├── .DS_Store
├── NaiveBayes
    ├── mnist_train_small.csv
    └── naiveBayes.ipynb
├── Perceptron
    ├── mnist_train_small.csv
    └── perceptron_jf.ipynb
├── README.md
├── data
    └── clean_weather.csv
├── gradientDescent
    └── gradientDescent.ipynb
├── knn
    ├── .DS_Store
    ├── knn.ipynb
    └── mnist_train_small.csv
├── linear_regression
    ├── .DS_Store
    ├── cal_housing_price_prediciton.ipynb
    ├── california_housing_test.csv
    ├── california_housing_train.csv
    ├── price_prediction.ipynb
    └── regression.ipynb
└── logistic_regression
    ├── logistic_classification.ipynb
    └── mnist_train_small.csv


/.DS_Store:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/taureanjoe/Machine-Learning/2d095810454989fafec46017a4a6d08631c5b999/.DS_Store


--------------------------------------------------------------------------------
/NaiveBayes/naiveBayes.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 2,
  6 |    "metadata": {},
  7 |    "outputs": [],
  8 |    "source": [
  9 |     "import numpy as np\n",
 10 |     "import pandas as pd\n",
 11 |     "import matplotlib.pyplot as plt\n",
 12 |     "\n",
 13 |     "from sklearn.preprocessing import MinMaxScaler"
 14 |    ]
 15 |   },
 16 |   {
 17 |    "cell_type": "code",
 18 |    "execution_count": 3,
 19 |    "metadata": {},
 20 |    "outputs": [
 21 |     {
 22 |      "data": {
 23 |       "text/html": [
 24 |        "<div>\n",
 25 |        "<style scoped>\n",
 26 |        "    .dataframe tbody tr th:only-of-type {\n",
 27 |        "        vertical-align: middle;\n",
 28 |        "    }\n",
 29 |        "\n",
 30 |        "    .dataframe tbody tr th {\n",
 31 |        "        vertical-align: top;\n",
 32 |        "    }\n",
 33 |        "\n",
 34 |        "    .dataframe thead th {\n",
 35 |        "        text-align: right;\n",
 36 |        "    }\n",
 37 |        "</style>\n",
 38 |        "<table border=\"1\" class=\"dataframe\">\n",
 39 |        "  <thead>\n",
 40 |        "    <tr style=\"text-align: right;\">\n",
 41 |        "      <th></th>\n",
 42 |        "      <th>0</th>\n",
 43 |        "      <th>1</th>\n",
 44 |        "      <th>2</th>\n",
 45 |        "      <th>3</th>\n",
 46 |        "      <th>4</th>\n",
 47 |        "      <th>5</th>\n",
 48 |        "      <th>6</th>\n",
 49 |        "      <th>7</th>\n",
 50 |        "      <th>8</th>\n",
 51 |        "      <th>9</th>\n",
 52 |        "      <th>...</th>\n",
 53 |        "      <th>775</th>\n",
 54 |        "      <th>776</th>\n",
 55 |        "      <th>777</th>\n",
 56 |        "      <th>778</th>\n",
 57 |        "      <th>779</th>\n",
 58 |        "      <th>780</th>\n",
 59 |        "      <th>781</th>\n",
 60 |        "      <th>782</th>\n",
 61 |        "      <th>783</th>\n",
 62 |        "      <th>784</th>\n",
 63 |        "    </tr>\n",
 64 |        "  </thead>\n",
 65 |        "  <tbody>\n",
 66 |        "    <tr>\n",
 67 |        "      <th>19995</th>\n",
 68 |        "      <td>0</td>\n",
 69 |        "      <td>0</td>\n",
 70 |        "      <td>0</td>\n",
 71 |        "      <td>0</td>\n",
 72 |        "      <td>0</td>\n",
 73 |        "      <td>0</td>\n",
 74 |        "      <td>0</td>\n",
 75 |        "      <td>0</td>\n",
 76 |        "      <td>0</td>\n",
 77 |        "      <td>0</td>\n",
 78 |        "      <td>...</td>\n",
 79 |        "      <td>0</td>\n",
 80 |        "      <td>0</td>\n",
 81 |        "      <td>0</td>\n",
 82 |        "      <td>0</td>\n",
 83 |        "      <td>0</td>\n",
 84 |        "      <td>0</td>\n",
 85 |        "      <td>0</td>\n",
 86 |        "      <td>0</td>\n",
 87 |        "      <td>0</td>\n",
 88 |        "      <td>0</td>\n",
 89 |        "    </tr>\n",
 90 |        "    <tr>\n",
 91 |        "      <th>19996</th>\n",
 92 |        "      <td>1</td>\n",
 93 |        "      <td>0</td>\n",
 94 |        "      <td>0</td>\n",
 95 |        "      <td>0</td>\n",
 96 |        "      <td>0</td>\n",
 97 |        "      <td>0</td>\n",
 98 |        "      <td>0</td>\n",
 99 |        "      <td>0</td>\n",
100 |        "      <td>0</td>\n",
101 |        "      <td>0</td>\n",
102 |        "      <td>...</td>\n",
103 |        "      <td>0</td>\n",
104 |        "      <td>0</td>\n",
105 |        "      <td>0</td>\n",
106 |        "      <td>0</td>\n",
107 |        "      <td>0</td>\n",
108 |        "      <td>0</td>\n",
109 |        "      <td>0</td>\n",
110 |        "      <td>0</td>\n",
111 |        "      <td>0</td>\n",
112 |        "      <td>0</td>\n",
113 |        "    </tr>\n",
114 |        "    <tr>\n",
115 |        "      <th>19997</th>\n",
116 |        "      <td>2</td>\n",
117 |        "      <td>0</td>\n",
118 |        "      <td>0</td>\n",
119 |        "      <td>0</td>\n",
120 |        "      <td>0</td>\n",
121 |        "      <td>0</td>\n",
122 |        "      <td>0</td>\n",
123 |        "      <td>0</td>\n",
124 |        "      <td>0</td>\n",
125 |        "      <td>0</td>\n",
126 |        "      <td>...</td>\n",
127 |        "      <td>0</td>\n",
128 |        "      <td>0</td>\n",
129 |        "      <td>0</td>\n",
130 |        "      <td>0</td>\n",
131 |        "      <td>0</td>\n",
132 |        "      <td>0</td>\n",
133 |        "      <td>0</td>\n",
134 |        "      <td>0</td>\n",
135 |        "      <td>0</td>\n",
136 |        "      <td>0</td>\n",
137 |        "    </tr>\n",
138 |        "    <tr>\n",
139 |        "      <th>19998</th>\n",
140 |        "      <td>9</td>\n",
141 |        "      <td>0</td>\n",
142 |        "      <td>0</td>\n",
143 |        "      <td>0</td>\n",
144 |        "      <td>0</td>\n",
145 |        "      <td>0</td>\n",
146 |        "      <td>0</td>\n",
147 |        "      <td>0</td>\n",
148 |        "      <td>0</td>\n",
149 |        "      <td>0</td>\n",
150 |        "      <td>...</td>\n",
151 |        "      <td>0</td>\n",
152 |        "      <td>0</td>\n",
153 |        "      <td>0</td>\n",
154 |        "      <td>0</td>\n",
155 |        "      <td>0</td>\n",
156 |        "      <td>0</td>\n",
157 |        "      <td>0</td>\n",
158 |        "      <td>0</td>\n",
159 |        "      <td>0</td>\n",
160 |        "      <td>0</td>\n",
161 |        "    </tr>\n",
162 |        "    <tr>\n",
163 |        "      <th>19999</th>\n",
164 |        "      <td>5</td>\n",
165 |        "      <td>0</td>\n",
166 |        "      <td>0</td>\n",
167 |        "      <td>0</td>\n",
168 |        "      <td>0</td>\n",
169 |        "      <td>0</td>\n",
170 |        "      <td>0</td>\n",
171 |        "      <td>0</td>\n",
172 |        "      <td>0</td>\n",
173 |        "      <td>0</td>\n",
174 |        "      <td>...</td>\n",
175 |        "      <td>0</td>\n",
176 |        "      <td>0</td>\n",
177 |        "      <td>0</td>\n",
178 |        "      <td>0</td>\n",
179 |        "      <td>0</td>\n",
180 |        "      <td>0</td>\n",
181 |        "      <td>0</td>\n",
182 |        "      <td>0</td>\n",
183 |        "      <td>0</td>\n",
184 |        "      <td>0</td>\n",
185 |        "    </tr>\n",
186 |        "  </tbody>\n",
187 |        "</table>\n",
188 |        "<p>5 rows × 785 columns</p>\n",
189 |        "</div>"
190 |       ],
191 |       "text/plain": [
192 |        "       0    1    2    3    4    5    6    7    8    9    ...  775  776  777  \\\n",
193 |        "19995    0    0    0    0    0    0    0    0    0    0  ...    0    0    0   \n",
194 |        "19996    1    0    0    0    0    0    0    0    0    0  ...    0    0    0   \n",
195 |        "19997    2    0    0    0    0    0    0    0    0    0  ...    0    0    0   \n",
196 |        "19998    9    0    0    0    0    0    0    0    0    0  ...    0    0    0   \n",
197 |        "19999    5    0    0    0    0    0    0    0    0    0  ...    0    0    0   \n",
198 |        "\n",
199 |        "       778  779  780  781  782  783  784  \n",
200 |        "19995    0    0    0    0    0    0    0  \n",
201 |        "19996    0    0    0    0    0    0    0  \n",
202 |        "19997    0    0    0    0    0    0    0  \n",
203 |        "19998    0    0    0    0    0    0    0  \n",
204 |        "19999    0    0    0    0    0    0    0  \n",
205 |        "\n",
206 |        "[5 rows x 785 columns]"
207 |       ]
208 |      },
209 |      "execution_count": 3,
210 |      "metadata": {},
211 |      "output_type": "execute_result"
212 |     }
213 |    ],
214 |    "source": [
215 |     "data = pd.read_csv(\"mnist_train_small.csv\", header= None)\n",
216 |     "data.tail()"
217 |    ]
218 |   },
219 |   {
220 |    "cell_type": "code",
221 |    "execution_count": 4,
222 |    "metadata": {},
223 |    "outputs": [],
224 |    "source": [
225 |     "# Mnist - Digit recognition dataset\n",
226 |     "# Image is embedded inside the csv file\n",
227 |     "# 28*28 -> flattened -> fitting into a csv file\n",
228 |     "\n",
229 |     "# 785 -> 1 column (output), 784 (image)\n",
230 |     "# pixel range - (0-255)\n",
231 |     "# 0 - black\n",
232 |     "# 255 - white"
233 |    ]
234 |   },
235 |   {
236 |    "cell_type": "code",
237 |    "execution_count": 5,
238 |    "metadata": {},
239 |    "outputs": [
240 |     {
241 |      "data": {
242 |       "text/plain": [
243 |        "False"
244 |       ]
245 |      },
246 |      "execution_count": 5,
247 |      "metadata": {},
248 |      "output_type": "execute_result"
249 |     }
250 |    ],
251 |    "source": [
252 |     "data.isnull().sum().any()\n"
253 |    ]
254 |   },
255 |   {
256 |    "cell_type": "code",
257 |    "execution_count": 6,
258 |    "metadata": {},
259 |    "outputs": [
260 |     {
261 |      "name": "stdout",
262 |      "output_type": "stream",
263 |      "text": [
264 |       "<class 'pandas.core.frame.DataFrame'>\n",
265 |       "RangeIndex: 20000 entries, 0 to 19999\n",
266 |       "Columns: 785 entries, 0 to 784\n",
267 |       "dtypes: int64(785)\n",
268 |       "memory usage: 119.8 MB\n"
269 |      ]
270 |     }
271 |    ],
272 |    "source": [
273 |     "data.info()"
274 |    ]
275 |   },
276 |   {
277 |    "cell_type": "code",
278 |    "execution_count": 7,
279 |    "metadata": {},
280 |    "outputs": [
281 |     {
282 |      "data": {
283 |       "text/plain": [
284 |        "((20000, 784), (20000,))"
285 |       ]
286 |      },
287 |      "execution_count": 7,
