├── README.md
└── PandasByMLM.ipynb


/README.md:
--------------------------------------------------------------------------------
 1 | # Python-Course-PL-II
 2 | 
 3 | **Vision, Mission and PEOs Vision of the Institute**
 4 | 
 5 | To achieve excellence in engineering education with strong ethical values.
 6 | 
 7 | **Mission of the Institute**
 8 | 
 9 | To impart high quality Technical Education through :
10 | 
11 | *Innovative and Interactive learning process and high quality, internationally recognized instructional programs.
12 | 
13 | *Fostering a scientific temper among students by the means of a liaison with the Academia, Industries and Government.
14 | 
15 | *Preparing students from diverse backgrounds to have aptitude for research and spirit of Professionalism.
16 | 
17 | *Inculcating in students a respect for fellow human beings and responsibility towards the society.
18 | 
19 | **Vision of the Department**
20 | 
21 | To provide prominent computer engineering education with socio-moral values.​
22 | 
23 | **Mission of the Department**
24 | 
25 | M1- To provide state-of-the-art ICT based teaching-learning process.
26 | 
27 | M2- To groom the students to become professionally sound computer engineers to meet growing needs of industry and society.
28 | 
29 | M3- To make the students responsible human being by inculcating ethical values.
30 | 
31 | **Program Educational Objectives (PEOs) of the Department**
32 | 
33 | PEO 1 – To provide the foundation of lifelong learning skills for advancing their careers being a professional, entrepreneur and leader.
34 | 
35 | PEO 2 – To develop computer professionals to fulfill industry expectations.
36 | 
37 | PEO 3 – To foster ethical and social values to be socially responsible human being.
38 | 


--------------------------------------------------------------------------------
/PandasByMLM.ipynb:
--------------------------------------------------------------------------------
   1 | {
   2 |   "nbformat": 4,
   3 |   "nbformat_minor": 0,
   4 |   "metadata": {
   5 |     "colab": {
   6 |       "provenance": []
   7 |     },
   8 |     "kernelspec": {
   9 |       "name": "python3",
  10 |       "display_name": "Python 3"
  11 |     },
  12 |     "language_info": {
  13 |       "name": "python"
  14 |     }
  15 |   },
  16 |   "cells": [
  17 |     {
  18 |       "cell_type": "markdown",
  19 |       "source": [
  20 |         "**Pandas Introduction**\n",
  21 |         "\n",
  22 |         "The name of Pandas is gotten from the word Board Information, and that implies an Econometrics from Multi-faceted information. It was created in 2008 by Wes McKinney and is used for data analysis in Python.\n",
  23 |         "\n",
  24 |         "Processing, such as restructuring, cleaning, merging, etc., is necessary for data analysis. Numpy, Scipy, Cython, and Panda are just a few of the fast data processing tools available. Yet, we incline toward Pandas since working with Pandas is quick, basic and more expressive than different apparatuses.\n",
  25 |         "\n",
  26 |         "**Key Features of Pandas**\n",
  27 |         "\n",
  28 |         "-It has a DataFrame object that is quick and effective, with both standard and custom indexing.\n",
  29 |         "\n",
  30 |         "-Utilized for reshaping and turning of the informational indexes.\n",
  31 |         "\n",
  32 |         "-For aggregations and transformations, group by data.\n",
  33 |         "\n",
  34 |         "-It is used to align the data and integrate the data that is missing.\n",
  35 |         "\n",
  36 |         "-Provide Time Series functionality.\n",
  37 |         "\n",
  38 |         "-Process a variety of data sets in various formats, such as matrix data, heterogeneous tabular data, and time series.\n",
  39 |         "\n",
  40 |         "-Manage the data sets' multiple operations, including subsetting, slicing, filtering, groupBy, reordering, and reshaping.\n",
  41 |         "\n",
  42 |         "-It incorporates with different libraries like SciPy, and scikit-learn.\n",
  43 |         "\n",
  44 |         "-Performs quickly, and the Cython can be used to accelerate it even further.\n",
  45 |         "\n",
  46 |         "**Benefits of Pandas**\n",
  47 |         "\n",
  48 |         "The following are the advantages of pandas overusing other languages:\n",
  49 |         "\n",
  50 |         "**Representation of Data:**\n",
  51 |         " Through its DataFrame and Series, it presents the data in a manner that is appropriate for data analysis.\n",
  52 |         "\n",
  53 |         "**Clear code:**\n",
  54 |         "Pandas' clear API lets you concentrate on the most important part of the code. In this way, it gives clear and brief code to the client.\n",
  55 |         "\n",
  56 |         "DataFrame and Series are the two data structures that Pandas provides for processing data. These data structures are discussed below:\n",
  57 |         "\n",
  58 |         "**Install and import**\n",
  59 |         "\n",
  60 |         "Pandas is an easy package to install. Open up your terminal program (for Mac users) or command line (for PC users) and install it using either of the following commands:\n",
  61 |         "\n",
  62 |         "`conda install pandas`\n",
  63 |         "\n",
  64 |         "OR\n",
  65 |         "\n",
  66 |         "`pip install pandas`\n",
  67 |         "\n",
  68 |         "Alternatively, if you're currently viewing this article in a Jupyter notebook you can run this cell:\n",
  69 |         "\n",
  70 |         "`!pip install pandas`\n",
  71 |         "\n",
  72 |         "Core components of pandas: **Series and DataFrames**\n",
  73 |         "\n",
  74 |         "The primary two components of pandas are the Series and DataFrame.\n",
  75 |         "\n",
  76 |         "A Series is essentially a column, and a DataFrame is a multi-dimensional table made up of a collection of Series.\n",
  77 |         "![series-and-dataframe.width-1200.png](data:image/png;base64,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)"
  78 |       ],
  79 |       "metadata": {
  80 |         "id": "tEc4CSjPh2ME"
  81 |       }
  82 |     },
  83 |     {
  84 |       "cell_type": "code",
  85 |       "execution_count": null,
  86 |       "metadata": {
  87 |         "id": "gdK1wbTThokG"
  88 |       },
  89 |       "outputs": [],
  90 |       "source": [
  91 |         "!pip install pandas"
  92 |       ]
  93 |     },
  94 |     {
  95 |       "cell_type": "markdown",
  96 |       "source": [
  97 |         "**Pandas as pd**\n",
  98 |         "\n",
  99 |         "Pandas is usually imported under the pd alias."
