├── 10 Univariate non-graphical EDA.ipynb
├── 11 Univariate visualizations (Categorical).ipynb
├── 12 Univariate visualizations (Numerical).ipynb
├── 13 Bivariate numerical.ipynb
├── 14 Bivariate Categorical - Numerical.ipynb
├── 15 Bivariate categorical .ipynb
├── 2 Understanding your data.ipynb
├── 3 Missing values.ipynb
├── 4 Duplicated values.ipynb
├── 6 Outliers(z_score).ipynb
├── 7 Outliers(IQR).ipynb
├── 8 Outliers(Percentile).ipynb
├── 9 Correction of datatype.ipynb
├── AB_NYC_2019.csv
├── EDA 5 (Outliers).pptx
├── README.md
├── scholarship.csv
└── weight-height.csv


/10 Univariate non-graphical EDA.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 1,
  6 |    "id": "8abdfe09",
  7 |    "metadata": {},
  8 |    "outputs": [],
  9 |    "source": [
 10 |     "import pandas as pd"
 11 |    ]
 12 |   },
 13 |   {
 14 |    "cell_type": "code",
 15 |    "execution_count": 2,
 16 |    "id": "119d4726",
 17 |    "metadata": {},
 18 |    "outputs": [],
 19 |    "source": [
 20 |     "df = pd.read_csv(\"AB_NYC_2019.csv\")"
 21 |    ]
 22 |   },
 23 |   {
 24 |    "cell_type": "code",
 25 |    "execution_count": 3,
 26 |    "id": "217b1e02",
 27 |    "metadata": {
 28 |     "scrolled": true
 29 |    },
 30 |    "outputs": [
 31 |     {
 32 |      "data": {
 33 |       "text/html": [
 34 |        "<div>\n",
 35 |        "<style scoped>\n",
 36 |        "    .dataframe tbody tr th:only-of-type {\n",
 37 |        "        vertical-align: middle;\n",
 38 |        "    }\n",
 39 |        "\n",
 40 |        "    .dataframe tbody tr th {\n",
 41 |        "        vertical-align: top;\n",
 42 |        "    }\n",
 43 |        "\n",
 44 |        "    .dataframe thead th {\n",
 45 |        "        text-align: right;\n",
 46 |        "    }\n",
 47 |        "</style>\n",
 48 |        "<table border=\"1\" class=\"dataframe\">\n",
 49 |        "  <thead>\n",
 50 |        "    <tr style=\"text-align: right;\">\n",
 51 |        "      <th></th>\n",
 52 |        "      <th>id</th>\n",
 53 |        "      <th>name</th>\n",
 54 |        "      <th>host_id</th>\n",
 55 |        "      <th>host_name</th>\n",
 56 |        "      <th>neighbourhood_group</th>\n",
 57 |        "      <th>neighbourhood</th>\n",
 58 |        "      <th>latitude</th>\n",
 59 |        "      <th>longitude</th>\n",
 60 |        "      <th>room_type</th>\n",
 61 |        "      <th>price</th>\n",
 62 |        "      <th>minimum_nights</th>\n",
 63 |        "      <th>number_of_reviews</th>\n",
 64 |        "      <th>last_review</th>\n",
 65 |        "      <th>reviews_per_month</th>\n",
 66 |        "      <th>calculated_host_listings_count</th>\n",
 67 |        "      <th>availability_365</th>\n",
 68 |        "    </tr>\n",
 69 |        "  </thead>\n",
 70 |        "  <tbody>\n",
 71 |        "    <tr>\n",
 72 |        "      <th>0</th>\n",
 73 |        "      <td>2539</td>\n",
 74 |        "      <td>Clean &amp; quiet apt home by the park</td>\n",
 75 |        "      <td>2787</td>\n",
 76 |        "      <td>John</td>\n",
 77 |        "      <td>Brooklyn</td>\n",
 78 |        "      <td>Kensington</td>\n",
 79 |        "      <td>40.64749</td>\n",
 80 |        "      <td>-73.97237</td>\n",
 81 |        "      <td>Private room</td>\n",
 82 |        "      <td>149</td>\n",
 83 |        "      <td>1</td>\n",
 84 |        "      <td>9</td>\n",
 85 |        "      <td>19-10-2018</td>\n",
 86 |        "      <td>0.21</td>\n",
 87 |        "      <td>6</td>\n",
 88 |        "      <td>365</td>\n",
 89 |        "    </tr>\n",
 90 |        "    <tr>\n",
 91 |        "      <th>1</th>\n",
 92 |        "      <td>2595</td>\n",
 93 |        "      <td>Skylit Midtown Castle</td>\n",
 94 |        "      <td>2845</td>\n",
 95 |        "      <td>Jennifer</td>\n",
 96 |        "      <td>Manhattan</td>\n",
 97 |        "      <td>Midtown</td>\n",
 98 |        "      <td>40.75362</td>\n",
 99 |        "      <td>-73.98377</td>\n",
100 |        "      <td>Entire home/apt</td>\n",
101 |        "      <td>225</td>\n",
102 |        "      <td>1</td>\n",
103 |        "      <td>45</td>\n",
104 |        "      <td>21-05-2019</td>\n",
105 |        "      <td>0.38</td>\n",
106 |        "      <td>2</td>\n",
107 |        "      <td>355</td>\n",
108 |        "    </tr>\n",
109 |        "    <tr>\n",
110 |        "      <th>2</th>\n",
111 |        "      <td>3647</td>\n",
112 |        "      <td>THE VILLAGE OF HARLEM....NEW YORK !</td>\n",
113 |        "      <td>4632</td>\n",
114 |        "      <td>Elisabeth</td>\n",
115 |        "      <td>Manhattan</td>\n",
116 |        "      <td>Harlem</td>\n",
117 |        "      <td>40.80902</td>\n",
118 |        "      <td>-73.94190</td>\n",
119 |        "      <td>Private room</td>\n",
120 |        "      <td>150</td>\n",
121 |        "      <td>3</td>\n",
122 |        "      <td>0</td>\n",
123 |        "      <td>NaN</td>\n",
124 |        "      <td>NaN</td>\n",
125 |        "      <td>1</td>\n",
126 |        "      <td>365</td>\n",
127 |        "    </tr>\n",
128 |        "    <tr>\n",
129 |        "      <th>3</th>\n",
130 |        "      <td>3831</td>\n",
131 |        "      <td>Cozy Entire Floor of Brownstone</td>\n",
132 |        "      <td>4869</td>\n",
133 |        "      <td>LisaRoxanne</td>\n",
134 |        "      <td>Brooklyn</td>\n",
135 |        "      <td>Clinton Hill</td>\n",
136 |        "      <td>40.68514</td>\n",
137 |        "      <td>-73.95976</td>\n",
138 |        "      <td>Entire home/apt</td>\n",
139 |        "      <td>89</td>\n",
140 |        "      <td>1</td>\n",
141 |        "      <td>270</td>\n",
142 |        "      <td>05-07-2019</td>\n",
143 |        "      <td>4.64</td>\n",
144 |        "      <td>1</td>\n",
145 |        "      <td>194</td>\n",
146 |        "    </tr>\n",
147 |        "    <tr>\n",
148 |        "      <th>4</th>\n",
149 |        "      <td>5022</td>\n",
150 |        "      <td>Entire Apt: Spacious Studio/Loft by central park</td>\n",
151 |        "      <td>7192</td>\n",
152 |        "      <td>Laura</td>\n",
153 |        "      <td>Manhattan</td>\n",
154 |        "      <td>East Harlem</td>\n",
155 |        "      <td>40.79851</td>\n",
156 |        "      <td>-73.94399</td>\n",
157 |        "      <td>Entire home/apt</td>\n",
158 |        "      <td>80</td>\n",
159 |        "      <td>10</td>\n",
160 |        "      <td>9</td>\n",
161 |        "      <td>19-11-2018</td>\n",
162 |        "      <td>0.10</td>\n",
163 |        "      <td>1</td>\n",
164 |        "      <td>0</td>\n",
165 |        "    </tr>\n",
166 |        "  </tbody>\n",
167 |        "</table>\n",
168 |        "</div>"
169 |       ],
170 |       "text/plain": [
171 |        "     id                                              name  host_id  \\\n",
172 |        "0  2539                Clean & quiet apt home by the park     2787   \n",
173 |        "1  2595                             Skylit Midtown Castle     2845   \n",
174 |        "2  3647               THE VILLAGE OF HARLEM....NEW YORK !     4632   \n",
175 |        "3  3831                   Cozy Entire Floor of Brownstone     4869   \n",
176 |        "4  5022  Entire Apt: Spacious Studio/Loft by central park     7192   \n",
177 |        "\n",
178 |        "     host_name neighbourhood_group neighbourhood  latitude  longitude  \\\n",
179 |        "0         John            Brooklyn    Kensington  40.64749  -73.97237   \n",
180 |        "1     Jennifer           Manhattan       Midtown  40.75362  -73.98377   \n",
181 |        "2    Elisabeth           Manhattan        Harlem  40.80902  -73.94190   \n",
182 |        "3  LisaRoxanne            Brooklyn  Clinton Hill  40.68514  -73.95976   \n",
183 |        "4        Laura           Manhattan   East Harlem  40.79851  -73.94399   \n",
184 |        "\n",
185 |        "         room_type  price  minimum_nights  number_of_reviews last_review  \\\n",
186 |        "0     Private room    149               1                  9  19-10-2018   \n",
187 |        "1  Entire home/apt    225               1                 45  21-05-2019   \n",
188 |        "2     Private room    150               3                  0         NaN   \n",
189 |        "3  Entire home/apt     89               1                270  05-07-2019   \n",
190 |        "4  Entire home/apt     80              10                  9  19-11-2018   \n",
191 |        "\n",
192 |        "   reviews_per_month  calculated_host_listings_count  availability_365  \n",
193 |        "0               0.21                               6               365  \n",
194 |        "1               0.38                               2               355  \n",
195 |        "2                NaN                               1               365  \n",
196 |        "3               4.64                               1               194  \n",
197 |        "4               0.10                               1                 0  "
198 |       ]
199 |      },
200 |      "execution_count": 3,
201 |      "metadata": {},
202 |      "output_type": "execute_result"
203 |     }
204 |    ],
205 |    "source": [
206 |     "df.head()"
207 |    ]
208 |   },
209 |   {
210 |    "cell_type": "code",
211 |    "execution_count": 4,
212 |    "id": "94df84f5",
213 |    "metadata": {},
214 |    "outputs": [],
215 |    "source": [
216 |     "df[\"id\"]=df[\"id\"].astype(str)\n",
217 |     "df[\"host_id\"]=df[\"host_id\"].astype(str)\n",
218 |     "df[\"latitude\"]=df[\"latitude\"].astype(str)\n",
219 |     "df[\"longitude\"]=df[\"longitude\"].astype(str)"
220 |    ]
221 |   },
222 |   {
223 |    "cell_type": "markdown",
224 |    "id": "56db9221",
225 |    "metadata": {},
226 |    "source": [
227 |     "How does the data look mathematically?"
228 |    ]
229 |   },
230 |   {
231 |    "cell_type": "code",
232 |    "execution_count": 5,
233 |    "id": "95b30309",
234 |    "metadata": {},
235 |    "outputs": [
236 |     {
237 |      "data": {
238 |       "text/html": [
239 |        "<div>\n",
240 |        "<style scoped>\n",
241 |        "    .dataframe tbody tr th:only-of-type {\n",
242 |        "        vertical-align: middle;\n",
243 |        "    }\n",
244 |        "\n",
245 |        "    .dataframe tbody tr th {\n",
246 |        "        vertical-align: top;\n",
247 |        "    }\n",
248 |        "\n",
249 |        "    .dataframe thead th {\n",
250 |        "        text-align: right;\n",
251 |        "    }\n",
252 |        "</style>\n",
253 |        "<table border=\"1\" class=\"dataframe\">\n",
254 |        "  <thead>\n",
255 |        "    <tr style=\"text-align: right;\">\n",
256 |        "      <th></th>\n",
257 |        "      <th>price</th>\n",
258 |        "      <th>minimum_nights</th>\n",
259 |        "      <th>number_of_reviews</th>\n",
260 |        "      <th>reviews_per_month</th>\n",
261 |        "      <th>calculated_host_listings_count</th>\n",
262 |        "      <th>availability_365</th>\n",
263 |        "    </tr>\n",
264 |        "  </thead>\n",
265 |        "  <tbody>\n",
266 |        "    <tr>\n",
267 |        "      <th>count</th>\n",
268 |        "      <td>48906.000000</td>\n",
269 |        "      <td>48906.000000</td>\n",
270 |        "      <td>48906.000000</td>\n",
271 |        "      <td>38854.000000</td>\n",
272 |        "      <td>48906.000000</td>\n",
273 |        "      <td>48906.000000</td>\n",
274 |        "    </tr>\n",
275 |        "    <tr>\n",
276 |        "      <th>mean</th>\n",
277 |        "      <td>152.711324</td>\n",
278 |        "      <td>7.031612</td>\n",
279 |        "      <td>23.300454</td>\n",
280 |        "      <td>1.373151</td>\n",
281 |        "      <td>7.142702</td>\n",
282 |        "      <td>112.782031</td>\n",
283 |        "    </tr>\n",
284 |        "    <tr>\n",
285 |        "      <th>std</th>\n",
286 |        "      <td>240.128713</td>\n",
287 |        "      <td>20.512489</td>\n",
288 |        "      <td>44.607175</td>\n",
289 |        "      <td>1.680270</td>\n",
290 |        "      <td>32.948926</td>\n",
291 |        "      <td>131.620370</td>\n",
292 |        "    </tr>\n",
293 |        "    <tr>\n",
294 |        "      <th>min</th>\n",
295 |        "      <td>0.000000</td>\n",
296 |        "      <td>1.000000</td>\n",
297 |        "      <td>0.000000</td>\n",
298 |        "      <td>0.010000</td>\n",
299 |        "      <td>1.000000</td>\n",
300 |        "      <td>0.000000</td>\n",
301 |        "    </tr>\n",
302 |        "    <tr>\n",
303 |        "      <th>25%</th>\n",
304 |        "      <td>69.000000</td>\n",
305 |        "      <td>1.000000</td>\n",
306 |        "      <td>1.000000</td>\n",
307 |        "      <td>0.190000</td>\n",
308 |        "      <td>1.000000</td>\n",
309 |        "      <td>0.000000</td>\n",
310 |        "    </tr>\n",
311 |        "    <tr>\n",
312 |        "      <th>50%</th>\n",
313 |        "      <td>106.000000</td>\n",
314 |        "      <td>3.000000</td>\n",
315 |        "      <td>5.000000</td>\n",
316 |        "      <td>0.720000</td>\n",
317 |        "      <td>1.000000</td>\n",
318 |        "      <td>45.000000</td>\n",
319 |        "    </tr>\n",
320 |        "    <tr>\n",
321 |        "      <th>75%</th>\n",
322 |        "      <td>175.000000</td>\n",
323 |        "      <td>5.000000</td>\n",
324 |        "      <td>24.000000</td>\n",
325 |        "      <td>2.020000</td>\n",
326 |        "      <td>2.000000</td>\n",
327 |        "      <td>227.000000</td>\n",
328 |        "    </tr>\n",
329 |        "    <tr>\n",
330 |        "      <th>max</th>\n",
331 |        "      <td>10000.000000</td>\n",
332 |        "      <td>1250.000000</td>\n",
333 |        "      <td>629.000000</td>\n",
334 |        "      <td>58.500000</td>\n",
335 |        "      <td>327.000000</td>\n",
336 |        "      <td>365.000000</td>\n",
337 |        "    </tr>\n",
338 |        "  </tbody>\n",
339 |        "</table>\n",
340 |        "</div>"
341 |       ],
342 |       "text/plain": [
343 |        "              price  minimum_nights  number_of_reviews  reviews_per_month  \\\n",
344 |        "count  48906.000000    48906.000000       48906.000000       38854.000000   \n",
345 |        "mean     152.711324        7.031612          23.300454           1.373151   \n",
346 |        "std      240.128713       20.512489          44.607175           1.680270   \n",
347 |        "min        0.000000        1.000000           0.000000           0.010000   \n",
348 |        "25%       69.000000        1.000000           1.000000           0.190000   \n",
349 |        "50%      106.000000        3.000000           5.000000           0.720000   \n",
350 |        "75%      175.000000        5.000000          24.000000           2.020000   \n",
351 |        "max    10000.000000     1250.000000         629.000000          58.500000   \n",
352 |        "\n",
353 |        "       calculated_host_listings_count  availability_365  \n",
354 |        "count                    48906.000000      48906.000000  \n",
355 |        "mean                         7.142702        112.782031  \n",
356 |        "std                         32.948926        131.620370  \n",
357 |        "min                          1.000000          0.000000  \n",
358 |        "25%                          1.000000          0.000000  \n",
359 |        "50%                          1.000000         45.000000  \n",
360 |        "75%                          2.000000        227.000000  \n",
361 |        "max                        327.000000        365.000000  "
362 |       ]
363 |      },
364 |      "execution_count": 5,
365 |      "metadata": {},
366 |      "output_type": "execute_result"
367 |     }
368 |    ],
369 |    "source": [
370 |     "df.describe()"
371 |    ]
372 |   },
373 |   {
374 |    "cell_type": "markdown",
375 |    "id": "138bafa9",
376 |    "metadata": {},
377 |    "source": [
378 |     "range of minimum nights for listings is 1 and 1250"
379 |    ]
380 |   },
381 |   {
382 |    "cell_type": "markdown",
383 |    "id": "a6b70275",
384 |    "metadata": {},
385 |    "source": [
386 |     "# Categorical Data"
387 |    ]
388 |   },
389 |   {
390 |    "cell_type": "code",
391 |    "execution_count": 6,
392 |    "id": "74b3cb63",
393 |    "metadata": {},
394 |    "outputs": [
395 |     {
396 |      "data": {
397 |       "text/plain": [
398 |        "id                                48895\n",
399 |        "name                              47896\n",
400 |        "host_id                           37457\n",
401 |        "host_name                         11452\n",
402 |        "neighbourhood_group                   5\n",
403 |        "neighbourhood                       221\n",
404 |        "latitude                          19048\n",
405 |        "longitude                         14718\n",
406 |        "room_type                             3\n",
407 |        "price                               674\n",
408 |        "minimum_nights                      109\n",
409 |        "number_of_reviews                   394\n",
410 |        "last_review                        1764\n",
411 |        "reviews_per_month                   937\n",
412 |        "calculated_host_listings_count       47\n",
413 |        "availability_365                    366\n",
414 |        "dtype: int64"
415 |       ]
416 |      },
417 |      "execution_count": 6,
418 |      "metadata": {},
419 |      "output_type": "execute_result"
420 |     }
421 |    ],
422 |    "source": [
423 |     "df.nunique()"
424 |    ]
425 |   },
426 |   {
427 |    "cell_type": "code",
428 |    "execution_count": 7,
429 |    "id": "56c9d1dc",
430 |    "metadata": {},
431 |    "outputs": [
432 |     {
433 |      "data": {
434 |       "text/plain": [
435 |        "Index(['id', 'name', 'host_id', 'host_name', 'neighbourhood_group',\n",
436 |        "       'neighbourhood', 'latitude', 'longitude', 'room_type', 'price',\n",
437 |        "       'minimum_nights', 'number_of_reviews', 'last_review',\n",
438 |        "       'reviews_per_month', 'calculated_host_listings_count',\n",
439 |        "       'availability_365'],\n",
440 |        "      dtype='object')"
441 |       ]
442 |      },
443 |      "execution_count": 7,
444 |      "metadata": {},
445 |      "output_type": "execute_result"
446 |     }
447 |    ],
448 |    "source": [
449 |     "df.columns"
450 |    ]
451 |   },
452 |   {
453 |    "cell_type": "code",
454 |    "execution_count": 8,
455 |    "id": "fa8aa028",
456 |    "metadata": {},
457 |    "outputs": [
458 |     {
459 |      "data": {
460 |       "text/plain": [
461 |        "Entire home/apt    25414\n",
462 |        "Private room       22332\n",
463 |        "Shared room         1160\n",
464 |        "Name: room_type, dtype: int64"
465 |       ]
466 |      },
467 |      "execution_count": 8,
468 |      "metadata": {},
469 |      "output_type": "execute_result"
470 |     }
471 |    ],
472 |    "source": [
473 |     "df[\"room_type\"].value_counts()"
474 |    ]
475 |   },
476 |   {
477 |    "cell_type": "code",
478 |    "execution_count": 9,
479 |    "id": "3401f55e",
480 |    "metadata": {},
481 |    "outputs": [
482 |     {
483 |      "data": {
484 |       "text/plain": [
485 |        "Entire home/apt    0.519650\n",
486 |        "Private room       0.456631\n",
487 |        "Shared room        0.023719\n",
488 |        "Name: room_type, dtype: float64"
489 |       ]
490 |      },
491 |      "execution_count": 9,
492 |      "metadata": {},
493 |      "output_type": "execute_result"
494 |     }
495 |    ],
496 |    "source": [
497 |     "df[\"room_type\"].value_counts(normalize = True)"
498 |    ]
499 |   },
500 |   {
501 |    "cell_type": "code",
502 |    "execution_count": 10,
503 |    "id": "5b722d04",
504 |    "metadata": {},
505 |    "outputs": [
506 |     {
507 |      "data": {
508 |       "text/plain": [
509 |        "Manhattan        21669\n",
510 |        "Brooklyn         20107\n",
511 |        "Queens            5666\n",
512 |        "Bronx             1091\n",
513 |        "Staten Island      373\n",
514 |        "Name: neighbourhood_group, dtype: int64"
515 |       ]
516 |      },
517 |      "execution_count": 10,
518 |      "metadata": {},
519 |      "output_type": "execute_result"
520 |     }
521 |    ],
522 |    "source": [
523 |     "df[\"neighbourhood_group\"].value_counts()"
524 |    ]
525 |   },
526 |   {
527 |    "cell_type": "markdown",
528 |    "id": "388dfebe",
529 |    "metadata": {},
530 |    "source": [
531 |     "# Numerical Data"
532 |    ]
533 |   },
534 |   {
535 |    "cell_type": "code",
536 |    "execution_count": 11,
537 |    "id": "c45b4650",
538 |    "metadata": {},
539 |    "outputs": [
540 |     {
541 |      "data": {
542 |       "text/plain": [
543 |        "(-10.001, 2000.0]    48820\n",
544 |        "(2000.0, 4000.0]        54\n",
545 |        "(4000.0, 6000.0]        16\n",
546 |        "(6000.0, 8000.0]         9\n",
547 |        "(8000.0, 10000.0]        7\n",
548 |        "Name: price, dtype: int64"
549 |       ]
550 |      },
551 |      "execution_count": 11,
552 |      "metadata": {},
553 |      "output_type": "execute_result"
554 |     }
555 |    ],
556 |    "source": [
557 |     "df[\"price\"].value_counts(bins = 5)"
558 |    ]
559 |   },
560 |   {
561 |    "cell_type": "code",
562 |    "execution_count": 12,
563 |    "id": "7f3ce5a3",
564 |    "metadata": {
565 |     "scrolled": false
566 |    },
567 |    "outputs": [
568 |     {
569 |      "data": {
570 |       "text/plain": [
571 |        "(50.0, 100.0]        17373\n",
572 |        "(100.0, 200.0]       16588\n",
573 |        "(200.0, 500.0]        7340\n",
574 |        "(0.0, 50.0]           6550\n",
575 |        "(500.0, 800.0]         624\n",
576 |        "(800.0, 2000.0]        334\n",
577 |        "(2000.0, 4000.0]        54\n",
578 |        "(4000.0, 10000.0]       32\n",
579 |        "(-10.001, 0.0]          11\n",
580 |        "Name: price, dtype: int64"
581 |       ]
582 |      },
583 |      "execution_count": 12,
584 |      "metadata": {},
585 |      "output_type": "execute_result"
586 |     }
587 |    ],
588 |    "source": [
589 |     "bins = [-10,0, 50,100, 200,500,800,2000,4000,10000]\n",
590 |     "df[\"price\"].value_counts(bins = bins)"
591 |    ]
592 |   },
593 |   {
594 |    "cell_type": "markdown",
595 |    "id": "993f989b",
596 |    "metadata": {},
597 |    "source": [
598 |     "It is mainly helpful in small datasets."
599 |    ]
600 |   },
601 |   {
602 |    "cell_type": "markdown",
603 |    "id": "c76d8cea",
604 |    "metadata": {},
605 |    "source": [
606 |     "## Measures of central tendency"
607 |    ]
608 |   },
609 |   {
610 |    "cell_type": "code",
611 |    "execution_count": 13,
612 |    "id": "329245f5",
613 |    "metadata": {
614 |     "scrolled": true
615 |    },
616 |    "outputs": [
617 |     {
618 |      "data": {
619 |       "text/plain": [
620 |        "152.71132376395533"
621 |       ]
622 |      },
623 |      "execution_count": 13,
624 |      "metadata": {},
625 |      "output_type": "execute_result"
626 |     }
627 |    ],
628 |    "source": [
629 |     "df[\"price\"].mean()"
630 |    ]
631 |   },
632 |   {
633 |    "cell_type": "code",
634 |    "execution_count": 14,
635 |    "id": "b48226ef",
636 |    "metadata": {},
637 |    "outputs": [
638 |     {
639 |      "data": {
640 |       "text/plain": [
641 |        "106.0"
642 |       ]
643 |      },
644 |      "execution_count": 14,
645 |      "metadata": {},
646 |      "output_type": "execute_result"
647 |     }
648 |    ],
649 |    "source": [
650 |     "df[\"price\"].median()"
651 |    ]
652 |   },
653 |   {
654 |    "cell_type": "code",
655 |    "execution_count": 15,
656 |    "id": "00bae1ee",
657 |    "metadata": {},
658 |    "outputs": [
659 |     {
660 |      "data": {
661 |       "text/plain": [
662 |        "240.1287131622509"
663 |       ]
664 |      },
665 |      "execution_count": 15,
666 |      "metadata": {},
667 |      "output_type": "execute_result"
668 |     }
669 |    ],
670 |    "source": [
671 |     "df[\"price\"].std()"
672 |    ]
673 |   },
674 |   {
675 |    "cell_type": "code",
676 |    "execution_count": 16,
677 |    "id": "33404a5d",
678 |    "metadata": {},
679 |    "outputs": [
680 |     {
681 |      "data": {
682 |       "text/plain": [
683 |        "7.031611663190611"
684 |       ]
685 |      },
686 |      "execution_count": 16,
687 |      "metadata": {},
688 |      "output_type": "execute_result"
689 |     }
690 |    ],
691 |    "source": [
692 |     "df[\"minimum_nights\"].mean()"
693 |    ]
694 |   },
695 |   {
696 |    "cell_type": "code",
697 |    "execution_count": 17,
698 |    "id": "a45e32fe",
699 |    "metadata": {},
700 |    "outputs": [
701 |     {
702 |      "data": {
703 |       "text/plain": [
704 |        "3.0"
705 |       ]
706 |      },
707 |      "execution_count": 17,
708 |      "metadata": {},
709 |      "output_type": "execute_result"
710 |     }
711 |    ],
712 |    "source": [
713 |     "df[\"minimum_nights\"].median()"
714 |    ]
715 |   },
716 |   {
717 |    "cell_type": "markdown",
718 |    "id": "ce2e309d",
719 |    "metadata": {},
720 |    "source": [
721 |     "## Measure of Spread"
722 |    ]
723 |   },
724 |   {
725 |    "cell_type": "code",
726 |    "execution_count": 18,
727 |    "id": "12649a50",
728 |    "metadata": {},
729 |    "outputs": [
730 |     {
731 |      "data": {
732 |       "text/plain": [
733 |        "19.120831694826197"
734 |       ]
735 |      },
736 |      "execution_count": 18,
737 |      "metadata": {},
738 |      "output_type": "execute_result"
739 |     }
740 |    ],
741 |    "source": [
742 |     "df[\"price\"].skew()"
743 |    ]
744 |   },
745 |   {
746 |    "cell_type": "code",
747 |    "execution_count": 19,
748 |    "id": "0e856dc2",
749 |    "metadata": {},
750 |    "outputs": [
751 |     {
752 |      "data": {
753 |       "text/plain": [
754 |        "585.7930484394186"
755 |       ]
756 |      },
757 |      "execution_count": 19,
758 |      "metadata": {},
759 |      "output_type": "execute_result"
760 |     }
761 |    ],
762 |    "source": [
763 |     "df[\"price\"].kurt()"
764 |    ]
765 |   },
766 |   {
767 |    "cell_type": "markdown",
768 |    "id": "8e4ad1db",
769 |    "metadata": {},
770 |    "source": [
771 |     "How many listings have availability throughout the year (365 days)"
772 |    ]
773 |   },
774 |   {
775 |    "cell_type": "code",
776 |    "execution_count": 20,
777 |    "id": "e1cc1b65",
778 |    "metadata": {},
779 |    "outputs": [
780 |     {
781 |      "data": {
782 |       "text/plain": [
783 |        "1295"
784 |       ]
785 |      },
786 |      "execution_count": 20,
787 |      "metadata": {},
788 |      "output_type": "execute_result"
789 |     }
790 |    ],
791 |    "source": [
792 |     "df[df[\"availability_365\"]==365].shape[0]"
793 |    ]
794 |   },
795 |   {
796 |    "cell_type": "code",
797 |    "execution_count": 21,
798 |    "id": "87d7ac64",
799 |    "metadata": {},
800 |    "outputs": [
801 |     {
802 |      "name": "stderr",
803 |      "output_type": "stream",
804 |      "text": [
805 |       "C:\\Users\\GFG19189\\AppData\\Local\\Temp\\ipykernel_1056\\1134722465.py:1: FutureWarning: The default value of numeric_only in DataFrame.corr is deprecated. In a future version, it will default to False. Select only valid columns or specify the value of numeric_only to silence this warning.\n",
806 |       "  df.corr()\n"
807 |      ]
808 |     },
809 |     {
810 |      "data": {
811 |       "text/html": [
812 |        "<div>\n",
813 |        "<style scoped>\n",
814 |        "    .dataframe tbody tr th:only-of-type {\n",
815 |        "        vertical-align: middle;\n",
816 |        "    }\n",
817 |        "\n",
818 |        "    .dataframe tbody tr th {\n",
819 |        "        vertical-align: top;\n",
820 |        "    }\n",
821 |        "\n",
822 |        "    .dataframe thead th {\n",
823 |        "        text-align: right;\n",
824 |        "    }\n",
825 |        "</style>\n",
826 |        "<table border=\"1\" class=\"dataframe\">\n",
827 |        "  <thead>\n",
828 |        "    <tr style=\"text-align: right;\">\n",
829 |        "      <th></th>\n",
830 |        "      <th>price</th>\n",
831 |        "      <th>minimum_nights</th>\n",
832 |        "      <th>number_of_reviews</th>\n",
833 |        "      <th>reviews_per_month</th>\n",
834 |        "      <th>calculated_host_listings_count</th>\n",
835 |        "      <th>availability_365</th>\n",
836 |        "    </tr>\n",
837 |        "  </thead>\n",
838 |        "  <tbody>\n",
839 |        "    <tr>\n",
840 |        "      <th>price</th>\n",
841 |        "      <td>1.000000</td>\n",
842 |        "      <td>0.042771</td>\n",
843 |        "      <td>-0.048014</td>\n",
844 |        "      <td>-0.030608</td>\n",
845 |        "      <td>0.057478</td>\n",
846 |        "      <td>0.081817</td>\n",
847 |        "    </tr>\n",
848 |        "    <tr>\n",
849 |        "      <th>minimum_nights</th>\n",
850 |        "      <td>0.042771</td>\n",
851 |        "      <td>1.000000</td>\n",
852 |        "      <td>-0.080093</td>\n",
853 |        "      <td>-0.121772</td>\n",
854 |        "      <td>0.127917</td>\n",
855 |        "      <td>0.144146</td>\n",
856 |        "    </tr>\n",
857 |        "    <tr>\n",
858 |        "      <th>number_of_reviews</th>\n",
859 |        "      <td>-0.048014</td>\n",
860 |        "      <td>-0.080093</td>\n",
861 |        "      <td>1.000000</td>\n",
862 |        "      <td>0.549291</td>\n",
863 |        "      <td>-0.072375</td>\n",
864 |        "      <td>0.172002</td>\n",
865 |        "    </tr>\n",
866 |        "    <tr>\n",
867 |        "      <th>reviews_per_month</th>\n",
868 |        "      <td>-0.030608</td>\n",
869 |        "      <td>-0.121772</td>\n",
870 |        "      <td>0.549291</td>\n",
871 |        "      <td>1.000000</td>\n",
872 |        "      <td>-0.009414</td>\n",
873 |        "      <td>0.185818</td>\n",
874 |        "    </tr>\n",
875 |        "    <tr>\n",
876 |        "      <th>calculated_host_listings_count</th>\n",
877 |        "      <td>0.057478</td>\n",
878 |        "      <td>0.127917</td>\n",
879 |        "      <td>-0.072375</td>\n",
880 |        "      <td>-0.009414</td>\n",
881 |        "      <td>1.000000</td>\n",
882 |        "      <td>0.225680</td>\n",
883 |        "    </tr>\n",
884 |        "    <tr>\n",
885 |        "      <th>availability_365</th>\n",
886 |        "      <td>0.081817</td>\n",
887 |        "      <td>0.144146</td>\n",
888 |        "      <td>0.172002</td>\n",
889 |        "      <td>0.185818</td>\n",
890 |        "      <td>0.225680</td>\n",
891 |        "      <td>1.000000</td>\n",
892 |        "    </tr>\n",
893 |        "  </tbody>\n",
894 |        "</table>\n",
895 |        "</div>"
896 |       ],
897 |       "text/plain": [
898 |        "                                   price  minimum_nights  number_of_reviews  \\\n",
899 |        "price                           1.000000        0.042771          -0.048014   \n",
900 |        "minimum_nights                  0.042771        1.000000          -0.080093   \n",
901 |        "number_of_reviews              -0.048014       -0.080093           1.000000   \n",
902 |        "reviews_per_month              -0.030608       -0.121772           0.549291   \n",
903 |        "calculated_host_listings_count  0.057478        0.127917          -0.072375   \n",
904 |        "availability_365                0.081817        0.144146           0.172002   \n",
905 |        "\n",
906 |        "                                reviews_per_month  \\\n",
907 |        "price                                   -0.030608   \n",
908 |        "minimum_nights                          -0.121772   \n",
909 |        "number_of_reviews                        0.549291   \n",
910 |        "reviews_per_month                        1.000000   \n",
911 |        "calculated_host_listings_count          -0.009414   \n",
912 |        "availability_365                         0.185818   \n",
913 |        "\n",
914 |        "                                calculated_host_listings_count  \\\n",
915 |        "price                                                 0.057478   \n",
916 |        "minimum_nights                                        0.127917   \n",
917 |        "number_of_reviews                                    -0.072375   \n",
918 |        "reviews_per_month                                    -0.009414   \n",
919 |        "calculated_host_listings_count                        1.000000   \n",
920 |        "availability_365                                      0.225680   \n",
921 |        "\n",
922 |        "                                availability_365  \n",
923 |        "price                                   0.081817  \n",
924 |        "minimum_nights                          0.144146  \n",
925 |        "number_of_reviews                       0.172002  \n",
926 |        "reviews_per_month                       0.185818  \n",
927 |        "calculated_host_listings_count          0.225680  \n",
928 |        "availability_365                        1.000000  "
929 |       ]
930 |      },
931 |      "execution_count": 21,
932 |      "metadata": {},
933 |      "output_type": "execute_result"
934 |     }
935 |    ],
936 |    "source": [
937 |     "df.corr()"
938 |    ]
939 |   }
940 |  ],
941 |  "metadata": {
942 |   "kernelspec": {
943 |    "display_name": "Python 3 (ipykernel)",
944 |    "language": "python",
945 |    "name": "python3"
946 |   },
947 |   "language_info": {
948 |    "codemirror_mode": {
949 |     "name": "ipython",
950 |     "version": 3
951 |    },
952 |    "file_extension": ".py",
953 |    "mimetype": "text/x-python",
954 |    "name": "python",
955 |    "nbconvert_exporter": "python",
956 |    "pygments_lexer": "ipython3",
957 |    "version": "3.11.1"
958 |   }
959 |  },
960 |  "nbformat": 4,
961 |  "nbformat_minor": 5
962 | }
963 | 


--------------------------------------------------------------------------------
/2 Understanding your data.ipynb:
--------------------------------------------------------------------------------
   1 | {
   2 |  "cells": [
   3 |   {
   4 |    "cell_type": "code",
   5 |    "execution_count": 29,
   6 |    "id": "8eb8b9b5",
   7 |    "metadata": {},
   8 |    "outputs": [],
   9 |    "source": [
  10 |     "import pandas as pd\n",
  11 |     "import seaborn as sns"
  12 |    ]
  13 |   },
  14 |   {
  15 |    "cell_type": "code",
  16 |    "execution_count": 30,
  17 |    "id": "ec399f59",
  18 |    "metadata": {},
  19 |    "outputs": [],
  20 |    "source": [
  21 |     "df = pd.read_csv(\"AB_NYC_2019.csv\")"
  22 |    ]
  23 |   },
  24 |   {
  25 |    "cell_type": "markdown",
  26 |    "id": "c7f041e4",
  27 |    "metadata": {},
  28 |    "source": [
  29 |     "## 1. Dimension of data?"