288 |      "metadata": {},
289 |      "output_type": "execute_result"
290 |     }
291 |    ],
292 |    "source": [
293 |     "# dividing features and targets\n",
294 |     "\n",
295 |     "X = data.iloc[:, 1:].values\n",
296 |     "Y = data.iloc[:, 0].values\n",
297 |     "\n",
298 |     "X.shape, Y.shape"
299 |    ]
300 |   },
301 |   {
302 |    "cell_type": "code",
303 |    "execution_count": 8,
304 |    "metadata": {},
305 |    "outputs": [
306 |     {
307 |      "data": {
308 |       "text/plain": [
309 |        "255"
310 |       ]
311 |      },
312 |      "execution_count": 8,
313 |      "metadata": {},
314 |      "output_type": "execute_result"
315 |     }
316 |    ],
317 |    "source": [
318 |     "X.max()"
319 |    ]
320 |   },
321 |   {
322 |    "cell_type": "code",
323 |    "execution_count": 9,
324 |    "metadata": {},
325 |    "outputs": [],
326 |    "source": [
327 |     "scaler = MinMaxScaler()\n",
328 |     "X = scaler.fit_transform(X)"
329 |    ]
330 |   },
331 |   {
332 |    "cell_type": "code",
333 |    "execution_count": 10,
334 |    "metadata": {},
335 |    "outputs": [
336 |     {
337 |      "data": {
338 |       "text/plain": [
339 |        "(20000, 784)"
340 |       ]
341 |      },
342 |      "execution_count": 10,
343 |      "metadata": {},
344 |      "output_type": "execute_result"
345 |     }
346 |    ],
347 |    "source": [
348 |     "X.shape"
349 |    ]
350 |   },
351 |   {
352 |    "cell_type": "code",
353 |    "execution_count": 11,
354 |    "metadata": {},
355 |    "outputs": [],
356 |    "source": [
357 |     "def PlotImage(X, Y):\n",
358 |     "    idx = np.random.choice(X.shape[0])\n",
359 |     "    label = Y[idx]\n",
360 |     "    print(\" Target : \", label)\n",
361 |     "    x = X[idx, :]\n",
362 |     "    x = x.reshape(28,28)\n",
363 |     "    plt.imshow(x) "
364 |    ]
365 |   },
366 |   {
367 |    "cell_type": "code",
368 |    "execution_count": 12,
369 |    "metadata": {},
370 |    "outputs": [
371 |     {
372 |      "name": "stdout",
373 |      "output_type": "stream",
374 |      "text": [
375 |       " Target :  8\n"
376 |      ]
377 |     },
378 |     {
379 |      "data": {
380 |       "image/png": "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",
381 |       "text/plain": [
382 |        "<Figure size 640x480 with 1 Axes>"
383 |       ]
384 |      },
385 |      "metadata": {},
386 |      "output_type": "display_data"
387 |     }
388 |    ],
389 |    "source": [
390 |     "PlotImage(X,Y)"
391 |    ]
392 |   },
393 |   {
394 |    "cell_type": "code",
395 |    "execution_count": 13,
396 |    "metadata": {},
397 |    "outputs": [
398 |     {
399 |      "name": "stdout",
400 |      "output_type": "stream",
401 |      "text": [
402 |       " training Data shape :  (16000, 784) (16000,)\n",
403 |       " testing Data shape :  (4000, 784) (4000,)\n"
404 |      ]
405 |     }
406 |    ],
407 |    "source": [
408 |     "from sklearn.model_selection import train_test_split\n",
409 |     "Xtrain,Xtest, Ytrain, Ytest = train_test_split(X, Y, test_size=0.2, shuffle=True, random_state=4)\n",
410 |     "\n",
411 |     "print(\" training Data shape : \", Xtrain.shape, Ytrain.shape)\n",
412 |     "print(\" testing Data shape : \", Xtest.shape, Ytest.shape)"
413 |    ]
414 |   },
415 |   {
416 |    "cell_type": "code",
417 |    "execution_count": 14,
418 |    "metadata": {},
419 |    "outputs": [
420 |     {
421 |      "name": "stdout",
422 |      "output_type": "stream",
423 |      "text": [
424 |       "CPU times: user 267 ms, sys: 114 ms, total: 381 ms\n",
425 |       "Wall time: 641 ms\n"
426 |      ]
427 |     },
428 |     {
429 |      "data": {
430 |       "text/html": [
431 |        "<style>#sk-container-id-1 {color: black;background-color: white;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>GaussianNB()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">GaussianNB</label><div class=\"sk-toggleable__content\"><pre>GaussianNB()</pre></div></div></div></div></div>"
432 |       ],
433 |       "text/plain": [
434 |        "GaussianNB()"
435 |       ]
436 |      },
437 |      "execution_count": 14,
438 |      "metadata": {},
439 |      "output_type": "execute_result"
440 |     }
441 |    ],
442 |    "source": [
443 |     "from sklearn.naive_bayes import GaussianNB\n",
444 |     "\n",
445 |     "model = GaussianNB()\n",
446 |     "%time model.fit(Xtrain, Ytrain)"
447 |    ]
448 |   },
449 |   {
450 |    "cell_type": "code",
451 |    "execution_count": 15,
452 |    "metadata": {},
453 |    "outputs": [
454 |     {
455 |      "name": "stdout",
456 |      "output_type": "stream",
457 |      "text": [
458 |       "CPU times: user 284 ms, sys: 86.9 ms, total: 371 ms\n",
459 |       "Wall time: 548 ms\n"
460 |      ]
461 |     }
462 |    ],
463 |    "source": [
464 |     "%time predictions = model.predict(Xtest)"
465 |    ]
466 |   },
467 |   {
468 |    "cell_type": "code",
469 |    "execution_count": 16,
470 |    "metadata": {},
471 |    "outputs": [
472 |     {
473 |      "data": {
474 |       "text/plain": [
475 |        "0.55425"
476 |       ]
477 |      },
478 |      "execution_count": 16,
479 |      "metadata": {},
480 |      "output_type": "execute_result"
481 |     }
482 |    ],
483 |    "source": [
484 |     "\n",
485 |     "# model.score() -> regression - R2score\n",
486 |     "#----------------> classification - accuracy\n",
487 |     "\n",
488 |     "model.score(Xtest, Ytest)"
489 |    ]
490 |   },
491 |   {
492 |    "cell_type": "code",
493 |    "execution_count": null,
494 |    "metadata": {},
495 |    "outputs": [],
496 |    "source": []
497 |   }
498 |  ],
499 |  "metadata": {
500 |   "kernelspec": {
501 |    "display_name": "Python 3.10.6 64-bit",
502 |    "language": "python",
503 |    "name": "python3"
504 |   },
505 |   "language_info": {
506 |    "codemirror_mode": {
507 |     "name": "ipython",
508 |     "version": 3
509 |    },
510 |    "file_extension": ".py",
511 |    "mimetype": "text/x-python",
512 |    "name": "python",
513 |    "nbconvert_exporter": "python",
514 |    "pygments_lexer": "ipython3",
515 |    "version": "3.10.6"
516 |   },
517 |   "orig_nbformat": 4,
518 |   "vscode": {
519 |    "interpreter": {
520 |     "hash": "aee8b7b246df8f9039afb4144a1f6fd8d2ca17a180786b69acc140d282b71a49"
521 |    }
522 |   }
523 |  },
524 |  "nbformat": 4,
525 |  "nbformat_minor": 2
526 | }
527 | 


--------------------------------------------------------------------------------
/Perceptron/perceptron_jf.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 3,
  6 |    "metadata": {},
  7 |    "outputs": [],
  8 |    "source": [
  9 |     "import numpy as np\n",
 10 |     "import pandas as pd\n",
 11 |     "import matplotlib.pyplot as plt\n",
 12 |     "\n",
 13 |     "from sklearn.preprocessing import MinMaxScaler"
 14 |    ]
 15 |   },
 16 |   {
 17 |    "cell_type": "code",
 18 |    "execution_count": 4,
 19 |    "metadata": {},
 20 |    "outputs": [
 21 |     {
 22 |      "data": {
 23 |       "text/html": [
 24 |        "<div>\n",
 25 |        "<style scoped>\n",
 26 |        "    .dataframe tbody tr th:only-of-type {\n",
 27 |        "        vertical-align: middle;\n",
 28 |        "    }\n",
 29 |        "\n",
 30 |        "    .dataframe tbody tr th {\n",
 31 |        "        vertical-align: top;\n",
 32 |        "    }\n",
 33 |        "\n",
 34 |        "    .dataframe thead th {\n",
 35 |        "        text-align: right;\n",
 36 |        "    }\n",
 37 |        "</style>\n",
 38 |        "<table border=\"1\" class=\"dataframe\">\n",
 39 |        "  <thead>\n",
 40 |        "    <tr style=\"text-align: right;\">\n",
 41 |        "      <th></th>\n",
 42 |        "      <th>0</th>\n",
 43 |        "      <th>1</th>\n",
 44 |        "      <th>2</th>\n",
 45 |        "      <th>3</th>\n",
 46 |        "      <th>4</th>\n",
 47 |        "      <th>5</th>\n",
 48 |        "      <th>6</th>\n",
 49 |        "      <th>7</th>\n",
 50 |        "      <th>8</th>\n",
 51 |        "      <th>9</th>\n",
 52 |        "      <th>...</th>\n",
 53 |        "      <th>775</th>\n",
 54 |        "      <th>776</th>\n",
 55 |        "      <th>777</th>\n",
 56 |        "      <th>778</th>\n",
 57 |        "      <th>779</th>\n",
 58 |        "      <th>780</th>\n",
 59 |        "      <th>781</th>\n",
 60 |        "      <th>782</th>\n",
 61 |        "      <th>783</th>\n",
 62 |        "      <th>784</th>\n",
 63 |        "    </tr>\n",
 64 |        "  </thead>\n",
 65 |        "  <tbody>\n",
 66 |        "    <tr>\n",
 67 |        "      <th>19995</th>\n",
 68 |        "      <td>0</td>\n",
 69 |        "      <td>0</td>\n",
 70 |        "      <td>0</td>\n",
 71 |        "      <td>0</td>\n",
 72 |        "      <td>0</td>\n",
 73 |        "      <td>0</td>\n",
 74 |        "      <td>0</td>\n",
 75 |        "      <td>0</td>\n",
 76 |        "      <td>0</td>\n",
 77 |        "      <td>0</td>\n",
 78 |        "      <td>...</td>\n",
 79 |        "      <td>0</td>\n",
 80 |        "      <td>0</td>\n",
 81 |        "      <td>0</td>\n",
 82 |        "      <td>0</td>\n",
 83 |        "      <td>0</td>\n",
 84 |        "      <td>0</td>\n",
 85 |        "      <td>0</td>\n",
 86 |        "      <td>0</td>\n",
 87 |        "      <td>0</td>\n",
 88 |        "      <td>0</td>\n",
 89 |        "    </tr>\n",
 90 |        "    <tr>\n",
 91 |        "      <th>19996</th>\n",
 92 |        "      <td>1</td>\n",
 93 |        "      <td>0</td>\n",
 94 |        "      <td>0</td>\n",
 95 |        "      <td>0</td>\n",
 96 |        "      <td>0</td>\n",
 97 |        "      <td>0</td>\n",
 98 |        "      <td>0</td>\n",
 99 |        "      <td>0</td>\n",
100 |        "      <td>0</td>\n",
101 |        "      <td>0</td>\n",
102 |        "      <td>...</td>\n",
103 |        "      <td>0</td>\n",
104 |        "      <td>0</td>\n",
105 |        "      <td>0</td>\n",
106 |        "      <td>0</td>\n",
107 |        "      <td>0</td>\n",
108 |        "      <td>0</td>\n",
109 |        "      <td>0</td>\n",
110 |        "      <td>0</td>\n",
111 |        "      <td>0</td>\n",
112 |        "      <td>0</td>\n",
113 |        "    </tr>\n",
114 |        "    <tr>\n",
115 |        "      <th>19997</th>\n",
116 |        "      <td>2</td>\n",
117 |        "      <td>0</td>\n",
