├── README.md
├── DSBDA_Assignment1(A).ipynb
├── DSBDA A=3 part2 (1).ipynb
├── DSBDA-Assignment3DSBDA.ipynb
└── DSBDA A=1 PART2 (1) (1).ipynb


/README.md:
--------------------------------------------------------------------------------
 1 | # DSBDA-PRACTICALS
 2 | 
 3 |   - [Assignment 1 - A](https://github.com/vaishnaviraykar/DSBDA-PRACTICALS/blob/main/DSBDA_Assignment1(A).ipynb)
 4 |   
 5 |   - [Assignment 1 - B](https://github.com/vaishnaviraykar/DSBDA-PRACTICALS/blob/main/DSBDA%20A%3D1%20PART2%20(1)%20(1).ipynb)
 6 |   
 7 |   - [Assignment 2](https://github.com/vaishnaviraykar/DSBDA-PRACTICALS/blob/main/Asssignment2.ipynb)
 8 |   
 9 |   - [Assignment 3 - A](https://github.com/vaishnaviraykar/DSBDA-PRACTICALS/blob/main/DSBDA-Assignment3DSBDA.ipynb)
10 |   
11 |   - [Assignment 3 - B](https://github.com/vaishnaviraykar/DSBDA-PRACTICALS/blob/main/DSBDA%20A%3D3%20part2%20(1).ipynb)
12 | 


--------------------------------------------------------------------------------
/DSBDA_Assignment1(A).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": "code",
 19 |       "execution_count": 1,
 20 |       "metadata": {
 21 |         "id": "S1Du7cyo_jpQ"
 22 |       },
 23 |       "outputs": [],
 24 |       "source": [
 25 |         "[1]  #1. Import all required python libraries\n",
 26 |         "\n",
 27 |         "#import numpy as np\n",
 28 |         "import pandas as pd\n",
 29 |         "\n",
 30 |         "import matplotlib\n",
 31 |         "from matplotlib import pyplot as plt\n",
 32 |         "#matplotlib.style.use(ggplot)\n",
 33 |         "\n",
 34 |         "\n",
 35 |         "import seaborn as sns"
 36 |       ]
 37 |     },
 38 |     {
 39 |       "cell_type": "code",
 40 |       "source": [
 41 |         "#2. preparing to load data into colab from local drive\n",
 42 |         "from google.colab import files\n",
 43 |         "uploaded = files.upload()"
 44 |       ],
 45 |       "metadata": {
 46 |         "colab": {
 47 |           "base_uri": "https://localhost:8080/",
 48 |           "height": 73
 49 |         },
 50 |         "id": "v64Wxr8TeNX1",
 51 |         "outputId": "7c3b830e-e744-47f0-86ff-5ec9757ef906"
 52 |       },
 53 |       "execution_count": 2,
 54 |       "outputs": [
 55 |         {
 56 |           "output_type": "display_data",
 57 |           "data": {
 58 |             "text/plain": [
 59 |               "<IPython.core.display.HTML object>"
 60 |             ],
 61 |             "text/html": [
 62 |               "\n",
 63 |               "     <input type=\"file\" id=\"files-6cf8a0fa-2bfc-4c72-abf5-91752a45849c\" name=\"files[]\" multiple disabled\n",
 64 |               "        style=\"border:none\" />\n",
 65 |               "     <output id=\"result-6cf8a0fa-2bfc-4c72-abf5-91752a45849c\">\n",
 66 |               "      Upload widget is only available when the cell has been executed in the\n",
 67 |               "      current browser session. Please rerun this cell to enable.\n",
 68 |               "      </output>\n",
 69 |               "      <script>// Copyright 2017 Google LLC\n",
 70 |               "//\n",
 71 |               "// Licensed under the Apache License, Version 2.0 (the \"License\");\n",
 72 |               "// you may not use this file except in compliance with the License.\n",
 73 |               "// You may obtain a copy of the License at\n",
 74 |               "//\n",
 75 |               "//      http://www.apache.org/licenses/LICENSE-2.0\n",
 76 |               "//\n",
 77 |               "// Unless required by applicable law or agreed to in writing, software\n",
 78 |               "// distributed under the License is distributed on an \"AS IS\" BASIS,\n",
 79 |               "// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
 80 |               "// See the License for the specific language governing permissions and\n",
 81 |               "// limitations under the License.\n",
 82 |               "\n",
 83 |               "/**\n",
 84 |               " * @fileoverview Helpers for google.colab Python module.\n",
 85 |               " */\n",
 86 |               "(function(scope) {\n",
 87 |               "function span(text, styleAttributes = {}) {\n",
 88 |               "  const element = document.createElement('span');\n",
 89 |               "  element.textContent = text;\n",
 90 |               "  for (const key of Object.keys(styleAttributes)) {\n",
 91 |               "    element.style[key] = styleAttributes[key];\n",
 92 |               "  }\n",
 93 |               "  return element;\n",
 94 |               "}\n",
 95 |               "\n",
 96 |               "// Max number of bytes which will be uploaded at a time.\n",
 97 |               "const MAX_PAYLOAD_SIZE = 100 * 1024;\n",
 98 |               "\n",
 99 |               "function _uploadFiles(inputId, outputId) {\n",
100 |               "  const steps = uploadFilesStep(inputId, outputId);\n",
101 |               "  const outputElement = document.getElementById(outputId);\n",
102 |               "  // Cache steps on the outputElement to make it available for the next call\n",
103 |               "  // to uploadFilesContinue from Python.\n",
104 |               "  outputElement.steps = steps;\n",
105 |               "\n",
106 |               "  return _uploadFilesContinue(outputId);\n",
107 |               "}\n",
108 |               "\n",
109 |               "// This is roughly an async generator (not supported in the browser yet),\n",
110 |               "// where there are multiple asynchronous steps and the Python side is going\n",
111 |               "// to poll for completion of each step.\n",
112 |               "// This uses a Promise to block the python side on completion of each step,\n",
113 |               "// then passes the result of the previous step as the input to the next step.\n",
114 |               "function _uploadFilesContinue(outputId) {\n",
115 |               "  const outputElement = document.getElementById(outputId);\n",
116 |               "  const steps = outputElement.steps;\n",
117 |               "\n",
118 |               "  const next = steps.next(outputElement.lastPromiseValue);\n",
119 |               "  return Promise.resolve(next.value.promise).then((value) => {\n",
120 |               "    // Cache the last promise value to make it available to the next\n",
121 |               "    // step of the generator.\n",
122 |               "    outputElement.lastPromiseValue = value;\n",
123 |               "    return next.value.response;\n",
124 |               "  });\n",
125 |               "}\n",
126 |               "\n",
127 |               "/**\n",
128 |               " * Generator function which is called between each async step of the upload\n",
129 |               " * process.\n",
130 |               " * @param {string} inputId Element ID of the input file picker element.\n",
131 |               " * @param {string} outputId Element ID of the output display.\n",
132 |               " * @return {!Iterable<!Object>} Iterable of next steps.\n",
133 |               " */\n",
134 |               "function* uploadFilesStep(inputId, outputId) {\n",
135 |               "  const inputElement = document.getElementById(inputId);\n",
136 |               "  inputElement.disabled = false;\n",
137 |               "\n",
138 |               "  const outputElement = document.getElementById(outputId);\n",
139 |               "  outputElement.innerHTML = '';\n",
140 |               "\n",
141 |               "  const pickedPromise = new Promise((resolve) => {\n",
142 |               "    inputElement.addEventListener('change', (e) => {\n",
143 |               "      resolve(e.target.files);\n",
144 |               "    });\n",
145 |               "  });\n",
146 |               "\n",
147 |               "  const cancel = document.createElement('button');\n",
148 |               "  inputElement.parentElement.appendChild(cancel);\n",
149 |               "  cancel.textContent = 'Cancel upload';\n",
150 |               "  const cancelPromise = new Promise((resolve) => {\n",
151 |               "    cancel.onclick = () => {\n",
152 |               "      resolve(null);\n",
153 |               "    };\n",
154 |               "  });\n",
155 |               "\n",
156 |               "  // Wait for the user to pick the files.\n",
157 |               "  const files = yield {\n",
158 |               "    promise: Promise.race([pickedPromise, cancelPromise]),\n",
159 |               "    response: {\n",
160 |               "      action: 'starting',\n",
161 |               "    }\n",
162 |               "  };\n",
163 |               "\n",
164 |               "  cancel.remove();\n",
165 |               "\n",
166 |               "  // Disable the input element since further picks are not allowed.\n",
167 |               "  inputElement.disabled = true;\n",
168 |               "\n",
169 |               "  if (!files) {\n",
170 |               "    return {\n",
171 |               "      response: {\n",
172 |               "        action: 'complete',\n",
173 |               "      }\n",
174 |               "    };\n",
175 |               "  }\n",
176 |               "\n",
177 |               "  for (const file of files) {\n",
178 |               "    const li = document.createElement('li');\n",
179 |               "    li.append(span(file.name, {fontWeight: 'bold'}));\n",
180 |               "    li.append(span(\n",
181 |               "        `(${file.type || 'n/a'}) - ${file.size} bytes, ` +\n",
182 |               "        `last modified: ${\n",
183 |               "            file.lastModifiedDate ? file.lastModifiedDate.toLocaleDateString() :\n",
184 |               "                                    'n/a'} - `));\n",
185 |               "    const percent = span('0% done');\n",
186 |               "    li.appendChild(percent);\n",
187 |               "\n",
188 |               "    outputElement.appendChild(li);\n",
189 |               "\n",
190 |               "    const fileDataPromise = new Promise((resolve) => {\n",
191 |               "      const reader = new FileReader();\n",
192 |               "      reader.onload = (e) => {\n",
193 |               "        resolve(e.target.result);\n",
194 |               "      };\n",
195 |               "      reader.readAsArrayBuffer(file);\n",
196 |               "    });\n",
197 |               "    // Wait for the data to be ready.\n",
198 |               "    let fileData = yield {\n",
199 |               "      promise: fileDataPromise,\n",
200 |               "      response: {\n",
201 |               "        action: 'continue',\n",
202 |               "      }\n",
203 |               "    };\n",
204 |               "\n",
205 |               "    // Use a chunked sending to avoid message size limits. See b/62115660.\n",
206 |               "    let position = 0;\n",
207 |               "    do {\n",
208 |               "      const length = Math.min(fileData.byteLength - position, MAX_PAYLOAD_SIZE);\n",
209 |               "      const chunk = new Uint8Array(fileData, position, length);\n",
210 |               "      position += length;\n",
211 |               "\n",
212 |               "      const base64 = btoa(String.fromCharCode.apply(null, chunk));\n",
213 |               "      yield {\n",
214 |               "        response: {\n",
215 |               "          action: 'append',\n",
216 |               "          file: file.name,\n",
217 |               "          data: base64,\n",
218 |               "        },\n",
219 |               "      };\n",
220 |               "\n",
221 |               "      let percentDone = fileData.byteLength === 0 ?\n",
222 |               "          100 :\n",
223 |               "          Math.round((position / fileData.byteLength) * 100);\n",
224 |               "      percent.textContent = `${percentDone}% done`;\n",
225 |               "\n",
226 |               "    } while (position < fileData.byteLength);\n",
227 |               "  }\n",
228 |               "\n",
229 |               "  // All done.\n",
230 |               "  yield {\n",
231 |               "    response: {\n",
232 |               "      action: 'complete',\n",
233 |               "    }\n",
234 |               "  };\n",
235 |               "}\n",
236 |               "\n",
237 |               "scope.google = scope.google || {};\n",
238 |               "scope.google.colab = scope.google.colab || {};\n",
239 |               "scope.google.colab._files = {\n",
240 |               "  _uploadFiles,\n",
241 |               "  _uploadFilesContinue,\n",
242 |               "};\n",
243 |               "})(self);\n",
244 |               "</script> "
245 |             ]
246 |           },
247 |           "metadata": {}
248 |         },
249 |         {
250 |           "output_type": "stream",
251 |           "name": "stdout",
252 |           "text": [
253 |             "Saving iris.data.csv to iris.data.csv\n"
254 |           ]
255 |         }
256 |       ]
257 |     },
258 |     {
259 |       "cell_type": "code",
260 |       "source": [
261 |         "  #3.loading data into dataframe\n",
262 |         "import io\n",
263 |         "df =  pd.read_csv(io.BytesIO(uploaded['iris.data.csv']))  #import csv file in dataframe called df\n",
264 |         "#Dataset is now stored in a Pandas Dataframe\n",
265 |         "\n",
266 |         " \n"
267 |       ],
268 |       "metadata": {
269 |         "id": "4-p5hfYfrXrW"
270 |       },
271 |       "execution_count": 3,
272 |       "outputs": []
273 |     },
274 |     {
275 |       "cell_type": "code",
276 |       "source": [
277 |         " #classes = df ['species'].unique().tolist()\n",
278 |         "#classes"
279 |       ],
280 |       "metadata": {
281 |         "id": "e0e_XMdXyD8a"
282 |       },
283 |       "execution_count": 4,
284 |       "outputs": []
285 |     },
286 |     {
287 |       "cell_type": "code",
288 |       "source": [
289 |         "  #4.1 Information of the data present in dataset\n",
290 |         "df.info()"
291 |       ],
292 |       "metadata": {
293 |         "colab": {
294 |           "base_uri": "https://localhost:8080/"
295 |         },
296 |         "id": "lf2-KAVUsJ0W",
297 |         "outputId": "4ade49ec-5463-439b-f8b2-c51cf7631ba2"
298 |       },
299 |       "execution_count": 5,
300 |       "outputs": [
301 |         {
302 |           "output_type": "stream",
303 |           "name": "stdout",
304 |           "text": [
305 |             "<class 'pandas.core.frame.DataFrame'>\n",
306 |             "RangeIndex: 149 entries, 0 to 148\n",
307 |             "Data columns (total 5 columns):\n",
308 |             " #   Column       Non-Null Count  Dtype  \n",
309 |             "---  ------       --------------  -----  \n",
310 |             " 0   5.1          149 non-null    float64\n",
311 |             " 1   3.5          149 non-null    float64\n",
312 |             " 2   1.4          149 non-null    float64\n",
313 |             " 3   0.2          149 non-null    float64\n",
314 |             " 4   Iris-setosa  149 non-null    object \n",
315 |             "dtypes: float64(4), object(1)\n",
316 |             "memory usage: 5.9+ KB\n"
317 |           ]
318 |         }
319 |       ]
320 |     },
321 |     {
322 |       "cell_type": "code",
323 |       "source": [
324 |         "# 4.2 Getting the dimension/shape of the data.\n",
325 |         "#Expect it to 150 rows and 5 columns\n",
326 |         "\n",
327 |         "print(df.shape)"
328 |       ],
329 |       "metadata": {
330 |         "colab": {
331 |           "base_uri": "https://localhost:8080/"
332 |         },
333 |         "id": "zQcdTTr7tO51",
334 |         "outputId": "abe46c73-e167-488f-8fbe-a55e696125b2"
335 |       },
336 |       "execution_count": 6,
337 |       "outputs": [
338 |         {
339 |           "output_type": "stream",
340 |           "name": "stdout",
341 |           "text": [
342 |             "(149, 5)\n"
343 |           ]
344 |         }
345 |       ]
346 |     },
347 |     {
348 |       "cell_type": "code",
349 |       "source": [
350 |         "# Print the first 20 data points -- the head of the dataset\n",
351 |         "print(df.head(10))"
352 |       ],
353 |       "metadata": {
354 |         "id": "PPFKzFXtt-B-",
355 |         "colab": {
356 |           "base_uri": "https://localhost:8080/"
357 |         },
358 |         "outputId": "790522fb-ae7b-4eb5-c26c-49b222fc4c89"
359 |       },
360 |       "execution_count": 7,
361 |       "outputs": [
362 |         {
363 |           "output_type": "stream",
364 |           "name": "stdout",
365 |           "text": [
366 |             "   5.1  3.5  1.4  0.2  Iris-setosa\n",
367 |             "0  4.9  3.0  1.4  0.2  Iris-setosa\n",
368 |             "1  4.7  3.2  1.3  0.2  Iris-setosa\n",
369 |             "2  4.6  3.1  1.5  0.2  Iris-setosa\n",
370 |             "3  5.0  3.6  1.4  0.2  Iris-setosa\n",
371 |             "4  5.4  3.9  1.7  0.4  Iris-setosa\n",
372 |             "5  4.6  3.4  1.4  0.3  Iris-setosa\n",
373 |             "6  5.0  3.4  1.5  0.2  Iris-setosa\n",
374 |             "7  4.4  2.9  1.4  0.2  Iris-setosa\n",
375 |             "8  4.9  3.1  1.5  0.1  Iris-setosa\n",
376 |             "9  5.4  3.7  1.5  0.2  Iris-setosa\n"
377 |           ]
378 |         }
379 |       ]
380 |     },
381 |     {
382 |       "cell_type": "code",
383 |       "source": [
384 |         "#4.3 Describing the data present in the dataset\n",
385 |         "#Use the describe function to describe some of the \n",
386 |         "#statistical properties of the data.\n",
387 |         "print(df.describe())\n",
388 |         "\n",
389 |         "\n",
390 |         "\n",
391 |         "\n",
392 |         "\n",
393 |         "\n",
394 |         "\n"
395 |       ],
396 |       "metadata": {
397 |         "id": "VGtPCZjKyr2R",
398 |         "colab": {
399 |           "base_uri": "https://localhost:8080/"
400 |         },
401 |         "outputId": "a000221a-5ed6-457b-a74b-c55e316f0c8d"
402 |       },
403 |       "execution_count": 8,
404 |       "outputs": [
405 |         {
406 |           "output_type": "stream",
407 |           "name": "stdout",
408 |           "text": [
409 |             "              5.1         3.5         1.4         0.2\n",
410 |             "count  149.000000  149.000000  149.000000  149.000000\n",
411 |             "mean     5.848322    3.051007    3.774497    1.205369\n",
412 |             "std      0.828594    0.433499    1.759651    0.761292\n",
413 |             "min      4.300000    2.000000    1.000000    0.100000\n",
414 |             "25%      5.100000    2.800000    1.600000    0.300000\n",
415 |             "50%      5.800000    3.000000    4.400000    1.300000\n",
416 |             "75%      6.400000    3.300000    5.100000    1.800000\n",
417 |             "max      7.900000    4.400000    6.900000    2.500000\n"
418 |           ]
419 |         }
420 |       ]
421 |     }
422 |   ]
423 | }


--------------------------------------------------------------------------------
/DSBDA A=3 part2 (1).ipynb:
--------------------------------------------------------------------------------
   1 | {
   2 |  "cells": [
   3 |   {
   4 |    "cell_type": "code",
   5 |    "execution_count": 1,
   6 |    "id": "4cf43d87",
   7 |    "metadata": {},
   8 |    "outputs": [],
   9 |    "source": [
  10 |     "import pandas as pd\n",
  11 |     "import numpy as np\n",
  12 |     "import matplotlib.pyplot as plt \n"
  13 |    ]
  14 |   },
  15 |   {
  16 |    "cell_type": "code",
  17 |    "execution_count": 2,
  18 |    "id": "5abb9d2c",
  19 |    "metadata": {},
  20 |    "outputs": [],
  21 |    "source": [
  22 |     "df=pd.read_csv('C:/Users/coeco/Downloads/Assign_3_Mall_Customers.csv')"
  23 |    ]
  24 |   },
  25 |   {
  26 |    "cell_type": "code",
  27 |    "execution_count": 3,
  28 |    "id": "c536e6b9",
  29 |    "metadata": {},
  30 |    "outputs": [],
  31 |    "source": [
  32 |     "df1=df\n",
  33 |     "df2=df1\n",
  34 |     "df3=df\n",
  35 |     "df4=df"
  36 |    ]
  37 |   },
  38 |   {
  39 |    "cell_type": "code",
  40 |    "execution_count": 4,
  41 |    "id": "cf5df6f0",
  42 |    "metadata": {},
  43 |    "outputs": [
  44 |     {
  45 |      "data": {
  46 |       "text/html": [
  47 |        "<div>\n",
  48 |        "<style scoped>\n",
  49 |        "    .dataframe tbody tr th:only-of-type {\n",
  50 |        "        vertical-align: middle;\n",
  51 |        "    }\n",
  52 |        "\n",
  53 |        "    .dataframe tbody tr th {\n",
  54 |        "        vertical-align: top;\n",
  55 |        "    }\n",
  56 |        "\n",
  57 |        "    .dataframe thead th {\n",
  58 |        "        text-align: right;\n",
  59 |        "    }\n",
  60 |        "</style>\n",
  61 |        "<table border=\"1\" class=\"dataframe\">\n",
  62 |        "  <thead>\n",
  63 |        "    <tr style=\"text-align: right;\">\n",
  64 |        "      <th></th>\n",
  65 |        "      <th>CustomerID</th>\n",
  66 |        "      <th>Gender</th>\n",
  67 |        "      <th>Age Group</th>\n",
  68 |        "      <th>Age</th>\n",
  69 |        "      <th>Salary</th>\n",
  70 |        "      <th>Spending Score (1-100)</th>\n",
  71 |        "    </tr>\n",
  72 |        "  </thead>\n",
  73 |        "  <tbody>\n",
  74 |        "    <tr>\n",
  75 |        "      <th>0</th>\n",
  76 |        "      <td>1</td>\n",
  77 |        "      <td>Male</td>\n",
  78 |        "      <td>Teen</td>\n",
  79 |        "      <td>19</td>\n",
  80 |        "      <td>15</td>\n",
  81 |        "      <td>39</td>\n",
  82 |        "    </tr>\n",
  83 |        "    <tr>\n",
  84 |        "      <th>1</th>\n",
  85 |        "      <td>2</td>\n",
  86 |        "      <td>Male</td>\n",
  87 |        "      <td>Middle Age</td>\n",
  88 |        "      <td>21</td>\n",
  89 |        "      <td>15</td>\n",
  90 |        "      <td>81</td>\n",
  91 |        "    </tr>\n",
  92 |        "    <tr>\n",
  93 |        "      <th>2</th>\n",
  94 |        "      <td>3</td>\n",
  95 |        "      <td>Female</td>\n",
  96 |        "      <td>Middle Age</td>\n",
  97 |        "      <td>20</td>\n",
  98 |        "      <td>16</td>\n",
  99 |        "      <td>6</td>\n",
 100 |        "    </tr>\n",
 101 |        "    <tr>\n",
 102 |        "      <th>3</th>\n",
 103 |        "      <td>4</td>\n",
 104 |        "      <td>Female</td>\n",
 105 |        "      <td>Middle Age</td>\n",
 106 |        "      <td>23</td>\n",
 107 |        "      <td>16</td>\n",
 108 |        "      <td>77</td>\n",
 109 |        "    </tr>\n",
 110 |        "    <tr>\n",
 111 |        "      <th>4</th>\n",
 112 |        "      <td>5</td>\n",
 113 |        "      <td>Female</td>\n",
 114 |        "      <td>Middle Age</td>\n",
 115 |        "      <td>31</td>\n",
 116 |        "      <td>17</td>\n",
 117 |        "      <td>40</td>\n",
 118 |        "    </tr>\n",
 119 |        "    <tr>\n",
 120 |        "      <th>...</th>\n",
 121 |        "      <td>...</td>\n",
 122 |        "      <td>...</td>\n",
 123 |        "      <td>...</td>\n",
 124 |        "      <td>...</td>\n",
 125 |        "      <td>...</td>\n",
 126 |        "      <td>...</td>\n",
 127 |        "    </tr>\n",
 128 |        "    <tr>\n",
 129 |        "      <th>195</th>\n",
 130 |        "      <td>196</td>\n",
 131 |        "      <td>Female</td>\n",
 132 |        "      <td>Middle Age</td>\n",
 133 |        "      <td>35</td>\n",
 134 |        "      <td>120</td>\n",
 135 |        "      <td>79</td>\n",
 136 |        "    </tr>\n",
 137 |        "    <tr>\n",
 138 |        "      <th>196</th>\n",
 139 |        "      <td>197</td>\n",
 140 |        "      <td>Female</td>\n",
 141 |        "      <td>Elder</td>\n",
 142 |        "      <td>45</td>\n",
 143 |        "      <td>126</td>\n",
 144 |        "      <td>28</td>\n",
 145 |        "    </tr>\n",
 146 |        "    <tr>\n",
 147 |        "      <th>197</th>\n",
 148 |        "      <td>198</td>\n",
 149 |        "      <td>Male</td>\n",
 150 |        "      <td>Middle Age</td>\n",
 151 |        "      <td>32</td>\n",
 152 |        "      <td>126</td>\n",
 153 |        "      <td>74</td>\n",
 154 |        "    </tr>\n",
 155 |        "    <tr>\n",
 156 |        "      <th>198</th>\n",
 157 |        "      <td>199</td>\n",
 158 |        "      <td>Male</td>\n",
 159 |        "      <td>Middle Age</td>\n",
 160 |        "      <td>32</td>\n",
 161 |        "      <td>137</td>\n",
 162 |        "      <td>18</td>\n",
 163 |        "    </tr>\n",
 164 |        "    <tr>\n",
 165 |        "      <th>199</th>\n",
 166 |        "      <td>200</td>\n",
 167 |        "      <td>Male</td>\n",
 168 |        "      <td>Middle Age</td>\n",
 169 |        "      <td>30</td>\n",
 170 |        "      <td>137</td>\n",
 171 |        "      <td>83</td>\n",
 172 |        "    </tr>\n",
 173 |        "  </tbody>\n",
 174 |        "</table>\n",
 175 |        "<p>200 rows × 6 columns</p>\n",
 176 |        "</div>"
 177 |       ],
 178 |       "text/plain": [
 179 |        "     CustomerID  Gender   Age Group  Age  Salary  Spending Score (1-100)\n",
 180 |        "0             1    Male        Teen   19      15                      39\n",
 181 |        "1             2    Male  Middle Age   21      15                      81\n",
 182 |        "2             3  Female  Middle Age   20      16                       6\n",
 183 |        "3             4  Female  Middle Age   23      16                      77\n",
 184 |        "4             5  Female  Middle Age   31      17                      40\n",
 185 |        "..          ...     ...         ...  ...     ...                     ...\n",
 186 |        "195         196  Female  Middle Age   35     120                      79\n",
 187 |        "196         197  Female       Elder   45     126                      28\n",
 188 |        "197         198    Male  Middle Age   32     126                      74\n",
 189 |        "198         199    Male  Middle Age   32     137                      18\n",
 190 |        "199         200    Male  Middle Age   30     137                      83\n",
 191 |        "\n",
 192 |        "[200 rows x 6 columns]"
 193 |       ]
 194 |      },
 195 |      "execution_count": 4,
 196 |      "metadata": {},
 197 |      "output_type": "execute_result"
 198 |     }
 199 |    ],
 200 |    "source": [
 201 |     "df"
 202 |    ]
 203 |   },
 204 |   {
 205 |    "cell_type": "code",
 206 |    "execution_count": 5,
 207 |    "id": "02c6d88f",
 208 |    "metadata": {},
 209 |    "outputs": [
 210 |     {
 211 |      "name": "stdout",
 212 |      "output_type": "stream",
 213 |      "text": [
 214 |       "<class 'pandas.core.frame.DataFrame'>\n",
