "4                    none          76             78             75  "
126 |       ]
127 |      },
128 |      "execution_count": 2,
129 |      "metadata": {},
130 |      "output_type": "execute_result"
131 |     }
132 |    ],
133 |    "source": [
134 |     "# reading the csv file\n",
135 |     "df_exams = pd.read_csv('StudentsPerformance.csv')\n",
136 |     "df_exams.head()"
137 |    ]
138 |   },
139 |   {
140 |    "cell_type": "markdown",
141 |    "id": "de860322",
142 |    "metadata": {},
143 |    "source": [
144 |     "# Selecting one column"
145 |    ]
146 |   },
147 |   {
148 |    "cell_type": "markdown",
149 |    "id": "4869f1d5",
150 |    "metadata": {},
151 |    "source": [
152 |     "## Syntax 1"
153 |    ]
154 |   },
155 |   {
156 |    "cell_type": "code",
157 |    "execution_count": 3,
158 |    "id": "79ba5c16",
159 |    "metadata": {},
160 |    "outputs": [
161 |     {
162 |      "data": {
163 |       "text/plain": [
164 |        "0      female\n",
165 |        "1      female\n",
166 |        "2      female\n",
167 |        "3        male\n",
168 |        "4        male\n",
169 |        "        ...  \n",
170 |        "995    female\n",
171 |        "996      male\n",
172 |        "997    female\n",
173 |        "998    female\n",
174 |        "999    female\n",
175 |        "Name: gender, Length: 1000, dtype: object"
176 |       ]
177 |      },
178 |      "execution_count": 3,
179 |      "metadata": {},
180 |      "output_type": "execute_result"
181 |     }
182 |    ],
183 |    "source": [
184 |     "# select a column with [] (preferred way to select a column)\n",
185 |     "df_exams['gender']"
186 |    ]
187 |   },
188 |   {
189 |    "cell_type": "code",
190 |    "execution_count": 4,
191 |    "id": "1da5d438",
192 |    "metadata": {},
193 |    "outputs": [
194 |     {
195 |      "data": {
196 |       "text/plain": [
197 |        "pandas.core.series.Series"
198 |       ]
199 |      },
200 |      "execution_count": 4,
201 |      "metadata": {},
202 |      "output_type": "execute_result"
203 |     }
204 |    ],
205 |    "source": [
206 |     "# check out the data type of a column\n",
207 |     "type(df_exams['gender'])"
208 |    ]
209 |   },
210 |   {
211 |    "cell_type": "code",
212 |    "execution_count": 5,
213 |    "id": "d7041d6f",
214 |    "metadata": {},
215 |    "outputs": [
216 |     {
217 |      "data": {
218 |       "text/plain": [
219 |        "0    female\n",
220 |        "1    female\n",
221 |        "2    female\n",
222 |        "3      male\n",
223 |        "4      male\n",
224 |        "Name: gender, dtype: object"
225 |       ]
226 |      },
227 |      "execution_count": 5,
228 |      "metadata": {},
229 |      "output_type": "execute_result"
230 |     }
231 |    ],
232 |    "source": [
233 |     "# series: attributes and methods\n",
234 |     "df_exams['gender'].index\n",
235 |     "df_exams['gender'].head()"
236 |    ]
237 |   },
238 |   {
239 |    "cell_type": "markdown",
240 |    "id": "025f3788",
241 |    "metadata": {},
242 |    "source": [
243 |     "## Syntax 2"
244 |    ]
245 |   },
246 |   {
247 |    "cell_type": "code",
248 |    "execution_count": 6,
249 |    "id": "5250d3b6",
250 |    "metadata": {},
251 |    "outputs": [
252 |     {
253 |      "data": {
254 |       "text/plain": [
255 |        "0      female\n",
256 |        "1      female\n",
257 |        "2      female\n",
258 |        "3        male\n",
259 |        "4        male\n",
260 |        "        ...  \n",
261 |        "995    female\n",
262 |        "996      male\n",
263 |        "997    female\n",
264 |        "998    female\n",
265 |        "999    female\n",
266 |        "Name: gender, Length: 1000, dtype: object"
267 |       ]
268 |      },
269 |      "execution_count": 6,
270 |      "metadata": {},
271 |      "output_type": "execute_result"
272 |     }
273 |    ],
274 |    "source": [
275 |     "# select a column with .\n",
276 |     "df_exams.gender"
277 |    ]
278 |   },
279 |   {
280 |    "cell_type": "code",
281 |    "execution_count": 7,
282 |    "id": "aa3433f7",
283 |    "metadata": {},
284 |    "outputs": [
285 |     {
286 |      "ename": "SyntaxError",
287 |      "evalue": "invalid syntax (<ipython-input-7-e8d7c858c562>, line 2)",
288 |      "output_type": "error",
289 |      "traceback": [
290 |       "\u001b[0;36m  File \u001b[0;32m\"<ipython-input-7-e8d7c858c562>\"\u001b[0;36m, line \u001b[0;32m2\u001b[0m\n\u001b[0;31m    df_exams.math score\u001b[0m\n\u001b[0m                  ^\u001b[0m\n\u001b[0;31mSyntaxError\u001b[0m\u001b[0;31m:\u001b[0m invalid syntax\n"
291 |      ]
292 |     }
293 |    ],
294 |    "source": [
295 |     "# select a column with . (pitfalls)\n",
296 |     "df_exams.math score"
297 |    ]
298 |   },
299 |   {
300 |    "cell_type": "code",
301 |    "execution_count": 8,
302 |    "id": "92b4ae17",
303 |    "metadata": {},
304 |    "outputs": [
305 |     {
306 |      "data": {
307 |       "text/plain": [
308 |        "0      72\n",
309 |        "1      69\n",
310 |        "2      90\n",
311 |        "3      47\n",
312 |        "4      76\n",
313 |        "       ..\n",
314 |        "995    88\n",
315 |        "996    62\n",
316 |        "997    59\n",
317 |        "998    68\n",
318 |        "999    77\n",
319 |        "Name: math score, Length: 1000, dtype: int64"
320 |       ]
321 |      },
322 |      "execution_count": 8,
323 |      "metadata": {},
324 |      "output_type": "execute_result"
325 |     }
326 |    ],
327 |    "source": [
328 |     "# select the same column using []\n",
329 |     "df_exams[\"math score\"]"
330 |    ]
331 |   }
332 |  ],
333 |  "metadata": {
334 |   "kernelspec": {
335 |    "display_name": "Python 3",
336 |    "language": "python",
337 |    "name": "python3"
338 |   },
339 |   "language_info": {
340 |    "codemirror_mode": {
341 |     "name": "ipython",
342 |     "version": 3
343 |    },
344 |    "file_extension": ".py",
345 |    "mimetype": "text/x-python",
346 |    "name": "python",
347 |    "nbconvert_exporter": "python",
348 |    "pygments_lexer": "ipython3",
349 |    "version": "3.8.8"
350 |   },
351 |   "toc": {
352 |    "base_numbering": 1,
353 |    "nav_menu": {},
354 |    "number_sections": true,
355 |    "sideBar": true,
356 |    "skip_h1_title": false,
357 |    "title_cell": "Table of Contents",
358 |    "title_sidebar": "Contents",
359 |    "toc_cell": false,
360 |    "toc_position": {},
361 |    "toc_section_display": true,
362 |    "toc_window_display": false
363 |   }
364 |  },
365 |  "nbformat": 4,
366 |  "nbformat_minor": 5
367 | }
368 | 


--------------------------------------------------------------------------------
/2.Intro to Pandas/5.Selecting Two or More Columns from a Dataframe.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 1,
  6 |    "id": "4e3fdade",
  7 |    "metadata": {},
  8 |    "outputs": [],
  9 |    "source": [
 10 |     "import pandas as pd"
 11 |    ]
 12 |   },
 13 |   {
 14 |    "cell_type": "code",
 15 |    "execution_count": 2,
 16 |    "id": "9dfaf0d2",
 17 |    "metadata": {
 18 |     "scrolled": false
 19 |    },
 20 |    "outputs": [
 21 |     {
 22 |      "data": {
 23 |       "text/html": [
 24 |        "<div>\n",
 25 |        "<style scoped>\n",
 26 |        "    .dataframe tbody tr th:only-of-type {\n",
 27 |        "        vertical-align: middle;\n",
 28 |        "    }\n",
 29 |        "\n",
 30 |        "    .dataframe tbody tr th {\n",
 31 |        "        vertical-align: top;\n",
 32 |        "    }\n",
 33 |        "\n",
 34 |        "    .dataframe thead th {\n",
 35 |        "        text-align: right;\n",
 36 |        "    }\n",
 37 |        "</style>\n",
 38 |        "<table border=\"1\" class=\"dataframe\">\n",
 39 |        "  <thead>\n",
 40 |        "    <tr style=\"text-align: right;\">\n",
 41 |        "      <th></th>\n",
 42 |        "      <th>gender</th>\n",
 43 |        "      <th>race/ethnicity</th>\n",
 44 |        "      <th>parental level of education</th>\n",
 45 |        "      <th>lunch</th>\n",
 46 |        "      <th>test preparation course</th>\n",
 47 |        "      <th>math score</th>\n",
 48 |        "      <th>reading score</th>\n",
 49 |        "      <th>writing score</th>\n",
 50 |        "    </tr>\n",
 51 |        "  </thead>\n",
 52 |        "  <tbody>\n",
 53 |        "    <tr>\n",
 54 |        "      <th>0</th>\n",
 55 |        "      <td>female</td>\n",
 56 |        "      <td>group B</td>\n",
 57 |        "      <td>bachelor's degree</td>\n",
 58 |        "      <td>standard</td>\n",
 59 |        "      <td>none</td>\n",
 60 |        "      <td>72</td>\n",
 61 |        "      <td>72</td>\n",
 62 |        "      <td>74</td>\n",
 63 |        "    </tr>\n",
 64 |        "    <tr>\n",
 65 |        "      <th>1</th>\n",
 66 |        "      <td>female</td>\n",
 67 |        "      <td>group C</td>\n",
 68 |        "      <td>some college</td>\n",
 69 |        "      <td>standard</td>\n",
 70 |        "      <td>completed</td>\n",
 71 |        "      <td>69</td>\n",
 72 |        "      <td>90</td>\n",
 73 |        "      <td>88</td>\n",
 74 |        "    </tr>\n",
 75 |        "    <tr>\n",
 76 |        "      <th>2</th>\n",
 77 |        "      <td>female</td>\n",
 78 |        "      <td>group B</td>\n",
 79 |        "      <td>master's degree</td>\n",
 80 |        "      <td>standard</td>\n",
 81 |        "      <td>none</td>\n",
 82 |        "      <td>90</td>\n",
 83 |        "      <td>95</td>\n",
 84 |        "      <td>93</td>\n",
 85 |        "    </tr>\n",
 86 |        "    <tr>\n",
 87 |        "      <th>3</th>\n",
 88 |        "      <td>male</td>\n",
 89 |        "      <td>group A</td>\n",
 90 |        "      <td>associate's degree</td>\n",
 91 |        "      <td>free/reduced</td>\n",
 92 |        "      <td>none</td>\n",
 93 |        "      <td>47</td>\n",
 94 |        "      <td>57</td>\n",
 95 |        "      <td>44</td>\n",
 96 |        "    </tr>\n",
 97 |        "    <tr>\n",
 98 |        "      <th>4</th>\n",
 99 |        "      <td>male</td>\n",
100 |        "      <td>group C</td>\n",
101 |        "      <td>some college</td>\n",
102 |        "      <td>standard</td>\n",
103 |        "      <td>none</td>\n",
104 |        "      <td>76</td>\n",
105 |        "      <td>78</td>\n",
106 |        "      <td>75</td>\n",
107 |        "    </tr>\n",
108 |        "  </tbody>\n",
109 |        "</table>\n",
110 |        "</div>"
111 |       ],
112 |       "text/plain": [
113 |        "   gender race/ethnicity parental level of education         lunch  \\\n",
114 |        "0  female        group B           bachelor's degree      standard   \n",
115 |        "1  female        group C                some college      standard   \n",
116 |        "2  female        group B             master's degree      standard   \n",
117 |        "3    male        group A          associate's degree  free/reduced   \n",
118 |        "4    male        group C                some college      standard   \n",
119 |        "\n",
120 |        "  test preparation course  math score  reading score  writing score  \n",
121 |        "0                    none          72             72             74  \n",
122 |        "1               completed          69             90             88  \n",
123 |        "2                    none          90             95             93  \n",
124 |        "3                    none          47             57             44  \n",
125 |        "4                    none          76             78             75  "
126 |       ]
127 |      },
128 |      "execution_count": 2,
129 |      "metadata": {},
130 |      "output_type": "execute_result"
131 |     }
132 |    ],
133 |    "source": [
134 |     "# reading the csv file\n",
135 |     "df_exams = pd.read_csv('StudentsPerformance.csv')\n",
136 |     "df_exams.head()"
137 |    ]
138 |   },
139 |   {
140 |    "cell_type": "markdown",
141 |    "id": "de860322",
142 |    "metadata": {},
143 |    "source": [
144 |     "# Selecting two or more columns"
145 |    ]
146 |   },
147 |   {
148 |    "cell_type": "code",
149 |    "execution_count": 3,
150 |    "id": "79ba5c16",
151 |    "metadata": {},
152 |    "outputs": [
153 |     {
154 |      "data": {
155 |       "text/html": [
156 |        "<div>\n",
157 |        "<style scoped>\n",
158 |        "    .dataframe tbody tr th:only-of-type {\n",
159 |        "        vertical-align: middle;\n",
160 |        "    }\n",
161 |        "\n",
162 |        "    .dataframe tbody tr th {\n",
163 |        "        vertical-align: top;\n",
164 |        "    }\n",
165 |        "\n",
166 |        "    .dataframe thead th {\n",
167 |        "        text-align: right;\n",
168 |        "    }\n",
169 |        "</style>\n",
170 |        "<table border=\"1\" class=\"dataframe\">\n",
171 |        "  <thead>\n",
172 |        "    <tr style=\"text-align: right;\">\n",
173 |        "      <th></th>\n",
174 |        "      <th>gender</th>\n",
175 |        "      <th>math score</th>\n",
176 |        "    </tr>\n",
177 |        "  </thead>\n",
178 |        "  <tbody>\n",
179 |        "    <tr>\n",
180 |        "      <th>0</th>\n",
181 |        "      <td>female</td>\n",
182 |        "      <td>72</td>\n",
183 |        "    </tr>\n",
184 |        "    <tr>\n",
185 |        "      <th>1</th>\n",
186 |        "      <td>female</td>\n",
187 |        "      <td>69</td>\n",
188 |        "    </tr>\n",
189 |        "    <tr>\n",
190 |        "      <th>2</th>\n",
191 |        "      <td>female</td>\n",
192 |        "      <td>90</td>\n",
193 |        "    </tr>\n",
194 |        "    <tr>\n",
195 |        "      <th>3</th>\n",
196 |        "      <td>male</td>\n",
197 |        "      <td>47</td>\n",
198 |        "    </tr>\n",
199 |        "    <tr>\n",
200 |        "      <th>4</th>\n",
201 |        "      <td>male</td>\n",
202 |        "      <td>76</td>\n",
203 |        "    </tr>\n",
204 |        "    <tr>\n",
205 |        "      <th>...</th>\n",
206 |        "      <td>...</td>\n",
207 |        "      <td>...</td>\n",
208 |        "    </tr>\n",
209 |        "    <tr>\n",
210 |        "      <th>995</th>\n",
211 |        "      <td>female</td>\n",
212 |        "      <td>88</td>\n",
213 |        "    </tr>\n",
214 |        "    <tr>\n",
215 |        "      <th>996</th>\n",
216 |        "      <td>male</td>\n",
217 |        "      <td>62</td>\n",
218 |        "    </tr>\n",
219 |        "    <tr>\n",
220 |        "      <th>997</th>\n",
221 |        "      <td>female</td>\n",
222 |        "      <td>59</td>\n",
223 |        "    </tr>\n",
224 |        "    <tr>\n",
225 |        "      <th>998</th>\n",
226 |        "      <td>female</td>\n",
227 |        "      <td>68</td>\n",
228 |        "    </tr>\n",
229 |        "    <tr>\n",
230 |        "      <th>999</th>\n",
231 |        "      <td>female</td>\n",
232 |        "      <td>77</td>\n",
233 |        "    </tr>\n",
234 |        "  </tbody>\n",
235 |        "</table>\n",
236 |        "<p>1000 rows × 2 columns</p>\n",
237 |        "</div>"
238 |       ],
239 |       "text/plain": [
240 |        "     gender  math score\n",
241 |        "0    female          72\n",
242 |        "1    female          69\n",
243 |        "2    female          90\n",
244 |        "3      male          47\n",
245 |        "4      male          76\n",
246 |        "..      ...         ...\n",
247 |        "995  female          88\n",
248 |        "996    male          62\n",
249 |        "997  female          59\n",
250 |        "998  female          68\n",
251 |        "999  female          77\n",
252 |        "\n",
253 |        "[1000 rows x 2 columns]"
254 |       ]
255 |      },
256 |      "execution_count": 3,
257 |      "metadata": {},
258 |      "output_type": "execute_result"
259 |     }
260 |    ],
261 |    "source": [
262 |     "# select 2 columns using [[]]\n",
263 |     "df_exams[['gender', 'math score']]"
264 |    ]
265 |   },
266 |   {
267 |    "cell_type": "code",
268 |    "execution_count": 4,
269 |    "id": "1da5d438",
270 |    "metadata": {},
271 |    "outputs": [
272 |     {
273 |      "data": {
274 |       "text/plain": [
275 |        "pandas.core.frame.DataFrame"
276 |       ]
277 |      },
278 |      "execution_count": 4,
279 |      "metadata": {},
280 |      "output_type": "execute_result"
281 |     }
282 |    ],
283 |    "source": [
284 |     "# check out the data type of the selection\n",
285 |     "type(df_exams[['gender', 'math score']])"
286 |    ]
287 |   },
288 |   {
289 |    "cell_type": "code",
290 |    "execution_count": 5,
291 |    "id": "42b11033",
292 |    "metadata": {},
293 |    "outputs": [
294 |     {
295 |      "data": {
296 |       "text/html": [
297 |        "<div>\n",
298 |        "<style scoped>\n",
299 |        "    .dataframe tbody tr th:only-of-type {\n",
300 |        "        vertical-align: middle;\n",
301 |        "    }\n",
302 |        "\n",
303 |        "    .dataframe tbody tr th {\n",
304 |        "        vertical-align: top;\n",
305 |        "    }\n",
306 |        "\n",
307 |        "    .dataframe thead th {\n",
308 |        "        text-align: right;\n",
309 |        "    }\n",
310 |        "</style>\n",
311 |        "<table border=\"1\" class=\"dataframe\">\n",
312 |        "  <thead>\n",
313 |        "    <tr style=\"text-align: right;\">\n",
314 |        "      <th></th>\n",
315 |        "      <th>gender</th>\n",
316 |        "      <th>math score</th>\n",
317 |        "      <th>reading score</th>\n",
318 |        "      <th>writing score</th>\n",
319 |        "    </tr>\n",
320 |        "  </thead>\n",
321 |        "  <tbody>\n",
322 |        "    <tr>\n",
323 |        "      <th>0</th>\n",
324 |        "      <td>female</td>\n",
325 |        "      <td>72</td>\n",
326 |        "      <td>72</td>\n",
327 |        "      <td>74</td>\n",
328 |        "    </tr>\n",
329 |        "    <tr>\n",
330 |        "      <th>1</th>\n",
331 |        "      <td>female</td>\n",
332 |        "      <td>69</td>\n",
333 |        "      <td>90</td>\n",
334 |        "      <td>88</td>\n",
335 |        "    </tr>\n",
336 |        "    <tr>\n",
337 |        "      <th>2</th>\n",
338 |        "      <td>female</td>\n",
339 |        "      <td>90</td>\n",
340 |        "      <td>95</td>\n",
341 |        "      <td>93</td>\n",
342 |        "    </tr>\n",
343 |        "    <tr>\n",
344 |        "      <th>3</th>\n",
345 |        "      <td>male</td>\n",
346 |        "      <td>47</td>\n",
347 |        "      <td>57</td>\n",
348 |        "      <td>44</td>\n",
349 |        "    </tr>\n",
350 |        "    <tr>\n",
351 |        "      <th>4</th>\n",
352 |        "      <td>male</td>\n",
353 |        "      <td>76</td>\n",
354 |        "      <td>78</td>\n",
355 |        "      <td>75</td>\n",
356 |        "    </tr>\n",
357 |        "    <tr>\n",
358 |        "      <th>...</th>\n",
359 |        "      <td>...</td>\n",
360 |        "      <td>...</td>\n",
361 |        "      <td>...</td>\n",
362 |        "      <td>...</td>\n",
363 |        "    </tr>\n",
364 |        "    <tr>\n",
365 |        "      <th>995</th>\n",
366 |        "      <td>female</td>\n",
367 |        "      <td>88</td>\n",
368 |        "      <td>99</td>\n",
369 |        "      <td>95</td>\n",
370 |        "    </tr>\n",
371 |        "    <tr>\n",
372 |        "      <th>996</th>\n",
373 |        "      <td>male</td>\n",
374 |        "      <td>62</td>\n",
375 |        "      <td>55</td>\n",
376 |        "      <td>55</td>\n",
377 |        "    </tr>\n",
378 |        "    <tr>\n",
379 |        "      <th>997</th>\n",
380 |        "      <td>female</td>\n",
381 |        "      <td>59</td>\n",
382 |        "      <td>71</td>\n",
383 |        "      <td>65</td>\n",
384 |        "    </tr>\n",
385 |        "    <tr>\n",
386 |        "      <th>998</th>\n",
387 |        "      <td>female</td>\n",
388 |        "      <td>68</td>\n",
389 |        "      <td>78</td>\n",
390 |        "      <td>77</td>\n",
391 |        "    </tr>\n",
392 |        "    <tr>\n",
393 |        "      <th>999</th>\n",
394 |        "      <td>female</td>\n",
395 |        "      <td>77</td>\n",
396 |        "      <td>86</td>\n",
397 |        "      <td>86</td>\n",
398 |        "    </tr>\n",
399 |        "  </tbody>\n",
400 |        "</table>\n",
401 |        "<p>1000 rows × 4 columns</p>\n",
402 |        "</div>"
403 |       ],
404 |       "text/plain": [
405 |        "     gender  math score  reading score  writing score\n",
406 |        "0    female          72             72             74\n",
407 |        "1    female          69             90             88\n",
408 |        "2    female          90             95             93\n",
409 |        "3      male          47             57             44\n",
410 |        "4      male          76             78             75\n",
411 |        "..      ...         ...            ...            ...\n",
412 |        "995  female          88             99             95\n",
413 |        "996    male          62             55             55\n",
414 |        "997  female          59             71             65\n",
415 |        "998  female          68             78             77\n",
416 |        "999  female          77             86             86\n",
417 |        "\n",
418 |        "[1000 rows x 4 columns]"
419 |       ]
420 |      },
421 |      "execution_count": 5,
422 |      "metadata": {},
423 |      "output_type": "execute_result"
424 |     }
425 |    ],
426 |    "source": [
427 |     "# select 2 or more columns using [[]]\n",
428 |     "df_exams[['gender', 'math score', 'reading score', 'writing score']]"
429 |    ]
430 |   },
431 |   {
432 |    "cell_type": "code",
433 |    "execution_count": 6,
434 |    "id": "45b07093",
435 |    "metadata": {},
436 |    "outputs": [],
437 |    "source": [
438 |     "# we can't select 2 or more columns with the \".\"\n",