 100 |       ],
 101 |       "metadata": {
 102 |         "id": "GxeYcuZjmwvA"
 103 |       }
 104 |     },
 105 |     {
 106 |       "cell_type": "code",
 107 |       "source": [
 108 |         "import pandas as pd\n",
 109 |         "\n",
 110 |         "mydataset = {\n",
 111 |         "  'cars': [\"BMW\", \"Volvo\", \"Ford\"],\n",
 112 |         "  'passings': [3, 7, 2]\n",
 113 |         "}\n",
 114 |         "\n",
 115 |         "myvar = pd.DataFrame(mydataset)\n",
 116 |         "\n",
 117 |         "print(myvar)"
 118 |       ],
 119 |       "metadata": {
 120 |         "id": "iM3QwN3fxGvq",
 121 |         "colab": {
 122 |           "base_uri": "https://localhost:8080/"
 123 |         },
 124 |         "outputId": "18b75eb8-d065-40d4-f806-060c04e3047c"
 125 |       },
 126 |       "execution_count": 1,
 127 |       "outputs": [
 128 |         {
 129 |           "output_type": "stream",
 130 |           "name": "stdout",
 131 |           "text": [
 132 |             "    cars  passings\n",
 133 |             "0    BMW         3\n",
 134 |             "1  Volvo         7\n",
 135 |             "2   Ford         2\n"
 136 |           ]
 137 |         }
 138 |       ]
 139 |     },
 140 |     {
 141 |       "cell_type": "markdown",
 142 |       "source": [
 143 |         "**What is a Series?**\n",
 144 |         "\n",
 145 |         "A Pandas Series is like a column in a table.\n",
 146 |         "\n",
 147 |         "It is a one-dimensional array holding data of any type."
 148 |       ],
 149 |       "metadata": {
 150 |         "id": "QRaaOzONxUe4"
 151 |       }
 152 |     },
 153 |     {
 154 |       "cell_type": "code",
 155 |       "source": [
 156 |         "import pandas as pd\n",
 157 |         "\n",
 158 |         "a = [1, 7, 2]\n",
 159 |         "\n",
 160 |         "myvar = pd.Series(a)\n",
 161 |         "\n",
 162 |         "print(myvar)"
 163 |       ],
 164 |       "metadata": {
 165 |         "id": "J3g4mmhexW1b",
 166 |         "colab": {
 167 |           "base_uri": "https://localhost:8080/"
 168 |         },
 169 |         "outputId": "23f94146-d729-4006-9d06-6011a5820d68"
 170 |       },
 171 |       "execution_count": 2,
 172 |       "outputs": [
 173 |         {
 174 |           "output_type": "stream",
 175 |           "name": "stdout",
 176 |           "text": [
 177 |             "0    1\n",
 178 |             "1    7\n",
 179 |             "2    2\n",
 180 |             "dtype: int64\n"
 181 |           ]
 182 |         }
 183 |       ]
 184 |     },
 185 |     {
 186 |       "cell_type": "markdown",
 187 |       "source": [
 188 |         "**Labels**\n",
 189 |         "\n",
 190 |         "If nothing else is specified, the values are labeled with their index number. First value has index 0, second value has index 1 etc.\n",
 191 |         "\n",
 192 |         "This label can be used to access a specified value."
 193 |       ],
 194 |       "metadata": {
 195 |         "id": "kQD5gMbuxoPp"
 196 |       }
 197 |     },
 198 |     {
 199 |       "cell_type": "code",
 200 |       "source": [
 201 |         "print(myvar[0])"
 202 |       ],
 203 |       "metadata": {
 204 |         "id": "6Qz3OB5kxtzB",
 205 |         "colab": {
 206 |           "base_uri": "https://localhost:8080/"
 207 |         },
 208 |         "outputId": "cab5ae52-dc55-4b3d-f314-3871c9803c3a"
 209 |       },
 210 |       "execution_count": 3,
 211 |       "outputs": [
 212 |         {
 213 |           "output_type": "stream",
 214 |           "name": "stdout",
 215 |           "text": [
 216 |             "1\n"
 217 |           ]
 218 |         }
 219 |       ]
 220 |     },
 221 |     {
 222 |       "cell_type": "markdown",
 223 |       "source": [
 224 |         "**Create Labels**\n",
 225 |         "\n",
 226 |         "With the index argument, you can name your own labels."
 227 |       ],
 228 |       "metadata": {
 229 |         "id": "At7mvmO1xv5Z"
 230 |       }
 231 |     },
 232 |     {
 233 |       "cell_type": "code",
 234 |       "source": [
 235 |         "import pandas as pd\n",
 236 |         "\n",
 237 |         "a = [1, 7, 2]\n",
 238 |         "\n",
 239 |         "myvar = pd.Series(a, index = [\"x\", \"y\", \"z\"])\n",
 240 |         "\n",
 241 |         "print(myvar)"
 242 |       ],
 243 |       "metadata": {
 244 |         "id": "5zzizT5px0b4",
 245 |         "colab": {
 246 |           "base_uri": "https://localhost:8080/"
 247 |         },
 248 |         "outputId": "0f125c58-ebf2-4b58-8816-9c4ad0cedd66"
 249 |       },
 250 |       "execution_count": 4,
 251 |       "outputs": [
 252 |         {
 253 |           "output_type": "stream",
 254 |           "name": "stdout",
 255 |           "text": [
 256 |             "x    1\n",
 257 |             "y    7\n",
 258 |             "z    2\n",
 259 |             "dtype: int64\n"
 260 |           ]
 261 |         }
 262 |       ]
 263 |     },
 264 |     {
 265 |       "cell_type": "markdown",
 266 |       "source": [
 267 |         "When you have created labels, you can access an item by referring to the label."
 268 |       ],
 269 |       "metadata": {
 270 |         "id": "mE7rBOQPx1i5"
 271 |       }
 272 |     },
 273 |     {
 274 |       "cell_type": "code",
 275 |       "source": [
 276 |         "print(myvar[\"y\"])"
 277 |       ],
 278 |       "metadata": {
 279 |         "id": "7-N8teo6x5i5",
 280 |         "colab": {
 281 |           "base_uri": "https://localhost:8080/"
 282 |         },
 283 |         "outputId": "d9818e2a-d8b3-4104-88b7-47fb78f0381a"
 284 |       },
 285 |       "execution_count": 5,
 286 |       "outputs": [
 287 |         {
 288 |           "output_type": "stream",
 289 |           "name": "stdout",
 290 |           "text": [
 291 |             "7\n"
 292 |           ]
 293 |         }
 294 |       ]
 295 |     },
 296 |     {
 297 |       "cell_type": "markdown",
 298 |       "source": [
 299 |         "**Key/Value Objects as Series**\n",
 300 |         "\n",
 301 |         "You can also use a key/value object, like a dictionary, when creating a Series."