 215 |       "RangeIndex: 200 entries, 0 to 199\n",
 216 |       "Data columns (total 6 columns):\n",
 217 |       " #   Column                  Non-Null Count  Dtype \n",
 218 |       "---  ------                  --------------  ----- \n",
 219 |       " 0   CustomerID              200 non-null    int64 \n",
 220 |       " 1   Gender                  200 non-null    object\n",
 221 |       " 2   Age Group               200 non-null    object\n",
 222 |       " 3   Age                     200 non-null    int64 \n",
 223 |       " 4   Salary                  200 non-null    int64 \n",
 224 |       " 5   Spending Score (1-100)  200 non-null    int64 \n",
 225 |       "dtypes: int64(4), object(2)\n",
 226 |       "memory usage: 9.5+ KB\n"
 227 |      ]
 228 |     }
 229 |    ],
 230 |    "source": [
 231 |     "df.info()"
 232 |    ]
 233 |   },
 234 |   {
 235 |    "cell_type": "code",
 236 |    "execution_count": 6,
 237 |    "id": "1dd78e6a",
 238 |    "metadata": {},
 239 |    "outputs": [
 240 |     {
 241 |      "data": {
 242 |       "text/plain": [
 243 |        "(200, 6)"
 244 |       ]
 245 |      },
 246 |      "execution_count": 6,
 247 |      "metadata": {},
 248 |      "output_type": "execute_result"
 249 |     }
 250 |    ],
 251 |    "source": [
 252 |     "df.shape"
 253 |    ]
 254 |   },
 255 |   {
 256 |    "cell_type": "code",
 257 |    "execution_count": 7,
 258 |    "id": "c1d4e462",
 259 |    "metadata": {},
 260 |    "outputs": [
 261 |     {
 262 |      "data": {
 263 |       "text/html": [
 264 |        "<div>\n",
 265 |        "<style scoped>\n",
 266 |        "    .dataframe tbody tr th:only-of-type {\n",
 267 |        "        vertical-align: middle;\n",
 268 |        "    }\n",
 269 |        "\n",
 270 |        "    .dataframe tbody tr th {\n",
 271 |        "        vertical-align: top;\n",
 272 |        "    }\n",
 273 |        "\n",
 274 |        "    .dataframe thead th {\n",
 275 |        "        text-align: right;\n",
 276 |        "    }\n",
 277 |        "</style>\n",
 278 |        "<table border=\"1\" class=\"dataframe\">\n",
 279 |        "  <thead>\n",
 280 |        "    <tr style=\"text-align: right;\">\n",
 281 |        "      <th></th>\n",
 282 |        "      <th>CustomerID</th>\n",
 283 |        "      <th>Gender</th>\n",
 284 |        "      <th>Age Group</th>\n",
 285 |        "      <th>Age</th>\n",
 286 |        "      <th>Salary</th>\n",
 287 |        "      <th>Spending Score (1-100)</th>\n",
 288 |        "    </tr>\n",
 289 |        "  </thead>\n",
 290 |        "  <tbody>\n",
 291 |        "    <tr>\n",
 292 |        "      <th>0</th>\n",
 293 |        "      <td>1</td>\n",
 294 |        "      <td>Male</td>\n",
 295 |        "      <td>Teen</td>\n",
 296 |        "      <td>19</td>\n",
 297 |        "      <td>15</td>\n",
 298 |        "      <td>39</td>\n",
 299 |        "    </tr>\n",
 300 |        "    <tr>\n",
 301 |        "      <th>1</th>\n",
 302 |        "      <td>2</td>\n",
 303 |        "      <td>Male</td>\n",
 304 |        "      <td>Middle Age</td>\n",
 305 |        "      <td>21</td>\n",
 306 |        "      <td>15</td>\n",
 307 |        "      <td>81</td>\n",
 308 |        "    </tr>\n",
 309 |        "    <tr>\n",
 310 |        "      <th>2</th>\n",
 311 |        "      <td>3</td>\n",
 312 |        "      <td>Female</td>\n",
 313 |        "      <td>Middle Age</td>\n",
 314 |        "      <td>20</td>\n",
 315 |        "      <td>16</td>\n",
 316 |        "      <td>6</td>\n",
 317 |        "    </tr>\n",
 318 |        "    <tr>\n",
 319 |        "      <th>3</th>\n",
 320 |        "      <td>4</td>\n",
 321 |        "      <td>Female</td>\n",
 322 |        "      <td>Middle Age</td>\n",
 323 |        "      <td>23</td>\n",
 324 |        "      <td>16</td>\n",
 325 |        "      <td>77</td>\n",
 326 |        "    </tr>\n",
 327 |        "    <tr>\n",
 328 |        "      <th>4</th>\n",
 329 |        "      <td>5</td>\n",
 330 |        "      <td>Female</td>\n",
 331 |        "      <td>Middle Age</td>\n",
 332 |        "      <td>31</td>\n",
 333 |        "      <td>17</td>\n",
 334 |        "      <td>40</td>\n",
 335 |        "    </tr>\n",
 336 |        "  </tbody>\n",
 337 |        "</table>\n",
 338 |        "</div>"
 339 |       ],
 340 |       "text/plain": [
 341 |        "   CustomerID  Gender   Age Group  Age  Salary  Spending Score (1-100)\n",
 342 |        "0           1    Male        Teen   19      15                      39\n",
 343 |        "1           2    Male  Middle Age   21      15                      81\n",
 344 |        "2           3  Female  Middle Age   20      16                       6\n",
 345 |        "3           4  Female  Middle Age   23      16                      77\n",
 346 |        "4           5  Female  Middle Age   31      17                      40"
 347 |       ]
 348 |      },
 349 |      "execution_count": 7,
 350 |      "metadata": {},
 351 |      "output_type": "execute_result"
 352 |     }
 353 |    ],
 354 |    "source": [
 355 |     "df.head()"
 356 |    ]
 357 |   },
 358 |   {
 359 |    "cell_type": "code",
 360 |    "execution_count": 8,
 361 |    "id": "0fe2e323",
 362 |    "metadata": {},
 363 |    "outputs": [
 364 |     {
 365 |      "data": {
 366 |       "text/html": [
 367 |        "<div>\n",
 368 |        "<style scoped>\n",
 369 |        "    .dataframe tbody tr th:only-of-type {\n",
 370 |        "        vertical-align: middle;\n",
 371 |        "    }\n",
 372 |        "\n",
 373 |        "    .dataframe tbody tr th {\n",
 374 |        "        vertical-align: top;\n",
 375 |        "    }\n",
 376 |        "\n",
 377 |        "    .dataframe thead th {\n",
 378 |        "        text-align: right;\n",
 379 |        "    }\n",
 380 |        "</style>\n",
 381 |        "<table border=\"1\" class=\"dataframe\">\n",
 382 |        "  <thead>\n",
 383 |        "    <tr style=\"text-align: right;\">\n",
 384 |        "      <th></th>\n",
 385 |        "      <th>CustomerID</th>\n",
 386 |        "      <th>Gender</th>\n",
 387 |        "      <th>Age Group</th>\n",
 388 |        "      <th>Age</th>\n",
 389 |        "      <th>Salary</th>\n",
 390 |        "      <th>Spending Score (1-100)</th>\n",
 391 |        "    </tr>\n",
 392 |        "  </thead>\n",
 393 |        "  <tbody>\n",
 394 |        "    <tr>\n",
 395 |        "      <th>195</th>\n",
 396 |        "      <td>196</td>\n",
 397 |        "      <td>Female</td>\n",
 398 |        "      <td>Middle Age</td>\n",
 399 |        "      <td>35</td>\n",
 400 |        "      <td>120</td>\n",
 401 |        "      <td>79</td>\n",
 402 |        "    </tr>\n",
 403 |        "    <tr>\n",
 404 |        "      <th>196</th>\n",
 405 |        "      <td>197</td>\n",
 406 |        "      <td>Female</td>\n",
 407 |        "      <td>Elder</td>\n",
 408 |        "      <td>45</td>\n",
 409 |        "      <td>126</td>\n",
 410 |        "      <td>28</td>\n",
 411 |        "    </tr>\n",
 412 |        "    <tr>\n",
 413 |        "      <th>197</th>\n",
 414 |        "      <td>198</td>\n",
 415 |        "      <td>Male</td>\n",
 416 |        "      <td>Middle Age</td>\n",
 417 |        "      <td>32</td>\n",
 418 |        "      <td>126</td>\n",
 419 |        "      <td>74</td>\n",
 420 |        "    </tr>\n",
 421 |        "    <tr>\n",
 422 |        "      <th>198</th>\n",
 423 |        "      <td>199</td>\n",
 424 |        "      <td>Male</td>\n",
 425 |        "      <td>Middle Age</td>\n",
 426 |        "      <td>32</td>\n",
 427 |        "      <td>137</td>\n",
 428 |        "      <td>18</td>\n",
 429 |        "    </tr>\n",
 430 |        "    <tr>\n",
 431 |        "      <th>199</th>\n",
 432 |        "      <td>200</td>\n",
 433 |        "      <td>Male</td>\n",
 434 |        "      <td>Middle Age</td>\n",
 435 |        "      <td>30</td>\n",
 436 |        "      <td>137</td>\n",
 437 |        "      <td>83</td>\n",
 438 |        "    </tr>\n",
 439 |        "  </tbody>\n",
 440 |        "</table>\n",
 441 |        "</div>"
 442 |       ],
 443 |       "text/plain": [
 444 |        "     CustomerID  Gender   Age Group  Age  Salary  Spending Score (1-100)\n",
 445 |        "195         196  Female  Middle Age   35     120                      79\n",
 446 |        "196         197  Female       Elder   45     126                      28\n",
 447 |        "197         198    Male  Middle Age   32     126                      74\n",
 448 |        "198         199    Male  Middle Age   32     137                      18\n",
 449 |        "199         200    Male  Middle Age   30     137                      83"
 450 |       ]
 451 |      },
 452 |      "execution_count": 8,
 453 |      "metadata": {},
 454 |      "output_type": "execute_result"
 455 |     }
 456 |    ],
 457 |    "source": [
 458 |     "df.tail()"
 459 |    ]
 460 |   },
 461 |   {
 462 |    "cell_type": "code",
 463 |    "execution_count": 9,
 464 |    "id": "d1080869",
 465 |    "metadata": {},
 466 |    "outputs": [
 467 |     {
 468 |      "data": {
 469 |       "text/html": [
 470 |        "<div>\n",
 471 |        "<style scoped>\n",
 472 |        "    .dataframe tbody tr th:only-of-type {\n",
 473 |        "        vertical-align: middle;\n",
 474 |        "    }\n",
 475 |        "\n",
 476 |        "    .dataframe tbody tr th {\n",
 477 |        "        vertical-align: top;\n",
 478 |        "    }\n",
 479 |        "\n",
 480 |        "    .dataframe thead th {\n",
 481 |        "        text-align: right;\n",
 482 |        "    }\n",
 483 |        "</style>\n",
 484 |        "<table border=\"1\" class=\"dataframe\">\n",
 485 |        "  <thead>\n",
 486 |        "    <tr style=\"text-align: right;\">\n",
 487 |        "      <th></th>\n",
 488 |        "      <th>CustomerID</th>\n",
 489 |        "      <th>Age</th>\n",
 490 |        "      <th>Salary</th>\n",
 491 |        "      <th>Spending Score (1-100)</th>\n",
 492 |        "    </tr>\n",
 493 |        "  </thead>\n",
 494 |        "  <tbody>\n",
 495 |        "    <tr>\n",
 496 |        "      <th>count</th>\n",
 497 |        "      <td>200.000000</td>\n",
 498 |        "      <td>200.000000</td>\n",
 499 |        "      <td>200.000000</td>\n",
 500 |        "      <td>200.000000</td>\n",
 501 |        "    </tr>\n",
 502 |        "    <tr>\n",
 503 |        "      <th>mean</th>\n",
 504 |        "      <td>100.500000</td>\n",
 505 |        "      <td>38.850000</td>\n",
 506 |        "      <td>60.560000</td>\n",
 507 |        "      <td>50.200000</td>\n",
 508 |        "    </tr>\n",
 509 |        "    <tr>\n",
 510 |        "      <th>std</th>\n",
 511 |        "      <td>57.879185</td>\n",
 512 |        "      <td>13.969007</td>\n",
 513 |        "      <td>26.264721</td>\n",
 514 |        "      <td>25.823522</td>\n",
 515 |        "    </tr>\n",
 516 |        "    <tr>\n",
 517 |        "      <th>min</th>\n",
 518 |        "      <td>1.000000</td>\n",
 519 |        "      <td>18.000000</td>\n",
 520 |        "      <td>15.000000</td>\n",
 521 |        "      <td>1.000000</td>\n",
 522 |        "    </tr>\n",
 523 |        "    <tr>\n",
 524 |        "      <th>25%</th>\n",
 525 |        "      <td>50.750000</td>\n",
 526 |        "      <td>28.750000</td>\n",
 527 |        "      <td>41.500000</td>\n",
 528 |        "      <td>34.750000</td>\n",
 529 |        "    </tr>\n",
 530 |        "    <tr>\n",
 531 |        "      <th>50%</th>\n",
 532 |        "      <td>100.500000</td>\n",
 533 |        "      <td>36.000000</td>\n",
 534 |        "      <td>61.500000</td>\n",
 535 |        "      <td>50.000000</td>\n",
 536 |        "    </tr>\n",
 537 |        "    <tr>\n",
 538 |        "      <th>75%</th>\n",
 539 |        "      <td>150.250000</td>\n",
 540 |        "      <td>49.000000</td>\n",
 541 |        "      <td>78.000000</td>\n",
 542 |        "      <td>73.000000</td>\n",
 543 |        "    </tr>\n",
 544 |        "    <tr>\n",
 545 |        "      <th>max</th>\n",
 546 |        "      <td>200.000000</td>\n",
 547 |        "      <td>70.000000</td>\n",
 548 |        "      <td>137.000000</td>\n",
 549 |        "      <td>99.000000</td>\n",
 550 |        "    </tr>\n",
 551 |        "  </tbody>\n",
 552 |        "</table>\n",
 553 |        "</div>"
 554 |       ],
 555 |       "text/plain": [
 556 |        "       CustomerID         Age      Salary  Spending Score (1-100)\n",
 557 |        "count  200.000000  200.000000  200.000000              200.000000\n",
 558 |        "mean   100.500000   38.850000   60.560000               50.200000\n",
 559 |        "std     57.879185   13.969007   26.264721               25.823522\n",
 560 |        "min      1.000000   18.000000   15.000000                1.000000\n",
 561 |        "25%     50.750000   28.750000   41.500000               34.750000\n",
 562 |        "50%    100.500000   36.000000   61.500000               50.000000\n",
 563 |        "75%    150.250000   49.000000   78.000000               73.000000\n",
 564 |        "max    200.000000   70.000000  137.000000               99.000000"
 565 |       ]
 566 |      },
 567 |      "execution_count": 9,
 568 |      "metadata": {},
 569 |      "output_type": "execute_result"
 570 |     }
 571 |    ],
 572 |    "source": [
 573 |     "df.describe()"
 574 |    ]
 575 |   },
 576 |   {
 577 |    "cell_type": "code",
 578 |    "execution_count": 10,
 579 |    "id": "dcd52d13",
 580 |    "metadata": {},
 581 |    "outputs": [],
 582 |    "source": [
 583 |     "import pandas as pd\n",
 584 |     "import numpy as np\n",
 585 |     "import requests\n",
 586 |     "df=pd.read_csv('C:/Users/coeco/Downloads/Assign_3_Mall_Customers.csv')"
 587 |    ]
 588 |   },
 589 |   {
 590 |    "cell_type": "code",
 591 |    "execution_count": 11,
 592 |    "id": "b0d17e5e",
 593 |    "metadata": {},
 594 |    "outputs": [
 595 |     {
 596 |      "data": {
 597 |       "text/plain": [
 598 |        "CustomerID    100.50\n",
 599 |        "Salary         60.56\n",
 600 |        "dtype: float64"
 601 |       ]
 602 |      },
 603 |      "execution_count": 11,
 604 |      "metadata": {},
 605 |      "output_type": "execute_result"
 606 |     }
 607 |    ],
 608 |    "source": [
 609 |     "df[['CustomerID','Salary']].mean()"
 610 |    ]
 611 |   },
 612 |   {
 613 |    "cell_type": "code",
 614 |    "execution_count": 12,
 615 |    "id": "e90b6adc",
 616 |    "metadata": {},
 617 |    "outputs": [
 618 |     {
 619 |      "data": {
 620 |       "text/plain": [
 621 |        "CustomerID                     1\n",
 622 |        "Gender                    Female\n",
 623 |        "Age Group                  Elder\n",
 624 |        "Age                           18\n",
 625 |        "Salary                        15\n",
 626 |        "Spending Score (1-100)         1\n",
 627 |        "dtype: object"
 628 |       ]
 629 |      },
 630 |      "execution_count": 12,
 631 |      "metadata": {},
 632 |      "output_type": "execute_result"
 633 |     }
 634 |    ],
 635 |    "source": [
 636 |     "df[['CustomerID','Gender','Age Group','Age','Salary','Spending Score (1-100)']].min()"
 637 |    ]
 638 |   },
 639 |   {
 640 |    "cell_type": "code",
 641 |    "execution_count": 13,
 642 |    "id": "130b0a2d",
 643 |    "metadata": {},
 644 |    "outputs": [
 645 |     {
 646 |      "data": {
 647 |       "text/plain": [
 648 |        "CustomerID                100.5\n",
 649 |        "Spending Score (1-100)     50.0\n",
 650 |        "dtype: float64"
 651 |       ]
 652 |      },
 653 |      "execution_count": 13,
 654 |      "metadata": {},
 655 |      "output_type": "execute_result"
 656 |     }
 657 |    ],
 658 |    "source": [
 659 |     "df[['CustomerID','Spending Score (1-100)']].median()"
 660 |    ]
 661 |   },
 662 |   {
 663 |    "cell_type": "code",
 664 |    "execution_count": 14,
 665 |    "id": "0a4c0f0e",
 666 |    "metadata": {},
 667 |    "outputs": [
 668 |     {
 669 |      "data": {
 670 |       "text/plain": [
 671 |        "CustomerID                 200\n",
 672 |        "Gender                    Male\n",
 673 |        "Age Group                 Teen\n",
 674 |        "Age                         70\n",
 675 |        "Salary                     137\n",
 676 |        "Spending Score (1-100)      99\n",
 677 |        "dtype: object"
 678 |       ]
 679 |      },
 680 |      "execution_count": 14,
 681 |      "metadata": {},
 682 |      "output_type": "execute_result"
 683 |     }
 684 |    ],
 685 |    "source": [
 686 |     "df[['CustomerID','Gender','Age Group','Age','Salary','Spending Score (1-100)']].max()"
 687 |    ]
 688 |   },
 689 |   {
 690 |    "cell_type": "code",
 691 |    "execution_count": 15,
 692 |    "id": "6f3a27dc",
 693 |    "metadata": {},
 694 |    "outputs": [
 695 |     {
 696 |      "data": {
 697 |       "text/plain": [
 698 |        "Salary                    26.264721\n",
 699 |        "Spending Score (1-100)    25.823522\n",
 700 |        "dtype: float64"
 701 |       ]
 702 |      },
 703 |      "execution_count": 15,
 704 |      "metadata": {},
 705 |      "output_type": "execute_result"
 706 |     }
 707 |    ],
 708 |    "source": [
 709 |     "df[['Salary','Spending Score (1-100)']].std()"
 710 |    ]
 711 |   },
 712 |   {
 713 |    "cell_type": "code",
 714 |    "execution_count": 16,
 715 |    "id": "5533ecbf",
 716 |    "metadata": {},
 717 |    "outputs": [],
 718 |    "source": [
 719 |     "df2=df.groupby('Gender')"
 720 |    ]
 721 |   },
 722 |   {
 723 |    "cell_type": "code",
 724 |    "execution_count": 17,
 725 |    "id": "43f3c88e",
 726 |    "metadata": {},
 727 |    "outputs": [
 728 |     {
 729 |      "data": {
 730 |       "text/plain": [
 731 |        "<pandas.core.groupby.generic.DataFrameGroupBy object at 0x0000027491A773D0>"
 732 |       ]
 733 |      },
 734 |      "execution_count": 17,
 735 |      "metadata": {},
 736 |      "output_type": "execute_result"
 737 |     }
 738 |    ],
 739 |    "source": [
 740 |     "df2"
 741 |    ]
 742 |   },
 743 |   {
 744 |    "cell_type": "code",
 745 |    "execution_count": 18,
 746 |    "id": "f915ab77",
 747 |    "metadata": {},
 748 |    "outputs": [
 749 |     {
 750 |      "name": "stdout",
 751 |      "output_type": "stream",
 752 |      "text": [
 753 |       "Female\n",
 754 |       "     CustomerID  Gender   Age Group  Age  Salary  Spending Score (1-100)\n",
 755 |       "2             3  Female  Middle Age   20      16                       6\n",
 756 |       "3             4  Female  Middle Age   23      16                      77\n",
 757 |       "4             5  Female  Middle Age   31      17                      40\n",
 758 |       "5             6  Female  Middle Age   22      17                      76\n",
 759 |       "6             7  Female  Middle Age   35      18                       6\n",
 760 |       "..          ...     ...         ...  ...     ...                     ...\n",
 761 |       "191         192  Female  Middle Age   32     103                      69\n",
 762 |       "193         194  Female  Middle Age   38     113                      91\n",
 763 |       "194         195  Female       Elder   47     120                      16\n",
 764 |       "195         196  Female  Middle Age   35     120                      79\n",
 765 |       "196         197  Female       Elder   45     126                      28\n",
 766 |       "\n",
 767 |       "[112 rows x 6 columns]\n",
 768 |       "Male\n",
 769 |       "     CustomerID Gender   Age Group  Age  Salary  Spending Score (1-100)\n",
 770 |       "0             1   Male        Teen   19      15                      39\n",
 771 |       "1             2   Male  Middle Age   21      15                      81\n",
 772 |       "8             9   Male       Elder   64      19                       3\n",
 773 |       "10           11   Male       Elder   67      19                      14\n",
 774 |       "14           15   Male  Middle Age   37      20                      13\n",
 775 |       "..          ...    ...         ...  ...     ...                     ...\n",
 776 |       "187         188   Male  Middle Age   28     101                      68\n",
 777 |       "192         193   Male  Middle Age   33     113                       8\n",
 778 |       "197         198   Male  Middle Age   32     126                      74\n",
 779 |       "198         199   Male  Middle Age   32     137                      18\n",
 780 |       "199         200   Male  Middle Age   30     137                      83\n",
 781 |       "\n",
 782 |       "[88 rows x 6 columns]\n"
 783 |      ]
 784 |     }
 785 |    ],
 786 |    "source": [
 787 |     "for Gender,Gender_f in df2:\n",
 788 |     "    print(Gender)\n",
 789 |     "    print(Gender_f)"
 790 |    ]
 791 |   },
 792 |   {
 793 |    "cell_type": "code",
 794 |    "execution_count": 19,
 795 |    "id": "62be058c",
 796 |    "metadata": {},
 797 |    "outputs": [
 798 |     {
 799 |      "data": {
 800 |       "text/html": [
 801 |        "<div>\n",
 802 |        "<style scoped>\n",
 803 |        "    .dataframe tbody tr th:only-of-type {\n",
 804 |        "        vertical-align: middle;\n",
 805 |        "    }\n",
 806 |        "\n",
 807 |        "    .dataframe tbody tr th {\n",
 808 |        "        vertical-align: top;\n",
 809 |        "    }\n",
 810 |        "\n",
 811 |        "    .dataframe thead th {\n",
 812 |        "        text-align: right;\n",
 813 |        "    }\n",
 814 |        "</style>\n",
 815 |        "<table border=\"1\" class=\"dataframe\">\n",
 816 |        "  <thead>\n",
 817 |        "    <tr style=\"text-align: right;\">\n",
 818 |        "      <th></th>\n",
 819 |        "      <th>CustomerID</th>\n",
 820 |        "      <th>Gender</th>\n",
 821 |        "      <th>Age Group</th>\n",
 822 |        "      <th>Age</th>\n",
 823 |        "      <th>Salary</th>\n",
 824 |        "      <th>Spending Score (1-100)</th>\n",
 825 |        "    </tr>\n",
 826 |        "  </thead>\n",
 827 |        "  <tbody>\n",
 828 |        "    <tr>\n",
 829 |        "      <th>2</th>\n",
 830 |        "      <td>3</td>\n",
 831 |        "      <td>Female</td>\n",
 832 |        "      <td>Middle Age</td>\n",
 833 |        "      <td>20</td>\n",
 834 |        "      <td>16</td>\n",
 835 |        "      <td>6</td>\n",
 836 |        "    </tr>\n",
 837 |        "    <tr>\n",
 838 |        "      <th>3</th>\n",
 839 |        "      <td>4</td>\n",
 840 |        "      <td>Female</td>\n",
 841 |        "      <td>Middle Age</td>\n",
 842 |        "      <td>23</td>\n",
 843 |        "      <td>16</td>\n",
 844 |        "      <td>77</td>\n",
 845 |        "    </tr>\n",
 846 |        "    <tr>\n",
 847 |        "      <th>4</th>\n",
 848 |        "      <td>5</td>\n",
 849 |        "      <td>Female</td>\n",
 850 |        "      <td>Middle Age</td>\n",
 851 |        "      <td>31</td>\n",
 852 |        "      <td>17</td>\n",
 853 |        "      <td>40</td>\n",
 854 |        "    </tr>\n",
 855 |        "    <tr>\n",
 856 |        "      <th>5</th>\n",
 857 |        "      <td>6</td>\n",
 858 |        "      <td>Female</td>\n",
 859 |        "      <td>Middle Age</td>\n",
 860 |        "      <td>22</td>\n",
 861 |        "      <td>17</td>\n",
 862 |        "      <td>76</td>\n",
 863 |        "    </tr>\n",
 864 |        "    <tr>\n",
 865 |        "      <th>6</th>\n",
 866 |        "      <td>7</td>\n",
 867 |        "      <td>Female</td>\n",
 868 |        "      <td>Middle Age</td>\n",
 869 |        "      <td>35</td>\n",
 870 |        "      <td>18</td>\n",
 871 |        "      <td>6</td>\n",
 872 |        "    </tr>\n",
 873 |        "    <tr>\n",
 874 |        "      <th>...</th>\n",
 875 |        "      <td>...</td>\n",
 876 |        "      <td>...</td>\n",
 877 |        "      <td>...</td>\n",
 878 |        "      <td>...</td>\n",
 879 |        "      <td>...</td>\n",
 880 |        "      <td>...</td>\n",
 881 |        "    </tr>\n",
 882 |        "    <tr>\n",
 883 |        "      <th>191</th>\n",
 884 |        "      <td>192</td>\n",
 885 |        "      <td>Female</td>\n",
 886 |        "      <td>Middle Age</td>\n",
 887 |        "      <td>32</td>\n",
 888 |        "      <td>103</td>\n",
 889 |        "      <td>69</td>\n",
 890 |        "    </tr>\n",
 891 |        "    <tr>\n",
 892 |        "      <th>193</th>\n",
 893 |        "      <td>194</td>\n",
 894 |        "      <td>Female</td>\n",
 895 |        "      <td>Middle Age</td>\n",
 896 |        "      <td>38</td>\n",
 897 |        "      <td>113</td>\n",
 898 |        "      <td>91</td>\n",
 899 |        "    </tr>\n",
 900 |        "    <tr>\n",
 901 |        "      <th>194</th>\n",
 902 |        "      <td>195</td>\n",
 903 |        "      <td>Female</td>\n",
 904 |        "      <td>Elder</td>\n",
 905 |        "      <td>47</td>\n",
 906 |        "      <td>120</td>\n",
 907 |        "      <td>16</td>\n",
 908 |        "    </tr>\n",
 909 |        "    <tr>\n",
 910 |        "      <th>195</th>\n",
 911 |        "      <td>196</td>\n",
 912 |        "      <td>Female</td>\n",
 913 |        "      <td>Middle Age</td>\n",
 914 |        "      <td>35</td>\n",
 915 |        "      <td>120</td>\n",
 916 |        "      <td>79</td>\n",
 917 |        "    </tr>\n",
 918 |        "    <tr>\n",
 919 |        "      <th>196</th>\n",
 920 |        "      <td>197</td>\n",
 921 |        "      <td>Female</td>\n",
 922 |        "      <td>Elder</td>\n",
 923 |        "      <td>45</td>\n",
 924 |        "      <td>126</td>\n",
 925 |        "      <td>28</td>\n",
 926 |        "    </tr>\n",
 927 |        "  </tbody>\n",
 928 |        "</table>\n",
 929 |        "<p>112 rows × 6 columns</p>\n",
 930 |        "</div>"
 931 |       ],
 932 |       "text/plain": [
 933 |        "     CustomerID  Gender   Age Group  Age  Salary  Spending Score (1-100)\n",
 934 |        "2             3  Female  Middle Age   20      16                       6\n",
 935 |        "3             4  Female  Middle Age   23      16                      77\n",
 936 |        "4             5  Female  Middle Age   31      17                      40\n",
 937 |        "5             6  Female  Middle Age   22      17                      76\n",
 938 |        "6             7  Female  Middle Age   35      18                       6\n",
 939 |        "..          ...     ...         ...  ...     ...                     ...\n",
 940 |        "191         192  Female  Middle Age   32     103                      69\n",
 941 |        "193         194  Female  Middle Age   38     113                      91\n",
 942 |        "194         195  Female       Elder   47     120                      16\n",