439 |     "# df_exams.'gender', 'math score'"
440 |    ]
441 |   }
442 |  ],
443 |  "metadata": {
444 |   "kernelspec": {
445 |    "display_name": "Python 3",
446 |    "language": "python",
447 |    "name": "python3"
448 |   },
449 |   "language_info": {
450 |    "codemirror_mode": {
451 |     "name": "ipython",
452 |     "version": 3
453 |    },
454 |    "file_extension": ".py",
455 |    "mimetype": "text/x-python",
456 |    "name": "python",
457 |    "nbconvert_exporter": "python",
458 |    "pygments_lexer": "ipython3",
459 |    "version": "3.8.8"
460 |   },
461 |   "toc": {
462 |    "base_numbering": 1,
463 |    "nav_menu": {},
464 |    "number_sections": true,
465 |    "sideBar": true,
466 |    "skip_h1_title": false,
467 |    "title_cell": "Table of Contents",
468 |    "title_sidebar": "Contents",
469 |    "toc_cell": false,
470 |    "toc_position": {},
471 |    "toc_section_display": true,
472 |    "toc_window_display": false
473 |   }
474 |  },
475 |  "nbformat": 4,
476 |  "nbformat_minor": 5
477 | }
478 | 


--------------------------------------------------------------------------------
/2.Intro to Pandas/7.Operations on Dataframes.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 1,
  6 |    "id": "4e3fdade",
  7 |    "metadata": {},
  8 |    "outputs": [],
  9 |    "source": [
 10 |     "import pandas as pd"
 11 |    ]
 12 |   },
 13 |   {
 14 |    "cell_type": "code",
 15 |    "execution_count": 2,
 16 |    "id": "9dfaf0d2",
 17 |    "metadata": {
 18 |     "scrolled": true
 19 |    },
 20 |    "outputs": [
 21 |     {
 22 |      "data": {
 23 |       "text/html": [
 24 |        "<div>\n",
 25 |        "<style scoped>\n",
 26 |        "    .dataframe tbody tr th:only-of-type {\n",
 27 |        "        vertical-align: middle;\n",
 28 |        "    }\n",
 29 |        "\n",
 30 |        "    .dataframe tbody tr th {\n",
 31 |        "        vertical-align: top;\n",
 32 |        "    }\n",
 33 |        "\n",
 34 |        "    .dataframe thead th {\n",
 35 |        "        text-align: right;\n",
 36 |        "    }\n",
 37 |        "</style>\n",
 38 |        "<table border=\"1\" class=\"dataframe\">\n",
 39 |        "  <thead>\n",
 40 |        "    <tr style=\"text-align: right;\">\n",
 41 |        "      <th></th>\n",
 42 |        "      <th>gender</th>\n",
 43 |        "      <th>race/ethnicity</th>\n",
 44 |        "      <th>parental level of education</th>\n",
 45 |        "      <th>lunch</th>\n",
 46 |        "      <th>test preparation course</th>\n",
 47 |        "      <th>math score</th>\n",
 48 |        "      <th>reading score</th>\n",
 49 |        "      <th>writing score</th>\n",
 50 |        "    </tr>\n",
 51 |        "  </thead>\n",
 52 |        "  <tbody>\n",
 53 |        "    <tr>\n",
 54 |        "      <th>0</th>\n",
 55 |        "      <td>female</td>\n",
 56 |        "      <td>group B</td>\n",
 57 |        "      <td>bachelor's degree</td>\n",
 58 |        "      <td>standard</td>\n",
 59 |        "      <td>none</td>\n",
 60 |        "      <td>72</td>\n",
 61 |        "      <td>72</td>\n",
 62 |        "      <td>74</td>\n",
 63 |        "    </tr>\n",
 64 |        "    <tr>\n",
 65 |        "      <th>1</th>\n",
 66 |        "      <td>female</td>\n",
 67 |        "      <td>group C</td>\n",
 68 |        "      <td>some college</td>\n",
 69 |        "      <td>standard</td>\n",
 70 |        "      <td>completed</td>\n",
 71 |        "      <td>69</td>\n",
 72 |        "      <td>90</td>\n",
 73 |        "      <td>88</td>\n",
 74 |        "    </tr>\n",
 75 |        "    <tr>\n",
 76 |        "      <th>2</th>\n",
 77 |        "      <td>female</td>\n",
 78 |        "      <td>group B</td>\n",
 79 |        "      <td>master's degree</td>\n",
 80 |        "      <td>standard</td>\n",
 81 |        "      <td>none</td>\n",
 82 |        "      <td>90</td>\n",
 83 |        "      <td>95</td>\n",
 84 |        "      <td>93</td>\n",
 85 |        "    </tr>\n",
 86 |        "    <tr>\n",
 87 |        "      <th>3</th>\n",
 88 |        "      <td>male</td>\n",
 89 |        "      <td>group A</td>\n",
 90 |        "      <td>associate's degree</td>\n",
 91 |        "      <td>free/reduced</td>\n",
 92 |        "      <td>none</td>\n",
 93 |        "      <td>47</td>\n",
 94 |        "      <td>57</td>\n",
 95 |        "      <td>44</td>\n",
 96 |        "    </tr>\n",
 97 |        "    <tr>\n",
 98 |        "      <th>4</th>\n",
 99 |        "      <td>male</td>\n",
100 |        "      <td>group C</td>\n",
101 |        "      <td>some college</td>\n",
102 |        "      <td>standard</td>\n",
103 |        "      <td>none</td>\n",
104 |        "      <td>76</td>\n",
105 |        "      <td>78</td>\n",
106 |        "      <td>75</td>\n",
107 |        "    </tr>\n",
108 |        "  </tbody>\n",
109 |        "</table>\n",
110 |        "</div>"
111 |       ],
112 |       "text/plain": [
113 |        "   gender race/ethnicity parental level of education         lunch  \\\n",
114 |        "0  female        group B           bachelor's degree      standard   \n",
115 |        "1  female        group C                some college      standard   \n",
116 |        "2  female        group B             master's degree      standard   \n",
117 |        "3    male        group A          associate's degree  free/reduced   \n",
118 |        "4    male        group C                some college      standard   \n",
119 |        "\n",
120 |        "  test preparation course  math score  reading score  writing score  \n",
121 |        "0                    none          72             72             74  \n",
122 |        "1               completed          69             90             88  \n",
123 |        "2                    none          90             95             93  \n",
124 |        "3                    none          47             57             44  \n",
125 |        "4                    none          76             78             75  "
126 |       ]
127 |      },
128 |      "execution_count": 2,
129 |      "metadata": {},
130 |      "output_type": "execute_result"
131 |     }
132 |    ],
133 |    "source": [
134 |     "# reading the csv file\n",
135 |     "df_exams = pd.read_csv('StudentsPerformance.csv')\n",
136 |     "df_exams.head()"
137 |    ]
138 |   },
139 |   {
140 |    "cell_type": "markdown",
141 |    "id": "65a8afc2",
142 |    "metadata": {},
143 |    "source": [
144 |     "# Math Operations"
145 |    ]
146 |   },
147 |   {
148 |    "cell_type": "markdown",
149 |    "id": "e93c4e2b",
150 |    "metadata": {},
151 |    "source": [
152 |     "## Operations in columns"
153 |    ]
154 |   },
155 |   {
156 |    "cell_type": "code",
157 |    "execution_count": 3,
158 |    "id": "63bd52ec",
159 |    "metadata": {
160 |     "scrolled": true
161 |    },
162 |    "outputs": [
163 |     {
164 |      "data": {
165 |       "text/plain": [
166 |        "66089"
167 |       ]
168 |      },
169 |      "execution_count": 3,
170 |      "metadata": {},
171 |      "output_type": "execute_result"
172 |     }
173 |    ],
174 |    "source": [
175 |     "# select a column and calculate total sum\n",
176 |     "df_exams['math score'].sum()"
177 |    ]
178 |   },
179 |   {
180 |    "cell_type": "code",
181 |    "execution_count": 4,
182 |    "id": "200f9c1e",
183 |    "metadata": {},
184 |    "outputs": [
185 |     {
186 |      "data": {
187 |       "text/plain": [
188 |        "0"
189 |       ]
190 |      },
191 |      "execution_count": 4,
192 |      "metadata": {},
193 |      "output_type": "execute_result"
194 |     }
195 |    ],
196 |    "source": [
197 |     "# count, mean, std, max, and min\n",
198 |     "df_exams['math score'].count()\n",
199 |     "df_exams['math score'].mean()\n",
200 |     "df_exams['math score'].std()\n",
201 |     "df_exams['math score'].max()\n",
202 |     "df_exams['math score'].min()"
203 |    ]
204 |   },
205 |   {
206 |    "cell_type": "code",
207 |    "execution_count": 5,
208 |    "id": "a4847df7",
209 |    "metadata": {},
210 |    "outputs": [
211 |     {
212 |      "data": {
213 |       "text/html": [
214 |        "<div>\n",
215 |        "<style scoped>\n",
216 |        "    .dataframe tbody tr th:only-of-type {\n",
217 |        "        vertical-align: middle;\n",
218 |        "    }\n",
219 |        "\n",
220 |        "    .dataframe tbody tr th {\n",
221 |        "        vertical-align: top;\n",
222 |        "    }\n",
223 |        "\n",
224 |        "    .dataframe thead th {\n",
225 |        "        text-align: right;\n",
226 |        "    }\n",
227 |        "</style>\n",
228 |        "<table border=\"1\" class=\"dataframe\">\n",
229 |        "  <thead>\n",
230 |        "    <tr style=\"text-align: right;\">\n",
231 |        "      <th></th>\n",
232 |        "      <th>math score</th>\n",
233 |        "      <th>reading score</th>\n",
234 |        "      <th>writing score</th>\n",
235 |        "    </tr>\n",
236 |        "  </thead>\n",
237 |        "  <tbody>\n",
238 |        "    <tr>\n",
239 |        "      <th>count</th>\n",
240 |        "      <td>1000.00000</td>\n",
241 |        "      <td>1000.000000</td>\n",
242 |        "      <td>1000.000000</td>\n",
243 |        "    </tr>\n",
244 |        "    <tr>\n",
245 |        "      <th>mean</th>\n",
246 |        "      <td>66.08900</td>\n",
247 |        "      <td>69.169000</td>\n",
248 |        "      <td>68.054000</td>\n",
249 |        "    </tr>\n",
250 |        "    <tr>\n",
251 |        "      <th>std</th>\n",
252 |        "      <td>15.16308</td>\n",
253 |        "      <td>14.600192</td>\n",
254 |        "      <td>15.195657</td>\n",
255 |        "    </tr>\n",
256 |        "    <tr>\n",
257 |        "      <th>min</th>\n",
258 |        "      <td>0.00000</td>\n",
259 |        "      <td>17.000000</td>\n",
260 |        "      <td>10.000000</td>\n",
261 |        "    </tr>\n",
262 |        "    <tr>\n",
263 |        "      <th>25%</th>\n",
264 |        "      <td>57.00000</td>\n",
265 |        "      <td>59.000000</td>\n",
266 |        "      <td>57.750000</td>\n",
267 |        "    </tr>\n",
268 |        "    <tr>\n",
269 |        "      <th>50%</th>\n",
270 |        "      <td>66.00000</td>\n",
271 |        "      <td>70.000000</td>\n",
272 |        "      <td>69.000000</td>\n",
273 |        "    </tr>\n",
274 |        "    <tr>\n",
275 |        "      <th>75%</th>\n",
276 |        "      <td>77.00000</td>\n",
277 |        "      <td>79.000000</td>\n",
278 |        "      <td>79.000000</td>\n",
279 |        "    </tr>\n",
280 |        "    <tr>\n",
281 |        "      <th>max</th>\n",
282 |        "      <td>100.00000</td>\n",
283 |        "      <td>100.000000</td>\n",
284 |        "      <td>100.000000</td>\n",
285 |        "    </tr>\n",
286 |        "  </tbody>\n",
287 |        "</table>\n",
288 |        "</div>"
289 |       ],
290 |       "text/plain": [
291 |        "       math score  reading score  writing score\n",
292 |        "count  1000.00000    1000.000000    1000.000000\n",
293 |        "mean     66.08900      69.169000      68.054000\n",
294 |        "std      15.16308      14.600192      15.195657\n",
295 |        "min       0.00000      17.000000      10.000000\n",
296 |        "25%      57.00000      59.000000      57.750000\n",
297 |        "50%      66.00000      70.000000      69.000000\n",
298 |        "75%      77.00000      79.000000      79.000000\n",
299 |        "max     100.00000     100.000000     100.000000"
300 |       ]
301 |      },
302 |      "execution_count": 5,
303 |      "metadata": {},
304 |      "output_type": "execute_result"
305 |     }
306 |    ],
307 |    "source": [
308 |     "# easier calculation with .describe()\n",
309 |     "df_exams.describe()"
310 |    ]
311 |   },
312 |   {
313 |    "cell_type": "markdown",
314 |    "id": "d85482c6",
315 |    "metadata": {},
316 |    "source": [
317 |     "## Operations in rows"
318 |    ]
319 |   },
320 |   {
321 |    "cell_type": "code",
322 |    "execution_count": 6,
323 |    "id": "21edc88a",
324 |    "metadata": {},
325 |    "outputs": [
326 |     {
327 |      "data": {
328 |       "text/plain": [
329 |        "0      218\n",
330 |        "1      247\n",
331 |        "2      278\n",
332 |        "3      148\n",
333 |        "4      229\n",
334 |        "      ... \n",
335 |        "995    282\n",
336 |        "996    172\n",
337 |        "997    195\n",
338 |        "998    223\n",
339 |        "999    249\n",
340 |        "Length: 1000, dtype: int64"
341 |       ]
342 |      },
343 |      "execution_count": 6,
344 |      "metadata": {},
345 |      "output_type": "execute_result"
346 |     }
347 |    ],
348 |    "source": [
349 |     "# calculating the sum in a row\n",
350 |     "df_exams['math score'] + df_exams['reading score'] + df_exams['writing score']"
351 |    ]
352 |   },
353 |   {
354 |    "cell_type": "code",
355 |    "execution_count": 7,
356 |    "id": "e62eb260",
357 |    "metadata": {},
358 |    "outputs": [],
359 |    "source": [
360 |     "# calculating the average score and assigning the result to a new column\n",
361 |     "df_exams['average'] = (df_exams['math score'] + df_exams['reading score'] + df_exams['writing score'])/3"
362 |    ]
363 |   },
364 |   {
365 |    "cell_type": "code",
366 |    "execution_count": 8,
367 |    "id": "63d8f21d",
368 |    "metadata": {},
369 |    "outputs": [
370 |     {
371 |      "data": {
372 |       "text/html": [
373 |        "<div>\n",
374 |        "<style scoped>\n",
375 |        "    .dataframe tbody tr th:only-of-type {\n",
376 |        "        vertical-align: middle;\n",
377 |        "    }\n",
378 |        "\n",
379 |        "    .dataframe tbody tr th {\n",
380 |        "        vertical-align: top;\n",
381 |        "    }\n",
382 |        "\n",
383 |        "    .dataframe thead th {\n",
384 |        "        text-align: right;\n",
385 |        "    }\n",
386 |        "</style>\n",
387 |        "<table border=\"1\" class=\"dataframe\">\n",
388 |        "  <thead>\n",
389 |        "    <tr style=\"text-align: right;\">\n",
390 |        "      <th></th>\n",
391 |        "      <th>gender</th>\n",
392 |        "      <th>race/ethnicity</th>\n",
393 |        "      <th>parental level of education</th>\n",
394 |        "      <th>lunch</th>\n",
395 |        "      <th>test preparation course</th>\n",
396 |        "      <th>math score</th>\n",
397 |        "      <th>reading score</th>\n",
398 |        "      <th>writing score</th>\n",
399 |        "      <th>average</th>\n",
400 |        "    </tr>\n",
401 |        "  </thead>\n",
402 |        "  <tbody>\n",
403 |        "    <tr>\n",
404 |        "      <th>0</th>\n",
405 |        "      <td>female</td>\n",
406 |        "      <td>group B</td>\n",
407 |        "      <td>bachelor's degree</td>\n",
408 |        "      <td>standard</td>\n",
409 |        "      <td>none</td>\n",
410 |        "      <td>72</td>\n",
411 |        "      <td>72</td>\n",
412 |        "      <td>74</td>\n",
413 |        "      <td>72.666667</td>\n",
414 |        "    </tr>\n",
415 |        "    <tr>\n",
416 |        "      <th>1</th>\n",
417 |        "      <td>female</td>\n",
418 |        "      <td>group C</td>\n",
419 |        "      <td>some college</td>\n",
420 |        "      <td>standard</td>\n",
421 |        "      <td>completed</td>\n",
422 |        "      <td>69</td>\n",
423 |        "      <td>90</td>\n",
424 |        "      <td>88</td>\n",
425 |        "      <td>82.333333</td>\n",
426 |        "    </tr>\n",
427 |        "    <tr>\n",
428 |        "      <th>2</th>\n",
429 |        "      <td>female</td>\n",
430 |        "      <td>group B</td>\n",
431 |        "      <td>master's degree</td>\n",
432 |        "      <td>standard</td>\n",
433 |        "      <td>none</td>\n",
434 |        "      <td>90</td>\n",
435 |        "      <td>95</td>\n",
436 |        "      <td>93</td>\n",
437 |        "      <td>92.666667</td>\n",
438 |        "    </tr>\n",
439 |        "    <tr>\n",
440 |        "      <th>3</th>\n",
441 |        "      <td>male</td>\n",
442 |        "      <td>group A</td>\n",
443 |        "      <td>associate's degree</td>\n",
444 |        "      <td>free/reduced</td>\n",
445 |        "      <td>none</td>\n",
446 |        "      <td>47</td>\n",
447 |        "      <td>57</td>\n",
448 |        "      <td>44</td>\n",
449 |        "      <td>49.333333</td>\n",
450 |        "    </tr>\n",
451 |        "    <tr>\n",
452 |        "      <th>4</th>\n",
453 |        "      <td>male</td>\n",
454 |        "      <td>group C</td>\n",
455 |        "      <td>some college</td>\n",
456 |        "      <td>standard</td>\n",
457 |        "      <td>none</td>\n",
458 |        "      <td>76</td>\n",
459 |        "      <td>78</td>\n",
460 |        "      <td>75</td>\n",
461 |        "      <td>76.333333</td>\n",
462 |        "    </tr>\n",
463 |        "    <tr>\n",
464 |        "      <th>...</th>\n",
465 |        "      <td>...</td>\n",
466 |        "      <td>...</td>\n",
467 |        "      <td>...</td>\n",
468 |        "      <td>...</td>\n",
469 |        "      <td>...</td>\n",
470 |        "      <td>...</td>\n",
471 |        "      <td>...</td>\n",
472 |        "      <td>...</td>\n",
473 |        "      <td>...</td>\n",
474 |        "    </tr>\n",
475 |        "    <tr>\n",
476 |        "      <th>995</th>\n",
477 |        "      <td>female</td>\n",
478 |        "      <td>group E</td>\n",
479 |        "      <td>master's degree</td>\n",
480 |        "      <td>standard</td>\n",
481 |        "      <td>completed</td>\n",
482 |        "      <td>88</td>\n",
483 |        "      <td>99</td>\n",
484 |        "      <td>95</td>\n",
485 |        "      <td>94.000000</td>\n",
486 |        "    </tr>\n",
487 |        "    <tr>\n",
488 |        "      <th>996</th>\n",
489 |        "      <td>male</td>\n",
490 |        "      <td>group C</td>\n",
491 |        "      <td>high school</td>\n",
492 |        "      <td>free/reduced</td>\n",
493 |        "      <td>none</td>\n",
494 |        "      <td>62</td>\n",
495 |        "      <td>55</td>\n",
496 |        "      <td>55</td>\n",
497 |        "      <td>57.333333</td>\n",
498 |        "    </tr>\n",
499 |        "    <tr>\n",
500 |        "      <th>997</th>\n",
501 |        "      <td>female</td>\n",
502 |        "      <td>group C</td>\n",
503 |        "      <td>high school</td>\n",
504 |        "      <td>free/reduced</td>\n",
505 |        "      <td>completed</td>\n",
506 |        "      <td>59</td>\n",
507 |        "      <td>71</td>\n",
508 |        "      <td>65</td>\n",
509 |        "      <td>65.000000</td>\n",
510 |        "    </tr>\n",
511 |        "    <tr>\n",
512 |        "      <th>998</th>\n",
513 |        "      <td>female</td>\n",
514 |        "      <td>group D</td>\n",
515 |        "      <td>some college</td>\n",
516 |        "      <td>standard</td>\n",
517 |        "      <td>completed</td>\n",
518 |        "      <td>68</td>\n",
519 |        "      <td>78</td>\n",
520 |        "      <td>77</td>\n",
521 |        "      <td>74.333333</td>\n",
522 |        "    </tr>\n",
523 |        "    <tr>\n",
524 |        "      <th>999</th>\n",
525 |        "      <td>female</td>\n",
526 |        "      <td>group D</td>\n",
527 |        "      <td>some college</td>\n",
528 |        "      <td>free/reduced</td>\n",
529 |        "      <td>none</td>\n",
530 |        "      <td>77</td>\n",
531 |        "      <td>86</td>\n",
532 |        "      <td>86</td>\n",
533 |        "      <td>83.000000</td>\n",
534 |        "    </tr>\n",
535 |        "  </tbody>\n",
536 |        "</table>\n",
537 |        "<p>1000 rows × 9 columns</p>\n",
538 |        "</div>"
539 |       ],
540 |       "text/plain": [
541 |        "     gender race/ethnicity parental level of education         lunch  \\\n",
542 |        "0    female        group B           bachelor's degree      standard   \n",
543 |        "1    female        group C                some college      standard   \n",
544 |        "2    female        group B             master's degree      standard   \n",
545 |        "3      male        group A          associate's degree  free/reduced   \n",
546 |        "4      male        group C                some college      standard   \n",
547 |        "..      ...            ...                         ...           ...   \n",
548 |        "995  female        group E             master's degree      standard   \n",
549 |        "996    male        group C                 high school  free/reduced   \n",
550 |        "997  female        group C                 high school  free/reduced   \n",
551 |        "998  female        group D                some college      standard   \n",
552 |        "999  female        group D                some college  free/reduced   \n",
553 |        "\n",
554 |        "    test preparation course  math score  reading score  writing score  \\\n",
555 |        "0                      none          72             72             74   \n",
556 |        "1                 completed          69             90             88   \n",
557 |        "2                      none          90             95             93   \n",
558 |        "3                      none          47             57             44   \n",
559 |        "4                      none          76             78             75   \n",
560 |        "..                      ...         ...            ...            ...   \n",
561 |        "995               completed          88             99             95   \n",
562 |        "996                    none          62             55             55   \n",
563 |        "997               completed          59             71             65   \n",
564 |        "998               completed          68             78             77   \n",