 302 |       ],
 303 |       "metadata": {
 304 |         "id": "tBg6FJOQx7Uw"
 305 |       }
 306 |     },
 307 |     {
 308 |       "cell_type": "code",
 309 |       "source": [
 310 |         "import pandas as pd\n",
 311 |         "\n",
 312 |         "calories = {\"day1\": 420, \"day2\": 380, \"day3\": 390}\n",
 313 |         "\n",
 314 |         "myvar = pd.Series(calories)\n",
 315 |         "\n",
 316 |         "print(myvar)"
 317 |       ],
 318 |       "metadata": {
 319 |         "id": "0qevUVNPx_Bp"
 320 |       },
 321 |       "execution_count": null,
 322 |       "outputs": []
 323 |     },
 324 |     {
 325 |       "cell_type": "markdown",
 326 |       "source": [
 327 |         "To select only some of the items in the dictionary, use the index argument and specify only the items you want to include in the Series."
 328 |       ],
 329 |       "metadata": {
 330 |         "id": "xufaS13oyBDK"
 331 |       }
 332 |     },
 333 |     {
 334 |       "cell_type": "code",
 335 |       "source": [
 336 |         "import pandas as pd\n",
 337 |         "\n",
 338 |         "calories = {\"day1\": 420, \"day2\": 380, \"day3\": 390}\n",
 339 |         "\n",
 340 |         "myvar = pd.Series(calories, index = [\"day1\", \"day2\"])\n",
 341 |         "\n",
 342 |         "print(myvar)"
 343 |       ],
 344 |       "metadata": {
 345 |         "id": "5jJyF9u4yDQR"
 346 |       },
 347 |       "execution_count": null,
 348 |       "outputs": []
 349 |     },
 350 |     {
 351 |       "cell_type": "markdown",
 352 |       "source": [
 353 |         "**DataFrames**\n",
 354 |         "\n",
 355 |         "Data sets in Pandas are usually multi-dimensional tables, called DataFrames.\n",
 356 |         "\n",
 357 |         "Series is like a column, a DataFrame is the whole table."
 358 |       ],
 359 |       "metadata": {
 360 |         "id": "2Ue5Kd9KyGe5"
 361 |       }
 362 |     },
 363 |     {
 364 |       "cell_type": "code",
 365 |       "source": [
 366 |         "import pandas as pd\n",
 367 |         "\n",
 368 |         "data = {\n",
 369 |         "  \"calories\": [420, 380, 390],\n",
 370 |         "  \"duration\": [50, 40, 45]\n",
 371 |         "}\n",
 372 |         "\n",
 373 |         "myvar = pd.DataFrame(data)\n",
 374 |         "\n",
 375 |         "print(myvar)"
 376 |       ],
 377 |       "metadata": {
 378 |         "id": "ecM9z8e0yKC6"
 379 |       },
 380 |       "execution_count": null,
 381 |       "outputs": []
 382 |     },
 383 |     {
 384 |       "cell_type": "markdown",
 385 |       "source": [
 386 |         "**What is a DataFrame?**\n",
 387 |         "\n",
 388 |         "A Pandas DataFrame is a 2 dimensional data structure, like a 2 dimensional array, or a table with rows and columns."
 389 |       ],
 390 |       "metadata": {
 391 |         "id": "fZASC2bYyNbR"
 392 |       }
 393 |     },
 394 |     {
 395 |       "cell_type": "code",
 396 |       "source": [
 397 |         "import pandas as pd\n",
 398 |         "\n",
 399 |         "data = {\n",
 400 |         "  \"calories\": [420, 380, 390],\n",
 401 |         "  \"duration\": [50, 40, 45]\n",
 402 |         "}\n",
 403 |         "\n",
 404 |         "#load data into a DataFrame object:\n",
 405 |         "df = pd.DataFrame(data)\n",
 406 |         "\n",
 407 |         "print(df)"
 408 |       ],
 409 |       "metadata": {
 410 |         "id": "RwW5JumIyT1J"
 411 |       },
 412 |       "execution_count": null,
 413 |       "outputs": []
 414 |     },
 415 |     {
 416 |       "cell_type": "markdown",
 417 |       "source": [
 418 |         "**Locate Row**\n",
 419 |         "\n",
 420 |         "As you can see from the result above, the DataFrame is like a table with rows and columns.\n",
 421 |         "\n",
 422 |         "Pandas use the loc attribute to return one or more specified row(s)"
 423 |       ],
 424 |       "metadata": {
 425 |         "id": "h3cTUKoyyUqx"
 426 |       }
 427 |     },
 428 |     {
 429 |       "cell_type": "code",
 430 |       "source": [
 431 |         "#refer to the row index:\n",
 432 |         "print(df.loc[0])"
 433 |       ],
 434 |       "metadata": {
 435 |         "id": "qCkOWOm9yYPS"
 436 |       },
 437 |       "execution_count": null,
 438 |       "outputs": []
 439 |     },
 440 |     {
 441 |       "cell_type": "code",
 442 |       "source": [
 443 |         "#use a list of indexes:\n",
 444 |         "print(df.loc[[0, 1]])"
 445 |       ],
 446 |       "metadata": {
 447 |         "id": "23AgoBrSyeGB"
 448 |       },
 449 |       "execution_count": null,
 450 |       "outputs": []
 451 |     },
 452 |     {
 453 |       "cell_type": "markdown",
 454 |       "source": [
 455 |         "**Named Indexes**\n",
 456 |         "\n",
 457 |         "With the index argument, you can name your own indexes."
 458 |       ],
 459 |       "metadata": {
 460 |         "id": "E3ml6fouybqb"
 461 |       }
 462 |     },
 463 |     {
 464 |       "cell_type": "code",
 465 |       "source": [
 466 |         "import pandas as pd\n",
 467 |         "\n",
 468 |         "data = {\n",
 469 |         "  \"calories\": [420, 380, 390],\n",
 470 |         "  \"duration\": [50, 40, 45]\n",
 471 |         "}\n",
 472 |         "\n",
 473 |         "df = pd.DataFrame(data, index = [\"day1\", \"day2\", \"day3\"])\n",
 474 |         "\n",
 475 |         "print(df)"
 476 |       ],
 477 |       "metadata": {
 478 |         "id": "gDt2OS34yjli"
 479 |       },
 480 |       "execution_count": null,
 481 |       "outputs": []
 482 |     },
 483 |     {
 484 |       "cell_type": "markdown",
 485 |       "source": [
 486 |         "**Locate Named Indexes**\n",
 487 |         "\n",
 488 |         "Use the named index in the loc attribute to return the specified row(s)."