118 |        "      <td>0</td>\n",
119 |        "      <td>0</td>\n",
120 |        "      <td>0</td>\n",
121 |        "      <td>0</td>\n",
122 |        "      <td>0</td>\n",
123 |        "      <td>0</td>\n",
124 |        "      <td>0</td>\n",
125 |        "      <td>0</td>\n",
126 |        "      <td>...</td>\n",
127 |        "      <td>0</td>\n",
128 |        "      <td>0</td>\n",
129 |        "      <td>0</td>\n",
130 |        "      <td>0</td>\n",
131 |        "      <td>0</td>\n",
132 |        "      <td>0</td>\n",
133 |        "      <td>0</td>\n",
134 |        "      <td>0</td>\n",
135 |        "      <td>0</td>\n",
136 |        "      <td>0</td>\n",
137 |        "    </tr>\n",
138 |        "    <tr>\n",
139 |        "      <th>19998</th>\n",
140 |        "      <td>9</td>\n",
141 |        "      <td>0</td>\n",
142 |        "      <td>0</td>\n",
143 |        "      <td>0</td>\n",
144 |        "      <td>0</td>\n",
145 |        "      <td>0</td>\n",
146 |        "      <td>0</td>\n",
147 |        "      <td>0</td>\n",
148 |        "      <td>0</td>\n",
149 |        "      <td>0</td>\n",
150 |        "      <td>...</td>\n",
151 |        "      <td>0</td>\n",
152 |        "      <td>0</td>\n",
153 |        "      <td>0</td>\n",
154 |        "      <td>0</td>\n",
155 |        "      <td>0</td>\n",
156 |        "      <td>0</td>\n",
157 |        "      <td>0</td>\n",
158 |        "      <td>0</td>\n",
159 |        "      <td>0</td>\n",
160 |        "      <td>0</td>\n",
161 |        "    </tr>\n",
162 |        "    <tr>\n",
163 |        "      <th>19999</th>\n",
164 |        "      <td>5</td>\n",
165 |        "      <td>0</td>\n",
166 |        "      <td>0</td>\n",
167 |        "      <td>0</td>\n",
168 |        "      <td>0</td>\n",
169 |        "      <td>0</td>\n",
170 |        "      <td>0</td>\n",
171 |        "      <td>0</td>\n",
172 |        "      <td>0</td>\n",
173 |        "      <td>0</td>\n",
174 |        "      <td>...</td>\n",
175 |        "      <td>0</td>\n",
176 |        "      <td>0</td>\n",
177 |        "      <td>0</td>\n",
178 |        "      <td>0</td>\n",
179 |        "      <td>0</td>\n",
180 |        "      <td>0</td>\n",
181 |        "      <td>0</td>\n",
182 |        "      <td>0</td>\n",
183 |        "      <td>0</td>\n",
184 |        "      <td>0</td>\n",
185 |        "    </tr>\n",
186 |        "  </tbody>\n",
187 |        "</table>\n",
188 |        "<p>5 rows × 785 columns</p>\n",
189 |        "</div>"
190 |       ],
191 |       "text/plain": [
192 |        "       0    1    2    3    4    5    6    7    8    9    ...  775  776  777  \\\n",
193 |        "19995    0    0    0    0    0    0    0    0    0    0  ...    0    0    0   \n",
194 |        "19996    1    0    0    0    0    0    0    0    0    0  ...    0    0    0   \n",
195 |        "19997    2    0    0    0    0    0    0    0    0    0  ...    0    0    0   \n",
196 |        "19998    9    0    0    0    0    0    0    0    0    0  ...    0    0    0   \n",
197 |        "19999    5    0    0    0    0    0    0    0    0    0  ...    0    0    0   \n",
198 |        "\n",
199 |        "       778  779  780  781  782  783  784  \n",
200 |        "19995    0    0    0    0    0    0    0  \n",
201 |        "19996    0    0    0    0    0    0    0  \n",
202 |        "19997    0    0    0    0    0    0    0  \n",
203 |        "19998    0    0    0    0    0    0    0  \n",
204 |        "19999    0    0    0    0    0    0    0  \n",
205 |        "\n",
206 |        "[5 rows x 785 columns]"
207 |       ]
208 |      },
209 |      "execution_count": 4,
210 |      "metadata": {},
211 |      "output_type": "execute_result"
212 |     }
213 |    ],
214 |    "source": [
215 |     "data = pd.read_csv(\"mnist_train_small.csv\", header= None)\n",
216 |     "data.tail()"
217 |    ]
218 |   },
219 |   {
220 |    "cell_type": "code",
221 |    "execution_count": 5,
222 |    "metadata": {},
223 |    "outputs": [],
224 |    "source": [
225 |     "# Mnist - Digit recognition dataset\n",
226 |     "# Image is embedded inside the csv file\n",
227 |     "# 28*28 -> flattened -> fitting into a csv file\n",
228 |     "\n",
229 |     "# 785 -> 1 column (output), 784 (image)\n",
230 |     "# pixel range - (0-255)\n",
231 |     "# 0 - black\n",
232 |     "# 255 - white"
233 |    ]
234 |   },
235 |   {
236 |    "cell_type": "code",
237 |    "execution_count": 6,
238 |    "metadata": {},
239 |    "outputs": [
240 |     {
241 |      "data": {
242 |       "text/plain": [
243 |        "False"
244 |       ]
245 |      },
246 |      "execution_count": 6,
247 |      "metadata": {},
248 |      "output_type": "execute_result"
249 |     }
250 |    ],
251 |    "source": [
252 |     "data.isnull().sum().any()\n"
253 |    ]
254 |   },
255 |   {
256 |    "cell_type": "code",
257 |    "execution_count": 7,
258 |    "metadata": {},
259 |    "outputs": [
260 |     {
261 |      "name": "stdout",
262 |      "output_type": "stream",
263 |      "text": [
264 |       "<class 'pandas.core.frame.DataFrame'>\n",
265 |       "RangeIndex: 20000 entries, 0 to 19999\n",
266 |       "Columns: 785 entries, 0 to 784\n",
267 |       "dtypes: int64(785)\n",
268 |       "memory usage: 119.8 MB\n"
269 |      ]
270 |     }
271 |    ],
272 |    "source": [
273 |     "data.info()"
274 |    ]
275 |   },
276 |   {
277 |    "cell_type": "code",
278 |    "execution_count": 8,
279 |    "metadata": {},
280 |    "outputs": [
281 |     {
282 |      "data": {
283 |       "text/plain": [
284 |        "((20000, 784), (20000,))"
285 |       ]
286 |      },
287 |      "execution_count": 8,
288 |      "metadata": {},
289 |      "output_type": "execute_result"
290 |     }
291 |    ],
292 |    "source": [
293 |     "# dividing features and targets\n",
294 |     "\n",
295 |     "X = data.iloc[:, 1:].values\n",
296 |     "Y = data.iloc[:, 0].values\n",
297 |     "\n",
298 |     "X.shape, Y.shape"
299 |    ]
300 |   },
301 |   {
302 |    "cell_type": "code",
303 |    "execution_count": 9,
304 |    "metadata": {},
305 |    "outputs": [
306 |     {
307 |      "data": {
308 |       "text/plain": [
309 |        "255"
310 |       ]
311 |      },
312 |      "execution_count": 9,
313 |      "metadata": {},
314 |      "output_type": "execute_result"
315 |     }
316 |    ],
317 |    "source": [
318 |     "X.max()"
319 |    ]
320 |   },
321 |   {
322 |    "cell_type": "code",
323 |    "execution_count": 10,
324 |    "metadata": {},
325 |    "outputs": [],
326 |    "source": [
327 |     "scaler = MinMaxScaler()\n",
328 |     "X = scaler.fit_transform(X)"
329 |    ]
330 |   },
331 |   {
332 |    "cell_type": "code",
333 |    "execution_count": 11,
334 |    "metadata": {},
335 |    "outputs": [
336 |     {
337 |      "data": {
338 |       "text/plain": [
339 |        "(20000, 784)"
340 |       ]
341 |      },
342 |      "execution_count": 11,
343 |      "metadata": {},
344 |      "output_type": "execute_result"
345 |     }
346 |    ],
347 |    "source": [
348 |     "X.shape"
349 |    ]
350 |   },
351 |   {
352 |    "cell_type": "code",
353 |    "execution_count": 12,
354 |    "metadata": {},
355 |    "outputs": [],
356 |    "source": [
357 |     "def PlotImage(X, Y):\n",
358 |     "    idx = np.random.choice(X.shape[0])\n",
359 |     "    label = Y[idx]\n",
360 |     "    print(\" Target : \", label)\n",
361 |     "    x = X[idx, :]\n",
362 |     "    x = x.reshape(28,28)\n",
363 |     "    plt.imshow(x) "
364 |    ]
365 |   },
366 |   {
367 |    "cell_type": "code",
368 |    "execution_count": 13,
369 |    "metadata": {},
370 |    "outputs": [
371 |     {
372 |      "name": "stdout",
373 |      "output_type": "stream",
374 |      "text": [
375 |       " Target :  8\n"
376 |      ]
377 |     },
378 |     {
379 |      "data": {
380 |       "image/png": "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",
381 |       "text/plain": [
382 |        "<Figure size 640x480 with 1 Axes>"
383 |       ]
384 |      },
385 |      "metadata": {},
386 |      "output_type": "display_data"
387 |     }
388 |    ],
389 |    "source": [
390 |     "PlotImage(X,Y)"
391 |    ]
392 |   },
393 |   {
394 |    "cell_type": "code",
395 |    "execution_count": 14,
396 |    "metadata": {},
397 |    "outputs": [
398 |     {
399 |      "name": "stdout",
400 |      "output_type": "stream",
401 |      "text": [
402 |       " training Data shape :  (16000, 784) (16000,)\n",
403 |       " testing Data shape :  (4000, 784) (4000,)\n"
404 |      ]
405 |     }
406 |    ],
407 |    "source": [
408 |     "from sklearn.model_selection import train_test_split\n",
409 |     "Xtrain,Xtest, Ytrain, Ytest = train_test_split(X, Y, test_size=0.2, shuffle=True, random_state=4)\n",
410 |     "\n",
411 |     "print(\" training Data shape : \", Xtrain.shape, Ytrain.shape)\n",
412 |     "print(\" testing Data shape : \", Xtest.shape, Ytest.shape)"
413 |    ]
414 |   },
415 |   {
416 |    "cell_type": "code",
417 |    "execution_count": 15,
418 |    "metadata": {},
419 |    "outputs": [
420 |     {
421 |      "name": "stdout",
422 |      "output_type": "stream",
423 |      "text": [
424 |       "CPU times: user 17.9 ms, sys: 923 µs, total: 18.8 ms\n",
425 |       "Wall time: 19.4 ms\n"
426 |      ]
427 |     },
428 |     {
429 |      "data": {
430 |       "text/html": [
431 |        "<style>#sk-container-id-1 {color: black;background-color: white;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>KNeighborsClassifier()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">KNeighborsClassifier</label><div class=\"sk-toggleable__content\"><pre>KNeighborsClassifier()</pre></div></div></div></div></div>"
432 |       ],
433 |       "text/plain": [
434 |        "KNeighborsClassifier()"
435 |       ]
436 |      },
437 |      "execution_count": 15,
438 |      "metadata": {},
439 |      "output_type": "execute_result"
440 |     }
441 |    ],
442 |    "source": [
443 |     "from sklearn.neighbors import KNeighborsClassifier\n",
444 |     "\n",
445 |     "model = KNeighborsClassifier()\n",
446 |     "%time model.fit(Xtrain, Ytrain)"
447 |    ]
448 |   },
449 |   {
450 |    "cell_type": "code",
451 |    "execution_count": 16,
452 |    "metadata": {},
453 |    "outputs": [
454 |     {
455 |      "name": "stdout",
456 |      "output_type": "stream",
457 |      "text": [