565 |        "999                    none          77             86             86   \n",
566 |        "\n",
567 |        "       average  \n",
568 |        "0    72.666667  \n",
569 |        "1    82.333333  \n",
570 |        "2    92.666667  \n",
571 |        "3    49.333333  \n",
572 |        "4    76.333333  \n",
573 |        "..         ...  \n",
574 |        "995  94.000000  \n",
575 |        "996  57.333333  \n",
576 |        "997  65.000000  \n",
577 |        "998  74.333333  \n",
578 |        "999  83.000000  \n",
579 |        "\n",
580 |        "[1000 rows x 9 columns]"
581 |       ]
582 |      },
583 |      "execution_count": 8,
584 |      "metadata": {},
585 |      "output_type": "execute_result"
586 |     }
587 |    ],
588 |    "source": [
589 |     "# showing the dataframe\n",
590 |     "df_exams"
591 |    ]
592 |   }
593 |  ],
594 |  "metadata": {
595 |   "kernelspec": {
596 |    "display_name": "Python 3",
597 |    "language": "python",
598 |    "name": "python3"
599 |   },
600 |   "language_info": {
601 |    "codemirror_mode": {
602 |     "name": "ipython",
603 |     "version": 3
604 |    },
605 |    "file_extension": ".py",
606 |    "mimetype": "text/x-python",
607 |    "name": "python",
608 |    "nbconvert_exporter": "python",
609 |    "pygments_lexer": "ipython3",
610 |    "version": "3.8.8"
611 |   },
612 |   "toc": {
613 |    "base_numbering": 1,
614 |    "nav_menu": {},
615 |    "number_sections": true,
616 |    "sideBar": true,
617 |    "skip_h1_title": false,
618 |    "title_cell": "Table of Contents",
619 |    "title_sidebar": "Contents",
620 |    "toc_cell": false,
621 |    "toc_position": {},
622 |    "toc_section_display": true,
623 |    "toc_window_display": false
624 |   }
625 |  },
626 |  "nbformat": 4,
627 |  "nbformat_minor": 5
628 | }
629 | 


--------------------------------------------------------------------------------
/2.Intro to Pandas/8.The value_counts() method.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 1,
  6 |    "id": "4e3fdade",
  7 |    "metadata": {},
  8 |    "outputs": [],
  9 |    "source": [
 10 |     "import pandas as pd"
 11 |    ]
 12 |   },
 13 |   {
 14 |    "cell_type": "code",
 15 |    "execution_count": 2,
 16 |    "id": "9dfaf0d2",
 17 |    "metadata": {},
 18 |    "outputs": [
 19 |     {
 20 |      "data": {
 21 |       "text/html": [
 22 |        "<div>\n",
 23 |        "<style scoped>\n",
 24 |        "    .dataframe tbody tr th:only-of-type {\n",
 25 |        "        vertical-align: middle;\n",
 26 |        "    }\n",
 27 |        "\n",
 28 |        "    .dataframe tbody tr th {\n",
 29 |        "        vertical-align: top;\n",
 30 |        "    }\n",
 31 |        "\n",
 32 |        "    .dataframe thead th {\n",
 33 |        "        text-align: right;\n",
 34 |        "    }\n",
 35 |        "</style>\n",
 36 |        "<table border=\"1\" class=\"dataframe\">\n",
 37 |        "  <thead>\n",
 38 |        "    <tr style=\"text-align: right;\">\n",
 39 |        "      <th></th>\n",
 40 |        "      <th>gender</th>\n",
 41 |        "      <th>race/ethnicity</th>\n",
 42 |        "      <th>parental level of education</th>\n",
 43 |        "      <th>lunch</th>\n",
 44 |        "      <th>test preparation course</th>\n",
 45 |        "      <th>math score</th>\n",
 46 |        "      <th>reading score</th>\n",
 47 |        "      <th>writing score</th>\n",
 48 |        "    </tr>\n",
 49 |        "  </thead>\n",
 50 |        "  <tbody>\n",
 51 |        "    <tr>\n",
 52 |        "      <th>0</th>\n",
 53 |        "      <td>female</td>\n",
 54 |        "      <td>group B</td>\n",
 55 |        "      <td>bachelor's degree</td>\n",
 56 |        "      <td>standard</td>\n",
 57 |        "      <td>none</td>\n",
 58 |        "      <td>72</td>\n",
 59 |        "      <td>72</td>\n",
 60 |        "      <td>74</td>\n",
 61 |        "    </tr>\n",
 62 |        "    <tr>\n",
 63 |        "      <th>1</th>\n",
 64 |        "      <td>female</td>\n",
 65 |        "      <td>group C</td>\n",
 66 |        "      <td>some college</td>\n",
 67 |        "      <td>standard</td>\n",
 68 |        "      <td>completed</td>\n",
 69 |        "      <td>69</td>\n",
 70 |        "      <td>90</td>\n",
 71 |        "      <td>88</td>\n",
 72 |        "    </tr>\n",
 73 |        "    <tr>\n",
 74 |        "      <th>2</th>\n",
 75 |        "      <td>female</td>\n",
 76 |        "      <td>group B</td>\n",
 77 |        "      <td>master's degree</td>\n",
 78 |        "      <td>standard</td>\n",
 79 |        "      <td>none</td>\n",
 80 |        "      <td>90</td>\n",
 81 |        "      <td>95</td>\n",
 82 |        "      <td>93</td>\n",
 83 |        "    </tr>\n",
 84 |        "    <tr>\n",
 85 |        "      <th>3</th>\n",
 86 |        "      <td>male</td>\n",
 87 |        "      <td>group A</td>\n",
 88 |        "      <td>associate's degree</td>\n",
 89 |        "      <td>free/reduced</td>\n",
 90 |        "      <td>none</td>\n",
 91 |        "      <td>47</td>\n",
 92 |        "      <td>57</td>\n",
 93 |        "      <td>44</td>\n",
 94 |        "    </tr>\n",
 95 |        "    <tr>\n",
 96 |        "      <th>4</th>\n",
 97 |        "      <td>male</td>\n",
 98 |        "      <td>group C</td>\n",
 99 |        "      <td>some college</td>\n",
100 |        "      <td>standard</td>\n",
101 |        "      <td>none</td>\n",
102 |        "      <td>76</td>\n",
103 |        "      <td>78</td>\n",
104 |        "      <td>75</td>\n",
105 |        "    </tr>\n",
106 |        "  </tbody>\n",
107 |        "</table>\n",
108 |        "</div>"
109 |       ],
110 |       "text/plain": [
111 |        "   gender race/ethnicity parental level of education         lunch  \\\n",
112 |        "0  female        group B           bachelor's degree      standard   \n",
113 |        "1  female        group C                some college      standard   \n",
114 |        "2  female        group B             master's degree      standard   \n",
115 |        "3    male        group A          associate's degree  free/reduced   \n",
116 |        "4    male        group C                some college      standard   \n",
117 |        "\n",
118 |        "  test preparation course  math score  reading score  writing score  \n",
119 |        "0                    none          72             72             74  \n",
120 |        "1               completed          69             90             88  \n",
121 |        "2                    none          90             95             93  \n",
122 |        "3                    none          47             57             44  \n",
123 |        "4                    none          76             78             75  "
124 |       ]
125 |      },
126 |      "execution_count": 2,
127 |      "metadata": {},
128 |      "output_type": "execute_result"
129 |     }
130 |    ],
131 |    "source": [
132 |     "# reading the csv file\n",
133 |     "df_exams = pd.read_csv('StudentsPerformance.csv')\n",
134 |     "df_exams.head()"
135 |    ]
136 |   },
137 |   {
138 |    "cell_type": "markdown",
139 |    "id": "9a47f15a",
140 |    "metadata": {},
141 |    "source": [
142 |     "# Value Counts"
143 |    ]
144 |   },
145 |   {
146 |    "cell_type": "code",
147 |    "execution_count": 3,
148 |    "id": "e04ff454",
149 |    "metadata": {},
150 |    "outputs": [
151 |     {
152 |      "data": {
153 |       "text/plain": [
154 |        "1000"
155 |       ]
156 |      },
157 |      "execution_count": 3,
158 |      "metadata": {},
159 |      "output_type": "execute_result"
160 |     }
161 |    ],
162 |    "source": [
163 |     "# counting gender elements\n",
164 |     "\n",
165 |     "# len function\n",
166 |     "len(df_exams['gender'])\n",
167 |     "# .count() method\n",
168 |     "df_exams['gender'].count()"
169 |    ]
170 |   },
171 |   {
172 |    "cell_type": "code",
173 |    "execution_count": 4,
174 |    "id": "07ab6370",
175 |    "metadata": {},
176 |    "outputs": [
177 |     {
178 |      "data": {
179 |       "text/plain": [
180 |        "female    518\n",
181 |        "male      482\n",
182 |        "Name: gender, dtype: int64"
183 |       ]
184 |      },
185 |      "execution_count": 4,
186 |      "metadata": {},
187 |      "output_type": "execute_result"
188 |     }
189 |    ],
190 |    "source": [
191 |     "# counting gender elements by category\n",
192 |     "df_exams['gender'].value_counts()"
193 |    ]
194 |   },
195 |   {
196 |    "cell_type": "code",
197 |    "execution_count": 5,
198 |    "id": "e4f100a9",
199 |    "metadata": {},
200 |    "outputs": [
201 |     {
202 |      "data": {
203 |       "text/plain": [
204 |        "female    0.518\n",
205 |        "male      0.482\n",
206 |        "Name: gender, dtype: float64"
207 |       ]
208 |      },
209 |      "execution_count": 5,
210 |      "metadata": {},
211 |      "output_type": "execute_result"
212 |     }
213 |    ],
214 |    "source": [
215 |     "# return the relative frequency (divide all values by the sum of values)\n",
216 |     "df_exams['gender'].value_counts(normalize=True)"
217 |    ]
218 |   },
219 |   {
220 |    "cell_type": "code",
221 |    "execution_count": 6,
222 |    "id": "620d6e12",
223 |    "metadata": {},
224 |    "outputs": [
225 |     {
226 |      "data": {
227 |       "text/plain": [
228 |        "some college          226\n",
229 |        "associate's degree    222\n",
230 |        "high school           196\n",
231 |        "some high school      179\n",
232 |        "bachelor's degree     118\n",
233 |        "master's degree        59\n",
234 |        "Name: parental level of education, dtype: int64"
235 |       ]
236 |      },
237 |      "execution_count": 6,
238 |      "metadata": {},
239 |      "output_type": "execute_result"
240 |     }
241 |    ],
242 |    "source": [
243 |     "# counting \"parental level of education\" elements by category\n",
244 |     "df_exams['parental level of education'].value_counts()"
245 |    ]
246 |   },
247 |   {
248 |    "cell_type": "code",
249 |    "execution_count": 7,
250 |    "id": "43ce51e7",
251 |    "metadata": {},
252 |    "outputs": [
253 |     {
254 |      "data": {
255 |       "text/plain": [
256 |        "some college          0.23\n",
257 |        "associate's degree    0.22\n",
258 |        "high school           0.20\n",
259 |        "some high school      0.18\n",
260 |        "bachelor's degree     0.12\n",
261 |        "master's degree       0.06\n",
262 |        "Name: parental level of education, dtype: float64"
263 |       ]
264 |      },
265 |      "execution_count": 7,
266 |      "metadata": {},
267 |      "output_type": "execute_result"
268 |     }
269 |    ],
270 |    "source": [
271 |     "# return the relative frequency and round to 2 decimals\n",
272 |     "df_exams['parental level of education'].value_counts(normalize=True).round(2)"
273 |    ]
274 |   }
275 |  ],
276 |  "metadata": {
277 |   "kernelspec": {
278 |    "display_name": "Python 3",
279 |    "language": "python",
280 |    "name": "python3"
281 |   },
282 |   "language_info": {
283 |    "codemirror_mode": {
284 |     "name": "ipython",
285 |     "version": 3
286 |    },
287 |    "file_extension": ".py",
288 |    "mimetype": "text/x-python",
289 |    "name": "python",
290 |    "nbconvert_exporter": "python",
291 |    "pygments_lexer": "ipython3",
292 |    "version": "3.8.8"
293 |   },
294 |   "toc": {
295 |    "base_numbering": 1,
296 |    "nav_menu": {},
297 |    "number_sections": true,
298 |    "sideBar": true,
299 |    "skip_h1_title": false,
300 |    "title_cell": "Table of Contents",
301 |    "title_sidebar": "Contents",
302 |    "toc_cell": false,
303 |    "toc_position": {},
304 |    "toc_section_display": true,
305 |    "toc_window_display": false
306 |   }
307 |  },
308 |  "nbformat": 4,
309 |  "nbformat_minor": 5
310 | }
311 | 


--------------------------------------------------------------------------------
/3.Pivot Table/gdp.csv:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/thepycoach/python-course-for-excel-users/a0c109d8f092b15cde0209a18f67de35cab45c87/3.Pivot Table/gdp.csv


--------------------------------------------------------------------------------
/3.Pivot Table/supermarket_sales.xlsx:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/thepycoach/python-course-for-excel-users/a0c109d8f092b15cde0209a18f67de35cab45c87/3.Pivot Table/supermarket_sales.xlsx


--------------------------------------------------------------------------------
/4.Data Visualization/1.Dataset Overview and Making Pivot Table.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 1,
  6 |    "id": "270bafb9",
  7 |    "metadata": {},
  8 |    "outputs": [],
  9 |    "source": [
 10 |     "import pandas as pd"
 11 |    ]
 12 |   },
 13 |   {
 14 |    "cell_type": "code",
 15 |    "execution_count": 2,
 16 |    "id": "47fc4e0d",
 17 |    "metadata": {},
 18 |    "outputs": [],
 19 |    "source": [
 20 |     "# reading the csv file\n",
 21 |     "df_population_raw = pd.read_csv('population_total.csv')"
 22 |    ]
 23 |   },
 24 |   {
 25 |    "cell_type": "code",
 26 |    "execution_count": 3,
 27 |    "id": "d44cbeb9",
 28 |    "metadata": {
 29 |     "scrolled": false
 30 |    },
 31 |    "outputs": [
 32 |     {
 33 |      "data": {
 34 |       "text/html": [
 35 |        "<div>\n",
 36 |        "<style scoped>\n",
 37 |        "    .dataframe tbody tr th:only-of-type {\n",
 38 |        "        vertical-align: middle;\n",
 39 |        "    }\n",
 40 |        "\n",
 41 |        "    .dataframe tbody tr th {\n",
 42 |        "        vertical-align: top;\n",
 43 |        "    }\n",
 44 |        "\n",
 45 |        "    .dataframe thead th {\n",
 46 |        "        text-align: right;\n",
 47 |        "    }\n",
 48 |        "</style>\n",
 49 |        "<table border=\"1\" class=\"dataframe\">\n",
 50 |        "  <thead>\n",
 51 |        "    <tr style=\"text-align: right;\">\n",
 52 |        "      <th></th>\n",
 53 |        "      <th>country</th>\n",
 54 |        "      <th>year</th>\n",
 55 |        "      <th>population</th>\n",
 56 |        "    </tr>\n",
 57 |        "  </thead>\n",
 58 |        "  <tbody>\n",
 59 |        "    <tr>\n",
 60 |        "      <th>0</th>\n",
 61 |        "      <td>China</td>\n",
 62 |        "      <td>2020.0</td>\n",
 63 |        "      <td>1.439324e+09</td>\n",
 64 |        "    </tr>\n",
 65 |        "    <tr>\n",
 66 |        "      <th>1</th>\n",
 67 |        "      <td>China</td>\n",
 68 |        "      <td>2019.0</td>\n",
 69 |        "      <td>1.433784e+09</td>\n",
 70 |        "    </tr>\n",
 71 |        "    <tr>\n",
 72 |        "      <th>2</th>\n",
 73 |        "      <td>China</td>\n",
 74 |        "      <td>2018.0</td>\n",
 75 |        "      <td>1.427648e+09</td>\n",
 76 |        "    </tr>\n",
 77 |        "    <tr>\n",
 78 |        "      <th>3</th>\n",
 79 |        "      <td>China</td>\n",
 80 |        "      <td>2017.0</td>\n",
 81 |        "      <td>1.421022e+09</td>\n",
 82 |        "    </tr>\n",
 83 |        "    <tr>\n",
 84 |        "      <th>4</th>\n",
 85 |        "      <td>China</td>\n",
 86 |        "      <td>2016.0</td>\n",
 87 |        "      <td>1.414049e+09</td>\n",
 88 |        "    </tr>\n",
 89 |        "    <tr>\n",
 90 |        "      <th>...</th>\n",
 91 |        "      <td>...</td>\n",
 92 |        "      <td>...</td>\n",
 93 |        "      <td>...</td>\n",
 94 |        "    </tr>\n",
 95 |        "    <tr>\n",
 96 |        "      <th>4180</th>\n",
 97 |        "      <td>United States</td>\n",
 98 |        "      <td>1965.0</td>\n",
 99 |        "      <td>1.997337e+08</td>\n",
100 |        "    </tr>\n",
101 |        "    <tr>\n",
102 |        "      <th>4181</th>\n",
103 |        "      <td>United States</td>\n",
104 |        "      <td>1960.0</td>\n",
105 |        "      <td>1.867206e+08</td>\n",
106 |        "    </tr>\n",
107 |        "    <tr>\n",
108 |        "      <th>4182</th>\n",
109 |        "      <td>United States</td>\n",
110 |        "      <td>1955.0</td>\n",
111 |        "      <td>1.716853e+08</td>\n",
112 |        "    </tr>\n",
113 |        "    <tr>\n",
114 |        "      <th>4183</th>\n",
115 |        "      <td>India</td>\n",
116 |        "      <td>1960.0</td>\n",
117 |        "      <td>4.505477e+08</td>\n",
118 |        "    </tr>\n",
119 |        "    <tr>\n",
120 |        "      <th>4184</th>\n",
121 |        "      <td>India</td>\n",
122 |        "      <td>1955.0</td>\n",
123 |        "      <td>4.098806e+08</td>\n",
124 |        "    </tr>\n",
125 |        "  </tbody>\n",
126 |        "</table>\n",
127 |        "<p>4185 rows × 3 columns</p>\n",
128 |        "</div>"
129 |       ],
130 |       "text/plain": [
131 |        "            country    year    population\n",
132 |        "0             China  2020.0  1.439324e+09\n",
133 |        "1             China  2019.0  1.433784e+09\n",
134 |        "2             China  2018.0  1.427648e+09\n",
135 |        "3             China  2017.0  1.421022e+09\n",
136 |        "4             China  2016.0  1.414049e+09\n",
137 |        "...             ...     ...           ...\n",
138 |        "4180  United States  1965.0  1.997337e+08\n",
139 |        "4181  United States  1960.0  1.867206e+08\n",
140 |        "4182  United States  1955.0  1.716853e+08\n",
141 |        "4183          India  1960.0  4.505477e+08\n",
142 |        "4184          India  1955.0  4.098806e+08\n",
143 |        "\n",
144 |        "[4185 rows x 3 columns]"
145 |       ]
146 |      },
147 |      "execution_count": 3,
148 |      "metadata": {},
149 |      "output_type": "execute_result"
150 |     }
151 |    ],
152 |    "source": [
153 |     "# first look at the dataset\n",
154 |     "df_population_raw"
155 |    ]
156 |   },
157 |   {
158 |    "cell_type": "markdown",
159 |    "id": "ec86a50f",
160 |    "metadata": {},
161 |    "source": [
162 |     "# Making a Pivot Table"
163 |    ]
164 |   },
165 |   {
166 |    "cell_type": "markdown",
167 |    "id": "1450c112",
168 |    "metadata": {},
169 |    "source": [
170 |     ".pivot(): Returns reshaped DataFrame organized by given index / column values (\"pivot without aggregation\")"
171 |    ]
172 |   },
173 |   {
174 |    "cell_type": "code",
175 |    "execution_count": 4,
176 |    "id": "4d01f725",
177 |    "metadata": {},
178 |    "outputs": [],
179 |    "source": [
180 |     "# dropping null values\n",
181 |     "df_population_raw.dropna(inplace=True)"
182 |    ]
183 |   },
184 |   {
185 |    "cell_type": "code",
186 |    "execution_count": 5,
187 |    "id": "aeb60686",
188 |    "metadata": {},
189 |    "outputs": [],
190 |    "source": [
191 |     "# making a pivot table\n",
192 |     "df_pivot = df_population_raw.pivot(index='year', columns='country',\n",
193 |     "                                        values='population')"
194 |    ]
195 |   },
196 |   {
197 |    "cell_type": "code",
198 |    "execution_count": 6,
199 |    "id": "918dc0db",
200 |    "metadata": {},
201 |    "outputs": [],
202 |    "source": [
203 |     "# selecting some countries\n",
204 |     "df_pivot = df_pivot[['United States', 'India', 'China', \n",
205 |     "                          'Indonesia', 'Brazil']]"
206 |    ]
207 |   },
208 |   {
209 |    "cell_type": "code",
210 |    "execution_count": 7,
211 |    "id": "d8c76de7",
212 |    "metadata": {
213 |     "scrolled": false
214 |    },
215 |    "outputs": [
216 |     {
217 |      "data": {
218 |       "text/html": [
219 |        "<div>\n",
220 |        "<style scoped>\n",
221 |        "    .dataframe tbody tr th:only-of-type {\n",
222 |        "        vertical-align: middle;\n",
223 |        "    }\n",
224 |        "\n",
225 |        "    .dataframe tbody tr th {\n",
226 |        "        vertical-align: top;\n",
227 |        "    }\n",
228 |        "\n",
229 |        "    .dataframe thead th {\n",
230 |        "        text-align: right;\n",
231 |        "    }\n",
232 |        "</style>\n",
233 |        "<table border=\"1\" class=\"dataframe\">\n",
234 |        "  <thead>\n",
235 |        "    <tr style=\"text-align: right;\">\n",
236 |        "      <th>country</th>\n",
237 |        "      <th>United States</th>\n",
238 |        "      <th>India</th>\n",
239 |        "      <th>China</th>\n",
240 |        "      <th>Indonesia</th>\n",
241 |        "      <th>Brazil</th>\n",
242 |        "    </tr>\n",
243 |        "    <tr>\n",
244 |        "      <th>year</th>\n",
245 |        "      <th></th>\n",
246 |        "      <th></th>\n",
247 |        "      <th></th>\n",
248 |        "      <th></th>\n",
249 |        "      <th></th>\n",
250 |        "    </tr>\n",
251 |        "  </thead>\n",
252 |        "  <tbody>\n",
253 |        "    <tr>\n",
254 |        "      <th>1955.0</th>\n",
255 |        "      <td>171685336.0</td>\n",
256 |        "      <td>4.098806e+08</td>\n",
257 |        "      <td>6.122416e+08</td>\n",
258 |        "      <td>77273425.0</td>\n",
259 |        "      <td>62533919.0</td>\n",
260 |        "    </tr>\n",
261 |        "    <tr>\n",
262 |        "      <th>1960.0</th>\n",
263 |        "      <td>186720571.0</td>\n",
264 |        "      <td>4.505477e+08</td>\n",
265 |        "      <td>6.604081e+08</td>\n",
266 |        "      <td>87751068.0</td>\n",
267 |        "      <td>72179226.0</td>\n",
268 |        "    </tr>\n",
269 |        "    <tr>\n",
270 |        "      <th>1965.0</th>\n",
271 |        "      <td>199733676.0</td>\n",
272 |        "      <td>4.991233e+08</td>\n",
273 |        "      <td>7.242190e+08</td>\n",
274 |        "      <td>100267062.0</td>\n",
275 |        "      <td>83373530.0</td>\n",
276 |        "    </tr>\n",
277 |        "    <tr>\n",
278 |        "      <th>1970.0</th>\n",
279 |        "      <td>209513341.0</td>\n",
280 |        "      <td>5.551898e+08</td>\n",