 489 |       ],
 490 |       "metadata": {
 491 |         "id": "3kxOKSmuykqx"
 492 |       }
 493 |     },
 494 |     {
 495 |       "cell_type": "code",
 496 |       "source": [
 497 |         "#refer to the named index:\n",
 498 |         "print(df.loc[\"day2\"])"
 499 |       ],
 500 |       "metadata": {
 501 |         "id": "tiFeiG7_yquq"
 502 |       },
 503 |       "execution_count": null,
 504 |       "outputs": []
 505 |     },
 506 |     {
 507 |       "cell_type": "markdown",
 508 |       "source": [
 509 |         "**Load Files Into a DataFrame**\n",
 510 |         "\n",
 511 |         "If your data sets are stored in a file, Pandas can load them into a DataFrame."
 512 |       ],
 513 |       "metadata": {
 514 |         "id": "XYxL0KggypKY"
 515 |       }
 516 |     },
 517 |     {
 518 |       "cell_type": "code",
 519 |       "source": [
 520 |         "import pandas as pd\n",
 521 |         "\n",
 522 |         "df = pd.read_csv('data.csv')\n",
 523 |         "\n",
 524 |         "print(df)"
 525 |       ],
 526 |       "metadata": {
 527 |         "id": "7UwzIDzVyvVx"
 528 |       },
 529 |       "execution_count": null,
 530 |       "outputs": []
 531 |     },
 532 |     {
 533 |       "cell_type": "markdown",
 534 |       "source": [
 535 |         "**Read CSV Files**\n",
 536 |         "\n",
 537 |         "A simple way to store big data sets is to use CSV files (comma separated files).\n",
 538 |         "\n",
 539 |         "CSV files contains plain text and is a well know format that can be read by everyone including Pandas.\n",
 540 |         "\n",
 541 |         "In our examples we will be using a CSV file called 'data.csv'."
 542 |       ],
 543 |       "metadata": {
 544 |         "id": "8M-ZQ7VQyxWJ"
 545 |       }
 546 |     },
 547 |     {
 548 |       "cell_type": "code",
 549 |       "source": [
 550 |         "import pandas as pd\n",
 551 |         "\n",
 552 |         "df = pd.read_csv('data.csv')\n",
 553 |         "\n",
 554 |         "print(df.to_string())"
 555 |       ],
 556 |       "metadata": {
 557 |         "id": "FLaaHFcPy2aY"
 558 |       },
 559 |       "execution_count": null,
 560 |       "outputs": []
 561 |     },
 562 |     {
 563 |       "cell_type": "markdown",
 564 |       "source": [
 565 |         "If you have a large DataFrame with many rows, Pandas will only return the first 5 rows, and the last 5 rows:"
 566 |       ],
 567 |       "metadata": {
 568 |         "id": "CWP4or5Uy-TY"
 569 |       }
 570 |     },
 571 |     {
 572 |       "cell_type": "code",
 573 |       "source": [
 574 |         "import pandas as pd\n",
 575 |         "\n",
 576 |         "df = pd.read_csv('data.csv')\n",
 577 |         "\n",
 578 |         "print(df)"
 579 |       ],
 580 |       "metadata": {
 581 |         "id": "xH10A-PLy494"
 582 |       },
 583 |       "execution_count": null,
 584 |       "outputs": []
 585 |     },
 586 |     {
 587 |       "cell_type": "markdown",
 588 |       "source": [
 589 |         "**max_rows**\n",
 590 |         "\n",
 591 |         "The number of rows returned is defined in Pandas option settings.\n",
 592 |         "\n",
 593 |         "You can check your system's maximum rows with the pd.options.display.max_rows statement."
 594 |       ],
 595 |       "metadata": {
 596 |         "id": "EmtD9Ssky_SI"
 597 |       }
 598 |     },
 599 |     {
 600 |       "cell_type": "code",
 601 |       "source": [
 602 |         "import pandas as pd\n",
 603 |         "\n",
 604 |         "print(pd.options.display.max_rows)"
 605 |       ],
 606 |       "metadata": {
 607 |         "id": "Mtn5RGItzJkQ"
 608 |       },
 609 |       "execution_count": null,
 610 |       "outputs": []
 611 |     },
 612 |     {
 613 |       "cell_type": "markdown",
 614 |       "source": [
 615 |         "You can change the maximum rows number with the same statement."
 616 |       ],
 617 |       "metadata": {
 618 |         "id": "zSGCxTT9zQAn"
 619 |       }
 620 |     },
 621 |     {
 622 |       "cell_type": "code",
 623 |       "source": [
 624 |         "import pandas as pd\n",
 625 |         "\n",
 626 |         "pd.options.display.max_rows = 9999\n",
 627 |         "\n",
 628 |         "df = pd.read_csv('data.csv')\n",
 629 |         "\n",
 630 |         "print(df)"
 631 |       ],
 632 |       "metadata": {
 633 |         "id": "Iuu2hCLszTsP"
 634 |       },
 635 |       "execution_count": null,
 636 |       "outputs": []
 637 |     },
 638 |     {
 639 |       "cell_type": "markdown",
 640 |       "source": [
 641 |         "# **Read JSON**\n",
 642 |         "\n",
 643 |         "Big data sets are often stored, or extracted as JSON.\n",
 644 |         "\n",
 645 |         "JSON is plain text, but has the format of an object, and is well known in the world of programming, including Pandas.\n",
 646 |         "\n",
 647 |         "In our examples we will be using a JSON file called 'data.json'."