  30 |    ]
  31 |   },
  32 |   {
  33 |    "cell_type": "code",
  34 |    "execution_count": 31,
  35 |    "id": "ab628eec",
  36 |    "metadata": {},
  37 |    "outputs": [
  38 |     {
  39 |      "data": {
  40 |       "text/plain": [
  41 |        "(48906, 16)"
  42 |       ]
  43 |      },
  44 |      "execution_count": 31,
  45 |      "metadata": {},
  46 |      "output_type": "execute_result"
  47 |     }
  48 |    ],
  49 |    "source": [
  50 |     "df.shape"
  51 |    ]
  52 |   },
  53 |   {
  54 |    "cell_type": "markdown",
  55 |    "id": "bae2d9b7",
  56 |    "metadata": {},
  57 |    "source": [
  58 |     "## 2. How does the data look like?"
  59 |    ]
  60 |   },
  61 |   {
  62 |    "cell_type": "code",
  63 |    "execution_count": 32,
  64 |    "id": "a3bff2be",
  65 |    "metadata": {},
  66 |    "outputs": [
  67 |     {
  68 |      "data": {
  69 |       "text/html": [
  70 |        "<div>\n",
  71 |        "<style scoped>\n",
  72 |        "    .dataframe tbody tr th:only-of-type {\n",
  73 |        "        vertical-align: middle;\n",
  74 |        "    }\n",
  75 |        "\n",
  76 |        "    .dataframe tbody tr th {\n",
  77 |        "        vertical-align: top;\n",
  78 |        "    }\n",
  79 |        "\n",
  80 |        "    .dataframe thead th {\n",
  81 |        "        text-align: right;\n",
  82 |        "    }\n",
  83 |        "</style>\n",
  84 |        "<table border=\"1\" class=\"dataframe\">\n",
  85 |        "  <thead>\n",
  86 |        "    <tr style=\"text-align: right;\">\n",
  87 |        "      <th></th>\n",
  88 |        "      <th>id</th>\n",
  89 |        "      <th>name</th>\n",
  90 |        "      <th>host_id</th>\n",
  91 |        "      <th>host_name</th>\n",
  92 |        "      <th>neighbourhood_group</th>\n",
  93 |        "      <th>neighbourhood</th>\n",
  94 |        "      <th>latitude</th>\n",
  95 |        "      <th>longitude</th>\n",
  96 |        "      <th>room_type</th>\n",
  97 |        "      <th>price</th>\n",
  98 |        "      <th>minimum_nights</th>\n",
  99 |        "      <th>number_of_reviews</th>\n",
 100 |        "      <th>last_review</th>\n",
 101 |        "      <th>reviews_per_month</th>\n",
 102 |        "      <th>calculated_host_listings_count</th>\n",
 103 |        "      <th>availability_365</th>\n",
 104 |        "    </tr>\n",
 105 |        "  </thead>\n",
 106 |        "  <tbody>\n",
 107 |        "    <tr>\n",
 108 |        "      <th>0</th>\n",
 109 |        "      <td>2539</td>\n",
 110 |        "      <td>Clean &amp; quiet apt home by the park</td>\n",
 111 |        "      <td>2787</td>\n",
 112 |        "      <td>John</td>\n",
 113 |        "      <td>Brooklyn</td>\n",
 114 |        "      <td>Kensington</td>\n",
 115 |        "      <td>40.64749</td>\n",
 116 |        "      <td>-73.97237</td>\n",
 117 |        "      <td>Private room</td>\n",
 118 |        "      <td>149</td>\n",
 119 |        "      <td>1</td>\n",
 120 |        "      <td>9</td>\n",
 121 |        "      <td>19-10-2018</td>\n",
 122 |        "      <td>0.21</td>\n",
 123 |        "      <td>6</td>\n",
 124 |        "      <td>365</td>\n",
 125 |        "    </tr>\n",
 126 |        "    <tr>\n",
 127 |        "      <th>1</th>\n",
 128 |        "      <td>2595</td>\n",
 129 |        "      <td>Skylit Midtown Castle</td>\n",
 130 |        "      <td>2845</td>\n",
 131 |        "      <td>Jennifer</td>\n",
 132 |        "      <td>Manhattan</td>\n",
 133 |        "      <td>Midtown</td>\n",
 134 |        "      <td>40.75362</td>\n",
 135 |        "      <td>-73.98377</td>\n",
 136 |        "      <td>Entire home/apt</td>\n",
 137 |        "      <td>225</td>\n",
 138 |        "      <td>1</td>\n",
 139 |        "      <td>45</td>\n",
 140 |        "      <td>21-05-2019</td>\n",
 141 |        "      <td>0.38</td>\n",
 142 |        "      <td>2</td>\n",
 143 |        "      <td>355</td>\n",
 144 |        "    </tr>\n",
 145 |        "    <tr>\n",
 146 |        "      <th>2</th>\n",
 147 |        "      <td>3647</td>\n",
 148 |        "      <td>THE VILLAGE OF HARLEM....NEW YORK !</td>\n",
 149 |        "      <td>4632</td>\n",
 150 |        "      <td>Elisabeth</td>\n",
 151 |        "      <td>Manhattan</td>\n",
 152 |        "      <td>Harlem</td>\n",
 153 |        "      <td>40.80902</td>\n",
 154 |        "      <td>-73.94190</td>\n",
 155 |        "      <td>Private room</td>\n",
 156 |        "      <td>150</td>\n",
 157 |        "      <td>3</td>\n",
 158 |        "      <td>0</td>\n",
 159 |        "      <td>NaN</td>\n",
 160 |        "      <td>NaN</td>\n",
 161 |        "      <td>1</td>\n",
 162 |        "      <td>365</td>\n",
 163 |        "    </tr>\n",
 164 |        "    <tr>\n",
 165 |        "      <th>3</th>\n",
 166 |        "      <td>3831</td>\n",
 167 |        "      <td>Cozy Entire Floor of Brownstone</td>\n",
 168 |        "      <td>4869</td>\n",
 169 |        "      <td>LisaRoxanne</td>\n",
 170 |        "      <td>Brooklyn</td>\n",
 171 |        "      <td>Clinton Hill</td>\n",
 172 |        "      <td>40.68514</td>\n",
 173 |        "      <td>-73.95976</td>\n",
 174 |        "      <td>Entire home/apt</td>\n",
 175 |        "      <td>89</td>\n",
 176 |        "      <td>1</td>\n",
 177 |        "      <td>270</td>\n",
 178 |        "      <td>05-07-2019</td>\n",
 179 |        "      <td>4.64</td>\n",
 180 |        "      <td>1</td>\n",
 181 |        "      <td>194</td>\n",
 182 |        "    </tr>\n",
 183 |        "    <tr>\n",
 184 |        "      <th>4</th>\n",
 185 |        "      <td>5022</td>\n",
 186 |        "      <td>Entire Apt: Spacious Studio/Loft by central park</td>\n",
 187 |        "      <td>7192</td>\n",
 188 |        "      <td>Laura</td>\n",
 189 |        "      <td>Manhattan</td>\n",
 190 |        "      <td>East Harlem</td>\n",
 191 |        "      <td>40.79851</td>\n",
 192 |        "      <td>-73.94399</td>\n",
 193 |        "      <td>Entire home/apt</td>\n",
 194 |        "      <td>80</td>\n",
 195 |        "      <td>10</td>\n",
 196 |        "      <td>9</td>\n",
 197 |        "      <td>19-11-2018</td>\n",
 198 |        "      <td>0.10</td>\n",
 199 |        "      <td>1</td>\n",
 200 |        "      <td>0</td>\n",
 201 |        "    </tr>\n",
 202 |        "  </tbody>\n",
 203 |        "</table>\n",
 204 |        "</div>"
 205 |       ],
 206 |       "text/plain": [
 207 |        "     id                                              name  host_id  \\\n",
 208 |        "0  2539                Clean & quiet apt home by the park     2787   \n",
 209 |        "1  2595                             Skylit Midtown Castle     2845   \n",
 210 |        "2  3647               THE VILLAGE OF HARLEM....NEW YORK !     4632   \n",
 211 |        "3  3831                   Cozy Entire Floor of Brownstone     4869   \n",
 212 |        "4  5022  Entire Apt: Spacious Studio/Loft by central park     7192   \n",
 213 |        "\n",
 214 |        "     host_name neighbourhood_group neighbourhood  latitude  longitude  \\\n",
 215 |        "0         John            Brooklyn    Kensington  40.64749  -73.97237   \n",
 216 |        "1     Jennifer           Manhattan       Midtown  40.75362  -73.98377   \n",
 217 |        "2    Elisabeth           Manhattan        Harlem  40.80902  -73.94190   \n",
 218 |        "3  LisaRoxanne            Brooklyn  Clinton Hill  40.68514  -73.95976   \n",
 219 |        "4        Laura           Manhattan   East Harlem  40.79851  -73.94399   \n",
 220 |        "\n",
 221 |        "         room_type  price  minimum_nights  number_of_reviews last_review  \\\n",
 222 |        "0     Private room    149               1                  9  19-10-2018   \n",
 223 |        "1  Entire home/apt    225               1                 45  21-05-2019   \n",
 224 |        "2     Private room    150               3                  0         NaN   \n",
 225 |        "3  Entire home/apt     89               1                270  05-07-2019   \n",
 226 |        "4  Entire home/apt     80              10                  9  19-11-2018   \n",
 227 |        "\n",
 228 |        "   reviews_per_month  calculated_host_listings_count  availability_365  \n",
 229 |        "0               0.21                               6               365  \n",
 230 |        "1               0.38                               2               355  \n",
 231 |        "2                NaN                               1               365  \n",
 232 |        "3               4.64                               1               194  \n",
 233 |        "4               0.10                               1                 0  "
 234 |       ]
 235 |      },
 236 |      "execution_count": 32,
 237 |      "metadata": {},
 238 |      "output_type": "execute_result"
 239 |     }
 240 |    ],
 241 |    "source": [
 242 |     "df.head()"
 243 |    ]
 244 |   },
 245 |   {
 246 |    "cell_type": "code",
 247 |    "execution_count": 33,
 248 |    "id": "29978697",
 249 |    "metadata": {},
 250 |    "outputs": [
 251 |     {
 252 |      "data": {
 253 |       "text/html": [
 254 |        "<div>\n",
 255 |        "<style scoped>\n",
 256 |        "    .dataframe tbody tr th:only-of-type {\n",
 257 |        "        vertical-align: middle;\n",
 258 |        "    }\n",
 259 |        "\n",
 260 |        "    .dataframe tbody tr th {\n",
 261 |        "        vertical-align: top;\n",
 262 |        "    }\n",
 263 |        "\n",
 264 |        "    .dataframe thead th {\n",
 265 |        "        text-align: right;\n",
 266 |        "    }\n",
 267 |        "</style>\n",
 268 |        "<table border=\"1\" class=\"dataframe\">\n",
 269 |        "  <thead>\n",
 270 |        "    <tr style=\"text-align: right;\">\n",
 271 |        "      <th></th>\n",
 272 |        "      <th>id</th>\n",
 273 |        "      <th>name</th>\n",
 274 |        "      <th>host_id</th>\n",
 275 |        "      <th>host_name</th>\n",
 276 |        "      <th>neighbourhood_group</th>\n",
 277 |        "      <th>neighbourhood</th>\n",
 278 |        "      <th>latitude</th>\n",
 279 |        "      <th>longitude</th>\n",
 280 |        "      <th>room_type</th>\n",
 281 |        "      <th>price</th>\n",
 282 |        "      <th>minimum_nights</th>\n",
 283 |        "      <th>number_of_reviews</th>\n",
 284 |        "      <th>last_review</th>\n",
 285 |        "      <th>reviews_per_month</th>\n",
 286 |        "      <th>calculated_host_listings_count</th>\n",
 287 |        "      <th>availability_365</th>\n",
 288 |        "    </tr>\n",
 289 |        "  </thead>\n",
 290 |        "  <tbody>\n",
 291 |        "    <tr>\n",
 292 |        "      <th>48901</th>\n",
 293 |        "      <td>5441</td>\n",
 294 |        "      <td>Central Manhattan/near Broadway</td>\n",
 295 |        "      <td>7989</td>\n",
 296 |        "      <td>Kate</td>\n",
 297 |        "      <td>Manhattan</td>\n",
 298 |        "      <td>Hell's Kitchen</td>\n",
 299 |        "      <td>40.76076</td>\n",
 300 |        "      <td>-73.98867</td>\n",
 301 |        "      <td>Private room</td>\n",
 302 |        "      <td>85</td>\n",
 303 |        "      <td>2</td>\n",
 304 |        "      <td>188</td>\n",
 305 |        "      <td>23-06-2019</td>\n",
 306 |        "      <td>1.50</td>\n",
 307 |        "      <td>1</td>\n",
 308 |        "      <td>39</td>\n",
 309 |        "    </tr>\n",
 310 |        "    <tr>\n",
 311 |        "      <th>48902</th>\n",
 312 |        "      <td>5803</td>\n",
 313 |        "      <td>Lovely Room 1, Garden, Best Area, Legal rental</td>\n",
 314 |        "      <td>9744</td>\n",
 315 |        "      <td>Laurie</td>\n",
 316 |        "      <td>Brooklyn</td>\n",
 317 |        "      <td>South Slope</td>\n",
 318 |        "      <td>40.66829</td>\n",
 319 |        "      <td>-73.98779</td>\n",
 320 |        "      <td>Private room</td>\n",
 321 |        "      <td>89</td>\n",
 322 |        "      <td>4</td>\n",
 323 |        "      <td>167</td>\n",
 324 |        "      <td>24-06-2019</td>\n",
 325 |        "      <td>1.34</td>\n",
 326 |        "      <td>3</td>\n",
 327 |        "      <td>314</td>\n",
 328 |        "    </tr>\n",
 329 |        "    <tr>\n",
 330 |        "      <th>48903</th>\n",
 331 |        "      <td>6021</td>\n",
 332 |        "      <td>Wonderful Guest Bedroom in Manhattan for SINGLES</td>\n",
 333 |        "      <td>11528</td>\n",
 334 |        "      <td>Claudio</td>\n",
 335 |        "      <td>Manhattan</td>\n",
 336 |        "      <td>Upper West Side</td>\n",
 337 |        "      <td>40.79826</td>\n",
 338 |        "      <td>-73.96113</td>\n",
 339 |        "      <td>Private room</td>\n",
 340 |        "      <td>85</td>\n",
 341 |        "      <td>2</td>\n",
 342 |        "      <td>113</td>\n",
 343 |        "      <td>05-07-2019</td>\n",
 344 |        "      <td>0.91</td>\n",
 345 |        "      <td>1</td>\n",
 346 |        "      <td>333</td>\n",
 347 |        "    </tr>\n",
 348 |        "    <tr>\n",
 349 |        "      <th>48904</th>\n",
 350 |        "      <td>6090</td>\n",
 351 |        "      <td>West Village Nest - Superhost</td>\n",
 352 |        "      <td>11975</td>\n",
 353 |        "      <td>Alina</td>\n",
 354 |        "      <td>Manhattan</td>\n",
 355 |        "      <td>West Village</td>\n",
 356 |        "      <td>40.73530</td>\n",
 357 |        "      <td>-74.00525</td>\n",
 358 |        "      <td>Entire home/apt</td>\n",
 359 |        "      <td>120</td>\n",
 360 |        "      <td>90</td>\n",
 361 |        "      <td>27</td>\n",
 362 |        "      <td>31-10-2018</td>\n",
 363 |        "      <td>0.22</td>\n",
 364 |        "      <td>1</td>\n",
 365 |        "      <td>0</td>\n",
 366 |        "    </tr>\n",
 367 |        "    <tr>\n",
 368 |        "      <th>48905</th>\n",
 369 |        "      <td>6848</td>\n",
 370 |        "      <td>Only 2 stops to Manhattan studio</td>\n",
 371 |        "      <td>15991</td>\n",
 372 |        "      <td>Allen &amp; Irina</td>\n",
 373 |        "      <td>Brooklyn</td>\n",
 374 |        "      <td>Williamsburg</td>\n",
 375 |        "      <td>40.70837</td>\n",
 376 |        "      <td>-73.95352</td>\n",
 377 |        "      <td>Entire home/apt</td>\n",
 378 |        "      <td>140</td>\n",
 379 |        "      <td>2</td>\n",
 380 |        "      <td>148</td>\n",
 381 |        "      <td>29-06-2019</td>\n",
 382 |        "      <td>1.20</td>\n",
 383 |        "      <td>1</td>\n",
 384 |        "      <td>46</td>\n",
 385 |        "    </tr>\n",
 386 |        "  </tbody>\n",
 387 |        "</table>\n",
 388 |        "</div>"
 389 |       ],
 390 |       "text/plain": [
 391 |        "         id                                              name  host_id  \\\n",
 392 |        "48901  5441                   Central Manhattan/near Broadway     7989   \n",
 393 |        "48902  5803    Lovely Room 1, Garden, Best Area, Legal rental     9744   \n",
 394 |        "48903  6021  Wonderful Guest Bedroom in Manhattan for SINGLES    11528   \n",
 395 |        "48904  6090                     West Village Nest - Superhost    11975   \n",
 396 |        "48905  6848                  Only 2 stops to Manhattan studio    15991   \n",
 397 |        "\n",
 398 |        "           host_name neighbourhood_group    neighbourhood  latitude  \\\n",
 399 |        "48901           Kate           Manhattan   Hell's Kitchen  40.76076   \n",
 400 |        "48902         Laurie            Brooklyn      South Slope  40.66829   \n",
 401 |        "48903        Claudio           Manhattan  Upper West Side  40.79826   \n",
 402 |        "48904          Alina           Manhattan     West Village  40.73530   \n",
 403 |        "48905  Allen & Irina            Brooklyn     Williamsburg  40.70837   \n",
 404 |        "\n",
 405 |        "       longitude        room_type  price  minimum_nights  number_of_reviews  \\\n",
 406 |        "48901  -73.98867     Private room     85               2                188   \n",
 407 |        "48902  -73.98779     Private room     89               4                167   \n",
 408 |        "48903  -73.96113     Private room     85               2                113   \n",
 409 |        "48904  -74.00525  Entire home/apt    120              90                 27   \n",
 410 |        "48905  -73.95352  Entire home/apt    140               2                148   \n",
 411 |        "\n",
 412 |        "      last_review  reviews_per_month  calculated_host_listings_count  \\\n",
 413 |        "48901  23-06-2019               1.50                               1   \n",
 414 |        "48902  24-06-2019               1.34                               3   \n",
 415 |        "48903  05-07-2019               0.91                               1   \n",
 416 |        "48904  31-10-2018               0.22                               1   \n",
 417 |        "48905  29-06-2019               1.20                               1   \n",
 418 |        "\n",
 419 |        "       availability_365  \n",
 420 |        "48901                39  \n",
 421 |        "48902               314  \n",
 422 |        "48903               333  \n",
 423 |        "48904                 0  \n",
 424 |        "48905                46  "
 425 |       ]
 426 |      },
 427 |      "execution_count": 33,
 428 |      "metadata": {},
 429 |      "output_type": "execute_result"
 430 |     }
 431 |    ],
 432 |    "source": [
 433 |     "df.tail()"
 434 |    ]
 435 |   },
 436 |   {
 437 |    "cell_type": "code",
 438 |    "execution_count": 34,
 439 |    "id": "e1ee689c",
 440 |    "metadata": {},
 441 |    "outputs": [
 442 |     {
 443 |      "data": {
 444 |       "text/html": [
 445 |        "<div>\n",
 446 |        "<style scoped>\n",
 447 |        "    .dataframe tbody tr th:only-of-type {\n",
 448 |        "        vertical-align: middle;\n",
 449 |        "    }\n",
 450 |        "\n",
 451 |        "    .dataframe tbody tr th {\n",
 452 |        "        vertical-align: top;\n",
 453 |        "    }\n",
 454 |        "\n",
 455 |        "    .dataframe thead th {\n",
 456 |        "        text-align: right;\n",
 457 |        "    }\n",
 458 |        "</style>\n",
 459 |        "<table border=\"1\" class=\"dataframe\">\n",
 460 |        "  <thead>\n",
 461 |        "    <tr style=\"text-align: right;\">\n",
 462 |        "      <th></th>\n",
 463 |        "      <th>id</th>\n",
 464 |        "      <th>name</th>\n",
 465 |        "      <th>host_id</th>\n",
 466 |        "      <th>host_name</th>\n",
 467 |        "      <th>neighbourhood_group</th>\n",
 468 |        "      <th>neighbourhood</th>\n",
 469 |        "      <th>latitude</th>\n",
 470 |        "      <th>longitude</th>\n",
 471 |        "      <th>room_type</th>\n",
 472 |        "      <th>price</th>\n",
 473 |        "      <th>minimum_nights</th>\n",
 474 |        "      <th>number_of_reviews</th>\n",
 475 |        "      <th>last_review</th>\n",
 476 |        "      <th>reviews_per_month</th>\n",
 477 |        "      <th>calculated_host_listings_count</th>\n",
 478 |        "      <th>availability_365</th>\n",
 479 |        "    </tr>\n",
 480 |        "  </thead>\n",
 481 |        "  <tbody>\n",
 482 |        "    <tr>\n",
 483 |        "      <th>7024</th>\n",
 484 |        "      <td>5050156</td>\n",
 485 |        "      <td>Wake Up In The City That Never Sleeps</td>\n",
 486 |        "      <td>193488</td>\n",
 487 |        "      <td>Jane</td>\n",
 488 |        "      <td>Manhattan</td>\n",
 489 |        "      <td>East Village</td>\n",
 490 |        "      <td>40.73273</td>\n",
 491 |        "      <td>-73.98969</td>\n",
 492 |        "      <td>Private room</td>\n",
 493 |        "      <td>135</td>\n",
 494 |        "      <td>1</td>\n",
 495 |        "      <td>14</td>\n",
 496 |        "      <td>26-05-2019</td>\n",
 497 |        "      <td>0.28</td>\n",
 498 |        "      <td>2</td>\n",
 499 |        "      <td>332</td>\n",
 500 |        "    </tr>\n",
 501 |        "    <tr>\n",
 502 |        "      <th>3221</th>\n",
 503 |        "      <td>1923153</td>\n",
 504 |        "      <td>Cozy Vintage Inspired East Village</td>\n",
 505 |        "      <td>9965028</td>\n",
 506 |        "      <td>Sasha</td>\n",
 507 |        "      <td>Manhattan</td>\n",
 508 |        "      <td>East Village</td>\n",
 509 |        "      <td>40.72709</td>\n",
 510 |        "      <td>-73.98442</td>\n",
 511 |        "      <td>Entire home/apt</td>\n",
 512 |        "      <td>450</td>\n",
 513 |        "      <td>2</td>\n",
 514 |        "      <td>18</td>\n",
 515 |        "      <td>15-01-2017</td>\n",
 516 |        "      <td>0.28</td>\n",
 517 |        "      <td>1</td>\n",
 518 |        "      <td>363</td>\n",
 519 |        "    </tr>\n",
 520 |        "    <tr>\n",
 521 |        "      <th>18637</th>\n",
 522 |        "      <td>14741623</td>\n",
 523 |        "      <td>Cozy Private Bedroom and Bathroom in Brooklyn</td>\n",
 524 |        "      <td>39181402</td>\n",
 525 |        "      <td>Sarah</td>\n",
 526 |        "      <td>Brooklyn</td>\n",
 527 |        "      <td>Bedford-Stuyvesant</td>\n",
 528 |        "      <td>40.68179</td>\n",
 529 |        "      <td>-73.95252</td>\n",
 530 |        "      <td>Private room</td>\n",
 531 |        "      <td>48</td>\n",
 532 |        "      <td>3</td>\n",
 533 |        "      <td>67</td>\n",
 534 |        "      <td>22-06-2019</td>\n",
 535 |        "      <td>1.95</td>\n",
 536 |        "      <td>1</td>\n",
 537 |        "      <td>70</td>\n",
 538 |        "    </tr>\n",
 539 |        "    <tr>\n",
 540 |        "      <th>15805</th>\n",
 541 |        "      <td>12786165</td>\n",
 542 |        "      <td>Cozy Private room in Chelsea !</td>\n",
 543 |        "      <td>69598657</td>\n",
 544 |        "      <td>Vh</td>\n",
 545 |        "      <td>Manhattan</td>\n",
 546 |        "      <td>Chelsea</td>\n",
 547 |        "      <td>40.75094</td>\n",
 548 |        "      <td>-73.99748</td>\n",
 549 |        "      <td>Private room</td>\n",
 550 |        "      <td>75</td>\n",
 551 |        "      <td>2</td>\n",
 552 |        "      <td>115</td>\n",
 553 |        "      <td>23-06-2019</td>\n",
 554 |        "      <td>2.99</td>\n",
 555 |        "      <td>1</td>\n",
 556 |        "      <td>37</td>\n",
 557 |        "    </tr>\n",
 558 |        "    <tr>\n",
 559 |        "      <th>24028</th>\n",
 560 |        "      <td>19368455</td>\n",
 561 |        "      <td>Chelsea Gem</td>\n",
 562 |        "      <td>70154608</td>\n",
 563 |        "      <td>Donna</td>\n",
 564 |        "      <td>Manhattan</td>\n",
 565 |        "      <td>Chelsea</td>\n",
 566 |        "      <td>40.74625</td>\n",
 567 |        "      <td>-73.99911</td>\n",
 568 |        "      <td>Entire home/apt</td>\n",
 569 |        "      <td>185</td>\n",
 570 |        "      <td>5</td>\n",
 571 |        "      <td>17</td>\n",
 572 |        "      <td>01-07-2019</td>\n",
 573 |        "      <td>0.88</td>\n",
 574 |        "      <td>1</td>\n",
 575 |        "      <td>15</td>\n",
 576 |        "    </tr>\n",
 577 |        "  </tbody>\n",
 578 |        "</table>\n",
 579 |        "</div>"
 580 |       ],
 581 |       "text/plain": [
 582 |        "             id                                           name   host_id  \\\n",
 583 |        "7024    5050156          Wake Up In The City That Never Sleeps    193488   \n",
 584 |        "3221    1923153             Cozy Vintage Inspired East Village   9965028   \n",
 585 |        "18637  14741623  Cozy Private Bedroom and Bathroom in Brooklyn  39181402   \n",
 586 |        "15805  12786165                 Cozy Private room in Chelsea !  69598657   \n",
 587 |        "24028  19368455                                    Chelsea Gem  70154608   \n",
 588 |        "\n",
 589 |        "      host_name neighbourhood_group       neighbourhood  latitude  longitude  \\\n",
 590 |        "7024       Jane           Manhattan        East Village  40.73273  -73.98969   \n",
 591 |        "3221      Sasha           Manhattan        East Village  40.72709  -73.98442   \n",
 592 |        "18637     Sarah            Brooklyn  Bedford-Stuyvesant  40.68179  -73.95252   \n",
 593 |        "15805        Vh           Manhattan             Chelsea  40.75094  -73.99748   \n",
 594 |        "24028     Donna           Manhattan             Chelsea  40.74625  -73.99911   \n",
 595 |        "\n",
 596 |        "             room_type  price  minimum_nights  number_of_reviews last_review  \\\n",
 597 |        "7024      Private room    135               1                 14  26-05-2019   \n",
 598 |        "3221   Entire home/apt    450               2                 18  15-01-2017   \n",
 599 |        "18637     Private room     48               3                 67  22-06-2019   \n",
 600 |        "15805     Private room     75               2                115  23-06-2019   \n",
 601 |        "24028  Entire home/apt    185               5                 17  01-07-2019   \n",
 602 |        "\n",
 603 |        "       reviews_per_month  calculated_host_listings_count  availability_365  \n",
 604 |        "7024                0.28                               2               332  \n",
 605 |        "3221                0.28                               1               363  \n",
 606 |        "18637               1.95                               1                70  \n",
 607 |        "15805               2.99                               1                37  \n",
 608 |        "24028               0.88                               1                15  "
 609 |       ]
 610 |      },
 611 |      "execution_count": 34,
 612 |      "metadata": {},
 613 |      "output_type": "execute_result"
 614 |     }
 615 |    ],
 616 |    "source": [
 617 |     "df.sample(5)"
 618 |    ]
 619 |   },
 620 |   {
 621 |    "cell_type": "markdown",
 622 |    "id": "14ded357",
 623 |    "metadata": {},
 624 |    "source": [
 625 |     "## 3. What is the datatype of cols?"