281 |        "      <td>8.276014e+08</td>\n",
282 |        "      <td>114793178.0</td>\n",
283 |        "      <td>95113265.0</td>\n",
284 |        "    </tr>\n",
285 |        "    <tr>\n",
286 |        "      <th>1975.0</th>\n",
287 |        "      <td>219081251.0</td>\n",
288 |        "      <td>6.231029e+08</td>\n",
289 |        "      <td>9.262409e+08</td>\n",
290 |        "      <td>130680727.0</td>\n",
291 |        "      <td>107216205.0</td>\n",
292 |        "    </tr>\n",
293 |        "    <tr>\n",
294 |        "      <th>1980.0</th>\n",
295 |        "      <td>229476354.0</td>\n",
296 |        "      <td>6.989528e+08</td>\n",
297 |        "      <td>1.000089e+09</td>\n",
298 |        "      <td>147447836.0</td>\n",
299 |        "      <td>120694009.0</td>\n",
300 |        "    </tr>\n",
301 |        "    <tr>\n",
302 |        "      <th>1985.0</th>\n",
303 |        "      <td>240499825.0</td>\n",
304 |        "      <td>7.843600e+08</td>\n",
305 |        "      <td>1.075589e+09</td>\n",
306 |        "      <td>164982451.0</td>\n",
307 |        "      <td>135274080.0</td>\n",
308 |        "    </tr>\n",
309 |        "    <tr>\n",
310 |        "      <th>1990.0</th>\n",
311 |        "      <td>252120309.0</td>\n",
312 |        "      <td>8.732778e+08</td>\n",
313 |        "      <td>1.176884e+09</td>\n",
314 |        "      <td>181413402.0</td>\n",
315 |        "      <td>149003223.0</td>\n",
316 |        "    </tr>\n",
317 |        "    <tr>\n",
318 |        "      <th>1995.0</th>\n",
319 |        "      <td>265163745.0</td>\n",
320 |        "      <td>9.639226e+08</td>\n",
321 |        "      <td>1.240921e+09</td>\n",
322 |        "      <td>196934260.0</td>\n",
323 |        "      <td>162019896.0</td>\n",
324 |        "    </tr>\n",
325 |        "    <tr>\n",
326 |        "      <th>2000.0</th>\n",
327 |        "      <td>281710909.0</td>\n",
328 |        "      <td>1.056576e+09</td>\n",
329 |        "      <td>1.290551e+09</td>\n",
330 |        "      <td>211513823.0</td>\n",
331 |        "      <td>174790340.0</td>\n",
332 |        "    </tr>\n",
333 |        "    <tr>\n",
334 |        "      <th>2005.0</th>\n",
335 |        "      <td>294993511.0</td>\n",
336 |        "      <td>1.147610e+09</td>\n",
337 |        "      <td>1.330776e+09</td>\n",
338 |        "      <td>226289470.0</td>\n",
339 |        "      <td>186127103.0</td>\n",
340 |        "    </tr>\n",
341 |        "    <tr>\n",
342 |        "      <th>2010.0</th>\n",
343 |        "      <td>309011475.0</td>\n",
344 |        "      <td>1.234281e+09</td>\n",
345 |        "      <td>1.368811e+09</td>\n",
346 |        "      <td>241834215.0</td>\n",
347 |        "      <td>195713635.0</td>\n",
348 |        "    </tr>\n",
349 |        "    <tr>\n",
350 |        "      <th>2015.0</th>\n",
351 |        "      <td>320878310.0</td>\n",
352 |        "      <td>1.310152e+09</td>\n",
353 |        "      <td>1.406848e+09</td>\n",
354 |        "      <td>258383256.0</td>\n",
355 |        "      <td>204471769.0</td>\n",
356 |        "    </tr>\n",
357 |        "    <tr>\n",
358 |        "      <th>2016.0</th>\n",
359 |        "      <td>323015995.0</td>\n",
360 |        "      <td>1.324517e+09</td>\n",
361 |        "      <td>1.414049e+09</td>\n",
362 |        "      <td>261556381.0</td>\n",
363 |        "      <td>206163053.0</td>\n",
364 |        "    </tr>\n",
365 |        "    <tr>\n",
366 |        "      <th>2017.0</th>\n",
367 |        "      <td>325084756.0</td>\n",
368 |        "      <td>1.338677e+09</td>\n",
369 |        "      <td>1.421022e+09</td>\n",
370 |        "      <td>264650963.0</td>\n",
371 |        "      <td>207833823.0</td>\n",
372 |        "    </tr>\n",
373 |        "    <tr>\n",
374 |        "      <th>2018.0</th>\n",
375 |        "      <td>327096265.0</td>\n",
376 |        "      <td>1.352642e+09</td>\n",
377 |        "      <td>1.427648e+09</td>\n",
378 |        "      <td>267670543.0</td>\n",
379 |        "      <td>209469323.0</td>\n",
380 |        "    </tr>\n",
381 |        "    <tr>\n",
382 |        "      <th>2019.0</th>\n",
383 |        "      <td>329064917.0</td>\n",
384 |        "      <td>1.366418e+09</td>\n",
385 |        "      <td>1.433784e+09</td>\n",
386 |        "      <td>270625568.0</td>\n",
387 |        "      <td>211049527.0</td>\n",
388 |        "    </tr>\n",
389 |        "    <tr>\n",
390 |        "      <th>2020.0</th>\n",
391 |        "      <td>331002651.0</td>\n",
392 |        "      <td>1.380004e+09</td>\n",
393 |        "      <td>1.439324e+09</td>\n",
394 |        "      <td>273523615.0</td>\n",
395 |        "      <td>212559417.0</td>\n",
396 |        "    </tr>\n",
397 |        "  </tbody>\n",
398 |        "</table>\n",
399 |        "</div>"
400 |       ],
401 |       "text/plain": [
402 |        "country  United States         India         China    Indonesia       Brazil\n",
403 |        "year                                                                        \n",
404 |        "1955.0     171685336.0  4.098806e+08  6.122416e+08   77273425.0   62533919.0\n",
405 |        "1960.0     186720571.0  4.505477e+08  6.604081e+08   87751068.0   72179226.0\n",
406 |        "1965.0     199733676.0  4.991233e+08  7.242190e+08  100267062.0   83373530.0\n",
407 |        "1970.0     209513341.0  5.551898e+08  8.276014e+08  114793178.0   95113265.0\n",
408 |        "1975.0     219081251.0  6.231029e+08  9.262409e+08  130680727.0  107216205.0\n",
409 |        "1980.0     229476354.0  6.989528e+08  1.000089e+09  147447836.0  120694009.0\n",
410 |        "1985.0     240499825.0  7.843600e+08  1.075589e+09  164982451.0  135274080.0\n",
411 |        "1990.0     252120309.0  8.732778e+08  1.176884e+09  181413402.0  149003223.0\n",
412 |        "1995.0     265163745.0  9.639226e+08  1.240921e+09  196934260.0  162019896.0\n",
413 |        "2000.0     281710909.0  1.056576e+09  1.290551e+09  211513823.0  174790340.0\n",
414 |        "2005.0     294993511.0  1.147610e+09  1.330776e+09  226289470.0  186127103.0\n",
415 |        "2010.0     309011475.0  1.234281e+09  1.368811e+09  241834215.0  195713635.0\n",
416 |        "2015.0     320878310.0  1.310152e+09  1.406848e+09  258383256.0  204471769.0\n",
417 |        "2016.0     323015995.0  1.324517e+09  1.414049e+09  261556381.0  206163053.0\n",
418 |        "2017.0     325084756.0  1.338677e+09  1.421022e+09  264650963.0  207833823.0\n",
419 |        "2018.0     327096265.0  1.352642e+09  1.427648e+09  267670543.0  209469323.0\n",
420 |        "2019.0     329064917.0  1.366418e+09  1.433784e+09  270625568.0  211049527.0\n",
421 |        "2020.0     331002651.0  1.380004e+09  1.439324e+09  273523615.0  212559417.0"
422 |       ]
423 |      },
424 |      "execution_count": 7,
425 |      "metadata": {},
426 |      "output_type": "execute_result"
427 |     }
428 |    ],
429 |    "source": [
430 |     "# showing pivot table\n",
431 |     "df_pivot"
432 |    ]
433 |   }
434 |  ],
435 |  "metadata": {
436 |   "kernelspec": {
437 |    "display_name": "Python 3",
438 |    "language": "python",
439 |    "name": "python3"
440 |   },
441 |   "language_info": {
442 |    "codemirror_mode": {
443 |     "name": "ipython",
444 |     "version": 3
445 |    },
446 |    "file_extension": ".py",
447 |    "mimetype": "text/x-python",
448 |    "name": "python",
449 |    "nbconvert_exporter": "python",
450 |    "pygments_lexer": "ipython3",
451 |    "version": "3.8.8"
452 |   },
453 |   "toc": {
454 |    "base_numbering": 1,
455 |    "nav_menu": {},
456 |    "number_sections": true,
457 |    "sideBar": true,
458 |    "skip_h1_title": false,
459 |    "title_cell": "Table of Contents",
460 |    "title_sidebar": "Contents",
461 |    "toc_cell": false,
462 |    "toc_position": {},
463 |    "toc_section_display": true,
464 |    "toc_window_display": false
465 |   }
466 |  },
467 |  "nbformat": 4,
468 |  "nbformat_minor": 5
469 | }
470 | 


--------------------------------------------------------------------------------
/Exercises/Intro to Pandas/Introduction to Pandas-Exercise.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": null,
  6 |    "id": "2bac431d",
  7 |    "metadata": {},
  8 |    "outputs": [],
  9 |    "source": [
 10 |     "# import pandas\n",
 11 |     "import pandas as pd"
 12 |    ]
 13 |   },
 14 |   {
 15 |    "cell_type": "code",
 16 |    "execution_count": null,
 17 |    "id": "730ef2aa",
 18 |    "metadata": {},
 19 |    "outputs": [],
 20 |    "source": [
 21 |     "# Optional: use the pd.set_option() to display all rows in a dataframe by default\n"
 22 |    ]
 23 |   },
 24 |   {
 25 |    "cell_type": "markdown",
 26 |    "id": "05c7ec54",
 27 |    "metadata": {},
 28 |    "source": [
 29 |     "# Create a DataFrame"
 30 |    ]
 31 |   },
 32 |   {
 33 |    "cell_type": "code",
 34 |    "execution_count": null,
 35 |    "id": "cfb39f8c",
 36 |    "metadata": {},
 37 |    "outputs": [],
 38 |    "source": [
 39 |     "# read the \"bestsellers with categories\" csv file (Dataset on Amazon's Top 50 bestselling books from 2009 to 2019.)\n"
 40 |    ]
 41 |   },
 42 |   {
 43 |    "cell_type": "code",
 44 |    "execution_count": null,
 45 |    "id": "618209c8",
 46 |    "metadata": {
 47 |     "scrolled": true
 48 |    },
 49 |    "outputs": [],
 50 |    "source": [
 51 |     "# get access to the shape attribute\n"
 52 |    ]
 53 |   },
 54 |   {
 55 |    "cell_type": "code",
 56 |    "execution_count": null,
 57 |    "id": "3acde70f",
 58 |    "metadata": {},
 59 |    "outputs": [],
 60 |    "source": [
 61 |     "# find the data types of each column\n"
 62 |    ]
 63 |   },
 64 |   {
 65 |    "cell_type": "markdown",
 66 |    "id": "7f15b10b",
 67 |    "metadata": {},
 68 |    "source": [
 69 |     "# Display a DataFrame"
 70 |    ]
 71 |   },
 72 |   {
 73 |    "cell_type": "code",
 74 |    "execution_count": null,
 75 |    "id": "ef6b8d45",
 76 |    "metadata": {
 77 |     "scrolled": true
 78 |    },
 79 |    "outputs": [],
 80 |    "source": [
 81 |     "# show first 5 rows in a dataframe\n"
 82 |    ]
 83 |   },
 84 |   {
 85 |    "cell_type": "code",
 86 |    "execution_count": null,
 87 |    "id": "a3da1b0a",
 88 |    "metadata": {},
 89 |    "outputs": [],
 90 |    "source": [
 91 |     "# describe basic statistics of the dataframe (mean, std, min, max)\n"
 92 |    ]
 93 |   },
 94 |   {
 95 |    "cell_type": "markdown",
 96 |    "id": "51f4d331",
 97 |    "metadata": {},
 98 |    "source": [
 99 |     "# Add a new Column with an array"
100 |    ]
101 |   },
102 |   {
103 |    "cell_type": "code",
104 |    "execution_count": null,
105 |    "id": "94c526df",
106 |    "metadata": {},
107 |    "outputs": [],
108 |    "source": [
109 |     "# Your task is to create a column named 'Critic Rating' that should have random integer numbers between 1 and 4\n",
110 |     "\n",
111 |     "# 1. import numpy and create 550 random integer numbers between 1 and 4\n",
112 |     "\n",
113 |     "# 2. add new 'Critic Rating' column to dataframe using the random numbers created\n",
114 |     "\n",
115 |     "\n",
116 |     "# Note the random numbers in this new 'Critic Rating' column will be different between your solution and mine, but we'll focus only on the code, in this section."
117 |    ]
118 |   },
119 |   {
120 |    "cell_type": "code",
121 |    "execution_count": null,
122 |    "id": "af7cec1e",
123 |    "metadata": {},
124 |    "outputs": [],
125 |    "source": [
126 |     "# show first 5 rows\n"
127 |    ]
128 |   },
129 |   {
130 |    "cell_type": "markdown",
131 |    "id": "822167f7",
132 |    "metadata": {},
133 |    "source": [
134 |     "# Basic Attributes, Methods and Functions"
135 |    ]
136 |   },
137 |   {
138 |    "cell_type": "code",
139 |    "execution_count": null,
140 |    "id": "3b8dfa8e",
141 |    "metadata": {},
142 |    "outputs": [],
143 |    "source": [
144 |     "# get access to the columns attribute\n"
145 |    ]
146 |   },
147 |   {
148 |    "cell_type": "markdown",
149 |    "id": "6fe2c5f5",
150 |    "metadata": {},
151 |    "source": [
152 |     "# Selecting Two or More Columns from a Dataframe"
153 |    ]
154 |   },
155 |   {
156 |    "cell_type": "code",
157 |    "execution_count": null,
158 |    "id": "1690dbfe",
159 |    "metadata": {},
160 |    "outputs": [],
161 |    "source": [
162 |     "# move the new 'Critic Rating' column between the columns \"User Rating\" and \"Reviews\" Then update the dataframe\n",
163 |     "\n",
164 |     "# Tip: Copy and paste the column names obtained with the columns attribute and then rearrange elements using [[]]\n"
165 |    ]
166 |   },
167 |   {
168 |    "cell_type": "code",
169 |    "execution_count": null,
170 |    "id": "4a294c74",
171 |    "metadata": {},
172 |    "outputs": [],
173 |    "source": [
174 |     "# show first 5 rows\n"
175 |    ]
176 |   },
177 |   {
178 |    "cell_type": "markdown",
179 |    "id": "fedaf280",
180 |    "metadata": {},
181 |    "source": [
182 |     "# Operations on Dataframes"
183 |    ]
184 |   },
185 |   {
186 |    "cell_type": "code",
187 |    "execution_count": null,
188 |    "id": "da1c2205",
189 |    "metadata": {},
190 |    "outputs": [],
191 |    "source": [
192 |     "# create a column named \"Average Rating\" by using the following formula: Average Rating = (User Rating + Critic Rating)/2\n"
193 |    ]
194 |   },
195 |   {
196 |    "cell_type": "code",
197 |    "execution_count": null,
198 |    "id": "ab6c226b",
199 |    "metadata": {},
200 |    "outputs": [],
201 |    "source": [
202 |     "# use the round function to round the values of the dataframe to 1 decimal and update the dataframe\n"
203 |    ]
204 |   },
205 |   {
206 |    "cell_type": "markdown",
207 |    "id": "5142f8af",
208 |    "metadata": {},
209 |    "source": [
210 |     "# Value Counts"
211 |    ]
212 |   },
213 |   {
214 |    "cell_type": "code",
215 |    "execution_count": null,
216 |    "id": "a3a1e3fc",
217 |    "metadata": {},
218 |    "outputs": [],
219 |    "source": [
220 |     "# count elements in \"Genre\" column by category and return the relative frequency \n"
221 |    ]
222 |   },
223 |   {
224 |    "cell_type": "markdown",
225 |    "id": "13ff41dd",
226 |    "metadata": {},
227 |    "source": [
228 |     "# Rename Columns"
229 |    ]
230 |   },
231 |   {
232 |    "cell_type": "code",
233 |    "execution_count": null,
234 |    "id": "f86a8194",
235 |    "metadata": {},
236 |    "outputs": [],
237 |    "source": [
238 |     "# rename columns \"User Rating,\" \"Critic Rating\" and \"Average Rating\" to \"UR,\" \"CR\" and \"AR\" then update the dataframe with the inplace paraneter\n"
239 |    ]
240 |   },
241 |   {
242 |    "cell_type": "code",
243 |    "execution_count": null,
244 |    "id": "3df4c15c",
245 |    "metadata": {},
246 |    "outputs": [],
247 |    "source": [
248 |     "# show first 5 rows\n"
249 |    ]
250 |   },
251 |   {
252 |    "cell_type": "code",
253 |    "execution_count": null,
254 |    "id": "474246ef",
255 |    "metadata": {},
256 |    "outputs": [],
257 |    "source": [
258 |     "# select only \"Name\", \"Author\", \"UR\", \"CR\", \"AR\" and \"Year\" columns and update dataframe\n"
259 |    ]
260 |   },
261 |   {
262 |    "cell_type": "markdown",
263 |    "id": "6c458cf9",
264 |    "metadata": {},
265 |    "source": [
266 |     "# Sort a dataframe"
267 |    ]
268 |   },
269 |   {
270 |    "cell_type": "code",
271 |    "execution_count": null,
272 |    "id": "50a7d2a8",
273 |    "metadata": {},
274 |    "outputs": [],
275 |    "source": [
276 |     "# sort the dataframe descending by \"UR\" and \"CR\"\n"
277 |    ]
278 |   }
279 |  ],
280 |  "metadata": {
281 |   "kernelspec": {
282 |    "display_name": "Python 3",
283 |    "language": "python",
284 |    "name": "python3"
285 |   },
286 |   "language_info": {
287 |    "codemirror_mode": {
288 |     "name": "ipython",
289 |     "version": 3
290 |    },
291 |    "file_extension": ".py",
292 |    "mimetype": "text/x-python",
293 |    "name": "python",
294 |    "nbconvert_exporter": "python",
295 |    "pygments_lexer": "ipython3",
296 |    "version": "3.8.8"
297 |   },
298 |   "toc": {
299 |    "base_numbering": 1,
300 |    "nav_menu": {},
301 |    "number_sections": true,
302 |    "sideBar": true,
303 |    "skip_h1_title": false,
304 |    "title_cell": "Table of Contents",
305 |    "title_sidebar": "Contents",
306 |    "toc_cell": false,
307 |    "toc_position": {},
308 |    "toc_section_display": true,
309 |    "toc_window_display": false
310 |   }
311 |  },
312 |  "nbformat": 4,
313 |  "nbformat_minor": 5
314 | }
315 | 


--------------------------------------------------------------------------------
/Exercises/Merging and Concatenating DataFrames/IMDb movies.csv.zip:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/thepycoach/python-course-for-excel-users/a0c109d8f092b15cde0209a18f67de35cab45c87/Exercises/Merging and Concatenating DataFrames/IMDb movies.csv.zip


--------------------------------------------------------------------------------
/Exercises/Merging and Concatenating DataFrames/IMDb ratings.csv.zip:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/thepycoach/python-course-for-excel-users/a0c109d8f092b15cde0209a18f67de35cab45c87/Exercises/Merging and Concatenating DataFrames/IMDb ratings.csv.zip


--------------------------------------------------------------------------------
/Exercises/Merging and Concatenating DataFrames/Merging and Concatenating DataFrames-Exercise.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": null,
  6 |    "id": "fad49839",
  7 |    "metadata": {},
  8 |    "outputs": [],
  9 |    "source": [
 10 |     "import pandas as pd"
 11 |    ]
 12 |   },
 13 |   {
 14 |    "cell_type": "code",
 15 |    "execution_count": null,
 16 |    "id": "09c6213f",
 17 |    "metadata": {},
 18 |    "outputs": [],
 19 |    "source": [
 20 |     "# read 'IMDb movies.csv' and 'IMDb ratings.csv'\n",
 21 |     "df_movies = pd.read_csv('IMDb movies.csv', low_memory=False)\n",
 22 |     "df_ratings = pd.read_csv('IMDb ratings.csv')"
 23 |    ]
 24 |   },
 25 |   {
 26 |    "cell_type": "code",
 27 |    "execution_count": null,
 28 |    "id": "d5670913",
 29 |    "metadata": {},
 30 |    "outputs": [],
 31 |    "source": [
 32 |     "# select columns\n",
 33 |     "df_movies = df_movies[['imdb_title_id', 'title', 'year',\n",
 34 |     "                       'genre', 'country']]\n",
 35 |     "\n",
 36 |     "df_ratings = df_ratings[['imdb_title_id', 'total_votes', 'mean_vote']]"
 37 |    ]
 38 |   },
 39 |   {
 40 |    "cell_type": "markdown",
 41 |    "id": "310fc4cc",
 42 |    "metadata": {},
 43 |    "source": [
 44 |     "# merge()"
 45 |    ]
 46 |   },
 47 |   {
 48 |    "cell_type": "markdown",
 49 |    "id": "de4aa87a",
 50 |    "metadata": {},
 51 |    "source": [
 52 |     "## Inner join"
 53 |    ]
 54 |   },
 55 |   {
 56 |    "cell_type": "code",
 57 |    "execution_count": null,
 58 |    "id": "e50bde09",
 59 |    "metadata": {},
 60 |    "outputs": [],
 61 |    "source": [
 62 |     "# merge df_movies and df_ratings (inner join)\n"
 63 |    ]
 64 |   },
 65 |   {
 66 |    "cell_type": "markdown",
 67 |    "id": "232dc587",
 68 |    "metadata": {},
 69 |    "source": [
 70 |     "## Outer join (Full join)"
 71 |    ]
 72 |   },
 73 |   {
 74 |    "cell_type": "code",
 75 |    "execution_count": null,
 76 |    "id": "eb7cbafe",
 77 |    "metadata": {},
 78 |    "outputs": [],
 79 |    "source": [
 80 |     "# merge df_movies and df_ratings (outer join)\n"
 81 |    ]
 82 |   },
 83 |   {
 84 |    "cell_type": "markdown",
 85 |    "id": "554af406",
 86 |    "metadata": {},
 87 |    "source": [
 88 |     "## Exclusive Outer join (Exclusive Full join)"
 89 |    ]
 90 |   },
 91 |   {
 92 |    "cell_type": "code",
 93 |    "execution_count": null,
 94 |    "id": "18842159",
 95 |    "metadata": {},
 96 |    "outputs": [],
 97 |    "source": [
 98 |     "# merge df_movies and df_ratings (Exclusive Full join)\n"
 99 |    ]
100 |   },
101 |   {
102 |    "cell_type": "markdown",
103 |    "id": "dbee2e97",
104 |    "metadata": {},
105 |    "source": [
106 |     "##  Left join"
107 |    ]
108 |   },
109 |   {
110 |    "cell_type": "code",
111 |    "execution_count": null,
112 |    "id": "5317af4a",
113 |    "metadata": {},
114 |    "outputs": [],
115 |    "source": [
116 |     "# extract a 50% sample of the df_movies dataframe\n"
117 |    ]
118 |   },
119 |   {
120 |    "cell_type": "code",
121 |    "execution_count": null,
122 |    "id": "3e41bd9f",
123 |    "metadata": {},
124 |    "outputs": [],
125 |    "source": [
126 |     "# merge df_movies_sample and df_ratings (left join)\n"
127 |    ]
128 |   },
129 |   {
130 |    "cell_type": "markdown",
131 |    "id": "3014d002",
132 |    "metadata": {},
133 |    "source": [
134 |     "## Exclusive Left join"
135 |    ]
136 |   },
137 |   {
138 |    "cell_type": "code",
139 |    "execution_count": null,
140 |    "id": "06b64daa",
141 |    "metadata": {},
142 |    "outputs": [],
143 |    "source": [
144 |     "# make a copy of the df_movies dataframe\n"
145 |    ]
146 |   },
147 |   {
148 |    "cell_type": "code",
149 |    "execution_count": null,
150 |    "id": "192b0988",
151 |    "metadata": {},
152 |    "outputs": [],
153 |    "source": [
154 |     "# set the first 1000 values of 'imdb_title_id' column as 'tt1234567890'\n"
155 |    ]
156 |   },
157 |   {
158 |    "cell_type": "code",
159 |    "execution_count": null,
160 |    "id": "d79c5ba4",
161 |    "metadata": {},
162 |    "outputs": [],
163 |    "source": [
164 |     "# merge df_movies_2 and df_ratings (exclusive left join)\n"
165 |    ]
166 |   },
167 |   {
168 |    "cell_type": "markdown",
169 |    "id": "4a2007ee",
170 |    "metadata": {},
171 |    "source": [
172 |     "## Right join"
173 |    ]
174 |   },
175 |   {
176 |    "cell_type": "code",
177 |    "execution_count": null,
178 |    "id": "fe292156",