 943 |        "195         196  Female  Middle Age   35     120                      79\n",
 944 |        "196         197  Female       Elder   45     126                      28\n",
 945 |        "\n",
 946 |        "[112 rows x 6 columns]"
 947 |       ]
 948 |      },
 949 |      "execution_count": 19,
 950 |      "metadata": {},
 951 |      "output_type": "execute_result"
 952 |     }
 953 |    ],
 954 |    "source": [
 955 |     "df2.get_group('Female')"
 956 |    ]
 957 |   },
 958 |   {
 959 |    "cell_type": "code",
 960 |    "execution_count": 20,
 961 |    "id": "6e269f8d",
 962 |    "metadata": {},
 963 |    "outputs": [
 964 |     {
 965 |      "data": {
 966 |       "text/html": [
 967 |        "<div>\n",
 968 |        "<style scoped>\n",
 969 |        "    .dataframe tbody tr th:only-of-type {\n",
 970 |        "        vertical-align: middle;\n",
 971 |        "    }\n",
 972 |        "\n",
 973 |        "    .dataframe tbody tr th {\n",
 974 |        "        vertical-align: top;\n",
 975 |        "    }\n",
 976 |        "\n",
 977 |        "    .dataframe thead th {\n",
 978 |        "        text-align: right;\n",
 979 |        "    }\n",
 980 |        "</style>\n",
 981 |        "<table border=\"1\" class=\"dataframe\">\n",
 982 |        "  <thead>\n",
 983 |        "    <tr style=\"text-align: right;\">\n",
 984 |        "      <th></th>\n",
 985 |        "      <th>CustomerID</th>\n",
 986 |        "      <th>Gender</th>\n",
 987 |        "      <th>Age Group</th>\n",
 988 |        "      <th>Age</th>\n",
 989 |        "      <th>Salary</th>\n",
 990 |        "      <th>Spending Score (1-100)</th>\n",
 991 |        "    </tr>\n",
 992 |        "  </thead>\n",
 993 |        "  <tbody>\n",
 994 |        "    <tr>\n",
 995 |        "      <th>0</th>\n",
 996 |        "      <td>1</td>\n",
 997 |        "      <td>Male</td>\n",
 998 |        "      <td>Teen</td>\n",
 999 |        "      <td>19</td>\n",
1000 |        "      <td>15</td>\n",
1001 |        "      <td>39</td>\n",
1002 |        "    </tr>\n",
1003 |        "    <tr>\n",
1004 |        "      <th>1</th>\n",
1005 |        "      <td>2</td>\n",
1006 |        "      <td>Male</td>\n",
1007 |        "      <td>Middle Age</td>\n",
1008 |        "      <td>21</td>\n",
1009 |        "      <td>15</td>\n",
1010 |        "      <td>81</td>\n",
1011 |        "    </tr>\n",
1012 |        "    <tr>\n",
1013 |        "      <th>8</th>\n",
1014 |        "      <td>9</td>\n",
1015 |        "      <td>Male</td>\n",
1016 |        "      <td>Elder</td>\n",
1017 |        "      <td>64</td>\n",
1018 |        "      <td>19</td>\n",
1019 |        "      <td>3</td>\n",
1020 |        "    </tr>\n",
1021 |        "    <tr>\n",
1022 |        "      <th>10</th>\n",
1023 |        "      <td>11</td>\n",
1024 |        "      <td>Male</td>\n",
1025 |        "      <td>Elder</td>\n",
1026 |        "      <td>67</td>\n",
1027 |        "      <td>19</td>\n",
1028 |        "      <td>14</td>\n",
1029 |        "    </tr>\n",
1030 |        "    <tr>\n",
1031 |        "      <th>14</th>\n",
1032 |        "      <td>15</td>\n",
1033 |        "      <td>Male</td>\n",
1034 |        "      <td>Middle Age</td>\n",
1035 |        "      <td>37</td>\n",
1036 |        "      <td>20</td>\n",
1037 |        "      <td>13</td>\n",
1038 |        "    </tr>\n",
1039 |        "    <tr>\n",
1040 |        "      <th>...</th>\n",
1041 |        "      <td>...</td>\n",
1042 |        "      <td>...</td>\n",
1043 |        "      <td>...</td>\n",
1044 |        "      <td>...</td>\n",
1045 |        "      <td>...</td>\n",
1046 |        "      <td>...</td>\n",
1047 |        "    </tr>\n",
1048 |        "    <tr>\n",
1049 |        "      <th>187</th>\n",
1050 |        "      <td>188</td>\n",
1051 |        "      <td>Male</td>\n",
1052 |        "      <td>Middle Age</td>\n",
1053 |        "      <td>28</td>\n",
1054 |        "      <td>101</td>\n",
1055 |        "      <td>68</td>\n",
1056 |        "    </tr>\n",
1057 |        "    <tr>\n",
1058 |        "      <th>192</th>\n",
1059 |        "      <td>193</td>\n",
1060 |        "      <td>Male</td>\n",
1061 |        "      <td>Middle Age</td>\n",
1062 |        "      <td>33</td>\n",
1063 |        "      <td>113</td>\n",
1064 |        "      <td>8</td>\n",
1065 |        "    </tr>\n",
1066 |        "    <tr>\n",
1067 |        "      <th>197</th>\n",
1068 |        "      <td>198</td>\n",
1069 |        "      <td>Male</td>\n",
1070 |        "      <td>Middle Age</td>\n",
1071 |        "      <td>32</td>\n",
1072 |        "      <td>126</td>\n",
1073 |        "      <td>74</td>\n",
1074 |        "    </tr>\n",
1075 |        "    <tr>\n",
1076 |        "      <th>198</th>\n",
1077 |        "      <td>199</td>\n",
1078 |        "      <td>Male</td>\n",
1079 |        "      <td>Middle Age</td>\n",
1080 |        "      <td>32</td>\n",
1081 |        "      <td>137</td>\n",
1082 |        "      <td>18</td>\n",
1083 |        "    </tr>\n",
1084 |        "    <tr>\n",
1085 |        "      <th>199</th>\n",
1086 |        "      <td>200</td>\n",
1087 |        "      <td>Male</td>\n",
1088 |        "      <td>Middle Age</td>\n",
1089 |        "      <td>30</td>\n",
1090 |        "      <td>137</td>\n",
1091 |        "      <td>83</td>\n",
1092 |        "    </tr>\n",
1093 |        "  </tbody>\n",
1094 |        "</table>\n",
1095 |        "<p>88 rows × 6 columns</p>\n",
1096 |        "</div>"
1097 |       ],
1098 |       "text/plain": [
1099 |        "     CustomerID Gender   Age Group  Age  Salary  Spending Score (1-100)\n",
1100 |        "0             1   Male        Teen   19      15                      39\n",
1101 |        "1             2   Male  Middle Age   21      15                      81\n",
1102 |        "8             9   Male       Elder   64      19                       3\n",
1103 |        "10           11   Male       Elder   67      19                      14\n",
1104 |        "14           15   Male  Middle Age   37      20                      13\n",
1105 |        "..          ...    ...         ...  ...     ...                     ...\n",
1106 |        "187         188   Male  Middle Age   28     101                      68\n",
1107 |        "192         193   Male  Middle Age   33     113                       8\n",
1108 |        "197         198   Male  Middle Age   32     126                      74\n",
1109 |        "198         199   Male  Middle Age   32     137                      18\n",
1110 |        "199         200   Male  Middle Age   30     137                      83\n",
1111 |        "\n",
1112 |        "[88 rows x 6 columns]"
1113 |       ]
1114 |      },
1115 |      "execution_count": 20,
1116 |      "metadata": {},
1117 |      "output_type": "execute_result"
1118 |     }
1119 |    ],
1120 |    "source": [
1121 |     "df2.get_group('Male')"
1122 |    ]
1123 |   },
1124 |   {
1125 |    "cell_type": "code",
1126 |    "execution_count": 21,
1127 |    "id": "5edd89ba",
1128 |    "metadata": {},
1129 |    "outputs": [
1130 |     {
1131 |      "data": {
1132 |       "text/html": [
1133 |        "<div>\n",
1134 |        "<style scoped>\n",
1135 |        "    .dataframe tbody tr th:only-of-type {\n",
1136 |        "        vertical-align: middle;\n",
1137 |        "    }\n",
1138 |        "\n",
1139 |        "    .dataframe tbody tr th {\n",
1140 |        "        vertical-align: top;\n",
1141 |        "    }\n",
1142 |        "\n",
1143 |        "    .dataframe thead th {\n",
1144 |        "        text-align: right;\n",
1145 |        "    }\n",
1146 |        "</style>\n",
1147 |        "<table border=\"1\" class=\"dataframe\">\n",
1148 |        "  <thead>\n",
1149 |        "    <tr style=\"text-align: right;\">\n",
1150 |        "      <th></th>\n",
1151 |        "      <th>CustomerID</th>\n",
1152 |        "      <th>Gender</th>\n",
1153 |        "      <th>Age Group</th>\n",
1154 |        "      <th>Age</th>\n",
1155 |        "      <th>Salary</th>\n",
1156 |        "      <th>Spending Score (1-100)</th>\n",
1157 |        "    </tr>\n",
1158 |        "    <tr>\n",
1159 |        "      <th>Gender</th>\n",
1160 |        "      <th></th>\n",
1161 |        "      <th></th>\n",
1162 |        "      <th></th>\n",
1163 |        "      <th></th>\n",
1164 |        "      <th></th>\n",
1165 |        "      <th></th>\n",
1166 |        "    </tr>\n",
1167 |        "  </thead>\n",
1168 |        "  <tbody>\n",
1169 |        "    <tr>\n",
1170 |        "      <th>Female</th>\n",
1171 |        "      <td>197</td>\n",
1172 |        "      <td>Female</td>\n",
1173 |        "      <td>Teen</td>\n",
1174 |        "      <td>68</td>\n",
1175 |        "      <td>126</td>\n",
1176 |        "      <td>99</td>\n",
1177 |        "    </tr>\n",
1178 |        "    <tr>\n",
1179 |        "      <th>Male</th>\n",
1180 |        "      <td>200</td>\n",
1181 |        "      <td>Male</td>\n",
1182 |        "      <td>Teen</td>\n",
1183 |        "      <td>70</td>\n",
1184 |        "      <td>137</td>\n",
1185 |        "      <td>97</td>\n",
1186 |        "    </tr>\n",
1187 |        "  </tbody>\n",
1188 |        "</table>\n",
1189 |        "</div>"
1190 |       ],
1191 |       "text/plain": [
1192 |        "        CustomerID  Gender Age Group  Age  Salary  Spending Score (1-100)\n",
1193 |        "Gender                                                                   \n",
1194 |        "Female         197  Female      Teen   68     126                      99\n",
1195 |        "Male           200    Male      Teen   70     137                      97"
1196 |       ]
1197 |      },
1198 |      "execution_count": 21,
1199 |      "metadata": {},
1200 |      "output_type": "execute_result"
1201 |     }
1202 |    ],
1203 |    "source": [
1204 |     "df2[['CustomerID','Gender','Age Group','Age','Salary','Spending Score (1-100)']].max()"
1205 |    ]
1206 |   },
1207 |   {
1208 |    "cell_type": "code",
1209 |    "execution_count": 22,
1210 |    "id": "64af1317",
1211 |    "metadata": {},
1212 |    "outputs": [
1213 |     {
1214 |      "data": {
1215 |       "text/html": [
1216 |        "<div>\n",
1217 |        "<style scoped>\n",
1218 |        "    .dataframe tbody tr th:only-of-type {\n",
1219 |        "        vertical-align: middle;\n",
1220 |        "    }\n",
1221 |        "\n",
1222 |        "    .dataframe tbody tr th {\n",
1223 |        "        vertical-align: top;\n",
1224 |        "    }\n",
1225 |        "\n",
1226 |        "    .dataframe thead th {\n",
1227 |        "        text-align: right;\n",
1228 |        "    }\n",
1229 |        "</style>\n",
1230 |        "<table border=\"1\" class=\"dataframe\">\n",
1231 |        "  <thead>\n",
1232 |        "    <tr style=\"text-align: right;\">\n",
1233 |        "      <th></th>\n",
1234 |        "      <th>CustomerID</th>\n",
1235 |        "      <th>Gender</th>\n",
1236 |        "      <th>Age Group</th>\n",
1237 |        "      <th>Age</th>\n",
1238 |        "      <th>Salary</th>\n",
1239 |        "      <th>Spending Score (1-100)</th>\n",
1240 |        "    </tr>\n",
1241 |        "    <tr>\n",
1242 |        "      <th>Gender</th>\n",
1243 |        "      <th></th>\n",
1244 |        "      <th></th>\n",
1245 |        "      <th></th>\n",
1246 |        "      <th></th>\n",
1247 |        "      <th></th>\n",
1248 |        "      <th></th>\n",
1249 |        "    </tr>\n",
1250 |        "  </thead>\n",
1251 |        "  <tbody>\n",
1252 |        "    <tr>\n",
1253 |        "      <th>Female</th>\n",
1254 |        "      <td>3</td>\n",
1255 |        "      <td>Female</td>\n",
1256 |        "      <td>Elder</td>\n",
1257 |        "      <td>18</td>\n",
1258 |        "      <td>16</td>\n",
1259 |        "      <td>5</td>\n",
1260 |        "    </tr>\n",
1261 |        "    <tr>\n",
1262 |        "      <th>Male</th>\n",
1263 |        "      <td>1</td>\n",
1264 |        "      <td>Male</td>\n",
1265 |        "      <td>Elder</td>\n",
1266 |        "      <td>18</td>\n",
1267 |        "      <td>15</td>\n",
1268 |        "      <td>1</td>\n",
1269 |        "    </tr>\n",
1270 |        "  </tbody>\n",
1271 |        "</table>\n",
1272 |        "</div>"
1273 |       ],
1274 |       "text/plain": [
1275 |        "        CustomerID  Gender Age Group  Age  Salary  Spending Score (1-100)\n",
1276 |        "Gender                                                                   \n",
1277 |        "Female           3  Female     Elder   18      16                       5\n",
1278 |        "Male             1    Male     Elder   18      15                       1"
1279 |       ]
1280 |      },
1281 |      "execution_count": 22,
1282 |      "metadata": {},
1283 |      "output_type": "execute_result"
1284 |     }
1285 |    ],
1286 |    "source": [
1287 |     "df2[['CustomerID','Gender','Age Group','Age','Salary','Spending Score (1-100)']].min()"
1288 |    ]
1289 |   },
1290 |   {
1291 |    "cell_type": "code",
1292 |    "execution_count": 23,
1293 |    "id": "2768daf5",
1294 |    "metadata": {},
1295 |    "outputs": [
1296 |     {
1297 |      "data": {
1298 |       "text/html": [
1299 |        "<div>\n",
1300 |        "<style scoped>\n",
1301 |        "    .dataframe tbody tr th:only-of-type {\n",
1302 |        "        vertical-align: middle;\n",
1303 |        "    }\n",
1304 |        "\n",
1305 |        "    .dataframe tbody tr th {\n",
1306 |        "        vertical-align: top;\n",
1307 |        "    }\n",
1308 |        "\n",
1309 |        "    .dataframe thead th {\n",
1310 |        "        text-align: right;\n",
1311 |        "    }\n",
1312 |        "</style>\n",
1313 |        "<table border=\"1\" class=\"dataframe\">\n",
1314 |        "  <thead>\n",
1315 |        "    <tr style=\"text-align: right;\">\n",
1316 |        "      <th></th>\n",
1317 |        "      <th>CustomerID</th>\n",
1318 |        "      <th>Age</th>\n",
1319 |        "      <th>Salary</th>\n",
1320 |        "      <th>Spending Score (1-100)</th>\n",
1321 |        "    </tr>\n",
1322 |        "    <tr>\n",
1323 |        "      <th>Gender</th>\n",
1324 |        "      <th></th>\n",
1325 |        "      <th></th>\n",
1326 |        "      <th></th>\n",
1327 |        "      <th></th>\n",
1328 |        "    </tr>\n",
1329 |        "  </thead>\n",
1330 |        "  <tbody>\n",
1331 |        "    <tr>\n",
1332 |        "      <th>Female</th>\n",
1333 |        "      <td>97.562500</td>\n",
1334 |        "      <td>38.098214</td>\n",
1335 |        "      <td>59.250000</td>\n",
1336 |        "      <td>51.526786</td>\n",
1337 |        "    </tr>\n",
1338 |        "    <tr>\n",
1339 |        "      <th>Male</th>\n",
1340 |        "      <td>104.238636</td>\n",
1341 |        "      <td>39.806818</td>\n",
1342 |        "      <td>62.227273</td>\n",
1343 |        "      <td>48.511364</td>\n",
1344 |        "    </tr>\n",
1345 |        "  </tbody>\n",
1346 |        "</table>\n",
1347 |        "</div>"
1348 |       ],
1349 |       "text/plain": [
1350 |        "        CustomerID        Age     Salary  Spending Score (1-100)\n",
1351 |        "Gender                                                          \n",
1352 |        "Female   97.562500  38.098214  59.250000               51.526786\n",
1353 |        "Male    104.238636  39.806818  62.227273               48.511364"
1354 |       ]
1355 |      },
1356 |      "execution_count": 23,
1357 |      "metadata": {},
1358 |      "output_type": "execute_result"
1359 |     }
1360 |    ],
1361 |    "source": [
1362 |     "df2[['CustomerID','Gender','Age Group','Age','Salary','Spending Score (1-100)']].mean()"
1363 |    ]
1364 |   },
1365 |   {
1366 |    "cell_type": "code",
1367 |    "execution_count": 24,
1368 |    "id": "6dd4b774",
1369 |    "metadata": {},
1370 |    "outputs": [
1371 |     {
1372 |      "data": {
1373 |       "text/html": [
1374 |        "<div>\n",
1375 |        "<style scoped>\n",
1376 |        "    .dataframe tbody tr th:only-of-type {\n",
1377 |        "        vertical-align: middle;\n",
1378 |        "    }\n",
1379 |        "\n",
1380 |        "    .dataframe tbody tr th {\n",
1381 |        "        vertical-align: top;\n",
1382 |        "    }\n",
1383 |        "\n",
1384 |        "    .dataframe thead th {\n",
1385 |        "        text-align: right;\n",
1386 |        "    }\n",
1387 |        "</style>\n",
1388 |        "<table border=\"1\" class=\"dataframe\">\n",
1389 |        "  <thead>\n",
1390 |        "    <tr style=\"text-align: right;\">\n",
1391 |        "      <th></th>\n",
1392 |        "      <th>CustomerID</th>\n",
1393 |        "      <th>Age</th>\n",
1394 |        "      <th>Salary</th>\n",
1395 |        "      <th>Spending Score (1-100)</th>\n",
1396 |        "    </tr>\n",
1397 |        "    <tr>\n",
1398 |        "      <th>Gender</th>\n",
1399 |        "      <th></th>\n",
1400 |        "      <th></th>\n",
1401 |        "      <th></th>\n",
1402 |        "      <th></th>\n",
1403 |        "    </tr>\n",
1404 |        "  </thead>\n",
1405 |        "  <tbody>\n",
1406 |        "    <tr>\n",
1407 |        "      <th>Female</th>\n",
1408 |        "      <td>58.276412</td>\n",
1409 |        "      <td>12.644095</td>\n",
1410 |        "      <td>26.011952</td>\n",
1411 |        "      <td>24.11495</td>\n",
1412 |        "    </tr>\n",
1413 |        "    <tr>\n",
1414 |        "      <th>Male</th>\n",
1415 |        "      <td>57.483830</td>\n",
1416 |        "      <td>15.514812</td>\n",
1417 |        "      <td>26.638373</td>\n",
1418 |        "      <td>27.89677</td>\n",
1419 |        "    </tr>\n",
1420 |        "  </tbody>\n",
1421 |        "</table>\n",
1422 |        "</div>"
1423 |       ],
1424 |       "text/plain": [
1425 |        "        CustomerID        Age     Salary  Spending Score (1-100)\n",
1426 |        "Gender                                                          \n",
1427 |        "Female   58.276412  12.644095  26.011952                24.11495\n",
1428 |        "Male     57.483830  15.514812  26.638373                27.89677"
1429 |       ]
1430 |      },
1431 |      "execution_count": 24,
1432 |      "metadata": {},
1433 |      "output_type": "execute_result"
1434 |     }
1435 |    ],
1436 |    "source": [
1437 |     "df2[['CustomerID','Gender','Age Group','Age','Salary','Spending Score (1-100)']].std()"
1438 |    ]
1439 |   },
1440 |   {
1441 |    "cell_type": "code",
1442 |    "execution_count": 25,
1443 |    "id": "0665061d",
1444 |    "metadata": {},
1445 |    "outputs": [],
1446 |    "source": [
1447 |     "a=np.percentile(df3['Age'],50)"
1448 |    ]
1449 |   },
1450 |   {
1451 |    "cell_type": "code",
1452 |    "execution_count": 26,
1453 |    "id": "4656b1a0",
1454 |    "metadata": {},
1455 |    "outputs": [
1456 |     {
1457 |      "data": {
1458 |       "text/plain": [
1459 |        "36.0"
1460 |       ]
1461 |      },
1462 |      "execution_count": 26,
1463 |      "metadata": {},
1464 |      "output_type": "execute_result"
1465 |     }
1466 |    ],
1467 |    "source": [
1468 |     "a"
1469 |    ]
1470 |   },
1471 |   {
1472 |    "cell_type": "code",
1473 |    "execution_count": 27,
1474 |    "id": "724e267c",
1475 |    "metadata": {},
1476 |    "outputs": [],
1477 |    "source": [
1478 |     "b=np.percentile(df3['Age'],100)"
1479 |    ]
1480 |   },
1481 |   {
1482 |    "cell_type": "code",
1483 |    "execution_count": 28,
1484 |    "id": "bdb3d4a7",
1485 |    "metadata": {},
1486 |    "outputs": [
1487 |     {
1488 |      "data": {
1489 |       "text/plain": [
1490 |        "70.0"
1491 |       ]
1492 |      },
1493 |      "execution_count": 28,
1494 |      "metadata": {},
1495 |      "output_type": "execute_result"
1496 |     }
1497 |    ],
1498 |    "source": [
1499 |     "b"
1500 |    ]
1501 |   },
1502 |   {
1503 |    "cell_type": "code",
1504 |    "execution_count": 29,
1505 |    "id": "20b12e3e",
1506 |    "metadata": {},
1507 |    "outputs": [],
1508 |    "source": [
1509 |     "a=np.percentile(df3['Salary'],50)"
1510 |    ]
1511 |   },
1512 |   {
1513 |    "cell_type": "code",
1514 |    "execution_count": 30,
1515 |    "id": "a3236481",
1516 |    "metadata": {},
1517 |    "outputs": [
1518 |     {
1519 |      "data": {
1520 |       "text/plain": [
1521 |        "61.5"
1522 |       ]
1523 |      },
1524 |      "execution_count": 30,
1525 |      "metadata": {},
1526 |      "output_type": "execute_result"
1527 |     }
1528 |    ],
1529 |    "source": [
1530 |     "a"
1531 |    ]
1532 |   },
1533 |   {
1534 |    "cell_type": "code",
1535 |    "execution_count": 31,
1536 |    "id": "049dbcf6",
1537 |    "metadata": {},
1538 |    "outputs": [],
1539 |    "source": [
1540 |     "b=np.percentile(df3['Salary'],60)"
1541 |    ]
1542 |   },
1543 |   {
1544 |    "cell_type": "code",
1545 |    "execution_count": 32,
1546 |    "id": "ac441aab",
1547 |    "metadata": {},
1548 |    "outputs": [
1549 |     {
1550 |      "data": {
1551 |       "text/plain": [
1552 |        "67.0"
1553 |       ]
1554 |      },
1555 |      "execution_count": 32,
1556 |      "metadata": {},
1557 |      "output_type": "execute_result"
1558 |     }
1559 |    ],
1560 |    "source": [
1561 |     "b"
1562 |    ]
1563 |   },
1564 |   {
1565 |    "cell_type": "code",
1566 |    "execution_count": 33,
1567 |    "id": "b1586c26",
1568 |    "metadata": {},
1569 |    "outputs": [],
1570 |    "source": [
1571 |     "a=np.percentile(df3['CustomerID'],50)"
1572 |    ]
1573 |   },
1574 |   {
1575 |    "cell_type": "code",
1576 |    "execution_count": 34,
1577 |    "id": "ce7e4eec",
1578 |    "metadata": {},
1579 |    "outputs": [
1580 |     {
1581 |      "data": {
1582 |       "text/plain": [
1583 |        "100.5"
1584 |       ]
1585 |      },
1586 |      "execution_count": 34,
1587 |      "metadata": {},
1588 |      "output_type": "execute_result"
1589 |     }
1590 |    ],
1591 |    "source": [
1592 |     "a"
1593 |    ]
1594 |   },
1595 |   {
1596 |    "cell_type": "code",
1597 |    "execution_count": 35,
1598 |    "id": "c420aa15",
1599 |    "metadata": {},
1600 |    "outputs": [],
1601 |    "source": [
1602 |     "a=np.percentile(df3['CustomerID'],80)"
1603 |    ]
1604 |   },
1605 |   {
1606 |    "cell_type": "code",
1607 |    "execution_count": 36,
1608 |    "id": "dc96fdf1",
1609 |    "metadata": {},
1610 |    "outputs": [
1611 |     {
1612 |      "data": {
1613 |       "text/plain": [
1614 |        "160.20000000000002"
1615 |       ]
1616 |      },
1617 |      "execution_count": 36,
1618 |      "metadata": {},
1619 |      "output_type": "execute_result"
1620 |     }
1621 |    ],
1622 |    "source": [
1623 |     "a"
1624 |    ]
1625 |   },
1626 |   {
1627 |    "cell_type": "code",
1628 |    "execution_count": 37,
1629 |    "id": "2d88404c",
1630 |    "metadata": {},
1631 |    "outputs": [],
1632 |    "source": [
1633 |     "a=np.percentile(df3['Spending Score (1-100)'],50)"
1634 |    ]
1635 |   },
1636 |   {
1637 |    "cell_type": "code",
1638 |    "execution_count": 38,
1639 |    "id": "d4c15884",
1640 |    "metadata": {},
1641 |    "outputs": [
1642 |     {
1643 |      "data": {
1644 |       "text/plain": [
1645 |        "50.0"
1646 |       ]
1647 |      },
1648 |      "execution_count": 38,
1649 |      "metadata": {},
1650 |      "output_type": "execute_result"
1651 |     }
1652 |    ],
1653 |    "source": [
1654 |     "a"
1655 |    ]
1656 |   },
1657 |   {
1658 |    "cell_type": "code",
1659 |    "execution_count": 39,
1660 |    "id": "37df2d34",
1661 |    "metadata": {},
1662 |    "outputs": [],
1663 |    "source": [
1664 |     "a=np.percentile(df3['Spending Score (1-100)'],40)"
1665 |    ]
1666 |   },
1667 |   {
1668 |    "cell_type": "code",
1669 |    "execution_count": 40,
1670 |    "id": "f378a9f4",
1671 |    "metadata": {},
1672 |    "outputs": [
1673 |     {
1674 |      "data": {
1675 |       "text/plain": [
1676 |        "45.60000000000001"
1677 |       ]
1678 |      },
1679 |      "execution_count": 40,
1680 |      "metadata": {},
1681 |      "output_type": "execute_result"
1682 |     }
1683 |    ],
1684 |    "source": [
1685 |     "a"
1686 |    ]
1687 |   },
1688 |   {
1689 |    "cell_type": "code",
1690 |    "execution_count": null,
1691 |    "id": "f6bcae27",
1692 |    "metadata": {},
1693 |    "outputs": [],
1694 |    "source": []
1695 |   }
1696 |  ],
1697 |  "metadata": {
1698 |   "kernelspec": {
1699 |    "display_name": "Python 3 (ipykernel)",
1700 |    "language": "python",
1701 |    "name": "python3"
1702 |   },
1703 |   "language_info": {
1704 |    "codemirror_mode": {
1705 |     "name": "ipython",
1706 |     "version": 3
1707 |    },
1708 |    "file_extension": ".py",
1709 |    "mimetype": "text/x-python",
1710 |    "name": "python",
1711 |    "nbconvert_exporter": "python",
1712 |    "pygments_lexer": "ipython3",
1713 |    "version": "3.9.13"
1714 |   }
1715 |  },
1716 |  "nbformat": 4,
1717 |  "nbformat_minor": 5
1718 | }
1719 | 


--------------------------------------------------------------------------------
/DSBDA-Assignment3DSBDA.ipynb:
--------------------------------------------------------------------------------
   1 | {
   2 |  "cells": [
   3 |   {
   4 |    "cell_type": "code",
   5 |    "execution_count": 1,
   6 |    "id": "a5132be9",
   7 |    "metadata": {},
   8 |    "outputs": [],
   9 |    "source": [
  10 |     "import pandas as pd\n",
  11 |     "import numpy as np\n",
  12 |     "import matplotlib.pyplot as plt"
  13 |    ]
  14 |   },
  15 |   {
  16 |    "cell_type": "code",
  17 |    "execution_count": 2,
  18 |    "id": "8d2ecc01",
  19 |    "metadata": {},
  20 |    "outputs": [],
  21 |    "source": [
  22 |     "df=pd.read_csv('C:/Users/coeco/Downloads/Assign_3_Mall_Customers.csv')"
  23 |    ]
  24 |   },
  25 |   {
  26 |    "cell_type": "code",
  27 |    "execution_count": 3,
  28 |    "id": "2d5e22b6",
  29 |    "metadata": {},
  30 |    "outputs": [],
  31 |    "source": [
  32 |     "df1=df\n",
  33 |     "df2=df1\n",
  34 |     "df3=df\n",
  35 |     "df4=df"
  36 |    ]
  37 |   },
  38 |   {
  39 |    "cell_type": "code",
  40 |    "execution_count": 4,
  41 |    "id": "0a8c9753",
  42 |    "metadata": {},
  43 |    "outputs": [
  44 |     {
  45 |      "data": {
  46 |       "text/html": [
  47 |        "<div>\n",
  48 |        "<style scoped>\n",
  49 |        "    .dataframe tbody tr th:only-of-type {\n",
  50 |        "        vertical-align: middle;\n",
  51 |        "    }\n",
  52 |        "\n",
  53 |        "    .dataframe tbody tr th {\n",
  54 |        "        vertical-align: top;\n",
  55 |        "    }\n",
  56 |        "\n",
  57 |        "    .dataframe thead th {\n",
  58 |        "        text-align: right;\n",
  59 |        "    }\n",
  60 |        "</style>\n",
  61 |        "<table border=\"1\" class=\"dataframe\">\n",
  62 |        "  <thead>\n",
  63 |        "    <tr style=\"text-align: right;\">\n",