 626 |    ]
 627 |   },
 628 |   {
 629 |    "cell_type": "code",
 630 |    "execution_count": 36,
 631 |    "id": "3b6ba267",
 632 |    "metadata": {},
 633 |    "outputs": [
 634 |     {
 635 |      "name": "stdout",
 636 |      "output_type": "stream",
 637 |      "text": [
 638 |       "<class 'pandas.core.frame.DataFrame'>\n",
 639 |       "RangeIndex: 48906 entries, 0 to 48905\n",
 640 |       "Data columns (total 16 columns):\n",
 641 |       " #   Column                          Non-Null Count  Dtype  \n",
 642 |       "---  ------                          --------------  -----  \n",
 643 |       " 0   id                              48906 non-null  int64  \n",
 644 |       " 1   name                            48890 non-null  object \n",
 645 |       " 2   host_id                         48906 non-null  int64  \n",
 646 |       " 3   host_name                       48885 non-null  object \n",
 647 |       " 4   neighbourhood_group             48906 non-null  object \n",
 648 |       " 5   neighbourhood                   48906 non-null  object \n",
 649 |       " 6   latitude                        48906 non-null  float64\n",
 650 |       " 7   longitude                       48906 non-null  float64\n",
 651 |       " 8   room_type                       48906 non-null  object \n",
 652 |       " 9   price                           48906 non-null  int64  \n",
 653 |       " 10  minimum_nights                  48906 non-null  int64  \n",
 654 |       " 11  number_of_reviews               48906 non-null  int64  \n",
 655 |       " 12  last_review                     38854 non-null  object \n",
 656 |       " 13  reviews_per_month               38854 non-null  float64\n",
 657 |       " 14  calculated_host_listings_count  48906 non-null  int64  \n",
 658 |       " 15  availability_365                48906 non-null  int64  \n",
 659 |       "dtypes: float64(3), int64(7), object(6)\n",
 660 |       "memory usage: 6.0+ MB\n"
 661 |      ]
 662 |     }
 663 |    ],
 664 |    "source": [
 665 |     "df.info()"
 666 |    ]
 667 |   },
 668 |   {
 669 |    "cell_type": "markdown",
 670 |    "id": "5f2c538a",
 671 |    "metadata": {},
 672 |    "source": [
 673 |     "## 4. Are there any missing values?"
 674 |    ]
 675 |   },
 676 |   {
 677 |    "cell_type": "code",
 678 |    "execution_count": 37,
 679 |    "id": "fe257b4f",
 680 |    "metadata": {},
 681 |    "outputs": [
 682 |     {
 683 |      "data": {
 684 |       "text/plain": [
 685 |        "id                                    0\n",
 686 |        "name                                 16\n",
 687 |        "host_id                               0\n",
 688 |        "host_name                            21\n",
 689 |        "neighbourhood_group                   0\n",
 690 |        "neighbourhood                         0\n",
 691 |        "latitude                              0\n",
 692 |        "longitude                             0\n",
 693 |        "room_type                             0\n",
 694 |        "price                                 0\n",
 695 |        "minimum_nights                        0\n",
 696 |        "number_of_reviews                     0\n",
 697 |        "last_review                       10052\n",
 698 |        "reviews_per_month                 10052\n",
 699 |        "calculated_host_listings_count        0\n",
 700 |        "availability_365                      0\n",
 701 |        "dtype: int64"
 702 |       ]
 703 |      },
 704 |      "execution_count": 37,
 705 |      "metadata": {},
 706 |      "output_type": "execute_result"
 707 |     }
 708 |    ],
 709 |    "source": [
 710 |     "df.isna().sum()"
 711 |    ]
 712 |   },
 713 |   {
 714 |    "cell_type": "markdown",
 715 |    "id": "b8b5f3a1",
 716 |    "metadata": {},
 717 |    "source": [
 718 |     "## 5. How does the data look like mathematically?"
 719 |    ]
 720 |   },
 721 |   {
 722 |    "cell_type": "code",
 723 |    "execution_count": 38,
 724 |    "id": "fa4bc8f7",
 725 |    "metadata": {},
 726 |    "outputs": [
 727 |     {
 728 |      "data": {
 729 |       "text/html": [
 730 |        "<div>\n",
 731 |        "<style scoped>\n",
 732 |        "    .dataframe tbody tr th:only-of-type {\n",
 733 |        "        vertical-align: middle;\n",
 734 |        "    }\n",
 735 |        "\n",
 736 |        "    .dataframe tbody tr th {\n",
 737 |        "        vertical-align: top;\n",
 738 |        "    }\n",
 739 |        "\n",
 740 |        "    .dataframe thead th {\n",
 741 |        "        text-align: right;\n",
 742 |        "    }\n",
 743 |        "</style>\n",
 744 |        "<table border=\"1\" class=\"dataframe\">\n",
 745 |        "  <thead>\n",
 746 |        "    <tr style=\"text-align: right;\">\n",
 747 |        "      <th></th>\n",
 748 |        "      <th>id</th>\n",
 749 |        "      <th>host_id</th>\n",
 750 |        "      <th>latitude</th>\n",
 751 |        "      <th>longitude</th>\n",
 752 |        "      <th>price</th>\n",
 753 |        "      <th>minimum_nights</th>\n",
 754 |        "      <th>number_of_reviews</th>\n",
 755 |        "      <th>reviews_per_month</th>\n",
 756 |        "      <th>calculated_host_listings_count</th>\n",
 757 |        "      <th>availability_365</th>\n",
 758 |        "    </tr>\n",
 759 |        "  </thead>\n",
 760 |        "  <tbody>\n",
 761 |        "    <tr>\n",
 762 |        "      <th>count</th>\n",
 763 |        "      <td>4.890600e+04</td>\n",
 764 |        "      <td>4.890600e+04</td>\n",
 765 |        "      <td>48906.000000</td>\n",
 766 |        "      <td>48906.000000</td>\n",
 767 |        "      <td>48906.000000</td>\n",
 768 |        "      <td>48906.000000</td>\n",
 769 |        "      <td>48906.000000</td>\n",
 770 |        "      <td>38854.000000</td>\n",
 771 |        "      <td>48906.000000</td>\n",
 772 |        "      <td>48906.000000</td>\n",
 773 |        "    </tr>\n",
 774 |        "    <tr>\n",
 775 |        "      <th>mean</th>\n",
 776 |        "      <td>1.901287e+07</td>\n",
 777 |        "      <td>6.760480e+07</td>\n",
 778 |        "      <td>40.728952</td>\n",
 779 |        "      <td>-73.952175</td>\n",
 780 |        "      <td>152.711324</td>\n",
 781 |        "      <td>7.031612</td>\n",
 782 |        "      <td>23.300454</td>\n",
 783 |        "      <td>1.373151</td>\n",
 784 |        "      <td>7.142702</td>\n",
 785 |        "      <td>112.782031</td>\n",
 786 |        "    </tr>\n",
 787 |        "    <tr>\n",
 788 |        "      <th>std</th>\n",
 789 |        "      <td>1.098557e+07</td>\n",
 790 |        "      <td>7.860866e+07</td>\n",
 791 |        "      <td>0.054529</td>\n",
 792 |        "      <td>0.046154</td>\n",
 793 |        "      <td>240.128713</td>\n",
 794 |        "      <td>20.512489</td>\n",
 795 |        "      <td>44.607175</td>\n",
 796 |        "      <td>1.680270</td>\n",
 797 |        "      <td>32.948926</td>\n",
 798 |        "      <td>131.620370</td>\n",
 799 |        "    </tr>\n",
 800 |        "    <tr>\n",
 801 |        "      <th>min</th>\n",
 802 |        "      <td>2.539000e+03</td>\n",
 803 |        "      <td>2.438000e+03</td>\n",
 804 |        "      <td>40.499790</td>\n",
 805 |        "      <td>-74.244420</td>\n",
 806 |        "      <td>0.000000</td>\n",
 807 |        "      <td>1.000000</td>\n",
 808 |        "      <td>0.000000</td>\n",
 809 |        "      <td>0.010000</td>\n",
 810 |        "      <td>1.000000</td>\n",
 811 |        "      <td>0.000000</td>\n",
 812 |        "    </tr>\n",
 813 |        "    <tr>\n",
 814 |        "      <th>25%</th>\n",
 815 |        "      <td>9.464662e+06</td>\n",
 816 |        "      <td>7.809567e+06</td>\n",
 817 |        "      <td>40.690100</td>\n",
 818 |        "      <td>-73.983080</td>\n",
 819 |        "      <td>69.000000</td>\n",
 820 |        "      <td>1.000000</td>\n",
 821 |        "      <td>1.000000</td>\n",
 822 |        "      <td>0.190000</td>\n",
 823 |        "      <td>1.000000</td>\n",
 824 |        "      <td>0.000000</td>\n",
 825 |        "    </tr>\n",
 826 |        "    <tr>\n",
 827 |        "      <th>50%</th>\n",
 828 |        "      <td>1.967545e+07</td>\n",
 829 |        "      <td>3.078463e+07</td>\n",
 830 |        "      <td>40.723080</td>\n",
 831 |        "      <td>-73.955685</td>\n",
 832 |        "      <td>106.000000</td>\n",
 833 |        "      <td>3.000000</td>\n",
 834 |        "      <td>5.000000</td>\n",
 835 |        "      <td>0.720000</td>\n",
 836 |        "      <td>1.000000</td>\n",
 837 |        "      <td>45.000000</td>\n",
 838 |        "    </tr>\n",
 839 |        "    <tr>\n",
 840 |        "      <th>75%</th>\n",
 841 |        "      <td>2.915085e+07</td>\n",
 842 |        "      <td>1.074344e+08</td>\n",
 843 |        "      <td>40.763120</td>\n",
 844 |        "      <td>-73.936283</td>\n",
 845 |        "      <td>175.000000</td>\n",
 846 |        "      <td>5.000000</td>\n",
 847 |        "      <td>24.000000</td>\n",
 848 |        "      <td>2.020000</td>\n",
 849 |        "      <td>2.000000</td>\n",
 850 |        "      <td>227.000000</td>\n",
 851 |        "    </tr>\n",
 852 |        "    <tr>\n",
 853 |        "      <th>max</th>\n",
 854 |        "      <td>3.648724e+07</td>\n",
 855 |        "      <td>2.743213e+08</td>\n",
 856 |        "      <td>40.913060</td>\n",
 857 |        "      <td>-73.712990</td>\n",
 858 |        "      <td>10000.000000</td>\n",
 859 |        "      <td>1250.000000</td>\n",
 860 |        "      <td>629.000000</td>\n",
 861 |        "      <td>58.500000</td>\n",
 862 |        "      <td>327.000000</td>\n",
 863 |        "      <td>365.000000</td>\n",
 864 |        "    </tr>\n",
 865 |        "  </tbody>\n",
 866 |        "</table>\n",
 867 |        "</div>"
 868 |       ],
 869 |       "text/plain": [
 870 |        "                 id       host_id      latitude     longitude         price  \\\n",
 871 |        "count  4.890600e+04  4.890600e+04  48906.000000  48906.000000  48906.000000   \n",
 872 |        "mean   1.901287e+07  6.760480e+07     40.728952    -73.952175    152.711324   \n",
 873 |        "std    1.098557e+07  7.860866e+07      0.054529      0.046154    240.128713   \n",
 874 |        "min    2.539000e+03  2.438000e+03     40.499790    -74.244420      0.000000   \n",
 875 |        "25%    9.464662e+06  7.809567e+06     40.690100    -73.983080     69.000000   \n",
 876 |        "50%    1.967545e+07  3.078463e+07     40.723080    -73.955685    106.000000   \n",
 877 |        "75%    2.915085e+07  1.074344e+08     40.763120    -73.936283    175.000000   \n",
 878 |        "max    3.648724e+07  2.743213e+08     40.913060    -73.712990  10000.000000   \n",
 879 |        "\n",
 880 |        "       minimum_nights  number_of_reviews  reviews_per_month  \\\n",
 881 |        "count    48906.000000       48906.000000       38854.000000   \n",
 882 |        "mean         7.031612          23.300454           1.373151   \n",
 883 |        "std         20.512489          44.607175           1.680270   \n",
 884 |        "min          1.000000           0.000000           0.010000   \n",
 885 |        "25%          1.000000           1.000000           0.190000   \n",
 886 |        "50%          3.000000           5.000000           0.720000   \n",
 887 |        "75%          5.000000          24.000000           2.020000   \n",
 888 |        "max       1250.000000         629.000000          58.500000   \n",
 889 |        "\n",
 890 |        "       calculated_host_listings_count  availability_365  \n",
 891 |        "count                    48906.000000      48906.000000  \n",
 892 |        "mean                         7.142702        112.782031  \n",
 893 |        "std                         32.948926        131.620370  \n",
 894 |        "min                          1.000000          0.000000  \n",
 895 |        "25%                          1.000000          0.000000  \n",
 896 |        "50%                          1.000000         45.000000  \n",
 897 |        "75%                          2.000000        227.000000  \n",
 898 |        "max                        327.000000        365.000000  "
 899 |       ]
 900 |      },
 901 |      "execution_count": 38,
 902 |      "metadata": {},
 903 |      "output_type": "execute_result"
 904 |     }
 905 |    ],
 906 |    "source": [
 907 |     "df.describe()"
 908 |    ]
 909 |   },
 910 |   {
 911 |    "cell_type": "markdown",
 912 |    "id": "290855e4",
 913 |    "metadata": {},
 914 |    "source": [
 915 |     "## 6. Are there any duplicate values?"
 916 |    ]
 917 |   },
 918 |   {
 919 |    "cell_type": "code",
 920 |    "execution_count": 39,
 921 |    "id": "0298e5a3",
 922 |    "metadata": {},
 923 |    "outputs": [
 924 |     {
 925 |      "data": {
 926 |       "text/plain": [
 927 |        "11"
 928 |       ]
 929 |      },
 930 |      "execution_count": 39,
 931 |      "metadata": {},
 932 |      "output_type": "execute_result"
 933 |     }
 934 |    ],
 935 |    "source": [
 936 |     "df.duplicated().sum()"
 937 |    ]
 938 |   },
 939 |   {
 940 |    "cell_type": "markdown",
 941 |    "id": "59b998f0",
 942 |    "metadata": {},
 943 |    "source": [
 944 |     "## 7. How many unique values are there in each column?"
 945 |    ]
 946 |   },
 947 |   {
 948 |    "cell_type": "code",
 949 |    "execution_count": 40,
 950 |    "id": "6541d846",
 951 |    "metadata": {},
 952 |    "outputs": [
 953 |     {
 954 |      "data": {
 955 |       "text/plain": [
 956 |        "id                                48895\n",
 957 |        "name                              47896\n",
 958 |        "host_id                           37457\n",
 959 |        "host_name                         11452\n",
 960 |        "neighbourhood_group                   5\n",
 961 |        "neighbourhood                       221\n",
 962 |        "latitude                          19048\n",
 963 |        "longitude                         14718\n",
 964 |        "room_type                             3\n",
 965 |        "price                               674\n",
 966 |        "minimum_nights                      109\n",
 967 |        "number_of_reviews                   394\n",
 968 |        "last_review                        1764\n",
 969 |        "reviews_per_month                   937\n",
 970 |        "calculated_host_listings_count       47\n",
 971 |        "availability_365                    366\n",
 972 |        "dtype: int64"
 973 |       ]
 974 |      },
 975 |      "execution_count": 40,
 976 |      "metadata": {},
 977 |      "output_type": "execute_result"
 978 |     }
 979 |    ],
 980 |    "source": [
 981 |     "df.nunique()"
 982 |    ]
 983 |   },
 984 |   {
 985 |    "cell_type": "code",
 986 |    "execution_count": 41,
 987 |    "id": "ce2dc51b",
 988 |    "metadata": {},
 989 |    "outputs": [
 990 |     {
 991 |      "data": {
 992 |       "text/plain": [
 993 |        "array(['Brooklyn', 'Manhattan', 'Queens', 'Staten Island', 'Bronx'],\n",
 994 |        "      dtype=object)"
 995 |       ]
 996 |      },
 997 |      "execution_count": 41,
 998 |      "metadata": {},
 999 |      "output_type": "execute_result"
1000 |     }
1001 |    ],
1002 |    "source": [
1003 |     "df[\"neighbourhood_group\"].unique()"
1004 |    ]
1005 |   },
1006 |   {
1007 |    "cell_type": "markdown",
1008 |    "id": "61865104",
1009 |    "metadata": {},
1010 |    "source": [
1011 |     "## 8. Are there any outliers in the numerical columns?"
1012 |    ]
1013 |   },
1014 |   {
1015 |    "cell_type": "code",
1016 |    "execution_count": 42,
1017 |    "id": "03a7266d",
1018 |    "metadata": {},
1019 |    "outputs": [
1020 |     {
1021 |      "data": {
1022 |       "text/plain": [
1023 |        "<AxesSubplot: >"
1024 |       ]
1025 |      },
1026 |      "execution_count": 42,
1027 |      "metadata": {},
1028 |      "output_type": "execute_result"
1029 |     },
1030 |     {
1031 |      "data": {