 648 |       ],
 649 |       "metadata": {
 650 |         "id": "ssy0VXOhzhr3"
 651 |       }
 652 |     },
 653 |     {
 654 |       "cell_type": "code",
 655 |       "source": [
 656 |         "import pandas as pd\n",
 657 |         "\n",
 658 |         "df = pd.read_json('data.json')\n",
 659 |         "\n",
 660 |         "print(df.to_string())"
 661 |       ],
 662 |       "metadata": {
 663 |         "id": "mU4F5TXpzmJQ"
 664 |       },
 665 |       "execution_count": null,
 666 |       "outputs": []
 667 |     },
 668 |     {
 669 |       "cell_type": "markdown",
 670 |       "source": [
 671 |         "If your JSON code is not in a file, but in a Python Dictionary, you can load it into a DataFrame directly:"
 672 |       ],
 673 |       "metadata": {
 674 |         "id": "hAJupDUR2WoE"
 675 |       }
 676 |     },
 677 |     {
 678 |       "cell_type": "code",
 679 |       "source": [
 680 |         "import pandas as pd\n",
 681 |         "\n",
 682 |         "data = {\n",
 683 |         "  \"Duration\":{\n",
 684 |         "    \"0\":60,\n",
 685 |         "    \"1\":60,\n",
 686 |         "    \"2\":60,\n",
 687 |         "    \"3\":45,\n",
 688 |         "    \"4\":45,\n",
 689 |         "    \"5\":60\n",
 690 |         "  },\n",
 691 |         "  \"Pulse\":{\n",
 692 |         "    \"0\":110,\n",
 693 |         "    \"1\":117,\n",
 694 |         "    \"2\":103,\n",
 695 |         "    \"3\":109,\n",
 696 |         "    \"4\":117,\n",
 697 |         "    \"5\":102\n",
 698 |         "  },\n",
 699 |         "  \"Maxpulse\":{\n",
 700 |         "    \"0\":130,\n",
 701 |         "    \"1\":145,\n",
 702 |         "    \"2\":135,\n",
 703 |         "    \"3\":175,\n",
 704 |         "    \"4\":148,\n",
 705 |         "    \"5\":127\n",
 706 |         "  },\n",
 707 |         "  \"Calories\":{\n",
 708 |         "    \"0\":409,\n",
 709 |         "    \"1\":479,\n",
 710 |         "    \"2\":340,\n",
 711 |         "    \"3\":282,\n",
 712 |         "    \"4\":406,\n",
 713 |         "    \"5\":300\n",
 714 |         "  }\n",
 715 |         "}\n",
 716 |         "\n",
 717 |         "df = pd.DataFrame(data)\n",
 718 |         "\n",
 719 |         "print(df)"
 720 |       ],
 721 |       "metadata": {
 722 |         "id": "GOPLyBlS2X-z"
 723 |       },
 724 |       "execution_count": null,
 725 |       "outputs": []
 726 |     },
 727 |     {
 728 |       "cell_type": "markdown",
 729 |       "source": [
 730 |         "Viewing the Data\n",
 731 |         "One of the most used method for getting a quick overview of the DataFrame, is the head() method.\n",
 732 |         "\n",
 733 |         "The head() method returns the headers and a specified number of rows, starting from the top."
 734 |       ],
 735 |       "metadata": {
 736 |         "id": "Jd5un6u82kGk"
 737 |       }
 738 |     },
 739 |     {
 740 |       "cell_type": "code",
 741 |       "source": [
 742 |         "import pandas as pd\n",
 743 |         "\n",
 744 |         "df = pd.read_csv('data.csv')\n",
 745 |         "\n",
 746 |         "print(df.head(10))"
 747 |       ],
 748 |       "metadata": {
 749 |         "id": "_RbP2dw32k_k"
 750 |       },
 751 |       "execution_count": null,
 752 |       "outputs": []
 753 |     },
 754 |     {
 755 |       "cell_type": "markdown",
 756 |       "source": [
 757 |         "***Refer moodle for dataset file***"
 758 |       ],
 759 |       "metadata": {
 760 |         "id": "qE7zheZG2nBV"
 761 |       }
 762 |     },
 763 |     {
 764 |       "cell_type": "code",
 765 |       "source": [
 766 |         "import pandas as pd\n",
 767 |         "\n",
 768 |         "df = pd.read_csv('data.csv')\n",
 769 |         "\n",
 770 |         "print(df.head())"
 771 |       ],
 772 |       "metadata": {
 773 |         "id": "knuDN7P823t7"
 774 |       },
 775 |       "execution_count": null,
 776 |       "outputs": []
 777 |     },
 778 |     {
 779 |       "cell_type": "markdown",
 780 |       "source": [
 781 |         "There is also a tail() method for viewing the last rows of the DataFrame.\n",
 782 |         "\n",
 783 |         "The tail() method returns the headers and a specified number of rows, starting from the bottom."
 784 |       ],
 785 |       "metadata": {
 786 |         "id": "Tb_Bpdwl27MD"
 787 |       }
 788 |     },
 789 |     {
 790 |       "cell_type": "code",
 791 |       "source": [
 792 |         "print(df.tail())"
 793 |       ],
 794 |       "metadata": {
 795 |         "id": "WxJe8LCQ29bb"
 796 |       },
 797 |       "execution_count": null,
 798 |       "outputs": []
 799 |     },
 800 |     {
 801 |       "cell_type": "markdown",
 802 |       "source": [
 803 |         "**Info About the Data**\n",
 804 |         "\n",
 805 |         "The DataFrames object has a method called info(), that gives you more information about the data set."