  64 |        "      <th></th>\n",
  65 |        "      <th>CustomerID</th>\n",
  66 |        "      <th>Gender</th>\n",
  67 |        "      <th>Age Group</th>\n",
  68 |        "      <th>Age</th>\n",
  69 |        "      <th>Salary</th>\n",
  70 |        "      <th>Spending Score (1-100)</th>\n",
  71 |        "    </tr>\n",
  72 |        "  </thead>\n",
  73 |        "  <tbody>\n",
  74 |        "    <tr>\n",
  75 |        "      <th>0</th>\n",
  76 |        "      <td>1</td>\n",
  77 |        "      <td>Male</td>\n",
  78 |        "      <td>Teen</td>\n",
  79 |        "      <td>19</td>\n",
  80 |        "      <td>15</td>\n",
  81 |        "      <td>39</td>\n",
  82 |        "    </tr>\n",
  83 |        "    <tr>\n",
  84 |        "      <th>1</th>\n",
  85 |        "      <td>2</td>\n",
  86 |        "      <td>Male</td>\n",
  87 |        "      <td>Middle Age</td>\n",
  88 |        "      <td>21</td>\n",
  89 |        "      <td>15</td>\n",
  90 |        "      <td>81</td>\n",
  91 |        "    </tr>\n",
  92 |        "    <tr>\n",
  93 |        "      <th>2</th>\n",
  94 |        "      <td>3</td>\n",
  95 |        "      <td>Female</td>\n",
  96 |        "      <td>Middle Age</td>\n",
  97 |        "      <td>20</td>\n",
  98 |        "      <td>16</td>\n",
  99 |        "      <td>6</td>\n",
 100 |        "    </tr>\n",
 101 |        "    <tr>\n",
 102 |        "      <th>3</th>\n",
 103 |        "      <td>4</td>\n",
 104 |        "      <td>Female</td>\n",
 105 |        "      <td>Middle Age</td>\n",
 106 |        "      <td>23</td>\n",
 107 |        "      <td>16</td>\n",
 108 |        "      <td>77</td>\n",
 109 |        "    </tr>\n",
 110 |        "    <tr>\n",
 111 |        "      <th>4</th>\n",
 112 |        "      <td>5</td>\n",
 113 |        "      <td>Female</td>\n",
 114 |        "      <td>Middle Age</td>\n",
 115 |        "      <td>31</td>\n",
 116 |        "      <td>17</td>\n",
 117 |        "      <td>40</td>\n",
 118 |        "    </tr>\n",
 119 |        "    <tr>\n",
 120 |        "      <th>...</th>\n",
 121 |        "      <td>...</td>\n",
 122 |        "      <td>...</td>\n",
 123 |        "      <td>...</td>\n",
 124 |        "      <td>...</td>\n",
 125 |        "      <td>...</td>\n",
 126 |        "      <td>...</td>\n",
 127 |        "    </tr>\n",
 128 |        "    <tr>\n",
 129 |        "      <th>195</th>\n",
 130 |        "      <td>196</td>\n",
 131 |        "      <td>Female</td>\n",
 132 |        "      <td>Middle Age</td>\n",
 133 |        "      <td>35</td>\n",
 134 |        "      <td>120</td>\n",
 135 |        "      <td>79</td>\n",
 136 |        "    </tr>\n",
 137 |        "    <tr>\n",
 138 |        "      <th>196</th>\n",
 139 |        "      <td>197</td>\n",
 140 |        "      <td>Female</td>\n",
 141 |        "      <td>Elder</td>\n",
 142 |        "      <td>45</td>\n",
 143 |        "      <td>126</td>\n",
 144 |        "      <td>28</td>\n",
 145 |        "    </tr>\n",
 146 |        "    <tr>\n",
 147 |        "      <th>197</th>\n",
 148 |        "      <td>198</td>\n",
 149 |        "      <td>Male</td>\n",
 150 |        "      <td>Middle Age</td>\n",
 151 |        "      <td>32</td>\n",
 152 |        "      <td>126</td>\n",
 153 |        "      <td>74</td>\n",
 154 |        "    </tr>\n",
 155 |        "    <tr>\n",
 156 |        "      <th>198</th>\n",
 157 |        "      <td>199</td>\n",
 158 |        "      <td>Male</td>\n",
 159 |        "      <td>Middle Age</td>\n",
 160 |        "      <td>32</td>\n",
 161 |        "      <td>137</td>\n",
 162 |        "      <td>18</td>\n",
 163 |        "    </tr>\n",
 164 |        "    <tr>\n",
 165 |        "      <th>199</th>\n",
 166 |        "      <td>200</td>\n",
 167 |        "      <td>Male</td>\n",
 168 |        "      <td>Middle Age</td>\n",
 169 |        "      <td>30</td>\n",
 170 |        "      <td>137</td>\n",
 171 |        "      <td>83</td>\n",
 172 |        "    </tr>\n",
 173 |        "  </tbody>\n",
 174 |        "</table>\n",
 175 |        "<p>200 rows × 6 columns</p>\n",
 176 |        "</div>"
 177 |       ],
 178 |       "text/plain": [
 179 |        "     CustomerID  Gender   Age Group  Age  Salary  Spending Score (1-100)\n",
 180 |        "0             1    Male        Teen   19      15                      39\n",
 181 |        "1             2    Male  Middle Age   21      15                      81\n",
 182 |        "2             3  Female  Middle Age   20      16                       6\n",
 183 |        "3             4  Female  Middle Age   23      16                      77\n",
 184 |        "4             5  Female  Middle Age   31      17                      40\n",
 185 |        "..          ...     ...         ...  ...     ...                     ...\n",
 186 |        "195         196  Female  Middle Age   35     120                      79\n",
 187 |        "196         197  Female       Elder   45     126                      28\n",
 188 |        "197         198    Male  Middle Age   32     126                      74\n",
 189 |        "198         199    Male  Middle Age   32     137                      18\n",
 190 |        "199         200    Male  Middle Age   30     137                      83\n",
 191 |        "\n",
 192 |        "[200 rows x 6 columns]"
 193 |       ]
 194 |      },
 195 |      "execution_count": 4,
 196 |      "metadata": {},
 197 |      "output_type": "execute_result"
 198 |     }
 199 |    ],
 200 |    "source": [
 201 |     "df"
 202 |    ]
 203 |   },
 204 |   {
 205 |    "cell_type": "code",
 206 |    "execution_count": 5,
 207 |    "id": "ac5610db",
 208 |    "metadata": {},
 209 |    "outputs": [
 210 |     {
 211 |      "data": {
 212 |       "text/plain": [
 213 |        "Index(['CustomerID', 'Gender', 'Age Group', 'Age', 'Salary',\n",
 214 |        "       'Spending Score (1-100)'],\n",
 215 |        "      dtype='object')"
 216 |       ]
 217 |      },
 218 |      "execution_count": 5,
 219 |      "metadata": {},
 220 |      "output_type": "execute_result"
 221 |     }
 222 |    ],
 223 |    "source": [
 224 |     "df.columns"
 225 |    ]
 226 |   },
 227 |   {
 228 |    "cell_type": "code",
 229 |    "execution_count": 6,
 230 |    "id": "d2311b86",
 231 |    "metadata": {},
 232 |    "outputs": [
 233 |     {
 234 |      "name": "stdout",
 235 |      "output_type": "stream",
 236 |      "text": [
 237 |       "60.56\n"
 238 |      ]
 239 |     }
 240 |    ],
 241 |    "source": [
 242 |     "print(df['Salary'].mean())"
 243 |    ]
 244 |   },
 245 |   {
 246 |    "cell_type": "code",
 247 |    "execution_count": 7,
 248 |    "id": "43e22a92",
 249 |    "metadata": {},
 250 |    "outputs": [
 251 |     {
 252 |      "name": "stdout",
 253 |      "output_type": "stream",
 254 |      "text": [
 255 |       "0    54\n",
 256 |       "1    78\n",
 257 |       "Name: Salary, dtype: int64\n"
 258 |      ]
 259 |     }
 260 |    ],
 261 |    "source": [
 262 |     "print(df['Salary'].mode())"
 263 |    ]
 264 |   },
 265 |   {
 266 |    "cell_type": "code",
 267 |    "execution_count": 8,
 268 |    "id": "8ec3d0ab",
 269 |    "metadata": {},
 270 |    "outputs": [
 271 |     {
 272 |      "name": "stdout",
 273 |      "output_type": "stream",
 274 |      "text": [
 275 |       "61.5\n"
 276 |      ]
 277 |     }
 278 |    ],
 279 |    "source": [
 280 |     "print(df['Salary'].median())"
 281 |    ]
 282 |   },
 283 |   {
 284 |    "cell_type": "code",
 285 |    "execution_count": 9,
 286 |    "id": "b3371013",
 287 |    "metadata": {},
 288 |    "outputs": [
 289 |     {
 290 |      "name": "stdout",
 291 |      "output_type": "stream",
 292 |      "text": [
 293 |       "100.5\n"
 294 |      ]
 295 |     }
 296 |    ],
 297 |    "source": [
 298 |     "print(df['CustomerID'].mean())"
 299 |    ]
 300 |   },
 301 |   {
 302 |    "cell_type": "code",
 303 |    "execution_count": 10,
 304 |    "id": "8c7cf63c",
 305 |    "metadata": {},
 306 |    "outputs": [
 307 |     {
 308 |      "name": "stdout",
 309 |      "output_type": "stream",
 310 |      "text": [
 311 |       "0        1\n",
 312 |       "1        2\n",
 313 |       "2        3\n",
 314 |       "3        4\n",
 315 |       "4        5\n",
 316 |       "      ... \n",
 317 |       "195    196\n",
 318 |       "196    197\n",
 319 |       "197    198\n",
 320 |       "198    199\n",
 321 |       "199    200\n",
 322 |       "Name: CustomerID, Length: 200, dtype: int64\n"
 323 |      ]
 324 |     }
 325 |    ],
 326 |    "source": [
 327 |     "print(df['CustomerID'].mode())"
 328 |    ]
 329 |   },
 330 |   {
 331 |    "cell_type": "code",
 332 |    "execution_count": 11,
 333 |    "id": "04f51439",
 334 |    "metadata": {},
 335 |    "outputs": [
 336 |     {
 337 |      "name": "stdout",
 338 |      "output_type": "stream",
 339 |      "text": [
 340 |       "100.5\n"
 341 |      ]
 342 |     }
 343 |    ],
 344 |    "source": [
 345 |     "print(df['CustomerID'].median())"
 346 |    ]
 347 |   },
 348 |   {
 349 |    "cell_type": "code",
 350 |    "execution_count": 12,
 351 |    "id": "4cfacd4d",
 352 |    "metadata": {},
 353 |    "outputs": [
 354 |     {
 355 |      "name": "stdout",
 356 |      "output_type": "stream",
 357 |      "text": [
 358 |       "0    Female\n",
 359 |       "Name: Gender, dtype: object\n"
 360 |      ]
 361 |     }
 362 |    ],
 363 |    "source": [
 364 |     "print(df['Gender'].mode())"
 365 |    ]
 366 |   },
 367 |   {
 368 |    "cell_type": "code",
 369 |    "execution_count": 13,
 370 |    "id": "10975ab6",
 371 |    "metadata": {},
 372 |    "outputs": [
 373 |     {
 374 |      "name": "stdout",
 375 |      "output_type": "stream",
 376 |      "text": [
 377 |       "0    Middle Age\n",
 378 |       "Name: Age Group, dtype: object\n"
 379 |      ]
 380 |     }
 381 |    ],
 382 |    "source": [
 383 |     "print(df['Age Group'].mode())"
 384 |    ]
 385 |   },
 386 |   {
 387 |    "cell_type": "code",
 388 |    "execution_count": 14,
 389 |    "id": "4a2fb1fb",
 390 |    "metadata": {},
 391 |    "outputs": [
 392 |     {
 393 |      "name": "stdout",
 394 |      "output_type": "stream",
 395 |      "text": [
 396 |       "38.85\n"
 397 |      ]
 398 |     }
 399 |    ],
 400 |    "source": [
 401 |     "print(df['Age'].mean())"
 402 |    ]
 403 |   },
 404 |   {
 405 |    "cell_type": "code",
 406 |    "execution_count": 15,
 407 |    "id": "eaf2e715",
 408 |    "metadata": {},
 409 |    "outputs": [
 410 |     {
 411 |      "name": "stdout",
 412 |      "output_type": "stream",
 413 |      "text": [
 414 |       "0    32\n",
 415 |       "Name: Age, dtype: int64\n"
 416 |      ]
 417 |     }
 418 |    ],
 419 |    "source": [
 420 |     "print(df['Age'].mode())"
 421 |    ]
 422 |   },
 423 |   {
 424 |    "cell_type": "code",
 425 |    "execution_count": 16,
 426 |    "id": "87536fb0",
 427 |    "metadata": {},
 428 |    "outputs": [
 429 |     {
 430 |      "name": "stdout",
 431 |      "output_type": "stream",
 432 |      "text": [
 433 |       "36.0\n"
 434 |      ]
 435 |     }
 436 |    ],
 437 |    "source": [
 438 |     "print(df['Age'].median())"
 439 |    ]
 440 |   },
 441 |   {
 442 |    "cell_type": "code",
 443 |    "execution_count": 17,
 444 |    "id": "78c21e09",
 445 |    "metadata": {},
 446 |    "outputs": [
 447 |     {
 448 |      "name": "stdout",
 449 |      "output_type": "stream",
 450 |      "text": [
 451 |       "50.2\n"
 452 |      ]
 453 |     }
 454 |    ],
 455 |    "source": [
 456 |     "print(df['Spending Score (1-100)'].mean())"
 457 |    ]
 458 |   },
 459 |   {
 460 |    "cell_type": "code",
 461 |    "execution_count": 18,
 462 |    "id": "ed836d66",
 463 |    "metadata": {},
 464 |    "outputs": [
 465 |     {
 466 |      "name": "stdout",
 467 |      "output_type": "stream",
 468 |      "text": [
 469 |       "0    42\n",
 470 |       "Name: Spending Score (1-100), dtype: int64\n"
 471 |      ]
 472 |     }
 473 |    ],
 474 |    "source": [
 475 |     "print(df['Spending Score (1-100)'].mode())"
 476 |    ]
 477 |   },
 478 |   {
 479 |    "cell_type": "code",
 480 |    "execution_count": 19,
 481 |    "id": "792372c1",
 482 |    "metadata": {},
 483 |    "outputs": [
 484 |     {
 485 |      "name": "stdout",
 486 |      "output_type": "stream",
 487 |      "text": [
 488 |       "50.0\n"
 489 |      ]
 490 |     }
 491 |    ],
 492 |    "source": [
 493 |     "print(df['Spending Score (1-100)'].median())"
 494 |    ]
 495 |   },
 496 |   {
 497 |    "cell_type": "code",
 498 |    "execution_count": 20,
 499 |    "id": "2e6f8867",
 500 |    "metadata": {},
 501 |    "outputs": [
 502 |     {
 503 |      "data": {
 504 |       "text/plain": [
 505 |        "0        1\n",
 506 |        "1        2\n",
 507 |        "2        3\n",
 508 |        "3        4\n",
 509 |        "4        5\n",
 510 |        "      ... \n",
 511 |        "195    196\n",
 512 |        "196    197\n",
 513 |        "197    198\n",
 514 |        "198    199\n",
 515 |        "199    200\n",
 516 |        "Name: CustomerID, Length: 200, dtype: int64"
 517 |       ]
 518 |      },
 519 |      "execution_count": 20,
 520 |      "metadata": {},
 521 |      "output_type": "execute_result"
 522 |     }
 523 |    ],
 524 |    "source": [
 525 |     "df['CustomerID']"
 526 |    ]
 527 |   },
 528 |   {
 529 |    "cell_type": "code",
 530 |    "execution_count": 21,
 531 |    "id": "a3c61e3e",
 532 |    "metadata": {},
 533 |    "outputs": [
 534 |     {
 535 |      "data": {
 536 |       "text/plain": [
 537 |        "0        Male\n",
 538 |        "1        Male\n",
 539 |        "2      Female\n",
 540 |        "3      Female\n",
 541 |        "4      Female\n",
 542 |        "        ...  \n",
 543 |        "195    Female\n",
 544 |        "196    Female\n",
 545 |        "197      Male\n",
 546 |        "198      Male\n",
 547 |        "199      Male\n",
 548 |        "Name: Gender, Length: 200, dtype: object"
 549 |       ]
 550 |      },
 551 |      "execution_count": 21,
 552 |      "metadata": {},
 553 |      "output_type": "execute_result"
 554 |     }
 555 |    ],
 556 |    "source": [
 557 |     "df['Gender']"
 558 |    ]
 559 |   },
 560 |   {
 561 |    "cell_type": "code",
 562 |    "execution_count": 22,
 563 |    "id": "997bb2bf",
 564 |    "metadata": {},
 565 |    "outputs": [
 566 |     {
 567 |      "data": {
 568 |       "text/plain": [
 569 |        "0            Teen\n",
 570 |        "1      Middle Age\n",
 571 |        "2      Middle Age\n",
 572 |        "3      Middle Age\n",
 573 |        "4      Middle Age\n",
 574 |        "          ...    \n",
 575 |        "195    Middle Age\n",
 576 |        "196         Elder\n",
 577 |        "197    Middle Age\n",
 578 |        "198    Middle Age\n",
 579 |        "199    Middle Age\n",
 580 |        "Name: Age Group, Length: 200, dtype: object"
 581 |       ]
 582 |      },
 583 |      "execution_count": 22,
 584 |      "metadata": {},
 585 |      "output_type": "execute_result"
 586 |     }
 587 |    ],
 588 |    "source": [
 589 |     "df['Age Group']"
 590 |    ]
 591 |   },
 592 |   {
 593 |    "cell_type": "code",
 594 |    "execution_count": 23,
 595 |    "id": "2717f589",
 596 |    "metadata": {},
 597 |    "outputs": [
 598 |     {
 599 |      "data": {
 600 |       "text/plain": [
 601 |        "0      19\n",
 602 |        "1      21\n",
 603 |        "2      20\n",
 604 |        "3      23\n",
 605 |        "4      31\n",
 606 |        "       ..\n",
 607 |        "195    35\n",
 608 |        "196    45\n",
 609 |        "197    32\n",
 610 |        "198    32\n",
 611 |        "199    30\n",
 612 |        "Name: Age, Length: 200, dtype: int64"
 613 |       ]
 614 |      },
 615 |      "execution_count": 23,
 616 |      "metadata": {},
 617 |      "output_type": "execute_result"
 618 |     }
 619 |    ],
 620 |    "source": [
 621 |     "df['Age']"
 622 |    ]
 623 |   },
 624 |   {
 625 |    "cell_type": "code",
 626 |    "execution_count": 24,
 627 |    "id": "7d2713b9",
 628 |    "metadata": {},
 629 |    "outputs": [
 630 |     {
 631 |      "data": {
 632 |       "text/plain": [
 633 |        "0       15\n",
 634 |        "1       15\n",
 635 |        "2       16\n",
 636 |        "3       16\n",
 637 |        "4       17\n",
 638 |        "      ... \n",
 639 |        "195    120\n",
 640 |        "196    126\n",
 641 |        "197    126\n",
 642 |        "198    137\n",
 643 |        "199    137\n",
 644 |        "Name: Salary, Length: 200, dtype: int64"
 645 |       ]
 646 |      },
 647 |      "execution_count": 24,
 648 |      "metadata": {},
 649 |      "output_type": "execute_result"
 650 |     }
 651 |    ],
 652 |    "source": [
 653 |     "df['Salary']"
 654 |    ]
 655 |   },
 656 |   {
 657 |    "cell_type": "code",
 658 |    "execution_count": 25,
 659 |    "id": "ca503190",
 660 |    "metadata": {},
 661 |    "outputs": [
 662 |     {
 663 |      "data": {
 664 |       "text/plain": [
 665 |        "0      39\n",
 666 |        "1      81\n",
 667 |        "2       6\n",
 668 |        "3      77\n",
 669 |        "4      40\n",
 670 |        "       ..\n",
 671 |        "195    79\n",
 672 |        "196    28\n",
 673 |        "197    74\n",
 674 |        "198    18\n",
 675 |        "199    83\n",
 676 |        "Name: Spending Score (1-100), Length: 200, dtype: int64"
 677 |       ]
 678 |      },
 679 |      "execution_count": 25,
 680 |      "metadata": {},
 681 |      "output_type": "execute_result"
 682 |     }
 683 |    ],
 684 |    "source": [
 685 |     "df['Spending Score (1-100)']"
 686 |    ]
 687 |   },
 688 |   {
 689 |    "cell_type": "code",
 690 |    "execution_count": 26,
 691 |    "id": "cf5ed0bc",
 692 |    "metadata": {},
 693 |    "outputs": [
 694 |     {
 695 |      "data": {
 696 |       "text/html": [
 697 |        "<div>\n",
 698 |        "<style scoped>\n",
 699 |        "    .dataframe tbody tr th:only-of-type {\n",
 700 |        "        vertical-align: middle;\n",
 701 |        "    }\n",
 702 |        "\n",
 703 |        "    .dataframe tbody tr th {\n",
 704 |        "        vertical-align: top;\n",
 705 |        "    }\n",
 706 |        "\n",
 707 |        "    .dataframe thead th {\n",
 708 |        "        text-align: right;\n",
 709 |        "    }\n",
 710 |        "</style>\n",
 711 |        "<table border=\"1\" class=\"dataframe\">\n",
 712 |        "  <thead>\n",
 713 |        "    <tr style=\"text-align: right;\">\n",
 714 |        "      <th></th>\n",
 715 |        "      <th>CustomerID</th>\n",
 716 |        "      <th>Gender</th>\n",
 717 |        "      <th>Age Group</th>\n",
 718 |        "      <th>Age</th>\n",
 719 |        "      <th>Salary</th>\n",
 720 |        "      <th>Spending Score (1-100)</th>\n",
 721 |        "    </tr>\n",
 722 |        "  </thead>\n",
 723 |        "  <tbody>\n",
 724 |        "    <tr>\n",
 725 |        "      <th>0</th>\n",
 726 |        "      <td>False</td>\n",
 727 |        "      <td>False</td>\n",
 728 |        "      <td>False</td>\n",
 729 |        "      <td>False</td>\n",
 730 |        "      <td>False</td>\n",
 731 |        "      <td>False</td>\n",
 732 |        "    </tr>\n",
 733 |        "    <tr>\n",
 734 |        "      <th>1</th>\n",
 735 |        "      <td>False</td>\n",
 736 |        "      <td>False</td>\n",
 737 |        "      <td>False</td>\n",
 738 |        "      <td>False</td>\n",
 739 |        "      <td>False</td>\n",
 740 |        "      <td>False</td>\n",
 741 |        "    </tr>\n",
 742 |        "    <tr>\n",
 743 |        "      <th>2</th>\n",
 744 |        "      <td>False</td>\n",
 745 |        "      <td>False</td>\n",
 746 |        "      <td>False</td>\n",
 747 |        "      <td>False</td>\n",
 748 |        "      <td>False</td>\n",
 749 |        "      <td>False</td>\n",
 750 |        "    </tr>\n",
 751 |        "    <tr>\n",
 752 |        "      <th>3</th>\n",
 753 |        "      <td>False</td>\n",
 754 |        "      <td>False</td>\n",
 755 |        "      <td>False</td>\n",
 756 |        "      <td>False</td>\n",
 757 |        "      <td>False</td>\n",
 758 |        "      <td>False</td>\n",
 759 |        "    </tr>\n",
 760 |        "    <tr>\n",
 761 |        "      <th>4</th>\n",
 762 |        "      <td>False</td>\n",
 763 |        "      <td>False</td>\n",
 764 |        "      <td>False</td>\n",
 765 |        "      <td>False</td>\n",
 766 |        "      <td>False</td>\n",
 767 |        "      <td>False</td>\n",
 768 |        "    </tr>\n",
 769 |        "    <tr>\n",
 770 |        "      <th>...</th>\n",
 771 |        "      <td>...</td>\n",
 772 |        "      <td>...</td>\n",
 773 |        "      <td>...</td>\n",
 774 |        "      <td>...</td>\n",
 775 |        "      <td>...</td>\n",
 776 |        "      <td>...</td>\n",
 777 |        "    </tr>\n",
 778 |        "    <tr>\n",
 779 |        "      <th>195</th>\n",
 780 |        "      <td>False</td>\n",
 781 |        "      <td>False</td>\n",
 782 |        "      <td>False</td>\n",
 783 |        "      <td>False</td>\n",
 784 |        "      <td>False</td>\n",
 785 |        "      <td>False</td>\n",
 786 |        "    </tr>\n",
 787 |        "    <tr>\n",
 788 |        "      <th>196</th>\n",
 789 |        "      <td>False</td>\n",
 790 |        "      <td>False</td>\n",
 791 |        "      <td>False</td>\n",
 792 |        "      <td>False</td>\n",
 793 |        "      <td>False</td>\n",
 794 |        "      <td>False</td>\n",
 795 |        "    </tr>\n",
 796 |        "    <tr>\n",
 797 |        "      <th>197</th>\n",
 798 |        "      <td>False</td>\n",
 799 |        "      <td>False</td>\n",
 800 |        "      <td>False</td>\n",
 801 |        "      <td>False</td>\n",
 802 |        "      <td>False</td>\n",
 803 |        "      <td>False</td>\n",
 804 |        "    </tr>\n",
 805 |        "    <tr>\n",
 806 |        "      <th>198</th>\n",
 807 |        "      <td>False</td>\n",
 808 |        "      <td>False</td>\n",
 809 |        "      <td>False</td>\n",
 810 |        "      <td>False</td>\n",
 811 |        "      <td>False</td>\n",
 812 |        "      <td>False</td>\n",
 813 |        "    </tr>\n",
 814 |        "    <tr>\n",
 815 |        "      <th>199</th>\n",
 816 |        "      <td>False</td>\n",
 817 |        "      <td>False</td>\n",
 818 |        "      <td>False</td>\n",
 819 |        "      <td>False</td>\n",
 820 |        "      <td>False</td>\n",
 821 |        "      <td>False</td>\n",
 822 |        "    </tr>\n",
 823 |        "  </tbody>\n",
 824 |        "</table>\n",
 825 |        "<p>200 rows × 6 columns</p>\n",
 826 |        "</div>"
 827 |       ],
 828 |       "text/plain": [
 829 |        "     CustomerID  Gender  Age Group    Age  Salary  Spending Score (1-100)\n",
 830 |        "0         False   False      False  False   False                   False\n",
 831 |        "1         False   False      False  False   False                   False\n",
 832 |        "2         False   False      False  False   False                   False\n",
 833 |        "3         False   False      False  False   False                   False\n",
 834 |        "4         False   False      False  False   False                   False\n",
 835 |        "..          ...     ...        ...    ...     ...                     ...\n",
 836 |        "195       False   False      False  False   False                   False\n",
 837 |        "196       False   False      False  False   False                   False\n",
 838 |        "197       False   False      False  False   False                   False\n",
 839 |        "198       False   False      False  False   False                   False\n",
 840 |        "199       False   False      False  False   False                   False\n",
 841 |        "\n",
 842 |        "[200 rows x 6 columns]"
 843 |       ]
 844 |      },
 845 |      "execution_count": 26,
 846 |      "metadata": {},
 847 |      "output_type": "execute_result"
 848 |     }
 849 |    ],
 850 |    "source": [
 851 |     "df.isnull()"
 852 |    ]
 853 |   },
 854 |   {
 855 |    "cell_type": "code",
 856 |    "execution_count": 27,
 857 |    "id": "57e87b15",
 858 |    "metadata": {},
 859 |    "outputs": [
 860 |     {
 861 |      "data": {
 862 |       "text/plain": [
 863 |        "CustomerID                0\n",
 864 |        "Gender                    0\n",
 865 |        "Age Group                 0\n",
 866 |        "Age                       0\n",
 867 |        "Salary                    0\n",
 868 |        "Spending Score (1-100)    0\n",
 869 |        "dtype: int64"
 870 |       ]
 871 |      },
 872 |      "execution_count": 27,
 873 |      "metadata": {},
 874 |      "output_type": "execute_result"
 875 |     }
 876 |    ],
 877 |    "source": [
 878 |     "df.isnull().sum()"
 879 |    ]
 880 |   },
 881 |   {
 882 |    "cell_type": "code",
 883 |    "execution_count": 28,
 884 |    "id": "53903062",
 885 |    "metadata": {},
 886 |    "outputs": [
 887 |     {
 888 |      "data": {
 889 |       "text/html": [
 890 |        "<div>\n",
 891 |        "<style scoped>\n",
 892 |        "    .dataframe tbody tr th:only-of-type {\n",
 893 |        "        vertical-align: middle;\n",
 894 |        "    }\n",
 895 |        "\n",
 896 |        "    .dataframe tbody tr th {\n",
 897 |        "        vertical-align: top;\n",
 898 |        "    }\n",
 899 |        "\n",
 900 |        "    .dataframe thead th {\n",
 901 |        "        text-align: right;\n",
 902 |        "    }\n",
 903 |        "</style>\n",
 904 |        "<table border=\"1\" class=\"dataframe\">\n",
 905 |        "  <thead>\n",
 906 |        "    <tr style=\"text-align: right;\">\n",
 907 |        "      <th></th>\n",
 908 |        "      <th>CustomerID</th>\n",
 909 |        "      <th>Age</th>\n",
 910 |        "      <th>Salary</th>\n",
 911 |        "      <th>Spending Score (1-100)</th>\n",
 912 |        "    </tr>\n",
 913 |        "  </thead>\n",
 914 |        "  <tbody>\n",
 915 |        "    <tr>\n",
 916 |        "      <th>count</th>\n",
 917 |        "      <td>200.000000</td>\n",
 918 |        "      <td>200.000000</td>\n",
 919 |        "      <td>200.000000</td>\n",
 920 |        "      <td>200.000000</td>\n",
 921 |        "    </tr>\n",
 922 |        "    <tr>\n",
 923 |        "      <th>mean</th>\n",
 924 |        "      <td>100.500000</td>\n",
 925 |        "      <td>38.850000</td>\n",
 926 |        "      <td>60.560000</td>\n",
 927 |        "      <td>50.200000</td>\n",
 928 |        "    </tr>\n",
 929 |        "    <tr>\n",
 930 |        "      <th>std</th>\n",
 931 |        "      <td>57.879185</td>\n",
 932 |        "      <td>13.969007</td>\n",