1032 |       "image/png": "iVBORw0KGgoAAAANSUhEUgAAAjkAAAGdCAYAAADwjmIIAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjYuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8o6BhiAAAACXBIWXMAAA9hAAAPYQGoP6dpAAAsoUlEQVR4nO3de3TU9Z3/8ddMYibcJlGQiYEJjdsqsuIFQ2LwVjWHaMEjre6CiehSqq0LFohV4VguP6wbLjUt1gtaWWGPSb3sWW9xwaVQZGvSEOIiN0HPEZlEnAEDmQElAWa+vz96MsvIxMbNMF/ymefjnDnHfN6f+c77iyczr3zn+/18HZZlWQIAADCM0+4GAAAATgdCDgAAMBIhBwAAGImQAwAAjETIAQAARiLkAAAAIxFyAACAkQg5AADASOl2N2CnSCSiffv2acCAAXI4HHa3AwAAusGyLB0+fFi5ublyOrs+XpPSIWffvn3yer12twEAAP4PmpubNXTo0C7rKR1yBgwYIOmv/0hut9vmbgAAQHeEQiF5vd7o53hXUjrkdH5F5Xa7CTkAAPQyf+tUE048BgAARiLkAAAAIxFyAACAkQg5AADASIQcAABgJEIOAAAwEiEHAAAYiZADAACMRMgBYKQFCxbo+9//vhYsWGB3KwBs8q1DzsaNG3XLLbcoNzdXDodDr7/+ekzdsizNmzdP5513nvr06aOSkhJ9/PHHMXMOHjyo8vJyud1uZWdna+rUqTpy5EjMnK1bt+qaa65RZmamvF6vlixZckovr776qoYPH67MzEyNHDlS//mf//ltdweAgQKBgDZs2CBJ2rBhgwKBgL0NAbDFtw45X375pS699FI99dRTcetLlizRE088oeXLl6uhoUH9+vVTaWmp2tvbo3PKy8u1Y8cOrV27VrW1tdq4caPuvffeaD0UCmns2LEaNmyYmpqatHTpUi1YsEDPPfdcdE5dXZ3uuOMOTZ06Vf/zP/+jCRMmaMKECdq+ffu33SUAhrnvvvtifv7nf/5nmzoBYCurByRZr732WvTnSCRi5eTkWEuXLo2OtbW1WS6Xy/rDH/5gWZZl7dy505JkNTY2RuesXr3acjgc1meffWZZlmU9/fTT1tlnn211dHRE5zz88MPWhRdeGP35H//xH61x48bF9FNUVGT99Kc/7Xb/wWDQkmQFg8FuPwfAmW316tXWddddd8pj9erVdrcGIEG6+/md0HNy9uzZI7/fr5KSkuhYVlaWioqKVF9fL0mqr69Xdna2CgoKonNKSkrkdDrV0NAQnXPttdcqIyMjOqe0tFS7d+/WoUOHonNOfp3OOZ2vE09HR4dCoVDMA4A5wuGwFi9eHLe2ePFihcPhJHcEwE4JDTl+v1+S5PF4YsY9Hk+05vf7NXjw4Jh6enq6zjnnnJg58bZx8mt0NaezHk9lZaWysrKiD6/X+213EcAZ7I033pBlWXFrlmXpjTfeSHJHAOyUUldXzZkzR8FgMPpobm62uyUAAHCaJDTk5OTkSNIpVzIEAoFoLScnR/v374+pnzhxQgcPHoyZE28bJ79GV3M66/G4XC653e6YBwBz3HrrrXI647+tOZ1O3XrrrUnuCICdEhpy8vPzlZOTo3Xr1kXHQqGQGhoaVFxcLEkqLi5WW1ubmpqaonPWr1+vSCSioqKi6JyNGzfq+PHj0Tlr167VhRdeqLPPPjs65+TX6ZzT+ToAUk9aWpoeeuihuLXZs2crLS0tyR0BsNO3DjlHjhzRli1btGXLFkl/Pdl4y5Yt8vl8cjgcmjlzpn71q1/pzTff1LZt23TXXXcpNzdXEyZMkCRddNFFuummm3TPPfdo06ZNeu+99zR9+nRNmjRJubm5kqSysjJlZGRo6tSp2rFjh15++WUtW7ZMFRUV0T5mzJihNWvW6PHHH9euXbu0YMECbd68WdOnT+/5vwqAXuumm27SwIEDY8YGDhyosWPH2tQRANt828u2/vSnP1mSTnncfffdlmX99TLyuXPnWh6Px3K5XNaNN95o7d69O2Ybra2t1h133GH179/fcrvd1pQpU6zDhw/HzPnggw+sq6++2nK5XNaQIUOsRYsWndLLK6+8Yl1wwQVWRkaG9fd///fW22+//a32hUvIATP5/f6Yy8f9fr/dLQFIoO5+fjssq4tLEVJAKBRSVlaWgsEg5+cAhlmwYIE2bNjArR0AA3X385uQQ8gBAKBX6e7nd0pdQg4AAFIHIQcAABiJkAMAAIxEyAEAAEYi5AAAACMRcgAAgJEIOQAAwEiEHAAAYCRCDgAAMBIhBwAAGImQAwAAjETIAQAARiLkAAAAIxFyAACAkQg5AADASIQcAABgJEIOAAAwEiEHAAAYiZADAACMRMgBAABGIuQAAAAjEXIAAICRCDkAAMBIhBwAAGAkQg4AADASIQcAABiJkAMAAIxEyAEAAEYi5AAAACMRcgAAgJEIOQAAwEiEHAAAYCRCDgAAMBIhBwAAGImQAwAAjETIAQAARiLkAAAAIxFyAACAkQg5AIxUV1eniRMnqq6uzu5WANiEkAPAOO3t7aqqqlIgEFBVVZXa29vtbgmADQg5AIxTXV2t1tZWSVJra6tqamps7giAHQg5AIzS0tKimpoaWZYlSbIsSzU1NWppabG5MwDJRsgBYAzLsrRs2bIuxzuDD4DUQMgBYAyfz6fGxkaFw+GY8XA4rMbGRvl8Pps6A2AHQg4AY+Tl5Wn06NFKS0uLGU9LS1NhYaHy8vJs6gyAHQg5AIzhcDg0Y8aMLscdDocNXQGwCyEHgFGGDh2qsrKyaKBxOBwqKyvTkCFDbO4MQLIRcgAYp7y8XAMHDpQkDRo0SGVlZTZ3BMAOhBwAxsnMzFRFRYU8Ho9mzZqlzMxMu1sCYIN0uxsAgNNhzJgxGjNmjN1tALARR3IAAICRCDkAAMBIhBwAAGAkQg4AADASIQcAABgp4SEnHA5r7ty5ys/PV58+ffR3f/d3evTRR2NujGdZlubNm6fzzjtPffr0UUlJiT7++OOY7Rw8eFDl5eVyu93Kzs7W1KlTdeTIkZg5W7du1TXXXKPMzEx5vV4tWbIk0bsDoJeqq6vTxIkTVVdXZ3crAGyS8JCzePFiPfPMM3ryySf14YcfavHixVqyZIl+97vfRecsWbJETzzxhJYvX66Ghgb169dPpaWlam9vj84pLy/Xjh07tHbtWtXW1mrjxo269957o/VQKKSxY8dq2LBhampq0tKlS7VgwQI999xzid4lAL1Me3u7qqqqFAgEVFVVFfPeAiB1OKyTD7EkwPjx4+XxeLRixYro2G233aY+ffroxRdflGVZys3N1QMPPKBf/OIXkqRgMCiPx6OVK1dq0qRJ+vDDDzVixAg1NjaqoKBAkrRmzRr94Ac/UEtLi3Jzc/XMM8/okUcekd/vV0ZGhiRp9uzZev3117Vr165u9RoKhZSVlaVgMCi3253IfwYANlqxYkX0/cbhcGjy5Mn68Y9/bHdbABKku5/fCT+SM2bMGK1bt04fffSRJOmDDz7Qn//8Z918882SpD179sjv96ukpCT6nKysLBUVFam+vl6SVF9fr+zs7GjAkaSSkhI5nU41NDRE51x77bXRgCNJpaWl2r17tw4dOpTo3QLQS7S0tKimpib6FbllWaqpqVFLS4vNnQFItoSveDx79myFQiENHz5caWlpCofDeuyxx1ReXi5J8vv9kiSPxxPzPI/HE635/X4NHjw4ttH0dJ1zzjkxc/Lz80/ZRmft7LPPPqW3jo4OdXR0RH8OhUI92VUAZxjLsrRs2bIux5csWcKdyIEUkvAjOa+88oqqq6tVU1Oj999/X6tWrdKvf/1rrVq1KtEv9a1VVlYqKysr+vB6vXa3BCCBfD6fGhsbFQ6HY8bD4bAaGxvl8/ls6gyAHRIech588EHNnj1bkyZN0siRIzV58mTNmjVLlZWVkqScnBxJUiAQiHleIBCI1nJycrR///6Y+okTJ3Tw4MGYOfG2cfJrfN2cOXMUDAajj+bm5h7uLYAzSV5enkaPHq20tLSY8bS0NBUWFiovL8+mzgDYIeEh56uvvpLTGbvZtLQ0RSIRSVJ+fr5ycnK0bt26aD0UCqmhoUHFxcWSpOLiYrW1tampqSk6Z/369YpEIioqKorO2bhxo44fPx6ds3btWl144YVxv6qSJJfLJbfbHfMAYA6Hw6EZM2Z0Oc5XVUBqSXjIueWWW/TYY4/p7bff1qeffqrXXntNVVVV+uEPfyjpr282M2fO1K9+9Su9+eab2rZtm+666y7l5uZqwoQJkqSLLrpIN910k+655x5t2rRJ7733nqZPn65JkyYpNzdXklRWVqaMjAxNnTpVO3bs0Msvv6xly5apoqIi0bsEoBcZOnSoysrKooHG4XCorKxMQ4YMsbkzAElnJVgoFLJmzJhh5eXlWZmZmdb5559vPfLII1ZHR0d0TiQSsebOnWt5PB7L5XJZN954o7V79+6Y7bS2tlp33HGH1b9/f8vtdltTpkyxDh8+HDPngw8+sK6++mrL5XJZQ4YMsRYtWvSteg0Gg5YkKxgM/t93GMAZ5+jRo9Ztt91mXXfdddbtt99uHT161O6WACRQdz+/E75OTm/COjmAuVasWKHq6mqVl5dr6tSpdrcDIIFsWycHAOzW3t6u1atXKxKJaPXq1ax4DKQoQg4A41RXV6u1tVWS1NraqpqaGps7AmAHQg4Ao7DiMYBOhBwAxrD+xorHKXwKIpCSCDkAjMGKxwBORsgBYAxWPAZwMkIOAGN0rmzcucJ6J8uyWPEYSEGEHABGGTp0qAYNGhQzNmjQIFY8BlIQIQeAUTZv3qwDBw7EjO3fv1+bN2+2qSMAdiHkADBGJBLRwoUL49YWLlx4ytdYAMxGyAFgjIaGBoVCobi1UCikhoaGJHcEwE6EHADGKCoq6vI+NllZWSoqKkpyRwDsRMgBYAyn06l58+bFrc2fP19OJ295QCrhNx6AUQoKCjRy5MiYsUsuuUSjRo2yqSMAdiHkADDOo48+Gj1q43Q6uzwZGYDZCDkAjJOdna3y8nI5nU6Vl5crOzvb7pYA2MBhpfAd60KhkLKyshQMBrs8WREAAJxZuvv5zZEcAABgJEIOAAAwEiEHAAAYiZADAACMRMgBAABGIuQAAAAjEXIAAICRCDkAAMBIhBwAAGAkQg4AADASIQcAABiJkAMAAIxEyAFgpLq6Ok2cOFF1dXV2twLAJoQcAMZpb29XVVWVAoGAqqqq1N7ebndLAGxAyAFgnOrqarW2tkqSWltbVVNTY3NHAOxAyAFglJaWFtXU1MiyLEmSZVmqqalRS0uLzZ0BSDZCDgBjWJalZcuWdTneGXwApAZCDgBj+Hw+NTY2KhwOx4yHw2E1NjbK5/PZ1BkAOxByABgjLy9Po0ePVlpaWsx4WlqaCgsLlZeXZ1NnAOxAyAFgDIfDoRkzZnQ57nA4bOgKgF0IOQCMMnToUJWVlUUDjcPhUFlZmYYMGWJzZwCSjZADwDjl5eUaOHCgJGnQoEEqKyuzuSMAdiDkADBOZmamcnJyJEkej0eZmZk2dwTADoQcAMYJBALavn27JGn79u0KBAI2dwTADoQcAMaZPn16zM/333+/TZ0AsBMhB4BR1qxZowMHDsSM7d+/X2vWrLGpIwB2IeQAMEY4HNbSpUvj1pYuXXrKIoEAzEbIAWCM2traLoNMOBxWbW1tkjsCYCdCDgBjjB8//pTVjjulpaVp/PjxSe4IgJ0IOQCM4XQ65fV649a8Xq+cTt7ygFTCbzwAY/h8Pn366adxa59++ik36ARSDCEHgDE6b9D5dQ6Hgxt0AimIkAPAGJ034ox3F3Ju0AmkHkIOAKNwg04AnQg5AIzDDToBSIQcAAbKzMxURUWFPB6PZs2axQ06gRSVbncDAHA6jBkzRmPGjLG7DQA24kgOAAAwEiEHAAAYiZADwEgrVqzQDTfcoBUrVtjdCgCbnJaQ89lnn+nOO+/UwIED1adPH40cOVKbN2+O1i3L0rx583TeeeepT58+Kikp0ccffxyzjYMHD6q8vFxut1vZ2dmaOnWqjhw5EjNn69atuuaaa5SZmSmv16slS5acjt0B0Mu0tbWpurpakUhE1dXVamtrs7slADZIeMg5dOiQrrrqKp111llavXq1du7cqccff1xnn312dM6SJUv0xBNPaPny5WpoaFC/fv1UWlqq9vb26Jzy8nLt2LFDa9euVW1trTZu3Kh77703Wg+FQho7dqyGDRumpqYmLV26VAsWLNBzzz2X6F0C0MvMnTtXkUhEkhSJRDRv3jybOwJgB4dlWVYiNzh79my99957+u///u+4dcuylJubqwceeEC/+MUvJEnBYFAej0crV67UpEmT9OGHH2rEiBFqbGxUQUGBJGnNmjX6wQ9+oJaWFuXm5uqZZ57RI488Ir/fr4yMjOhrv/7669q1a1e3eg2FQsrKylIwGJTb7U7A3gOw2+bNm6PvLSf79a9/HX0/AdC7dffzO+FHct58800VFBToH/7hHzR48GBdfvnl+v3vfx+t79mzR36/XyUlJdGxrKwsFRUVqb6+XpJUX1+v7OzsmDekkpISOZ1ONTQ0ROdce+210YAjSaWlpdq9e7cOHToUt7eOjg6FQqGYBwBzRCIRLVy4MG5t4cKF0aM7AFJDwkPOJ598omeeeUbf+9739M477+i+++7Tz3/+c61atUqS5Pf7JUkejyfmeR6PJ1rz+/0aPHhwTD09PV3nnHNOzJx42zj5Nb6usrJSWVlZ0YfX6+3h3gI4kzQ0NHT5x0soFIr+kQQgNSQ85EQiEY0aNUr/8i//ossvv1z33nuv7rnnHi1fvjzRL/WtzZkzR8FgMPpobm62uyUACVRUVNTloevOI8YAUkfCQ855552nESNGxIxddNFF8vl8kqScnBxJUiAQiJkTCASitZycHO3fvz+mfuLECR08eDBmTrxtnPwaX+dyueR2u2MeAMzhdDq7PMl4/vz5cjpZNQNIJQn/jb/qqqu0e/fumLGPPvpIw4YNkyTl5+crJydH69ati9Y7DyMXFxdLkoqLi9XW1qampqbonPXr1ysSiUT/EisuLtbGjRt1/Pjx6Jy1a9fqwgsvjLmSC0BqKSgo0MiRI2PGLrnkEo0aNcqmjgDYxkqwTZs2Wenp6dZjjz1mffzxx1Z1dbXVt29f68UXX4zOWbRokZWdnW298cYb1tatW61bb73Vys/Pt44ePRqdc9NNN1mXX3651dDQYP35z3+2vve971l33HFHtN7W1mZ5PB5r8uTJ1vbt262XXnrJ6tu3r/Xss892u9dgMGhJsoLBYGJ2HsAZ4dChQ9b1119vXXfdddb1119vHTp0yO6WACRQdz+/Ex5yLMuy3nrrLeviiy+2XC6XNXz4cOu5556LqUciEWvu3LmWx+OxXC6XdeONN1q7d++OmdPa2mrdcccdVv/+/S23221NmTLFOnz4cMycDz74wLr66qstl8tlDRkyxFq0aNG36pOQA5jr+eeft66//nrr+eeft7sVAAnW3c/vhK+T05uwTg4AAL2PbevkAAAAnAkIOQAAwEiEHAAAYCRCDgAAMBIhBwAAGImQAwAAjETIAQAARiLkAAAAIxFyAACAkQg5AADASIQcAABgJEIOAAAwEiEHAAAYiZADwEh1dXWaOHGi6urq7G4FgE0IOQCM097erqqqKgUCAVVVVam9vd3ulgDYgJADwDjV1dVqbW2VJLW2tqqmpsbmjgDYgZADwCgtLS2qqamRZVmSJMuyVFNTo5aWFps7A5BshBwAxrAsS8uWLetyvDP4AEgNhBwAxvD5fGpsbFQ4HI4ZD4fDamxslM/ns6kzAHYg5AAwRl5enkaPHi2nM/atzel0qrCwUHl5eTZ1BsAOhBwAxnA4HJoxY8YpX0tZlqUZM2bI4XDY1BkAOxByABjP4XBwPg6Qggg5AIzReYJxvCM2nHgMpB5CDgBjdJ54HIlEYsYjkQgnHgMpiJADwBh5eXkaNGhQ3Nq5557LicdAiiHkADDG8ePH9cUXX8StHThwQMePH09yRwDsRMgBYIzKysoe1QGYhZADwBhz5szpUR2AWQg5AIyRkZGhcePGxa3dcsstysjISHJHAOxEyAFglAcffPCUS8gdDoceeOABmzoCYBdCDgDj/O53v/vGnwGkBkIOAONcfPHF0UvJBw0apIsvvtjmjgDYId3uBgDgdPj3f/93u1sAYDOO5AAAACMRcgAAgJEIOQAAwEiEHAAAYCRCDgAAMBIhB4CRVqxYoRtuuEErVqywuxUANiHkADBOW1ubqqurFYlEVF1drba2NrtbAmADQg4A48ydO1eRSESSFIlENG/ePJs7AmAHQg4Ao2zevFnbtm2LGdu6das2b95sU0cA7ELIAWCMSCSihQsXxq0tXLgwenQHQGog5AAwRkNDg0KhUNxaKBRSQ0NDkjsCYCdCDgBjFBUVye12x61lZWWpqKgoyR0BsBMhB4AxnE5nlycZz58/X04nb3lAKuE3HoBRCgoKNHLkyJixSy65RKNGjbKpIwB2IeQAMM6jjz4aPWrjdDq7PBkZgNkIOQCMk52drREjRkiSRowYoezsbHsbAmALQg4A47S1tWnnzp2SpJ07d7LiMZCiCDkAjMOKxwAkQg4Aw7DiMYBOhBwAxmDFYwAnI+QAMAYrHgM4GSEHgDEKCwuVlpYWt5aWlqbCwsIkdwTAToQcAMZoaWlROByOWwuHw2ppaUlyRwDsdNpDzqJFi+RwODRz5szoWHt7u6ZNm6aBAweqf//+uu222xQIBGKe5/P5NG7cOPXt21eDBw/Wgw8+qBMnTsTM2bBhg0aNGiWXy6Xvfve7Wrly5eneHQBnMK/X2+W9q9xut7xeb5I7AmCn0xpyGhsb9eyzz+qSSy6JGZ81a5beeustvfrqq3r33Xe1b98+/ehHP4rWw+Gwxo0bp2PHjqmurk6rVq3SypUrYy4D3bNnj8aNG6frr79eW7Zs0cyZM/WTn/xE77zzzuncJQBnsObm5m88J6e5uTnJHQGw02kLOUeOHFF5ebl+//vf6+yzz46OB4NBrVixQlVVVbrhhht0xRVX6IUXXlBdXZ3+8pe/SJL+67/+Szt37tSLL76oyy67TDfffLMeffRRPfXUUzp27Jgkafny5crPz9fjjz+uiy66SNOnT9ftt9+u3/zmN6drlwCc4fLy8pSfnx+3lp+fr7y8vCR3BMBOpy3kTJs2TePGjVNJSUnMeFNTk44fPx4zPnz4cOXl5am+vl6SVF9fr5EjR8rj8UTnlJaWKhQKaceOHdE5X992aWlpdBvxdHR0KBQKxTwAmCMSiWjv3r1xa3v37uUSciDFnJaQ89JLL+n9999XZWXlKTW/36+MjIxT7iXj8Xjk9/ujc04OOJ31zto3zQmFQjp69GjcviorK5WVlRV98P08YJba2toug0wkElFtbW2SOwJgp4SHnObmZs2YMUPV1dXKzMxM9OZ7ZM6cOQoGg9EH388DZhk/fnz07uNfl5aWpvHjxye5IwB2SnjIaWpq0v79+zVq1Cilp6crPT1d7777rp544gmlp6fL4/Ho2LFjp9wwLxAIKCcnR5KUk5NzytVWnT//rTlut1t9+vSJ25vL5ZLb7Y55ADCH0+nUsGHD4taGDRvWZQACYKaE/8bfeOON2rZtm7Zs2RJ9FBQUqLy8PPrfZ511ltatWxd9zu7du+Xz+VRcXCxJKi4u1rZt27R///7onLVr18rtdmvEiBHROSdvo3NO5zYApB6fz6c9e/bErX3yySfy+XxJ7giAndITvcEBAwbo4osvjhnr16+fBg4cGB2fOnWqKioqdM4558jtduv+++9XcXGxrrzySknS2LFjNWLECE2ePFlLliyR3+/XL3/5S02bNk0ul0uS9LOf/UxPPvmkHnroIf34xz/W+vXr9corr+jtt99O9C4B6CXy8vI0evRoNTY2nlIrLCzk6iogxdhy7PY3v/mNxo8fr9tuu03XXnutcnJy9B//8R/Relpammpra5WWlqbi4mLdeeeduuuuu2JuvJefn6+3335ba9eu1aWXXqrHH39czz//vEpLS+3YJQBnAIfDoYkTJ8atTZw4UQ6HI8kdAbCTw7Isy+4m7BIKhZSVlaVgMMj5OYABLMvST3/6U3300Uen1C644AI9++yzBB3AAN39/OYsPADG+PTTT+MGHEn66KOP9Omnnya3IQC2IuQAMMbnn3/eozoAsxByABjjyiuvVP/+/ePW+vfvH724AUBqIOQAMIbT6dSCBQvi1hYuXMg6OUCK4TcegFE6Fwz9usGDBye5EwB2I+QAMIZlWVq8eHHc2uLFi5XCF5MCKYmQA8AYe/fu1bZt2+LWtm3b1uUdygGYiZADAACMRMgBYAyv19vlycVOp1NerzfJHQGwEyEHgDE2bdqkSCQStxaJRLRp06YkdwTAToQcAMYoKirqcon3rKwsFRUVJbkjAHYi5AAwhtPp1Lx58+LW5s+fzzo5QIrhNx6AUQoKCjRy5MiYsUsuuUSjRo2yqSMAdiHkADDOo48+Gj1q43Q6tXDhQps7AmAHQg4A42RnZ6u8vFxOp1Pl5eXKzs62uyUANiDkAAAAIxFyABinra1N1dXVikQiqq6uVltbm90tAbABIQeAcebOnRtdLycSiXR5xRUAsxFyABhl8+bNp9y/auvWrdq8ebNNHQGwCyEHgDEikUiXV1ItXLiwy9WQAZiJkAPAGA0NDQqFQnFroVBIDQ0NSe4IgJ0IOQCMwW0dAJyMkAPAGNzWAcDJ+I0HYJSCggLl5OTEjOXk5HBbByAFEXIAGMfv93/jzwBSAyEHgFHuvPPObzUOwFyEHADGOHLkiFpaWuLWWlpadOTIkSR3BMBOhBwAxpgyZUqP6gDMQsgBYIwXXnihR3UAZiHkADBGv379lJGREbeWkZGhfv36JbkjAHYi5AAwhs/n07Fjx+LWjh07Jp/Pl+SOANiJkAPAGF6vV/37949b69+/v7xeb5I7AmAnQg4AY/h8vi6voDpy5AhHcoAUQ8gBAABGIuQAMEZeXt43fl2Vl5eX5I4A2ImQA8AYzc3N3/h1VXNzc5I7AmAnQg4AY3i9Xrnd7rg1t9vNicdAiiHkADBGc3OzQqFQ3FooFOJIDpBiCDkAjOH1etW3b9+4tb59+3IkB0gxhBwAxti7d6+++uqruLWvvvpKe/fuTXJHAOxEyAFgjM8//7xHdQBmIeQAMEZRUVGP6gDMQsgBYIyPPvqoR3UAZiHkADDGwoULe1QHYBZCDgBjPP/88z2qAzALIQeAMfr166ehQ4fGreXl5alfv35J7giAnQg5AIxhWZbOO++8uDWPxyPLspLcEQA7EXIAGMPn86mxsTFurbGxUT6fL8kdAbATIQeAMbxe7zfehZwVj4HUQsgBYAyfz/eNdyHnSA6QWgg5AADASIQcAMbwer1KS0uLW0tLS+PrKiDFEHIAGGPTpk0Kh8Nxa+FwWJs2bUpyRwDsRMgBYIzCwsIuj+Skp6ersLAwyR0BsBMhB4AxWlpaujySc+LECbW0tCS5IwB2IuQAMEZeXp4uuOCCuLULL7xQeXl5Se4IgJ0SHnIqKys1evRoDRgwQIMHD9aECRO0e/fumDnt7e2aNm2aBg4cqP79++u2225TIBCImePz+TRu3Dj17dtXgwcP1oMPPqgTJ07EzNmwYYNGjRoll8ul7373u1q5cmWidwdAL2JZlvbt2xe39tlnn7HiMZBiEh5y3n33XU2bNk1/+ctftHbtWh0/flxjx47Vl19+GZ0za9YsvfXWW3r11Vf17rvvat++ffrRj34UrYfDYY0bN07Hjh1TXV2dVq1apZUrV2revHnROXv27NG4ceN0/fXXa8uWLZo5c6Z+8pOf6J133kn0LgHoJRoaGr5xnZyGhoYkdwTATg7rNP9pc+DAAQ0ePFjvvvuurr32WgWDQZ177rmqqanR7bffLknatWuXLrroItXX1+vKK6/U6tWrNX78eO3bt08ej0eStHz5cj388MM6cOCAMjIy9PDDD+vtt9/W9u3bo681adIktbW1ac2aNd3qLRQKKSsrS8FgUG63O/E7DyCpIpGIbrjhhi7r69evl9PJt/RAb9fdz+/T/tseDAYlSeecc44kqampScePH1dJSUl0zvDhw5WXl6f6+npJUn19vUaOHBkNOJJUWlqqUCikHTt2ROecvI3OOZ3biKejo0OhUCjmAcAcXX1V1d06ALOc1pATiUQ0c+ZMXXXVVbr44oslSX6/XxkZGcrOzo6Z6/F45Pf7o3NODjid9c7aN80JhUI6evRo3H4qKyuVlZUVfbAwGGCWO++8s0d1AGY5rSFn2rRp2r59u1566aXT+TLdNmfOHAWDweijubnZ7pYAJNDixYt7VAdglvTTteHp06ertrZWGzdu1NChQ6PjOTk5OnbsmNra2mKO5gQCAeXk5ETnfH1l0s6rr06e8/UrsgKBgNxut/r06RO3J5fLJZfL1eN9A3Bm+luL/bEYIJBaEn4kx7IsTZ8+Xa+99prWr1+v/Pz8mPoVV1yhs846S+vWrYuO7d69Wz6fT8XFxZKk4uJibdu2Tfv374/OWbt2rdxut0aMGBGdc/I2Oud0bgNA6olEIt9476pIJJLkjgDYKeEhZ9q0aXrxxRdVU1OjAQMGyO/3y+/3R8+TycrK0tSpU1VRUaE//elPampq0pQpU1RcXKwrr7xSkjR27FiNGDFCkydP1gcffKB33nlHv/zlLzVt2rTokZif/exn+uSTT/TQQw9p165devrpp/XKK69o1qxZid4lAL1EbW3tN967qra2NskdAbBTwi8hdzgcccdfeOEF/dM//ZOkvy4G+MADD+gPf/iDOjo6VFpaqqeffjr6VZQk7d27V/fdd582bNigfv366e6779aiRYuUnv6/37Bt2LBBs2bN0s6dOzV06FDNnTs3+hrdwSXkgFnC4bBKSkriLvrncDj0xz/+scsjPQB6j+5+fp/2dXLOZIQcwCwnTpw4ZWmJk/3xj3+M+UMJQO90xqyTAwDJ8m//9m89qgMwCyEHgDHGjBnTozoAsxByABjjb51YzInHQGoh5AAwxoABA3pUB2AWQg4AY3zTScfdqQMwCyEHgDHOP/989e3bN26tb9++Ov/885PcEQA7EXIAGOP48eP66quv4ta++uorHT9+PMkdAbATIQeAMSorK3tUB2AWQg4AY5SVlfWoDsAshBwAxui8t93/tQ7ALIQcAMa46667elQHYBZCDgBjTJ8+vUd1AGYh5AAwxuWXX96jOgCzEHIAGOPzzz/vUR2AWQg5AIxhWVaP6gDMQsgBAABGIuQAMMaJEyd6VAdgFkIOAGO89dZbPaoDMAshB4Ax+vXr16M6ALMQcgAYg3VyAJyMkAPAGJMnT+5RHYBZCDkAjPHzn/+8R3UAZiHkADDGsWPHelQHYBZCDgBjnH/++T2qAzALIQeAMR566KEe1QGYhZADwBijRo3qUR2AWQg5AIxx7rnn9qgOwCyEHADGYMVjACcj5AAAACMRcgAAgJEIOQAAwEiEHADGGD58eI/qAMxCyAFgjF27dvWoDsAshBwAAGAkQg4AADASIQcAABiJkAMAAIxEyAEAAEYi5AAAACMRcgAAgJEIOQAAwEiEHAAAYCRCDgAAMBIhBwAAGImQAwAAjETIAQAARiLkAAAAI6Xb3QBgAsuy1N7ebncb6IajR4/a3ULKyszMlMPhsLsNpBBCDpAA7e3tuvnmm+1uA93A/yf7rF69Wn369LG7DaQQvq4CAABG4kgOkACZmZlavXq13W2kvO4cpeH/k30yMzPtbgEphpADJIDD4eAw/Blgw4YN+v73v/+NdQCpg6+rABilqyBDwAFSD0dyejGu6AG6j6uqgP+VKle6EXJ6Ma7oAbqP3xXgf6XKlW58XdWLWZZldwsAgF4oVT4/en3Ieeqpp/Sd73xHmZmZKioq0qZNm+xuKWk6OjrsbgEA0AulyudHrw45L7/8sioqKjR//ny9//77uvTSS1VaWqr9+/fb3RoAALBZrw45VVVVuueeezRlyhSNGDFCy5cvV9++ffWv//qvdreWFC6Xy+4WAAC9UKp8fvTaE4+PHTumpqYmzZkzJzrmdDpVUlKi+vr6uM/p6OiIOUQXCoVOe5+nU58+fVjY7AzR3t6uH/7wh3a3AZzRXnvtNRYEPEOkyv+HXhtyvvjiC4XDYXk8nphxj8ejXbt2xX1OZWWl/t//+3/JaC8pWIAOQG+SmZnJexaSqteGnP+LOXPmqKKiIvpzKBSS1+u1sSOYgts6nFksy4oetXW5XCmxHkhvkCpHD3Dm6LUhZ9CgQUpLS1MgEIgZDwQCysnJifscl8uVMt9DIrk4qnbm6du3r90tALBZrz3xOCMjQ1dccYXWrVsXHYtEIlq3bp2Ki4tt7AwAAJwJeu2RHEmqqKjQ3XffrYKCAhUWFuq3v/2tvvzyS02ZMsXu1gAAgM16dciZOHGiDhw4oHnz5snv9+uyyy7TmjVrTjkZGQAApB6HlSprO8cRCoWUlZWlYDAot9ttdzsAAKAbuvv53WvPyQEAAPgmhBwAAGAkQg4AADASIQcAABiJkAMAAIxEyAEAAEYi5AAAACMRcgAAgJEIOQAAwEi9+rYOPdW52HMoFLK5EwAA0F2dn9t/66YNKR1yDh8+LEnyer02dwIAAL6tw4cPKysrq8t6St+7KhKJaN++fRowYIAcDofd7QBIoFAoJK/Xq+bmZu5NBxjGsiwdPnxYubm5cjq7PvMmpUMOAHNxA14AnHgMAACMRMgBAABGIuQAMJLL5dL8+fPlcrnsbgWATTgnBwAAGIkjOQAAwEiEHAAAYCRCDgAAMBIhBwAAGImQA8A4Tz31lL7zne8oMzNTRUVF2rRpk90tAbABIQeAUV5++WVVVFRo/vz5ev/993XppZeqtLRU+/fvt7s1AEnGJeQAjFJUVKTRo0frySeflPTXe9R5vV7df//9mj17ts3dAUgmjuQAMMaxY8fU1NSkkpKS6JjT6VRJSYnq6+tt7AyAHQg5AIzxxRdfKBwOy+PxxIx7PB75/X6bugJgF0IOAAAwEiEHgDEGDRqktLQ0BQKBmPFAIKCcnBybugJgF0IOAGNkZGToiiuu0Lp166JjkUhE69atU3FxsY2dAbBDut0NAEAiVVRU6O6771ZBQYEKCwv129/+Vl9++aWmTJlid2sAkoyQA8AoEydO1IEDBzRv3jz5/X5ddtllWrNmzSknIwMwH+vkAAAAI3FODgAAMBIhBwAAGImQAwAAjETIAQAARiLkAAAAIxFyAACAkQg5AADASIQcAABgJEIOAAAwEiEHAAAYiZADAACMRMgBAABG+v/CD31hklVczQAAAABJRU5ErkJggg==\n",
1033 |       "text/plain": [
1034 |        "<Figure size 640x480 with 1 Axes>"
1035 |       ]
1036 |      },
1037 |      "metadata": {},
1038 |      "output_type": "display_data"
1039 |     }
1040 |    ],
1041 |    "source": [
1042 |     "sns.boxplot(df[\"price\"])"
1043 |    ]
1044 |   },
1045 |   {
1046 |    "cell_type": "code",
1047 |    "execution_count": 43,
1048 |    "id": "35d534e9",
1049 |    "metadata": {},
1050 |    "outputs": [
1051 |     {
1052 |      "data": {
1053 |       "text/plain": [
1054 |        "<AxesSubplot: >"
1055 |       ]
1056 |      },
1057 |      "execution_count": 43,
1058 |      "metadata": {},
1059 |      "output_type": "execute_result"
1060 |     },
1061 |     {
1062 |      "data": {
1063 |       "image/png": "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\n",
1064 |       "text/plain": [
1065 |        "<Figure size 640x480 with 1 Axes>"
1066 |       ]
1067 |      },
1068 |      "metadata": {},
1069 |      "output_type": "display_data"
1070 |     }
1071 |    ],
1072 |    "source": [
1073 |     "sns.boxplot(df[\"availability_365\"])"
1074 |    ]
1075 |   }
1076 |  ],
1077 |  "metadata": {
1078 |   "kernelspec": {
1079 |    "display_name": "Python 3 (ipykernel)",
1080 |    "language": "python",
1081 |    "name": "python3"
1082 |   },
1083 |   "language_info": {
1084 |    "codemirror_mode": {
1085 |     "name": "ipython",
1086 |     "version": 3
1087 |    },
1088 |    "file_extension": ".py",
1089 |    "mimetype": "text/x-python",
1090 |    "name": "python",
1091 |    "nbconvert_exporter": "python",
1092 |    "pygments_lexer": "ipython3",
1093 |    "version": "3.11.1"
1094 |   }
1095 |  },
1096 |  "nbformat": 4,
1097 |  "nbformat_minor": 5
1098 | }
1099 | 


--------------------------------------------------------------------------------
/3 Missing values.ipynb:
--------------------------------------------------------------------------------
   1 | {
   2 |  "cells": [
   3 |   {
   4 |    "cell_type": "markdown",
   5 |    "id": "bb76a3b8",
   6 |    "metadata": {},
   7 |    "source": [
   8 |     "In the field of data-related research, it is very important to handle missing data either by deleting or imputation(handling the missing values with some estimation)."