458 |       "CPU times: user 6.65 s, sys: 213 ms, total: 6.86 s\n",
459 |       "Wall time: 4.52 s\n"
460 |      ]
461 |     }
462 |    ],
463 |    "source": [
464 |     "%time predictions = model.predict(Xtest)"
465 |    ]
466 |   },
467 |   {
468 |    "cell_type": "code",
469 |    "execution_count": 17,
470 |    "metadata": {},
471 |    "outputs": [
472 |     {
473 |      "data": {
474 |       "text/plain": [
475 |        "0.95925"
476 |       ]
477 |      },
478 |      "execution_count": 17,
479 |      "metadata": {},
480 |      "output_type": "execute_result"
481 |     }
482 |    ],
483 |    "source": [
484 |     "\n",
485 |     "# model.score() -> regression - R2score\n",
486 |     "#----------------> classification - accuracy\n",
487 |     "\n",
488 |     "model.score(Xtest, Ytest)"
489 |    ]
490 |   },
491 |   {
492 |    "cell_type": "code",
493 |    "execution_count": 18,
494 |    "metadata": {},
495 |    "outputs": [
496 |     {
497 |      "name": "stdout",
498 |      "output_type": "stream",
499 |      "text": [
500 |       "  K :   3\n",
501 |       " Accuracy :  0.9615\n",
502 |       "  K :   5\n",
503 |       " Accuracy :  0.95925\n",
504 |       "  K :   7\n",
505 |       " Accuracy :  0.958\n",
506 |       "  K :   9\n",
507 |       " Accuracy :  0.95575\n"
508 |      ]
509 |     }
510 |    ],
511 |    "source": [
512 |     "# Selection of K\n",
513 |     "\n",
514 |     "for k in [3,5,7,9]:\n",
515 |     "    print(\"  K :  \", k)\n",
516 |     "    model = KNeighborsClassifier(n_neighbors=k)\n",
517 |     "    model.fit(Xtrain, Ytrain)\n",
518 |     "    print(\" Accuracy : \", model.score(Xtest, Ytest))\n"
519 |    ]
520 |   },
521 |   {
522 |    "cell_type": "code",
523 |    "execution_count": 20,
524 |    "metadata": {},
525 |    "outputs": [
526 |     {
527 |      "data": {
528 |       "text/html": [
529 |        "<style>#sk-container-id-3 {color: black;background-color: white;}#sk-container-id-3 pre{padding: 0;}#sk-container-id-3 div.sk-toggleable {background-color: white;}#sk-container-id-3 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-3 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-3 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-3 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-3 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-3 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-3 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-3 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-3 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-3 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-3 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-3 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-3 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-3 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-3 div.sk-item {position: relative;z-index: 1;}#sk-container-id-3 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-3 div.sk-item::before, #sk-container-id-3 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-3 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-3 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-3 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-3 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-3 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-3 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-3 div.sk-label-container {text-align: center;}#sk-container-id-3 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-3 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-3\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>Perceptron()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-3\" type=\"checkbox\" checked><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">Perceptron</label><div class=\"sk-toggleable__content\"><pre>Perceptron()</pre></div></div></div></div></div>"
530 |       ],
531 |       "text/plain": [
532 |        "Perceptron()"
533 |       ]
534 |      },
535 |      "execution_count": 20,
536 |      "metadata": {},
537 |      "output_type": "execute_result"
538 |     }
539 |    ],
540 |    "source": [
541 |     "from sklearn.linear_model import Perceptron\n",
542 |     "\n",
543 |     "model = Perceptron()\n",
544 |     "model.fit(Xtrain, Ytrain)"
545 |    ]
546 |   },
547 |   {
548 |    "cell_type": "code",
549 |    "execution_count": 21,
550 |    "metadata": {},
551 |    "outputs": [
552 |     {
553 |      "data": {
554 |       "text/plain": [
555 |        "0.89725"
556 |       ]
557 |      },
558 |      "execution_count": 21,
559 |      "metadata": {},
560 |      "output_type": "execute_result"
561 |     }
562 |    ],
563 |    "source": [
564 |     "model.score(Xtrain, Ytrain)"
565 |    ]
566 |   },
567 |   {
568 |    "cell_type": "code",
569 |    "execution_count": 22,
570 |    "metadata": {},
571 |    "outputs": [
572 |     {
573 |      "data": {
574 |       "text/plain": [
575 |        "0.872"
576 |       ]
577 |      },
578 |      "execution_count": 22,
579 |      "metadata": {},
580 |      "output_type": "execute_result"
581 |     }
582 |    ],
583 |    "source": [
584 |     "model.score(Xtest, Ytest)"
585 |    ]
586 |   },
587 |   {
588 |    "cell_type": "code",
589 |    "execution_count": null,
590 |    "metadata": {},
591 |    "outputs": [],
592 |    "source": []
593 |   }
594 |  ],
595 |  "metadata": {
596 |   "kernelspec": {
597 |    "display_name": "Python 3.10.6 64-bit",
598 |    "language": "python",
599 |    "name": "python3"
600 |   },
601 |   "language_info": {
602 |    "codemirror_mode": {
603 |     "name": "ipython",
604 |     "version": 3
605 |    },
606 |    "file_extension": ".py",
607 |    "mimetype": "text/x-python",
608 |    "name": "python",
609 |    "nbconvert_exporter": "python",
610 |    "pygments_lexer": "ipython3",
611 |    "version": "3.10.6"
612 |   },
613 |   "orig_nbformat": 4,
614 |   "vscode": {
615 |    "interpreter": {
616 |     "hash": "aee8b7b246df8f9039afb4144a1f6fd8d2ca17a180786b69acc140d282b71a49"
617 |    }
618 |   }
619 |  },
620 |  "nbformat": 4,
621 |  "nbformat_minor": 2
622 | }
623 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
1 | # hi all
2 | 


--------------------------------------------------------------------------------
/knn/.DS_Store:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/taureanjoe/Machine-Learning/2d095810454989fafec46017a4a6d08631c5b999/knn/.DS_Store


--------------------------------------------------------------------------------
/knn/knn.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 2,
  6 |    "metadata": {},
  7 |    "outputs": [],
  8 |    "source": [
  9 |     "import numpy as np\n",
 10 |     "import pandas as pd\n",
 11 |     "import matplotlib.pyplot as plt\n",
 12 |     "\n",
 13 |     "from sklearn.preprocessing import MinMaxScaler"
 14 |    ]
 15 |   },
 16 |   {
 17 |    "cell_type": "code",
 18 |    "execution_count": 4,
 19 |    "metadata": {},
 20 |    "outputs": [
 21 |     {
 22 |      "data": {
 23 |       "text/html": [
 24 |        "<div>\n",
 25 |        "<style scoped>\n",
 26 |        "    .dataframe tbody tr th:only-of-type {\n",
 27 |        "        vertical-align: middle;\n",
 28 |        "    }\n",
 29 |        "\n",
 30 |        "    .dataframe tbody tr th {\n",
 31 |        "        vertical-align: top;\n",
 32 |        "    }\n",
 33 |        "\n",
 34 |        "    .dataframe thead th {\n",
 35 |        "        text-align: right;\n",
 36 |        "    }\n",
 37 |        "</style>\n",
 38 |        "<table border=\"1\" class=\"dataframe\">\n",
 39 |        "  <thead>\n",
 40 |        "    <tr style=\"text-align: right;\">\n",
 41 |        "      <th></th>\n",
 42 |        "      <th>0</th>\n",
 43 |        "      <th>1</th>\n",
 44 |        "      <th>2</th>\n",
 45 |        "      <th>3</th>\n",
 46 |        "      <th>4</th>\n",
 47 |        "      <th>5</th>\n",
 48 |        "      <th>6</th>\n",
 49 |        "      <th>7</th>\n",
 50 |        "      <th>8</th>\n",
 51 |        "      <th>9</th>\n",
 52 |        "      <th>...</th>\n",
 53 |        "      <th>775</th>\n",
 54 |        "      <th>776</th>\n",
 55 |        "      <th>777</th>\n",
 56 |        "      <th>778</th>\n",
 57 |        "      <th>779</th>\n",
 58 |        "      <th>780</th>\n",
 59 |        "      <th>781</th>\n",
 60 |        "      <th>782</th>\n",
 61 |        "      <th>783</th>\n",
 62 |        "      <th>784</th>\n",
 63 |        "    </tr>\n",
 64 |        "  </thead>\n",
 65 |        "  <tbody>\n",
 66 |        "    <tr>\n",
 67 |        "      <th>19995</th>\n",
 68 |        "      <td>0</td>\n",
 69 |        "      <td>0</td>\n",
 70 |        "      <td>0</td>\n",
 71 |        "      <td>0</td>\n",
 72 |        "      <td>0</td>\n",
 73 |        "      <td>0</td>\n",
 74 |        "      <td>0</td>\n",
 75 |        "      <td>0</td>\n",
 76 |        "      <td>0</td>\n",
 77 |        "      <td>0</td>\n",
 78 |        "      <td>...</td>\n",
 79 |        "      <td>0</td>\n",
 80 |        "      <td>0</td>\n",
 81 |        "      <td>0</td>\n",
 82 |        "      <td>0</td>\n",
 83 |        "      <td>0</td>\n",
 84 |        "      <td>0</td>\n",
 85 |        "      <td>0</td>\n",
 86 |        "      <td>0</td>\n",
 87 |        "      <td>0</td>\n",
 88 |        "      <td>0</td>\n",
 89 |        "    </tr>\n",
 90 |        "    <tr>\n",
 91 |        "      <th>19996</th>\n",
 92 |        "      <td>1</td>\n",
 93 |        "      <td>0</td>\n",
 94 |        "      <td>0</td>\n",
 95 |        "      <td>0</td>\n",
 96 |        "      <td>0</td>\n",
 97 |        "      <td>0</td>\n",
 98 |        "      <td>0</td>\n",
 99 |        "      <td>0</td>\n",
100 |        "      <td>0</td>\n",
101 |        "      <td>0</td>\n",
102 |        "      <td>...</td>\n",
103 |        "      <td>0</td>\n",
104 |        "      <td>0</td>\n",
105 |        "      <td>0</td>\n",
106 |        "      <td>0</td>\n",
107 |        "      <td>0</td>\n",
108 |        "      <td>0</td>\n",
109 |        "      <td>0</td>\n",
110 |        "      <td>0</td>\n",
111 |        "      <td>0</td>\n",
112 |        "      <td>0</td>\n",
113 |        "    </tr>\n",
114 |        "    <tr>\n",
115 |        "      <th>19997</th>\n",
116 |        "      <td>2</td>\n",
117 |        "      <td>0</td>\n",