 933 |        "      <td>26.264721</td>\n",
 934 |        "      <td>25.823522</td>\n",
 935 |        "    </tr>\n",
 936 |        "    <tr>\n",
 937 |        "      <th>min</th>\n",
 938 |        "      <td>1.000000</td>\n",
 939 |        "      <td>18.000000</td>\n",
 940 |        "      <td>15.000000</td>\n",
 941 |        "      <td>1.000000</td>\n",
 942 |        "    </tr>\n",
 943 |        "    <tr>\n",
 944 |        "      <th>25%</th>\n",
 945 |        "      <td>50.750000</td>\n",
 946 |        "      <td>28.750000</td>\n",
 947 |        "      <td>41.500000</td>\n",
 948 |        "      <td>34.750000</td>\n",
 949 |        "    </tr>\n",
 950 |        "    <tr>\n",
 951 |        "      <th>50%</th>\n",
 952 |        "      <td>100.500000</td>\n",
 953 |        "      <td>36.000000</td>\n",
 954 |        "      <td>61.500000</td>\n",
 955 |        "      <td>50.000000</td>\n",
 956 |        "    </tr>\n",
 957 |        "    <tr>\n",
 958 |        "      <th>75%</th>\n",
 959 |        "      <td>150.250000</td>\n",
 960 |        "      <td>49.000000</td>\n",
 961 |        "      <td>78.000000</td>\n",
 962 |        "      <td>73.000000</td>\n",
 963 |        "    </tr>\n",
 964 |        "    <tr>\n",
 965 |        "      <th>max</th>\n",
 966 |        "      <td>200.000000</td>\n",
 967 |        "      <td>70.000000</td>\n",
 968 |        "      <td>137.000000</td>\n",
 969 |        "      <td>99.000000</td>\n",
 970 |        "    </tr>\n",
 971 |        "  </tbody>\n",
 972 |        "</table>\n",
 973 |        "</div>"
 974 |       ],
 975 |       "text/plain": [
 976 |        "       CustomerID         Age      Salary  Spending Score (1-100)\n",
 977 |        "count  200.000000  200.000000  200.000000              200.000000\n",
 978 |        "mean   100.500000   38.850000   60.560000               50.200000\n",
 979 |        "std     57.879185   13.969007   26.264721               25.823522\n",
 980 |        "min      1.000000   18.000000   15.000000                1.000000\n",
 981 |        "25%     50.750000   28.750000   41.500000               34.750000\n",
 982 |        "50%    100.500000   36.000000   61.500000               50.000000\n",
 983 |        "75%    150.250000   49.000000   78.000000               73.000000\n",
 984 |        "max    200.000000   70.000000  137.000000               99.000000"
 985 |       ]
 986 |      },
 987 |      "execution_count": 28,
 988 |      "metadata": {},
 989 |      "output_type": "execute_result"
 990 |     }
 991 |    ],
 992 |    "source": [
 993 |     "df.describe()"
 994 |    ]
 995 |   },
 996 |   {
 997 |    "cell_type": "code",
 998 |    "execution_count": 29,
 999 |    "id": "a06157ff",
1000 |    "metadata": {},
1001 |    "outputs": [
1002 |     {
1003 |      "data": {
1004 |       "text/html": [
1005 |        "<div>\n",
1006 |        "<style scoped>\n",
1007 |        "    .dataframe tbody tr th:only-of-type {\n",
1008 |        "        vertical-align: middle;\n",
1009 |        "    }\n",
1010 |        "\n",
1011 |        "    .dataframe tbody tr th {\n",
1012 |        "        vertical-align: top;\n",
1013 |        "    }\n",
1014 |        "\n",
1015 |        "    .dataframe thead th {\n",
1016 |        "        text-align: right;\n",
1017 |        "    }\n",
1018 |        "</style>\n",
1019 |        "<table border=\"1\" class=\"dataframe\">\n",
1020 |        "  <thead>\n",
1021 |        "    <tr style=\"text-align: right;\">\n",
1022 |        "      <th></th>\n",
1023 |        "      <th>CustomerID</th>\n",
1024 |        "      <th>Gender</th>\n",
1025 |        "      <th>Age Group</th>\n",
1026 |        "      <th>Age</th>\n",
1027 |        "      <th>Salary</th>\n",
1028 |        "      <th>Spending Score (1-100)</th>\n",
1029 |        "    </tr>\n",
1030 |        "  </thead>\n",
1031 |        "  <tbody>\n",
1032 |        "    <tr>\n",
1033 |        "      <th>0</th>\n",
1034 |        "      <td>1</td>\n",
1035 |        "      <td>Male</td>\n",
1036 |        "      <td>Teen</td>\n",
1037 |        "      <td>19</td>\n",
1038 |        "      <td>15</td>\n",
1039 |        "      <td>39</td>\n",
1040 |        "    </tr>\n",
1041 |        "    <tr>\n",
1042 |        "      <th>1</th>\n",
1043 |        "      <td>2</td>\n",
1044 |        "      <td>Male</td>\n",
1045 |        "      <td>Middle Age</td>\n",
1046 |        "      <td>21</td>\n",
1047 |        "      <td>15</td>\n",
1048 |        "      <td>81</td>\n",
1049 |        "    </tr>\n",
1050 |        "    <tr>\n",
1051 |        "      <th>2</th>\n",
1052 |        "      <td>3</td>\n",
1053 |        "      <td>Female</td>\n",
1054 |        "      <td>Middle Age</td>\n",
1055 |        "      <td>20</td>\n",
1056 |        "      <td>16</td>\n",
1057 |        "      <td>6</td>\n",
1058 |        "    </tr>\n",
1059 |        "    <tr>\n",
1060 |        "      <th>3</th>\n",
1061 |        "      <td>4</td>\n",
1062 |        "      <td>Female</td>\n",
1063 |        "      <td>Middle Age</td>\n",
1064 |        "      <td>23</td>\n",
1065 |        "      <td>16</td>\n",
1066 |        "      <td>77</td>\n",
1067 |        "    </tr>\n",
1068 |        "    <tr>\n",
1069 |        "      <th>4</th>\n",
1070 |        "      <td>5</td>\n",
1071 |        "      <td>Female</td>\n",
1072 |        "      <td>Middle Age</td>\n",
1073 |        "      <td>31</td>\n",
1074 |        "      <td>17</td>\n",
1075 |        "      <td>40</td>\n",
1076 |        "    </tr>\n",
1077 |        "  </tbody>\n",
1078 |        "</table>\n",
1079 |        "</div>"
1080 |       ],
1081 |       "text/plain": [
1082 |        "   CustomerID  Gender   Age Group  Age  Salary  Spending Score (1-100)\n",
1083 |        "0           1    Male        Teen   19      15                      39\n",
1084 |        "1           2    Male  Middle Age   21      15                      81\n",
1085 |        "2           3  Female  Middle Age   20      16                       6\n",
1086 |        "3           4  Female  Middle Age   23      16                      77\n",
1087 |        "4           5  Female  Middle Age   31      17                      40"
1088 |       ]
1089 |      },
1090 |      "execution_count": 29,
1091 |      "metadata": {},
1092 |      "output_type": "execute_result"
1093 |     }
1094 |    ],
1095 |    "source": [
1096 |     "df2.head()"
1097 |    ]
1098 |   },
1099 |   {
1100 |    "cell_type": "code",
1101 |    "execution_count": 30,
1102 |    "id": "b2c01dd9",
1103 |    "metadata": {},
1104 |    "outputs": [
1105 |     {
1106 |      "data": {
1107 |       "text/html": [
1108 |        "<div>\n",
1109 |        "<style scoped>\n",
1110 |        "    .dataframe tbody tr th:only-of-type {\n",
1111 |        "        vertical-align: middle;\n",
1112 |        "    }\n",
1113 |        "\n",
1114 |        "    .dataframe tbody tr th {\n",
1115 |        "        vertical-align: top;\n",
1116 |        "    }\n",
1117 |        "\n",
1118 |        "    .dataframe thead th {\n",
1119 |        "        text-align: right;\n",
1120 |        "    }\n",
1121 |        "</style>\n",
1122 |        "<table border=\"1\" class=\"dataframe\">\n",
1123 |        "  <thead>\n",
1124 |        "    <tr style=\"text-align: right;\">\n",
1125 |        "      <th></th>\n",
1126 |        "      <th>CustomerID</th>\n",
1127 |        "      <th>Gender</th>\n",
1128 |        "      <th>Age Group</th>\n",
1129 |        "      <th>Age</th>\n",
1130 |        "      <th>Salary</th>\n",
1131 |        "      <th>Spending Score (1-100)</th>\n",
1132 |        "    </tr>\n",
1133 |        "  </thead>\n",
1134 |        "  <tbody>\n",
1135 |        "    <tr>\n",
1136 |        "      <th>0</th>\n",
1137 |        "      <td>1</td>\n",
1138 |        "      <td>Male</td>\n",
1139 |        "      <td>Teen</td>\n",
1140 |        "      <td>19</td>\n",
1141 |        "      <td>15</td>\n",
1142 |        "      <td>39</td>\n",
1143 |        "    </tr>\n",
1144 |        "    <tr>\n",
1145 |        "      <th>1</th>\n",
1146 |        "      <td>2</td>\n",
1147 |        "      <td>Male</td>\n",
1148 |        "      <td>Middle Age</td>\n",
1149 |        "      <td>21</td>\n",
1150 |        "      <td>15</td>\n",
1151 |        "      <td>81</td>\n",
1152 |        "    </tr>\n",
1153 |        "    <tr>\n",
1154 |        "      <th>2</th>\n",
1155 |        "      <td>3</td>\n",
1156 |        "      <td>Female</td>\n",
1157 |        "      <td>Middle Age</td>\n",
1158 |        "      <td>20</td>\n",
1159 |        "      <td>16</td>\n",
1160 |        "      <td>6</td>\n",
1161 |        "    </tr>\n",
1162 |        "    <tr>\n",
1163 |        "      <th>3</th>\n",
1164 |        "      <td>4</td>\n",
1165 |        "      <td>Female</td>\n",
1166 |        "      <td>Middle Age</td>\n",
1167 |        "      <td>23</td>\n",
1168 |        "      <td>16</td>\n",
1169 |        "      <td>77</td>\n",
1170 |        "    </tr>\n",
1171 |        "    <tr>\n",
1172 |        "      <th>4</th>\n",
1173 |        "      <td>5</td>\n",
1174 |        "      <td>Female</td>\n",
1175 |        "      <td>Middle Age</td>\n",
1176 |        "      <td>31</td>\n",
1177 |        "      <td>17</td>\n",
1178 |        "      <td>40</td>\n",
1179 |        "    </tr>\n",
1180 |        "  </tbody>\n",
1181 |        "</table>\n",
1182 |        "</div>"
1183 |       ],
1184 |       "text/plain": [
1185 |        "   CustomerID  Gender   Age Group  Age  Salary  Spending Score (1-100)\n",
1186 |        "0           1    Male        Teen   19      15                      39\n",
1187 |        "1           2    Male  Middle Age   21      15                      81\n",
1188 |        "2           3  Female  Middle Age   20      16                       6\n",
1189 |        "3           4  Female  Middle Age   23      16                      77\n",
1190 |        "4           5  Female  Middle Age   31      17                      40"
1191 |       ]
1192 |      },
1193 |      "execution_count": 30,
1194 |      "metadata": {},
1195 |      "output_type": "execute_result"
1196 |     }
1197 |    ],
1198 |    "source": [
1199 |     "df1.head()"
1200 |    ]
1201 |   },
1202 |   {
1203 |    "cell_type": "code",
1204 |    "execution_count": 31,
1205 |    "id": "da0f648e",
1206 |    "metadata": {},
1207 |    "outputs": [
1208 |     {
1209 |      "data": {
1210 |       "text/html": [
1211 |        "<div>\n",
1212 |        "<style scoped>\n",
1213 |        "    .dataframe tbody tr th:only-of-type {\n",
1214 |        "        vertical-align: middle;\n",
1215 |        "    }\n",
1216 |        "\n",
1217 |        "    .dataframe tbody tr th {\n",
1218 |        "        vertical-align: top;\n",
1219 |        "    }\n",
1220 |        "\n",
1221 |        "    .dataframe thead th {\n",
1222 |        "        text-align: right;\n",
1223 |        "    }\n",
1224 |        "</style>\n",
1225 |        "<table border=\"1\" class=\"dataframe\">\n",
1226 |        "  <thead>\n",
1227 |        "    <tr style=\"text-align: right;\">\n",
1228 |        "      <th></th>\n",
1229 |        "      <th>CustomerID</th>\n",
1230 |        "      <th>Gender</th>\n",
1231 |        "      <th>Age Group</th>\n",
1232 |        "      <th>Age</th>\n",
1233 |        "      <th>Salary</th>\n",
1234 |        "      <th>Spending Score (1-100)</th>\n",
1235 |        "    </tr>\n",
1236 |        "  </thead>\n",
1237 |        "  <tbody>\n",
1238 |        "    <tr>\n",
1239 |        "      <th>0</th>\n",
1240 |        "      <td>1</td>\n",
1241 |        "      <td>Male</td>\n",
1242 |        "      <td>Teen</td>\n",
1243 |        "      <td>19</td>\n",
1244 |        "      <td>15</td>\n",
1245 |        "      <td>39</td>\n",
1246 |        "    </tr>\n",
1247 |        "    <tr>\n",
1248 |        "      <th>1</th>\n",
1249 |        "      <td>2</td>\n",
1250 |        "      <td>Male</td>\n",
1251 |        "      <td>Middle Age</td>\n",
1252 |        "      <td>21</td>\n",
1253 |        "      <td>15</td>\n",
1254 |        "      <td>81</td>\n",
1255 |        "    </tr>\n",
1256 |        "    <tr>\n",
1257 |        "      <th>2</th>\n",
1258 |        "      <td>3</td>\n",
1259 |        "      <td>Female</td>\n",
1260 |        "      <td>Middle Age</td>\n",
1261 |        "      <td>20</td>\n",
1262 |        "      <td>16</td>\n",
1263 |        "      <td>6</td>\n",
1264 |        "    </tr>\n",
1265 |        "    <tr>\n",
1266 |        "      <th>3</th>\n",
1267 |        "      <td>4</td>\n",
1268 |        "      <td>Female</td>\n",
1269 |        "      <td>Middle Age</td>\n",
1270 |        "      <td>23</td>\n",
1271 |        "      <td>16</td>\n",
1272 |        "      <td>77</td>\n",
1273 |        "    </tr>\n",
1274 |        "    <tr>\n",
1275 |        "      <th>4</th>\n",
1276 |        "      <td>5</td>\n",
1277 |        "      <td>Female</td>\n",
1278 |        "      <td>Middle Age</td>\n",
1279 |        "      <td>31</td>\n",
1280 |        "      <td>17</td>\n",
1281 |        "      <td>40</td>\n",
1282 |        "    </tr>\n",
1283 |        "  </tbody>\n",
1284 |        "</table>\n",
1285 |        "</div>"
1286 |       ],
1287 |       "text/plain": [
1288 |        "   CustomerID  Gender   Age Group  Age  Salary  Spending Score (1-100)\n",
1289 |        "0           1    Male        Teen   19      15                      39\n",
1290 |        "1           2    Male  Middle Age   21      15                      81\n",
1291 |        "2           3  Female  Middle Age   20      16                       6\n",
1292 |        "3           4  Female  Middle Age   23      16                      77\n",
1293 |        "4           5  Female  Middle Age   31      17                      40"
1294 |       ]
1295 |      },
1296 |      "execution_count": 31,
1297 |      "metadata": {},
1298 |      "output_type": "execute_result"
1299 |     }
1300 |    ],
1301 |    "source": [
1302 |     "df3.head()"
1303 |    ]
1304 |   },
1305 |   {
1306 |    "cell_type": "code",
1307 |    "execution_count": 32,
1308 |    "id": "93e1980c",
1309 |    "metadata": {},
1310 |    "outputs": [
1311 |     {
1312 |      "data": {
1313 |       "text/html": [
1314 |        "<div>\n",
1315 |        "<style scoped>\n",
1316 |        "    .dataframe tbody tr th:only-of-type {\n",
1317 |        "        vertical-align: middle;\n",
1318 |        "    }\n",
1319 |        "\n",
1320 |        "    .dataframe tbody tr th {\n",
1321 |        "        vertical-align: top;\n",
1322 |        "    }\n",
1323 |        "\n",
1324 |        "    .dataframe thead th {\n",
1325 |        "        text-align: right;\n",
1326 |        "    }\n",
1327 |        "</style>\n",
1328 |        "<table border=\"1\" class=\"dataframe\">\n",
1329 |        "  <thead>\n",
1330 |        "    <tr style=\"text-align: right;\">\n",
1331 |        "      <th></th>\n",
1332 |        "      <th>CustomerID</th>\n",
1333 |        "      <th>Gender</th>\n",
1334 |        "      <th>Age Group</th>\n",
1335 |        "      <th>Age</th>\n",
1336 |        "      <th>Salary</th>\n",
1337 |        "      <th>Spending Score (1-100)</th>\n",
1338 |        "    </tr>\n",
1339 |        "  </thead>\n",
1340 |        "  <tbody>\n",
1341 |        "    <tr>\n",
1342 |        "      <th>0</th>\n",
1343 |        "      <td>1</td>\n",
1344 |        "      <td>Male</td>\n",
1345 |        "      <td>Teen</td>\n",
1346 |        "      <td>19</td>\n",
1347 |        "      <td>15</td>\n",
1348 |        "      <td>39</td>\n",
1349 |        "    </tr>\n",
1350 |        "    <tr>\n",
1351 |        "      <th>1</th>\n",
1352 |        "      <td>2</td>\n",
1353 |        "      <td>Male</td>\n",
1354 |        "      <td>Middle Age</td>\n",
1355 |        "      <td>21</td>\n",
1356 |        "      <td>15</td>\n",
1357 |        "      <td>81</td>\n",
1358 |        "    </tr>\n",
1359 |        "    <tr>\n",
1360 |        "      <th>2</th>\n",
1361 |        "      <td>3</td>\n",
1362 |        "      <td>Female</td>\n",
1363 |        "      <td>Middle Age</td>\n",
1364 |        "      <td>20</td>\n",
1365 |        "      <td>16</td>\n",
1366 |        "      <td>6</td>\n",
1367 |        "    </tr>\n",
1368 |        "    <tr>\n",
1369 |        "      <th>3</th>\n",
1370 |        "      <td>4</td>\n",
1371 |        "      <td>Female</td>\n",
1372 |        "      <td>Middle Age</td>\n",
1373 |        "      <td>23</td>\n",
1374 |        "      <td>16</td>\n",
1375 |        "      <td>77</td>\n",
1376 |        "    </tr>\n",
1377 |        "    <tr>\n",
1378 |        "      <th>4</th>\n",
1379 |        "      <td>5</td>\n",
1380 |        "      <td>Female</td>\n",
1381 |        "      <td>Middle Age</td>\n",
1382 |        "      <td>31</td>\n",
1383 |        "      <td>17</td>\n",
1384 |        "      <td>40</td>\n",
1385 |        "    </tr>\n",
1386 |        "  </tbody>\n",
1387 |        "</table>\n",
1388 |        "</div>"
1389 |       ],
1390 |       "text/plain": [
1391 |        "   CustomerID  Gender   Age Group  Age  Salary  Spending Score (1-100)\n",
1392 |        "0           1    Male        Teen   19      15                      39\n",
1393 |        "1           2    Male  Middle Age   21      15                      81\n",
1394 |        "2           3  Female  Middle Age   20      16                       6\n",
1395 |        "3           4  Female  Middle Age   23      16                      77\n",
1396 |        "4           5  Female  Middle Age   31      17                      40"
1397 |       ]
1398 |      },
1399 |      "execution_count": 32,
1400 |      "metadata": {},
1401 |      "output_type": "execute_result"
1402 |     }
1403 |    ],
1404 |    "source": [
1405 |     "df4.head()"
1406 |    ]
1407 |   },
1408 |   {
1409 |    "cell_type": "code",
1410 |    "execution_count": 33,
1411 |    "id": "d5a0ba61",
1412 |    "metadata": {},
1413 |    "outputs": [
1414 |     {
1415 |      "data": {
1416 |       "text/html": [
1417 |        "<div>\n",
1418 |        "<style scoped>\n",
1419 |        "    .dataframe tbody tr th:only-of-type {\n",
1420 |        "        vertical-align: middle;\n",
1421 |        "    }\n",
1422 |        "\n",
1423 |        "    .dataframe tbody tr th {\n",
1424 |        "        vertical-align: top;\n",
1425 |        "    }\n",
1426 |        "\n",
1427 |        "    .dataframe thead th {\n",
1428 |        "        text-align: right;\n",
1429 |        "    }\n",
1430 |        "</style>\n",
1431 |        "<table border=\"1\" class=\"dataframe\">\n",
1432 |        "  <thead>\n",
1433 |        "    <tr style=\"text-align: right;\">\n",
1434 |        "      <th></th>\n",
1435 |        "      <th>CustomerID</th>\n",
1436 |        "      <th>Gender</th>\n",
1437 |        "      <th>Age Group</th>\n",
1438 |        "      <th>Age</th>\n",
1439 |        "      <th>Salary</th>\n",
1440 |        "      <th>Spending Score (1-100)</th>\n",
1441 |        "    </tr>\n",
1442 |        "  </thead>\n",
1443 |        "  <tbody>\n",
1444 |        "    <tr>\n",
1445 |        "      <th>0</th>\n",
1446 |        "      <td>1</td>\n",
1447 |        "      <td>Male</td>\n",
1448 |        "      <td>Teen</td>\n",
1449 |        "      <td>19</td>\n",
1450 |        "      <td>15</td>\n",
1451 |        "      <td>39</td>\n",
1452 |        "    </tr>\n",
1453 |        "    <tr>\n",
1454 |        "      <th>1</th>\n",
1455 |        "      <td>2</td>\n",
1456 |        "      <td>Male</td>\n",
1457 |        "      <td>Middle Age</td>\n",
1458 |        "      <td>21</td>\n",
1459 |        "      <td>15</td>\n",
1460 |        "      <td>81</td>\n",
1461 |        "    </tr>\n",
1462 |        "    <tr>\n",
1463 |        "      <th>2</th>\n",
1464 |        "      <td>3</td>\n",
1465 |        "      <td>Female</td>\n",
1466 |        "      <td>Middle Age</td>\n",
1467 |        "      <td>20</td>\n",
1468 |        "      <td>16</td>\n",
1469 |        "      <td>6</td>\n",
1470 |        "    </tr>\n",
1471 |        "    <tr>\n",
1472 |        "      <th>3</th>\n",
1473 |        "      <td>4</td>\n",
1474 |        "      <td>Female</td>\n",
1475 |        "      <td>Middle Age</td>\n",
1476 |        "      <td>23</td>\n",
1477 |        "      <td>16</td>\n",
1478 |        "      <td>77</td>\n",
1479 |        "    </tr>\n",
1480 |        "    <tr>\n",
1481 |        "      <th>4</th>\n",
1482 |        "      <td>5</td>\n",
1483 |        "      <td>Female</td>\n",
1484 |        "      <td>Middle Age</td>\n",
1485 |        "      <td>31</td>\n",
1486 |        "      <td>17</td>\n",
1487 |        "      <td>40</td>\n",
1488 |        "    </tr>\n",
1489 |        "    <tr>\n",
1490 |        "      <th>...</th>\n",
1491 |        "      <td>...</td>\n",
1492 |        "      <td>...</td>\n",
1493 |        "      <td>...</td>\n",
1494 |        "      <td>...</td>\n",
1495 |        "      <td>...</td>\n",
1496 |        "      <td>...</td>\n",
1497 |        "    </tr>\n",
1498 |        "    <tr>\n",
1499 |        "      <th>195</th>\n",
1500 |        "      <td>196</td>\n",
1501 |        "      <td>Female</td>\n",
1502 |        "      <td>Middle Age</td>\n",
1503 |        "      <td>35</td>\n",
1504 |        "      <td>120</td>\n",
1505 |        "      <td>79</td>\n",
1506 |        "    </tr>\n",
1507 |        "    <tr>\n",
1508 |        "      <th>196</th>\n",
1509 |        "      <td>197</td>\n",
1510 |        "      <td>Female</td>\n",
1511 |        "      <td>Elder</td>\n",
1512 |        "      <td>45</td>\n",
1513 |        "      <td>126</td>\n",
1514 |        "      <td>28</td>\n",
1515 |        "    </tr>\n",
1516 |        "    <tr>\n",
1517 |        "      <th>197</th>\n",
1518 |        "      <td>198</td>\n",
1519 |        "      <td>Male</td>\n",
1520 |        "      <td>Middle Age</td>\n",
1521 |        "      <td>32</td>\n",
1522 |        "      <td>126</td>\n",
1523 |        "      <td>74</td>\n",
1524 |        "    </tr>\n",
1525 |        "    <tr>\n",
1526 |        "      <th>198</th>\n",
1527 |        "      <td>199</td>\n",
1528 |        "      <td>Male</td>\n",
1529 |        "      <td>Middle Age</td>\n",
1530 |        "      <td>32</td>\n",
1531 |        "      <td>137</td>\n",
1532 |        "      <td>18</td>\n",
1533 |        "    </tr>\n",
1534 |        "    <tr>\n",
1535 |        "      <th>199</th>\n",
1536 |        "      <td>200</td>\n",
1537 |        "      <td>Male</td>\n",
1538 |        "      <td>Middle Age</td>\n",
1539 |        "      <td>30</td>\n",
1540 |        "      <td>137</td>\n",
1541 |        "      <td>83</td>\n",
1542 |        "    </tr>\n",
1543 |        "  </tbody>\n",
1544 |        "</table>\n",
1545 |        "<p>200 rows × 6 columns</p>\n",
1546 |        "</div>"
1547 |       ],
1548 |       "text/plain": [
1549 |        "     CustomerID  Gender   Age Group  Age  Salary  Spending Score (1-100)\n",
1550 |        "0             1    Male        Teen   19      15                      39\n",
1551 |        "1             2    Male  Middle Age   21      15                      81\n",
1552 |        "2             3  Female  Middle Age   20      16                       6\n",
1553 |        "3             4  Female  Middle Age   23      16                      77\n",
1554 |        "4             5  Female  Middle Age   31      17                      40\n",
1555 |        "..          ...     ...         ...  ...     ...                     ...\n",
1556 |        "195         196  Female  Middle Age   35     120                      79\n",
1557 |        "196         197  Female       Elder   45     126                      28\n",
1558 |        "197         198    Male  Middle Age   32     126                      74\n",
1559 |        "198         199    Male  Middle Age   32     137                      18\n",
1560 |        "199         200    Male  Middle Age   30     137                      83\n",
1561 |        "\n",
1562 |        "[200 rows x 6 columns]"
1563 |       ]
1564 |      },
1565 |      "execution_count": 33,
1566 |      "metadata": {},
1567 |      "output_type": "execute_result"
1568 |     }
1569 |    ],
1570 |    "source": [
1571 |     "df.replace(to_replace=np.nan,value=80)"
1572 |    ]
1573 |   },
1574 |   {
1575 |    "cell_type": "code",
1576 |    "execution_count": 34,
1577 |    "id": "3c07d865",
1578 |    "metadata": {},
1579 |    "outputs": [
1580 |     {
1581 |      "name": "stdout",
1582 |      "output_type": "stream",
1583 |      "text": [
1584 |       "<class 'pandas.core.frame.DataFrame'>\n",
1585 |       "RangeIndex: 200 entries, 0 to 199\n",
1586 |       "Data columns (total 6 columns):\n",
1587 |       " #   Column                  Non-Null Count  Dtype \n",
1588 |       "---  ------                  --------------  ----- \n",
1589 |       " 0   CustomerID              200 non-null    int64 \n",
1590 |       " 1   Gender                  200 non-null    object\n",
1591 |       " 2   Age Group               200 non-null    object\n",
1592 |       " 3   Age                     200 non-null    int64 \n",
1593 |       " 4   Salary                  200 non-null    int64 \n",
1594 |       " 5   Spending Score (1-100)  200 non-null    int64 \n",
1595 |       "dtypes: int64(4), object(2)\n",
1596 |       "memory usage: 9.5+ KB\n"
1597 |      ]
1598 |     }
1599 |    ],
1600 |    "source": [
1601 |     "df.info()"
1602 |    ]
1603 |   },
1604 |   {
1605 |    "cell_type": "code",
1606 |    "execution_count": 35,
1607 |    "id": "fbbe0a22",
1608 |    "metadata": {},
1609 |    "outputs": [
1610 |     {
1611 |      "name": "stdout",
1612 |      "output_type": "stream",
1613 |      "text": [
1614 |       "(200, 6)\n"
1615 |      ]
1616 |     }
1617 |    ],
1618 |    "source": [
1619 |     "print(df.shape)"
1620 |    ]
1621 |   },
1622 |   {
1623 |    "cell_type": "code",
1624 |    "execution_count": 36,
1625 |    "id": "e796e277",
1626 |    "metadata": {},
1627 |    "outputs": [
1628 |     {
1629 |      "name": "stdout",
1630 |      "output_type": "stream",
1631 |      "text": [
1632 |       "    CustomerID  Gender   Age Group  Age  Salary  Spending Score (1-100)\n",
1633 |       "0            1    Male        Teen   19      15                      39\n",
1634 |       "1            2    Male  Middle Age   21      15                      81\n",
1635 |       "2            3  Female  Middle Age   20      16                       6\n",
1636 |       "3            4  Female  Middle Age   23      16                      77\n",
1637 |       "4            5  Female  Middle Age   31      17                      40\n",
1638 |       "5            6  Female  Middle Age   22      17                      76\n",
1639 |       "6            7  Female  Middle Age   35      18                       6\n",
1640 |       "7            8  Female  Middle Age   23      18                      94\n",
1641 |       "8            9    Male       Elder   64      19                       3\n",