   9 |    ]
  10 |   },
  11 |   {
  12 |    "cell_type": "markdown",
  13 |    "id": "2dbb8dd1",
  14 |    "metadata": {},
  15 |    "source": [
  16 |     "Different Methods of Dealing With Missing Data\n",
  17 |     "1. Deleting the column with missing data\n",
  18 |     "2. Deleting the row with missing data\n",
  19 |     "3. Filling the Missing Values – Imputation\n",
  20 |     "   \n",
  21 |     "   (i) Numerical data - use mean\n",
  22 |     "   \n",
  23 |     "   (ii) categorical data \n",
  24 |     "       - use mode\n",
  25 |     "       - assign the NaN values their own category\n",
  26 |     "   \n",
  27 |     "   \n",
  28 |     "4. Advanced Imputation"
  29 |    ]
  30 |   },
  31 |   {
  32 |    "cell_type": "code",
  33 |    "execution_count": 2,
  34 |    "id": "e9dcf94b",
  35 |    "metadata": {},
  36 |    "outputs": [],
  37 |    "source": [
  38 |     "import pandas as pd"
  39 |    ]
  40 |   },
  41 |   {
  42 |    "cell_type": "code",
  43 |    "execution_count": 3,
  44 |    "id": "d2efcf45",
  45 |    "metadata": {},
  46 |    "outputs": [],
  47 |    "source": [
  48 |     "data = pd.read_csv(\"AB_NYC_2019.csv\")"
  49 |    ]
  50 |   },
  51 |   {
  52 |    "cell_type": "code",
  53 |    "execution_count": 178,
  54 |    "id": "63308fe4",
  55 |    "metadata": {},
  56 |    "outputs": [
  57 |     {
  58 |      "data": {
  59 |       "text/html": [
  60 |        "<div>\n",
  61 |        "<style scoped>\n",
  62 |        "    .dataframe tbody tr th:only-of-type {\n",
  63 |        "        vertical-align: middle;\n",
  64 |        "    }\n",
  65 |        "\n",
  66 |        "    .dataframe tbody tr th {\n",
  67 |        "        vertical-align: top;\n",
  68 |        "    }\n",
  69 |        "\n",
  70 |        "    .dataframe thead th {\n",
  71 |        "        text-align: right;\n",
  72 |        "    }\n",
  73 |        "</style>\n",
  74 |        "<table border=\"1\" class=\"dataframe\">\n",
  75 |        "  <thead>\n",
  76 |        "    <tr style=\"text-align: right;\">\n",
  77 |        "      <th></th>\n",
  78 |        "      <th>id</th>\n",
  79 |        "      <th>name</th>\n",
  80 |        "      <th>host_id</th>\n",
  81 |        "      <th>host_name</th>\n",
  82 |        "      <th>neighbourhood_group</th>\n",
  83 |        "      <th>neighbourhood</th>\n",
  84 |        "      <th>latitude</th>\n",
  85 |        "      <th>longitude</th>\n",
  86 |        "      <th>room_type</th>\n",
  87 |        "      <th>price</th>\n",
  88 |        "      <th>minimum_nights</th>\n",
  89 |        "      <th>number_of_reviews</th>\n",
  90 |        "      <th>last_review</th>\n",
  91 |        "      <th>reviews_per_month</th>\n",
  92 |        "      <th>calculated_host_listings_count</th>\n",
  93 |        "      <th>availability_365</th>\n",
  94 |        "    </tr>\n",
  95 |        "  </thead>\n",
  96 |        "  <tbody>\n",
  97 |        "    <tr>\n",
  98 |        "      <th>0</th>\n",
  99 |        "      <td>2539</td>\n",
 100 |        "      <td>Clean &amp; quiet apt home by the park</td>\n",
 101 |        "      <td>2787</td>\n",
 102 |        "      <td>John</td>\n",
 103 |        "      <td>Brooklyn</td>\n",
 104 |        "      <td>Kensington</td>\n",
 105 |        "      <td>40.64749</td>\n",
 106 |        "      <td>-73.97237</td>\n",
 107 |        "      <td>Private room</td>\n",
 108 |        "      <td>149</td>\n",
 109 |        "      <td>1</td>\n",
 110 |        "      <td>9</td>\n",
 111 |        "      <td>2018-10-19</td>\n",
 112 |        "      <td>0.21</td>\n",
 113 |        "      <td>6</td>\n",
 114 |        "      <td>365</td>\n",
 115 |        "    </tr>\n",
 116 |        "    <tr>\n",
 117 |        "      <th>1</th>\n",
 118 |        "      <td>2595</td>\n",
 119 |        "      <td>Skylit Midtown Castle</td>\n",
 120 |        "      <td>2845</td>\n",
 121 |        "      <td>Jennifer</td>\n",
 122 |        "      <td>Manhattan</td>\n",
 123 |        "      <td>Midtown</td>\n",
 124 |        "      <td>40.75362</td>\n",
 125 |        "      <td>-73.98377</td>\n",
 126 |        "      <td>Entire home/apt</td>\n",
 127 |        "      <td>225</td>\n",
 128 |        "      <td>1</td>\n",
 129 |        "      <td>45</td>\n",
 130 |        "      <td>2019-05-21</td>\n",
 131 |        "      <td>0.38</td>\n",
 132 |        "      <td>2</td>\n",
 133 |        "      <td>355</td>\n",
 134 |        "    </tr>\n",
 135 |        "    <tr>\n",
 136 |        "      <th>2</th>\n",
 137 |        "      <td>3647</td>\n",
 138 |        "      <td>THE VILLAGE OF HARLEM....NEW YORK !</td>\n",
 139 |        "      <td>4632</td>\n",
 140 |        "      <td>Elisabeth</td>\n",
 141 |        "      <td>Manhattan</td>\n",
 142 |        "      <td>Harlem</td>\n",
 143 |        "      <td>40.80902</td>\n",
 144 |        "      <td>-73.94190</td>\n",
 145 |        "      <td>Private room</td>\n",
 146 |        "      <td>150</td>\n",
 147 |        "      <td>3</td>\n",
 148 |        "      <td>0</td>\n",
 149 |        "      <td>NaN</td>\n",
 150 |        "      <td>NaN</td>\n",
 151 |        "      <td>1</td>\n",
 152 |        "      <td>365</td>\n",
 153 |        "    </tr>\n",
 154 |        "    <tr>\n",
 155 |        "      <th>3</th>\n",
 156 |        "      <td>3831</td>\n",
 157 |        "      <td>Cozy Entire Floor of Brownstone</td>\n",
 158 |        "      <td>4869</td>\n",
 159 |        "      <td>LisaRoxanne</td>\n",
 160 |        "      <td>Brooklyn</td>\n",
 161 |        "      <td>Clinton Hill</td>\n",
 162 |        "      <td>40.68514</td>\n",
 163 |        "      <td>-73.95976</td>\n",
 164 |        "      <td>Entire home/apt</td>\n",
 165 |        "      <td>89</td>\n",
 166 |        "      <td>1</td>\n",
 167 |        "      <td>270</td>\n",
 168 |        "      <td>2019-07-05</td>\n",
 169 |        "      <td>4.64</td>\n",
 170 |        "      <td>1</td>\n",
 171 |        "      <td>194</td>\n",
 172 |        "    </tr>\n",
 173 |        "    <tr>\n",
 174 |        "      <th>4</th>\n",
 175 |        "      <td>5022</td>\n",
 176 |        "      <td>Entire Apt: Spacious Studio/Loft by central park</td>\n",
 177 |        "      <td>7192</td>\n",
 178 |        "      <td>Laura</td>\n",
 179 |        "      <td>Manhattan</td>\n",
 180 |        "      <td>East Harlem</td>\n",
 181 |        "      <td>40.79851</td>\n",
 182 |        "      <td>-73.94399</td>\n",
 183 |        "      <td>Entire home/apt</td>\n",
 184 |        "      <td>80</td>\n",
 185 |        "      <td>10</td>\n",
 186 |        "      <td>9</td>\n",
 187 |        "      <td>2018-11-19</td>\n",
 188 |        "      <td>0.10</td>\n",
 189 |        "      <td>1</td>\n",
 190 |        "      <td>0</td>\n",
 191 |        "    </tr>\n",
 192 |        "  </tbody>\n",
 193 |        "</table>\n",
 194 |        "</div>"
 195 |       ],
 196 |       "text/plain": [
 197 |        "     id                                              name  host_id  \\\n",
 198 |        "0  2539                Clean & quiet apt home by the park     2787   \n",
 199 |        "1  2595                             Skylit Midtown Castle     2845   \n",
 200 |        "2  3647               THE VILLAGE OF HARLEM....NEW YORK !     4632   \n",
 201 |        "3  3831                   Cozy Entire Floor of Brownstone     4869   \n",
 202 |        "4  5022  Entire Apt: Spacious Studio/Loft by central park     7192   \n",
 203 |        "\n",
 204 |        "     host_name neighbourhood_group neighbourhood  latitude  longitude  \\\n",
 205 |        "0         John            Brooklyn    Kensington  40.64749  -73.97237   \n",
 206 |        "1     Jennifer           Manhattan       Midtown  40.75362  -73.98377   \n",
 207 |        "2    Elisabeth           Manhattan        Harlem  40.80902  -73.94190   \n",
 208 |        "3  LisaRoxanne            Brooklyn  Clinton Hill  40.68514  -73.95976   \n",
 209 |        "4        Laura           Manhattan   East Harlem  40.79851  -73.94399   \n",
 210 |        "\n",
 211 |        "         room_type  price  minimum_nights  number_of_reviews last_review  \\\n",
 212 |        "0     Private room    149               1                  9  2018-10-19   \n",
 213 |        "1  Entire home/apt    225               1                 45  2019-05-21   \n",
 214 |        "2     Private room    150               3                  0         NaN   \n",
 215 |        "3  Entire home/apt     89               1                270  2019-07-05   \n",
 216 |        "4  Entire home/apt     80              10                  9  2018-11-19   \n",
 217 |        "\n",
 218 |        "   reviews_per_month  calculated_host_listings_count  availability_365  \n",
 219 |        "0               0.21                               6               365  \n",
 220 |        "1               0.38                               2               355  \n",
 221 |        "2                NaN                               1               365  \n",
 222 |        "3               4.64                               1               194  \n",
 223 |        "4               0.10                               1                 0  "
 224 |       ]
 225 |      },
 226 |      "execution_count": 178,
 227 |      "metadata": {},
 228 |      "output_type": "execute_result"
 229 |     }
 230 |    ],
 231 |    "source": [
 232 |     "data.head()"
 233 |    ]
 234 |   },
 235 |   {
 236 |    "cell_type": "code",
 237 |    "execution_count": 5,
 238 |    "id": "312e5057",
 239 |    "metadata": {},
 240 |    "outputs": [
 241 |     {
 242 |      "data": {
 243 |       "text/plain": [
 244 |        "(48915, 16)"
 245 |       ]
 246 |      },
 247 |      "execution_count": 5,
 248 |      "metadata": {},
 249 |      "output_type": "execute_result"
 250 |     }
 251 |    ],
 252 |    "source": [
 253 |     "data.shape"
 254 |    ]
 255 |   },
 256 |   {
 257 |    "cell_type": "code",
 258 |    "execution_count": 4,
 259 |    "id": "899d0abc",
 260 |    "metadata": {
 261 |     "scrolled": true
 262 |    },
 263 |    "outputs": [
 264 |     {
 265 |      "data": {
 266 |       "text/plain": [
 267 |        "id                                    0\n",
 268 |        "name                                 16\n",
 269 |        "host_id                               0\n",
 270 |        "host_name                            21\n",
 271 |        "neighbourhood_group                   0\n",
 272 |        "neighbourhood                         0\n",
 273 |        "latitude                              0\n",
 274 |        "longitude                             0\n",
 275 |        "room_type                             0\n",
 276 |        "price                                 0\n",
 277 |        "minimum_nights                        0\n",
 278 |        "number_of_reviews                     0\n",
 279 |        "last_review                       10052\n",
 280 |        "reviews_per_month                 10052\n",
 281 |        "calculated_host_listings_count        0\n",
 282 |        "availability_365                      0\n",
 283 |        "dtype: int64"
 284 |       ]
 285 |      },
 286 |      "execution_count": 4,
 287 |      "metadata": {},
 288 |      "output_type": "execute_result"
 289 |     }
 290 |    ],
 291 |    "source": [
 292 |     "data.isna().sum()"
 293 |    ]
 294 |   },
 295 |   {
 296 |    "cell_type": "markdown",
 297 |    "id": "835ab45b",
 298 |    "metadata": {},
 299 |    "source": [
 300 |     "### Removing column"
 301 |    ]
 302 |   },
 303 |   {
 304 |    "cell_type": "code",
 305 |    "execution_count": 6,
 306 |    "id": "6ff99b23",
 307 |    "metadata": {},
 308 |    "outputs": [],
 309 |    "source": [
 310 |     "df1 = data.drop(\"last_review\",axis =1)"
 311 |    ]
 312 |   },
 313 |   {
 314 |    "cell_type": "code",
 315 |    "execution_count": 7,
 316 |    "id": "c19a92e7",
 317 |    "metadata": {},
 318 |    "outputs": [
 319 |     {
 320 |      "data": {
 321 |       "text/plain": [
 322 |        "id                                    0\n",
 323 |        "name                                 16\n",
 324 |        "host_id                               0\n",
 325 |        "host_name                            21\n",
 326 |        "neighbourhood_group                   0\n",
 327 |        "neighbourhood                         0\n",
 328 |        "latitude                              0\n",
 329 |        "longitude                             0\n",
 330 |        "room_type                             0\n",
 331 |        "price                                 0\n",
 332 |        "minimum_nights                        0\n",
 333 |        "number_of_reviews                     0\n",
 334 |        "reviews_per_month                 10052\n",
 335 |        "calculated_host_listings_count        0\n",
 336 |        "availability_365                      0\n",
 337 |        "dtype: int64"
 338 |       ]
 339 |      },
 340 |      "execution_count": 7,
 341 |      "metadata": {},
 342 |      "output_type": "execute_result"
 343 |     }
 344 |    ],
 345 |    "source": [
 346 |     "df1.isna().sum()"
 347 |    ]
 348 |   },
 349 |   {
 350 |    "cell_type": "code",
 351 |    "execution_count": 184,
 352 |    "id": "7678f06e",
 353 |    "metadata": {},
 354 |    "outputs": [
 355 |     {
 356 |      "data": {
 357 |       "text/plain": [
 358 |        "(48895, 15)"
 359 |       ]
 360 |      },
 361 |      "execution_count": 184,
 362 |      "metadata": {},
 363 |      "output_type": "execute_result"
 364 |     }
 365 |    ],
 366 |    "source": [
 367 |     "df1.shape"
 368 |    ]
 369 |   },
 370 |   {
 371 |    "cell_type": "markdown",
 372 |    "id": "e872761c",
 373 |    "metadata": {},
 374 |    "source": [
 375 |     "### Removing rows"
 376 |    ]
 377 |   },
 378 |   {
 379 |    "cell_type": "code",
 380 |    "execution_count": 185,
 381 |    "id": "c73417f6",
 382 |    "metadata": {},
 383 |    "outputs": [],
 384 |    "source": [
 385 |     "df2 = data.dropna()"
 386 |    ]
 387 |   },
 388 |   {
 389 |    "cell_type": "code",
 390 |    "execution_count": 186,
 391 |    "id": "6fae1f74",
 392 |    "metadata": {},
 393 |    "outputs": [
 394 |     {
 395 |      "data": {
 396 |       "text/plain": [
 397 |        "(38821, 16)"
 398 |       ]
 399 |      },
 400 |      "execution_count": 186,
 401 |      "metadata": {},
 402 |      "output_type": "execute_result"
 403 |     }
 404 |    ],
 405 |    "source": [
 406 |     "df2.shape"
 407 |    ]
 408 |   },
 409 |   {
 410 |    "cell_type": "code",
 411 |    "execution_count": 187,
 412 |    "id": "1c655dc5",
 413 |    "metadata": {},
 414 |    "outputs": [
 415 |     {
 416 |      "data": {
 417 |       "text/plain": [
 418 |        "id                                0\n",
 419 |        "name                              0\n",
 420 |        "host_id                           0\n",
 421 |        "host_name                         0\n",
 422 |        "neighbourhood_group               0\n",
 423 |        "neighbourhood                     0\n",
 424 |        "latitude                          0\n",
 425 |        "longitude                         0\n",
 426 |        "room_type                         0\n",
 427 |        "price                             0\n",
 428 |        "minimum_nights                    0\n",
 429 |        "number_of_reviews                 0\n",
 430 |        "last_review                       0\n",
 431 |        "reviews_per_month                 0\n",
 432 |        "calculated_host_listings_count    0\n",
 433 |        "availability_365                  0\n",
 434 |        "dtype: int64"
 435 |       ]
 436 |      },
 437 |      "execution_count": 187,
 438 |      "metadata": {},
 439 |      "output_type": "execute_result"
 440 |     }
 441 |    ],
 442 |    "source": [
 443 |     "df2.isna().sum()"
 444 |    ]
 445 |   },
 446 |   {
 447 |    "cell_type": "markdown",
 448 |    "id": "25afd242",
 449 |    "metadata": {},
 450 |    "source": [
 451 |     "### Filling the missing values - Imputation"
 452 |    ]
 453 |   },
 454 |   {
 455 |    "cell_type": "code",
 456 |    "execution_count": 188,
 457 |    "id": "427c815c",
 458 |    "metadata": {},
 459 |    "outputs": [],
 460 |    "source": [
 461 |     "df3 = pd.read_csv(\"AB_NYC_2019.csv\")"
 462 |    ]
 463 |   },
 464 |   {
 465 |    "cell_type": "code",
 466 |    "execution_count": 189,
 467 |    "id": "9a34dc54",
 468 |    "metadata": {},
 469 |    "outputs": [
 470 |     {
 471 |      "data": {
 472 |       "text/plain": [
 473 |        "(48895, 16)"
 474 |       ]
 475 |      },
 476 |      "execution_count": 189,
 477 |      "metadata": {},
 478 |      "output_type": "execute_result"
 479 |     }
 480 |    ],
 481 |    "source": [
 482 |     "df3.shape"
 483 |    ]
 484 |   },
 485 |   {
 486 |    "cell_type": "code",
 487 |    "execution_count": 190,
 488 |    "id": "a32e8937",
 489 |    "metadata": {},
 490 |    "outputs": [
 491 |     {
 492 |      "data": {
 493 |       "text/html": [
 494 |        "<div>\n",
 495 |        "<style scoped>\n",
 496 |        "    .dataframe tbody tr th:only-of-type {\n",
 497 |        "        vertical-align: middle;\n",
 498 |        "    }\n",
 499 |        "\n",
 500 |        "    .dataframe tbody tr th {\n",
 501 |        "        vertical-align: top;\n",
 502 |        "    }\n",
 503 |        "\n",
 504 |        "    .dataframe thead th {\n",
 505 |        "        text-align: right;\n",
 506 |        "    }\n",
 507 |        "</style>\n",
 508 |        "<table border=\"1\" class=\"dataframe\">\n",
 509 |        "  <thead>\n",
 510 |        "    <tr style=\"text-align: right;\">\n",
 511 |        "      <th></th>\n",
 512 |        "      <th>id</th>\n",
 513 |        "      <th>name</th>\n",
 514 |        "      <th>host_id</th>\n",
 515 |        "      <th>host_name</th>\n",
 516 |        "      <th>neighbourhood_group</th>\n",
 517 |        "      <th>neighbourhood</th>\n",
 518 |        "      <th>latitude</th>\n",
 519 |        "      <th>longitude</th>\n",
 520 |        "      <th>room_type</th>\n",
 521 |        "      <th>price</th>\n",
 522 |        "      <th>minimum_nights</th>\n",
 523 |        "      <th>number_of_reviews</th>\n",
 524 |        "      <th>last_review</th>\n",
 525 |        "      <th>reviews_per_month</th>\n",
 526 |        "      <th>calculated_host_listings_count</th>\n",
 527 |        "      <th>availability_365</th>\n",
 528 |        "    </tr>\n",
 529 |        "  </thead>\n",
 530 |        "  <tbody>\n",
 531 |        "    <tr>\n",
 532 |        "      <th>0</th>\n",
 533 |        "      <td>2539</td>\n",
 534 |        "      <td>Clean &amp; quiet apt home by the park</td>\n",
 535 |        "      <td>2787</td>\n",
 536 |        "      <td>John</td>\n",
 537 |        "      <td>Brooklyn</td>\n",
 538 |        "      <td>Kensington</td>\n",
 539 |        "      <td>40.64749</td>\n",
 540 |        "      <td>-73.97237</td>\n",
 541 |        "      <td>Private room</td>\n",
 542 |        "      <td>149</td>\n",
 543 |        "      <td>1</td>\n",
 544 |        "      <td>9</td>\n",
 545 |        "      <td>2018-10-19</td>\n",
 546 |        "      <td>0.21</td>\n",
 547 |        "      <td>6</td>\n",
 548 |        "      <td>365</td>\n",
 549 |        "    </tr>\n",
 550 |        "    <tr>\n",
 551 |        "      <th>1</th>\n",
 552 |        "      <td>2595</td>\n",
 553 |        "      <td>Skylit Midtown Castle</td>\n",
 554 |        "      <td>2845</td>\n",
 555 |        "      <td>Jennifer</td>\n",
 556 |        "      <td>Manhattan</td>\n",
 557 |        "      <td>Midtown</td>\n",
 558 |        "      <td>40.75362</td>\n",
 559 |        "      <td>-73.98377</td>\n",
 560 |        "      <td>Entire home/apt</td>\n",
 561 |        "      <td>225</td>\n",
 562 |        "      <td>1</td>\n",
 563 |        "      <td>45</td>\n",
 564 |        "      <td>2019-05-21</td>\n",
 565 |        "      <td>0.38</td>\n",
 566 |        "      <td>2</td>\n",
 567 |        "      <td>355</td>\n",
 568 |        "    </tr>\n",
 569 |        "    <tr>\n",
 570 |        "      <th>2</th>\n",
 571 |        "      <td>3647</td>\n",
 572 |        "      <td>THE VILLAGE OF HARLEM....NEW YORK !</td>\n",
 573 |        "      <td>4632</td>\n",
 574 |        "      <td>Elisabeth</td>\n",
 575 |        "      <td>Manhattan</td>\n",
 576 |        "      <td>Harlem</td>\n",
 577 |        "      <td>40.80902</td>\n",
 578 |        "      <td>-73.94190</td>\n",
 579 |        "      <td>Private room</td>\n",
 580 |        "      <td>150</td>\n",
 581 |        "      <td>3</td>\n",
 582 |        "      <td>0</td>\n",
 583 |        "      <td>NaN</td>\n",
 584 |        "      <td>NaN</td>\n",
 585 |        "      <td>1</td>\n",
 586 |        "      <td>365</td>\n",
 587 |        "    </tr>\n",
 588 |        "    <tr>\n",
 589 |        "      <th>3</th>\n",
 590 |        "      <td>3831</td>\n",
 591 |        "      <td>Cozy Entire Floor of Brownstone</td>\n",
 592 |        "      <td>4869</td>\n",
 593 |        "      <td>LisaRoxanne</td>\n",
 594 |        "      <td>Brooklyn</td>\n",
 595 |        "      <td>Clinton Hill</td>\n",
 596 |        "      <td>40.68514</td>\n",
 597 |        "      <td>-73.95976</td>\n",
 598 |        "      <td>Entire home/apt</td>\n",
 599 |        "      <td>89</td>\n",
 600 |        "      <td>1</td>\n",
 601 |        "      <td>270</td>\n",
 602 |        "      <td>2019-07-05</td>\n",
 603 |        "      <td>4.64</td>\n",
 604 |        "      <td>1</td>\n",
 605 |        "      <td>194</td>\n",
 606 |        "    </tr>\n",
 607 |        "    <tr>\n",
 608 |        "      <th>4</th>\n",
 609 |        "      <td>5022</td>\n",
 610 |        "      <td>Entire Apt: Spacious Studio/Loft by central park</td>\n",
 611 |        "      <td>7192</td>\n",
 612 |        "      <td>Laura</td>\n",
 613 |        "      <td>Manhattan</td>\n",
 614 |        "      <td>East Harlem</td>\n",
 615 |        "      <td>40.79851</td>\n",
 616 |        "      <td>-73.94399</td>\n",
 617 |        "      <td>Entire home/apt</td>\n",
 618 |        "      <td>80</td>\n",
 619 |        "      <td>10</td>\n",
 620 |        "      <td>9</td>\n",
 621 |        "      <td>2018-11-19</td>\n",
 622 |        "      <td>0.10</td>\n",
 623 |        "      <td>1</td>\n",
 624 |        "      <td>0</td>\n",
 625 |        "    </tr>\n",
 626 |        "  </tbody>\n",
 627 |        "</table>\n",
 628 |        "</div>"
 629 |       ],
 630 |       "text/plain": [
 631 |        "     id                                              name  host_id  \\\n",
 632 |        "0  2539                Clean & quiet apt home by the park     2787   \n",
 633 |        "1  2595                             Skylit Midtown Castle     2845   \n",
 634 |        "2  3647               THE VILLAGE OF HARLEM....NEW YORK !     4632   \n",
 635 |        "3  3831                   Cozy Entire Floor of Brownstone     4869   \n",
 636 |        "4  5022  Entire Apt: Spacious Studio/Loft by central park     7192   \n",
 637 |        "\n",
 638 |        "     host_name neighbourhood_group neighbourhood  latitude  longitude  \\\n",
 639 |        "0         John            Brooklyn    Kensington  40.64749  -73.97237   \n",
 640 |        "1     Jennifer           Manhattan       Midtown  40.75362  -73.98377   \n",
 641 |        "2    Elisabeth           Manhattan        Harlem  40.80902  -73.94190   \n",
 642 |        "3  LisaRoxanne            Brooklyn  Clinton Hill  40.68514  -73.95976   \n",
 643 |        "4        Laura           Manhattan   East Harlem  40.79851  -73.94399   \n",
 644 |        "\n",
 645 |        "         room_type  price  minimum_nights  number_of_reviews last_review  \\\n",
 646 |        "0     Private room    149               1                  9  2018-10-19   \n",
 647 |        "1  Entire home/apt    225               1                 45  2019-05-21   \n",
 648 |        "2     Private room    150               3                  0         NaN   \n",
 649 |        "3  Entire home/apt     89               1                270  2019-07-05   \n",
 650 |        "4  Entire home/apt     80              10                  9  2018-11-19   \n",
 651 |        "\n",
 652 |        "   reviews_per_month  calculated_host_listings_count  availability_365  \n",
 653 |        "0               0.21                               6               365  \n",
 654 |        "1               0.38                               2               355  \n",
 655 |        "2                NaN                               1               365  \n",
 656 |        "3               4.64                               1               194  \n",
 657 |        "4               0.10                               1                 0  "
 658 |       ]
 659 |      },
 660 |      "execution_count": 190,
 661 |      "metadata": {},
 662 |      "output_type": "execute_result"
 663 |     }
 664 |    ],
 665 |    "source": [
 666 |     "df3.head()"
 667 |    ]
 668 |   },
 669 |   {
 670 |    "cell_type": "code",
 671 |    "execution_count": 191,
 672 |    "id": "413c8f0f",
 673 |    "metadata": {},
 674 |    "outputs": [
 675 |     {
 676 |      "data": {
 677 |       "text/plain": [
 678 |        "id                                    0\n",
 679 |        "name                                 16\n",
 680 |        "host_id                               0\n",
 681 |        "host_name                            21\n",
 682 |        "neighbourhood_group                   0\n",
 683 |        "neighbourhood                         0\n",
 684 |        "latitude                              0\n",
 685 |        "longitude                             0\n",
 686 |        "room_type                             0\n",
 687 |        "price                                 0\n",
 688 |        "minimum_nights                        0\n",
 689 |        "number_of_reviews                     0\n",
 690 |        "last_review                       10052\n",
 691 |        "reviews_per_month                 10052\n",
 692 |        "calculated_host_listings_count        0\n",
 693 |        "availability_365                      0\n",
 694 |        "dtype: int64"
 695 |       ]
 696 |      },
 697 |      "execution_count": 191,
 698 |      "metadata": {},
 699 |      "output_type": "execute_result"
 700 |     }
 701 |    ],
 702 |    "source": [
 703 |     "df3.isna().sum()"
 704 |    ]
 705 |   },
 706 |   {
 707 |    "cell_type": "markdown",
 708 |    "id": "c509b61c",
 709 |    "metadata": {},
 710 |    "source": [
 711 |     "#### Numeric data (Use Mean)"
 712 |    ]
 713 |   },
 714 |   {
 715 |    "cell_type": "code",
 716 |    "execution_count": 192,
 717 |    "id": "3c56ea41",
 718 |    "metadata": {},
 719 |    "outputs": [],
 720 |    "source": [
 721 |     "mean_value = df3['reviews_per_month'].mean()\n",
 722 |     "df3['reviews_per_month'].fillna(mean_value, inplace=True)"
 723 |    ]
 724 |   },
 725 |   {
 726 |    "cell_type": "code",
 727 |    "execution_count": 193,
 728 |    "id": "a391aa62",
 729 |    "metadata": {},
 730 |    "outputs": [
 731 |     {
 732 |      "data": {
 733 |       "text/html": [
 734 |        "<div>\n",
 735 |        "<style scoped>\n",
 736 |        "    .dataframe tbody tr th:only-of-type {\n",
 737 |        "        vertical-align: middle;\n",
 738 |        "    }\n",
 739 |        "\n",
 740 |        "    .dataframe tbody tr th {\n",
 741 |        "        vertical-align: top;\n",
 742 |        "    }\n",
 743 |        "\n",
 744 |        "    .dataframe thead th {\n",
 745 |        "        text-align: right;\n",
 746 |        "    }\n",
 747 |        "</style>\n",
 748 |        "<table border=\"1\" class=\"dataframe\">\n",
 749 |        "  <thead>\n",
 750 |        "    <tr style=\"text-align: right;\">\n",
 751 |        "      <th></th>\n",
 752 |        "      <th>id</th>\n",
 753 |        "      <th>name</th>\n",
 754 |        "      <th>host_id</th>\n",
 755 |        "      <th>host_name</th>\n",
 756 |        "      <th>neighbourhood_group</th>\n",
 757 |        "      <th>neighbourhood</th>\n",
 758 |        "      <th>latitude</th>\n",
 759 |        "      <th>longitude</th>\n",
 760 |        "      <th>room_type</th>\n",
 761 |        "      <th>price</th>\n",
 762 |        "      <th>minimum_nights</th>\n",
 763 |        "      <th>number_of_reviews</th>\n",
 764 |        "      <th>last_review</th>\n",
 765 |        "      <th>reviews_per_month</th>\n",
 766 |        "      <th>calculated_host_listings_count</th>\n",
 767 |        "      <th>availability_365</th>\n",
 768 |        "    </tr>\n",
 769 |        "  </thead>\n",
 770 |        "  <tbody>\n",
 771 |        "    <tr>\n",
 772 |        "      <th>0</th>\n",
 773 |        "      <td>2539</td>\n",
 774 |        "      <td>Clean &amp; quiet apt home by the park</td>\n",
 775 |        "      <td>2787</td>\n",
 776 |        "      <td>John</td>\n",
 777 |        "      <td>Brooklyn</td>\n",
 778 |        "      <td>Kensington</td>\n",
 779 |        "      <td>40.64749</td>\n",
 780 |        "      <td>-73.97237</td>\n",
 781 |        "      <td>Private room</td>\n",
 782 |        "      <td>149</td>\n",
 783 |        "      <td>1</td>\n",
 784 |        "      <td>9</td>\n",
 785 |        "      <td>2018-10-19</td>\n",
 786 |        "      <td>0.210000</td>\n",
 787 |        "      <td>6</td>\n",
 788 |        "      <td>365</td>\n",
 789 |        "    </tr>\n",
 790 |        "    <tr>\n",
 791 |        "      <th>1</th>\n",
 792 |        "      <td>2595</td>\n",
 793 |        "      <td>Skylit Midtown Castle</td>\n",
 794 |        "      <td>2845</td>\n",
 795 |        "      <td>Jennifer</td>\n",
 796 |        "      <td>Manhattan</td>\n",
 797 |        "      <td>Midtown</td>\n",
 798 |        "      <td>40.75362</td>\n",
 799 |        "      <td>-73.98377</td>\n",
 800 |        "      <td>Entire home/apt</td>\n",
 801 |        "      <td>225</td>\n",
 802 |        "      <td>1</td>\n",
 803 |        "      <td>45</td>\n",
 804 |        "      <td>2019-05-21</td>\n",