179 |    "metadata": {},
180 |    "outputs": [],
181 |    "source": [
182 |     "# extract a 30% sample of the df_ratings dataframe\n"
183 |    ]
184 |   },
185 |   {
186 |    "cell_type": "code",
187 |    "execution_count": null,
188 |    "id": "0ffdcd45",
189 |    "metadata": {},
190 |    "outputs": [],
191 |    "source": [
192 |     "# merge df_movies and df_ratings_sample (right join)\n"
193 |    ]
194 |   },
195 |   {
196 |    "cell_type": "markdown",
197 |    "id": "c79f3005",
198 |    "metadata": {},
199 |    "source": [
200 |     "## Exclusive Right join"
201 |    ]
202 |   },
203 |   {
204 |    "cell_type": "code",
205 |    "execution_count": null,
206 |    "id": "048c2de3",
207 |    "metadata": {},
208 |    "outputs": [],
209 |    "source": [
210 |     "# make a copy of the df_ratings dataframe\n"
211 |    ]
212 |   },
213 |   {
214 |    "cell_type": "code",
215 |    "execution_count": null,
216 |    "id": "f71e384a",
217 |    "metadata": {},
218 |    "outputs": [],
219 |    "source": [
220 |     "# set the first 1000 values of 'imdb_title_id' column as 'tt1234567890'\n"
221 |    ]
222 |   },
223 |   {
224 |    "cell_type": "code",
225 |    "execution_count": null,
226 |    "id": "358048b3",
227 |    "metadata": {},
228 |    "outputs": [],
229 |    "source": [
230 |     "# merge df_movies and df_ratings_2 (exclusive right join)\n"
231 |    ]
232 |   }
233 |  ],
234 |  "metadata": {
235 |   "kernelspec": {
236 |    "display_name": "Python 3",
237 |    "language": "python",
238 |    "name": "python3"
239 |   },
240 |   "language_info": {
241 |    "codemirror_mode": {
242 |     "name": "ipython",
243 |     "version": 3
244 |    },
245 |    "file_extension": ".py",
246 |    "mimetype": "text/x-python",
247 |    "name": "python",
248 |    "nbconvert_exporter": "python",
249 |    "pygments_lexer": "ipython3",
250 |    "version": "3.8.8"
251 |   },
252 |   "toc": {
253 |    "base_numbering": 1,
254 |    "nav_menu": {},
255 |    "number_sections": true,
256 |    "sideBar": true,
257 |    "skip_h1_title": false,
258 |    "title_cell": "Table of Contents",
259 |    "title_sidebar": "Contents",
260 |    "toc_cell": false,
261 |    "toc_position": {},
262 |    "toc_section_display": true,
263 |    "toc_window_display": false
264 |   }
265 |  },
266 |  "nbformat": 4,
267 |  "nbformat_minor": 5
268 | }
269 | 


--------------------------------------------------------------------------------
/Exercises/Merging and Concatenating DataFrames/Merging and Concatenating DataFrames-Solution.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 1,
  6 |    "id": "fad49839",
  7 |    "metadata": {},
  8 |    "outputs": [],
  9 |    "source": [
 10 |     "import pandas as pd"
 11 |    ]
 12 |   },
 13 |   {
 14 |    "cell_type": "code",
 15 |    "execution_count": 2,
 16 |    "id": "09c6213f",
 17 |    "metadata": {},
 18 |    "outputs": [],
 19 |    "source": [
 20 |     "# read 'IMDb movies.csv' and 'IMDb ratings.csv'\n",
 21 |     "df_movies = pd.read_csv('IMDb movies.csv', low_memory=False)\n",
 22 |     "df_ratings = pd.read_csv('IMDb ratings.csv')"
 23 |    ]
 24 |   },
 25 |   {
 26 |    "cell_type": "code",
 27 |    "execution_count": 3,
 28 |    "id": "d5670913",
 29 |    "metadata": {},
 30 |    "outputs": [],
 31 |    "source": [
 32 |     "# select columns\n",
 33 |     "df_movies = df_movies[['imdb_title_id', 'title', 'year',\n",
 34 |     "                       'genre', 'country']]\n",
 35 |     "\n",
 36 |     "df_ratings = df_ratings[['imdb_title_id', 'total_votes', 'mean_vote']]"
 37 |    ]
 38 |   },
 39 |   {
 40 |    "cell_type": "markdown",
 41 |    "id": "310fc4cc",
 42 |    "metadata": {},
 43 |    "source": [
 44 |     "# merge()"
 45 |    ]
 46 |   },
 47 |   {
 48 |    "cell_type": "markdown",
 49 |    "id": "de4aa87a",
 50 |    "metadata": {},
 51 |    "source": [
 52 |     "## Inner join"
 53 |    ]
 54 |   },
 55 |   {
 56 |    "cell_type": "code",
 57 |    "execution_count": 4,
 58 |    "id": "e50bde09",
 59 |    "metadata": {},
 60 |    "outputs": [
 61 |     {
 62 |      "data": {
 63 |       "text/html": [
 64 |        "<div>\n",
 65 |        "<style scoped>\n",
 66 |        "    .dataframe tbody tr th:only-of-type {\n",
 67 |        "        vertical-align: middle;\n",
 68 |        "    }\n",
 69 |        "\n",
 70 |        "    .dataframe tbody tr th {\n",
 71 |        "        vertical-align: top;\n",
 72 |        "    }\n",
 73 |        "\n",
 74 |        "    .dataframe thead th {\n",
 75 |        "        text-align: right;\n",
 76 |        "    }\n",
 77 |        "</style>\n",
 78 |        "<table border=\"1\" class=\"dataframe\">\n",
 79 |        "  <thead>\n",
 80 |        "    <tr style=\"text-align: right;\">\n",
 81 |        "      <th></th>\n",
 82 |        "      <th>imdb_title_id</th>\n",
 83 |        "      <th>title</th>\n",
 84 |        "      <th>year</th>\n",
 85 |        "      <th>genre</th>\n",
 86 |        "      <th>country</th>\n",
 87 |        "      <th>total_votes</th>\n",
 88 |        "      <th>mean_vote</th>\n",
 89 |        "    </tr>\n",
 90 |        "  </thead>\n",
 91 |        "  <tbody>\n",
 92 |        "    <tr>\n",
 93 |        "      <th>0</th>\n",
 94 |        "      <td>tt0000009</td>\n",
 95 |        "      <td>Miss Jerry</td>\n",
 96 |        "      <td>1894</td>\n",
 97 |        "      <td>Romance</td>\n",
 98 |        "      <td>USA</td>\n",
 99 |        "      <td>154</td>\n",
100 |        "      <td>5.9</td>\n",
101 |        "    </tr>\n",
102 |        "    <tr>\n",
103 |        "      <th>1</th>\n",
104 |        "      <td>tt0000574</td>\n",
105 |        "      <td>The Story of the Kelly Gang</td>\n",
106 |        "      <td>1906</td>\n",
107 |        "      <td>Biography, Crime, Drama</td>\n",
108 |        "      <td>Australia</td>\n",
109 |        "      <td>589</td>\n",
110 |        "      <td>6.3</td>\n",
111 |        "    </tr>\n",
112 |        "    <tr>\n",
113 |        "      <th>2</th>\n",
114 |        "      <td>tt0001892</td>\n",
115 |        "      <td>Den sorte drøm</td>\n",
116 |        "      <td>1911</td>\n",
117 |        "      <td>Drama</td>\n",
118 |        "      <td>Germany, Denmark</td>\n",
119 |        "      <td>188</td>\n",
120 |        "      <td>6.0</td>\n",
121 |        "    </tr>\n",
122 |        "    <tr>\n",
123 |        "      <th>3</th>\n",
124 |        "      <td>tt0002101</td>\n",
125 |        "      <td>Cleopatra</td>\n",
126 |        "      <td>1912</td>\n",
127 |        "      <td>Drama, History</td>\n",
128 |        "      <td>USA</td>\n",
129 |        "      <td>446</td>\n",
130 |        "      <td>5.3</td>\n",
131 |        "    </tr>\n",
132 |        "    <tr>\n",
133 |        "      <th>4</th>\n",
134 |        "      <td>tt0002130</td>\n",
135 |        "      <td>L'Inferno</td>\n",
136 |        "      <td>1911</td>\n",
137 |        "      <td>Adventure, Drama, Fantasy</td>\n",
138 |        "      <td>Italy</td>\n",
139 |        "      <td>2237</td>\n",
140 |        "      <td>6.9</td>\n",
141 |        "    </tr>\n",
142 |        "    <tr>\n",
143 |        "      <th>...</th>\n",
144 |        "      <td>...</td>\n",
145 |        "      <td>...</td>\n",
146 |        "      <td>...</td>\n",
147 |        "      <td>...</td>\n",
148 |        "      <td>...</td>\n",
149 |        "      <td>...</td>\n",
150 |        "      <td>...</td>\n",
151 |        "    </tr>\n",
152 |        "    <tr>\n",
153 |        "      <th>85850</th>\n",
154 |        "      <td>tt9908390</td>\n",
155 |        "      <td>Le lion</td>\n",
156 |        "      <td>2020</td>\n",
157 |        "      <td>Comedy</td>\n",
158 |        "      <td>France, Belgium</td>\n",
159 |        "      <td>398</td>\n",
160 |        "      <td>5.5</td>\n",
161 |        "    </tr>\n",
162 |        "    <tr>\n",
163 |        "      <th>85851</th>\n",
164 |        "      <td>tt9911196</td>\n",
165 |        "      <td>De Beentjes van Sint-Hildegard</td>\n",
166 |        "      <td>2020</td>\n",
167 |        "      <td>Comedy, Drama</td>\n",
168 |        "      <td>Netherlands</td>\n",
169 |        "      <td>724</td>\n",
170 |        "      <td>7.9</td>\n",
171 |        "    </tr>\n",
172 |        "    <tr>\n",
173 |        "      <th>85852</th>\n",
174 |        "      <td>tt9911774</td>\n",
175 |        "      <td>Padmavyuhathile Abhimanyu</td>\n",
176 |        "      <td>2019</td>\n",
177 |        "      <td>Drama</td>\n",
178 |        "      <td>India</td>\n",
179 |        "      <td>265</td>\n",
180 |        "      <td>7.8</td>\n",
181 |        "    </tr>\n",
182 |        "    <tr>\n",
183 |        "      <th>85853</th>\n",
184 |        "      <td>tt9914286</td>\n",
185 |        "      <td>Sokagin Çocuklari</td>\n",
186 |        "      <td>2019</td>\n",
187 |        "      <td>Drama, Family</td>\n",
188 |        "      <td>Turkey</td>\n",
189 |        "      <td>194</td>\n",
190 |        "      <td>9.4</td>\n",
191 |        "    </tr>\n",
192 |        "    <tr>\n",
193 |        "      <th>85854</th>\n",
194 |        "      <td>tt9914942</td>\n",
195 |        "      <td>La vida sense la Sara Amat</td>\n",
196 |        "      <td>2019</td>\n",
197 |        "      <td>Drama</td>\n",
198 |        "      <td>Spain</td>\n",
199 |        "      <td>102</td>\n",
200 |        "      <td>6.8</td>\n",
201 |        "    </tr>\n",
202 |        "  </tbody>\n",
203 |        "</table>\n",
204 |        "<p>85855 rows × 7 columns</p>\n",
205 |        "</div>"
206 |       ],
207 |       "text/plain": [
208 |        "      imdb_title_id                           title  year  \\\n",
209 |        "0         tt0000009                      Miss Jerry  1894   \n",
210 |        "1         tt0000574     The Story of the Kelly Gang  1906   \n",
211 |        "2         tt0001892                  Den sorte drøm  1911   \n",
212 |        "3         tt0002101                       Cleopatra  1912   \n",
213 |        "4         tt0002130                       L'Inferno  1911   \n",
214 |        "...             ...                             ...   ...   \n",
215 |        "85850     tt9908390                         Le lion  2020   \n",
216 |        "85851     tt9911196  De Beentjes van Sint-Hildegard  2020   \n",
217 |        "85852     tt9911774       Padmavyuhathile Abhimanyu  2019   \n",
218 |        "85853     tt9914286               Sokagin Çocuklari  2019   \n",
219 |        "85854     tt9914942      La vida sense la Sara Amat  2019   \n",
220 |        "\n",
221 |        "                           genre           country  total_votes  mean_vote  \n",
222 |        "0                        Romance               USA          154        5.9  \n",
223 |        "1        Biography, Crime, Drama         Australia          589        6.3  \n",
224 |        "2                          Drama  Germany, Denmark          188        6.0  \n",
225 |        "3                 Drama, History               USA          446        5.3  \n",
226 |        "4      Adventure, Drama, Fantasy             Italy         2237        6.9  \n",
227 |        "...                          ...               ...          ...        ...  \n",
228 |        "85850                     Comedy   France, Belgium          398        5.5  \n",
229 |        "85851              Comedy, Drama       Netherlands          724        7.9  \n",
230 |        "85852                      Drama             India          265        7.8  \n",
231 |        "85853              Drama, Family            Turkey          194        9.4  \n",
232 |        "85854                      Drama             Spain          102        6.8  \n",
233 |        "\n",
234 |        "[85855 rows x 7 columns]"
235 |       ]
236 |      },
237 |      "execution_count": 4,
238 |      "metadata": {},
239 |      "output_type": "execute_result"
240 |     }
241 |    ],
242 |    "source": [
243 |     "# merge df_movies and df_ratings (inner join)\n",
244 |     "df_movies.merge(df_ratings, on='imdb_title_id')"
245 |    ]
246 |   },
247 |   {
248 |    "cell_type": "markdown",
249 |    "id": "232dc587",
250 |    "metadata": {},
251 |    "source": [
252 |     "## Outer join (Full join)"
253 |    ]
254 |   },
255 |   {
256 |    "cell_type": "code",
257 |    "execution_count": 5,
258 |    "id": "eb7cbafe",
259 |    "metadata": {},
260 |    "outputs": [
261 |     {
262 |      "data": {
263 |       "text/html": [
264 |        "<div>\n",
265 |        "<style scoped>\n",
266 |        "    .dataframe tbody tr th:only-of-type {\n",
267 |        "        vertical-align: middle;\n",
268 |        "    }\n",
269 |        "\n",
270 |        "    .dataframe tbody tr th {\n",
271 |        "        vertical-align: top;\n",
272 |        "    }\n",
273 |        "\n",
274 |        "    .dataframe thead th {\n",
275 |        "        text-align: right;\n",
276 |        "    }\n",
277 |        "</style>\n",
278 |        "<table border=\"1\" class=\"dataframe\">\n",
279 |        "  <thead>\n",
280 |        "    <tr style=\"text-align: right;\">\n",
281 |        "      <th></th>\n",
282 |        "      <th>imdb_title_id</th>\n",
283 |        "      <th>title</th>\n",
284 |        "      <th>year</th>\n",
285 |        "      <th>genre</th>\n",
286 |        "      <th>country</th>\n",
287 |        "      <th>total_votes</th>\n",
288 |        "      <th>mean_vote</th>\n",
289 |        "    </tr>\n",
290 |        "  </thead>\n",
291 |        "  <tbody>\n",
292 |        "    <tr>\n",
293 |        "      <th>0</th>\n",
294 |        "      <td>tt0000009</td>\n",
295 |        "      <td>Miss Jerry</td>\n",
296 |        "      <td>1894</td>\n",
297 |        "      <td>Romance</td>\n",
298 |        "      <td>USA</td>\n",
299 |        "      <td>154</td>\n",
300 |        "      <td>5.9</td>\n",
301 |        "    </tr>\n",
302 |        "    <tr>\n",
303 |        "      <th>1</th>\n",
304 |        "      <td>tt0000574</td>\n",
305 |        "      <td>The Story of the Kelly Gang</td>\n",
306 |        "      <td>1906</td>\n",
307 |        "      <td>Biography, Crime, Drama</td>\n",
308 |        "      <td>Australia</td>\n",
309 |        "      <td>589</td>\n",
310 |        "      <td>6.3</td>\n",
311 |        "    </tr>\n",
312 |        "    <tr>\n",
313 |        "      <th>2</th>\n",
314 |        "      <td>tt0001892</td>\n",
315 |        "      <td>Den sorte drøm</td>\n",
316 |        "      <td>1911</td>\n",
317 |        "      <td>Drama</td>\n",
318 |        "      <td>Germany, Denmark</td>\n",
319 |        "      <td>188</td>\n",
320 |        "      <td>6.0</td>\n",
321 |        "    </tr>\n",
322 |        "    <tr>\n",
323 |        "      <th>3</th>\n",
324 |        "      <td>tt0002101</td>\n",
325 |        "      <td>Cleopatra</td>\n",
326 |        "      <td>1912</td>\n",
327 |        "      <td>Drama, History</td>\n",
328 |        "      <td>USA</td>\n",
329 |        "      <td>446</td>\n",
330 |        "      <td>5.3</td>\n",
331 |        "    </tr>\n",
332 |        "    <tr>\n",
333 |        "      <th>4</th>\n",
334 |        "      <td>tt0002130</td>\n",
335 |        "      <td>L'Inferno</td>\n",
336 |        "      <td>1911</td>\n",
337 |        "      <td>Adventure, Drama, Fantasy</td>\n",
338 |        "      <td>Italy</td>\n",
339 |        "      <td>2237</td>\n",
340 |        "      <td>6.9</td>\n",
341 |        "    </tr>\n",
342 |        "    <tr>\n",
343 |        "      <th>...</th>\n",
344 |        "      <td>...</td>\n",
345 |        "      <td>...</td>\n",
346 |        "      <td>...</td>\n",
347 |        "      <td>...</td>\n",
348 |        "      <td>...</td>\n",
349 |        "      <td>...</td>\n",
350 |        "      <td>...</td>\n",
351 |        "    </tr>\n",
352 |        "    <tr>\n",
353 |        "      <th>85850</th>\n",
354 |        "      <td>tt9908390</td>\n",
355 |        "      <td>Le lion</td>\n",
356 |        "      <td>2020</td>\n",
357 |        "      <td>Comedy</td>\n",
358 |        "      <td>France, Belgium</td>\n",
359 |        "      <td>398</td>\n",
360 |        "      <td>5.5</td>\n",
361 |        "    </tr>\n",
362 |        "    <tr>\n",
363 |        "      <th>85851</th>\n",
364 |        "      <td>tt9911196</td>\n",
365 |        "      <td>De Beentjes van Sint-Hildegard</td>\n",
366 |        "      <td>2020</td>\n",
367 |        "      <td>Comedy, Drama</td>\n",
368 |        "      <td>Netherlands</td>\n",
369 |        "      <td>724</td>\n",
370 |        "      <td>7.9</td>\n",
371 |        "    </tr>\n",
372 |        "    <tr>\n",
373 |        "      <th>85852</th>\n",
374 |        "      <td>tt9911774</td>\n",
375 |        "      <td>Padmavyuhathile Abhimanyu</td>\n",
376 |        "      <td>2019</td>\n",
377 |        "      <td>Drama</td>\n",
378 |        "      <td>India</td>\n",
379 |        "      <td>265</td>\n",
380 |        "      <td>7.8</td>\n",
381 |        "    </tr>\n",
382 |        "    <tr>\n",
383 |        "      <th>85853</th>\n",
384 |        "      <td>tt9914286</td>\n",
385 |        "      <td>Sokagin Çocuklari</td>\n",
386 |        "      <td>2019</td>\n",
387 |        "      <td>Drama, Family</td>\n",
388 |        "      <td>Turkey</td>\n",
389 |        "      <td>194</td>\n",
390 |        "      <td>9.4</td>\n",
391 |        "    </tr>\n",
392 |        "    <tr>\n",
393 |        "      <th>85854</th>\n",
394 |        "      <td>tt9914942</td>\n",
395 |        "      <td>La vida sense la Sara Amat</td>\n",
396 |        "      <td>2019</td>\n",
397 |        "      <td>Drama</td>\n",
398 |        "      <td>Spain</td>\n",
399 |        "      <td>102</td>\n",
400 |        "      <td>6.8</td>\n",
401 |        "    </tr>\n",
402 |        "  </tbody>\n",
403 |        "</table>\n",
404 |        "<p>85855 rows × 7 columns</p>\n",
405 |        "</div>"
406 |       ],
407 |       "text/plain": [
408 |        "      imdb_title_id                           title  year  \\\n",
409 |        "0         tt0000009                      Miss Jerry  1894   \n",
410 |        "1         tt0000574     The Story of the Kelly Gang  1906   \n",
411 |        "2         tt0001892                  Den sorte drøm  1911   \n",
412 |        "3         tt0002101                       Cleopatra  1912   \n",
413 |        "4         tt0002130                       L'Inferno  1911   \n",
414 |        "...             ...                             ...   ...   \n",
415 |        "85850     tt9908390                         Le lion  2020   \n",
416 |        "85851     tt9911196  De Beentjes van Sint-Hildegard  2020   \n",
417 |        "85852     tt9911774       Padmavyuhathile Abhimanyu  2019   \n",
418 |        "85853     tt9914286               Sokagin Çocuklari  2019   \n",
419 |        "85854     tt9914942      La vida sense la Sara Amat  2019   \n",
420 |        "\n",
421 |        "                           genre           country  total_votes  mean_vote  \n",
422 |        "0                        Romance               USA          154        5.9  \n",
423 |        "1        Biography, Crime, Drama         Australia          589        6.3  \n",
424 |        "2                          Drama  Germany, Denmark          188        6.0  \n",
425 |        "3                 Drama, History               USA          446        5.3  \n",
426 |        "4      Adventure, Drama, Fantasy             Italy         2237        6.9  \n",
427 |        "...                          ...               ...          ...        ...  \n",
428 |        "85850                     Comedy   France, Belgium          398        5.5  \n",
429 |        "85851              Comedy, Drama       Netherlands          724        7.9  \n",
430 |        "85852                      Drama             India          265        7.8  \n",
431 |        "85853              Drama, Family            Turkey          194        9.4  \n",
432 |        "85854                      Drama             Spain          102        6.8  \n",
433 |        "\n",
434 |        "[85855 rows x 7 columns]"
435 |       ]
436 |      },
437 |      "execution_count": 5,
438 |      "metadata": {},
439 |      "output_type": "execute_result"
440 |     }
441 |    ],
442 |    "source": [
443 |     "# merge df_movies and df_ratings (outer join)\n",
444 |     "df_movies.merge(df_ratings, on='imdb_title_id', how='outer')"
445 |    ]
446 |   },
447 |   {
448 |    "cell_type": "markdown",
449 |    "id": "554af406",
450 |    "metadata": {},
451 |    "source": [
452 |     "## Exclusive Outer join (Exclusive Full join)"
453 |    ]
454 |   },
455 |   {
456 |    "cell_type": "code",
457 |    "execution_count": 6,
458 |    "id": "18842159",
459 |    "metadata": {},
460 |    "outputs": [
461 |     {
462 |      "data": {
463 |       "text/html": [
464 |        "<div>\n",
465 |        "<style scoped>\n",
466 |        "    .dataframe tbody tr th:only-of-type {\n",
467 |        "        vertical-align: middle;\n",
468 |        "    }\n",
469 |        "\n",
470 |        "    .dataframe tbody tr th {\n",
471 |        "        vertical-align: top;\n",
472 |        "    }\n",
473 |        "\n",
474 |        "    .dataframe thead th {\n",
475 |        "        text-align: right;\n",
476 |        "    }\n",
477 |        "</style>\n",
478 |        "<table border=\"1\" class=\"dataframe\">\n",
479 |        "  <thead>\n",
480 |        "    <tr style=\"text-align: right;\">\n",
481 |        "      <th></th>\n",
482 |        "      <th>imdb_title_id</th>\n",
483 |        "      <th>title</th>\n",
484 |        "      <th>year</th>\n",
485 |        "      <th>genre</th>\n",
486 |        "      <th>country</th>\n",
487 |        "      <th>total_votes</th>\n",
488 |        "      <th>mean_vote</th>\n",
489 |        "      <th>_merge</th>\n",
490 |        "    </tr>\n",
491 |        "  </thead>\n",
492 |        "  <tbody>\n",
493 |        "  </tbody>\n",
494 |        "</table>\n",
495 |        "</div>"
496 |       ],