1642 |       "9           10  Female  Middle Age   30      19                      72\n",
1643 |       "10          11    Male       Elder   67      19                      14\n",
1644 |       "11          12  Female  Middle Age   35      19                      99\n",
1645 |       "12          13  Female       Elder   58      20                      15\n",
1646 |       "13          14  Female  Middle Age   24      20                      77\n",
1647 |       "14          15    Male  Middle Age   37      20                      13\n",
1648 |       "15          16    Male  Middle Age   22      20                      79\n",
1649 |       "16          17  Female  Middle Age   35      21                      35\n",
1650 |       "17          18    Male  Middle Age   20      21                      66\n",
1651 |       "18          19    Male       Elder   52      23                      29\n",
1652 |       "19          20  Female  Middle Age   35      23                      98\n"
1653 |      ]
1654 |     }
1655 |    ],
1656 |    "source": [
1657 |     "print(df.head(20))"
1658 |    ]
1659 |   },
1660 |   {
1661 |    "cell_type": "code",
1662 |    "execution_count": 37,
1663 |    "id": "656589f5",
1664 |    "metadata": {},
1665 |    "outputs": [
1666 |     {
1667 |      "data": {
1668 |       "text/plain": [
1669 |        "Middle Age    0.52\n",
1670 |        "Elder         0.42\n",
1671 |        "Teen          0.06\n",
1672 |        "Name: Age Group, dtype: float64"
1673 |       ]
1674 |      },
1675 |      "execution_count": 37,
1676 |      "metadata": {},
1677 |      "output_type": "execute_result"
1678 |     }
1679 |    ],
1680 |    "source": [
1681 |     "df['Age Group'].value_counts(normalize=True)"
1682 |    ]
1683 |   },
1684 |   {
1685 |    "cell_type": "code",
1686 |    "execution_count": 38,
1687 |    "id": "71877d43",
1688 |    "metadata": {},
1689 |    "outputs": [
1690 |     {
1691 |      "data": {
1692 |       "text/plain": [
1693 |        "1      0.005\n",
1694 |        "138    0.005\n",
1695 |        "128    0.005\n",
1696 |        "129    0.005\n",
1697 |        "130    0.005\n",
1698 |        "       ...  \n",
1699 |        "70     0.005\n",
1700 |        "71     0.005\n",
1701 |        "72     0.005\n",
1702 |        "73     0.005\n",
1703 |        "200    0.005\n",
1704 |        "Name: CustomerID, Length: 200, dtype: float64"
1705 |       ]
1706 |      },
1707 |      "execution_count": 38,
1708 |      "metadata": {},
1709 |      "output_type": "execute_result"
1710 |     }
1711 |    ],
1712 |    "source": [
1713 |     "df['CustomerID'].value_counts(normalize=True)"
1714 |    ]
1715 |   },
1716 |   {
1717 |    "cell_type": "code",
1718 |    "execution_count": 39,
1719 |    "id": "738abec1",
1720 |    "metadata": {},
1721 |    "outputs": [
1722 |     {
1723 |      "data": {
1724 |       "text/plain": [
1725 |        "Female    0.56\n",
1726 |        "Male      0.44\n",
1727 |        "Name: Gender, dtype: float64"
1728 |       ]
1729 |      },
1730 |      "execution_count": 39,
1731 |      "metadata": {},
1732 |      "output_type": "execute_result"
1733 |     }
1734 |    ],
1735 |    "source": [
1736 |     "df['Gender'].value_counts(normalize=True)"
1737 |    ]
1738 |   },
1739 |   {
1740 |    "cell_type": "code",
1741 |    "execution_count": 40,
1742 |    "id": "b8ad6ee3",
1743 |    "metadata": {},
1744 |    "outputs": [
1745 |     {
1746 |      "data": {
1747 |       "text/plain": [
1748 |        "32    0.055\n",
1749 |        "35    0.045\n",
1750 |        "19    0.040\n",
1751 |        "31    0.040\n",
1752 |        "30    0.035\n",
1753 |        "49    0.035\n",
1754 |        "40    0.030\n",
1755 |        "38    0.030\n",
1756 |        "47    0.030\n",
1757 |        "27    0.030\n",
1758 |        "36    0.030\n",
1759 |        "23    0.030\n",
1760 |        "34    0.025\n",
1761 |        "20    0.025\n",
1762 |        "29    0.025\n",
1763 |        "50    0.025\n",
1764 |        "48    0.025\n",
1765 |        "21    0.025\n",
1766 |        "24    0.020\n",
1767 |        "18    0.020\n",
1768 |        "28    0.020\n",
1769 |        "67    0.020\n",
1770 |        "59    0.020\n",
1771 |        "54    0.020\n",
1772 |        "43    0.015\n",
1773 |        "60    0.015\n",
1774 |        "45    0.015\n",
1775 |        "39    0.015\n",
1776 |        "33    0.015\n",
1777 |        "37    0.015\n",
1778 |        "22    0.015\n",
1779 |        "25    0.015\n",
1780 |        "46    0.015\n",
1781 |        "68    0.015\n",
1782 |        "52    0.010\n",
1783 |        "44    0.010\n",
1784 |        "66    0.010\n",
1785 |        "57    0.010\n",
1786 |        "26    0.010\n",
1787 |        "53    0.010\n",
1788 |        "42    0.010\n",
1789 |        "63    0.010\n",
1790 |        "70    0.010\n",
1791 |        "51    0.010\n",
1792 |        "58    0.010\n",
1793 |        "65    0.010\n",
1794 |        "41    0.010\n",
1795 |        "55    0.005\n",
1796 |        "69    0.005\n",
1797 |        "64    0.005\n",
1798 |        "56    0.005\n",
1799 |        "Name: Age, dtype: float64"
1800 |       ]
1801 |      },
1802 |      "execution_count": 40,
1803 |      "metadata": {},
1804 |      "output_type": "execute_result"
1805 |     }
1806 |    ],
1807 |    "source": [
1808 |     "df['Age'].value_counts(normalize=True)"
1809 |    ]
1810 |   },
1811 |   {
1812 |    "cell_type": "code",
1813 |    "execution_count": 41,
1814 |    "id": "2dd5a141",
1815 |    "metadata": {},
1816 |    "outputs": [
1817 |     {
1818 |      "data": {
1819 |       "text/plain": [
1820 |        "54     0.06\n",
1821 |        "78     0.06\n",
1822 |        "48     0.03\n",
1823 |        "71     0.03\n",
1824 |        "63     0.03\n",
1825 |        "       ... \n",
1826 |        "58     0.01\n",
1827 |        "59     0.01\n",
1828 |        "16     0.01\n",
1829 |        "64     0.01\n",
1830 |        "137    0.01\n",
1831 |        "Name: Salary, Length: 64, dtype: float64"
1832 |       ]
1833 |      },
1834 |      "execution_count": 41,
1835 |      "metadata": {},
1836 |      "output_type": "execute_result"
1837 |     }
1838 |    ],
1839 |    "source": [
1840 |     "df['Salary'].value_counts(normalize=True)"
1841 |    ]
1842 |   },
1843 |   {
1844 |    "cell_type": "code",
1845 |    "execution_count": 42,
1846 |    "id": "9b27978c",
1847 |    "metadata": {},
1848 |    "outputs": [
1849 |     {
1850 |      "data": {
1851 |       "text/plain": [
1852 |        "42    0.040\n",
1853 |        "55    0.035\n",
1854 |        "46    0.030\n",
1855 |        "73    0.030\n",
1856 |        "35    0.025\n",
1857 |        "      ...  \n",
1858 |        "31    0.005\n",
1859 |        "44    0.005\n",
1860 |        "53    0.005\n",
1861 |        "65    0.005\n",
1862 |        "18    0.005\n",
1863 |        "Name: Spending Score (1-100), Length: 84, dtype: float64"
1864 |       ]
1865 |      },
1866 |      "execution_count": 42,
1867 |      "metadata": {},
1868 |      "output_type": "execute_result"
1869 |     }
1870 |    ],
1871 |    "source": [
1872 |     "df['Spending Score (1-100)'].value_counts(normalize=True)"
1873 |    ]
1874 |   },
1875 |   {
1876 |    "cell_type": "code",
1877 |    "execution_count": 43,
1878 |    "id": "2cf26351",
1879 |    "metadata": {},
1880 |    "outputs": [
1881 |     {
1882 |      "data": {
1883 |       "text/html": [
1884 |        "<div>\n",
1885 |        "<style scoped>\n",
1886 |        "    .dataframe tbody tr th:only-of-type {\n",
1887 |        "        vertical-align: middle;\n",
1888 |        "    }\n",
1889 |        "\n",
1890 |        "    .dataframe tbody tr th {\n",
1891 |        "        vertical-align: top;\n",
1892 |        "    }\n",
1893 |        "\n",
1894 |        "    .dataframe thead th {\n",
1895 |        "        text-align: right;\n",
1896 |        "    }\n",
1897 |        "</style>\n",
1898 |        "<table border=\"1\" class=\"dataframe\">\n",
1899 |        "  <thead>\n",
1900 |        "    <tr style=\"text-align: right;\">\n",
1901 |        "      <th></th>\n",
1902 |        "      <th>Gender</th>\n",
1903 |        "      <th>Age</th>\n",
1904 |        "      <th>Salary</th>\n",
1905 |        "    </tr>\n",
1906 |        "  </thead>\n",
1907 |        "  <tbody>\n",
1908 |        "    <tr>\n",
1909 |        "      <th>0</th>\n",
1910 |        "      <td>Male</td>\n",
1911 |        "      <td>19</td>\n",
1912 |        "      <td>15</td>\n",
1913 |        "    </tr>\n",
1914 |        "    <tr>\n",
1915 |        "      <th>1</th>\n",
1916 |        "      <td>Female</td>\n",
1917 |        "      <td>22</td>\n",
1918 |        "      <td>17</td>\n",
1919 |        "    </tr>\n",
1920 |        "    <tr>\n",
1921 |        "      <th>2</th>\n",
1922 |        "      <td>Female</td>\n",
1923 |        "      <td>35</td>\n",
1924 |        "      <td>21</td>\n",
1925 |        "    </tr>\n",
1926 |        "  </tbody>\n",
1927 |        "</table>\n",
1928 |        "</div>"
1929 |       ],
1930 |       "text/plain": [
1931 |        "   Gender  Age  Salary\n",
1932 |        "0    Male   19      15\n",
1933 |        "1  Female   22      17\n",
1934 |        "2  Female   35      21"
1935 |       ]
1936 |      },
1937 |      "execution_count": 43,
1938 |      "metadata": {},
1939 |      "output_type": "execute_result"
1940 |     }
1941 |    ],
1942 |    "source": [
1943 |     "df = pd.DataFrame([['Male', 19, 15],\n",
1944 |     "                  ['Female', 22, 17],\n",
1945 |     "                  ['Female', 35, 21]])\n",
1946 |     "df.columns = ['Gender','Age','Salary']\n",
1947 |     "df.head()"
1948 |    ]
1949 |   },
1950 |   {
1951 |    "cell_type": "code",
1952 |    "execution_count": null,
1953 |    "id": "ddae8cd4",
1954 |    "metadata": {},
1955 |    "outputs": [],
1956 |    "source": []
1957 |   },
1958 |   {
1959 |    "cell_type": "code",
1960 |    "execution_count": null,
1961 |    "id": "fd3e1027",
1962 |    "metadata": {},
1963 |    "outputs": [],
1964 |    "source": []
1965 |   },
1966 |   {
1967 |    "cell_type": "code",
1968 |    "execution_count": null,
1969 |    "id": "f86138b7",
1970 |    "metadata": {},
1971 |    "outputs": [],
1972 |    "source": []
1973 |   },
1974 |   {
1975 |    "cell_type": "code",
1976 |    "execution_count": null,
1977 |    "id": "07f42db6",
1978 |    "metadata": {},
1979 |    "outputs": [],
1980 |    "source": []
1981 |   }
1982 |  ],
1983 |  "metadata": {
1984 |   "kernelspec": {
1985 |    "display_name": "Python 3 (ipykernel)",
1986 |    "language": "python",
1987 |    "name": "python3"
1988 |   },
1989 |   "language_info": {
1990 |    "codemirror_mode": {
1991 |     "name": "ipython",
1992 |     "version": 3
1993 |    },
1994 |    "file_extension": ".py",
1995 |    "mimetype": "text/x-python",
1996 |    "name": "python",
1997 |    "nbconvert_exporter": "python",
1998 |    "pygments_lexer": "ipython3",
1999 |    "version": "3.9.13"
2000 |   }
2001 |  },
2002 |  "nbformat": 4,
2003 |  "nbformat_minor": 5
2004 | }
2005 | 


--------------------------------------------------------------------------------
/DSBDA A=1 PART2 (1) (1).ipynb:
--------------------------------------------------------------------------------
   1 | {
   2 |  "cells": [
   3 |   {
   4 |    "cell_type": "code",
   5 |    "execution_count": 1,
   6 |    "id": "6d8e9d37",
   7 |    "metadata": {},
   8 |    "outputs": [],
   9 |    "source": [
  10 |     "import pandas as pd"
  11 |    ]
  12 |   },
  13 |   {
  14 |    "cell_type": "code",
  15 |    "execution_count": 2,
  16 |    "id": "e0077717",
  17 |    "metadata": {},
  18 |    "outputs": [],
  19 |    "source": [
  20 |     "csv_url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'"
  21 |    ]
  22 |   },
  23 |   {
  24 |    "cell_type": "code",
  25 |    "execution_count": 3,
  26 |    "id": "eabd856b",
  27 |    "metadata": {},
  28 |    "outputs": [],
  29 |    "source": [
  30 |     "iris=pd.read_csv(csv_url, header = None)"
  31 |    ]
  32 |   },
  33 |   {
  34 |    "cell_type": "code",
  35 |    "execution_count": 4,
  36 |    "id": "4e936a14",
  37 |    "metadata": {},
  38 |    "outputs": [],
  39 |    "source": [
  40 |     "col_name = ['Sepal_Length','Sepal_Width','Petal_Length','Petal_Width','Species']"
  41 |    ]
  42 |   },
  43 |   {
  44 |    "cell_type": "code",
  45 |    "execution_count": 5,
  46 |    "id": "f01bba3d",
  47 |    "metadata": {},
  48 |    "outputs": [],
  49 |    "source": [
  50 |     "iris = pd.read_csv(csv_url, names = col_name)"
  51 |    ]
  52 |   },
  53 |   {
  54 |    "cell_type": "code",
  55 |    "execution_count": 6,
  56 |    "id": "5e3ad842",
  57 |    "metadata": {},
  58 |    "outputs": [],
  59 |    "source": [
  60 |     "df1=df=iris"
  61 |    ]
  62 |   },
  63 |   {
  64 |    "cell_type": "code",
  65 |    "execution_count": 7,
  66 |    "id": "84845444",
  67 |    "metadata": {},
  68 |    "outputs": [
  69 |     {
  70 |      "data": {
  71 |       "text/html": [
  72 |        "<div>\n",
  73 |        "<style scoped>\n",
  74 |        "    .dataframe tbody tr th:only-of-type {\n",
  75 |        "        vertical-align: middle;\n",
  76 |        "    }\n",
  77 |        "\n",
  78 |        "    .dataframe tbody tr th {\n",
  79 |        "        vertical-align: top;\n",
  80 |        "    }\n",
  81 |        "\n",
  82 |        "    .dataframe thead th {\n",
  83 |        "        text-align: right;\n",
  84 |        "    }\n",
  85 |        "</style>\n",
  86 |        "<table border=\"1\" class=\"dataframe\">\n",
  87 |        "  <thead>\n",
  88 |        "    <tr style=\"text-align: right;\">\n",
  89 |        "      <th></th>\n",
  90 |        "      <th>Sepal_Length</th>\n",
  91 |        "      <th>Sepal_Width</th>\n",
  92 |        "      <th>Petal_Length</th>\n",
  93 |        "      <th>Petal_Width</th>\n",
  94 |        "      <th>Species</th>\n",
  95 |        "    </tr>\n",
  96 |        "  </thead>\n",
  97 |        "  <tbody>\n",
  98 |        "    <tr>\n",
  99 |        "      <th>0</th>\n",
 100 |        "      <td>5.1</td>\n",
 101 |        "      <td>3.5</td>\n",
 102 |        "      <td>1.4</td>\n",
 103 |        "      <td>0.2</td>\n",
 104 |        "      <td>Iris-setosa</td>\n",
 105 |        "    </tr>\n",
 106 |        "    <tr>\n",
 107 |        "      <th>1</th>\n",
 108 |        "      <td>4.9</td>\n",
 109 |        "      <td>3.0</td>\n",
 110 |        "      <td>1.4</td>\n",
 111 |        "      <td>0.2</td>\n",
 112 |        "      <td>Iris-setosa</td>\n",
 113 |        "    </tr>\n",
 114 |        "    <tr>\n",
 115 |        "      <th>2</th>\n",
 116 |        "      <td>4.7</td>\n",
 117 |        "      <td>3.2</td>\n",
 118 |        "      <td>1.3</td>\n",
 119 |        "      <td>0.2</td>\n",
 120 |        "      <td>Iris-setosa</td>\n",
 121 |        "    </tr>\n",
 122 |        "    <tr>\n",
 123 |        "      <th>3</th>\n",
 124 |        "      <td>4.6</td>\n",
 125 |        "      <td>3.1</td>\n",
 126 |        "      <td>1.5</td>\n",
 127 |        "      <td>0.2</td>\n",
 128 |        "      <td>Iris-setosa</td>\n",
 129 |        "    </tr>\n",
 130 |        "    <tr>\n",
 131 |        "      <th>4</th>\n",
 132 |        "      <td>5.0</td>\n",
 133 |        "      <td>3.6</td>\n",
 134 |        "      <td>1.4</td>\n",
 135 |        "      <td>0.2</td>\n",
 136 |        "      <td>Iris-setosa</td>\n",
 137 |        "    </tr>\n",
 138 |        "    <tr>\n",
 139 |        "      <th>5</th>\n",
 140 |        "      <td>5.4</td>\n",
 141 |        "      <td>3.9</td>\n",
 142 |        "      <td>1.7</td>\n",
 143 |        "      <td>0.4</td>\n",
 144 |        "      <td>Iris-setosa</td>\n",
 145 |        "    </tr>\n",
 146 |        "    <tr>\n",
 147 |        "      <th>6</th>\n",
 148 |        "      <td>4.6</td>\n",
 149 |        "      <td>3.4</td>\n",
 150 |        "      <td>1.4</td>\n",
 151 |        "      <td>0.3</td>\n",
 152 |        "      <td>Iris-setosa</td>\n",
 153 |        "    </tr>\n",
 154 |        "    <tr>\n",
 155 |        "      <th>7</th>\n",
 156 |        "      <td>5.0</td>\n",
 157 |        "      <td>3.4</td>\n",
 158 |        "      <td>1.5</td>\n",
 159 |        "      <td>0.2</td>\n",
 160 |        "      <td>Iris-setosa</td>\n",
 161 |        "    </tr>\n",
 162 |        "  </tbody>\n",
 163 |        "</table>\n",
 164 |        "</div>"
 165 |       ],
 166 |       "text/plain": [
 167 |        "   Sepal_Length  Sepal_Width  Petal_Length  Petal_Width      Species\n",
 168 |        "0           5.1          3.5           1.4          0.2  Iris-setosa\n",
 169 |        "1           4.9          3.0           1.4          0.2  Iris-setosa\n",
 170 |        "2           4.7          3.2           1.3          0.2  Iris-setosa\n",
 171 |        "3           4.6          3.1           1.5          0.2  Iris-setosa\n",
 172 |        "4           5.0          3.6           1.4          0.2  Iris-setosa\n",
 173 |        "5           5.4          3.9           1.7          0.4  Iris-setosa\n",
 174 |        "6           4.6          3.4           1.4          0.3  Iris-setosa\n",
 175 |        "7           5.0          3.4           1.5          0.2  Iris-setosa"
 176 |       ]
 177 |      },
 178 |      "execution_count": 7,
 179 |      "metadata": {},
 180 |      "output_type": "execute_result"
 181 |     }
 182 |    ],
 183 |    "source": [
 184 |     "iris.head(8)"
 185 |    ]
 186 |   },
 187 |   {
 188 |    "cell_type": "code",
 189 |    "execution_count": 8,
 190 |    "id": "cf3b452c",
 191 |    "metadata": {},
 192 |    "outputs": [
 193 |     {
 194 |      "data": {
 195 |       "text/html": [
 196 |        "<div>\n",
 197 |        "<style scoped>\n",
 198 |        "    .dataframe tbody tr th:only-of-type {\n",
 199 |        "        vertical-align: middle;\n",
 200 |        "    }\n",
 201 |        "\n",
 202 |        "    .dataframe tbody tr th {\n",
 203 |        "        vertical-align: top;\n",
 204 |        "    }\n",
 205 |        "\n",
 206 |        "    .dataframe thead th {\n",
 207 |        "        text-align: right;\n",
 208 |        "    }\n",
 209 |        "</style>\n",
 210 |        "<table border=\"1\" class=\"dataframe\">\n",
 211 |        "  <thead>\n",
 212 |        "    <tr style=\"text-align: right;\">\n",
 213 |        "      <th></th>\n",
 214 |        "      <th>Sepal_Length</th>\n",
 215 |        "      <th>Sepal_Width</th>\n",
 216 |        "      <th>Petal_Length</th>\n",
 217 |        "      <th>Petal_Width</th>\n",
 218 |        "      <th>Species</th>\n",
 219 |        "    </tr>\n",
 220 |        "  </thead>\n",
 221 |        "  <tbody>\n",
 222 |        "    <tr>\n",
 223 |        "      <th>144</th>\n",
 224 |        "      <td>6.7</td>\n",
 225 |        "      <td>3.3</td>\n",
 226 |        "      <td>5.7</td>\n",
 227 |        "      <td>2.5</td>\n",
 228 |        "      <td>Iris-virginica</td>\n",
 229 |        "    </tr>\n",
 230 |        "    <tr>\n",
 231 |        "      <th>145</th>\n",
 232 |        "      <td>6.7</td>\n",
 233 |        "      <td>3.0</td>\n",
 234 |        "      <td>5.2</td>\n",
 235 |        "      <td>2.3</td>\n",
 236 |        "      <td>Iris-virginica</td>\n",
 237 |        "    </tr>\n",
 238 |        "    <tr>\n",
 239 |        "      <th>146</th>\n",
 240 |        "      <td>6.3</td>\n",
 241 |        "      <td>2.5</td>\n",
 242 |        "      <td>5.0</td>\n",
 243 |        "      <td>1.9</td>\n",
 244 |        "      <td>Iris-virginica</td>\n",
 245 |        "    </tr>\n",
 246 |        "    <tr>\n",
 247 |        "      <th>147</th>\n",
 248 |        "      <td>6.5</td>\n",
 249 |        "      <td>3.0</td>\n",
 250 |        "      <td>5.2</td>\n",
 251 |        "      <td>2.0</td>\n",
 252 |        "      <td>Iris-virginica</td>\n",
 253 |        "    </tr>\n",
 254 |        "    <tr>\n",
 255 |        "      <th>148</th>\n",
 256 |        "      <td>6.2</td>\n",
 257 |        "      <td>3.4</td>\n",
 258 |        "      <td>5.4</td>\n",
 259 |        "      <td>2.3</td>\n",
 260 |        "      <td>Iris-virginica</td>\n",
 261 |        "    </tr>\n",
 262 |        "    <tr>\n",
 263 |        "      <th>149</th>\n",
 264 |        "      <td>5.9</td>\n",
 265 |        "      <td>3.0</td>\n",
 266 |        "      <td>5.1</td>\n",
 267 |        "      <td>1.8</td>\n",
 268 |        "      <td>Iris-virginica</td>\n",
 269 |        "    </tr>\n",
 270 |        "  </tbody>\n",
 271 |        "</table>\n",
 272 |        "</div>"
 273 |       ],
 274 |       "text/plain": [
 275 |        "     Sepal_Length  Sepal_Width  Petal_Length  Petal_Width         Species\n",
 276 |        "144           6.7          3.3           5.7          2.5  Iris-virginica\n",
 277 |        "145           6.7          3.0           5.2          2.3  Iris-virginica\n",
 278 |        "146           6.3          2.5           5.0          1.9  Iris-virginica\n",
 279 |        "147           6.5          3.0           5.2          2.0  Iris-virginica\n",
 280 |        "148           6.2          3.4           5.4          2.3  Iris-virginica\n",
 281 |        "149           5.9          3.0           5.1          1.8  Iris-virginica"
 282 |       ]
 283 |      },
 284 |      "execution_count": 8,
 285 |      "metadata": {},
 286 |      "output_type": "execute_result"
 287 |     }
 288 |    ],
 289 |    "source": [
 290 |     "iris.tail(6)"
 291 |    ]
 292 |   },
 293 |   {
 294 |    "cell_type": "code",
 295 |    "execution_count": 9,
 296 |    "id": "1b91f6a5",
 297 |    "metadata": {},
 298 |    "outputs": [
 299 |     {
 300 |      "data": {
 301 |       "text/plain": [
 302 |        "RangeIndex(start=0, stop=150, step=1)"
 303 |       ]
 304 |      },
 305 |      "execution_count": 9,
 306 |      "metadata": {},
 307 |      "output_type": "execute_result"
 308 |     }
 309 |    ],
 310 |    "source": [
 311 |     "iris.index"
 312 |    ]
 313 |   },
 314 |   {
 315 |    "cell_type": "code",
 316 |    "execution_count": 10,
 317 |    "id": "88afcc1e",
 318 |    "metadata": {},
 319 |    "outputs": [
 320 |     {
 321 |      "data": {
 322 |       "text/plain": [
 323 |        "Index(['Sepal_Length', 'Sepal_Width', 'Petal_Length', 'Petal_Width',\n",
 324 |        "       'Species'],\n",
 325 |        "      dtype='object')"
 326 |       ]
 327 |      },
 328 |      "execution_count": 10,
 329 |      "metadata": {},
 330 |      "output_type": "execute_result"
 331 |     }
 332 |    ],
 333 |    "source": [
 334 |     "iris.columns"
 335 |    ]
 336 |   },
 337 |   {
 338 |    "cell_type": "code",
 339 |    "execution_count": 11,
 340 |    "id": "08a54b7d",
 341 |    "metadata": {},
 342 |    "outputs": [
 343 |     {
 344 |      "data": {
 345 |       "text/plain": [
 346 |        "(150, 5)"
 347 |       ]
 348 |      },
 349 |      "execution_count": 11,
 350 |      "metadata": {},
 351 |      "output_type": "execute_result"
 352 |     }
 353 |    ],
 354 |    "source": [
 355 |     "iris.shape"
 356 |    ]
 357 |   },
 358 |   {
 359 |    "cell_type": "code",
 360 |    "execution_count": 12,
 361 |    "id": "7a05d054",
 362 |    "metadata": {},
 363 |    "outputs": [
 364 |     {
 365 |      "data": {
 366 |       "text/plain": [
 367 |        "Sepal_Length    float64\n",
 368 |        "Sepal_Width     float64\n",
 369 |        "Petal_Length    float64\n",
 370 |        "Petal_Width     float64\n",
 371 |        "Species          object\n",
 372 |        "dtype: object"
 373 |       ]
 374 |      },
 375 |      "execution_count": 12,
 376 |      "metadata": {},
 377 |      "output_type": "execute_result"
 378 |     }
 379 |    ],
 380 |    "source": [
 381 |     "iris.dtypes"
 382 |    ]
 383 |   },
 384 |   {
 385 |    "cell_type": "code",
 386 |    "execution_count": 13,
 387 |    "id": "e8f6a558",
 388 |    "metadata": {},
 389 |    "outputs": [
 390 |     {
 391 |      "data": {
 392 |       "text/html": [
 393 |        "<div>\n",
 394 |        "<style scoped>\n",
 395 |        "    .dataframe tbody tr th:only-of-type {\n",
 396 |        "        vertical-align: middle;\n",
 397 |        "    }\n",
 398 |        "\n",
 399 |        "    .dataframe tbody tr th {\n",
 400 |        "        vertical-align: top;\n",
 401 |        "    }\n",
 402 |        "\n",
 403 |        "    .dataframe thead th {\n",
 404 |        "        text-align: right;\n",
 405 |        "    }\n",
 406 |        "</style>\n",
 407 |        "<table border=\"1\" class=\"dataframe\">\n",
 408 |        "  <thead>\n",
 409 |        "    <tr style=\"text-align: right;\">\n",
 410 |        "      <th></th>\n",
 411 |        "      <th>Sepal_Length</th>\n",
 412 |        "      <th>Sepal_Width</th>\n",
 413 |        "      <th>Petal_Length</th>\n",
 414 |        "      <th>Petal_Width</th>\n",
 415 |        "    </tr>\n",
 416 |        "  </thead>\n",
 417 |        "  <tbody>\n",
 418 |        "    <tr>\n",
 419 |        "      <th>count</th>\n",
 420 |        "      <td>150.000000</td>\n",
 421 |        "      <td>150.000000</td>\n",
 422 |        "      <td>150.000000</td>\n",
 423 |        "      <td>150.000000</td>\n",
 424 |        "    </tr>\n",
 425 |        "    <tr>\n",
 426 |        "      <th>mean</th>\n",
 427 |        "      <td>5.843333</td>\n",
 428 |        "      <td>3.054000</td>\n",
 429 |        "      <td>3.758667</td>\n",
 430 |        "      <td>1.198667</td>\n",
 431 |        "    </tr>\n",
 432 |        "    <tr>\n",
 433 |        "      <th>std</th>\n",
 434 |        "      <td>0.828066</td>\n",
 435 |        "      <td>0.433594</td>\n",
 436 |        "      <td>1.764420</td>\n",
 437 |        "      <td>0.763161</td>\n",
 438 |        "    </tr>\n",
 439 |        "    <tr>\n",
 440 |        "      <th>min</th>\n",
 441 |        "      <td>4.300000</td>\n",
 442 |        "      <td>2.000000</td>\n",
 443 |        "      <td>1.000000</td>\n",
 444 |        "      <td>0.100000</td>\n",
 445 |        "    </tr>\n",
 446 |        "    <tr>\n",
 447 |        "      <th>25%</th>\n",
 448 |        "      <td>5.100000</td>\n",
 449 |        "      <td>2.800000</td>\n",
 450 |        "      <td>1.600000</td>\n",
 451 |        "      <td>0.300000</td>\n",
 452 |        "    </tr>\n",
 453 |        "    <tr>\n",
 454 |        "      <th>50%</th>\n",
 455 |        "      <td>5.800000</td>\n",
 456 |        "      <td>3.000000</td>\n",
 457 |        "      <td>4.350000</td>\n",
 458 |        "      <td>1.300000</td>\n",
 459 |        "    </tr>\n",
 460 |        "    <tr>\n",
 461 |        "      <th>75%</th>\n",
 462 |        "      <td>6.400000</td>\n",
 463 |        "      <td>3.300000</td>\n",
 464 |        "      <td>5.100000</td>\n",
 465 |        "      <td>1.800000</td>\n",
 466 |        "    </tr>\n",
 467 |        "    <tr>\n",
 468 |        "      <th>max</th>\n",