 805 |        "      <td>0.380000</td>\n",
 806 |        "      <td>2</td>\n",
 807 |        "      <td>355</td>\n",
 808 |        "    </tr>\n",
 809 |        "    <tr>\n",
 810 |        "      <th>2</th>\n",
 811 |        "      <td>3647</td>\n",
 812 |        "      <td>THE VILLAGE OF HARLEM....NEW YORK !</td>\n",
 813 |        "      <td>4632</td>\n",
 814 |        "      <td>Elisabeth</td>\n",
 815 |        "      <td>Manhattan</td>\n",
 816 |        "      <td>Harlem</td>\n",
 817 |        "      <td>40.80902</td>\n",
 818 |        "      <td>-73.94190</td>\n",
 819 |        "      <td>Private room</td>\n",
 820 |        "      <td>150</td>\n",
 821 |        "      <td>3</td>\n",
 822 |        "      <td>0</td>\n",
 823 |        "      <td>NaN</td>\n",
 824 |        "      <td>1.373221</td>\n",
 825 |        "      <td>1</td>\n",
 826 |        "      <td>365</td>\n",
 827 |        "    </tr>\n",
 828 |        "    <tr>\n",
 829 |        "      <th>3</th>\n",
 830 |        "      <td>3831</td>\n",
 831 |        "      <td>Cozy Entire Floor of Brownstone</td>\n",
 832 |        "      <td>4869</td>\n",
 833 |        "      <td>LisaRoxanne</td>\n",
 834 |        "      <td>Brooklyn</td>\n",
 835 |        "      <td>Clinton Hill</td>\n",
 836 |        "      <td>40.68514</td>\n",
 837 |        "      <td>-73.95976</td>\n",
 838 |        "      <td>Entire home/apt</td>\n",
 839 |        "      <td>89</td>\n",
 840 |        "      <td>1</td>\n",
 841 |        "      <td>270</td>\n",
 842 |        "      <td>2019-07-05</td>\n",
 843 |        "      <td>4.640000</td>\n",
 844 |        "      <td>1</td>\n",
 845 |        "      <td>194</td>\n",
 846 |        "    </tr>\n",
 847 |        "    <tr>\n",
 848 |        "      <th>4</th>\n",
 849 |        "      <td>5022</td>\n",
 850 |        "      <td>Entire Apt: Spacious Studio/Loft by central park</td>\n",
 851 |        "      <td>7192</td>\n",
 852 |        "      <td>Laura</td>\n",
 853 |        "      <td>Manhattan</td>\n",
 854 |        "      <td>East Harlem</td>\n",
 855 |        "      <td>40.79851</td>\n",
 856 |        "      <td>-73.94399</td>\n",
 857 |        "      <td>Entire home/apt</td>\n",
 858 |        "      <td>80</td>\n",
 859 |        "      <td>10</td>\n",
 860 |        "      <td>9</td>\n",
 861 |        "      <td>2018-11-19</td>\n",
 862 |        "      <td>0.100000</td>\n",
 863 |        "      <td>1</td>\n",
 864 |        "      <td>0</td>\n",
 865 |        "    </tr>\n",
 866 |        "  </tbody>\n",
 867 |        "</table>\n",
 868 |        "</div>"
 869 |       ],
 870 |       "text/plain": [
 871 |        "     id                                              name  host_id  \\\n",
 872 |        "0  2539                Clean & quiet apt home by the park     2787   \n",
 873 |        "1  2595                             Skylit Midtown Castle     2845   \n",
 874 |        "2  3647               THE VILLAGE OF HARLEM....NEW YORK !     4632   \n",
 875 |        "3  3831                   Cozy Entire Floor of Brownstone     4869   \n",
 876 |        "4  5022  Entire Apt: Spacious Studio/Loft by central park     7192   \n",
 877 |        "\n",
 878 |        "     host_name neighbourhood_group neighbourhood  latitude  longitude  \\\n",
 879 |        "0         John            Brooklyn    Kensington  40.64749  -73.97237   \n",
 880 |        "1     Jennifer           Manhattan       Midtown  40.75362  -73.98377   \n",
 881 |        "2    Elisabeth           Manhattan        Harlem  40.80902  -73.94190   \n",
 882 |        "3  LisaRoxanne            Brooklyn  Clinton Hill  40.68514  -73.95976   \n",
 883 |        "4        Laura           Manhattan   East Harlem  40.79851  -73.94399   \n",
 884 |        "\n",
 885 |        "         room_type  price  minimum_nights  number_of_reviews last_review  \\\n",
 886 |        "0     Private room    149               1                  9  2018-10-19   \n",
 887 |        "1  Entire home/apt    225               1                 45  2019-05-21   \n",
 888 |        "2     Private room    150               3                  0         NaN   \n",
 889 |        "3  Entire home/apt     89               1                270  2019-07-05   \n",
 890 |        "4  Entire home/apt     80              10                  9  2018-11-19   \n",
 891 |        "\n",
 892 |        "   reviews_per_month  calculated_host_listings_count  availability_365  \n",
 893 |        "0           0.210000                               6               365  \n",
 894 |        "1           0.380000                               2               355  \n",
 895 |        "2           1.373221                               1               365  \n",
 896 |        "3           4.640000                               1               194  \n",
 897 |        "4           0.100000                               1                 0  "
 898 |       ]
 899 |      },
 900 |      "execution_count": 193,
 901 |      "metadata": {},
 902 |      "output_type": "execute_result"
 903 |     }
 904 |    ],
 905 |    "source": [
 906 |     "df3.head()"
 907 |    ]
 908 |   },
 909 |   {
 910 |    "cell_type": "code",
 911 |    "execution_count": 194,
 912 |    "id": "4d16c6c0",
 913 |    "metadata": {
 914 |     "scrolled": false
 915 |    },
 916 |    "outputs": [
 917 |     {
 918 |      "data": {
 919 |       "text/html": [
 920 |        "<div>\n",
 921 |        "<style scoped>\n",
 922 |        "    .dataframe tbody tr th:only-of-type {\n",
 923 |        "        vertical-align: middle;\n",
 924 |        "    }\n",
 925 |        "\n",
 926 |        "    .dataframe tbody tr th {\n",
 927 |        "        vertical-align: top;\n",
 928 |        "    }\n",
 929 |        "\n",
 930 |        "    .dataframe thead th {\n",
 931 |        "        text-align: right;\n",
 932 |        "    }\n",
 933 |        "</style>\n",
 934 |        "<table border=\"1\" class=\"dataframe\">\n",
 935 |        "  <thead>\n",
 936 |        "    <tr style=\"text-align: right;\">\n",
 937 |        "      <th></th>\n",
 938 |        "      <th>id</th>\n",
 939 |        "      <th>name</th>\n",
 940 |        "      <th>host_id</th>\n",
 941 |        "      <th>host_name</th>\n",
 942 |        "      <th>neighbourhood_group</th>\n",
 943 |        "      <th>neighbourhood</th>\n",
 944 |        "      <th>latitude</th>\n",
 945 |        "      <th>longitude</th>\n",
 946 |        "      <th>room_type</th>\n",
 947 |        "      <th>price</th>\n",
 948 |        "      <th>minimum_nights</th>\n",
 949 |        "      <th>number_of_reviews</th>\n",
 950 |        "      <th>last_review</th>\n",
 951 |        "      <th>reviews_per_month</th>\n",
 952 |        "      <th>calculated_host_listings_count</th>\n",
 953 |        "      <th>availability_365</th>\n",
 954 |        "    </tr>\n",
 955 |        "  </thead>\n",
 956 |        "  <tbody>\n",
 957 |        "    <tr>\n",
 958 |        "      <th>2</th>\n",
 959 |        "      <td>3647</td>\n",
 960 |        "      <td>THE VILLAGE OF HARLEM....NEW YORK !</td>\n",
 961 |        "      <td>4632</td>\n",
 962 |        "      <td>Elisabeth</td>\n",
 963 |        "      <td>Manhattan</td>\n",
 964 |        "      <td>Harlem</td>\n",
 965 |        "      <td>40.80902</td>\n",
 966 |        "      <td>-73.94190</td>\n",
 967 |        "      <td>Private room</td>\n",
 968 |        "      <td>150</td>\n",
 969 |        "      <td>3</td>\n",
 970 |        "      <td>0</td>\n",
 971 |        "      <td>NaN</td>\n",
 972 |        "      <td>1.373221</td>\n",
 973 |        "      <td>1</td>\n",
 974 |        "      <td>365</td>\n",
 975 |        "    </tr>\n",
 976 |        "    <tr>\n",
 977 |        "      <th>19</th>\n",
 978 |        "      <td>7750</td>\n",
 979 |        "      <td>Huge 2 BR Upper East  Cental Park</td>\n",
 980 |        "      <td>17985</td>\n",
 981 |        "      <td>Sing</td>\n",
 982 |        "      <td>Manhattan</td>\n",
 983 |        "      <td>East Harlem</td>\n",
 984 |        "      <td>40.79685</td>\n",
 985 |        "      <td>-73.94872</td>\n",
 986 |        "      <td>Entire home/apt</td>\n",
 987 |        "      <td>190</td>\n",
 988 |        "      <td>7</td>\n",
 989 |        "      <td>0</td>\n",
 990 |        "      <td>NaN</td>\n",
 991 |        "      <td>1.373221</td>\n",
 992 |        "      <td>2</td>\n",
 993 |        "      <td>249</td>\n",
 994 |        "    </tr>\n",
 995 |        "  </tbody>\n",
 996 |        "</table>\n",
 997 |        "</div>"
 998 |       ],
 999 |       "text/plain": [
1000 |        "      id                                 name  host_id  host_name  \\\n",
1001 |        "2   3647  THE VILLAGE OF HARLEM....NEW YORK !     4632  Elisabeth   \n",
1002 |        "19  7750    Huge 2 BR Upper East  Cental Park    17985       Sing   \n",
1003 |        "\n",
1004 |        "   neighbourhood_group neighbourhood  latitude  longitude        room_type  \\\n",
1005 |        "2            Manhattan        Harlem  40.80902  -73.94190     Private room   \n",
1006 |        "19           Manhattan   East Harlem  40.79685  -73.94872  Entire home/apt   \n",
1007 |        "\n",
1008 |        "    price  minimum_nights  number_of_reviews last_review  reviews_per_month  \\\n",
1009 |        "2     150               3                  0         NaN           1.373221   \n",
1010 |        "19    190               7                  0         NaN           1.373221   \n",
1011 |        "\n",
1012 |        "    calculated_host_listings_count  availability_365  \n",
1013 |        "2                                1               365  \n",
1014 |        "19                               2               249  "
1015 |       ]
1016 |      },
1017 |      "execution_count": 194,
1018 |      "metadata": {},
1019 |      "output_type": "execute_result"
1020 |     }
1021 |    ],
1022 |    "source": [
1023 |     "df3[df3[\"number_of_reviews\"]==0].head(2)"
1024 |    ]
1025 |   },
1026 |   {
1027 |    "cell_type": "code",
1028 |    "execution_count": 195,
1029 |    "id": "033155b6",
1030 |    "metadata": {},
1031 |    "outputs": [
1032 |     {
1033 |      "data": {
1034 |       "text/plain": [
1035 |        "id                                    0\n",
1036 |        "name                                 16\n",
1037 |        "host_id                               0\n",
1038 |        "host_name                            21\n",
1039 |        "neighbourhood_group                   0\n",
1040 |        "neighbourhood                         0\n",
1041 |        "latitude                              0\n",
1042 |        "longitude                             0\n",
1043 |        "room_type                             0\n",
1044 |        "price                                 0\n",
1045 |        "minimum_nights                        0\n",
1046 |        "number_of_reviews                     0\n",
1047 |        "last_review                       10052\n",
1048 |        "reviews_per_month                     0\n",
1049 |        "calculated_host_listings_count        0\n",
1050 |        "availability_365                      0\n",
1051 |        "dtype: int64"
1052 |       ]
1053 |      },
1054 |      "execution_count": 195,
1055 |      "metadata": {},
1056 |      "output_type": "execute_result"
1057 |     }
1058 |    ],
1059 |    "source": [
1060 |     "df3.isna().sum()"
1061 |    ]
1062 |   },
1063 |   {
1064 |    "cell_type": "markdown",
1065 |    "id": "a0819870",
1066 |    "metadata": {},
1067 |    "source": [
1068 |     "#### Categorical Data (Use mode value)"
1069 |    ]
1070 |   },
1071 |   {
1072 |    "cell_type": "code",
1073 |    "execution_count": 196,
1074 |    "id": "7b666009",
1075 |    "metadata": {},
1076 |    "outputs": [
1077 |     {
1078 |      "data": {
1079 |       "text/plain": [
1080 |        "0        2018-10-19\n",
1081 |        "1        2019-05-21\n",
1082 |        "2        2019-06-23\n",
1083 |        "3        2019-07-05\n",
1084 |        "4        2018-11-19\n",
1085 |        "            ...    \n",
1086 |        "48890    2019-06-23\n",
1087 |        "48891    2019-06-23\n",
1088 |        "48892    2019-06-23\n",
1089 |        "48893    2019-06-23\n",
1090 |        "48894    2019-06-23\n",
1091 |        "Name: last_review, Length: 48895, dtype: object"
1092 |       ]
1093 |      },
1094 |      "execution_count": 196,
1095 |      "metadata": {},
1096 |      "output_type": "execute_result"
1097 |     }
1098 |    ],
1099 |    "source": [
1100 |     "df3[\"last_review\"].fillna(df3[\"last_review\"].value_counts().index[0])"
1101 |    ]
1102 |   },
1103 |   {
1104 |    "cell_type": "markdown",
1105 |    "id": "ddb737e0",
1106 |    "metadata": {},
1107 |    "source": [
1108 |     "#### Categorical data (Use new category)"
1109 |    ]
1110 |   },
1111 |   {
1112 |    "cell_type": "code",
1113 |    "execution_count": 197,
1114 |    "id": "5c4904a4",
1115 |    "metadata": {},
1116 |    "outputs": [],
1117 |    "source": [
1118 |     "df3[\"last_review\"].fillna(\"Not Reviewed\", inplace = True)"
1119 |    ]
1120 |   },
1121 |   {
1122 |    "cell_type": "code",
1123 |    "execution_count": 198,
1124 |    "id": "15dfab92",
1125 |    "metadata": {},
1126 |    "outputs": [
1127 |     {
1128 |      "data": {
1129 |       "text/html": [
1130 |        "<div>\n",
1131 |        "<style scoped>\n",
1132 |        "    .dataframe tbody tr th:only-of-type {\n",
1133 |        "        vertical-align: middle;\n",
1134 |        "    }\n",
1135 |        "\n",
1136 |        "    .dataframe tbody tr th {\n",
1137 |        "        vertical-align: top;\n",
1138 |        "    }\n",
1139 |        "\n",
1140 |        "    .dataframe thead th {\n",
1141 |        "        text-align: right;\n",
1142 |        "    }\n",
1143 |        "</style>\n",
1144 |        "<table border=\"1\" class=\"dataframe\">\n",
1145 |        "  <thead>\n",
1146 |        "    <tr style=\"text-align: right;\">\n",
1147 |        "      <th></th>\n",
1148 |        "      <th>id</th>\n",
1149 |        "      <th>name</th>\n",
1150 |        "      <th>host_id</th>\n",
1151 |        "      <th>host_name</th>\n",
1152 |        "      <th>neighbourhood_group</th>\n",
1153 |        "      <th>neighbourhood</th>\n",
1154 |        "      <th>latitude</th>\n",
1155 |        "      <th>longitude</th>\n",
1156 |        "      <th>room_type</th>\n",
1157 |        "      <th>price</th>\n",
1158 |        "      <th>minimum_nights</th>\n",
1159 |        "      <th>number_of_reviews</th>\n",
1160 |        "      <th>last_review</th>\n",
1161 |        "      <th>reviews_per_month</th>\n",
1162 |        "      <th>calculated_host_listings_count</th>\n",
1163 |        "      <th>availability_365</th>\n",
1164 |        "    </tr>\n",
1165 |        "  </thead>\n",
1166 |        "  <tbody>\n",
1167 |        "    <tr>\n",
1168 |        "      <th>0</th>\n",
1169 |        "      <td>2539</td>\n",
1170 |        "      <td>Clean &amp; quiet apt home by the park</td>\n",
1171 |        "      <td>2787</td>\n",
1172 |        "      <td>John</td>\n",
1173 |        "      <td>Brooklyn</td>\n",
1174 |        "      <td>Kensington</td>\n",
1175 |        "      <td>40.64749</td>\n",
1176 |        "      <td>-73.97237</td>\n",
1177 |        "      <td>Private room</td>\n",
1178 |        "      <td>149</td>\n",
1179 |        "      <td>1</td>\n",
1180 |        "      <td>9</td>\n",
1181 |        "      <td>2018-10-19</td>\n",
1182 |        "      <td>0.210000</td>\n",
1183 |        "      <td>6</td>\n",
1184 |        "      <td>365</td>\n",
1185 |        "    </tr>\n",
1186 |        "    <tr>\n",
1187 |        "      <th>1</th>\n",
1188 |        "      <td>2595</td>\n",
1189 |        "      <td>Skylit Midtown Castle</td>\n",
1190 |        "      <td>2845</td>\n",
1191 |        "      <td>Jennifer</td>\n",
1192 |        "      <td>Manhattan</td>\n",
1193 |        "      <td>Midtown</td>\n",
1194 |        "      <td>40.75362</td>\n",
1195 |        "      <td>-73.98377</td>\n",
1196 |        "      <td>Entire home/apt</td>\n",
1197 |        "      <td>225</td>\n",
1198 |        "      <td>1</td>\n",
1199 |        "      <td>45</td>\n",
1200 |        "      <td>2019-05-21</td>\n",
1201 |        "      <td>0.380000</td>\n",
1202 |        "      <td>2</td>\n",
1203 |        "      <td>355</td>\n",
1204 |        "    </tr>\n",
1205 |        "    <tr>\n",
1206 |        "      <th>2</th>\n",
1207 |        "      <td>3647</td>\n",
1208 |        "      <td>THE VILLAGE OF HARLEM....NEW YORK !</td>\n",
1209 |        "      <td>4632</td>\n",
1210 |        "      <td>Elisabeth</td>\n",
1211 |        "      <td>Manhattan</td>\n",
1212 |        "      <td>Harlem</td>\n",
1213 |        "      <td>40.80902</td>\n",
1214 |        "      <td>-73.94190</td>\n",
1215 |        "      <td>Private room</td>\n",
1216 |        "      <td>150</td>\n",
1217 |        "      <td>3</td>\n",
1218 |        "      <td>0</td>\n",
1219 |        "      <td>Not Reviewed</td>\n",
1220 |        "      <td>1.373221</td>\n",
1221 |        "      <td>1</td>\n",
1222 |        "      <td>365</td>\n",
1223 |        "    </tr>\n",
1224 |        "    <tr>\n",
1225 |        "      <th>3</th>\n",
1226 |        "      <td>3831</td>\n",
1227 |        "      <td>Cozy Entire Floor of Brownstone</td>\n",
1228 |        "      <td>4869</td>\n",
1229 |        "      <td>LisaRoxanne</td>\n",
1230 |        "      <td>Brooklyn</td>\n",
1231 |        "      <td>Clinton Hill</td>\n",
1232 |        "      <td>40.68514</td>\n",
1233 |        "      <td>-73.95976</td>\n",
1234 |        "      <td>Entire home/apt</td>\n",
1235 |        "      <td>89</td>\n",
1236 |        "      <td>1</td>\n",
1237 |        "      <td>270</td>\n",
1238 |        "      <td>2019-07-05</td>\n",
1239 |        "      <td>4.640000</td>\n",
1240 |        "      <td>1</td>\n",
1241 |        "      <td>194</td>\n",
1242 |        "    </tr>\n",
1243 |        "    <tr>\n",
1244 |        "      <th>4</th>\n",
1245 |        "      <td>5022</td>\n",
1246 |        "      <td>Entire Apt: Spacious Studio/Loft by central park</td>\n",
1247 |        "      <td>7192</td>\n",
1248 |        "      <td>Laura</td>\n",
1249 |        "      <td>Manhattan</td>\n",
1250 |        "      <td>East Harlem</td>\n",
1251 |        "      <td>40.79851</td>\n",
1252 |        "      <td>-73.94399</td>\n",
1253 |        "      <td>Entire home/apt</td>\n",
1254 |        "      <td>80</td>\n",
1255 |        "      <td>10</td>\n",
1256 |        "      <td>9</td>\n",
1257 |        "      <td>2018-11-19</td>\n",
1258 |        "      <td>0.100000</td>\n",
1259 |        "      <td>1</td>\n",
1260 |        "      <td>0</td>\n",
1261 |        "    </tr>\n",
1262 |        "  </tbody>\n",
1263 |        "</table>\n",
1264 |        "</div>"
1265 |       ],
1266 |       "text/plain": [
1267 |        "     id                                              name  host_id  \\\n",
1268 |        "0  2539                Clean & quiet apt home by the park     2787   \n",
1269 |        "1  2595                             Skylit Midtown Castle     2845   \n",
1270 |        "2  3647               THE VILLAGE OF HARLEM....NEW YORK !     4632   \n",
1271 |        "3  3831                   Cozy Entire Floor of Brownstone     4869   \n",
1272 |        "4  5022  Entire Apt: Spacious Studio/Loft by central park     7192   \n",
1273 |        "\n",
1274 |        "     host_name neighbourhood_group neighbourhood  latitude  longitude  \\\n",
1275 |        "0         John            Brooklyn    Kensington  40.64749  -73.97237   \n",
1276 |        "1     Jennifer           Manhattan       Midtown  40.75362  -73.98377   \n",
1277 |        "2    Elisabeth           Manhattan        Harlem  40.80902  -73.94190   \n",
1278 |        "3  LisaRoxanne            Brooklyn  Clinton Hill  40.68514  -73.95976   \n",
1279 |        "4        Laura           Manhattan   East Harlem  40.79851  -73.94399   \n",
1280 |        "\n",
1281 |        "         room_type  price  minimum_nights  number_of_reviews   last_review  \\\n",
1282 |        "0     Private room    149               1                  9    2018-10-19   \n",
1283 |        "1  Entire home/apt    225               1                 45    2019-05-21   \n",
1284 |        "2     Private room    150               3                  0  Not Reviewed   \n",
1285 |        "3  Entire home/apt     89               1                270    2019-07-05   \n",
1286 |        "4  Entire home/apt     80              10                  9    2018-11-19   \n",
1287 |        "\n",
1288 |        "   reviews_per_month  calculated_host_listings_count  availability_365  \n",
1289 |        "0           0.210000                               6               365  \n",
1290 |        "1           0.380000                               2               355  \n",
1291 |        "2           1.373221                               1               365  \n",
1292 |        "3           4.640000                               1               194  \n",
1293 |        "4           0.100000                               1                 0  "
1294 |       ]
1295 |      },
1296 |      "execution_count": 198,
1297 |      "metadata": {},
1298 |      "output_type": "execute_result"
1299 |     }
1300 |    ],
1301 |    "source": [
1302 |     "df3.head()"
1303 |    ]
1304 |   },
1305 |   {
1306 |    "cell_type": "code",
1307 |    "execution_count": 199,
1308 |    "id": "ec36e3a0",
1309 |    "metadata": {},
1310 |    "outputs": [
1311 |     {
1312 |      "data": {
1313 |       "text/plain": [
1314 |        "id                                 0\n",
1315 |        "name                              16\n",
1316 |        "host_id                            0\n",
1317 |        "host_name                         21\n",
1318 |        "neighbourhood_group                0\n",
1319 |        "neighbourhood                      0\n",
1320 |        "latitude                           0\n",
1321 |        "longitude                          0\n",
1322 |        "room_type                          0\n",
1323 |        "price                              0\n",
1324 |        "minimum_nights                     0\n",
1325 |        "number_of_reviews                  0\n",
1326 |        "last_review                        0\n",
1327 |        "reviews_per_month                  0\n",
1328 |        "calculated_host_listings_count     0\n",
1329 |        "availability_365                   0\n",
1330 |        "dtype: int64"
1331 |       ]
1332 |      },
1333 |      "execution_count": 199,
1334 |      "metadata": {},
1335 |      "output_type": "execute_result"
1336 |     }
1337 |    ],
1338 |    "source": [
1339 |     "df3.isna().sum()"
1340 |    ]
1341 |   },
1342 |   {
1343 |    "cell_type": "code",
1344 |    "execution_count": 200,
1345 |    "id": "e73131e5",
1346 |    "metadata": {},
1347 |    "outputs": [],
1348 |    "source": [
1349 |     "df3[\"host_name\"].fillna(\"Unknown\", inplace = True)"
1350 |    ]
1351 |   },
1352 |   {
1353 |    "cell_type": "code",
1354 |    "execution_count": 201,
1355 |    "id": "4b4b6401",
1356 |    "metadata": {},
1357 |    "outputs": [
1358 |     {
1359 |      "data": {
1360 |       "text/plain": [
1361 |        "id                                 0\n",
1362 |        "name                              16\n",
1363 |        "host_id                            0\n",
1364 |        "host_name                          0\n",
1365 |        "neighbourhood_group                0\n",
1366 |        "neighbourhood                      0\n",
1367 |        "latitude                           0\n",
1368 |        "longitude                          0\n",
1369 |        "room_type                          0\n",
1370 |        "price                              0\n",
1371 |        "minimum_nights                     0\n",
1372 |        "number_of_reviews                  0\n",
1373 |        "last_review                        0\n",
1374 |        "reviews_per_month                  0\n",
1375 |        "calculated_host_listings_count     0\n",
1376 |        "availability_365                   0\n",
1377 |        "dtype: int64"
1378 |       ]
1379 |      },
1380 |      "execution_count": 201,
1381 |      "metadata": {},
1382 |      "output_type": "execute_result"
1383 |     }
1384 |    ],
1385 |    "source": [
1386 |     "df3.isna().sum()"
1387 |    ]
1388 |   },
1389 |   {
1390 |    "cell_type": "code",
1391 |    "execution_count": 202,
1392 |    "id": "2578e4a2",
1393 |    "metadata": {},
1394 |    "outputs": [],
1395 |    "source": [
1396 |     "df3[\"name\"].fillna(method = \"pad\", inplace = True)"
1397 |    ]
1398 |   },
1399 |   {
1400 |    "cell_type": "code",
1401 |    "execution_count": 203,
1402 |    "id": "65efa95f",
1403 |    "metadata": {},
1404 |    "outputs": [
1405 |     {
1406 |      "data": {
1407 |       "text/plain": [
1408 |        "id                                0\n",
1409 |        "name                              0\n",
1410 |        "host_id                           0\n",
1411 |        "host_name                         0\n",
1412 |        "neighbourhood_group               0\n",
1413 |        "neighbourhood                     0\n",
1414 |        "latitude                          0\n",
1415 |        "longitude                         0\n",
1416 |        "room_type                         0\n",
1417 |        "price                             0\n",
1418 |        "minimum_nights                    0\n",
1419 |        "number_of_reviews                 0\n",
1420 |        "last_review                       0\n",
1421 |        "reviews_per_month                 0\n",
1422 |        "calculated_host_listings_count    0\n",
1423 |        "availability_365                  0\n",
1424 |        "dtype: int64"
1425 |       ]
1426 |      },
1427 |      "execution_count": 203,
1428 |      "metadata": {},
1429 |      "output_type": "execute_result"
1430 |     }
1431 |    ],
1432 |    "source": [
1433 |     "df3.isna().sum()"
1434 |    ]
1435 |   },
1436 |   {
1437 |    "cell_type": "code",
1438 |    "execution_count": 204,
1439 |    "id": "d8622bff",
1440 |    "metadata": {
1441 |     "scrolled": true
1442 |    },
1443 |    "outputs": [
1444 |     {
1445 |      "data": {
1446 |       "text/html": [
1447 |        "<div>\n",
1448 |        "<style scoped>\n",
1449 |        "    .dataframe tbody tr th:only-of-type {\n",
1450 |        "        vertical-align: middle;\n",
1451 |        "    }\n",
1452 |        "\n",
1453 |        "    .dataframe tbody tr th {\n",
1454 |        "        vertical-align: top;\n",
1455 |        "    }\n",
1456 |        "\n",
1457 |        "    .dataframe thead th {\n",
1458 |        "        text-align: right;\n",
1459 |        "    }\n",
1460 |        "</style>\n",
1461 |        "<table border=\"1\" class=\"dataframe\">\n",
1462 |        "  <thead>\n",
1463 |        "    <tr style=\"text-align: right;\">\n",
1464 |        "      <th></th>\n",
1465 |        "      <th>id</th>\n",
1466 |        "      <th>name</th>\n",
1467 |        "      <th>host_id</th>\n",
1468 |        "      <th>host_name</th>\n",
1469 |        "      <th>neighbourhood_group</th>\n",
1470 |        "      <th>neighbourhood</th>\n",
1471 |        "      <th>latitude</th>\n",
1472 |        "      <th>longitude</th>\n",
1473 |        "      <th>room_type</th>\n",
1474 |        "      <th>price</th>\n",
1475 |        "      <th>minimum_nights</th>\n",
1476 |        "      <th>number_of_reviews</th>\n",
1477 |        "      <th>last_review</th>\n",
1478 |        "      <th>reviews_per_month</th>\n",
1479 |        "      <th>calculated_host_listings_count</th>\n",
1480 |        "      <th>availability_365</th>\n",
1481 |        "    </tr>\n",
1482 |        "  </thead>\n",
1483 |        "  <tbody>\n",
1484 |        "    <tr>\n",
1485 |        "      <th>0</th>\n",
1486 |        "      <td>2539</td>\n",
1487 |        "      <td>Clean &amp; quiet apt home by the park</td>\n",
1488 |        "      <td>2787</td>\n",
1489 |        "      <td>John</td>\n",
1490 |        "      <td>Brooklyn</td>\n",
1491 |        "      <td>Kensington</td>\n",
1492 |        "      <td>40.64749</td>\n",
1493 |        "      <td>-73.97237</td>\n",
1494 |        "      <td>Private room</td>\n",
1495 |        "      <td>149</td>\n",
1496 |        "      <td>1</td>\n",
1497 |        "      <td>9</td>\n",
1498 |        "      <td>2018-10-19</td>\n",
1499 |        "      <td>0.210000</td>\n",
1500 |        "      <td>6</td>\n",
1501 |        "      <td>365</td>\n",
1502 |        "    </tr>\n",
1503 |        "    <tr>\n",
1504 |        "      <th>1</th>\n",
1505 |        "      <td>2595</td>\n",
1506 |        "      <td>Skylit Midtown Castle</td>\n",
1507 |        "      <td>2845</td>\n",
1508 |        "      <td>Jennifer</td>\n",
1509 |        "      <td>Manhattan</td>\n",
1510 |        "      <td>Midtown</td>\n",
1511 |        "      <td>40.75362</td>\n",
1512 |        "      <td>-73.98377</td>\n",
1513 |        "      <td>Entire home/apt</td>\n",
1514 |        "      <td>225</td>\n",
1515 |        "      <td>1</td>\n",
1516 |        "      <td>45</td>\n",
1517 |        "      <td>2019-05-21</td>\n",
1518 |        "      <td>0.380000</td>\n",
1519 |        "      <td>2</td>\n",
1520 |        "      <td>355</td>\n",
1521 |        "    </tr>\n",
1522 |        "    <tr>\n",
1523 |        "      <th>2</th>\n",
1524 |        "      <td>3647</td>\n",
1525 |        "      <td>THE VILLAGE OF HARLEM....NEW YORK !</td>\n",
1526 |        "      <td>4632</td>\n",
1527 |        "      <td>Elisabeth</td>\n",
1528 |        "      <td>Manhattan</td>\n",
1529 |        "      <td>Harlem</td>\n",
1530 |        "      <td>40.80902</td>\n",
1531 |        "      <td>-73.94190</td>\n",
1532 |        "      <td>Private room</td>\n",
1533 |        "      <td>150</td>\n",
1534 |        "      <td>3</td>\n",
1535 |        "      <td>0</td>\n",
1536 |        "      <td>Not Reviewed</td>\n",
1537 |        "      <td>1.373221</td>\n",
1538 |        "      <td>1</td>\n",
1539 |        "      <td>365</td>\n",
1540 |        "    </tr>\n",
1541 |        "    <tr>\n",
1542 |        "      <th>3</th>\n",