 806 |       ],
 807 |       "metadata": {
 808 |         "id": "rOua88zc2_4L"
 809 |       }
 810 |     },
 811 |     {
 812 |       "cell_type": "code",
 813 |       "source": [
 814 |         "print(df.info())"
 815 |       ],
 816 |       "metadata": {
 817 |         "id": "8UidciRB3D54"
 818 |       },
 819 |       "execution_count": null,
 820 |       "outputs": []
 821 |     },
 822 |     {
 823 |       "cell_type": "markdown",
 824 |       "source": [
 825 |         "**Data Cleaning**\n",
 826 |         "\n",
 827 |         "Data cleaning means fixing bad data in your data set.\n",
 828 |         "\n",
 829 |         "Bad data could be:\n",
 830 |         "\n",
 831 |         "Empty cells\n",
 832 |         "\n",
 833 |         "Data in wrong format\n",
 834 |         "\n",
 835 |         "Wrong data\n",
 836 |         "\n",
 837 |         "Duplicates\n",
 838 |         "\n",
 839 |         "\n",
 840 |         "\n",
 841 |         "```\n",
 842 |         "data set contains some empty cells (\"Date\" in row 22, and \"Calories\" in row 18 and 28).\n",
 843 |         "\n",
 844 |         "The data set contains wrong format (\"Date\" in row 26).\n",
 845 |         "\n",
 846 |         "The data set contains wrong data (\"Duration\" in row 7).\n",
 847 |         "\n",
 848 |         "The data set contains duplicates (row 11 and 12).\n",
 849 |         "```\n",
 850 |         "\n"
 851 |       ],
 852 |       "metadata": {
 853 |         "id": "rijrGgvT3EjE"
 854 |       }
 855 |     },
 856 |     {
 857 |       "cell_type": "markdown",
 858 |       "source": [
 859 |         "**Empty Cells**\n",
 860 |         "\n",
 861 |         "Empty cells can potentially give you a wrong result when you analyze data.\n",
 862 |         "\n",
 863 |         "**Remove Rows**\n",
 864 |         "\n",
 865 |         "One way to deal with empty cells is to remove rows that contain empty cells.\n",
 866 |         "\n",
 867 |         "This is usually OK, since data sets can be very big, and removing a few rows will not have a big impact on the result.\n"
 868 |       ],
 869 |       "metadata": {
 870 |         "id": "fzDVZJq08jjc"
 871 |       }
 872 |     },
 873 |     {
 874 |       "cell_type": "code",
 875 |       "source": [
 876 |         "import pandas as pd\n",
 877 |         "\n",
 878 |         "df = pd.read_csv('data.csv')\n",
 879 |         "\n",
 880 |         "new_df = df.dropna()\n",
 881 |         "\n",
 882 |         "print(new_df.to_string())"
 883 |       ],
 884 |       "metadata": {
 885 |         "id": "bhlGgpvc8bjt"
 886 |       },
 887 |       "execution_count": null,
 888 |       "outputs": []
 889 |     },
 890 |     {
 891 |       "cell_type": "markdown",
 892 |       "source": [
 893 |         "If you want to change the original DataFrame, use the inplace = True argument:"
 894 |       ],
 895 |       "metadata": {
 896 |         "id": "E3bsHIWW8vX1"
 897 |       }
 898 |     },
 899 |     {
 900 |       "cell_type": "code",
 901 |       "source": [
 902 |         "import pandas as pd\n",
 903 |         "\n",
 904 |         "df = pd.read_csv('data.csv')\n",
 905 |         "\n",
 906 |         "df.dropna(inplace = True)\n",
 907 |         "\n",
 908 |         "print(df.to_string())"
 909 |       ],
 910 |       "metadata": {
 911 |         "id": "drun59y-8wFP"
 912 |       },
 913 |       "execution_count": null,
 914 |       "outputs": []
 915 |     },
 916 |     {
 917 |       "cell_type": "markdown",
 918 |       "source": [
 919 |         "**Replace Empty Values**\n",
 920 |         "\n",
 921 |         "Another way of dealing with empty cells is to insert a new value instead.\n",
 922 |         "\n",
 923 |         "This way you do not have to delete entire rows just because of some empty cells.\n",
 924 |         "\n",
 925 |         "The fillna() method allows us to replace empty cells with a value:"
 926 |       ],
 927 |       "metadata": {
 928 |         "id": "2vzCS1KD8yGX"
 929 |       }
 930 |     },
 931 |     {
 932 |       "cell_type": "code",
 933 |       "source": [
 934 |         "import pandas as pd\n",
 935 |         "\n",
 936 |         "df = pd.read_csv('data.csv')\n",
 937 |         "\n",
 938 |         "df.fillna(130, inplace = True)"
 939 |       ],
 940 |       "metadata": {
 941 |         "id": "2K81qK3s815l"
 942 |       },
 943 |       "execution_count": null,
 944 |       "outputs": []
 945 |     },
 946 |     {
 947 |       "cell_type": "markdown",
 948 |       "source": [
 949 |         "**Replace Only For Specified Columns**\n",
 950 |         "\n",
 951 |         "The example above replaces all empty cells in the whole Data Frame.\n",
 952 |         "\n",
 953 |         "To only replace empty values for one column, specify the column name for the DataFrame:"
 954 |       ],
 955 |       "metadata": {
 956 |         "id": "tudG3-dA84TF"
 957 |       }
 958 |     },
 959 |     {
 960 |       "cell_type": "code",
 961 |       "source": [
 962 |         "import pandas as pd\n",
 963 |         "\n",
 964 |         "df = pd.read_csv('data.csv')\n",
 965 |         "\n",
 966 |         "df[\"Calories\"].fillna(130, inplace = True)"
 967 |       ],
 968 |       "metadata": {
 969 |         "id": "_BwJ2vi189MV"
 970 |       },
 971 |       "execution_count": null,
 972 |       "outputs": []
 973 |     },
 974 |     {
 975 |       "cell_type": "markdown",
 976 |       "source": [
 977 |         "**Replace Using Mean, Median, or Mode**\n",
 978 |         "\n",
 979 |         "A common way to replace empty cells, is to calculate the mean, median or mode value of the column.\n",
 980 |         "\n",
 981 |         "Pandas uses the mean() median() and mode() methods to calculate the respective values for a specified column:"
 982 |       ],
 983 |       "metadata": {
 984 |         "id": "FN2XWe829ASl"
 985 |       }
 986 |     },
 987 |     {
 988 |       "cell_type": "code",
 989 |       "source": [
 990 |         "import pandas as pd\n",
 991 |         "\n",
 992 |         "df = pd.read_csv('data.csv')\n",
 993 |         "\n",
 994 |         "x = df[\"Calories\"].mean()\n",
 995 |         "\n",
 996 |         "df[\"Calories\"].fillna(x, inplace = True)"
 997 |       ],
 998 |       "metadata": {
 999 |         "id": "MF_WLwXJ9DHY"
1000 |       },
1001 |       "execution_count": null,
1002 |       "outputs": []
1003 |     },
1004 |     {
1005 |       "cell_type": "markdown",
1006 |       "source": [
1007 |         "Calculate the MEDIAN, and replace any empty values with it:"
1008 |       ],
1009 |       "metadata": {
1010 |         "id": "fC-euHfc9FuN"
1011 |       }
1012 |     },
1013 |     {
1014 |       "cell_type": "code",
1015 |       "source": [
1016 |         "import pandas as pd\n",
1017 |         "\n",
1018 |         "df = pd.read_csv('data.csv')\n",
1019 |         "\n",
1020 |         "x = df[\"Calories\"].median()\n",
1021 |         "\n",
1022 |         "df[\"Calories\"].fillna(x, inplace = True)"
1023 |       ],
1024 |       "metadata": {
1025 |         "id": "D1aLvcDQ9IiN"
1026 |       },
1027 |       "execution_count": null,
1028 |       "outputs": []
1029 |     },
1030 |     {
1031 |       "cell_type": "markdown",
1032 |       "source": [
1033 |         "Median = the value in the middle, after you have sorted all values ascending."