497 |       "text/plain": [
498 |        "Empty DataFrame\n",
499 |        "Columns: [imdb_title_id, title, year, genre, country, total_votes, mean_vote, _merge]\n",
500 |        "Index: []"
501 |       ]
502 |      },
503 |      "execution_count": 6,
504 |      "metadata": {},
505 |      "output_type": "execute_result"
506 |     }
507 |    ],
508 |    "source": [
509 |     "# merge df_movies and df_ratings (Exclusive Full join)\n",
510 |     "df_movies.merge(df_ratings, on='imdb_title_id', how='outer', \n",
511 |     "                indicator=True).query(\"_merge=='left_only' or _merge=='right_only'\")"
512 |    ]
513 |   },
514 |   {
515 |    "cell_type": "markdown",
516 |    "id": "dbee2e97",
517 |    "metadata": {},
518 |    "source": [
519 |     "##  Left join"
520 |    ]
521 |   },
522 |   {
523 |    "cell_type": "code",
524 |    "execution_count": 7,
525 |    "id": "5317af4a",
526 |    "metadata": {},
527 |    "outputs": [],
528 |    "source": [
529 |     "# extract a 50% sample of the df_movies dataframe\n",
530 |     "df_movies_sample = df_movies.sample(frac=0.5)"
531 |    ]
532 |   },
533 |   {
534 |    "cell_type": "code",
535 |    "execution_count": 8,
536 |    "id": "3e41bd9f",
537 |    "metadata": {},
538 |    "outputs": [],
539 |    "source": [
540 |     "# merge df_movies_sample and df_ratings (left join)\n",
541 |     "df_left = df_movies_sample.merge(df_ratings, on='imdb_title_id',\n",
542 |     "                                 how='left')"
543 |    ]
544 |   },
545 |   {
546 |    "cell_type": "markdown",
547 |    "id": "3014d002",
548 |    "metadata": {},
549 |    "source": [
550 |     "## Exclusive Left join"
551 |    ]
552 |   },
553 |   {
554 |    "cell_type": "code",
555 |    "execution_count": 9,
556 |    "id": "06b64daa",
557 |    "metadata": {},
558 |    "outputs": [],
559 |    "source": [
560 |     "# make a copy of the df_movies dataframe\n",
561 |     "df_movies_2 = df_movies.copy()"
562 |    ]
563 |   },
564 |   {
565 |    "cell_type": "code",
566 |    "execution_count": 10,
567 |    "id": "192b0988",
568 |    "metadata": {},
569 |    "outputs": [],
570 |    "source": [
571 |     "# set the first 1000 values of 'imdb_title_id' column as 'tt1234567890'\n",
572 |     "for index in df_movies_2.index:\n",
573 |     "    if index < 1000:\n",
574 |     "        df_movies_2.loc[index, 'imdb_title_id'] = 'tt1234567890'"
575 |    ]
576 |   },
577 |   {
578 |    "cell_type": "code",
579 |    "execution_count": 11,
580 |    "id": "d79c5ba4",
581 |    "metadata": {},
582 |    "outputs": [],
583 |    "source": [
584 |     "# merge df_movies_2 and df_ratings (exclusive left join)\n",
585 |     "df_exclusive_left = df_movies_2.merge(df_ratings,\n",
586 |     "                                      on='imdb_title_id',\n",
587 |     "                                      how='outer', \n",
588 |     "                                      indicator=True).query(\"_merge=='left_only'\")"
589 |    ]
590 |   },
591 |   {
592 |    "cell_type": "markdown",
593 |    "id": "4a2007ee",
594 |    "metadata": {},
595 |    "source": [
596 |     "## Right join"
597 |    ]
598 |   },
599 |   {
600 |    "cell_type": "code",
601 |    "execution_count": 12,
602 |    "id": "fe292156",
603 |    "metadata": {},
604 |    "outputs": [],
605 |    "source": [
606 |     "# extract a 30% sample of the df_ratings dataframe\n",
607 |     "df_ratings_sample = df_ratings.sample(frac=0.3)"
608 |    ]
609 |   },
610 |   {
611 |    "cell_type": "code",
612 |    "execution_count": 13,
613 |    "id": "0ffdcd45",
614 |    "metadata": {},
615 |    "outputs": [],
616 |    "source": [
617 |     "# merge df_movies and df_ratings_sample (right join)\n",
618 |     "df_right = df_movies.merge(df_ratings_sample, on='imdb_title_id',\n",
619 |     "                           how='right')"
620 |    ]
621 |   },
622 |   {
623 |    "cell_type": "markdown",
624 |    "id": "c79f3005",
625 |    "metadata": {},
626 |    "source": [
627 |     "## Exclusive Right join"
628 |    ]
629 |   },
630 |   {
631 |    "cell_type": "code",
632 |    "execution_count": 14,
633 |    "id": "048c2de3",
634 |    "metadata": {},
635 |    "outputs": [],
636 |    "source": [
637 |     "# make a copy of the df_ratings dataframe\n",
638 |     "df_ratings_2 = df_ratings.copy()"
639 |    ]
640 |   },
641 |   {
642 |    "cell_type": "code",
643 |    "execution_count": 15,
644 |    "id": "f71e384a",
645 |    "metadata": {},
646 |    "outputs": [],
647 |    "source": [
648 |     "# set the first 1000 values of 'imdb_title_id' column as 'tt1234567890'\n",
649 |     "for index in df_ratings_2.index:\n",
650 |     "    if index < 1000:\n",
651 |     "        df_ratings_2.loc[index, 'imdb_title_id'] = 'tt1234567890'"
652 |    ]
653 |   },
654 |   {
655 |    "cell_type": "code",
656 |    "execution_count": 16,
657 |    "id": "358048b3",
658 |    "metadata": {},
659 |    "outputs": [],
660 |    "source": [
661 |     "# merge df_movies and df_ratings_2 (exclusive right join)\n",
662 |     "df_exclusive_right = df_movies.merge(df_ratings_2,\n",
663 |     "                                     on='imdb_title_id',\n",
664 |     "                                     how='outer', \n",
665 |     "                                     indicator=True).query(\"_merge=='right_only'\")"
666 |    ]
667 |   }
668 |  ],
669 |  "metadata": {
670 |   "kernelspec": {
671 |    "display_name": "Python 3",
672 |    "language": "python",
673 |    "name": "python3"
674 |   },
675 |   "language_info": {
676 |    "codemirror_mode": {
677 |     "name": "ipython",
678 |     "version": 3
679 |    },
680 |    "file_extension": ".py",
681 |    "mimetype": "text/x-python",
682 |    "name": "python",
683 |    "nbconvert_exporter": "python",
684 |    "pygments_lexer": "ipython3",
685 |    "version": "3.8.8"
686 |   },
687 |   "toc": {
688 |    "base_numbering": 1,
689 |    "nav_menu": {},
690 |    "number_sections": true,
691 |    "sideBar": true,
692 |    "skip_h1_title": false,
693 |    "title_cell": "Table of Contents",
694 |    "title_sidebar": "Contents",
695 |    "toc_cell": false,
696 |    "toc_position": {},
697 |    "toc_section_display": true,
698 |    "toc_window_display": false
699 |   }
700 |  },
701 |  "nbformat": 4,
702 |  "nbformat_minor": 5
703 | }
704 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
1 | ## FREE Python Cheat Sheet
2 | 
3 | 🇺🇸 Link: https://artificialcorner.com/p/redeem-my-udemy-courses-for-free
4 | 
5 | ## Formulario de Python Gratis
6 | 
7 | 🇪🇸 Link: https://artificialcorner.com/p/formularios-gratis-de-python
8 | 


--------------------------------------------------------------------------------
/Web Scraping with Pandas.ipynb:
--------------------------------------------------------------------------------
   1 | {
   2 |  "cells": [
   3 |   {
   4 |    "cell_type": "code",
   5 |    "execution_count": 1,
   6 |    "id": "9bcec48b",
   7 |    "metadata": {},
   8 |    "outputs": [],
   9 |    "source": [
  10 |     "import pandas as pd"
  11 |    ]
  12 |   },
  13 |   {
  14 |    "cell_type": "markdown",
  15 |    "id": "b8784766",
  16 |    "metadata": {},
  17 |    "source": [
  18 |     "# Read a .csv from a URL with Pandas"
  19 |    ]
  20 |   },
  21 |   {
  22 |    "cell_type": "markdown",
  23 |    "id": "1e116955",
  24 |    "metadata": {},
  25 |    "source": [
  26 |     "Target website: https://www.football-data.co.uk/data.php"
  27 |    ]
  28 |   },
  29 |   {
  30 |    "cell_type": "code",
  31 |    "execution_count": 2,
  32 |    "id": "62ad1716",
  33 |    "metadata": {},
  34 |    "outputs": [],
  35 |    "source": [
  36 |     "# reading 1 csv file from the website\n",
  37 |     "df_premier21 = pd.read_csv('https://www.football-data.co.uk/mmz4281/2122/E0.csv')"
  38 |    ]
  39 |   },
  40 |   {
  41 |    "cell_type": "code",
  42 |    "execution_count": 3,
  43 |    "id": "e0b6be7b",
  44 |    "metadata": {},
  45 |    "outputs": [
  46 |     {
  47 |      "data": {
  48 |       "text/html": [
  49 |        "<div>\n",
  50 |        "<style scoped>\n",
  51 |        "    .dataframe tbody tr th:only-of-type {\n",
  52 |        "        vertical-align: middle;\n",
  53 |        "    }\n",
  54 |        "\n",
  55 |        "    .dataframe tbody tr th {\n",
  56 |        "        vertical-align: top;\n",
  57 |        "    }\n",
  58 |        "\n",
  59 |        "    .dataframe thead th {\n",
  60 |        "        text-align: right;\n",
  61 |        "    }\n",
  62 |        "</style>\n",
  63 |        "<table border=\"1\" class=\"dataframe\">\n",
  64 |        "  <thead>\n",
  65 |        "    <tr style=\"text-align: right;\">\n",
  66 |        "      <th></th>\n",
  67 |        "      <th>Div</th>\n",
  68 |        "      <th>Date</th>\n",
  69 |        "      <th>Time</th>\n",
  70 |        "      <th>HomeTeam</th>\n",
  71 |        "      <th>AwayTeam</th>\n",
  72 |        "      <th>FTHG</th>\n",
  73 |        "      <th>FTAG</th>\n",
  74 |        "      <th>FTR</th>\n",
  75 |        "      <th>HTHG</th>\n",
  76 |        "      <th>HTAG</th>\n",
  77 |        "      <th>...</th>\n",
  78 |        "      <th>AvgC&lt;2.5</th>\n",
  79 |        "      <th>AHCh</th>\n",
  80 |        "      <th>B365CAHH</th>\n",
  81 |        "      <th>B365CAHA</th>\n",
  82 |        "      <th>PCAHH</th>\n",
  83 |        "      <th>PCAHA</th>\n",
  84 |        "      <th>MaxCAHH</th>\n",
  85 |        "      <th>MaxCAHA</th>\n",
  86 |        "      <th>AvgCAHH</th>\n",
  87 |        "      <th>AvgCAHA</th>\n",
  88 |        "    </tr>\n",
  89 |        "  </thead>\n",
  90 |        "  <tbody>\n",
  91 |        "    <tr>\n",
  92 |        "      <th>0</th>\n",
  93 |        "      <td>E0</td>\n",
  94 |        "      <td>13/08/2021</td>\n",
  95 |        "      <td>20:00</td>\n",
  96 |        "      <td>Brentford</td>\n",
  97 |        "      <td>Arsenal</td>\n",
  98 |        "      <td>2</td>\n",
  99 |        "      <td>0</td>\n",
 100 |        "      <td>H</td>\n",
 101 |        "      <td>1</td>\n",
 102 |        "      <td>0</td>\n",
 103 |        "      <td>...</td>\n",
 104 |        "      <td>1.62</td>\n",
 105 |        "      <td>0.50</td>\n",
 106 |        "      <td>1.75</td>\n",
 107 |        "      <td>2.05</td>\n",
 108 |        "      <td>1.81</td>\n",
 109 |        "      <td>2.13</td>\n",
 110 |        "      <td>2.05</td>\n",
 111 |        "      <td>2.17</td>\n",
 112 |        "      <td>1.80</td>\n",
 113 |        "      <td>2.09</td>\n",
 114 |        "    </tr>\n",
 115 |        "    <tr>\n",
 116 |        "      <th>1</th>\n",
 117 |        "      <td>E0</td>\n",
 118 |        "      <td>14/08/2021</td>\n",
 119 |        "      <td>12:30</td>\n",
 120 |        "      <td>Man United</td>\n",
 121 |        "      <td>Leeds</td>\n",
 122 |        "      <td>5</td>\n",
 123 |        "      <td>1</td>\n",
 124 |        "      <td>H</td>\n",
 125 |        "      <td>1</td>\n",
 126 |        "      <td>0</td>\n",
 127 |        "      <td>...</td>\n",
 128 |        "      <td>2.25</td>\n",
 129 |        "      <td>-1.00</td>\n",
 130 |        "      <td>2.05</td>\n",
 131 |        "      <td>1.75</td>\n",
 132 |        "      <td>2.17</td>\n",
 133 |        "      <td>1.77</td>\n",
 134 |        "      <td>2.19</td>\n",
 135 |        "      <td>1.93</td>\n",
 136 |        "      <td>2.10</td>\n",
 137 |        "      <td>1.79</td>\n",
 138 |        "    </tr>\n",
 139 |        "    <tr>\n",
 140 |        "      <th>2</th>\n",
 141 |        "      <td>E0</td>\n",
 142 |        "      <td>14/08/2021</td>\n",
 143 |        "      <td>15:00</td>\n",
 144 |        "      <td>Burnley</td>\n",
 145 |        "      <td>Brighton</td>\n",
 146 |        "      <td>1</td>\n",
 147 |        "      <td>2</td>\n",
 148 |        "      <td>A</td>\n",
 149 |        "      <td>1</td>\n",
 150 |        "      <td>0</td>\n",
 151 |        "      <td>...</td>\n",
 152 |        "      <td>1.62</td>\n",
 153 |        "      <td>0.25</td>\n",
 154 |        "      <td>1.79</td>\n",
 155 |        "      <td>2.15</td>\n",
 156 |        "      <td>1.81</td>\n",
 157 |        "      <td>2.14</td>\n",
 158 |        "      <td>1.82</td>\n",
 159 |        "      <td>2.19</td>\n",
 160 |        "      <td>1.79</td>\n",
 161 |        "      <td>2.12</td>\n",
 162 |        "    </tr>\n",
 163 |        "    <tr>\n",
 164 |        "      <th>3</th>\n",
 165 |        "      <td>E0</td>\n",
 166 |        "      <td>14/08/2021</td>\n",
 167 |        "      <td>15:00</td>\n",
 168 |        "      <td>Chelsea</td>\n",
 169 |        "      <td>Crystal Palace</td>\n",
 170 |        "      <td>3</td>\n",
 171 |        "      <td>0</td>\n",
 172 |        "      <td>H</td>\n",
 173 |        "      <td>2</td>\n",
 174 |        "      <td>0</td>\n",
 175 |        "      <td>...</td>\n",
 176 |        "      <td>1.94</td>\n",
 177 |        "      <td>-1.50</td>\n",
 178 |        "      <td>2.05</td>\n",
 179 |        "      <td>1.75</td>\n",
 180 |        "      <td>2.12</td>\n",
 181 |        "      <td>1.81</td>\n",
 182 |        "      <td>2.16</td>\n",
 183 |        "      <td>1.93</td>\n",
 184 |        "      <td>2.06</td>\n",
 185 |        "      <td>1.82</td>\n",
 186 |        "    </tr>\n",
 187 |        "    <tr>\n",
 188 |        "      <th>4</th>\n",
 189 |        "      <td>E0</td>\n",
 190 |        "      <td>14/08/2021</td>\n",
 191 |        "      <td>15:00</td>\n",
 192 |        "      <td>Everton</td>\n",
 193 |        "      <td>Southampton</td>\n",
 194 |        "      <td>3</td>\n",
 195 |        "      <td>1</td>\n",
 196 |        "      <td>H</td>\n",
 197 |        "      <td>0</td>\n",
 198 |        "      <td>1</td>\n",
 199 |        "      <td>...</td>\n",
 200 |        "      <td>1.67</td>\n",
 201 |        "      <td>-0.50</td>\n",
 202 |        "      <td>2.05</td>\n",
 203 |        "      <td>1.88</td>\n",
 204 |        "      <td>2.05</td>\n",
 205 |        "      <td>1.88</td>\n",
 206 |        "      <td>2.08</td>\n",
 207 |        "      <td>1.90</td>\n",
 208 |        "      <td>2.03</td>\n",
 209 |        "      <td>1.86</td>\n",
 210 |        "    </tr>\n",
 211 |        "    <tr>\n",
 212 |        "      <th>...</th>\n",
 213 |        "      <td>...</td>\n",
 214 |        "      <td>...</td>\n",
 215 |        "      <td>...</td>\n",
 216 |        "      <td>...</td>\n",
 217 |        "      <td>...</td>\n",
 218 |        "      <td>...</td>\n",
 219 |        "      <td>...</td>\n",
 220 |        "      <td>...</td>\n",
 221 |        "      <td>...</td>\n",
 222 |        "      <td>...</td>\n",
 223 |        "      <td>...</td>\n",
 224 |        "      <td>...</td>\n",
 225 |        "      <td>...</td>\n",
 226 |        "      <td>...</td>\n",
 227 |        "      <td>...</td>\n",
 228 |        "      <td>...</td>\n",
 229 |        "      <td>...</td>\n",
 230 |        "      <td>...</td>\n",
 231 |        "      <td>...</td>\n",
 232 |        "      <td>...</td>\n",
 233 |        "      <td>...</td>\n",
 234 |        "    </tr>\n",
 235 |        "    <tr>\n",
 236 |        "      <th>210</th>\n",
 237 |        "      <td>E0</td>\n",
 238 |        "      <td>23/01/2022</td>\n",
 239 |        "      <td>14:00</td>\n",
 240 |        "      <td>Arsenal</td>\n",
 241 |        "      <td>Burnley</td>\n",
 242 |        "      <td>0</td>\n",
 243 |        "      <td>0</td>\n",
 244 |        "      <td>D</td>\n",
 245 |        "      <td>0</td>\n",
 246 |        "      <td>0</td>\n",
 247 |        "      <td>...</td>\n",
 248 |        "      <td>2.32</td>\n",
 249 |        "      <td>-1.50</td>\n",
 250 |        "      <td>1.92</td>\n",
 251 |        "      <td>2.01</td>\n",
 252 |        "      <td>1.93</td>\n",
 253 |        "      <td>2.00</td>\n",
 254 |        "      <td>1.93</td>\n",
 255 |        "      <td>2.11</td>\n",
 256 |        "      <td>1.90</td>\n",
 257 |        "      <td>1.98</td>\n",
 258 |        "    </tr>\n",
 259 |        "    <tr>\n",
 260 |        "      <th>211</th>\n",
 261 |        "      <td>E0</td>\n",
 262 |        "      <td>23/01/2022</td>\n",
 263 |        "      <td>14:00</td>\n",
 264 |        "      <td>Crystal Palace</td>\n",
 265 |        "      <td>Liverpool</td>\n",
 266 |        "      <td>1</td>\n",
 267 |        "      <td>3</td>\n",
 268 |        "      <td>A</td>\n",
 269 |        "      <td>0</td>\n",
 270 |        "      <td>2</td>\n",
 271 |        "      <td>...</td>\n",
 272 |        "      <td>2.11</td>\n",
 273 |        "      <td>1.00</td>\n",
 274 |        "      <td>1.96</td>\n",
 275 |        "      <td>1.97</td>\n",
 276 |        "      <td>1.94</td>\n",
 277 |        "      <td>1.97</td>\n",
 278 |        "      <td>2.07</td>\n",
 279 |        "      <td>2.02</td>\n",
 280 |        "      <td>1.92</td>\n",
 281 |        "      <td>1.96</td>\n",
 282 |        "    </tr>\n",
 283 |        "    <tr>\n",
 284 |        "      <th>212</th>\n",
 285 |        "      <td>E0</td>\n",
 286 |        "      <td>23/01/2022</td>\n",
 287 |        "      <td>14:00</td>\n",
 288 |        "      <td>Leicester</td>\n",
 289 |        "      <td>Brighton</td>\n",
 290 |        "      <td>1</td>\n",
 291 |        "      <td>1</td>\n",
 292 |        "      <td>D</td>\n",
 293 |        "      <td>0</td>\n",
 294 |        "      <td>0</td>\n",
 295 |        "      <td>...</td>\n",
 296 |        "      <td>2.10</td>\n",
 297 |        "      <td>0.00</td>\n",
 298 |        "      <td>1.92</td>\n",
 299 |        "      <td>2.01</td>\n",
 300 |        "      <td>1.93</td>\n",
 301 |        "      <td>1.99</td>\n",
 302 |        "      <td>1.94</td>\n",
 303 |        "      <td>2.13</td>\n",
 304 |        "      <td>1.87</td>\n",
 305 |        "      <td>2.01</td>\n",
 306 |        "    </tr>\n",
 307 |        "    <tr>\n",
 308 |        "      <th>213</th>\n",
 309 |        "      <td>E0</td>\n",
 310 |        "      <td>23/01/2022</td>\n",
 311 |        "      <td>16:30</td>\n",
 312 |        "      <td>Chelsea</td>\n",
 313 |        "      <td>Tottenham</td>\n",
 314 |        "      <td>2</td>\n",
 315 |        "      <td>0</td>\n",
 316 |        "      <td>H</td>\n",
 317 |        "      <td>0</td>\n",
 318 |        "      <td>0</td>\n",
 319 |        "      <td>...</td>\n",
 320 |        "      <td>1.84</td>\n",
 321 |        "      <td>-0.75</td>\n",
 322 |        "      <td>1.99</td>\n",
 323 |        "      <td>1.94</td>\n",
 324 |        "      <td>1.97</td>\n",
 325 |        "      <td>1.95</td>\n",
 326 |        "      <td>2.03</td>\n",
 327 |        "      <td>2.07</td>\n",
 328 |        "      <td>1.96</td>\n",
 329 |        "      <td>1.92</td>\n",
 330 |        "    </tr>\n",
 331 |        "    <tr>\n",
 332 |        "      <th>214</th>\n",
 333 |        "      <td>E0</td>\n",
 334 |        "      <td>05/02/2022</td>\n",
 335 |        "      <td>18:00</td>\n",
 336 |        "      <td>Burnley</td>\n",
 337 |        "      <td>Watford</td>\n",
 338 |        "      <td>0</td>\n",
 339 |        "      <td>0</td>\n",
 340 |        "      <td>D</td>\n",
 341 |        "      <td>0</td>\n",
 342 |        "      <td>0</td>\n",
 343 |        "      <td>...</td>\n",
 344 |        "      <td>1.73</td>\n",
 345 |        "      <td>-0.25</td>\n",
 346 |        "      <td>1.90</td>\n",
 347 |        "      <td>2.00</td>\n",
 348 |        "      <td>1.89</td>\n",
 349 |        "      <td>2.03</td>\n",
 350 |        "      <td>1.93</td>\n",
 351 |        "      <td>2.07</td>\n",
 352 |        "      <td>1.87</td>\n",
 353 |        "      <td>2.01</td>\n",
 354 |        "    </tr>\n",
 355 |        "  </tbody>\n",
 356 |        "</table>\n",
 357 |        "<p>215 rows × 106 columns</p>\n",
 358 |        "</div>"
 359 |       ],
 360 |       "text/plain": [
 361 |        "    Div        Date   Time        HomeTeam        AwayTeam  FTHG  FTAG FTR  \\\n",
 362 |        "0    E0  13/08/2021  20:00       Brentford         Arsenal     2     0   H   \n",
 363 |        "1    E0  14/08/2021  12:30      Man United           Leeds     5     1   H   \n",
 364 |        "2    E0  14/08/2021  15:00         Burnley        Brighton     1     2   A   \n",
 365 |        "3    E0  14/08/2021  15:00         Chelsea  Crystal Palace     3     0   H   \n",
 366 |        "4    E0  14/08/2021  15:00         Everton     Southampton     3     1   H   \n",
 367 |        "..   ..         ...    ...             ...             ...   ...   ...  ..   \n",
 368 |        "210  E0  23/01/2022  14:00         Arsenal         Burnley     0     0   D   \n",
 369 |        "211  E0  23/01/2022  14:00  Crystal Palace       Liverpool     1     3   A   \n",
 370 |        "212  E0  23/01/2022  14:00       Leicester        Brighton     1     1   D   \n",
 371 |        "213  E0  23/01/2022  16:30         Chelsea       Tottenham     2     0   H   \n",
 372 |        "214  E0  05/02/2022  18:00         Burnley         Watford     0     0   D   \n",
 373 |        "\n",
 374 |        "     HTHG  HTAG  ... AvgC<2.5  AHCh  B365CAHH  B365CAHA  PCAHH  PCAHA  \\\n",
 375 |        "0       1     0  ...     1.62  0.50      1.75      2.05   1.81   2.13   \n",
 376 |        "1       1     0  ...     2.25 -1.00      2.05      1.75   2.17   1.77   \n",
 377 |        "2       1     0  ...     1.62  0.25      1.79      2.15   1.81   2.14   \n",
 378 |        "3       2     0  ...     1.94 -1.50      2.05      1.75   2.12   1.81   \n",
 379 |        "4       0     1  ...     1.67 -0.50      2.05      1.88   2.05   1.88   \n",
 380 |        "..    ...   ...  ...      ...   ...       ...       ...    ...    ...   \n",
 381 |        "210     0     0  ...     2.32 -1.50      1.92      2.01   1.93   2.00   \n",
 382 |        "211     0     2  ...     2.11  1.00      1.96      1.97   1.94   1.97   \n",