1543 |        "      <td>3831</td>\n",
1544 |        "      <td>Cozy Entire Floor of Brownstone</td>\n",
1545 |        "      <td>4869</td>\n",
1546 |        "      <td>LisaRoxanne</td>\n",
1547 |        "      <td>Brooklyn</td>\n",
1548 |        "      <td>Clinton Hill</td>\n",
1549 |        "      <td>40.68514</td>\n",
1550 |        "      <td>-73.95976</td>\n",
1551 |        "      <td>Entire home/apt</td>\n",
1552 |        "      <td>89</td>\n",
1553 |        "      <td>1</td>\n",
1554 |        "      <td>270</td>\n",
1555 |        "      <td>2019-07-05</td>\n",
1556 |        "      <td>4.640000</td>\n",
1557 |        "      <td>1</td>\n",
1558 |        "      <td>194</td>\n",
1559 |        "    </tr>\n",
1560 |        "    <tr>\n",
1561 |        "      <th>4</th>\n",
1562 |        "      <td>5022</td>\n",
1563 |        "      <td>Entire Apt: Spacious Studio/Loft by central park</td>\n",
1564 |        "      <td>7192</td>\n",
1565 |        "      <td>Laura</td>\n",
1566 |        "      <td>Manhattan</td>\n",
1567 |        "      <td>East Harlem</td>\n",
1568 |        "      <td>40.79851</td>\n",
1569 |        "      <td>-73.94399</td>\n",
1570 |        "      <td>Entire home/apt</td>\n",
1571 |        "      <td>80</td>\n",
1572 |        "      <td>10</td>\n",
1573 |        "      <td>9</td>\n",
1574 |        "      <td>2018-11-19</td>\n",
1575 |        "      <td>0.100000</td>\n",
1576 |        "      <td>1</td>\n",
1577 |        "      <td>0</td>\n",
1578 |        "    </tr>\n",
1579 |        "  </tbody>\n",
1580 |        "</table>\n",
1581 |        "</div>"
1582 |       ],
1583 |       "text/plain": [
1584 |        "     id                                              name  host_id  \\\n",
1585 |        "0  2539                Clean & quiet apt home by the park     2787   \n",
1586 |        "1  2595                             Skylit Midtown Castle     2845   \n",
1587 |        "2  3647               THE VILLAGE OF HARLEM....NEW YORK !     4632   \n",
1588 |        "3  3831                   Cozy Entire Floor of Brownstone     4869   \n",
1589 |        "4  5022  Entire Apt: Spacious Studio/Loft by central park     7192   \n",
1590 |        "\n",
1591 |        "     host_name neighbourhood_group neighbourhood  latitude  longitude  \\\n",
1592 |        "0         John            Brooklyn    Kensington  40.64749  -73.97237   \n",
1593 |        "1     Jennifer           Manhattan       Midtown  40.75362  -73.98377   \n",
1594 |        "2    Elisabeth           Manhattan        Harlem  40.80902  -73.94190   \n",
1595 |        "3  LisaRoxanne            Brooklyn  Clinton Hill  40.68514  -73.95976   \n",
1596 |        "4        Laura           Manhattan   East Harlem  40.79851  -73.94399   \n",
1597 |        "\n",
1598 |        "         room_type  price  minimum_nights  number_of_reviews   last_review  \\\n",
1599 |        "0     Private room    149               1                  9    2018-10-19   \n",
1600 |        "1  Entire home/apt    225               1                 45    2019-05-21   \n",
1601 |        "2     Private room    150               3                  0  Not Reviewed   \n",
1602 |        "3  Entire home/apt     89               1                270    2019-07-05   \n",
1603 |        "4  Entire home/apt     80              10                  9    2018-11-19   \n",
1604 |        "\n",
1605 |        "   reviews_per_month  calculated_host_listings_count  availability_365  \n",
1606 |        "0           0.210000                               6               365  \n",
1607 |        "1           0.380000                               2               355  \n",
1608 |        "2           1.373221                               1               365  \n",
1609 |        "3           4.640000                               1               194  \n",
1610 |        "4           0.100000                               1                 0  "
1611 |       ]
1612 |      },
1613 |      "execution_count": 204,
1614 |      "metadata": {},
1615 |      "output_type": "execute_result"
1616 |     }
1617 |    ],
1618 |    "source": [
1619 |     "df3.head()"
1620 |    ]
1621 |   },
1622 |   {
1623 |    "cell_type": "markdown",
1624 |    "id": "de6d9cb6",
1625 |    "metadata": {},
1626 |    "source": [
1627 |     "### Advanced Imputation"
1628 |    ]
1629 |   },
1630 |   {
1631 |    "cell_type": "code",
1632 |    "execution_count": 205,
1633 |    "id": "c4e67106",
1634 |    "metadata": {},
1635 |    "outputs": [],
1636 |    "source": [
1637 |     "df = data"
1638 |    ]
1639 |   },
1640 |   {
1641 |    "cell_type": "code",
1642 |    "execution_count": 207,
1643 |    "id": "43a21a00",
1644 |    "metadata": {},
1645 |    "outputs": [
1646 |     {
1647 |      "data": {
1648 |       "text/plain": [
1649 |        "id                                    0\n",
1650 |        "name                                 16\n",
1651 |        "host_id                               0\n",
1652 |        "host_name                            21\n",
1653 |        "neighbourhood_group                   0\n",
1654 |        "neighbourhood                         0\n",
1655 |        "latitude                              0\n",
1656 |        "longitude                             0\n",
1657 |        "room_type                             0\n",
1658 |        "price                                 0\n",
1659 |        "minimum_nights                        0\n",
1660 |        "number_of_reviews                     0\n",
1661 |        "last_review                       10052\n",
1662 |        "reviews_per_month                 10052\n",
1663 |        "calculated_host_listings_count        0\n",
1664 |        "availability_365                      0\n",
1665 |        "dtype: int64"
1666 |       ]
1667 |      },
1668 |      "execution_count": 207,
1669 |      "metadata": {},
1670 |      "output_type": "execute_result"
1671 |     }
1672 |    ],
1673 |    "source": [
1674 |     "df.isna().sum()"
1675 |    ]
1676 |   },
1677 |   {
1678 |    "cell_type": "code",
1679 |    "execution_count": 209,
1680 |    "id": "a4df50d0",
1681 |    "metadata": {},
1682 |    "outputs": [],
1683 |    "source": [
1684 |     "df[\"reviews_per_month\"].interpolate(inplace = True)"
1685 |    ]
1686 |   },
1687 |   {
1688 |    "cell_type": "code",
1689 |    "execution_count": 211,
1690 |    "id": "55a6d283",
1691 |    "metadata": {},
1692 |    "outputs": [
1693 |     {
1694 |      "data": {
1695 |       "text/html": [
1696 |        "<div>\n",
1697 |        "<style scoped>\n",
1698 |        "    .dataframe tbody tr th:only-of-type {\n",
1699 |        "        vertical-align: middle;\n",
1700 |        "    }\n",
1701 |        "\n",
1702 |        "    .dataframe tbody tr th {\n",
1703 |        "        vertical-align: top;\n",
1704 |        "    }\n",
1705 |        "\n",
1706 |        "    .dataframe thead th {\n",
1707 |        "        text-align: right;\n",
1708 |        "    }\n",
1709 |        "</style>\n",
1710 |        "<table border=\"1\" class=\"dataframe\">\n",
1711 |        "  <thead>\n",
1712 |        "    <tr style=\"text-align: right;\">\n",
1713 |        "      <th></th>\n",
1714 |        "      <th>id</th>\n",
1715 |        "      <th>name</th>\n",
1716 |        "      <th>host_id</th>\n",
1717 |        "      <th>host_name</th>\n",
1718 |        "      <th>neighbourhood_group</th>\n",
1719 |        "      <th>neighbourhood</th>\n",
1720 |        "      <th>latitude</th>\n",
1721 |        "      <th>longitude</th>\n",
1722 |        "      <th>room_type</th>\n",
1723 |        "      <th>price</th>\n",
1724 |        "      <th>minimum_nights</th>\n",
1725 |        "      <th>number_of_reviews</th>\n",
1726 |        "      <th>last_review</th>\n",
1727 |        "      <th>reviews_per_month</th>\n",
1728 |        "      <th>calculated_host_listings_count</th>\n",
1729 |        "      <th>availability_365</th>\n",
1730 |        "    </tr>\n",
1731 |        "  </thead>\n",
1732 |        "  <tbody>\n",
1733 |        "    <tr>\n",
1734 |        "      <th>0</th>\n",
1735 |        "      <td>2539</td>\n",
1736 |        "      <td>Clean &amp; quiet apt home by the park</td>\n",
1737 |        "      <td>2787</td>\n",
1738 |        "      <td>John</td>\n",
1739 |        "      <td>Brooklyn</td>\n",
1740 |        "      <td>Kensington</td>\n",
1741 |        "      <td>40.64749</td>\n",
1742 |        "      <td>-73.97237</td>\n",
1743 |        "      <td>Private room</td>\n",
1744 |        "      <td>149</td>\n",
1745 |        "      <td>1</td>\n",
1746 |        "      <td>9</td>\n",
1747 |        "      <td>2018-10-19</td>\n",
1748 |        "      <td>0.21</td>\n",
1749 |        "      <td>6</td>\n",
1750 |        "      <td>365</td>\n",
1751 |        "    </tr>\n",
1752 |        "    <tr>\n",
1753 |        "      <th>1</th>\n",
1754 |        "      <td>2595</td>\n",
1755 |        "      <td>Skylit Midtown Castle</td>\n",
1756 |        "      <td>2845</td>\n",
1757 |        "      <td>Jennifer</td>\n",
1758 |        "      <td>Manhattan</td>\n",
1759 |        "      <td>Midtown</td>\n",
1760 |        "      <td>40.75362</td>\n",
1761 |        "      <td>-73.98377</td>\n",
1762 |        "      <td>Entire home/apt</td>\n",
1763 |        "      <td>225</td>\n",
1764 |        "      <td>1</td>\n",
1765 |        "      <td>45</td>\n",
1766 |        "      <td>2019-05-21</td>\n",
1767 |        "      <td>0.38</td>\n",
1768 |        "      <td>2</td>\n",
1769 |        "      <td>355</td>\n",
1770 |        "    </tr>\n",
1771 |        "    <tr>\n",
1772 |        "      <th>2</th>\n",
1773 |        "      <td>3647</td>\n",
1774 |        "      <td>THE VILLAGE OF HARLEM....NEW YORK !</td>\n",
1775 |        "      <td>4632</td>\n",
1776 |        "      <td>Elisabeth</td>\n",
1777 |        "      <td>Manhattan</td>\n",
1778 |        "      <td>Harlem</td>\n",
1779 |        "      <td>40.80902</td>\n",
1780 |        "      <td>-73.94190</td>\n",
1781 |        "      <td>Private room</td>\n",
1782 |        "      <td>150</td>\n",
1783 |        "      <td>3</td>\n",
1784 |        "      <td>0</td>\n",
1785 |        "      <td>NaN</td>\n",
1786 |        "      <td>2.51</td>\n",
1787 |        "      <td>1</td>\n",
1788 |        "      <td>365</td>\n",
1789 |        "    </tr>\n",
1790 |        "    <tr>\n",
1791 |        "      <th>3</th>\n",
1792 |        "      <td>3831</td>\n",
1793 |        "      <td>Cozy Entire Floor of Brownstone</td>\n",
1794 |        "      <td>4869</td>\n",
1795 |        "      <td>LisaRoxanne</td>\n",
1796 |        "      <td>Brooklyn</td>\n",
1797 |        "      <td>Clinton Hill</td>\n",
1798 |        "      <td>40.68514</td>\n",
1799 |        "      <td>-73.95976</td>\n",
1800 |        "      <td>Entire home/apt</td>\n",
1801 |        "      <td>89</td>\n",
1802 |        "      <td>1</td>\n",
1803 |        "      <td>270</td>\n",
1804 |        "      <td>2019-07-05</td>\n",
1805 |        "      <td>4.64</td>\n",
1806 |        "      <td>1</td>\n",
1807 |        "      <td>194</td>\n",
1808 |        "    </tr>\n",
1809 |        "    <tr>\n",
1810 |        "      <th>4</th>\n",
1811 |        "      <td>5022</td>\n",
1812 |        "      <td>Entire Apt: Spacious Studio/Loft by central park</td>\n",
1813 |        "      <td>7192</td>\n",
1814 |        "      <td>Laura</td>\n",
1815 |        "      <td>Manhattan</td>\n",
1816 |        "      <td>East Harlem</td>\n",
1817 |        "      <td>40.79851</td>\n",
1818 |        "      <td>-73.94399</td>\n",
1819 |        "      <td>Entire home/apt</td>\n",
1820 |        "      <td>80</td>\n",
1821 |        "      <td>10</td>\n",
1822 |        "      <td>9</td>\n",
1823 |        "      <td>2018-11-19</td>\n",
1824 |        "      <td>0.10</td>\n",
1825 |        "      <td>1</td>\n",
1826 |        "      <td>0</td>\n",
1827 |        "    </tr>\n",
1828 |        "  </tbody>\n",
1829 |        "</table>\n",
1830 |        "</div>"
1831 |       ],
1832 |       "text/plain": [
1833 |        "     id                                              name  host_id  \\\n",
1834 |        "0  2539                Clean & quiet apt home by the park     2787   \n",
1835 |        "1  2595                             Skylit Midtown Castle     2845   \n",
1836 |        "2  3647               THE VILLAGE OF HARLEM....NEW YORK !     4632   \n",
1837 |        "3  3831                   Cozy Entire Floor of Brownstone     4869   \n",
1838 |        "4  5022  Entire Apt: Spacious Studio/Loft by central park     7192   \n",
1839 |        "\n",
1840 |        "     host_name neighbourhood_group neighbourhood  latitude  longitude  \\\n",
1841 |        "0         John            Brooklyn    Kensington  40.64749  -73.97237   \n",
1842 |        "1     Jennifer           Manhattan       Midtown  40.75362  -73.98377   \n",
1843 |        "2    Elisabeth           Manhattan        Harlem  40.80902  -73.94190   \n",
1844 |        "3  LisaRoxanne            Brooklyn  Clinton Hill  40.68514  -73.95976   \n",
1845 |        "4        Laura           Manhattan   East Harlem  40.79851  -73.94399   \n",
1846 |        "\n",
1847 |        "         room_type  price  minimum_nights  number_of_reviews last_review  \\\n",
1848 |        "0     Private room    149               1                  9  2018-10-19   \n",
1849 |        "1  Entire home/apt    225               1                 45  2019-05-21   \n",
1850 |        "2     Private room    150               3                  0         NaN   \n",
1851 |        "3  Entire home/apt     89               1                270  2019-07-05   \n",
1852 |        "4  Entire home/apt     80              10                  9  2018-11-19   \n",
1853 |        "\n",
1854 |        "   reviews_per_month  calculated_host_listings_count  availability_365  \n",
1855 |        "0               0.21                               6               365  \n",
1856 |        "1               0.38                               2               355  \n",
1857 |        "2               2.51                               1               365  \n",
1858 |        "3               4.64                               1               194  \n",
1859 |        "4               0.10                               1                 0  "
1860 |       ]
1861 |      },
1862 |      "execution_count": 211,
1863 |      "metadata": {},
1864 |      "output_type": "execute_result"
1865 |     }
1866 |    ],
1867 |    "source": [
1868 |     "df.head()"
1869 |    ]
1870 |   },
1871 |   {
1872 |    "cell_type": "markdown",
1873 |    "id": "332397ae",
1874 |    "metadata": {},
1875 |    "source": [
1876 |     "### Handling Duplicate data"
1877 |    ]
1878 |   },
1879 |   {
1880 |    "cell_type": "code",
1881 |    "execution_count": 174,
1882 |    "id": "d6f88ece",
1883 |    "metadata": {},
1884 |    "outputs": [
1885 |     {
1886 |      "data": {
1887 |       "text/plain": [
1888 |        "0"
1889 |       ]
1890 |      },
1891 |      "execution_count": 174,
1892 |      "metadata": {},
1893 |      "output_type": "execute_result"
1894 |     }
1895 |    ],
1896 |    "source": [
1897 |     "data.duplicated().sum()"
1898 |    ]
1899 |   },
1900 |   {
1901 |    "cell_type": "code",
1902 |    "execution_count": 212,
1903 |    "id": "32248270",
1904 |    "metadata": {},
1905 |    "outputs": [],
1906 |    "source": [
1907 |     "data.drop_duplicates(inplace = True)"
1908 |    ]
1909 |   }
1910 |  ],
1911 |  "metadata": {
1912 |   "kernelspec": {
1913 |    "display_name": "Python 3 (ipykernel)",
1914 |    "language": "python",
1915 |    "name": "python3"
1916 |   },
1917 |   "language_info": {
1918 |    "codemirror_mode": {
1919 |     "name": "ipython",
1920 |     "version": 3
1921 |    },
1922 |    "file_extension": ".py",
1923 |    "mimetype": "text/x-python",
1924 |    "name": "python",
1925 |    "nbconvert_exporter": "python",
1926 |    "pygments_lexer": "ipython3",
1927 |    "version": "3.11.1"
1928 |   }
1929 |  },
1930 |  "nbformat": 4,
1931 |  "nbformat_minor": 5
1932 | }
1933 | 


--------------------------------------------------------------------------------
/9 Correction of datatype.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 1,
  6 |    "id": "6332b62b",
  7 |    "metadata": {},
  8 |    "outputs": [],
  9 |    "source": [
 10 |     "import pandas as pd"
 11 |    ]
 12 |   },
 13 |   {
 14 |    "cell_type": "code",
 15 |    "execution_count": 2,
 16 |    "id": "06f8ba29",
 17 |    "metadata": {},
 18 |    "outputs": [],
 19 |    "source": [
 20 |     "df = pd.read_csv(\"AB_NYC_2019.csv\")"
 21 |    ]
 22 |   },
 23 |   {
 24 |    "cell_type": "code",
 25 |    "execution_count": 4,
 26 |    "id": "5d1321df",
 27 |    "metadata": {},
 28 |    "outputs": [
 29 |     {
 30 |      "data": {
 31 |       "text/html": [
 32 |        "<div>\n",
 33 |        "<style scoped>\n",
 34 |        "    .dataframe tbody tr th:only-of-type {\n",
 35 |        "        vertical-align: middle;\n",
 36 |        "    }\n",
 37 |        "\n",
 38 |        "    .dataframe tbody tr th {\n",
 39 |        "        vertical-align: top;\n",
 40 |        "    }\n",
 41 |        "\n",
 42 |        "    .dataframe thead th {\n",
 43 |        "        text-align: right;\n",
 44 |        "    }\n",
 45 |        "</style>\n",
 46 |        "<table border=\"1\" class=\"dataframe\">\n",
 47 |        "  <thead>\n",
 48 |        "    <tr style=\"text-align: right;\">\n",
 49 |        "      <th></th>\n",
 50 |        "      <th>id</th>\n",
 51 |        "      <th>name</th>\n",
 52 |        "      <th>host_id</th>\n",
 53 |        "      <th>host_name</th>\n",
 54 |        "      <th>neighbourhood_group</th>\n",
 55 |        "      <th>neighbourhood</th>\n",
 56 |        "      <th>latitude</th>\n",
 57 |        "      <th>longitude</th>\n",
 58 |        "      <th>room_type</th>\n",
 59 |        "      <th>price</th>\n",
 60 |        "      <th>minimum_nights</th>\n",
 61 |        "      <th>number_of_reviews</th>\n",
 62 |        "      <th>last_review</th>\n",
 63 |        "      <th>reviews_per_month</th>\n",
 64 |        "      <th>calculated_host_listings_count</th>\n",
 65 |        "      <th>availability_365</th>\n",
 66 |        "    </tr>\n",
 67 |        "  </thead>\n",
 68 |        "  <tbody>\n",
 69 |        "    <tr>\n",
 70 |        "      <th>0</th>\n",
 71 |        "      <td>2539</td>\n",
 72 |        "      <td>Clean &amp; quiet apt home by the park</td>\n",
 73 |        "      <td>2787</td>\n",
 74 |        "      <td>John</td>\n",
 75 |        "      <td>Brooklyn</td>\n",
 76 |        "      <td>Kensington</td>\n",
 77 |        "      <td>40.64749</td>\n",
 78 |        "      <td>-73.97237</td>\n",
 79 |        "      <td>Private room</td>\n",
 80 |        "      <td>149</td>\n",
 81 |        "      <td>1</td>\n",
 82 |        "      <td>9</td>\n",
 83 |        "      <td>19-10-2018</td>\n",
 84 |        "      <td>0.21</td>\n",
 85 |        "      <td>6</td>\n",
 86 |        "      <td>365</td>\n",
 87 |        "    </tr>\n",
 88 |        "    <tr>\n",
 89 |        "      <th>1</th>\n",
 90 |        "      <td>2595</td>\n",
 91 |        "      <td>Skylit Midtown Castle</td>\n",
 92 |        "      <td>2845</td>\n",
 93 |        "      <td>Jennifer</td>\n",
 94 |        "      <td>Manhattan</td>\n",
 95 |        "      <td>Midtown</td>\n",
 96 |        "      <td>40.75362</td>\n",
 97 |        "      <td>-73.98377</td>\n",
 98 |        "      <td>Entire home/apt</td>\n",
 99 |        "      <td>225</td>\n",
100 |        "      <td>1</td>\n",
101 |        "      <td>45</td>\n",
102 |        "      <td>21-05-2019</td>\n",
103 |        "      <td>0.38</td>\n",
104 |        "      <td>2</td>\n",
105 |        "      <td>355</td>\n",
106 |        "    </tr>\n",
107 |        "  </tbody>\n",
108 |        "</table>\n",
109 |        "</div>"
110 |       ],
111 |       "text/plain": [
112 |        "     id                                name  host_id host_name  \\\n",
113 |        "0  2539  Clean & quiet apt home by the park     2787      John   \n",
114 |        "1  2595               Skylit Midtown Castle     2845  Jennifer   \n",
115 |        "\n",
116 |        "  neighbourhood_group neighbourhood  latitude  longitude        room_type  \\\n",
117 |        "0            Brooklyn    Kensington  40.64749  -73.97237     Private room   \n",
118 |        "1           Manhattan       Midtown  40.75362  -73.98377  Entire home/apt   \n",
119 |        "\n",
120 |        "   price  minimum_nights  number_of_reviews last_review  reviews_per_month  \\\n",
121 |        "0    149               1                  9  19-10-2018               0.21   \n",
122 |        "1    225               1                 45  21-05-2019               0.38   \n",
123 |        "\n",
124 |        "   calculated_host_listings_count  availability_365  \n",
125 |        "0                               6               365  \n",
126 |        "1                               2               355  "
127 |       ]
128 |      },
129 |      "execution_count": 4,
130 |      "metadata": {},
131 |      "output_type": "execute_result"
132 |     }
133 |    ],
134 |    "source": [
135 |     "df.head(2)"
136 |    ]
137 |   },
138 |   {
139 |    "cell_type": "code",
140 |    "execution_count": 3,
141 |    "id": "2fc99302",
142 |    "metadata": {},
143 |    "outputs": [
144 |     {
145 |      "name": "stdout",
146 |      "output_type": "stream",
147 |      "text": [
148 |       "<class 'pandas.core.frame.DataFrame'>\n",
149 |       "RangeIndex: 48906 entries, 0 to 48905\n",
150 |       "Data columns (total 16 columns):\n",
151 |       " #   Column                          Non-Null Count  Dtype  \n",
152 |       "---  ------                          --------------  -----  \n",
153 |       " 0   id                              48906 non-null  int64  \n",
154 |       " 1   name                            48890 non-null  object \n",
155 |       " 2   host_id                         48906 non-null  int64  \n",
156 |       " 3   host_name                       48885 non-null  object \n",
157 |       " 4   neighbourhood_group             48906 non-null  object \n",
158 |       " 5   neighbourhood                   48906 non-null  object \n",
159 |       " 6   latitude                        48906 non-null  float64\n",
160 |       " 7   longitude                       48906 non-null  float64\n",
161 |       " 8   room_type                       48906 non-null  object \n",
162 |       " 9   price                           48906 non-null  int64  \n",
163 |       " 10  minimum_nights                  48906 non-null  int64  \n",
164 |       " 11  number_of_reviews               48906 non-null  int64  \n",
165 |       " 12  last_review                     38854 non-null  object \n",
166 |       " 13  reviews_per_month               38854 non-null  float64\n",
167 |       " 14  calculated_host_listings_count  48906 non-null  int64  \n",
168 |       " 15  availability_365                48906 non-null  int64  \n",
169 |       "dtypes: float64(3), int64(7), object(6)\n",
170 |       "memory usage: 6.0+ MB\n"
171 |      ]
172 |     }
173 |    ],
174 |    "source": [
175 |     "df.info()"
176 |    ]
177 |   },
178 |   {
179 |    "cell_type": "code",
180 |    "execution_count": 9,
181 |    "id": "bff805e2",
182 |    "metadata": {},
183 |    "outputs": [],
184 |    "source": [
185 |     "df[\"id\"] = df[\"id\"].astype(str)"
186 |    ]
187 |   },
188 |   {
189 |    "cell_type": "code",
190 |    "execution_count": 18,
191 |    "id": "e30541cc",
192 |    "metadata": {},
193 |    "outputs": [
194 |     {
195 |      "data": {
196 |       "text/plain": [
197 |        "dtype('O')"
198 |       ]
199 |      },
200 |      "execution_count": 18,
201 |      "metadata": {},
202 |      "output_type": "execute_result"
203 |     }
204 |    ],
205 |    "source": [
206 |     "df[\"id\"].dtype"
207 |    ]
208 |   },
209 |   {
210 |    "cell_type": "code",
211 |    "execution_count": 19,
212 |    "id": "0ff5acec",
213 |    "metadata": {},
214 |    "outputs": [],
215 |    "source": [
216 |     "df[\"host_id\"] = df[\"host_id\"].astype(str)"
217 |    ]
218 |   },
219 |   {
220 |    "cell_type": "code",
221 |    "execution_count": 20,
222 |    "id": "8dd6d327",
223 |    "metadata": {},
224 |    "outputs": [
225 |     {
226 |      "name": "stderr",
227 |      "output_type": "stream",
228 |      "text": [
229 |       "C:\\Users\\GFG19189\\AppData\\Local\\Temp\\ipykernel_3288\\3465608367.py:1: UserWarning: Parsing dates in DD/MM/YYYY format when dayfirst=False (the default) was specified. This may lead to inconsistently parsed dates! Specify a format to ensure consistent parsing.\n",
230 |       "  df[\"last_review\"] = pd.to_datetime(df[\"last_review\"])\n"
231 |      ]
232 |     }
233 |    ],
234 |    "source": [
235 |     "df[\"last_review\"] = pd.to_datetime(df[\"last_review\"])"
236 |    ]
237 |   },
238 |   {
239 |    "cell_type": "code",
240 |    "execution_count": 22,
241 |    "id": "8bfd344f",
242 |    "metadata": {},
243 |    "outputs": [
244 |     {
245 |      "name": "stdout",
246 |      "output_type": "stream",
247 |      "text": [
248 |       "<class 'pandas.core.frame.DataFrame'>\n",
249 |       "RangeIndex: 48906 entries, 0 to 48905\n",
250 |       "Data columns (total 16 columns):\n",
251 |       " #   Column                          Non-Null Count  Dtype         \n",
252 |       "---  ------                          --------------  -----         \n",
253 |       " 0   id                              48906 non-null  object        \n",
254 |       " 1   name                            48890 non-null  object        \n",
255 |       " 2   host_id                         48906 non-null  object        \n",
256 |       " 3   host_name                       48885 non-null  object        \n",
257 |       " 4   neighbourhood_group             48906 non-null  object        \n",
258 |       " 5   neighbourhood                   48906 non-null  object        \n",
259 |       " 6   latitude                        48906 non-null  float64       \n",
260 |       " 7   longitude                       48906 non-null  float64       \n",
261 |       " 8   room_type                       48906 non-null  object        \n",
262 |       " 9   price                           48906 non-null  int64         \n",
263 |       " 10  minimum_nights                  48906 non-null  int64         \n",
264 |       " 11  number_of_reviews               48906 non-null  int64         \n",
265 |       " 12  last_review                     38854 non-null  datetime64[ns]\n",
266 |       " 13  reviews_per_month               38854 non-null  float64       \n",
267 |       " 14  calculated_host_listings_count  48906 non-null  int64         \n",
268 |       " 15  availability_365                48906 non-null  int64         \n",
269 |       "dtypes: datetime64[ns](1), float64(3), int64(5), object(7)\n",
270 |       "memory usage: 6.0+ MB\n"
271 |      ]
272 |     }
273 |    ],
274 |    "source": [
275 |     "df.info()"
276 |    ]
277 |   }
278 |  ],
279 |  "metadata": {
280 |   "kernelspec": {
281 |    "display_name": "Python 3 (ipykernel)",
282 |    "language": "python",
283 |    "name": "python3"
284 |   },
285 |   "language_info": {
286 |    "codemirror_mode": {
287 |     "name": "ipython",
288 |     "version": 3
289 |    },
290 |    "file_extension": ".py",
291 |    "mimetype": "text/x-python",
292 |    "name": "python",
293 |    "nbconvert_exporter": "python",
294 |    "pygments_lexer": "ipython3",
295 |    "version": "3.11.1"
296 |   }
297 |  },
298 |  "nbformat": 4,
299 |  "nbformat_minor": 5
300 | }
301 | 


--------------------------------------------------------------------------------
/EDA 5 (Outliers).pptx:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/sakshisinghal936/eda_data_science_course/80bc747c0d9ad6cfb2535812458a184d29d0d61d/EDA 5 (Outliers).pptx


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | # Introduction to Exploratory Data Analysis (EDA) Course
 2 | 
 3 | ## Overview
 4 | 
 5 | Welcome to the "Introduction to Exploratory Data Analysis (EDA)" course! This course will help you to effectively analyze and gain insights from various datasets.
 6 | 
 7 | ## Course Content
 8 | 
 9 | This course consists of the following modules:
10 | 
11 | 1. **Understanding your data:** Before starting analysis, we first understand the data.
12 | 
13 | 2. **Dealing with Missing Values:** Learn how to identify and handle missing data in a dataset using appropriate techniques.
14 | 
15 | 3. **Dealing with Duplicate Data:** Explore methods to detect and manage duplicate records in your data.
16 | 
17 | 4. **Dealing with Outliers:** Discover how to identify and handle outliers that can impact your analysis.
18 | 
19 | 5. **Correction of DataType:** According to the data and analysis, we will see how to change the datatype.
20 | 
21 | 6. **Univariate Analysis:** Learn how to perform univariate analysis to examine the distribution and characteristics of individual variables.
22 | 
23 | 11. **Univariate Analysis Visualization:** Discover visualization techniques for univariate analysis to gain deeper insights into data patterns.
24 | 
25 | 12. **Bivariate Analysis:** Understand how to perform bivariate analysis to explore relationships between two variables.
26 | 
27 | ## Code Files
28 | 
29 | The code files for each module are provided in this repository. These files contain hands-on examples and implementations of the concepts covered in the course. You can use these code files to practice and reinforce your understanding of EDA techniques.
30 | 
31 | ## Requirements
32 | 
33 | Before you begin the course, ensure you have the following:
34 | 
35 | - Basic knowledge of Python programming language (for running code examples).
36 | - Familiarity with data handling concepts and basic statistical methods.
37 | 
38 | ## How to Use the Code Files
39 | 
40 | 1. Clone or download this repository to your local machine.
41 | 2. Open the code files in your preferred Python IDE or Jupyter Notebook.
42 | 3. Experiment with the code and datasets to enhance your understanding.