 469 |        "      <td>7.900000</td>\n",
 470 |        "      <td>4.400000</td>\n",
 471 |        "      <td>6.900000</td>\n",
 472 |        "      <td>2.500000</td>\n",
 473 |        "    </tr>\n",
 474 |        "  </tbody>\n",
 475 |        "</table>\n",
 476 |        "</div>"
 477 |       ],
 478 |       "text/plain": [
 479 |        "       Sepal_Length  Sepal_Width  Petal_Length  Petal_Width\n",
 480 |        "count    150.000000   150.000000    150.000000   150.000000\n",
 481 |        "mean       5.843333     3.054000      3.758667     1.198667\n",
 482 |        "std        0.828066     0.433594      1.764420     0.763161\n",
 483 |        "min        4.300000     2.000000      1.000000     0.100000\n",
 484 |        "25%        5.100000     2.800000      1.600000     0.300000\n",
 485 |        "50%        5.800000     3.000000      4.350000     1.300000\n",
 486 |        "75%        6.400000     3.300000      5.100000     1.800000\n",
 487 |        "max        7.900000     4.400000      6.900000     2.500000"
 488 |       ]
 489 |      },
 490 |      "execution_count": 13,
 491 |      "metadata": {},
 492 |      "output_type": "execute_result"
 493 |     }
 494 |    ],
 495 |    "source": [
 496 |     "iris.describe()"
 497 |    ]
 498 |   },
 499 |   {
 500 |    "cell_type": "code",
 501 |    "execution_count": 14,
 502 |    "id": "e183dfeb",
 503 |    "metadata": {},
 504 |    "outputs": [
 505 |     {
 506 |      "data": {
 507 |       "text/plain": [
 508 |        "array(['Sepal_Length', 'Sepal_Width', 'Petal_Length', 'Petal_Width',\n",
 509 |        "       'Species'], dtype=object)"
 510 |       ]
 511 |      },
 512 |      "execution_count": 14,
 513 |      "metadata": {},
 514 |      "output_type": "execute_result"
 515 |     }
 516 |    ],
 517 |    "source": [
 518 |     "iris.columns.values"
 519 |    ]
 520 |   },
 521 |   {
 522 |    "cell_type": "code",
 523 |    "execution_count": 15,
 524 |    "id": "bc4ba47f",
 525 |    "metadata": {},
 526 |    "outputs": [
 527 |     {
 528 |      "data": {
 529 |       "text/plain": [
 530 |        "Sepal_Length            4.4\n",
 531 |        "Sepal_Width             2.9\n",
 532 |        "Petal_Length            1.4\n",
 533 |        "Petal_Width             0.2\n",
 534 |        "Species         Iris-setosa\n",
 535 |        "Name: 8, dtype: object"
 536 |       ]
 537 |      },
 538 |      "execution_count": 15,
 539 |      "metadata": {},
 540 |      "output_type": "execute_result"
 541 |     }
 542 |    ],
 543 |    "source": [
 544 |     "iris.iloc[8]"
 545 |    ]
 546 |   },
 547 |   {
 548 |    "cell_type": "code",
 549 |    "execution_count": 16,
 550 |    "id": "a1d0794f",
 551 |    "metadata": {},
 552 |    "outputs": [
 553 |     {
 554 |      "data": {
 555 |       "text/html": [
 556 |        "<div>\n",
 557 |        "<style scoped>\n",
 558 |        "    .dataframe tbody tr th:only-of-type {\n",
 559 |        "        vertical-align: middle;\n",
 560 |        "    }\n",
 561 |        "\n",
 562 |        "    .dataframe tbody tr th {\n",
 563 |        "        vertical-align: top;\n",
 564 |        "    }\n",
 565 |        "\n",
 566 |        "    .dataframe thead th {\n",
 567 |        "        text-align: right;\n",
 568 |        "    }\n",
 569 |        "</style>\n",
 570 |        "<table border=\"1\" class=\"dataframe\">\n",
 571 |        "  <thead>\n",
 572 |        "    <tr style=\"text-align: right;\">\n",
 573 |        "      <th></th>\n",
 574 |        "      <th>Sepal_Length</th>\n",
 575 |        "      <th>Sepal_Width</th>\n",
 576 |        "      <th>Petal_Length</th>\n",
 577 |        "      <th>Petal_Width</th>\n",
 578 |        "      <th>Species</th>\n",
 579 |        "    </tr>\n",
 580 |        "  </thead>\n",
 581 |        "  <tbody>\n",
 582 |        "    <tr>\n",
 583 |        "      <th>47</th>\n",
 584 |        "      <td>4.6</td>\n",
 585 |        "      <td>3.2</td>\n",
 586 |        "      <td>1.4</td>\n",
 587 |        "      <td>0.2</td>\n",
 588 |        "      <td>Iris-setosa</td>\n",
 589 |        "    </tr>\n",
 590 |        "    <tr>\n",
 591 |        "      <th>48</th>\n",
 592 |        "      <td>5.3</td>\n",
 593 |        "      <td>3.7</td>\n",
 594 |        "      <td>1.5</td>\n",
 595 |        "      <td>0.2</td>\n",
 596 |        "      <td>Iris-setosa</td>\n",
 597 |        "    </tr>\n",
 598 |        "    <tr>\n",
 599 |        "      <th>49</th>\n",
 600 |        "      <td>5.0</td>\n",
 601 |        "      <td>3.3</td>\n",
 602 |        "      <td>1.4</td>\n",
 603 |        "      <td>0.2</td>\n",
 604 |        "      <td>Iris-setosa</td>\n",
 605 |        "    </tr>\n",
 606 |        "    <tr>\n",
 607 |        "      <th>50</th>\n",
 608 |        "      <td>7.0</td>\n",
 609 |        "      <td>3.2</td>\n",
 610 |        "      <td>4.7</td>\n",
 611 |        "      <td>1.4</td>\n",
 612 |        "      <td>Iris-versicolor</td>\n",
 613 |        "    </tr>\n",
 614 |        "  </tbody>\n",
 615 |        "</table>\n",
 616 |        "</div>"
 617 |       ],
 618 |       "text/plain": [
 619 |        "    Sepal_Length  Sepal_Width  Petal_Length  Petal_Width          Species\n",
 620 |        "47           4.6          3.2           1.4          0.2      Iris-setosa\n",
 621 |        "48           5.3          3.7           1.5          0.2      Iris-setosa\n",
 622 |        "49           5.0          3.3           1.4          0.2      Iris-setosa\n",
 623 |        "50           7.0          3.2           4.7          1.4  Iris-versicolor"
 624 |       ]
 625 |      },
 626 |      "execution_count": 16,
 627 |      "metadata": {},
 628 |      "output_type": "execute_result"
 629 |     }
 630 |    ],
 631 |    "source": [
 632 |     "iris[47:51]"
 633 |    ]
 634 |   },
 635 |   {
 636 |    "cell_type": "code",
 637 |    "execution_count": 17,
 638 |    "id": "6bd30eb9",
 639 |    "metadata": {},
 640 |    "outputs": [
 641 |     {
 642 |      "data": {
 643 |       "text/html": [
 644 |        "<div>\n",
 645 |        "<style scoped>\n",
 646 |        "    .dataframe tbody tr th:only-of-type {\n",
 647 |        "        vertical-align: middle;\n",
 648 |        "    }\n",
 649 |        "\n",
 650 |        "    .dataframe tbody tr th {\n",
 651 |        "        vertical-align: top;\n",
 652 |        "    }\n",
 653 |        "\n",
 654 |        "    .dataframe thead th {\n",
 655 |        "        text-align: right;\n",
 656 |        "    }\n",
 657 |        "</style>\n",
 658 |        "<table border=\"1\" class=\"dataframe\">\n",
 659 |        "  <thead>\n",
 660 |        "    <tr style=\"text-align: right;\">\n",
 661 |        "      <th></th>\n",
 662 |        "      <th>Sepal_Length</th>\n",
 663 |        "      <th>Sepal_Width</th>\n",
 664 |        "    </tr>\n",
 665 |        "  </thead>\n",
 666 |        "  <tbody>\n",
 667 |        "    <tr>\n",
 668 |        "      <th>0</th>\n",
 669 |        "      <td>5.1</td>\n",
 670 |        "      <td>3.5</td>\n",
 671 |        "    </tr>\n",
 672 |        "    <tr>\n",
 673 |        "      <th>1</th>\n",
 674 |        "      <td>4.9</td>\n",
 675 |        "      <td>3.0</td>\n",
 676 |        "    </tr>\n",
 677 |        "    <tr>\n",
 678 |        "      <th>2</th>\n",
 679 |        "      <td>4.7</td>\n",
 680 |        "      <td>3.2</td>\n",
 681 |        "    </tr>\n",
 682 |        "    <tr>\n",
 683 |        "      <th>3</th>\n",
 684 |        "      <td>4.6</td>\n",
 685 |        "      <td>3.1</td>\n",
 686 |        "    </tr>\n",
 687 |        "    <tr>\n",
 688 |        "      <th>4</th>\n",
 689 |        "      <td>5.0</td>\n",
 690 |        "      <td>3.6</td>\n",
 691 |        "    </tr>\n",
 692 |        "    <tr>\n",
 693 |        "      <th>...</th>\n",
 694 |        "      <td>...</td>\n",
 695 |        "      <td>...</td>\n",
 696 |        "    </tr>\n",
 697 |        "    <tr>\n",
 698 |        "      <th>145</th>\n",
 699 |        "      <td>6.7</td>\n",
 700 |        "      <td>3.0</td>\n",
 701 |        "    </tr>\n",
 702 |        "    <tr>\n",
 703 |        "      <th>146</th>\n",
 704 |        "      <td>6.3</td>\n",
 705 |        "      <td>2.5</td>\n",
 706 |        "    </tr>\n",
 707 |        "    <tr>\n",
 708 |        "      <th>147</th>\n",
 709 |        "      <td>6.5</td>\n",
 710 |        "      <td>3.0</td>\n",
 711 |        "    </tr>\n",
 712 |        "    <tr>\n",
 713 |        "      <th>148</th>\n",
 714 |        "      <td>6.2</td>\n",
 715 |        "      <td>3.4</td>\n",
 716 |        "    </tr>\n",
 717 |        "    <tr>\n",
 718 |        "      <th>149</th>\n",
 719 |        "      <td>5.9</td>\n",
 720 |        "      <td>3.0</td>\n",
 721 |        "    </tr>\n",
 722 |        "  </tbody>\n",
 723 |        "</table>\n",
 724 |        "<p>150 rows × 2 columns</p>\n",
 725 |        "</div>"
 726 |       ],
 727 |       "text/plain": [
 728 |        "     Sepal_Length  Sepal_Width\n",
 729 |        "0             5.1          3.5\n",
 730 |        "1             4.9          3.0\n",
 731 |        "2             4.7          3.2\n",
 732 |        "3             4.6          3.1\n",
 733 |        "4             5.0          3.6\n",
 734 |        "..            ...          ...\n",
 735 |        "145           6.7          3.0\n",
 736 |        "146           6.3          2.5\n",
 737 |        "147           6.5          3.0\n",
 738 |        "148           6.2          3.4\n",
 739 |        "149           5.9          3.0\n",
 740 |        "\n",
 741 |        "[150 rows x 2 columns]"
 742 |       ]
 743 |      },
 744 |      "execution_count": 17,
 745 |      "metadata": {},
 746 |      "output_type": "execute_result"
 747 |     }
 748 |    ],
 749 |    "source": [
 750 |     "iris.loc[:,[\"Sepal_Length\",\"Sepal_Width\"]]"
 751 |    ]
 752 |   },
 753 |   {
 754 |    "cell_type": "code",
 755 |    "execution_count": 18,
 756 |    "id": "495cb730",
 757 |    "metadata": {},
 758 |    "outputs": [
 759 |     {
 760 |      "data": {
 761 |       "text/html": [
 762 |        "<div>\n",
 763 |        "<style scoped>\n",
 764 |        "    .dataframe tbody tr th:only-of-type {\n",
 765 |        "        vertical-align: middle;\n",
 766 |        "    }\n",
 767 |        "\n",
 768 |        "    .dataframe tbody tr th {\n",
 769 |        "        vertical-align: top;\n",
 770 |        "    }\n",
 771 |        "\n",
 772 |        "    .dataframe thead th {\n",
 773 |        "        text-align: right;\n",
 774 |        "    }\n",
 775 |        "</style>\n",
 776 |        "<table border=\"1\" class=\"dataframe\">\n",
 777 |        "  <thead>\n",
 778 |        "    <tr style=\"text-align: right;\">\n",
 779 |        "      <th></th>\n",
 780 |        "      <th>Petal_Length</th>\n",
 781 |        "      <th>Petal_Width</th>\n",
 782 |        "    </tr>\n",
 783 |        "  </thead>\n",
 784 |        "  <tbody>\n",
 785 |        "    <tr>\n",
 786 |        "      <th>0</th>\n",
 787 |        "      <td>1.4</td>\n",
 788 |        "      <td>0.2</td>\n",
 789 |        "    </tr>\n",
 790 |        "    <tr>\n",
 791 |        "      <th>1</th>\n",
 792 |        "      <td>1.4</td>\n",
 793 |        "      <td>0.2</td>\n",
 794 |        "    </tr>\n",
 795 |        "    <tr>\n",
 796 |        "      <th>2</th>\n",
 797 |        "      <td>1.3</td>\n",
 798 |        "      <td>0.2</td>\n",
 799 |        "    </tr>\n",
 800 |        "    <tr>\n",
 801 |        "      <th>3</th>\n",
 802 |        "      <td>1.5</td>\n",
 803 |        "      <td>0.2</td>\n",
 804 |        "    </tr>\n",
 805 |        "    <tr>\n",
 806 |        "      <th>4</th>\n",
 807 |        "      <td>1.4</td>\n",
 808 |        "      <td>0.2</td>\n",
 809 |        "    </tr>\n",
 810 |        "    <tr>\n",
 811 |        "      <th>...</th>\n",
 812 |        "      <td>...</td>\n",
 813 |        "      <td>...</td>\n",
 814 |        "    </tr>\n",
 815 |        "    <tr>\n",
 816 |        "      <th>145</th>\n",
 817 |        "      <td>5.2</td>\n",
 818 |        "      <td>2.3</td>\n",
 819 |        "    </tr>\n",
 820 |        "    <tr>\n",
 821 |        "      <th>146</th>\n",
 822 |        "      <td>5.0</td>\n",
 823 |        "      <td>1.9</td>\n",
 824 |        "    </tr>\n",
 825 |        "    <tr>\n",
 826 |        "      <th>147</th>\n",
 827 |        "      <td>5.2</td>\n",
 828 |        "      <td>2.0</td>\n",
 829 |        "    </tr>\n",
 830 |        "    <tr>\n",
 831 |        "      <th>148</th>\n",
 832 |        "      <td>5.4</td>\n",
 833 |        "      <td>2.3</td>\n",
 834 |        "    </tr>\n",
 835 |        "    <tr>\n",
 836 |        "      <th>149</th>\n",
 837 |        "      <td>5.1</td>\n",
 838 |        "      <td>1.8</td>\n",
 839 |        "    </tr>\n",
 840 |        "  </tbody>\n",
 841 |        "</table>\n",
 842 |        "<p>150 rows × 2 columns</p>\n",
 843 |        "</div>"
 844 |       ],
 845 |       "text/plain": [
 846 |        "     Petal_Length  Petal_Width\n",
 847 |        "0             1.4          0.2\n",
 848 |        "1             1.4          0.2\n",
 849 |        "2             1.3          0.2\n",
 850 |        "3             1.5          0.2\n",
 851 |        "4             1.4          0.2\n",
 852 |        "..            ...          ...\n",
 853 |        "145           5.2          2.3\n",
 854 |        "146           5.0          1.9\n",
 855 |        "147           5.2          2.0\n",
 856 |        "148           5.4          2.3\n",
 857 |        "149           5.1          1.8\n",
 858 |        "\n",
 859 |        "[150 rows x 2 columns]"
 860 |       ]
 861 |      },
 862 |      "execution_count": 18,
 863 |      "metadata": {},
 864 |      "output_type": "execute_result"
 865 |     }
 866 |    ],
 867 |    "source": [
 868 |     "cols_2_4=iris.columns[2:4]\n",
 869 |     "iris[cols_2_4]"
 870 |    ]
 871 |   },
 872 |   {
 873 |    "cell_type": "code",
 874 |    "execution_count": 19,
 875 |    "id": "8099b16e",
 876 |    "metadata": {},
 877 |    "outputs": [
 878 |     {
 879 |      "data": {
 880 |       "text/plain": [
 881 |        "Sepal_Length    False\n",
 882 |        "Sepal_Width     False\n",
 883 |        "Petal_Length    False\n",
 884 |        "Petal_Width     False\n",
 885 |        "Species         False\n",
 886 |        "dtype: bool"
 887 |       ]
 888 |      },
 889 |      "execution_count": 19,
 890 |      "metadata": {},
 891 |      "output_type": "execute_result"
 892 |     }
 893 |    ],
 894 |    "source": [
 895 |     "iris.isnull().any()"
 896 |    ]
 897 |   },
 898 |   {
 899 |    "cell_type": "code",
 900 |    "execution_count": 20,
 901 |    "id": "c4f4fd2a",
 902 |    "metadata": {},
 903 |    "outputs": [
 904 |     {
 905 |      "data": {
 906 |       "text/plain": [
 907 |        "Sepal_Length    0\n",
 908 |        "Sepal_Width     0\n",
 909 |        "Petal_Length    0\n",
 910 |        "Petal_Width     0\n",
 911 |        "Species         0\n",
 912 |        "dtype: int64"
 913 |       ]
 914 |      },
 915 |      "execution_count": 20,
 916 |      "metadata": {},
 917 |      "output_type": "execute_result"
 918 |     }
 919 |    ],
 920 |    "source": [
 921 |     "iris.isnull().sum()"
 922 |    ]
 923 |   },
 924 |   {
 925 |    "cell_type": "code",
 926 |    "execution_count": 21,
 927 |    "id": "166c41d5",
 928 |    "metadata": {},
 929 |    "outputs": [
 930 |     {
 931 |      "data": {
 932 |       "text/plain": [
 933 |        "Sepal_Length    float64\n",
 934 |        "Sepal_Width     float64\n",
 935 |        "Petal_Length    float64\n",
 936 |        "Petal_Width     float64\n",
 937 |        "Species          object\n",
 938 |        "dtype: object"
 939 |       ]
 940 |      },
 941 |      "execution_count": 21,
 942 |      "metadata": {},
 943 |      "output_type": "execute_result"
 944 |     }
 945 |    ],
 946 |    "source": [
 947 |     "iris.dtypes"
 948 |    ]
 949 |   },
 950 |   {
 951 |    "cell_type": "code",
 952 |    "execution_count": 22,
 953 |    "id": "7075f286",
 954 |    "metadata": {},
 955 |    "outputs": [],
 956 |    "source": [
 957 |     "df=iris\n",
 958 |     "df['petal length(cm)']= iris['Petal_Length'].astype('int')"
 959 |    ]
 960 |   },
 961 |   {
 962 |    "cell_type": "code",
 963 |    "execution_count": 23,
 964 |    "id": "21fa96d2",
 965 |    "metadata": {},
 966 |    "outputs": [],
 967 |    "source": [
 968 |     "df1=df"
 969 |    ]
 970 |   },
 971 |   {
 972 |    "cell_type": "code",
 973 |    "execution_count": 24,
 974 |    "id": "efa7b7db",
 975 |    "metadata": {},
 976 |    "outputs": [
 977 |     {
 978 |      "data": {
 979 |       "text/html": [
 980 |        "<div>\n",
 981 |        "<style scoped>\n",
 982 |        "    .dataframe tbody tr th:only-of-type {\n",
 983 |        "        vertical-align: middle;\n",
 984 |        "    }\n",
 985 |        "\n",
 986 |        "    .dataframe tbody tr th {\n",
 987 |        "        vertical-align: top;\n",
 988 |        "    }\n",
 989 |        "\n",
 990 |        "    .dataframe thead th {\n",
 991 |        "        text-align: right;\n",
 992 |        "    }\n",
 993 |        "</style>\n",
 994 |        "<table border=\"1\" class=\"dataframe\">\n",
 995 |        "  <thead>\n",
 996 |        "    <tr style=\"text-align: right;\">\n",
 997 |        "      <th></th>\n",
 998 |        "      <th>Sepal_Length</th>\n",
 999 |        "      <th>Sepal_Width</th>\n",
1000 |        "      <th>Petal_Length</th>\n",
1001 |        "      <th>Petal_Width</th>\n",
1002 |        "      <th>Species</th>\n",
1003 |        "      <th>petal length(cm)</th>\n",
1004 |        "    </tr>\n",
1005 |        "  </thead>\n",
1006 |        "  <tbody>\n",
1007 |        "    <tr>\n",
1008 |        "      <th>0</th>\n",
1009 |        "      <td>5.1</td>\n",
1010 |        "      <td>3.5</td>\n",
1011 |        "      <td>1.4</td>\n",
1012 |        "      <td>0.2</td>\n",
1013 |        "      <td>Iris-setosa</td>\n",
1014 |        "      <td>1</td>\n",
1015 |        "    </tr>\n",
1016 |        "    <tr>\n",
1017 |        "      <th>1</th>\n",
1018 |        "      <td>4.9</td>\n",
1019 |        "      <td>3.0</td>\n",
1020 |        "      <td>1.4</td>\n",
1021 |        "      <td>0.2</td>\n",
1022 |        "      <td>Iris-setosa</td>\n",
1023 |        "      <td>1</td>\n",
1024 |        "    </tr>\n",
1025 |        "    <tr>\n",
1026 |        "      <th>2</th>\n",
1027 |        "      <td>4.7</td>\n",
1028 |        "      <td>3.2</td>\n",
1029 |        "      <td>1.3</td>\n",
1030 |        "      <td>0.2</td>\n",
1031 |        "      <td>Iris-setosa</td>\n",
1032 |        "      <td>1</td>\n",
1033 |        "    </tr>\n",
1034 |        "    <tr>\n",
1035 |        "      <th>3</th>\n",
1036 |        "      <td>4.6</td>\n",
1037 |        "      <td>3.1</td>\n",
1038 |        "      <td>1.5</td>\n",
1039 |        "      <td>0.2</td>\n",
1040 |        "      <td>Iris-setosa</td>\n",
1041 |        "      <td>1</td>\n",
1042 |        "    </tr>\n",
1043 |        "    <tr>\n",
1044 |        "      <th>4</th>\n",
1045 |        "      <td>5.0</td>\n",
1046 |        "      <td>3.6</td>\n",
1047 |        "      <td>1.4</td>\n",
1048 |        "      <td>0.2</td>\n",
1049 |        "      <td>Iris-setosa</td>\n",
1050 |        "      <td>1</td>\n",
1051 |        "    </tr>\n",
1052 |        "    <tr>\n",
1053 |        "      <th>...</th>\n",
1054 |        "      <td>...</td>\n",
1055 |        "      <td>...</td>\n",
1056 |        "      <td>...</td>\n",
1057 |        "      <td>...</td>\n",
1058 |        "      <td>...</td>\n",
1059 |        "      <td>...</td>\n",
1060 |        "    </tr>\n",
1061 |        "    <tr>\n",
1062 |        "      <th>145</th>\n",
1063 |        "      <td>6.7</td>\n",
1064 |        "      <td>3.0</td>\n",
1065 |        "      <td>5.2</td>\n",
1066 |        "      <td>2.3</td>\n",
1067 |        "      <td>Iris-virginica</td>\n",
1068 |        "      <td>5</td>\n",
1069 |        "    </tr>\n",
1070 |        "    <tr>\n",
1071 |        "      <th>146</th>\n",
1072 |        "      <td>6.3</td>\n",
1073 |        "      <td>2.5</td>\n",
1074 |        "      <td>5.0</td>\n",
1075 |        "      <td>1.9</td>\n",
1076 |        "      <td>Iris-virginica</td>\n",
1077 |        "      <td>5</td>\n",
1078 |        "    </tr>\n",
1079 |        "    <tr>\n",
1080 |        "      <th>147</th>\n",
1081 |        "      <td>6.5</td>\n",
1082 |        "      <td>3.0</td>\n",
1083 |        "      <td>5.2</td>\n",
1084 |        "      <td>2.0</td>\n",
1085 |        "      <td>Iris-virginica</td>\n",
1086 |        "      <td>5</td>\n",
1087 |        "    </tr>\n",
1088 |        "    <tr>\n",
1089 |        "      <th>148</th>\n",
1090 |        "      <td>6.2</td>\n",
1091 |        "      <td>3.4</td>\n",
1092 |        "      <td>5.4</td>\n",
1093 |        "      <td>2.3</td>\n",
1094 |        "      <td>Iris-virginica</td>\n",
1095 |        "      <td>5</td>\n",
1096 |        "    </tr>\n",
1097 |        "    <tr>\n",
1098 |        "      <th>149</th>\n",
1099 |        "      <td>5.9</td>\n",
1100 |        "      <td>3.0</td>\n",
1101 |        "      <td>5.1</td>\n",
1102 |        "      <td>1.8</td>\n",
1103 |        "      <td>Iris-virginica</td>\n",
1104 |        "      <td>5</td>\n",
1105 |        "    </tr>\n",
1106 |        "  </tbody>\n",
1107 |        "</table>\n",
1108 |        "<p>150 rows × 6 columns</p>\n",
1109 |        "</div>"
1110 |       ],
1111 |       "text/plain": [
1112 |        "     Sepal_Length  Sepal_Width  Petal_Length  Petal_Width         Species  \\\n",
1113 |        "0             5.1          3.5           1.4          0.2     Iris-setosa   \n",
1114 |        "1             4.9          3.0           1.4          0.2     Iris-setosa   \n",
1115 |        "2             4.7          3.2           1.3          0.2     Iris-setosa   \n",
1116 |        "3             4.6          3.1           1.5          0.2     Iris-setosa   \n",
1117 |        "4             5.0          3.6           1.4          0.2     Iris-setosa   \n",
1118 |        "..            ...          ...           ...          ...             ...   \n",
1119 |        "145           6.7          3.0           5.2          2.3  Iris-virginica   \n",
1120 |        "146           6.3          2.5           5.0          1.9  Iris-virginica   \n",
1121 |        "147           6.5          3.0           5.2          2.0  Iris-virginica   \n",
1122 |        "148           6.2          3.4           5.4          2.3  Iris-virginica   \n",
1123 |        "149           5.9          3.0           5.1          1.8  Iris-virginica   \n",
1124 |        "\n",
1125 |        "     petal length(cm)  \n",
1126 |        "0                   1  \n",
1127 |        "1                   1  \n",
1128 |        "2                   1  \n",
1129 |        "3                   1  \n",
1130 |        "4                   1  \n",
1131 |        "..                ...  \n",
1132 |        "145                 5  \n",
1133 |        "146                 5  \n",
1134 |        "147                 5  \n",
1135 |        "148                 5  \n",
1136 |        "149                 5  \n",
1137 |        "\n",
1138 |        "[150 rows x 6 columns]"
1139 |       ]
1140 |      },
1141 |      "execution_count": 24,
1142 |      "metadata": {},
1143 |      "output_type": "execute_result"
1144 |     }
1145 |    ],
1146 |    "source": [
1147 |     "df"
1148 |    ]
1149 |   },
1150 |   {
1151 |    "cell_type": "markdown",
1152 |    "id": "08a1cbe3",
1153 |    "metadata": {},
1154 |    "source": [
1155 |     "# Data Normalization"
1156 |    ]
1157 |   },
1158 |   {
1159 |    "cell_type": "code",
1160 |    "execution_count": 25,
1161 |    "id": "53f8141c",
1162 |    "metadata": {},
1163 |    "outputs": [],
1164 |    "source": [
1165 |     "from sklearn import preprocessing \n",
1166 |     "min_max_scaler = preprocessing.MinMaxScaler()"
1167 |    ]
1168 |   },
1169 |   {
1170 |    "cell_type": "code",
1171 |    "execution_count": 26,
1172 |    "id": "8aa308ab",
1173 |    "metadata": {},
1174 |    "outputs": [],
1175 |    "source": [
1176 |     "x=iris.iloc[:,:4]"
1177 |    ]
1178 |   },
1179 |   {
1180 |    "cell_type": "code",
1181 |    "execution_count": 27,
1182 |    "id": "a2bd881b",
1183 |    "metadata": {},
1184 |    "outputs": [
1185 |     {
1186 |      "data": {
1187 |       "text/html": [
1188 |        "<div>\n",
1189 |        "<style scoped>\n",
1190 |        "    .dataframe tbody tr th:only-of-type {\n",
1191 |        "        vertical-align: middle;\n",
1192 |        "    }\n",
1193 |        "\n",
1194 |        "    .dataframe tbody tr th {\n",
1195 |        "        vertical-align: top;\n",
1196 |        "    }\n",
1197 |        "\n",
1198 |        "    .dataframe thead th {\n",
1199 |        "        text-align: right;\n",
1200 |        "    }\n",
1201 |        "</style>\n",
1202 |        "<table border=\"1\" class=\"dataframe\">\n",
1203 |        "  <thead>\n",
1204 |        "    <tr style=\"text-align: right;\">\n",
1205 |        "      <th></th>\n",
1206 |        "      <th>Sepal_Length</th>\n",
1207 |        "      <th>Sepal_Width</th>\n",
1208 |        "      <th>Petal_Length</th>\n",
1209 |        "      <th>Petal_Width</th>\n",
1210 |        "    </tr>\n",
1211 |        "  </thead>\n",
1212 |        "  <tbody>\n",
1213 |        "    <tr>\n",
1214 |        "      <th>0</th>\n",
1215 |        "      <td>5.1</td>\n",
1216 |        "      <td>3.5</td>\n",
1217 |        "      <td>1.4</td>\n",
1218 |        "      <td>0.2</td>\n",
1219 |        "    </tr>\n",
1220 |        "    <tr>\n",
1221 |        "      <th>1</th>\n",
1222 |        "      <td>4.9</td>\n",
1223 |        "      <td>3.0</td>\n",
1224 |        "      <td>1.4</td>\n",
1225 |        "      <td>0.2</td>\n",
1226 |        "    </tr>\n",
1227 |        "    <tr>\n",
1228 |        "      <th>2</th>\n",
1229 |        "      <td>4.7</td>\n",
1230 |        "      <td>3.2</td>\n",
1231 |        "      <td>1.3</td>\n",
1232 |        "      <td>0.2</td>\n",
1233 |        "    </tr>\n",
1234 |        "    <tr>\n",
1235 |        "      <th>3</th>\n",
1236 |        "      <td>4.6</td>\n",
1237 |        "      <td>3.1</td>\n",
1238 |        "      <td>1.5</td>\n",
1239 |        "      <td>0.2</td>\n",
1240 |        "    </tr>\n",
1241 |        "    <tr>\n",
1242 |        "      <th>4</th>\n",
1243 |        "      <td>5.0</td>\n",
1244 |        "      <td>3.6</td>\n",
1245 |        "      <td>1.4</td>\n",
1246 |        "      <td>0.2</td>\n",
1247 |        "    </tr>\n",
1248 |        "    <tr>\n",
1249 |        "      <th>...</th>\n",
1250 |        "      <td>...</td>\n",
1251 |        "      <td>...</td>\n",
1252 |        "      <td>...</td>\n",