 383 |        "212     0     0  ...     2.10  0.00      1.92      2.01   1.93   1.99   \n",
 384 |        "213     0     0  ...     1.84 -0.75      1.99      1.94   1.97   1.95   \n",
 385 |        "214     0     0  ...     1.73 -0.25      1.90      2.00   1.89   2.03   \n",
 386 |        "\n",
 387 |        "     MaxCAHH  MaxCAHA  AvgCAHH  AvgCAHA  \n",
 388 |        "0       2.05     2.17     1.80     2.09  \n",
 389 |        "1       2.19     1.93     2.10     1.79  \n",
 390 |        "2       1.82     2.19     1.79     2.12  \n",
 391 |        "3       2.16     1.93     2.06     1.82  \n",
 392 |        "4       2.08     1.90     2.03     1.86  \n",
 393 |        "..       ...      ...      ...      ...  \n",
 394 |        "210     1.93     2.11     1.90     1.98  \n",
 395 |        "211     2.07     2.02     1.92     1.96  \n",
 396 |        "212     1.94     2.13     1.87     2.01  \n",
 397 |        "213     2.03     2.07     1.96     1.92  \n",
 398 |        "214     1.93     2.07     1.87     2.01  \n",
 399 |        "\n",
 400 |        "[215 rows x 106 columns]"
 401 |       ]
 402 |      },
 403 |      "execution_count": 3,
 404 |      "metadata": {},
 405 |      "output_type": "execute_result"
 406 |     }
 407 |    ],
 408 |    "source": [
 409 |     "# showing dataframe\n",
 410 |     "df_premier21"
 411 |    ]
 412 |   },
 413 |   {
 414 |    "cell_type": "code",
 415 |    "execution_count": 4,
 416 |    "id": "f9bcd9f5",
 417 |    "metadata": {},
 418 |    "outputs": [],
 419 |    "source": [
 420 |     "# rename columns\n",
 421 |     "df_premier21 = df_premier21.rename(columns={'Date':'date',\n",
 422 |     "                                            'HomeTeam':'home_team',\n",
 423 |     "                                            'AwayTeam':'away_team',\n",
 424 |     "                                            'FTHG': 'home_goals',\n",
 425 |     "                                            'FTAG': 'away_goals'})"
 426 |    ]
 427 |   },
 428 |   {
 429 |    "cell_type": "code",
 430 |    "execution_count": 5,
 431 |    "id": "a650ca82",
 432 |    "metadata": {},
 433 |    "outputs": [
 434 |     {
 435 |      "data": {
 436 |       "text/html": [
 437 |        "<div>\n",
 438 |        "<style scoped>\n",
 439 |        "    .dataframe tbody tr th:only-of-type {\n",
 440 |        "        vertical-align: middle;\n",
 441 |        "    }\n",
 442 |        "\n",
 443 |        "    .dataframe tbody tr th {\n",
 444 |        "        vertical-align: top;\n",
 445 |        "    }\n",
 446 |        "\n",
 447 |        "    .dataframe thead th {\n",
 448 |        "        text-align: right;\n",
 449 |        "    }\n",
 450 |        "</style>\n",
 451 |        "<table border=\"1\" class=\"dataframe\">\n",
 452 |        "  <thead>\n",
 453 |        "    <tr style=\"text-align: right;\">\n",
 454 |        "      <th></th>\n",
 455 |        "      <th>Div</th>\n",
 456 |        "      <th>date</th>\n",
 457 |        "      <th>Time</th>\n",
 458 |        "      <th>home_team</th>\n",
 459 |        "      <th>away_team</th>\n",
 460 |        "      <th>home_goals</th>\n",
 461 |        "      <th>away_goals</th>\n",
 462 |        "      <th>FTR</th>\n",
 463 |        "      <th>HTHG</th>\n",
 464 |        "      <th>HTAG</th>\n",
 465 |        "      <th>...</th>\n",
 466 |        "      <th>AvgC&lt;2.5</th>\n",
 467 |        "      <th>AHCh</th>\n",
 468 |        "      <th>B365CAHH</th>\n",
 469 |        "      <th>B365CAHA</th>\n",
 470 |        "      <th>PCAHH</th>\n",
 471 |        "      <th>PCAHA</th>\n",
 472 |        "      <th>MaxCAHH</th>\n",
 473 |        "      <th>MaxCAHA</th>\n",
 474 |        "      <th>AvgCAHH</th>\n",
 475 |        "      <th>AvgCAHA</th>\n",
 476 |        "    </tr>\n",
 477 |        "  </thead>\n",
 478 |        "  <tbody>\n",
 479 |        "    <tr>\n",
 480 |        "      <th>0</th>\n",
 481 |        "      <td>E0</td>\n",
 482 |        "      <td>13/08/2021</td>\n",
 483 |        "      <td>20:00</td>\n",
 484 |        "      <td>Brentford</td>\n",
 485 |        "      <td>Arsenal</td>\n",
 486 |        "      <td>2</td>\n",
 487 |        "      <td>0</td>\n",
 488 |        "      <td>H</td>\n",
 489 |        "      <td>1</td>\n",
 490 |        "      <td>0</td>\n",
 491 |        "      <td>...</td>\n",
 492 |        "      <td>1.62</td>\n",
 493 |        "      <td>0.50</td>\n",
 494 |        "      <td>1.75</td>\n",
 495 |        "      <td>2.05</td>\n",
 496 |        "      <td>1.81</td>\n",
 497 |        "      <td>2.13</td>\n",
 498 |        "      <td>2.05</td>\n",
 499 |        "      <td>2.17</td>\n",
 500 |        "      <td>1.80</td>\n",
 501 |        "      <td>2.09</td>\n",
 502 |        "    </tr>\n",
 503 |        "    <tr>\n",
 504 |        "      <th>1</th>\n",
 505 |        "      <td>E0</td>\n",
 506 |        "      <td>14/08/2021</td>\n",
 507 |        "      <td>12:30</td>\n",
 508 |        "      <td>Man United</td>\n",
 509 |        "      <td>Leeds</td>\n",
 510 |        "      <td>5</td>\n",
 511 |        "      <td>1</td>\n",
 512 |        "      <td>H</td>\n",
 513 |        "      <td>1</td>\n",
 514 |        "      <td>0</td>\n",
 515 |        "      <td>...</td>\n",
 516 |        "      <td>2.25</td>\n",
 517 |        "      <td>-1.00</td>\n",
 518 |        "      <td>2.05</td>\n",
 519 |        "      <td>1.75</td>\n",
 520 |        "      <td>2.17</td>\n",
 521 |        "      <td>1.77</td>\n",
 522 |        "      <td>2.19</td>\n",
 523 |        "      <td>1.93</td>\n",
 524 |        "      <td>2.10</td>\n",
 525 |        "      <td>1.79</td>\n",
 526 |        "    </tr>\n",
 527 |        "    <tr>\n",
 528 |        "      <th>2</th>\n",
 529 |        "      <td>E0</td>\n",
 530 |        "      <td>14/08/2021</td>\n",
 531 |        "      <td>15:00</td>\n",
 532 |        "      <td>Burnley</td>\n",
 533 |        "      <td>Brighton</td>\n",
 534 |        "      <td>1</td>\n",
 535 |        "      <td>2</td>\n",
 536 |        "      <td>A</td>\n",
 537 |        "      <td>1</td>\n",
 538 |        "      <td>0</td>\n",
 539 |        "      <td>...</td>\n",
 540 |        "      <td>1.62</td>\n",
 541 |        "      <td>0.25</td>\n",
 542 |        "      <td>1.79</td>\n",
 543 |        "      <td>2.15</td>\n",
 544 |        "      <td>1.81</td>\n",
 545 |        "      <td>2.14</td>\n",
 546 |        "      <td>1.82</td>\n",
 547 |        "      <td>2.19</td>\n",
 548 |        "      <td>1.79</td>\n",
 549 |        "      <td>2.12</td>\n",
 550 |        "    </tr>\n",
 551 |        "    <tr>\n",
 552 |        "      <th>3</th>\n",
 553 |        "      <td>E0</td>\n",
 554 |        "      <td>14/08/2021</td>\n",
 555 |        "      <td>15:00</td>\n",
 556 |        "      <td>Chelsea</td>\n",
 557 |        "      <td>Crystal Palace</td>\n",
 558 |        "      <td>3</td>\n",
 559 |        "      <td>0</td>\n",
 560 |        "      <td>H</td>\n",
 561 |        "      <td>2</td>\n",
 562 |        "      <td>0</td>\n",
 563 |        "      <td>...</td>\n",
 564 |        "      <td>1.94</td>\n",
 565 |        "      <td>-1.50</td>\n",
 566 |        "      <td>2.05</td>\n",
 567 |        "      <td>1.75</td>\n",
 568 |        "      <td>2.12</td>\n",
 569 |        "      <td>1.81</td>\n",
 570 |        "      <td>2.16</td>\n",
 571 |        "      <td>1.93</td>\n",
 572 |        "      <td>2.06</td>\n",
 573 |        "      <td>1.82</td>\n",
 574 |        "    </tr>\n",
 575 |        "    <tr>\n",
 576 |        "      <th>4</th>\n",
 577 |        "      <td>E0</td>\n",
 578 |        "      <td>14/08/2021</td>\n",
 579 |        "      <td>15:00</td>\n",
 580 |        "      <td>Everton</td>\n",
 581 |        "      <td>Southampton</td>\n",
 582 |        "      <td>3</td>\n",
 583 |        "      <td>1</td>\n",
 584 |        "      <td>H</td>\n",
 585 |        "      <td>0</td>\n",
 586 |        "      <td>1</td>\n",
 587 |        "      <td>...</td>\n",
 588 |        "      <td>1.67</td>\n",
 589 |        "      <td>-0.50</td>\n",
 590 |        "      <td>2.05</td>\n",
 591 |        "      <td>1.88</td>\n",
 592 |        "      <td>2.05</td>\n",
 593 |        "      <td>1.88</td>\n",
 594 |        "      <td>2.08</td>\n",
 595 |        "      <td>1.90</td>\n",
 596 |        "      <td>2.03</td>\n",
 597 |        "      <td>1.86</td>\n",
 598 |        "    </tr>\n",
 599 |        "    <tr>\n",
 600 |        "      <th>...</th>\n",
 601 |        "      <td>...</td>\n",
 602 |        "      <td>...</td>\n",
 603 |        "      <td>...</td>\n",
 604 |        "      <td>...</td>\n",
 605 |        "      <td>...</td>\n",
 606 |        "      <td>...</td>\n",
 607 |        "      <td>...</td>\n",
 608 |        "      <td>...</td>\n",
 609 |        "      <td>...</td>\n",
 610 |        "      <td>...</td>\n",
 611 |        "      <td>...</td>\n",
 612 |        "      <td>...</td>\n",
 613 |        "      <td>...</td>\n",
 614 |        "      <td>...</td>\n",
 615 |        "      <td>...</td>\n",
 616 |        "      <td>...</td>\n",
 617 |        "      <td>...</td>\n",
 618 |        "      <td>...</td>\n",
 619 |        "      <td>...</td>\n",
 620 |        "      <td>...</td>\n",
 621 |        "      <td>...</td>\n",
 622 |        "    </tr>\n",
 623 |        "    <tr>\n",
 624 |        "      <th>210</th>\n",
 625 |        "      <td>E0</td>\n",
 626 |        "      <td>23/01/2022</td>\n",
 627 |        "      <td>14:00</td>\n",
 628 |        "      <td>Arsenal</td>\n",
 629 |        "      <td>Burnley</td>\n",
 630 |        "      <td>0</td>\n",
 631 |        "      <td>0</td>\n",
 632 |        "      <td>D</td>\n",
 633 |        "      <td>0</td>\n",
 634 |        "      <td>0</td>\n",
 635 |        "      <td>...</td>\n",
 636 |        "      <td>2.32</td>\n",
 637 |        "      <td>-1.50</td>\n",
 638 |        "      <td>1.92</td>\n",
 639 |        "      <td>2.01</td>\n",
 640 |        "      <td>1.93</td>\n",
 641 |        "      <td>2.00</td>\n",
 642 |        "      <td>1.93</td>\n",
 643 |        "      <td>2.11</td>\n",
 644 |        "      <td>1.90</td>\n",
 645 |        "      <td>1.98</td>\n",
 646 |        "    </tr>\n",
 647 |        "    <tr>\n",
 648 |        "      <th>211</th>\n",
 649 |        "      <td>E0</td>\n",
 650 |        "      <td>23/01/2022</td>\n",
 651 |        "      <td>14:00</td>\n",
 652 |        "      <td>Crystal Palace</td>\n",
 653 |        "      <td>Liverpool</td>\n",
 654 |        "      <td>1</td>\n",
 655 |        "      <td>3</td>\n",
 656 |        "      <td>A</td>\n",
 657 |        "      <td>0</td>\n",
 658 |        "      <td>2</td>\n",
 659 |        "      <td>...</td>\n",
 660 |        "      <td>2.11</td>\n",
 661 |        "      <td>1.00</td>\n",
 662 |        "      <td>1.96</td>\n",
 663 |        "      <td>1.97</td>\n",
 664 |        "      <td>1.94</td>\n",
 665 |        "      <td>1.97</td>\n",
 666 |        "      <td>2.07</td>\n",
 667 |        "      <td>2.02</td>\n",
 668 |        "      <td>1.92</td>\n",
 669 |        "      <td>1.96</td>\n",
 670 |        "    </tr>\n",
 671 |        "    <tr>\n",
 672 |        "      <th>212</th>\n",
 673 |        "      <td>E0</td>\n",
 674 |        "      <td>23/01/2022</td>\n",
 675 |        "      <td>14:00</td>\n",
 676 |        "      <td>Leicester</td>\n",
 677 |        "      <td>Brighton</td>\n",
 678 |        "      <td>1</td>\n",
 679 |        "      <td>1</td>\n",
 680 |        "      <td>D</td>\n",
 681 |        "      <td>0</td>\n",
 682 |        "      <td>0</td>\n",
 683 |        "      <td>...</td>\n",
 684 |        "      <td>2.10</td>\n",
 685 |        "      <td>0.00</td>\n",
 686 |        "      <td>1.92</td>\n",
 687 |        "      <td>2.01</td>\n",
 688 |        "      <td>1.93</td>\n",
 689 |        "      <td>1.99</td>\n",
 690 |        "      <td>1.94</td>\n",
 691 |        "      <td>2.13</td>\n",
 692 |        "      <td>1.87</td>\n",
 693 |        "      <td>2.01</td>\n",
 694 |        "    </tr>\n",
 695 |        "    <tr>\n",
 696 |        "      <th>213</th>\n",
 697 |        "      <td>E0</td>\n",
 698 |        "      <td>23/01/2022</td>\n",
 699 |        "      <td>16:30</td>\n",
 700 |        "      <td>Chelsea</td>\n",
 701 |        "      <td>Tottenham</td>\n",
 702 |        "      <td>2</td>\n",
 703 |        "      <td>0</td>\n",
 704 |        "      <td>H</td>\n",
 705 |        "      <td>0</td>\n",
 706 |        "      <td>0</td>\n",
 707 |        "      <td>...</td>\n",
 708 |        "      <td>1.84</td>\n",
 709 |        "      <td>-0.75</td>\n",
 710 |        "      <td>1.99</td>\n",
 711 |        "      <td>1.94</td>\n",
 712 |        "      <td>1.97</td>\n",
 713 |        "      <td>1.95</td>\n",
 714 |        "      <td>2.03</td>\n",
 715 |        "      <td>2.07</td>\n",
 716 |        "      <td>1.96</td>\n",
 717 |        "      <td>1.92</td>\n",
 718 |        "    </tr>\n",
 719 |        "    <tr>\n",
 720 |        "      <th>214</th>\n",
 721 |        "      <td>E0</td>\n",
 722 |        "      <td>05/02/2022</td>\n",
 723 |        "      <td>18:00</td>\n",
 724 |        "      <td>Burnley</td>\n",
 725 |        "      <td>Watford</td>\n",
 726 |        "      <td>0</td>\n",
 727 |        "      <td>0</td>\n",
 728 |        "      <td>D</td>\n",
 729 |        "      <td>0</td>\n",
 730 |        "      <td>0</td>\n",
 731 |        "      <td>...</td>\n",
 732 |        "      <td>1.73</td>\n",
 733 |        "      <td>-0.25</td>\n",
 734 |        "      <td>1.90</td>\n",
 735 |        "      <td>2.00</td>\n",
 736 |        "      <td>1.89</td>\n",
 737 |        "      <td>2.03</td>\n",
 738 |        "      <td>1.93</td>\n",
 739 |        "      <td>2.07</td>\n",
 740 |        "      <td>1.87</td>\n",
 741 |        "      <td>2.01</td>\n",
 742 |        "    </tr>\n",
 743 |        "  </tbody>\n",
 744 |        "</table>\n",
 745 |        "<p>215 rows × 106 columns</p>\n",
 746 |        "</div>"
 747 |       ],
 748 |       "text/plain": [
 749 |        "    Div        date   Time       home_team       away_team  home_goals  \\\n",
 750 |        "0    E0  13/08/2021  20:00       Brentford         Arsenal           2   \n",
 751 |        "1    E0  14/08/2021  12:30      Man United           Leeds           5   \n",
 752 |        "2    E0  14/08/2021  15:00         Burnley        Brighton           1   \n",
 753 |        "3    E0  14/08/2021  15:00         Chelsea  Crystal Palace           3   \n",
 754 |        "4    E0  14/08/2021  15:00         Everton     Southampton           3   \n",
 755 |        "..   ..         ...    ...             ...             ...         ...   \n",
 756 |        "210  E0  23/01/2022  14:00         Arsenal         Burnley           0   \n",
 757 |        "211  E0  23/01/2022  14:00  Crystal Palace       Liverpool           1   \n",
 758 |        "212  E0  23/01/2022  14:00       Leicester        Brighton           1   \n",
 759 |        "213  E0  23/01/2022  16:30         Chelsea       Tottenham           2   \n",
 760 |        "214  E0  05/02/2022  18:00         Burnley         Watford           0   \n",
 761 |        "\n",
 762 |        "     away_goals FTR  HTHG  HTAG  ... AvgC<2.5  AHCh  B365CAHH  B365CAHA  \\\n",
 763 |        "0             0   H     1     0  ...     1.62  0.50      1.75      2.05   \n",
 764 |        "1             1   H     1     0  ...     2.25 -1.00      2.05      1.75   \n",
 765 |        "2             2   A     1     0  ...     1.62  0.25      1.79      2.15   \n",
 766 |        "3             0   H     2     0  ...     1.94 -1.50      2.05      1.75   \n",
 767 |        "4             1   H     0     1  ...     1.67 -0.50      2.05      1.88   \n",
 768 |        "..          ...  ..   ...   ...  ...      ...   ...       ...       ...   \n",
 769 |        "210           0   D     0     0  ...     2.32 -1.50      1.92      2.01   \n",
 770 |        "211           3   A     0     2  ...     2.11  1.00      1.96      1.97   \n",
 771 |        "212           1   D     0     0  ...     2.10  0.00      1.92      2.01   \n",
 772 |        "213           0   H     0     0  ...     1.84 -0.75      1.99      1.94   \n",
 773 |        "214           0   D     0     0  ...     1.73 -0.25      1.90      2.00   \n",
 774 |        "\n",
 775 |        "     PCAHH  PCAHA  MaxCAHH  MaxCAHA  AvgCAHH  AvgCAHA  \n",
 776 |        "0     1.81   2.13     2.05     2.17     1.80     2.09  \n",
 777 |        "1     2.17   1.77     2.19     1.93     2.10     1.79  \n",
 778 |        "2     1.81   2.14     1.82     2.19     1.79     2.12  \n",
 779 |        "3     2.12   1.81     2.16     1.93     2.06     1.82  \n",
 780 |        "4     2.05   1.88     2.08     1.90     2.03     1.86  \n",
 781 |        "..     ...    ...      ...      ...      ...      ...  \n",
 782 |        "210   1.93   2.00     1.93     2.11     1.90     1.98  \n",
 783 |        "211   1.94   1.97     2.07     2.02     1.92     1.96  \n",
 784 |        "212   1.93   1.99     1.94     2.13     1.87     2.01  \n",
 785 |        "213   1.97   1.95     2.03     2.07     1.96     1.92  \n",
 786 |        "214   1.89   2.03     1.93     2.07     1.87     2.01  \n",
 787 |        "\n",
 788 |        "[215 rows x 106 columns]"
 789 |       ]
 790 |      },
 791 |      "execution_count": 5,
 792 |      "metadata": {},
 793 |      "output_type": "execute_result"
 794 |     }
 795 |    ],
 796 |    "source": [
 797 |     "# show dataframe\n",
 798 |     "df_premier21"
 799 |    ]
 800 |   },
 801 |   {
 802 |    "cell_type": "markdown",
 803 |    "id": "sacred-march",
 804 |    "metadata": {},
 805 |    "source": []
 806 |   },
 807 |   {
 808 |    "cell_type": "markdown",
 809 |    "id": "sacred-directive",
 810 |    "metadata": {},
 811 |    "source": [
 812 |     "# Read HTML"
 813 |    ]
 814 |   },
 815 |   {
 816 |    "cell_type": "markdown",
 817 |    "id": "dental-cradle",
 818 |    "metadata": {},
 819 |    "source": [
 820 |     "Target Website: https://en.wikipedia.org/wiki/List_of_The_Simpsons_episodes_(seasons_1%E2%80%9320)"
 821 |    ]
 822 |   },
 823 |   {
 824 |    "cell_type": "code",
 825 |    "execution_count": 6,
 826 |    "id": "sacred-louisville",
 827 |    "metadata": {},
 828 |    "outputs": [],
 829 |    "source": [
 830 |     "simpsons = pd.read_html('https://en.wikipedia.org/wiki/List_of_The_Simpsons_episodes_(seasons_1%E2%80%9320)')"
 831 |    ]
 832 |   },
 833 |   {
 834 |    "cell_type": "code",
 835 |    "execution_count": 7,
 836 |    "id": "pending-plaza",
 837 |    "metadata": {},
 838 |    "outputs": [
 839 |     {
 840 |      "data": {
 841 |       "text/html": [
 842 |        "<div>\n",
 843 |        "<style scoped>\n",
 844 |        "    .dataframe tbody tr th:only-of-type {\n",
 845 |        "        vertical-align: middle;\n",
 846 |        "    }\n",
 847 |        "\n",
 848 |        "    .dataframe tbody tr th {\n",
 849 |        "        vertical-align: top;\n",
 850 |        "    }\n",
 851 |        "\n",
 852 |        "    .dataframe thead th {\n",
 853 |        "        text-align: right;\n",
 854 |        "    }\n",
 855 |        "</style>\n",
 856 |        "<table border=\"1\" class=\"dataframe\">\n",
 857 |        "  <thead>\n",
 858 |        "    <tr style=\"text-align: right;\">\n",
 859 |        "      <th></th>\n",
 860 |        "      <th>No.overall</th>\n",
 861 |        "      <th>No. inseason</th>\n",
 862 |        "      <th>Title</th>\n",
 863 |        "      <th>Directed by</th>\n",
 864 |        "      <th>Written by</th>\n",
 865 |        "      <th>Original air date</th>\n",
 866 |        "      <th>Prod.code</th>\n",
 867 |        "      <th>U.S. viewers(millions)</th>\n",
 868 |        "    </tr>\n",
 869 |        "  </thead>\n",
 870 |        "  <tbody>\n",
 871 |        "    <tr>\n",
 872 |        "      <th>0</th>\n",
 873 |        "      <td>1</td>\n",
 874 |        "      <td>1</td>\n",
 875 |        "      <td>\"Simpsons Roasting on an Open Fire\"</td>\n",
 876 |        "      <td>David Silverman</td>\n",
 877 |        "      <td>Mimi Pond</td>\n",
 878 |        "      <td>December 17, 1989</td>\n",
 879 |        "      <td>7G08</td>\n",
 880 |        "      <td>26.7[46]</td>\n",
 881 |        "    </tr>\n",
 882 |        "    <tr>\n",
 883 |        "      <th>1</th>\n",
 884 |        "      <td>2</td>\n",
 885 |        "      <td>2</td>\n",
 886 |        "      <td>\"Bart the Genius\"</td>\n",
 887 |        "      <td>David Silverman</td>\n",
 888 |        "      <td>Jon Vitti</td>\n",
 889 |        "      <td>January 14, 1990</td>\n",
 890 |        "      <td>7G02</td>\n",
 891 |        "      <td>24.5[46]</td>\n",
 892 |        "    </tr>\n",
 893 |        "    <tr>\n",
 894 |        "      <th>2</th>\n",
 895 |        "      <td>3</td>\n",
 896 |        "      <td>3</td>\n",
 897 |        "      <td>\"Homer's Odyssey\"</td>\n",
 898 |        "      <td>Wesley Archer</td>\n",
 899 |        "      <td>Jay Kogen &amp; Wallace Wolodarsky</td>\n",
 900 |        "      <td>January 21, 1990</td>\n",
 901 |        "      <td>7G03</td>\n",
 902 |        "      <td>27.5[47]</td>\n",
 903 |        "    </tr>\n",
 904 |        "    <tr>\n",
 905 |        "      <th>3</th>\n",
 906 |        "      <td>4</td>\n",
 907 |        "      <td>4</td>\n",
 908 |        "      <td>\"There's No Disgrace Like Home\"</td>\n",
 909 |        "      <td>Gregg Vanzo &amp; Kent Butterworth</td>\n",
 910 |        "      <td>Al Jean &amp; Mike Reiss</td>\n",
 911 |        "      <td>January 28, 1990</td>\n",
 912 |        "      <td>7G04</td>\n",
 913 |        "      <td>20.2[48]</td>\n",
 914 |        "    </tr>\n",
 915 |        "    <tr>\n",
 916 |        "      <th>4</th>\n",
 917 |        "      <td>5</td>\n",
 918 |        "      <td>5</td>\n",
 919 |        "      <td>\"Bart the General\"</td>\n",