118 |        "      <td>0</td>\n",
119 |        "      <td>0</td>\n",
120 |        "      <td>0</td>\n",
121 |        "      <td>0</td>\n",
122 |        "      <td>0</td>\n",
123 |        "      <td>0</td>\n",
124 |        "      <td>0</td>\n",
125 |        "      <td>0</td>\n",
126 |        "      <td>...</td>\n",
127 |        "      <td>0</td>\n",
128 |        "      <td>0</td>\n",
129 |        "      <td>0</td>\n",
130 |        "      <td>0</td>\n",
131 |        "      <td>0</td>\n",
132 |        "      <td>0</td>\n",
133 |        "      <td>0</td>\n",
134 |        "      <td>0</td>\n",
135 |        "      <td>0</td>\n",
136 |        "      <td>0</td>\n",
137 |        "    </tr>\n",
138 |        "    <tr>\n",
139 |        "      <th>19998</th>\n",
140 |        "      <td>9</td>\n",
141 |        "      <td>0</td>\n",
142 |        "      <td>0</td>\n",
143 |        "      <td>0</td>\n",
144 |        "      <td>0</td>\n",
145 |        "      <td>0</td>\n",
146 |        "      <td>0</td>\n",
147 |        "      <td>0</td>\n",
148 |        "      <td>0</td>\n",
149 |        "      <td>0</td>\n",
150 |        "      <td>...</td>\n",
151 |        "      <td>0</td>\n",
152 |        "      <td>0</td>\n",
153 |        "      <td>0</td>\n",
154 |        "      <td>0</td>\n",
155 |        "      <td>0</td>\n",
156 |        "      <td>0</td>\n",
157 |        "      <td>0</td>\n",
158 |        "      <td>0</td>\n",
159 |        "      <td>0</td>\n",
160 |        "      <td>0</td>\n",
161 |        "    </tr>\n",
162 |        "    <tr>\n",
163 |        "      <th>19999</th>\n",
164 |        "      <td>5</td>\n",
165 |        "      <td>0</td>\n",
166 |        "      <td>0</td>\n",
167 |        "      <td>0</td>\n",
168 |        "      <td>0</td>\n",
169 |        "      <td>0</td>\n",
170 |        "      <td>0</td>\n",
171 |        "      <td>0</td>\n",
172 |        "      <td>0</td>\n",
173 |        "      <td>0</td>\n",
174 |        "      <td>...</td>\n",
175 |        "      <td>0</td>\n",
176 |        "      <td>0</td>\n",
177 |        "      <td>0</td>\n",
178 |        "      <td>0</td>\n",
179 |        "      <td>0</td>\n",
180 |        "      <td>0</td>\n",
181 |        "      <td>0</td>\n",
182 |        "      <td>0</td>\n",
183 |        "      <td>0</td>\n",
184 |        "      <td>0</td>\n",
185 |        "    </tr>\n",
186 |        "  </tbody>\n",
187 |        "</table>\n",
188 |        "<p>5 rows × 785 columns</p>\n",
189 |        "</div>"
190 |       ],
191 |       "text/plain": [
192 |        "       0    1    2    3    4    5    6    7    8    9    ...  775  776  777  \\\n",
193 |        "19995    0    0    0    0    0    0    0    0    0    0  ...    0    0    0   \n",
194 |        "19996    1    0    0    0    0    0    0    0    0    0  ...    0    0    0   \n",
195 |        "19997    2    0    0    0    0    0    0    0    0    0  ...    0    0    0   \n",
196 |        "19998    9    0    0    0    0    0    0    0    0    0  ...    0    0    0   \n",
197 |        "19999    5    0    0    0    0    0    0    0    0    0  ...    0    0    0   \n",
198 |        "\n",
199 |        "       778  779  780  781  782  783  784  \n",
200 |        "19995    0    0    0    0    0    0    0  \n",
201 |        "19996    0    0    0    0    0    0    0  \n",
202 |        "19997    0    0    0    0    0    0    0  \n",
203 |        "19998    0    0    0    0    0    0    0  \n",
204 |        "19999    0    0    0    0    0    0    0  \n",
205 |        "\n",
206 |        "[5 rows x 785 columns]"
207 |       ]
208 |      },
209 |      "execution_count": 4,
210 |      "metadata": {},
211 |      "output_type": "execute_result"
212 |     }
213 |    ],
214 |    "source": [
215 |     "data = pd.read_csv(\"mnist_train_small.csv\", header= None)\n",
216 |     "data.tail()"
217 |    ]
218 |   },
219 |   {
220 |    "cell_type": "code",
221 |    "execution_count": 5,
222 |    "metadata": {},
223 |    "outputs": [],
224 |    "source": [
225 |     "# Mnist - Digit recognition dataset\n",
226 |     "# Image is embedded inside the csv file\n",
227 |     "# 28*28 -> flattened -> fitting into a csv file\n",
228 |     "\n",
229 |     "# 785 -> 1 column (output), 784 (image)\n",
230 |     "# pixel range - (0-255)\n",
231 |     "# 0 - black\n",
232 |     "# 255 - white"
233 |    ]
234 |   },
235 |   {
236 |    "cell_type": "code",
237 |    "execution_count": 6,
238 |    "metadata": {},
239 |    "outputs": [
240 |     {
241 |      "data": {
242 |       "text/plain": [
243 |        "False"
244 |       ]
245 |      },
246 |      "execution_count": 6,
247 |      "metadata": {},
248 |      "output_type": "execute_result"
249 |     }
250 |    ],
251 |    "source": [
252 |     "data.isnull().sum().any()\n"
253 |    ]
254 |   },
255 |   {
256 |    "cell_type": "code",
257 |    "execution_count": 7,
258 |    "metadata": {},
259 |    "outputs": [
260 |     {
261 |      "name": "stdout",
262 |      "output_type": "stream",
263 |      "text": [
264 |       "<class 'pandas.core.frame.DataFrame'>\n",
265 |       "RangeIndex: 20000 entries, 0 to 19999\n",
266 |       "Columns: 785 entries, 0 to 784\n",
267 |       "dtypes: int64(785)\n",
268 |       "memory usage: 119.8 MB\n"
269 |      ]
270 |     }
271 |    ],
272 |    "source": [
273 |     "data.info()"
274 |    ]
275 |   },
276 |   {
277 |    "cell_type": "code",
278 |    "execution_count": 8,
279 |    "metadata": {},
280 |    "outputs": [
281 |     {
282 |      "data": {
283 |       "text/plain": [
284 |        "((20000, 784), (20000,))"
285 |       ]
286 |      },
287 |      "execution_count": 8,
288 |      "metadata": {},
289 |      "output_type": "execute_result"
290 |     }
291 |    ],
292 |    "source": [
293 |     "# dividing features and targets\n",
294 |     "\n",
295 |     "X = data.iloc[:, 1:].values\n",
296 |     "Y = data.iloc[:, 0].values\n",
297 |     "\n",
298 |     "X.shape, Y.shape"
299 |    ]
300 |   },
301 |   {
302 |    "cell_type": "code",
303 |    "execution_count": 9,
304 |    "metadata": {},
305 |    "outputs": [
306 |     {
307 |      "data": {
308 |       "text/plain": [
309 |        "255"
310 |       ]
311 |      },
312 |      "execution_count": 9,
313 |      "metadata": {},
314 |      "output_type": "execute_result"
315 |     }
316 |    ],
317 |    "source": [
318 |     "X.max()"
319 |    ]
320 |   },
321 |   {
322 |    "cell_type": "code",
323 |    "execution_count": 10,
324 |    "metadata": {},
325 |    "outputs": [],
326 |    "source": [
327 |     "scaler = MinMaxScaler()\n",
328 |     "X = scaler.fit_transform(X)"
329 |    ]
330 |   },
331 |   {
332 |    "cell_type": "code",
333 |    "execution_count": 11,
334 |    "metadata": {},
335 |    "outputs": [
336 |     {
337 |      "data": {
338 |       "text/plain": [
339 |        "(20000, 784)"
340 |       ]
341 |      },
342 |      "execution_count": 11,
343 |      "metadata": {},
344 |      "output_type": "execute_result"
345 |     }
346 |    ],
347 |    "source": [
348 |     "X.shape"
349 |    ]
350 |   },
351 |   {
352 |    "cell_type": "code",
353 |    "execution_count": 12,
354 |    "metadata": {},
355 |    "outputs": [],
356 |    "source": [
357 |     "def PlotImage(X, Y):\n",
358 |     "    idx = np.random.choice(X.shape[0])\n",
359 |     "    label = Y[idx]\n",
360 |     "    print(\" Target : \", label)\n",
361 |     "    x = X[idx, :]\n",
362 |     "    x = x.reshape(28,28)\n",
363 |     "    plt.imshow(x) "
364 |    ]
365 |   },
366 |   {
367 |    "cell_type": "code",
368 |    "execution_count": 13,
369 |    "metadata": {},
370 |    "outputs": [
371 |     {
372 |      "name": "stdout",
373 |      "output_type": "stream",
374 |      "text": [
375 |       " Target :  7\n"
376 |      ]
377 |     },
378 |     {
379 |      "data": {
380 |       "image/png": "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",
381 |       "text/plain": [
382 |        "<Figure size 640x480 with 1 Axes>"
383 |       ]
384 |      },
385 |      "metadata": {},
386 |      "output_type": "display_data"
387 |     }
388 |    ],
389 |    "source": [
390 |     "PlotImage(X,Y)"
391 |    ]
392 |   },
393 |   {
394 |    "cell_type": "code",
395 |    "execution_count": 14,
396 |    "metadata": {},
397 |    "outputs": [
398 |     {
399 |      "name": "stdout",
400 |      "output_type": "stream",
401 |      "text": [
402 |       " training Data shape :  (16000, 784) (16000,)\n",
403 |       " testing Data shape :  (4000, 784) (4000,)\n"
404 |      ]
405 |     }
406 |    ],
407 |    "source": [
408 |     "from sklearn.model_selection import train_test_split\n",
409 |     "Xtrain,Xtest, Ytrain, Ytest = train_test_split(X, Y, test_size=0.2, shuffle=True, random_state=4)\n",
410 |     "\n",
411 |     "print(\" training Data shape : \", Xtrain.shape, Ytrain.shape)\n",
412 |     "print(\" testing Data shape : \", Xtest.shape, Ytest.shape)"
413 |    ]
414 |   },
415 |   {
416 |    "cell_type": "code",
417 |    "execution_count": 15,
418 |    "metadata": {},
419 |    "outputs": [
420 |     {
421 |      "name": "stdout",
422 |      "output_type": "stream",
423 |      "text": [
424 |       "CPU times: user 29 ms, sys: 1.71 ms, total: 30.7 ms\n",
425 |       "Wall time: 69.9 ms\n"
426 |      ]
427 |     },
428 |     {
429 |      "data": {
430 |       "text/html": [
431 |        "<style>#sk-container-id-1 {color: black;background-color: white;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>KNeighborsClassifier()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">KNeighborsClassifier</label><div class=\"sk-toggleable__content\"><pre>KNeighborsClassifier()</pre></div></div></div></div></div>"
432 |       ],
433 |       "text/plain": [
434 |        "KNeighborsClassifier()"
435 |       ]
436 |      },
437 |      "execution_count": 15,
438 |      "metadata": {},
439 |      "output_type": "execute_result"
440 |     }
441 |    ],
442 |    "source": [
443 |     "from sklearn.neighbors import KNeighborsClassifier\n",
444 |     "\n",
445 |     "model = KNeighborsClassifier()\n",
446 |     "%time model.fit(Xtrain, Ytrain)"
447 |    ]
448 |   },
449 |   {
450 |    "cell_type": "code",
451 |    "execution_count": 16,
452 |    "metadata": {},
453 |    "outputs": [
454 |     {
455 |      "name": "stdout",
456 |      "output_type": "stream",
457 |      "text": [