1253 |        "      <td>...</td>\n",
1254 |        "    </tr>\n",
1255 |        "    <tr>\n",
1256 |        "      <th>145</th>\n",
1257 |        "      <td>6.7</td>\n",
1258 |        "      <td>3.0</td>\n",
1259 |        "      <td>5.2</td>\n",
1260 |        "      <td>2.3</td>\n",
1261 |        "    </tr>\n",
1262 |        "    <tr>\n",
1263 |        "      <th>146</th>\n",
1264 |        "      <td>6.3</td>\n",
1265 |        "      <td>2.5</td>\n",
1266 |        "      <td>5.0</td>\n",
1267 |        "      <td>1.9</td>\n",
1268 |        "    </tr>\n",
1269 |        "    <tr>\n",
1270 |        "      <th>147</th>\n",
1271 |        "      <td>6.5</td>\n",
1272 |        "      <td>3.0</td>\n",
1273 |        "      <td>5.2</td>\n",
1274 |        "      <td>2.0</td>\n",
1275 |        "    </tr>\n",
1276 |        "    <tr>\n",
1277 |        "      <th>148</th>\n",
1278 |        "      <td>6.2</td>\n",
1279 |        "      <td>3.4</td>\n",
1280 |        "      <td>5.4</td>\n",
1281 |        "      <td>2.3</td>\n",
1282 |        "    </tr>\n",
1283 |        "    <tr>\n",
1284 |        "      <th>149</th>\n",
1285 |        "      <td>5.9</td>\n",
1286 |        "      <td>3.0</td>\n",
1287 |        "      <td>5.1</td>\n",
1288 |        "      <td>1.8</td>\n",
1289 |        "    </tr>\n",
1290 |        "  </tbody>\n",
1291 |        "</table>\n",
1292 |        "<p>150 rows × 4 columns</p>\n",
1293 |        "</div>"
1294 |       ],
1295 |       "text/plain": [
1296 |        "     Sepal_Length  Sepal_Width  Petal_Length  Petal_Width\n",
1297 |        "0             5.1          3.5           1.4          0.2\n",
1298 |        "1             4.9          3.0           1.4          0.2\n",
1299 |        "2             4.7          3.2           1.3          0.2\n",
1300 |        "3             4.6          3.1           1.5          0.2\n",
1301 |        "4             5.0          3.6           1.4          0.2\n",
1302 |        "..            ...          ...           ...          ...\n",
1303 |        "145           6.7          3.0           5.2          2.3\n",
1304 |        "146           6.3          2.5           5.0          1.9\n",
1305 |        "147           6.5          3.0           5.2          2.0\n",
1306 |        "148           6.2          3.4           5.4          2.3\n",
1307 |        "149           5.9          3.0           5.1          1.8\n",
1308 |        "\n",
1309 |        "[150 rows x 4 columns]"
1310 |       ]
1311 |      },
1312 |      "execution_count": 27,
1313 |      "metadata": {},
1314 |      "output_type": "execute_result"
1315 |     }
1316 |    ],
1317 |    "source": [
1318 |     "x"
1319 |    ]
1320 |   },
1321 |   {
1322 |    "cell_type": "code",
1323 |    "execution_count": 28,
1324 |    "id": "d3836f0b",
1325 |    "metadata": {},
1326 |    "outputs": [],
1327 |    "source": [
1328 |     "x_scaled = min_max_scaler.fit_transform(x)"
1329 |    ]
1330 |   },
1331 |   {
1332 |    "cell_type": "code",
1333 |    "execution_count": 29,
1334 |    "id": "b69004aa",
1335 |    "metadata": {},
1336 |    "outputs": [],
1337 |    "source": [
1338 |     "x_scaled = min_max_scaler.fit_transform(x)"
1339 |    ]
1340 |   },
1341 |   {
1342 |    "cell_type": "code",
1343 |    "execution_count": 30,
1344 |    "id": "19c17e6a",
1345 |    "metadata": {},
1346 |    "outputs": [],
1347 |    "source": [
1348 |     "df_normalized = pd.DataFrame(x_scaled)"
1349 |    ]
1350 |   },
1351 |   {
1352 |    "cell_type": "code",
1353 |    "execution_count": 31,
1354 |    "id": "f84253d3",
1355 |    "metadata": {},
1356 |    "outputs": [
1357 |     {
1358 |      "data": {
1359 |       "text/html": [
1360 |        "<div>\n",
1361 |        "<style scoped>\n",
1362 |        "    .dataframe tbody tr th:only-of-type {\n",
1363 |        "        vertical-align: middle;\n",
1364 |        "    }\n",
1365 |        "\n",
1366 |        "    .dataframe tbody tr th {\n",
1367 |        "        vertical-align: top;\n",
1368 |        "    }\n",
1369 |        "\n",
1370 |        "    .dataframe thead th {\n",
1371 |        "        text-align: right;\n",
1372 |        "    }\n",
1373 |        "</style>\n",
1374 |        "<table border=\"1\" class=\"dataframe\">\n",
1375 |        "  <thead>\n",
1376 |        "    <tr style=\"text-align: right;\">\n",
1377 |        "      <th></th>\n",
1378 |        "      <th>0</th>\n",
1379 |        "      <th>1</th>\n",
1380 |        "      <th>2</th>\n",
1381 |        "      <th>3</th>\n",
1382 |        "    </tr>\n",
1383 |        "  </thead>\n",
1384 |        "  <tbody>\n",
1385 |        "    <tr>\n",
1386 |        "      <th>0</th>\n",
1387 |        "      <td>0.222222</td>\n",
1388 |        "      <td>0.625000</td>\n",
1389 |        "      <td>0.067797</td>\n",
1390 |        "      <td>0.041667</td>\n",
1391 |        "    </tr>\n",
1392 |        "    <tr>\n",
1393 |        "      <th>1</th>\n",
1394 |        "      <td>0.166667</td>\n",
1395 |        "      <td>0.416667</td>\n",
1396 |        "      <td>0.067797</td>\n",
1397 |        "      <td>0.041667</td>\n",
1398 |        "    </tr>\n",
1399 |        "    <tr>\n",
1400 |        "      <th>2</th>\n",
1401 |        "      <td>0.111111</td>\n",
1402 |        "      <td>0.500000</td>\n",
1403 |        "      <td>0.050847</td>\n",
1404 |        "      <td>0.041667</td>\n",
1405 |        "    </tr>\n",
1406 |        "    <tr>\n",
1407 |        "      <th>3</th>\n",
1408 |        "      <td>0.083333</td>\n",
1409 |        "      <td>0.458333</td>\n",
1410 |        "      <td>0.084746</td>\n",
1411 |        "      <td>0.041667</td>\n",
1412 |        "    </tr>\n",
1413 |        "    <tr>\n",
1414 |        "      <th>4</th>\n",
1415 |        "      <td>0.194444</td>\n",
1416 |        "      <td>0.666667</td>\n",
1417 |        "      <td>0.067797</td>\n",
1418 |        "      <td>0.041667</td>\n",
1419 |        "    </tr>\n",
1420 |        "    <tr>\n",
1421 |        "      <th>...</th>\n",
1422 |        "      <td>...</td>\n",
1423 |        "      <td>...</td>\n",
1424 |        "      <td>...</td>\n",
1425 |        "      <td>...</td>\n",
1426 |        "    </tr>\n",
1427 |        "    <tr>\n",
1428 |        "      <th>145</th>\n",
1429 |        "      <td>0.666667</td>\n",
1430 |        "      <td>0.416667</td>\n",
1431 |        "      <td>0.711864</td>\n",
1432 |        "      <td>0.916667</td>\n",
1433 |        "    </tr>\n",
1434 |        "    <tr>\n",
1435 |        "      <th>146</th>\n",
1436 |        "      <td>0.555556</td>\n",
1437 |        "      <td>0.208333</td>\n",
1438 |        "      <td>0.677966</td>\n",
1439 |        "      <td>0.750000</td>\n",
1440 |        "    </tr>\n",
1441 |        "    <tr>\n",
1442 |        "      <th>147</th>\n",
1443 |        "      <td>0.611111</td>\n",
1444 |        "      <td>0.416667</td>\n",
1445 |        "      <td>0.711864</td>\n",
1446 |        "      <td>0.791667</td>\n",
1447 |        "    </tr>\n",
1448 |        "    <tr>\n",
1449 |        "      <th>148</th>\n",
1450 |        "      <td>0.527778</td>\n",
1451 |        "      <td>0.583333</td>\n",
1452 |        "      <td>0.745763</td>\n",
1453 |        "      <td>0.916667</td>\n",
1454 |        "    </tr>\n",
1455 |        "    <tr>\n",
1456 |        "      <th>149</th>\n",
1457 |        "      <td>0.444444</td>\n",
1458 |        "      <td>0.416667</td>\n",
1459 |        "      <td>0.694915</td>\n",
1460 |        "      <td>0.708333</td>\n",
1461 |        "    </tr>\n",
1462 |        "  </tbody>\n",
1463 |        "</table>\n",
1464 |        "<p>150 rows × 4 columns</p>\n",
1465 |        "</div>"
1466 |       ],
1467 |       "text/plain": [
1468 |        "            0         1         2         3\n",
1469 |        "0    0.222222  0.625000  0.067797  0.041667\n",
1470 |        "1    0.166667  0.416667  0.067797  0.041667\n",
1471 |        "2    0.111111  0.500000  0.050847  0.041667\n",
1472 |        "3    0.083333  0.458333  0.084746  0.041667\n",
1473 |        "4    0.194444  0.666667  0.067797  0.041667\n",
1474 |        "..        ...       ...       ...       ...\n",
1475 |        "145  0.666667  0.416667  0.711864  0.916667\n",
1476 |        "146  0.555556  0.208333  0.677966  0.750000\n",
1477 |        "147  0.611111  0.416667  0.711864  0.791667\n",
1478 |        "148  0.527778  0.583333  0.745763  0.916667\n",
1479 |        "149  0.444444  0.416667  0.694915  0.708333\n",
1480 |        "\n",
1481 |        "[150 rows x 4 columns]"
1482 |       ]
1483 |      },
1484 |      "execution_count": 31,
1485 |      "metadata": {},
1486 |      "output_type": "execute_result"
1487 |     }
1488 |    ],
1489 |    "source": [
1490 |     "df_normalized"
1491 |    ]
1492 |   },
1493 |   {
1494 |    "cell_type": "markdown",
1495 |    "id": "dbfd1a7c",
1496 |    "metadata": {},
1497 |    "source": [
1498 |     "# Handling categorical variable"
1499 |    ]
1500 |   },
1501 |   {
1502 |    "cell_type": "markdown",
1503 |    "id": "0dd1b634",
1504 |    "metadata": {},
1505 |    "source": [
1506 |     "label encoder"
1507 |    ]
1508 |   },
1509 |   {
1510 |    "cell_type": "code",
1511 |    "execution_count": 32,
1512 |    "id": "faa8476f",
1513 |    "metadata": {},
1514 |    "outputs": [
1515 |     {
1516 |      "data": {
1517 |       "text/plain": [
1518 |        "array(['Iris-setosa', 'Iris-versicolor', 'Iris-virginica'], dtype=object)"
1519 |       ]
1520 |      },
1521 |      "execution_count": 32,
1522 |      "metadata": {},
1523 |      "output_type": "execute_result"
1524 |     }
1525 |    ],
1526 |    "source": [
1527 |     "df2=df1\n",
1528 |     "df2['Species'].unique()"
1529 |    ]
1530 |   },
1531 |   {
1532 |    "cell_type": "code",
1533 |    "execution_count": 33,
1534 |    "id": "89b90e42",
1535 |    "metadata": {},
1536 |    "outputs": [],
1537 |    "source": [
1538 |     "from sklearn import preprocessing \n",
1539 |     "enc = preprocessing.OneHotEncoder()"
1540 |    ]
1541 |   },
1542 |   {
1543 |    "cell_type": "code",
1544 |    "execution_count": 34,
1545 |    "id": "84a0a869",
1546 |    "metadata": {},
1547 |    "outputs": [],
1548 |    "source": [
1549 |     "features_df=df2.drop(columns=['Species'])"
1550 |    ]
1551 |   },
1552 |   {
1553 |    "cell_type": "code",
1554 |    "execution_count": 35,
1555 |    "id": "6943e7bc",
1556 |    "metadata": {},
1557 |    "outputs": [
1558 |     {
1559 |      "data": {
1560 |       "text/html": [
1561 |        "<div>\n",
1562 |        "<style scoped>\n",
1563 |        "    .dataframe tbody tr th:only-of-type {\n",
1564 |        "        vertical-align: middle;\n",
1565 |        "    }\n",
1566 |        "\n",
1567 |        "    .dataframe tbody tr th {\n",
1568 |        "        vertical-align: top;\n",
1569 |        "    }\n",
1570 |        "\n",
1571 |        "    .dataframe thead th {\n",
1572 |        "        text-align: right;\n",
1573 |        "    }\n",
1574 |        "</style>\n",
1575 |        "<table border=\"1\" class=\"dataframe\">\n",
1576 |        "  <thead>\n",
1577 |        "    <tr style=\"text-align: right;\">\n",
1578 |        "      <th></th>\n",
1579 |        "      <th>Sepal_Length</th>\n",
1580 |        "      <th>Sepal_Width</th>\n",
1581 |        "      <th>Petal_Length</th>\n",
1582 |        "      <th>Petal_Width</th>\n",
1583 |        "      <th>petal length(cm)</th>\n",
1584 |        "    </tr>\n",
1585 |        "  </thead>\n",
1586 |        "  <tbody>\n",
1587 |        "    <tr>\n",
1588 |        "      <th>0</th>\n",
1589 |        "      <td>5.1</td>\n",
1590 |        "      <td>3.5</td>\n",
1591 |        "      <td>1.4</td>\n",
1592 |        "      <td>0.2</td>\n",
1593 |        "      <td>1</td>\n",
1594 |        "    </tr>\n",
1595 |        "    <tr>\n",
1596 |        "      <th>1</th>\n",
1597 |        "      <td>4.9</td>\n",
1598 |        "      <td>3.0</td>\n",
1599 |        "      <td>1.4</td>\n",
1600 |        "      <td>0.2</td>\n",
1601 |        "      <td>1</td>\n",
1602 |        "    </tr>\n",
1603 |        "    <tr>\n",
1604 |        "      <th>2</th>\n",
1605 |        "      <td>4.7</td>\n",
1606 |        "      <td>3.2</td>\n",
1607 |        "      <td>1.3</td>\n",
1608 |        "      <td>0.2</td>\n",
1609 |        "      <td>1</td>\n",
1610 |        "    </tr>\n",
1611 |        "    <tr>\n",
1612 |        "      <th>3</th>\n",
1613 |        "      <td>4.6</td>\n",
1614 |        "      <td>3.1</td>\n",
1615 |        "      <td>1.5</td>\n",
1616 |        "      <td>0.2</td>\n",
1617 |        "      <td>1</td>\n",
1618 |        "    </tr>\n",
1619 |        "    <tr>\n",
1620 |        "      <th>4</th>\n",
1621 |        "      <td>5.0</td>\n",
1622 |        "      <td>3.6</td>\n",
1623 |        "      <td>1.4</td>\n",
1624 |        "      <td>0.2</td>\n",
1625 |        "      <td>1</td>\n",
1626 |        "    </tr>\n",
1627 |        "    <tr>\n",
1628 |        "      <th>...</th>\n",
1629 |        "      <td>...</td>\n",
1630 |        "      <td>...</td>\n",
1631 |        "      <td>...</td>\n",
1632 |        "      <td>...</td>\n",
1633 |        "      <td>...</td>\n",
1634 |        "    </tr>\n",
1635 |        "    <tr>\n",
1636 |        "      <th>145</th>\n",
1637 |        "      <td>6.7</td>\n",
1638 |        "      <td>3.0</td>\n",
1639 |        "      <td>5.2</td>\n",
1640 |        "      <td>2.3</td>\n",
1641 |        "      <td>5</td>\n",
1642 |        "    </tr>\n",
1643 |        "    <tr>\n",
1644 |        "      <th>146</th>\n",
1645 |        "      <td>6.3</td>\n",
1646 |        "      <td>2.5</td>\n",
1647 |        "      <td>5.0</td>\n",
1648 |        "      <td>1.9</td>\n",
1649 |        "      <td>5</td>\n",
1650 |        "    </tr>\n",
1651 |        "    <tr>\n",
1652 |        "      <th>147</th>\n",
1653 |        "      <td>6.5</td>\n",
1654 |        "      <td>3.0</td>\n",
1655 |        "      <td>5.2</td>\n",
1656 |        "      <td>2.0</td>\n",
1657 |        "      <td>5</td>\n",
1658 |        "    </tr>\n",
1659 |        "    <tr>\n",
1660 |        "      <th>148</th>\n",
1661 |        "      <td>6.2</td>\n",
1662 |        "      <td>3.4</td>\n",
1663 |        "      <td>5.4</td>\n",
1664 |        "      <td>2.3</td>\n",
1665 |        "      <td>5</td>\n",
1666 |        "    </tr>\n",
1667 |        "    <tr>\n",
1668 |        "      <th>149</th>\n",
1669 |        "      <td>5.9</td>\n",
1670 |        "      <td>3.0</td>\n",
1671 |        "      <td>5.1</td>\n",
1672 |        "      <td>1.8</td>\n",
1673 |        "      <td>5</td>\n",
1674 |        "    </tr>\n",
1675 |        "  </tbody>\n",
1676 |        "</table>\n",
1677 |        "<p>150 rows × 5 columns</p>\n",
1678 |        "</div>"
1679 |       ],
1680 |       "text/plain": [
1681 |        "     Sepal_Length  Sepal_Width  Petal_Length  Petal_Width  petal length(cm)\n",
1682 |        "0             5.1          3.5           1.4          0.2                 1\n",
1683 |        "1             4.9          3.0           1.4          0.2                 1\n",
1684 |        "2             4.7          3.2           1.3          0.2                 1\n",
1685 |        "3             4.6          3.1           1.5          0.2                 1\n",
1686 |        "4             5.0          3.6           1.4          0.2                 1\n",
1687 |        "..            ...          ...           ...          ...               ...\n",
1688 |        "145           6.7          3.0           5.2          2.3                 5\n",
1689 |        "146           6.3          2.5           5.0          1.9                 5\n",
1690 |        "147           6.5          3.0           5.2          2.0                 5\n",
1691 |        "148           6.2          3.4           5.4          2.3                 5\n",
1692 |        "149           5.9          3.0           5.1          1.8                 5\n",
1693 |        "\n",
1694 |        "[150 rows x 5 columns]"
1695 |       ]
1696 |      },
1697 |      "execution_count": 35,
1698 |      "metadata": {},
1699 |      "output_type": "execute_result"
1700 |     }
1701 |    ],
1702 |    "source": [
1703 |     "features_df"
1704 |    ]
1705 |   },
1706 |   {
1707 |    "cell_type": "code",
1708 |    "execution_count": 36,
1709 |    "id": "db194e38",
1710 |    "metadata": {},
1711 |    "outputs": [],
1712 |    "source": [
1713 |     "enc_df=(enc. fit_transform(df2[['Species']])).toarray()"
1714 |    ]
1715 |   },
1716 |   {
1717 |    "cell_type": "code",
1718 |    "execution_count": 37,
1719 |    "id": "9e9f56c9",
1720 |    "metadata": {},
1721 |    "outputs": [],
1722 |    "source": [
1723 |     "enc_df = pd.DataFrame(enc_df, columns = ['Iris-Setosa','Iris-Vrsicolor','Iris-virginca'])"
1724 |    ]
1725 |   },
1726 |   {
1727 |    "cell_type": "code",
1728 |    "execution_count": 38,
1729 |    "id": "b9dd8e20",
1730 |    "metadata": {},
1731 |    "outputs": [],
1732 |    "source": [
1733 |     "df_encode = features_df.join(enc_df)"
1734 |    ]
1735 |   },
1736 |   {
1737 |    "cell_type": "code",
1738 |    "execution_count": 39,
1739 |    "id": "52e6f717",
1740 |    "metadata": {},
1741 |    "outputs": [
1742 |     {
1743 |      "data": {
1744 |       "text/html": [
1745 |        "<div>\n",
1746 |        "<style scoped>\n",
1747 |        "    .dataframe tbody tr th:only-of-type {\n",
1748 |        "        vertical-align: middle;\n",
1749 |        "    }\n",
1750 |        "\n",
1751 |        "    .dataframe tbody tr th {\n",
1752 |        "        vertical-align: top;\n",
1753 |        "    }\n",
1754 |        "\n",
1755 |        "    .dataframe thead th {\n",
1756 |        "        text-align: right;\n",
1757 |        "    }\n",
1758 |        "</style>\n",
1759 |        "<table border=\"1\" class=\"dataframe\">\n",
1760 |        "  <thead>\n",
1761 |        "    <tr style=\"text-align: right;\">\n",
1762 |        "      <th></th>\n",
1763 |        "      <th>Sepal_Length</th>\n",
1764 |        "      <th>Sepal_Width</th>\n",
1765 |        "      <th>Petal_Length</th>\n",
1766 |        "      <th>Petal_Width</th>\n",
1767 |        "      <th>petal length(cm)</th>\n",
1768 |        "      <th>Iris-Setosa</th>\n",
1769 |        "      <th>Iris-Vrsicolor</th>\n",
1770 |        "      <th>Iris-virginca</th>\n",
1771 |        "    </tr>\n",
1772 |        "  </thead>\n",
1773 |        "  <tbody>\n",
1774 |        "    <tr>\n",
1775 |        "      <th>0</th>\n",
1776 |        "      <td>5.1</td>\n",
1777 |        "      <td>3.5</td>\n",
1778 |        "      <td>1.4</td>\n",
1779 |        "      <td>0.2</td>\n",
1780 |        "      <td>1</td>\n",
1781 |        "      <td>1.0</td>\n",
1782 |        "      <td>0.0</td>\n",
1783 |        "      <td>0.0</td>\n",
1784 |        "    </tr>\n",
1785 |        "    <tr>\n",
1786 |        "      <th>1</th>\n",
1787 |        "      <td>4.9</td>\n",
1788 |        "      <td>3.0</td>\n",
1789 |        "      <td>1.4</td>\n",
1790 |        "      <td>0.2</td>\n",
1791 |        "      <td>1</td>\n",
1792 |        "      <td>1.0</td>\n",
1793 |        "      <td>0.0</td>\n",
1794 |        "      <td>0.0</td>\n",
1795 |        "    </tr>\n",
1796 |        "    <tr>\n",
1797 |        "      <th>2</th>\n",
1798 |        "      <td>4.7</td>\n",
1799 |        "      <td>3.2</td>\n",
1800 |        "      <td>1.3</td>\n",
1801 |        "      <td>0.2</td>\n",
1802 |        "      <td>1</td>\n",
1803 |        "      <td>1.0</td>\n",
1804 |        "      <td>0.0</td>\n",
1805 |        "      <td>0.0</td>\n",
1806 |        "    </tr>\n",
1807 |        "    <tr>\n",
1808 |        "      <th>3</th>\n",
1809 |        "      <td>4.6</td>\n",
1810 |        "      <td>3.1</td>\n",
1811 |        "      <td>1.5</td>\n",
1812 |        "      <td>0.2</td>\n",
1813 |        "      <td>1</td>\n",
1814 |        "      <td>1.0</td>\n",
1815 |        "      <td>0.0</td>\n",
1816 |        "      <td>0.0</td>\n",
1817 |        "    </tr>\n",
1818 |        "    <tr>\n",
1819 |        "      <th>4</th>\n",
1820 |        "      <td>5.0</td>\n",
1821 |        "      <td>3.6</td>\n",
1822 |        "      <td>1.4</td>\n",
1823 |        "      <td>0.2</td>\n",
1824 |        "      <td>1</td>\n",
1825 |        "      <td>1.0</td>\n",
1826 |        "      <td>0.0</td>\n",
1827 |        "      <td>0.0</td>\n",
1828 |        "    </tr>\n",
1829 |        "    <tr>\n",
1830 |        "      <th>...</th>\n",
1831 |        "      <td>...</td>\n",
1832 |        "      <td>...</td>\n",
1833 |        "      <td>...</td>\n",
1834 |        "      <td>...</td>\n",
1835 |        "      <td>...</td>\n",
1836 |        "      <td>...</td>\n",
1837 |        "      <td>...</td>\n",
1838 |        "      <td>...</td>\n",
1839 |        "    </tr>\n",
1840 |        "    <tr>\n",
1841 |        "      <th>145</th>\n",
1842 |        "      <td>6.7</td>\n",
1843 |        "      <td>3.0</td>\n",
1844 |        "      <td>5.2</td>\n",
1845 |        "      <td>2.3</td>\n",
1846 |        "      <td>5</td>\n",
1847 |        "      <td>0.0</td>\n",
1848 |        "      <td>0.0</td>\n",
1849 |        "      <td>1.0</td>\n",
1850 |        "    </tr>\n",
1851 |        "    <tr>\n",
1852 |        "      <th>146</th>\n",
1853 |        "      <td>6.3</td>\n",
1854 |        "      <td>2.5</td>\n",
1855 |        "      <td>5.0</td>\n",
1856 |        "      <td>1.9</td>\n",
1857 |        "      <td>5</td>\n",
1858 |        "      <td>0.0</td>\n",
1859 |        "      <td>0.0</td>\n",
1860 |        "      <td>1.0</td>\n",
1861 |        "    </tr>\n",
1862 |        "    <tr>\n",
1863 |        "      <th>147</th>\n",
1864 |        "      <td>6.5</td>\n",
1865 |        "      <td>3.0</td>\n",
1866 |        "      <td>5.2</td>\n",
1867 |        "      <td>2.0</td>\n",
1868 |        "      <td>5</td>\n",
1869 |        "      <td>0.0</td>\n",
1870 |        "      <td>0.0</td>\n",
1871 |        "      <td>1.0</td>\n",
1872 |        "    </tr>\n",
1873 |        "    <tr>\n",
1874 |        "      <th>148</th>\n",
1875 |        "      <td>6.2</td>\n",
1876 |        "      <td>3.4</td>\n",
1877 |        "      <td>5.4</td>\n",
1878 |        "      <td>2.3</td>\n",
1879 |        "      <td>5</td>\n",
1880 |        "      <td>0.0</td>\n",
1881 |        "      <td>0.0</td>\n",
1882 |        "      <td>1.0</td>\n",
1883 |        "    </tr>\n",
1884 |        "    <tr>\n",
1885 |        "      <th>149</th>\n",
1886 |        "      <td>5.9</td>\n",
1887 |        "      <td>3.0</td>\n",
1888 |        "      <td>5.1</td>\n",
1889 |        "      <td>1.8</td>\n",
1890 |        "      <td>5</td>\n",
1891 |        "      <td>0.0</td>\n",
1892 |        "      <td>0.0</td>\n",
1893 |        "      <td>1.0</td>\n",
1894 |        "    </tr>\n",
1895 |        "  </tbody>\n",
1896 |        "</table>\n",
1897 |        "<p>150 rows × 8 columns</p>\n",
1898 |        "</div>"
1899 |       ],
1900 |       "text/plain": [
1901 |        "     Sepal_Length  Sepal_Width  Petal_Length  Petal_Width  petal length(cm)  \\\n",
1902 |        "0             5.1          3.5           1.4          0.2                 1   \n",
1903 |        "1             4.9          3.0           1.4          0.2                 1   \n",
1904 |        "2             4.7          3.2           1.3          0.2                 1   \n",
1905 |        "3             4.6          3.1           1.5          0.2                 1   \n",
1906 |        "4             5.0          3.6           1.4          0.2                 1   \n",
1907 |        "..            ...          ...           ...          ...               ...   \n",
1908 |        "145           6.7          3.0           5.2          2.3                 5   \n",
1909 |        "146           6.3          2.5           5.0          1.9                 5   \n",
1910 |        "147           6.5          3.0           5.2          2.0                 5   \n",
1911 |        "148           6.2          3.4           5.4          2.3                 5   \n",
1912 |        "149           5.9          3.0           5.1          1.8                 5   \n",
1913 |        "\n",
1914 |        "     Iris-Setosa  Iris-Vrsicolor  Iris-virginca  \n",
1915 |        "0            1.0             0.0            0.0  \n",
1916 |        "1            1.0             0.0            0.0  \n",
1917 |        "2            1.0             0.0            0.0  \n",
1918 |        "3            1.0             0.0            0.0  \n",
1919 |        "4            1.0             0.0            0.0  \n",
1920 |        "..           ...             ...            ...  \n",
1921 |        "145          0.0             0.0            1.0  \n",
1922 |        "146          0.0             0.0            1.0  \n",
1923 |        "147          0.0             0.0            1.0  \n",
1924 |        "148          0.0             0.0            1.0  \n",
1925 |        "149          0.0             0.0            1.0  \n",
1926 |        "\n",
1927 |        "[150 rows x 8 columns]"
1928 |       ]
1929 |      },
1930 |      "execution_count": 39,
1931 |      "metadata": {},
1932 |      "output_type": "execute_result"
1933 |     }
1934 |    ],
1935 |    "source": [
1936 |     "df_encode"
1937 |    ]
1938 |   },
1939 |   {
1940 |    "cell_type": "code",
1941 |    "execution_count": null,
1942 |    "id": "4122e8aa",
1943 |    "metadata": {},
1944 |    "outputs": [],
1945 |    "source": []
1946 |   },
1947 |   {
1948 |    "cell_type": "code",
1949 |    "execution_count": null,
1950 |    "id": "0c97b5d4",
1951 |    "metadata": {},
1952 |    "outputs": [],
1953 |    "source": []
1954 |   },
1955 |   {
1956 |    "cell_type": "code",
1957 |    "execution_count": null,
1958 |    "id": "11f191f1",
1959 |    "metadata": {},
1960 |    "outputs": [],
1961 |    "source": []
1962 |   },
1963 |   {
1964 |    "cell_type": "code",
1965 |    "execution_count": null,
1966 |    "id": "d318f1e8",
1967 |    "metadata": {},
1968 |    "outputs": [],
1969 |    "source": []
1970 |   },
1971 |   {
1972 |    "cell_type": "code",
1973 |    "execution_count": null,
1974 |    "id": "bf4ab003",
1975 |    "metadata": {},
1976 |    "outputs": [],
1977 |    "source": []
1978 |   }
1979 |  ],
1980 |  "metadata": {
1981 |   "kernelspec": {
1982 |    "display_name": "Python 3 (ipykernel)",
1983 |    "language": "python",
1984 |    "name": "python3"
1985 |   },
1986 |   "language_info": {
1987 |    "codemirror_mode": {
1988 |     "name": "ipython",
1989 |     "version": 3
1990 |    },
1991 |    "file_extension": ".py",
1992 |    "mimetype": "text/x-python",
1993 |    "name": "python",
1994 |    "nbconvert_exporter": "python",
1995 |    "pygments_lexer": "ipython3",
1996 |    "version": "3.9.13"
1997 |   }
1998 |  },
1999 |  "nbformat": 4,
2000 |  "nbformat_minor": 5
2001 | }
2002 | 


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