 920 |        "      <td>David Silverman</td>\n",
 921 |        "      <td>John Swartzwelder</td>\n",
 922 |        "      <td>February 4, 1990</td>\n",
 923 |        "      <td>7G05</td>\n",
 924 |        "      <td>27.1[49]</td>\n",
 925 |        "    </tr>\n",
 926 |        "  </tbody>\n",
 927 |        "</table>\n",
 928 |        "</div>"
 929 |       ],
 930 |       "text/plain": [
 931 |        "   No.overall  No. inseason                                Title  \\\n",
 932 |        "0           1             1  \"Simpsons Roasting on an Open Fire\"   \n",
 933 |        "1           2             2                    \"Bart the Genius\"   \n",
 934 |        "2           3             3                    \"Homer's Odyssey\"   \n",
 935 |        "3           4             4      \"There's No Disgrace Like Home\"   \n",
 936 |        "4           5             5                   \"Bart the General\"   \n",
 937 |        "\n",
 938 |        "                      Directed by                      Written by  \\\n",
 939 |        "0                 David Silverman                       Mimi Pond   \n",
 940 |        "1                 David Silverman                       Jon Vitti   \n",
 941 |        "2                   Wesley Archer  Jay Kogen & Wallace Wolodarsky   \n",
 942 |        "3  Gregg Vanzo & Kent Butterworth            Al Jean & Mike Reiss   \n",
 943 |        "4                 David Silverman               John Swartzwelder   \n",
 944 |        "\n",
 945 |        "   Original air date Prod.code U.S. viewers(millions)  \n",
 946 |        "0  December 17, 1989      7G08               26.7[46]  \n",
 947 |        "1   January 14, 1990      7G02               24.5[46]  \n",
 948 |        "2   January 21, 1990      7G03               27.5[47]  \n",
 949 |        "3   January 28, 1990      7G04               20.2[48]  \n",
 950 |        "4   February 4, 1990      7G05               27.1[49]  "
 951 |       ]
 952 |      },
 953 |      "execution_count": 7,
 954 |      "metadata": {},
 955 |      "output_type": "execute_result"
 956 |     }
 957 |    ],
 958 |    "source": [
 959 |     "simpsons[1].head()"
 960 |    ]
 961 |   }
 962 |  ],
 963 |  "metadata": {
 964 |   "hide_input": false,
 965 |   "kernelspec": {
 966 |    "display_name": "Python 3",
 967 |    "language": "python",
 968 |    "name": "python3"
 969 |   },
 970 |   "language_info": {
 971 |    "codemirror_mode": {
 972 |     "name": "ipython",
 973 |     "version": 3
 974 |    },
 975 |    "file_extension": ".py",
 976 |    "mimetype": "text/x-python",
 977 |    "name": "python",
 978 |    "nbconvert_exporter": "python",
 979 |    "pygments_lexer": "ipython3",
 980 |    "version": "3.7.3"
 981 |   },
 982 |   "nbTranslate": {
 983 |    "displayLangs": [
 984 |     "es",
 985 |     "en"
 986 |    ],
 987 |    "hotkey": "alt-t",
 988 |    "langInMainMenu": true,
 989 |    "sourceLang": "en",
 990 |    "targetLang": "es",
 991 |    "useGoogleTranslate": true
 992 |   },
 993 |   "toc": {
 994 |    "base_numbering": 1,
 995 |    "nav_menu": {},
 996 |    "number_sections": true,
 997 |    "sideBar": true,
 998 |    "skip_h1_title": false,
 999 |    "title_cell": "Table of Contents",
1000 |    "title_sidebar": "Contents",
1001 |    "toc_cell": false,
1002 |    "toc_position": {},
1003 |    "toc_section_display": true,
1004 |    "toc_window_display": false
1005 |   }
1006 |  },
1007 |  "nbformat": 4,
1008 |  "nbformat_minor": 5
1009 | }
1010 | 


--------------------------------------------------------------------------------
/loc vs iloc.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "markdown",
  5 |    "id": "90a2167f",
  6 |    "metadata": {},
  7 |    "source": [
  8 |     "# loc vs iloc"
  9 |    ]
 10 |   },
 11 |   {
 12 |    "cell_type": "code",
 13 |    "execution_count": 1,
 14 |    "id": "bc43ac4b",
 15 |    "metadata": {},
 16 |    "outputs": [],
 17 |    "source": [
 18 |     "import pandas as pd"
 19 |    ]
 20 |   },
 21 |   {
 22 |    "cell_type": "code",
 23 |    "execution_count": 2,
 24 |    "id": "bc70a60e",
 25 |    "metadata": {},
 26 |    "outputs": [],
 27 |    "source": [
 28 |     "names = ['L. Messi', 'Cristiano Ronaldo', 'Neymar Jr', 'J. Oblak', 'E. Hazard']\n",
 29 |     "age = [32, 34, 27, 26, 28]\n",
 30 |     "height_cm = [170, 187, 175, 188, 175]\n",
 31 |     "nationality = ['Argentina', 'Portugal', 'Brazil', 'Slovenia', 'Belgium']\n",
 32 |     "club = ['Paris Saint-Germain', 'Manchester United', 'Paris Saint-Germain', 'Atlético Madrid', 'Real Madrid']\n",
 33 |     "\n",
 34 |     "df = pd.DataFrame(index=names, data={'age':age, 'height_cm':height_cm, 'nationality':nationality, 'club':club})"
 35 |    ]
 36 |   },
 37 |   {
 38 |    "cell_type": "code",
 39 |    "execution_count": 3,
 40 |    "id": "f85e1494",
 41 |    "metadata": {},
 42 |    "outputs": [
 43 |     {
 44 |      "data": {
 45 |       "text/html": [
 46 |        "<div>\n",
 47 |        "<style scoped>\n",
 48 |        "    .dataframe tbody tr th:only-of-type {\n",
 49 |        "        vertical-align: middle;\n",
 50 |        "    }\n",
 51 |        "\n",
 52 |        "    .dataframe tbody tr th {\n",
 53 |        "        vertical-align: top;\n",
 54 |        "    }\n",
 55 |        "\n",
 56 |        "    .dataframe thead th {\n",
 57 |        "        text-align: right;\n",
 58 |        "    }\n",
 59 |        "</style>\n",
 60 |        "<table border=\"1\" class=\"dataframe\">\n",
 61 |        "  <thead>\n",
 62 |        "    <tr style=\"text-align: right;\">\n",
 63 |        "      <th></th>\n",
 64 |        "      <th>age</th>\n",
 65 |        "      <th>height_cm</th>\n",
 66 |        "      <th>nationality</th>\n",
 67 |        "      <th>club</th>\n",
 68 |        "    </tr>\n",
 69 |        "  </thead>\n",
 70 |        "  <tbody>\n",
 71 |        "    <tr>\n",
 72 |        "      <th>L. Messi</th>\n",
 73 |        "      <td>32</td>\n",
 74 |        "      <td>170</td>\n",
 75 |        "      <td>Argentina</td>\n",
 76 |        "      <td>Paris Saint-Germain</td>\n",
 77 |        "    </tr>\n",
 78 |        "    <tr>\n",
 79 |        "      <th>Cristiano Ronaldo</th>\n",
 80 |        "      <td>34</td>\n",
 81 |        "      <td>187</td>\n",
 82 |        "      <td>Portugal</td>\n",
 83 |        "      <td>Manchester United</td>\n",
 84 |        "    </tr>\n",
 85 |        "    <tr>\n",
 86 |        "      <th>Neymar Jr</th>\n",
 87 |        "      <td>27</td>\n",
 88 |        "      <td>175</td>\n",
 89 |        "      <td>Brazil</td>\n",
 90 |        "      <td>Paris Saint-Germain</td>\n",
 91 |        "    </tr>\n",
 92 |        "    <tr>\n",
 93 |        "      <th>J. Oblak</th>\n",
 94 |        "      <td>26</td>\n",
 95 |        "      <td>188</td>\n",
 96 |        "      <td>Slovenia</td>\n",
 97 |        "      <td>Atlético Madrid</td>\n",
 98 |        "    </tr>\n",
 99 |        "    <tr>\n",
100 |        "      <th>E. Hazard</th>\n",
101 |        "      <td>28</td>\n",
102 |        "      <td>175</td>\n",
103 |        "      <td>Belgium</td>\n",
104 |        "      <td>Real Madrid</td>\n",
105 |        "    </tr>\n",
106 |        "  </tbody>\n",
107 |        "</table>\n",
108 |        "</div>"
109 |       ],
110 |       "text/plain": [
111 |        "                   age  height_cm nationality                 club\n",
112 |        "L. Messi            32        170   Argentina  Paris Saint-Germain\n",
113 |        "Cristiano Ronaldo   34        187    Portugal    Manchester United\n",
114 |        "Neymar Jr           27        175      Brazil  Paris Saint-Germain\n",
115 |        "J. Oblak            26        188    Slovenia      Atlético Madrid\n",
116 |        "E. Hazard           28        175     Belgium          Real Madrid"
117 |       ]
118 |      },
119 |      "execution_count": 3,
120 |      "metadata": {},
121 |      "output_type": "execute_result"
122 |     }
123 |    ],
124 |    "source": [
125 |     "df"
126 |    ]
127 |   },
128 |   {
129 |    "cell_type": "markdown",
130 |    "id": "afe4e373",
131 |    "metadata": {},
132 |    "source": [
133 |     "## Selecting with a single value"
134 |    ]
135 |   },
136 |   {
137 |    "cell_type": "code",
138 |    "execution_count": 4,
139 |    "id": "e67bf7a1",
140 |    "metadata": {},
141 |    "outputs": [
142 |     {
143 |      "data": {
144 |       "text/plain": [
145 |        "170"
146 |       ]
147 |      },
148 |      "execution_count": 4,
149 |      "metadata": {},
150 |      "output_type": "execute_result"
151 |     }
152 |    ],
153 |    "source": [
154 |     "# get the height of L.Messi\n",
155 |     "# loc\n",
156 |     "df.loc['L. Messi', 'height_cm']\n",
157 |     "# iloc\n",
158 |     "df.iloc[0, 1]"
159 |    ]
160 |   },
161 |   {
162 |    "cell_type": "code",
163 |    "execution_count": 5,
164 |    "id": "fcebb39c",
165 |    "metadata": {},
166 |    "outputs": [
167 |     {
168 |      "data": {
169 |       "text/plain": [
170 |        "187"
171 |       ]
172 |      },
173 |      "execution_count": 5,
174 |      "metadata": {},
175 |      "output_type": "execute_result"
176 |     }
177 |    ],
178 |    "source": [
179 |     "# get the height of Cristiano Ronaldo\n",
180 |     "# loc\n",
181 |     "df.loc['Cristiano Ronaldo', 'height_cm']\n",
182 |     "# iloc\n",
183 |     "df.iloc[1, 1]"
184 |    ]
185 |   },
186 |   {
187 |    "cell_type": "code",
188 |    "execution_count": 6,
189 |    "id": "e86ba675",
190 |    "metadata": {},
191 |    "outputs": [
192 |     {
193 |      "data": {
194 |       "text/plain": [
195 |        "age                             32\n",
196 |        "height_cm                      170\n",
197 |        "nationality              Argentina\n",
198 |        "club           Paris Saint-Germain\n",
199 |        "Name: L. Messi, dtype: object"
200 |       ]
201 |      },
202 |      "execution_count": 6,
203 |      "metadata": {},
204 |      "output_type": "execute_result"
205 |     }
206 |    ],
207 |    "source": [
208 |     "# get all the data about L.Messi\n",
209 |     "# loc\n",
210 |     "df.loc['L. Messi', :]\n",
211 |     "# iloc\n",
212 |     "df.iloc[0, :]"
213 |    ]
214 |   },
215 |   {
216 |    "cell_type": "markdown",
217 |    "id": "71d2b2b8",
218 |    "metadata": {},
219 |    "source": [
220 |     "## Selecting with a list of values"
221 |    ]
222 |   },
223 |   {
224 |    "cell_type": "code",
225 |    "execution_count": 7,
226 |    "id": "f62aa834",
227 |    "metadata": {},
228 |    "outputs": [
229 |     {
230 |      "data": {
231 |       "text/html": [
232 |        "<div>\n",
233 |        "<style scoped>\n",
234 |        "    .dataframe tbody tr th:only-of-type {\n",
235 |        "        vertical-align: middle;\n",
236 |        "    }\n",
237 |        "\n",
238 |        "    .dataframe tbody tr th {\n",
239 |        "        vertical-align: top;\n",
240 |        "    }\n",
241 |        "\n",
242 |        "    .dataframe thead th {\n",
243 |        "        text-align: right;\n",
244 |        "    }\n",
245 |        "</style>\n",
246 |        "<table border=\"1\" class=\"dataframe\">\n",
247 |        "  <thead>\n",
248 |        "    <tr style=\"text-align: right;\">\n",
249 |        "      <th></th>\n",
250 |        "      <th>age</th>\n",
251 |        "      <th>height_cm</th>\n",
252 |        "      <th>nationality</th>\n",
253 |        "      <th>club</th>\n",
254 |        "    </tr>\n",
255 |        "  </thead>\n",
256 |        "  <tbody>\n",
257 |        "    <tr>\n",
258 |        "      <th>L. Messi</th>\n",
259 |        "      <td>32</td>\n",
260 |        "      <td>170</td>\n",
261 |        "      <td>Argentina</td>\n",
262 |        "      <td>Paris Saint-Germain</td>\n",
263 |        "    </tr>\n",
264 |        "    <tr>\n",
265 |        "      <th>Cristiano Ronaldo</th>\n",
266 |        "      <td>34</td>\n",
267 |        "      <td>187</td>\n",
268 |        "      <td>Portugal</td>\n",
269 |        "      <td>Manchester United</td>\n",
270 |        "    </tr>\n",
271 |        "  </tbody>\n",
272 |        "</table>\n",
273 |        "</div>"
274 |       ],
275 |       "text/plain": [
276 |        "                   age  height_cm nationality                 club\n",
277 |        "L. Messi            32        170   Argentina  Paris Saint-Germain\n",
278 |        "Cristiano Ronaldo   34        187    Portugal    Manchester United"
279 |       ]
280 |      },
281 |      "execution_count": 7,
282 |      "metadata": {},
283 |      "output_type": "execute_result"
284 |     }
285 |    ],
286 |    "source": [
287 |     "# get all data about L.Messi and Cristiano Ronaldo\n",
288 |     "# loc\n",
289 |     "df.loc[['L. Messi', 'Cristiano Ronaldo']]\n",
290 |     "# iloc\n",
291 |     "df.iloc[[0, 1]]"
292 |    ]
293 |   },
294 |   {
295 |    "cell_type": "code",
296 |    "execution_count": 8,
297 |    "id": "78a4fed7",
298 |    "metadata": {},
299 |    "outputs": [
300 |     {
301 |      "data": {
302 |       "text/plain": [
303 |        "L. Messi             170\n",
304 |        "Cristiano Ronaldo    187\n",
305 |        "Name: height_cm, dtype: int64"
306 |       ]
307 |      },
308 |      "execution_count": 8,
309 |      "metadata": {},
310 |      "output_type": "execute_result"
311 |     }
312 |    ],
313 |    "source": [
314 |     "# get the height of L.Messi and Cristiano Ronaldo\n",
315 |     "df.loc[['L. Messi', 'Cristiano Ronaldo'], 'height_cm']\n",
316 |     "\n",
317 |     "# get the height of L.Messi and Cristiano Ronaldo\n",
318 |     "df.iloc[[0, 1], 1]"
319 |    ]
320 |   },
321 |   {
322 |    "cell_type": "markdown",
323 |    "id": "4501bd3d",
324 |    "metadata": {},
325 |    "source": [
326 |     "## Selecting a range of data with a slice"
327 |    ]
328 |   },
329 |   {
330 |    "cell_type": "code",
331 |    "execution_count": 9,
332 |    "id": "06fba14b",
333 |    "metadata": {},
334 |    "outputs": [
335 |     {
336 |      "data": {
337 |       "text/html": [
338 |        "<div>\n",
339 |        "<style scoped>\n",
340 |        "    .dataframe tbody tr th:only-of-type {\n",
341 |        "        vertical-align: middle;\n",
342 |        "    }\n",
343 |        "\n",
344 |        "    .dataframe tbody tr th {\n",
345 |        "        vertical-align: top;\n",
346 |        "    }\n",
347 |        "\n",
348 |        "    .dataframe thead th {\n",
349 |        "        text-align: right;\n",
350 |        "    }\n",
351 |        "</style>\n",
352 |        "<table border=\"1\" class=\"dataframe\">\n",
353 |        "  <thead>\n",
354 |        "    <tr style=\"text-align: right;\">\n",
355 |        "      <th></th>\n",
356 |        "      <th>age</th>\n",
357 |        "      <th>height_cm</th>\n",
358 |        "      <th>nationality</th>\n",
359 |        "    </tr>\n",
360 |        "  </thead>\n",
361 |        "  <tbody>\n",
362 |        "    <tr>\n",
363 |        "      <th>L. Messi</th>\n",
364 |        "      <td>32</td>\n",
365 |        "      <td>170</td>\n",
366 |        "      <td>Argentina</td>\n",
367 |        "    </tr>\n",
368 |        "    <tr>\n",
369 |        "      <th>Cristiano Ronaldo</th>\n",
370 |        "      <td>34</td>\n",
371 |        "      <td>187</td>\n",
372 |        "      <td>Portugal</td>\n",
373 |        "    </tr>\n",
374 |        "  </tbody>\n",
375 |        "</table>\n",
376 |        "</div>"
377 |       ],
378 |       "text/plain": [
379 |        "                   age  height_cm nationality\n",
380 |        "L. Messi            32        170   Argentina\n",
381 |        "Cristiano Ronaldo   34        187    Portugal"
382 |       ]
383 |      },
384 |      "execution_count": 9,
385 |      "metadata": {},
386 |      "output_type": "execute_result"
387 |     }
388 |    ],
389 |    "source": [
390 |     "# slice column labels: from age to nationality\n",
391 |     "# loc\n",
392 |     "players = ['L. Messi', 'Cristiano Ronaldo']\n",
393 |     "df.loc[players, 'age':'nationality']\n",
394 |     "\n",
395 |     "# iloc\n",
396 |     "players = [0, 1]\n",
397 |     "df.iloc[players, 0:3] # age:nationality+1"
398 |    ]
399 |   },
400 |   {
401 |    "cell_type": "markdown",
402 |    "id": "c17b2be7",
403 |    "metadata": {},
404 |    "source": [
405 |     "## Selecting with conditions"
406 |    ]
407 |   },
408 |   {
409 |    "cell_type": "code",
410 |    "execution_count": 10,
411 |    "id": "355313ed",
412 |    "metadata": {},
413 |    "outputs": [
414 |     {
415 |      "data": {
416 |       "text/html": [
417 |        "<div>\n",
418 |        "<style scoped>\n",
419 |        "    .dataframe tbody tr th:only-of-type {\n",
420 |        "        vertical-align: middle;\n",
421 |        "    }\n",
422 |        "\n",
423 |        "    .dataframe tbody tr th {\n",
424 |        "        vertical-align: top;\n",
425 |        "    }\n",
426 |        "\n",
427 |        "    .dataframe thead th {\n",
428 |        "        text-align: right;\n",
429 |        "    }\n",
430 |        "</style>\n",
431 |        "<table border=\"1\" class=\"dataframe\">\n",
432 |        "  <thead>\n",
433 |        "    <tr style=\"text-align: right;\">\n",
434 |        "      <th></th>\n",
435 |        "      <th>age</th>\n",
436 |        "      <th>height_cm</th>\n",
437 |        "      <th>club</th>\n",
438 |        "    </tr>\n",
439 |        "  </thead>\n",
440 |        "  <tbody>\n",
441 |        "    <tr>\n",
442 |        "      <th>Cristiano Ronaldo</th>\n",
443 |        "      <td>34</td>\n",
444 |        "      <td>187</td>\n",
445 |        "      <td>Manchester United</td>\n",
446 |        "    </tr>\n",
447 |        "    <tr>\n",
448 |        "      <th>J. Oblak</th>\n",
449 |        "      <td>26</td>\n",
450 |        "      <td>188</td>\n",
451 |        "      <td>Atlético Madrid</td>\n",
452 |        "    </tr>\n",
453 |        "  </tbody>\n",
454 |        "</table>\n",
455 |        "</div>"
456 |       ],
457 |       "text/plain": [
458 |        "                   age  height_cm               club\n",
459 |        "Cristiano Ronaldo   34        187  Manchester United\n",
460 |        "J. Oblak            26        188    Atlético Madrid"
461 |       ]
462 |      },
463 |      "execution_count": 10,
464 |      "metadata": {},
465 |      "output_type": "execute_result"
466 |     }
467 |    ],
468 |    "source": [
469 |     "# one condition: select player with height above 180cm\n",
470 |     "# loc\n",
471 |     "columns = ['age', 'height_cm', 'club']\n",
472 |     "df.loc[df['height_cm']>180, columns]\n",
473 |     "\n",
474 |     "# iloc\n",
475 |     "columns = [0,1,3]\n",
476 |     "df.iloc[list(df['height_cm']>180), columns]"
477 |    ]
478 |   },
479 |   {
480 |    "cell_type": "code",
481 |    "execution_count": 11,
482 |    "id": "2515c8f2",
483 |    "metadata": {},
484 |    "outputs": [
485 |     {
486 |      "data": {
487 |       "text/html": [
488 |        "<div>\n",
489 |        "<style scoped>\n",
490 |        "    .dataframe tbody tr th:only-of-type {\n",
491 |        "        vertical-align: middle;\n",
492 |        "    }\n",
493 |        "\n",
494 |        "    .dataframe tbody tr th {\n",
495 |        "        vertical-align: top;\n",
496 |        "    }\n",
497 |        "\n",
498 |        "    .dataframe thead th {\n",
499 |        "        text-align: right;\n",
500 |        "    }\n",
501 |        "</style>\n",
502 |        "<table border=\"1\" class=\"dataframe\">\n",
503 |        "  <thead>\n",
504 |        "    <tr style=\"text-align: right;\">\n",
505 |        "      <th></th>\n",
506 |        "      <th>age</th>\n",
507 |        "      <th>height_cm</th>\n",
508 |        "      <th>nationality</th>\n",
509 |        "      <th>club</th>\n",
510 |        "    </tr>\n",
511 |        "  </thead>\n",
512 |        "  <tbody>\n",
513 |        "    <tr>\n",
514 |        "      <th>Neymar Jr</th>\n",
515 |        "      <td>27</td>\n",
516 |        "      <td>175</td>\n",
517 |        "      <td>Brazil</td>\n",
518 |        "      <td>Paris Saint-Germain</td>\n",
519 |        "    </tr>\n",
520 |        "  </tbody>\n",
521 |        "</table>\n",
522 |        "</div>"
523 |       ],
524 |       "text/plain": [
525 |        "           age  height_cm nationality                 club\n",
526 |        "Neymar Jr   27        175      Brazil  Paris Saint-Germain"
527 |       ]
528 |      },
529 |      "execution_count": 11,
530 |      "metadata": {},
531 |      "output_type": "execute_result"
532 |     }
533 |    ],
534 |    "source": [
535 |     "# multiple conditions: select player with height above 180cm that played in PSG\n",
536 |     "# loc\n",
537 |     "df.loc[(df['height_cm']>170) & (df['club']=='Paris Saint-Germain'), :]\n",
538 |     "\n",
539 |     "# iloc\n",
540 |     "df.iloc[list((df['height_cm']>170) & (df['club']=='Paris Saint-Germain')), :]"
541 |    ]
542 |   }
543 |  ],
544 |  "metadata": {
545 |   "kernelspec": {
546 |    "display_name": "Python 3",
547 |    "language": "python",
548 |    "name": "python3"
549 |   },
550 |   "language_info": {
551 |    "codemirror_mode": {
552 |     "name": "ipython",
553 |     "version": 3
554 |    },
555 |    "file_extension": ".py",
556 |    "mimetype": "text/x-python",
557 |    "name": "python",
558 |    "nbconvert_exporter": "python",
559 |    "pygments_lexer": "ipython3",
560 |    "version": "3.8.8"
561 |   },
562 |   "toc": {
563 |    "base_numbering": 1,
564 |    "nav_menu": {},
565 |    "number_sections": true,
566 |    "sideBar": true,
567 |    "skip_h1_title": false,
568 |    "title_cell": "Table of Contents",
569 |    "title_sidebar": "Contents",
570 |    "toc_cell": false,
571 |    "toc_position": {},
572 |    "toc_section_display": true,
573 |    "toc_window_display": false
574 |   }
575 |  },
576 |  "nbformat": 4,
577 |  "nbformat_minor": 5
578 | }
579 | 


--------------------------------------------------------------------------------