458 |       "CPU times: user 6.42 s, sys: 170 ms, total: 6.59 s\n",
459 |       "Wall time: 4.69 s\n"
460 |      ]
461 |     }
462 |    ],
463 |    "source": [
464 |     "%time predictions = model.predict(Xtest)"
465 |    ]
466 |   },
467 |   {
468 |    "cell_type": "code",
469 |    "execution_count": 17,
470 |    "metadata": {},
471 |    "outputs": [
472 |     {
473 |      "data": {
474 |       "text/plain": [
475 |        "0.95925"
476 |       ]
477 |      },
478 |      "execution_count": 17,
479 |      "metadata": {},
480 |      "output_type": "execute_result"
481 |     }
482 |    ],
483 |    "source": [
484 |     "\n",
485 |     "# model.score() -> regression - R2score\n",
486 |     "#----------------> classification - accuracy\n",
487 |     "\n",
488 |     "model.score(Xtest, Ytest)"
489 |    ]
490 |   },
491 |   {
492 |    "cell_type": "code",
493 |    "execution_count": 18,
494 |    "metadata": {},
495 |    "outputs": [
496 |     {
497 |      "name": "stdout",
498 |      "output_type": "stream",
499 |      "text": [
500 |       "  K :   3\n",
501 |       " Accuracy :  0.9615\n",
502 |       "  K :   5\n",
503 |       " Accuracy :  0.95925\n",
504 |       "  K :   7\n",
505 |       " Accuracy :  0.958\n",
506 |       "  K :   9\n",
507 |       " Accuracy :  0.95575\n"
508 |      ]
509 |     }
510 |    ],
511 |    "source": [
512 |     "# Selection of K\n",
513 |     "\n",
514 |     "for k in [3,5,7,9]:\n",
515 |     "    print(\"  K :  \", k)\n",
516 |     "    model = KNeighborsClassifier(n_neighbors=k)\n",
517 |     "    model.fit(Xtrain, Ytrain)\n",
518 |     "    print(\" Accuracy : \", model.score(Xtest, Ytest))\n"
519 |    ]
520 |   },
521 |   {
522 |    "cell_type": "code",
523 |    "execution_count": null,
524 |    "metadata": {},
525 |    "outputs": [],
526 |    "source": []
527 |   }
528 |  ],
529 |  "metadata": {
530 |   "kernelspec": {
531 |    "display_name": "Python 3.10.6 64-bit",
532 |    "language": "python",
533 |    "name": "python3"
534 |   },
535 |   "language_info": {
536 |    "codemirror_mode": {
537 |     "name": "ipython",
538 |     "version": 3
539 |    },
540 |    "file_extension": ".py",
541 |    "mimetype": "text/x-python",
542 |    "name": "python",
543 |    "nbconvert_exporter": "python",
544 |    "pygments_lexer": "ipython3",
545 |    "version": "3.10.6"
546 |   },
547 |   "orig_nbformat": 4,
548 |   "vscode": {
549 |    "interpreter": {
550 |     "hash": "aee8b7b246df8f9039afb4144a1f6fd8d2ca17a180786b69acc140d282b71a49"
551 |    }
552 |   }
553 |  },
554 |  "nbformat": 4,
555 |  "nbformat_minor": 2
556 | }
557 | 


--------------------------------------------------------------------------------
/linear_regression/.DS_Store:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/taureanjoe/Machine-Learning/2d095810454989fafec46017a4a6d08631c5b999/linear_regression/.DS_Store


--------------------------------------------------------------------------------
/linear_regression/cal_housing_price_prediciton.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |   "cells": [
  3 |     {
  4 |       "cell_type": "code",
  5 |       "execution_count": 1,
  6 |       "metadata": {
  7 |         "id": "-riwMJJihZJs"
  8 |       },
  9 |       "outputs": [],
 10 |       "source": [
 11 |         "# Linear Regression - Ordinary Least Squares\n",
 12 |         "# 1. Line which has least Mean Squared Error ( only 1 which is best fit)\n",
 13 |         "\n",
 14 |         "# Y = mx + c\n",
 15 |         "# price = m*(sq ft) + intercept\n",
 16 |         "\n",
 17 |         "# MSE - mean squared error\n",
 18 |         "# Mean of Squared Differences between Actual and Estimation (Prediction)\n",
 19 |         "\n",
 20 |         "# difficult \n",
 21 |         "# features: sqft, n of bedrooms, ladnmarks, children play area,  swmming pool, flooring\n",
 22 |         "# output - price\n",
 23 |         "\n",
 24 |         "# y = mx + c\n",
 25 |         "# y = m1x1 + m2x2 + m4x4 + m6x6 + c\n",
 26 |         "\n",
 27 |         "\n",
 28 |         "\n",
 29 |         "\n",
 30 |         "# -> write detailed formula\n",
 31 |         "\n",
 32 |         "\n",
 33 |         "\n",
 34 |         "\n",
 35 |         "# prediction = W.X + b\n",
 36 |         "\n",
 37 |         "# foreward propagation\n",
 38 |         "# take data into model and get prediction\n",
 39 |         "\n",
 40 |         "\n",
 41 |         "# back propagation(learning)\n",
 42 |         "# calculate loss -> MSE\n",
 43 |         "# adjust the weights such that MSE goes down\n",
 44 |         "\n",
 45 |         "# optmization - gradient descent \n",
 46 |         "# code\n",
 47 |         "\n",
 48 |         "# what are the weights set to?\n",
 49 |         "# 1. weights are initialized randomly \n",
 50 |         "# as a part of training/learning, these weights need to be adjusted\n",
 51 |         "\n",
 52 |         "# how did we get the best line?\n",
 53 |         "# 1. adjusted weights.X + adjusted bias => best line\n",
 54 |         "\n",
 55 |         "# jeoff hinton\n",
 56 |         "# yann lecun\n",
 57 |         "\n",
 58 |         "\n"
 59 |       ]
 60 |     },
 61 |     {
 62 |       "cell_type": "code",
 63 |       "execution_count": 2,
 64 |       "metadata": {
 65 |         "id": "aBWG14fxaD5g"
 66 |       },
 67 |       "outputs": [],
 68 |       "source": [
 69 |         "import pandas as pd\n",
 70 |         "import numpy as np"
 71 |       ]
 72 |     },
 73 |     {
 74 |       "cell_type": "code",
 75 |       "execution_count": 3,
 76 |       "metadata": {
 77 |         "id": "xBTEYsdzaL7o"
 78 |       },
 79 |       "outputs": [],
 80 |       "source": [
 81 |         "data = pd.read_csv(\"california_housing_train.csv\")"
 82 |       ]
 83 |     },
 84 |     {
 85 |       "cell_type": "code",
 86 |       "execution_count": null,
 87 |       "metadata": {},
 88 |       "outputs": [],
 89 |       "source": []
 90 |     },
 91 |     {
 92 |       "cell_type": "code",
 93 |       "execution_count": 4,
 94 |       "metadata": {
 95 |         "colab": {
 96 |           "base_uri": "https://localhost:8080/",
 97 |           "height": 268
 98 |         },
 99 |         "id": "EPCiOuBkanla",
100 |         "outputId": "ac87dd62-79eb-4978-8225-9ddeb7dfcd4c"
101 |       },
102 |       "outputs": [
103 |         {
104 |           "data": {
105 |             "text/html": [
106 |               "<div>\n",
107 |               "<style scoped>\n",
108 |               "    .dataframe tbody tr th:only-of-type {\n",
109 |               "        vertical-align: middle;\n",
110 |               "    }\n",
111 |               "\n",
112 |               "    .dataframe tbody tr th {\n",
113 |               "        vertical-align: top;\n",
114 |               "    }\n",
115 |               "\n",
116 |               "    .dataframe thead th {\n",
117 |               "        text-align: right;\n",
118 |               "    }\n",
119 |               "</style>\n",
120 |               "<table border=\"1\" class=\"dataframe\">\n",
121 |               "  <thead>\n",
122 |               "    <tr style=\"text-align: right;\">\n",
123 |               "      <th></th>\n",
124 |               "      <th>longitude</th>\n",
125 |               "      <th>latitude</th>\n",
126 |               "      <th>housing_median_age</th>\n",
127 |               "      <th>total_rooms</th>\n",
128 |               "      <th>total_bedrooms</th>\n",
129 |               "      <th>population</th>\n",
130 |               "      <th>households</th>\n",
131 |               "      <th>median_income</th>\n",
132 |               "      <th>median_house_value</th>\n",
133 |               "    </tr>\n",
134 |               "  </thead>\n",
135 |               "  <tbody>\n",
136 |               "    <tr>\n",
137 |               "      <th>0</th>\n",
138 |               "      <td>-114.31</td>\n",
139 |               "      <td>34.19</td>\n",
140 |               "      <td>15.0</td>\n",
141 |               "      <td>5612.0</td>\n",
142 |               "      <td>1283.0</td>\n",
143 |               "      <td>1015.0</td>\n",
144 |               "      <td>472.0</td>\n",
145 |               "      <td>1.4936</td>\n",
146 |               "      <td>66900.0</td>\n",
147 |               "    </tr>\n",
148 |               "    <tr>\n",
149 |               "      <th>1</th>\n",
150 |               "      <td>-114.47</td>\n",
151 |               "      <td>34.40</td>\n",
152 |               "      <td>19.0</td>\n",
153 |               "      <td>7650.0</td>\n",
154 |               "      <td>1901.0</td>\n",
155 |               "      <td>1129.0</td>\n",
156 |               "      <td>463.0</td>\n",
157 |               "      <td>1.8200</td>\n",
158 |               "      <td>80100.0</td>\n",
159 |               "    </tr>\n",
160 |               "    <tr>\n",
161 |               "      <th>2</th>\n",
162 |               "      <td>-114.56</td>\n",
163 |               "      <td>33.69</td>\n",
164 |               "      <td>17.0</td>\n",
165 |               "      <td>720.0</td>\n",
166 |               "      <td>174.0</td>\n",
167 |               "      <td>333.0</td>\n",
168 |               "      <td>117.0</td>\n",
169 |               "      <td>1.6509</td>\n",
170 |               "      <td>85700.0</td>\n",
171 |               "    </tr>\n",
172 |               "    <tr>\n",
173 |               "      <th>3</th>\n",
174 |               "      <td>-114.57</td>\n",
175 |               "      <td>33.64</td>\n",
176 |               "      <td>14.0</td>\n",
177 |               "      <td>1501.0</td>\n",
178 |               "      <td>337.0</td>\n",
179 |               "      <td>515.0</td>\n",
180 |               "      <td>226.0</td>\n",
181 |               "      <td>3.1917</td>\n",
182 |               "      <td>73400.0</td>\n",
183 |               "    </tr>\n",
184 |               "    <tr>\n",
185 |               "      <th>4</th>\n",
186 |               "      <td>-114.57</td>\n",
187 |               "      <td>33.57</td>\n",
188 |               "      <td>20.0</td>\n",
189 |               "      <td>1454.0</td>\n",
190 |               "      <td>326.0</td>\n",
191 |               "      <td>624.0</td>\n",
192 |               "      <td>262.0</td>\n",
193 |               "      <td>1.9250</td>\n",