43 | 


--------------------------------------------------------------------------------
/scholarship.csv:
--------------------------------------------------------------------------------
   1 | semester_percentage,scholarship_exam_marks,got_scholarship
   2 | 71.9,26,1
   3 | 74.6,38,1
   4 | 75.4,40,1
   5 | 64.2,8,1
   6 | 72.3,17,0
   7 | 73,23,1
   8 | 66.9,11,0
   9 | 71.2,39,1
  10 | 64.5,38,0
  11 | 77.5,94,1
  12 | 68.2,16,1
  13 | 63.8,7,1
  14 | 65.8,16,1
  15 | 56.8,26,0
  16 | 79.1,43,0
  17 | 71,21,0
  18 | 65.3,19,0
  19 | 75.6,22,1
  20 | 69.3,27,0
  21 | 76.3,29,0
  22 | 66.9,47,0
  23 | 74.3,33,1
  24 | 67.6,54,1
  25 | 60.5,11,0
  26 | 64.4,11,0
  27 | 62.8,58,1
  28 | 74.5,8,1
  29 | 65.3,46,0
  30 | 72.3,19,0
  31 | 65.1,15,1
  32 | 74.6,16,0
  33 | 76.6,44,0
  34 | 59.1,11,1
  35 | 62.3,27,0
  36 | 81.5,9,0
  37 | 74.8,12,0
  38 | 68.5,16,1
  39 | 85.1,9,1
  40 | 65.8,20,1
  41 | 72.5,17,0
  42 | 66,86,1
  43 | 67,38,0
  44 | 74.6,71,1
  45 | 78.5,63,0
  46 | 78.8,55,0
  47 | 69.2,10,1
  48 | 73,15,0
  49 | 69.2,46,0
  50 | 62.9,42,0
  51 | 82.3,28,1
  52 | 62,18,1
  53 | 62.4,28,1
  54 | 75.3,27,1
  55 | 66.9,33,1
  56 | 84.2,36,1
  57 | 81.2,15,0
  58 | 69.3,15,1
  59 | 77.3,24,0
  60 | 73.4,43,0
  61 | 77,32,1
  62 | 79.4,31,1
  63 | 75.1,86,0
  64 | 76.1,22,0
  65 | 62.2,26,0
  66 | 69.8,52,1
  67 | 62.7,28,1
  68 | 66.7,31,1
  69 | 80.4,18,1
  70 | 65.8,30,0
  71 | 74.1,44,0
  72 | 69.8,17,1
  73 | 61.3,20,1
  74 | 79,19,0
  75 | 63.9,12,1
  76 | 61.6,3,1
  77 | 67.7,56,1
  78 | 83.5,12,0
  79 | 71,28,1
  80 | 82,12,0
  81 | 76.3,19,1
  82 | 68.7,46,1
  83 | 71.2,44,1
  84 | 72.2,12,0
  85 | 73.8,20,1
  86 | 56.5,35,1
  87 | 60.3,28,0
  88 | 71.9,22,1
  89 | 69.6,19,1
  90 | 67.8,39,0
  91 | 65.6,17,0
  92 | 76.1,15,1
  93 | 74.2,6,1
  94 | 64.8,63,0
  95 | 70,30,0
  96 | 71.5,21,1
  97 | 68.9,35,1
  98 | 70.9,28,1
  99 | 73.3,52,1
 100 | 81.2,76,0
 101 | 74.6,23,0
 102 | 65.6,46,0
 103 | 64.8,26,1
 104 | 59.2,22,1
 105 | 64.4,18,1
 106 | 68.2,47,1
 107 | 67.2,12,1
 108 | 65.9,22,0
 109 | 73.2,9,0
 110 | 59.4,10,0
 111 | 72.3,21,1
 112 | 69.6,31,0
 113 | 64.8,33,0
 114 | 72.3,15,0
 115 | 72.4,10,0
 116 | 63,77,1
 117 | 72.8,37,0
 118 | 71.6,21,0
 119 | 71.1,0,1
 120 | 69,54,0
 121 | 70,39,0
 122 | 69.9,46,1
 123 | 59.1,27,0
 124 | 59.7,51,0
 125 | 62.5,52,0
 126 | 62,30,0
 127 | 74.6,55,1
 128 | 71.6,37,0
 129 | 69.5,23,1
 130 | 67.6,25,0
 131 | 68.1,39,1
 132 | 59.1,53,0
 133 | 81.9,19,1
 134 | 77.1,18,0
 135 | 76.5,64,1
 136 | 63.3,93,0
 137 | 66.3,47,0
 138 | 72.8,15,0
 139 | 56.9,53,0
 140 | 75.3,8,1
 141 | 80.9,5,1
 142 | 68.5,22,1
 143 | 71.9,18,0
 144 | 76.6,41,1
 145 | 63.2,33,1
 146 | 66.7,17,0
 147 | 70.8,28,0
 148 | 67.5,22,1
 149 | 66.8,11,0
 150 | 68.6,49,1
 151 | 68.1,58,0
 152 | 85.3,22,0
 153 | 72.9,16,1
 154 | 77.8,56,0
 155 | 62.9,10,1
 156 | 75.7,54,1
 157 | 78.4,12,0
 158 | 64,34,0
 159 | 70.7,81,1
 160 | 57.4,50,0
 161 | 67,22,0
 162 | 73.6,10,1
 163 | 62.6,52,1
 164 | 78,90,0
 165 | 67.7,42,1
 166 | 62.9,34,1
 167 | 75.3,7,0
 168 | 77.6,59,0
 169 | 66.5,48,1
 170 | 65.1,37,1
 171 | 61.9,16,1
 172 | 61.7,37,0
 173 | 62,38,1
 174 | 72.4,43,1
 175 | 67.1,48,0
 176 | 73.1,21,1
 177 | 75.7,26,1
 178 | 77.2,30,1
 179 | 62.2,40,1
 180 | 75.1,39,0
 181 | 64,45,1
 182 | 71.8,29,0
 183 | 73,42,0
 184 | 68.7,76,0
 185 | 61.1,18,1
 186 | 77.8,33,0
 187 | 73,31,0
 188 | 69.7,63,1
 189 | 66.3,10,1
 190 | 59.2,55,1
 191 | 66.3,9,0
 192 | 75.4,23,0
 193 | 66.3,8,0
 194 | 66.7,38,0
 195 | 63.1,14,0
 196 | 81.9,33,0
 197 | 67.1,44,0
 198 | 72.8,34,1
 199 | 67.5,27,0
 200 | 82.9,44,1
 201 | 74.3,25,1
 202 | 57.7,22,0
 203 | 66.7,15,0
 204 | 65.1,48,1
 205 | 79.3,52,0
 206 | 70.1,5,1
 207 | 69.9,47,1
 208 | 75,25,0
 209 | 70.5,16,0
 210 | 72.5,12,1
 211 | 68.8,35,0
 212 | 65.8,19,1
 213 | 73.6,14,0
 214 | 62.3,57,0
 215 | 66.2,19,1
 216 | 74.2,60,1
 217 | 77.2,22,0
 218 | 54.2,36,1
 219 | 69.2,16,0
 220 | 66.2,52,0
 221 | 54.8,3,0
 222 | 77.5,16,1
 223 | 67.8,24,1
 224 | 69.7,78,0
 225 | 61.5,11,1
 226 | 71.5,19,0
 227 | 73.6,13,1
 228 | 67.9,21,1
 229 | 70.3,19,0
 230 | 76.1,15,0
 231 | 66.8,13,0
 232 | 71.2,14,1
 233 | 64,35,0
 234 | 77.7,34,0
 235 | 72.5,41,0
 236 | 80.9,36,0
 237 | 72,52,1
 238 | 77,36,1
 239 | 71.4,52,1
 240 | 74.1,78,0
 241 | 67.1,16,1
 242 | 72.5,38,0
 243 | 72.2,18,0
 244 | 59.9,44,0
 245 | 67.8,55,0
 246 | 76.8,44,0
 247 | 67.8,62,0
 248 | 76.7,26,0
 249 | 62.5,49,0
 250 | 69,44,0
 251 | 74.6,52,0
 252 | 74,13,1
 253 | 64.6,45,0
 254 | 62.4,54,1
 255 | 69.8,76,0
 256 | 67,64,0
 257 | 77.6,10,0
 258 | 73.7,48,1
 259 | 57.4,76,0
 260 | 61.2,6,1
 261 | 71.6,10,0
 262 | 56.6,57,1
 263 | 71.7,11,1
 264 | 71.9,10,1
 265 | 81.1,50,1
 266 | 78.2,28,1
 267 | 69.4,57,0
 268 | 77.3,50,1
 269 | 60,65,0
 270 | 73.8,21,0
 271 | 64.7,16,0
 272 | 68,16,1
 273 | 76.4,21,1
 274 | 62.3,56,1
 275 | 70,9,0
 276 | 71.3,4,1
 277 | 80.3,39,0
 278 | 69.6,46,0
 279 | 64.5,15,1
 280 | 52.3,17,1
 281 | 84.9,40,1
 282 | 66.2,55,0
 283 | 76.8,22,1
 284 | 64.3,44,1
 285 | 70.9,87,0
 286 | 69.9,62,1
 287 | 74.2,57,1
 288 | 62.9,58,1
 289 | 62.4,24,1
 290 | 70.7,21,0
 291 | 67.3,9,1
 292 | 83.8,87,0
 293 | 74.6,14,1
 294 | 58.2,41,0
 295 | 69.7,11,1
 296 | 61.2,17,0
 297 | 60.2,64,0
 298 | 69.9,19,0
 299 | 70.3,32,1
 300 | 61.6,48,0
 301 | 67.5,15,1
 302 | 73.6,52,1
 303 | 78.4,5,1
 304 | 79.5,34,0
 305 | 73.5,56,0
 306 | 71.2,33,1
 307 | 66.7,32,1
 308 | 68.6,19,0
 309 | 74.7,28,1
 310 | 72,47,1
 311 | 74.6,31,1
 312 | 55.6,50,0
 313 | 69.7,87,1
 314 | 70.2,55,1
 315 | 65.1,18,1
 316 | 74.3,14,1
 317 | 79.6,37,0
 318 | 70.7,38,1
 319 | 74.7,19,0
 320 | 67.4,60,0
 321 | 75.3,13,0
 322 | 71.8,51,1
 323 | 68.2,47,0
 324 | 67.7,38,1
 325 | 66,38,0
 326 | 66.4,90,0
 327 | 66.5,13,0
 328 | 75.4,13,0
 329 | 82.1,56,0
 330 | 74,28,1
 331 | 73,35,0
 332 | 66.8,16,1
 333 | 61.2,22,1
 334 | 70.3,39,0
 335 | 67.4,20,1
 336 | 65.6,19,1
 337 | 69,17,1
 338 | 79.3,9,1
 339 | 69.5,68,0
 340 | 74.5,46,1
 341 | 73.2,18,1
 342 | 74.5,51,0
 343 | 74.1,8,1
 344 | 63.7,23,0
 345 | 72,70,1
 346 | 72,26,1
 347 | 62.6,13,1
 348 | 73.1,33,0
 349 | 72.4,34,1
 350 | 61.3,17,1
 351 | 81.2,16,0
 352 | 72.1,70,0
 353 | 69.2,10,0
 354 | 65.1,4,1
 355 | 68.2,28,1
 356 | 67.3,23,1
 357 | 64.2,18,1
 358 | 59.1,50,1
 359 | 79.2,42,1
 360 | 67.4,52,0
 361 | 76.1,40,0
 362 | 72.4,33,0
 363 | 63.7,37,1
 364 | 72.5,21,1
 365 | 76.1,13,0
 366 | 68.7,9,1
 367 | 70.7,25,0
 368 | 67.8,42,0
 369 | 64.1,30,0
 370 | 70.9,32,0
 371 | 66.9,36,1
 372 | 57,79,1
 373 | 59,29,0
 374 | 59.5,8,0
 375 | 55.8,41,0
 376 | 73.4,41,0
 377 | 73.1,31,0
 378 | 62.5,60,0
 379 | 67,47,1
 380 | 72.7,25,1
 381 | 73.7,65,0
 382 | 71.2,31,1
 383 | 61.7,53,0
 384 | 75.5,61,0
 385 | 72.6,4,1
 386 | 70.3,33,0
 387 | 73.3,21,0
 388 | 76.3,43,0
 389 | 72.5,7,1
 390 | 72.8,23,0
 391 | 59,16,1
 392 | 66.3,16,1
 393 | 77.7,66,1
 394 | 67.6,35,0
 395 | 66,18,0
 396 | 79.4,18,1
 397 | 72.9,11,0
 398 | 72.8,10,1
 399 | 75.5,63,0
 400 | 75.5,48,0
 401 | 57.4,43,1
 402 | 60,33,1
 403 | 67.4,22,0
 404 | 60.8,34,1
 405 | 67.1,83,0
 406 | 80.2,35,1
 407 | 66,32,1
 408 | 71.4,17,1
 409 | 82.3,20,1
 410 | 78,24,1
 411 | 69.2,24,0
 412 | 73.6,37,1
 413 | 60.4,66,0
 414 | 65,45,1
 415 | 66.5,28,1
 416 | 73,36,1
 417 | 63.7,46,1
 418 | 75.1,55,1
 419 | 69,19,0
 420 | 63,29,0
 421 | 62.2,46,0
 422 | 75.9,49,0
 423 | 62.9,46,0
 424 | 70.9,19,0
 425 | 82.7,26,0
 426 | 69.1,30,0
 427 | 74.5,15,0
 428 | 72.6,21,0
 429 | 61.7,39,1
 430 | 78.9,46,0
 431 | 73.5,55,0
 432 | 72.2,19,1
 433 | 76.4,21,0
 434 | 66.7,26,1
 435 | 57.7,11,1
 436 | 70.1,5,0
 437 | 74.5,37,0
 438 | 63.1,19,0
 439 | 67.3,22,0
 440 | 73.1,7,0
 441 | 66.7,10,1
 442 | 85.6,22,0
 443 | 78,15,1
 444 | 70.8,48,1
 445 | 69.2,77,0
 446 | 66.6,14,1
 447 | 55.6,10,0
 448 | 66,23,1
 449 | 65,17,1
 450 | 63.2,31,0
 451 | 62.1,37,0
 452 | 64.4,31,1
 453 | 59.4,31,0
 454 | 65.9,42,1
 455 | 73.1,24,1
 456 | 71.3,53,0
 457 | 69.2,43,0
 458 | 67.6,12,1
 459 | 65.8,20,0
 460 | 71.3,47,0
 461 | 66.2,79,1
 462 | 69.1,4,1
 463 | 73.9,12,0
 464 | 67.1,9,1
 465 | 68.2,49,1
 466 | 62.8,37,1
 467 | 76.5,49,0
 468 | 64.5,16,0
 469 | 66.5,7,0
 470 | 67.3,70,0
 471 | 58.6,46,1
 472 | 64.6,28,0
 473 | 54.8,18,0
 474 | 61.9,38,1
 475 | 63.8,25,0
 476 | 71.1,25,1
 477 | 73.8,10,0
 478 | 68.3,34,0
 479 | 57.8,18,0
 480 | 73.2,36,1
 481 | 63.8,33,0
 482 | 68,37,0
 483 | 73.3,32,0
 484 | 75.6,8,0
 485 | 79.3,25,0
 486 | 58.1,18,0
 487 | 49.2,44,1
 488 | 76.7,65,1
 489 | 69.5,13,0
 490 | 67.5,43,0
 491 | 72.4,50,0
 492 | 73.4,32,0
 493 | 77.7,49,1
 494 | 85,21,1
 495 | 68,18,0
 496 | 68.3,51,0
 497 | 69.5,64,1
 498 | 75.2,35,1
 499 | 68,37,1
 500 | 68.9,14,0
 501 | 64.2,31,0
 502 | 60.7,24,1
 503 | 65.2,31,0
 504 | 71.8,50,1
 505 | 69.7,10,1
 506 | 72.4,25,0
 507 | 64.8,18,1
 508 | 78.4,8,1
 509 | 67.7,75,1
 510 | 64.1,14,1
 511 | 78.3,48,0
 512 | 68.4,34,1
 513 | 75.3,50,0
 514 | 70.8,9,1
 515 | 64.3,46,0
 516 | 73.6,15,0
 517 | 77.5,44,0
 518 | 68.3,28,0
 519 | 63.7,38,1
 520 | 75.3,22,0
 521 | 66,8,1
 522 | 73.9,20,1
 523 | 57.2,37,1
 524 | 67.1,63,1
 525 | 61.3,19,0
 526 | 68.5,21,0
 527 | 63.3,17,0
 528 | 71.2,34,0
 529 | 77.2,37,0
 530 | 69,38,1
 531 | 71.9,34,0
 532 | 62.8,18,1
 533 | 70,81,1
 534 | 69,20,0
 535 | 71.9,15,0
 536 | 60.5,45,1
 537 | 64.9,62,0
 538 | 68.7,48,1
 539 | 71.3,9,1
 540 | 75.8,27,0
 541 | 67.9,14,0
 542 | 63.7,63,0
 543 | 61.1,18,1
 544 | 70.6,22,0
 545 | 74.8,16,0
 546 | 71.1,14,1
 547 | 63.5,17,1
 548 | 67.5,18,1
 549 | 73.3,39,0
 550 | 74.8,30,1
 551 | 73.7,79,1
 552 | 66.2,38,1
 553 | 65.5,66,1
 554 | 64,24,0
 555 | 74.6,17,0
 556 | 68.4,9,1
 557 | 64.6,32,0
 558 | 67,15,1
 559 | 64.7,25,0
 560 | 72.8,14,0
 561 | 66.1,58,1
 562 | 71.1,67,0
 563 | 70.7,58,0
 564 | 60.6,23,0
 565 | 68.1,14,1
 566 | 71.7,34,1
 567 | 66.1,54,1
 568 | 60.3,25,0
 569 | 61.8,36,1
 570 | 81.3,4,0
 571 | 70.8,30,0
 572 | 70.4,18,0
 573 | 64.7,66,1
 574 | 76.6,37,1
 575 | 72.3,54,1
 576 | 65.4,33,0
 577 | 75.5,16,0
 578 | 61.2,8,1
 579 | 68.5,24,1
 580 | 75.2,47,0
 581 | 71.3,13,0
 582 | 79,63,1
 583 | 65.7,25,0
 584 | 70.5,27,1
 585 | 71,68,0
 586 | 65.7,60,1
 587 | 78.5,49,1
 588 | 65.8,15,0
 589 | 75.8,14,1
 590 | 63.8,25,0
 591 | 66,16,0
 592 | 66.8,22,1
 593 | 78.9,35,0
 594 | 70.9,27,1
 595 | 65.5,62,0
 596 | 69.5,64,0
 597 | 61.3,7,1
 598 | 84.8,25,1
 599 | 78.5,32,0
 600 | 75.9,27,1
 601 | 70.2,55,0
 602 | 62.4,38,1
 603 | 68.9,17,1
 604 | 71.6,32,0
 605 | 65.5,54,1
 606 | 68.9,40,1
 607 | 66.4,42,0
 608 | 67.9,24,0
 609 | 77.6,49,1
 610 | 73.3,16,1
 611 | 65.5,4,0
 612 | 73.2,61,1
 613 | 72,19,1
 614 | 61.4,60,1
 615 | 66.6,55,1
 616 | 80.5,41,0
 617 | 65.1,12,0
 618 | 70.9,33,1
 619 | 70.8,22,0
 620 | 67,22,0
 621 | 68.1,43,0
 622 | 70.7,18,1
 623 | 78.5,28,1
 624 | 74,19,1
 625 | 73.5,14,1
 626 | 73.5,80,1
 627 | 76,30,1
 628 | 76.3,19,1
 629 | 63.1,30,1
 630 | 71.2,9,0
 631 | 81.5,11,1
 632 | 65.6,96,1
 633 | 72.6,16,0
 634 | 63.7,13,0
 635 | 66.3,39,1
 636 | 76.9,39,0
 637 | 66.9,10,0
 638 | 63.9,43,1
 639 | 72.5,74,0
 640 | 74.6,74,1
 641 | 64.2,43,1
 642 | 63.6,61,1
 643 | 74.9,22,0
 644 | 78.9,39,1
 645 | 75.9,28,0
 646 | 76.5,29,1
 647 | 67.5,36,0
 648 | 73.8,45,1
 649 | 66.9,4,1
 650 | 71.5,24,0
 651 | 76,65,1
 652 | 61.9,27,0
 653 | 65.7,39,1
 654 | 76,43,1
 655 | 69.3,48,0
 656 | 70.3,76,0
 657 | 73.6,34,0
 658 | 73.9,72,1
 659 | 76,23,0
 660 | 75.7,9,0
 661 | 66.8,37,0
 662 | 59.7,26,1
 663 | 57.2,47,0
 664 | 73.8,15,1
 665 | 70.5,31,1
 666 | 72.3,34,0
 667 | 61.6,10,0
 668 | 76.4,27,1
 669 | 71.7,54,0
 670 | 72.4,47,0
 671 | 69.4,8,1
 672 | 75.1,17,1
 673 | 74.5,31,0
 674 | 77.5,13,0
 675 | 68.7,20,0
 676 | 67.3,31,1
 677 | 61,20,0
 678 | 67.3,21,1
 679 | 67.5,24,0
 680 | 66.5,34,1
 681 | 67,35,0
 682 | 73.5,15,0
 683 | 67.8,10,1
 684 | 63.4,17,1
 685 | 65,69,0
 686 | 80.2,67,0
 687 | 60.5,87,1
 688 | 71.5,62,1
 689 | 68.1,23,0
 690 | 65.9,36,0
 691 | 80.2,67,0
 692 | 70.1,26,0
 693 | 73.2,14,0
 694 | 69.5,43,0
 695 | 66.4,42,1
 696 | 71.2,51,0
 697 | 67.5,11,1
 698 | 69.4,20,0
 699 | 72.3,49,1
 700 | 72.7,16,0
 701 | 66.4,20,0
 702 | 68.2,16,1
 703 | 67.4,2,1
 704 | 62.4,39,0
 705 | 70.4,41,0
 706 | 69.1,45,1
 707 | 65.5,35,1
 708 | 71.1,13,1
 709 | 68.6,11,1
 710 | 79.1,50,0
 711 | 69.7,42,1
 712 | 75.6,6,1
 713 | 69.7,30,1
 714 | 63.5,8,1
 715 | 78,24,0
 716 | 70.6,19,1
 717 | 74.1,17,1
 718 | 70.6,19,1
 719 | 64.9,21,0
 720 | 71.2,36,1
 721 | 71.7,26,0
 722 | 68.7,43,0
 723 | 69.8,11,0
 724 | 68.6,29,0
 725 | 73.5,10,1
 726 | 79.5,21,0
 727 | 63.4,10,0
 728 | 79.3,25,0
 729 | 70,30,0
 730 | 66.3,23,0
 731 | 67.9,58,1
 732 | 61.4,90,1
 733 | 67.4,5,0
 734 | 72.6,55,1
 735 | 70.7,10,0
 736 | 67.7,50,1
 737 | 72.3,39,1
 738 | 68.6,24,1
 739 | 65.2,12,1
 740 | 70.4,17,1
 741 | 63.4,39,0
 742 | 62.1,74,1
 743 | 75.8,66,0
 744 | 67.9,29,0
 745 | 76.2,15,1
 746 | 74.9,58,0
 747 | 68.2,13,1
 748 | 67.2,25,1
 749 | 62.6,18,0
 750 | 70.2,9,0
 751 | 73.1,61,1
 752 | 64.3,8,1
 753 | 66.9,20,1
 754 | 73.7,35,0
 755 | 68.7,42,0
 756 | 79.1,17,0
 757 | 69.4,26,0
 758 | 74.1,30,1
 759 | 68.4,15,0
 760 | 65.5,29,0
 761 | 65.5,22,1
 762 | 71.3,48,1
 763 | 80.2,6,0
 764 | 67.9,14,1
 765 | 71.6,59,1
 766 | 64.7,70,1
 767 | 65.5,28,0
 768 | 71.7,34,0
 769 | 73.3,31,0
 770 | 65.5,63,1
 771 | 66.8,18,1
 772 | 73.3,67,1
 773 | 73.1,86,1
 774 | 66.3,26,0
 775 | 80.6,79,0
 776 | 69.3,69,0
 777 | 67.6,24,0
 778 | 70.8,30,0
 779 | 76.7,23,0
 780 | 69.8,34,0
 781 | 63.9,32,0
 782 | 56.2,31,0
 783 | 71.7,49,1
 784 | 76.5,41,0
 785 | 62.3,24,1
 786 | 61.9,19,0
 787 | 60.7,29,1
 788 | 75,10,1
 789 | 70.2,9,0
 790 | 65.4,19,0
 791 | 64.6,74,0
 792 | 74.8,47,0
 793 | 76.5,12,1
 794 | 79.2,32,0
 795 | 72.3,9,0
 796 | 62.4,17,1
 797 | 70,9,1
 798 | 60.2,60,0
 799 | 81.4,20,1
 800 | 58.6,56,0
 801 | 68.9,53,1
 802 | 65,28,0
 803 | 63.1,14,0
 804 | 61,16,0
 805 | 71.9,20,1
 806 | 64.9,81,0
 807 | 62.3,13,0
 808 | 63.9,15,0
 809 | 71.6,19,1
 810 | 76.8,31,0
 811 | 63.9,22,1
 812 | 71.4,21,1
 813 | 80.4,14,0
 814 | 59.9,23,0
 815 | 74.3,52,1
 816 | 77.8,17,1
 817 | 52.7,43,0
 818 | 71.9,23,1
 819 | 78.4,26,0
 820 | 55.2,62,0
 821 | 69.3,10,0
 822 | 62.7,16,0
 823 | 61,9,0
 824 | 73.3,32,1
 825 | 66.7,18,0
 826 | 74.8,27,1
 827 | 63,23,0
 828 | 70.5,32,0
 829 | 64.6,21,0
 830 | 64.4,63,1
 831 | 68.7,37,0
 832 | 64.6,28,0
 833 | 68.1,55,1
 834 | 69.1,59,0
 835 | 72.9,23,1
 836 | 62.2,52,1
 837 | 66.7,65,1
 838 | 70.9,33,1
 839 | 66.5,24,0
 840 | 68.4,32,0
 841 | 64.4,24,1
 842 | 68.9,22,1
 843 | 74.5,27,1
 844 | 73.3,14,1
 845 | 63.1,60,0
 846 | 76.2,18,1
 847 | 59.8,36,0
 848 | 69.9,97,0
 849 | 72,54,1
 850 | 72,27,1
 851 | 78.9,8,1
 852 | 83.9,37,1
 853 | 62.9,17,0
 854 | 65.4,43,1
 855 | 77.4,22,0
 856 | 58.3,68,1
 857 | 78.9,9,1
 858 | 75.2,6,1
 859 | 57.2,64,1
 860 | 75.1,26,0
 861 | 65.2,22,0
 862 | 75.1,21,0
 863 | 63.2,28,0
 864 | 60.4,37,1
 865 | 80.4,2,1
 866 | 63.2,5,0
 867 | 67.7,16,0
 868 | 72.9,35,0
 869 | 80.4,26,0
 870 | 73.3,36,0
 871 | 55.1,58,1
 872 | 66.7,15,1
 873 | 65.6,60,0
 874 | 69.5,54,0
 875 | 79,42,1
 876 | 66,24,0
 877 | 57.3,16,1
 878 | 63.3,20,0
 879 | 63.2,9,0
 880 | 69.8,34,0
 881 | 68.3,31,0
 882 | 64,13,0
 883 | 77.2,42,0
 884 | 72.5,35,1
 885 | 79.8,6,1
 886 | 71.1,4,1
 887 | 71.3,16,1
 888 | 72.2,17,1
 889 | 71.9,17,1
 890 | 76.2,23,1
 891 | 73.9,38,0
 892 | 77.3,30,0
 893 | 74.2,26,1
 894 | 59.6,18,1
 895 | 70.7,32,1
 896 | 65,16,0
 897 | 78.2,35,1
 898 | 57.3,38,0
 899 | 71.3,35,1
 900 | 71.4,18,1
 901 | 76.2,8,1
 902 | 60.8,19,1
 903 | 71,50,1
 904 | 70.3,42,1
 905 | 75.6,28,1
 906 | 73.6,32,0
 907 | 70.8,29,0
 908 | 75.6,34,1
 909 | 70.3,44,1
 910 | 60.6,17,1
 911 | 65.7,11,1
 912 | 78.2,29,1
 913 | 74.5,36,1
 914 | 74.8,38,1
 915 | 67.8,7,1
 916 | 69.7,25,0
 917 | 68.8,34,0
 918 | 68.8,11,1
 919 | 59.5,100,0
 920 | 70.9,9,0
 921 | 65.9,21,0
 922 | 79.7,52,1
 923 | 69.1,38,1
 924 | 76.8,23,1
 925 | 65.2,10,0
 926 | 68.5,23,1
 927 | 69.1,56,1
 928 | 70.2,14,0
 929 | 73.7,52,1
 930 | 66.3,32,0
 931 | 68.9,25,0
 932 | 69.4,7,1
 933 | 71.9,33,0
 934 | 68.9,71,0
 935 | 60.1,9,0
 936 | 71.5,9,0
 937 | 81.2,37,1
 938 | 73.2,20,0
 939 | 64.2,34,0
 940 | 62.7,24,0
 941 | 69.8,41,0
 942 | 61.6,38,0
 943 | 71.8,8,0
 944 | 70.3,6,0
 945 | 73.6,2,0
 946 | 72.1,21,1
 947 | 67.1,26,1
 948 | 79.5,12,0
 949 | 64.9,70,0
 950 | 63.8,15,0
 951 | 79.4,11,0
 952 | 66.5,33,1
 953 | 75.2,48,1
 954 | 77.1,25,1
 955 | 69.1,44,0
 956 | 80,39,1
 957 | 72,26,1
 958 | 68.6,21,0
 959 | 65.1,27,1
 960 | 74.3,11,0
 961 | 67.6,27,1
 962 | 68.1,10,1
 963 | 76.5,9,0
 964 | 70.9,46,1
 965 | 67.4,8,0
 966 | 80.9,54,1
 967 | 73.7,52,1
 968 | 62.4,72,1
 969 | 73.5,59,0
 970 | 68.4,26,0
 971 | 68.6,41,0
 972 | 72.8,42,1
 973 | 66.9,18,1
 974 | 70.2,18,0
 975 | 61,37,1
 976 | 64.2,38,0
 977 | 84.3,25,1
 978 | 69.6,48,0
 979 | 71.8,49,0
 980 | 67.8,12,0
 981 | 70,13,1
 982 | 61.8,27,0
 983 | 80.6,37,0
 984 | 68.7,22,0
 985 | 68.1,11,1
 986 | 68.9,16,1
 987 | 71,26,0
 988 | 70.9,19,1
 989 | 67.7,62,0
 990 | 56.4,37,1
 991 | 62.3,31,0
 992 | 61.7,33,1
 993 | 70.4,57,0
 994 | 62.6,12,0
 995 | 67.3,21,1
 996 | 64.8,63,0
 997 | 88.7,44,1
 998 | 91.2,65,1
 999 | 48.9,34,0
1000 | 86.2,46,1
1001 | 49,10,1
1002 | 


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