1034 |       ],
1035 |       "metadata": {
1036 |         "id": "gsiZJCkv9Kjn"
1037 |       }
1038 |     },
1039 |     {
1040 |       "cell_type": "code",
1041 |       "source": [
1042 |         "import pandas as pd\n",
1043 |         "\n",
1044 |         "df = pd.read_csv('data.csv')\n",
1045 |         "\n",
1046 |         "x = df[\"Calories\"].mode()[0]\n",
1047 |         "\n",
1048 |         "df[\"Calories\"].fillna(x, inplace = True)"
1049 |       ],
1050 |       "metadata": {
1051 |         "id": "LuKr0KWO9NC0"
1052 |       },
1053 |       "execution_count": null,
1054 |       "outputs": []
1055 |     },
1056 |     {
1057 |       "cell_type": "markdown",
1058 |       "source": [
1059 |         "**Data of Wrong Format**\n",
1060 |         "\n",
1061 |         "Cells with data of wrong format can make it difficult, or even impossible, to analyze data.\n",
1062 |         "\n",
1063 |         "To fix it, you have two options: remove the rows, or convert all cells in the columns into the same format.\n",
1064 |         "\n",
1065 |         "Convert Into a Correct Format\n",
1066 |         "In our Data Frame, we have two cells with the wrong format. Check out row 22 and 26, the 'Date' column should be a string that represents a date:"
1067 |       ],
1068 |       "metadata": {
1069 |         "id": "QWModtbl9RKN"
1070 |       }
1071 |     },
1072 |     {
1073 |       "cell_type": "markdown",
1074 |       "source": [
1075 |         "Let's try to convert all cells in the 'Date' column into dates.\n",
1076 |         "\n",
1077 |         "Pandas has a to_datetime() method for this:"
1078 |       ],
1079 |       "metadata": {
1080 |         "id": "-Ee8ahcc9d5G"
1081 |       }
1082 |     },
1083 |     {
1084 |       "cell_type": "code",
1085 |       "source": [
1086 |         "import pandas as pd\n",
1087 |         "\n",
1088 |         "df = pd.read_csv('data.csv')\n",
1089 |         "\n",
1090 |         "df['Date'] = pd.to_datetime(df['Date'])\n",
1091 |         "\n",
1092 |         "print(df.to_string())"
1093 |       ],
1094 |       "metadata": {
1095 |         "id": "l5jkm9L59ZXK"
1096 |       },
1097 |       "execution_count": null,
1098 |       "outputs": []
1099 |     },
1100 |     {
1101 |       "cell_type": "markdown",
1102 |       "source": [
1103 |         "As you can see from the result, the date in row 26 was fixed, but the empty date in row 22 got a NaT (Not a Time) value, in other words an empty value. One way to deal with empty values is simply removing the entire row.\n",
1104 |         "\n",
1105 |         "**Removing Rows**\n",
1106 |         "\n",
1107 |         "The result from the converting in the example above gave us a NaT value, which can be handled as a NULL value, and we can remove the row by using the dropna() method."
1108 |       ],
1109 |       "metadata": {
1110 |         "id": "OHZ7feSH9mcs"
1111 |       }
1112 |     },
1113 |     {
1114 |       "cell_type": "code",
1115 |       "source": [
1116 |         "df.dropna(subset=['Date'], inplace = True)"
1117 |       ],
1118 |       "metadata": {
1119 |         "id": "VAjOpZ099nQW"
1120 |       },
1121 |       "execution_count": null,
1122 |       "outputs": []
1123 |     },
1124 |     {
1125 |       "cell_type": "markdown",
1126 |       "source": [
1127 |         "**Wrong Data**\n",
1128 |         "\n",
1129 |         "\"Wrong data\" does not have to be \"empty cells\" or \"wrong format\", it can just be wrong, like if someone registered \"199\" instead of \"1.99\".\n",
1130 |         "\n",
1131 |         "Sometimes you can spot wrong data by looking at the data set, because you have an expectation of what it should be.\n",
1132 |         "\n",
1133 |         "If you take a look at our data set, you can see that in row 7, the duration is 450, but for all the other rows the duration is between 30 and 60.\n",
1134 |         "\n",
1135 |         "It doesn't have to be wrong, but taking in consideration that this is the data set of someone's workout sessions, we conclude with the fact that this person did not work out in 450 minutes.\n",
1136 |         "\n",
1137 |         "**Replacing Values**\n",
1138 |         "\n",
1139 |         "One way to fix wrong values is to replace them with something else.\n",
1140 |         "\n",
1141 |         "In our example, it is most likely a typo, and the value should be \"45\" instead of \"450\", and we could just insert \"45\" in row 7:"
1142 |       ],
1143 |       "metadata": {
1144 |         "id": "Y4ELYWCu9w4M"
1145 |       }
1146 |     },
1147 |     {
1148 |       "cell_type": "code",
1149 |       "source": [
1150 |         "df.loc[7, 'Duration'] = 45"
1151 |       ],
1152 |       "metadata": {
1153 |         "id": "EkTEN2Oa91Qc"
1154 |       },
1155 |       "execution_count": null,
1156 |       "outputs": []
1157 |     },
1158 |     {
1159 |       "cell_type": "markdown",
1160 |       "source": [
1161 |         "For small data sets you might be able to replace the wrong data one by one, but not for big data sets.\n",
1162 |         "\n",
1163 |         "To replace wrong data for larger data sets you can create some rules, e.g. set some boundaries for legal values, and replace any values that are outside of the boundaries."
1164 |       ],
1165 |       "metadata": {
1166 |         "id": "UqejnLjj-Qhk"
1167 |       }
1168 |     },
1169 |     {
1170 |       "cell_type": "code",
1171 |       "source": [
1172 |         "for x in df.index:\n",
1173 |         "  if df.loc[x, \"Duration\"] > 120:\n",
1174 |         "    df.loc[x, \"Duration\"] = 120"
1175 |       ],
1176 |       "metadata": {
1177 |         "id": "l1aPH6Mv-Rek"
1178 |       },
1179 |       "execution_count": null,
1180 |       "outputs": []
1181 |     },
1182 |     {
1183 |       "cell_type": "markdown",
1184 |       "source": [
1185 |         "**Removing Rows**\n",
1186 |         "\n",
1187 |         "Another way of handling wrong data is to remove the rows that contains wrong data.\n",
1188 |         "\n",
1189 |         "This way you do not have to find out what to replace them with, and there is a good chance you do not need them to do your analyses."