194 |               "      <td>65500.0</td>\n",
195 |               "    </tr>\n",
196 |               "  </tbody>\n",
197 |               "</table>\n",
198 |               "</div>"
199 |             ],
200 |             "text/plain": [
201 |               "   longitude  latitude  housing_median_age  total_rooms  total_bedrooms  \\\n",
202 |               "0    -114.31     34.19                15.0       5612.0          1283.0   \n",
203 |               "1    -114.47     34.40                19.0       7650.0          1901.0   \n",
204 |               "2    -114.56     33.69                17.0        720.0           174.0   \n",
205 |               "3    -114.57     33.64                14.0       1501.0           337.0   \n",
206 |               "4    -114.57     33.57                20.0       1454.0           326.0   \n",
207 |               "\n",
208 |               "   population  households  median_income  median_house_value  \n",
209 |               "0      1015.0       472.0         1.4936             66900.0  \n",
210 |               "1      1129.0       463.0         1.8200             80100.0  \n",
211 |               "2       333.0       117.0         1.6509             85700.0  \n",
212 |               "3       515.0       226.0         3.1917             73400.0  \n",
213 |               "4       624.0       262.0         1.9250             65500.0  "
214 |             ]
215 |           },
216 |           "execution_count": 4,
217 |           "metadata": {},
218 |           "output_type": "execute_result"
219 |         }
220 |       ],
221 |       "source": [
222 |         "data.head()"
223 |       ]
224 |     },
225 |     {
226 |       "cell_type": "code",
227 |       "execution_count": 5,
228 |       "metadata": {
229 |         "colab": {
230 |           "base_uri": "https://localhost:8080/"
231 |         },
232 |         "id": "RqrjPopia6uf",
233 |         "outputId": "b8609e6b-0222-451c-e2b1-2c09a5eac153"
234 |       },
235 |       "outputs": [
236 |         {
237 |           "data": {
238 |             "text/plain": [
239 |               "longitude             0\n",
240 |               "latitude              0\n",
241 |               "housing_median_age    0\n",
242 |               "total_rooms           0\n",
243 |               "total_bedrooms        0\n",
244 |               "population            0\n",
245 |               "households            0\n",
246 |               "median_income         0\n",
247 |               "median_house_value    0\n",
248 |               "dtype: int64"
249 |             ]
250 |           },
251 |           "execution_count": 5,
252 |           "metadata": {},
253 |           "output_type": "execute_result"
254 |         }
255 |       ],
256 |       "source": [
257 |         "data.isnull().sum()"
258 |       ]
259 |     },
260 |     {
261 |       "cell_type": "code",
262 |       "execution_count": 6,
263 |       "metadata": {
264 |         "colab": {
265 |           "base_uri": "https://localhost:8080/"
266 |         },
267 |         "id": "-kKSmydwa-CP",
268 |         "outputId": "8c8b675f-f9c6-440f-b9f3-3020020ee68f"
269 |       },
270 |       "outputs": [
271 |         {
272 |           "name": "stdout",
273 |           "output_type": "stream",
274 |           "text": [
275 |             "<class 'pandas.core.frame.DataFrame'>\n",
276 |             "RangeIndex: 17000 entries, 0 to 16999\n",
277 |             "Data columns (total 9 columns):\n",
278 |             " #   Column              Non-Null Count  Dtype  \n",
279 |             "---  ------              --------------  -----  \n",
280 |             " 0   longitude           17000 non-null  float64\n",
281 |             " 1   latitude            17000 non-null  float64\n",
282 |             " 2   housing_median_age  17000 non-null  float64\n",
283 |             " 3   total_rooms         17000 non-null  float64\n",
284 |             " 4   total_bedrooms      17000 non-null  float64\n",
285 |             " 5   population          17000 non-null  float64\n",
286 |             " 6   households          17000 non-null  float64\n",
287 |             " 7   median_income       17000 non-null  float64\n",
288 |             " 8   median_house_value  17000 non-null  float64\n",
289 |             "dtypes: float64(9)\n",
290 |             "memory usage: 1.2 MB\n"
291 |           ]
292 |         }
293 |       ],
294 |       "source": [
295 |         "data.info()"
296 |       ]
297 |     },
298 |     {
299 |       "cell_type": "code",
300 |       "execution_count": 7,
301 |       "metadata": {
302 |         "id": "ftCZURcmao1L"
303 |       },
304 |       "outputs": [],
305 |       "source": [
306 |         "# scale the data\n",
307 |         "from sklearn.preprocessing import MinMaxScaler\n",
308 |         "scaler = MinMaxScaler()\n",
309 |         "data.iloc[:,:] = scaler.fit_transform(data)"
310 |       ]
311 |     },
312 |     {
313 |       "cell_type": "code",
314 |       "execution_count": 8,
315 |       "metadata": {
316 |         "colab": {
317 |           "base_uri": "https://localhost:8080/",
318 |           "height": 268
319 |         },
320 |         "id": "k4vBLS8rez7D",
321 |         "outputId": "9baa0559-c7cd-4591-81f7-ae70289b3bb7"
322 |       },
323 |       "outputs": [
324 |         {
325 |           "data": {
326 |             "text/html": [
327 |               "<div>\n",
328 |               "<style scoped>\n",
329 |               "    .dataframe tbody tr th:only-of-type {\n",
330 |               "        vertical-align: middle;\n",
331 |               "    }\n",
332 |               "\n",
333 |               "    .dataframe tbody tr th {\n",
334 |               "        vertical-align: top;\n",
335 |               "    }\n",
336 |               "\n",
337 |               "    .dataframe thead th {\n",
338 |               "        text-align: right;\n",
339 |               "    }\n",
340 |               "</style>\n",
341 |               "<table border=\"1\" class=\"dataframe\">\n",
342 |               "  <thead>\n",
343 |               "    <tr style=\"text-align: right;\">\n",
344 |               "      <th></th>\n",
345 |               "      <th>longitude</th>\n",
346 |               "      <th>latitude</th>\n",
347 |               "      <th>housing_median_age</th>\n",
348 |               "      <th>total_rooms</th>\n",
349 |               "      <th>total_bedrooms</th>\n",
350 |               "      <th>population</th>\n",
351 |               "      <th>households</th>\n",
352 |               "      <th>median_income</th>\n",
353 |               "      <th>median_house_value</th>\n",
354 |               "    </tr>\n",
355 |               "  </thead>\n",
356 |               "  <tbody>\n",
357 |               "    <tr>\n",
358 |               "      <th>0</th>\n",
359 |               "      <td>1.000000</td>\n",
360 |               "      <td>0.175345</td>\n",
361 |               "      <td>0.274510</td>\n",
362 |               "      <td>0.147885</td>\n",
363 |               "      <td>0.198945</td>\n",
364 |               "      <td>0.028364</td>\n",
365 |               "      <td>0.077454</td>\n",
366 |               "      <td>0.068530</td>\n",
367 |               "      <td>0.107012</td>\n",
368 |               "    </tr>\n",
369 |               "    <tr>\n",
370 |               "      <th>1</th>\n",
371 |               "      <td>0.984064</td>\n",
372 |               "      <td>0.197662</td>\n",
373 |               "      <td>0.352941</td>\n",
374 |               "      <td>0.201608</td>\n",
375 |               "      <td>0.294848</td>\n",
376 |               "      <td>0.031559</td>\n",
377 |               "      <td>0.075974</td>\n",
378 |               "      <td>0.091040</td>\n",
379 |               "      <td>0.134228</td>\n",
380 |               "    </tr>\n",
381 |               "    <tr>\n",
382 |               "      <th>2</th>\n",
383 |               "      <td>0.975100</td>\n",
384 |               "      <td>0.122210</td>\n",
385 |               "      <td>0.313725</td>\n",
386 |               "      <td>0.018927</td>\n",
387 |               "      <td>0.026847</td>\n",
388 |               "      <td>0.009249</td>\n",
389 |               "      <td>0.019076</td>\n",
390 |               "      <td>0.079378</td>\n",
391 |               "      <td>0.145775</td>\n",
392 |               "    </tr>\n",
393 |               "    <tr>\n",
394 |               "      <th>3</th>\n",
395 |               "      <td>0.974104</td>\n",
396 |               "      <td>0.116897</td>\n",
397 |               "      <td>0.254902</td>\n",
398 |               "      <td>0.039515</td>\n",
399 |               "      <td>0.052142</td>\n",
400 |               "      <td>0.014350</td>\n",
401 |               "      <td>0.037000</td>\n",
402 |               "      <td>0.185639</td>\n",
403 |               "      <td>0.120414</td>\n",
404 |               "    </tr>\n",
405 |               "    <tr>\n",
406 |               "      <th>4</th>\n",
407 |               "      <td>0.974104</td>\n",
408 |               "      <td>0.109458</td>\n",
409 |               "      <td>0.372549</td>\n",
410 |               "      <td>0.038276</td>\n",
411 |               "      <td>0.050435</td>\n",
412 |               "      <td>0.017405</td>\n",
413 |               "      <td>0.042921</td>\n",
414 |               "      <td>0.098281</td>\n",
415 |               "      <td>0.104125</td>\n",
416 |               "    </tr>\n",
417 |               "  </tbody>\n",
418 |               "</table>\n",
419 |               "</div>"
420 |             ],
421 |             "text/plain": [
422 |               "   longitude  latitude  housing_median_age  total_rooms  total_bedrooms  \\\n",
423 |               "0   1.000000  0.175345            0.274510     0.147885        0.198945   \n",
424 |               "1   0.984064  0.197662            0.352941     0.201608        0.294848   \n",
425 |               "2   0.975100  0.122210            0.313725     0.018927        0.026847   \n",
426 |               "3   0.974104  0.116897            0.254902     0.039515        0.052142   \n",
427 |               "4   0.974104  0.109458            0.372549     0.038276        0.050435   \n",
428 |               "\n",