1190 |       ],
1191 |       "metadata": {
1192 |         "id": "d4MzF0_y-Tpl"
1193 |       }
1194 |     },
1195 |     {
1196 |       "cell_type": "code",
1197 |       "source": [
1198 |         "for x in df.index:\n",
1199 |         "  if df.loc[x, \"Duration\"] > 120:\n",
1200 |         "    df.drop(x, inplace = True)"
1201 |       ],
1202 |       "metadata": {
1203 |         "id": "Cuv0s8_y-Zt-"
1204 |       },
1205 |       "execution_count": null,
1206 |       "outputs": []
1207 |     },
1208 |     {
1209 |       "cell_type": "markdown",
1210 |       "source": [
1211 |         "**Discovering Duplicates**\n",
1212 |         "\n",
1213 |         "Duplicate rows are rows that have been registered more than one time.\n",
1214 |         "\n",
1215 |         "By taking a look at our test data set, we can assume that row 11 and 12 are duplicates.\n",
1216 |         "\n",
1217 |         "To discover duplicates, we can use the duplicated() method.\n",
1218 |         "\n",
1219 |         "The duplicated() method returns a Boolean values for each row:\n"
1220 |       ],
1221 |       "metadata": {
1222 |         "id": "oYQVLxDF-hcr"
1223 |       }
1224 |     },
1225 |     {
1226 |       "cell_type": "code",
1227 |       "source": [
1228 |         "print(df.duplicated())"
1229 |       ],
1230 |       "metadata": {
1231 |         "id": "cDtxZ0xo-qRs"
1232 |       },
1233 |       "execution_count": null,
1234 |       "outputs": []
1235 |     },
1236 |     {
1237 |       "cell_type": "markdown",
1238 |       "source": [
1239 |         "**Removing Duplicates**\n",
1240 |         "\n",
1241 |         "To remove duplicates, use the drop_duplicates() method."
1242 |       ],
1243 |       "metadata": {
1244 |         "id": "BHL2Lndg-q9j"
1245 |       }
1246 |     },
1247 |     {
1248 |       "cell_type": "code",
1249 |       "source": [
1250 |         "df.drop_duplicates(inplace = True)"
1251 |       ],
1252 |       "metadata": {
1253 |         "id": "fiC7pcOp-uWj"
1254 |       },
1255 |       "execution_count": null,
1256 |       "outputs": []
1257 |     },
1258 |     {
1259 |       "cell_type": "markdown",
1260 |       "source": [
1261 |         "**Finding Relationships**\n",
1262 |         "\n",
1263 |         "A great aspect of the Pandas module is the corr() method.\n",
1264 |         "\n",
1265 |         "The corr() method calculates the relationship between each column in your data set.\n",
1266 |         "\n",
1267 |         "The examples in this page uses a CSV file called: 'data.csv'."
1268 |       ],
1269 |       "metadata": {
1270 |         "id": "BUJByCP_-0H7"
1271 |       }
1272 |     },
1273 |     {
1274 |       "cell_type": "code",
1275 |       "source": [
1276 |         "df.corr()"
1277 |       ],
1278 |       "metadata": {
1279 |         "id": "69Lz1aM1-63c"
1280 |       },
1281 |       "execution_count": null,
1282 |       "outputs": []
1283 |     },
1284 |     {
1285 |       "cell_type": "markdown",
1286 |       "source": [
1287 |         "**Result Explained**\n",
1288 |         "\n",
1289 |         "The Result of the corr() method is a table with a lot of numbers that represents how well the relationship is between two columns.\n",
1290 |         "\n",
1291 |         "\n",
1292 |         "The number varies from -1 to 1.\n",
1293 |         "\n",
1294 |         "\n",
1295 |         "1 means that there is a 1 to 1 relationship (a perfect correlation), and for this data set, each time a value went up in the first column, the other one went up as well.\n",
1296 |         "\n",
1297 |         "\n",
1298 |         "0.9 is also a good relationship, and if you increase one value, the other will probably increase as well.\n",
1299 |         "\n",
1300 |         "\n",
1301 |         "-0.9 would be just as good relationship as 0.9, but if you increase one value, the other will probably go down.\n",
1302 |         "\n",
1303 |         "\n",
1304 |         "0.2 means NOT a good relationship, meaning that if one value goes up does not mean that the other will.\n",
1305 |         "\n",
1306 |         "**Perfect Correlation:**\n",
1307 |         "We can see that \"Duration\" and \"Duration\" got the number 1.000000, which makes sense, each column always has a perfect relationship with itself.\n",
1308 |         "\n",
1309 |         "**Good Correlation:**\n",
1310 |         "\"Duration\" and \"Calories\" got a 0.922721 correlation, which is a very good correlation, and we can predict that the longer you work out, the more calories you burn, and the other way around: if you burned a lot of calories, you probably had a long work out.\n",
1311 |         "\n",
1312 |         "**Bad Correlation:**\n",
1313 |         "\"Duration\" and \"Maxpulse\" got a 0.009403 correlation, which is a very bad correlation, meaning that we can not predict the max pulse by just looking at the duration of the work out, and vice versa.\n",
1314 |         "\n",
1315 |         "\n",
1316 |         "# **Plotting**\n",
1317 |         "Pandas uses the plot() method to create diagrams.\n",
1318 |         "\n",
1319 |         "We can use Pyplot, a submodule of the Matplotlib library to visualize the diagram on the screen."
1320 |       ],
1321 |       "metadata": {
1322 |         "id": "fmuTvgU5--Qz"
1323 |       }
1324 |     },
1325 |     {
1326 |       "cell_type": "code",
1327 |       "source": [
1328 |         "import pandas as pd\n",
1329 |         "import matplotlib.pyplot as plt\n",
1330 |         "\n",
1331 |         "df = pd.read_csv('data.csv')\n",
1332 |         "\n",
1333 |         "df.plot()\n",
1334 |         "\n",
1335 |         "plt.show()"
1336 |       ],
1337 |       "metadata": {
1338 |         "id": "cf0Ja3NTD22d"
1339 |       },
1340 |       "execution_count": null,
1341 |       "outputs": []
1342 |     }
1343 |   ]
1344 | }


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