429 |               "   population  households  median_income  median_house_value  \n",
430 |               "0    0.028364    0.077454       0.068530            0.107012  \n",
431 |               "1    0.031559    0.075974       0.091040            0.134228  \n",
432 |               "2    0.009249    0.019076       0.079378            0.145775  \n",
433 |               "3    0.014350    0.037000       0.185639            0.120414  \n",
434 |               "4    0.017405    0.042921       0.098281            0.104125  "
435 |             ]
436 |           },
437 |           "execution_count": 8,
438 |           "metadata": {},
439 |           "output_type": "execute_result"
440 |         }
441 |       ],
442 |       "source": [
443 |         "data.head()"
444 |       ]
445 |     },
446 |     {
447 |       "cell_type": "code",
448 |       "execution_count": 25,
449 |       "metadata": {
450 |         "id": "895IpB4Ee1XF"
451 |       },
452 |       "outputs": [],
453 |       "source": [
454 |         "X = data.iloc[:, :-1].values # features\n",
455 |         "Y = data.iloc[:, -1].values # target/output"
456 |       ]
457 |     },
458 |     {
459 |       "cell_type": "code",
460 |       "execution_count": 10,
461 |       "metadata": {
462 |         "colab": {
463 |           "base_uri": "https://localhost:8080/"
464 |         },
465 |         "id": "vNQ_VkxEfTqV",
466 |         "outputId": "e80fe680-9043-4750-f215-910d0ab1e7de"
467 |       },
468 |       "outputs": [
469 |         {
470 |           "data": {
471 |             "text/plain": [
472 |               "((17000, 8), (17000,))"
473 |             ]
474 |           },
475 |           "execution_count": 10,
476 |           "metadata": {},
477 |           "output_type": "execute_result"
478 |         }
479 |       ],
480 |       "source": [
481 |         "X.shape, Y.shape"
482 |       ]
483 |     },
484 |     {
485 |       "cell_type": "code",
486 |       "execution_count": 11,
487 |       "metadata": {
488 |         "id": "cbuUe8V7fUVz"
489 |       },
490 |       "outputs": [],
491 |       "source": [
492 |         "from sklearn.model_selection import train_test_split\n",
493 |         "Xtrain, Xtest, Ytrain, Ytest = train_test_split(X,Y, test_size = 0.2, shuffle = True, random_state = 4)"
494 |       ]
495 |     },
496 |     {
497 |       "cell_type": "code",
498 |       "execution_count": 12,
499 |       "metadata": {
500 |         "colab": {
501 |           "base_uri": "https://localhost:8080/"
502 |         },
503 |         "id": "fp4XNOPrfp1N",
504 |         "outputId": "7a5bb691-d470-4941-b668-e1a7ef356eea"
505 |       },
506 |       "outputs": [
507 |         {
508 |           "data": {
509 |             "text/html": [
510 |               "<style>#sk-container-id-1 {color: black;background-color: white;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>LinearRegression()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">LinearRegression</label><div class=\"sk-toggleable__content\"><pre>LinearRegression()</pre></div></div></div></div></div>"
511 |             ],
512 |             "text/plain": [
513 |               "LinearRegression()"
514 |             ]
515 |           },
516 |           "execution_count": 12,
517 |           "metadata": {},
518 |           "output_type": "execute_result"
519 |         }
520 |       ],
521 |       "source": [
522 |         "from sklearn.linear_model import LinearRegression\n",
523 |         "\n",
524 |         "model = LinearRegression()\n",
525 |         "model.fit(Xtrain, Ytrain)\n"
526 |       ]
527 |     },
528 |     {
529 |       "cell_type": "code",
530 |       "execution_count": 13,
531 |       "metadata": {
532 |         "id": "Fj_EkhbfgJC6"
533 |       },
534 |       "outputs": [],
535 |       "source": [
536 |         "#MSE\n",
537 |         "# mean of squared differences between actual and predictions\n",
538 |         "\n",
539 |         "def MSE(actual, prediction):\n",
540 |         "  error = actual - prediction\n",
541 |         "  squared = np.square(error)\n",
542 |         "  return np.mean(squared)\n"
543 |       ]
544 |     },
545 |     {
546 |       "cell_type": "code",
547 |       "execution_count": 14,
548 |       "metadata": {
549 |         "colab": {
550 |           "base_uri": "https://localhost:8080/"
551 |         },
552 |         "id": "1Dfdtn3Rgnt7",
553 |         "outputId": "74e024f2-1b36-473d-8714-d568f24e9714"
554 |       },
555 |       "outputs": [
556 |         {
557 |           "data": {
558 |             "text/plain": [
559 |               "0.02000868218950632"
560 |             ]
561 |           },
562 |           "execution_count": 14,
563 |           "metadata": {},
564 |           "output_type": "execute_result"
565 |         }
566 |       ],
567 |       "source": [
568 |         "prediction_testing = model.predict(Xtest)\n",
569 |         "\n",
570 |         "MSE(Ytest, prediction_testing)"
571 |       ]
572 |     },
573 |     {
574 |       "cell_type": "code",
575 |       "execution_count": 15,
576 |       "metadata": {
577 |         "colab": {
578 |           "base_uri": "https://localhost:8080/"
579 |         },
580 |         "id": "xDSQa_xdg3zl",
581 |         "outputId": "08890285-e196-427b-a026-cb9c8fee3c8d"
582 |       },
583 |       "outputs": [
584 |         {
585 |           "data": {
586 |             "text/plain": [
587 |               "array([-0.91447718, -0.84873666,  0.11771612, -0.66327286,  1.57499784,\n",
588 |               "       -2.68089479,  0.50641965,  1.20543441])"
589 |             ]
590 |           },
591 |           "execution_count": 15,
592 |           "metadata": {},
593 |           "output_type": "execute_result"
594 |         }
595 |       ],
596 |       "source": [
597 |         "model.coef_"
598 |       ]
599 |     },
600 |     {
601 |       "cell_type": "code",
602 |       "execution_count": 16,
603 |       "metadata": {
604 |         "id": "2A9HyOaolna2"
605 |       },
606 |       "outputs": [],
607 |       "source": [
608 |         "# rule\n",
609 |         "# a.b => columns of a should be equal to rows of b\n",
610 |         "\n",
611 |         "def prediction(x, weights, b):\n",
612 |         "  return x.dot(weights) + b"
613 |       ]
614 |     },
615 |     {
616 |       "cell_type": "code",
617 |       "execution_count": 17,
618 |       "metadata": {
619 |         "colab": {
620 |           "base_uri": "https://localhost:8080/"
621 |         },
622 |         "id": "aIEoQhYKoKdp",
623 |         "outputId": "ce369dbb-e8f3-4a43-bbc1-5bc76afe827a"
624 |       },
625 |       "outputs": [
626 |         {
627 |           "data": {
628 |             "text/plain": [
629 |               "(3400, 8)"
630 |             ]
631 |           },
632 |           "execution_count": 17,
633 |           "metadata": {},
634 |           "output_type": "execute_result"
635 |         }
636 |       ],
637 |       "source": [
638 |         "Xtest.shape"
639 |       ]
640 |     },
641 |     {
642 |       "cell_type": "code",
643 |       "execution_count": 18,
644 |       "metadata": {
645 |         "colab": {
646 |           "base_uri": "https://localhost:8080/"
647 |         },
648 |         "id": "8NNVeU0ioL8a",
649 |         "outputId": "cfa17670-e62c-46df-9811-e6b223a3ca0e"
650 |       },
651 |       "outputs": [
652 |         {
653 |           "data": {
654 |             "text/plain": [
655 |               "array([0.28914931, 0.44840173, 0.55358487, ..., 0.20538748, 0.52725745,\n",
656 |               "       0.75157992])"
657 |             ]
658 |           },
659 |           "execution_count": 18,
660 |           "metadata": {},
661 |           "output_type": "execute_result"
662 |         }
663 |       ],
664 |       "source": [
665 |         "prediction(Xtest, model.coef_, model.intercept_)"
666 |       ]
667 |     },
668 |     {
669 |       "cell_type": "code",
670 |       "execution_count": 19,
671 |       "metadata": {
672 |         "colab": {
673 |           "base_uri": "https://localhost:8080/"
674 |         },
675 |         "id": "zucBSZthoQuS",
676 |         "outputId": "9e12769a-91e2-4e7b-be46-e9e2750900b9"
677 |       },
678 |       "outputs": [
679 |         {
680 |           "data": {
681 |             "text/plain": [
682 |               "array([0.28914931, 0.44840173, 0.55358487, ..., 0.20538748, 0.52725745,\n",
683 |               "       0.75157992])"
684 |             ]
685 |           },
686 |           "execution_count": 19,
687 |           "metadata": {},
688 |           "output_type": "execute_result"
689 |         }
690 |       ],
691 |       "source": [
692 |         "model.predict(Xtest)"
693 |       ]
694 |     },
695 |     {
696 |       "cell_type": "code",
697 |       "execution_count": 20,
698 |       "metadata": {
699 |         "id": "USZmnhqboS_g"
700 |       },
701 |       "outputs": [],
702 |       "source": [
703 |         "# proves that our function give exact same result as that of sklearn algo"
704 |       ]
705 |     },
706 |     {
707 |       "cell_type": "code",
708 |       "execution_count": 21,
709 |       "metadata": {
710 |         "id": "wp3eY83voZoL"
711 |       },
712 |       "outputs": [],
713 |       "source": [
714 |         "# Lasso and Ridge Regression\n",
715 |         "\n"
716 |       ]
717 |     },
718 |     {
719 |       "cell_type": "code",
720 |       "execution_count": 22,
721 |       "metadata": {},
722 |       "outputs": [
723 |         {
724 |           "data": {
725 |             "text/html": [
726 |               "<style>#sk-container-id-2 {color: black;background-color: white;}#sk-container-id-2 pre{padding: 0;}#sk-container-id-2 div.sk-toggleable {background-color: white;}#sk-container-id-2 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-2 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-2 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-2 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-2 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-2 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-2 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-2 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-2 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-2 div.sk-item {position: relative;z-index: 1;}#sk-container-id-2 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-2 div.sk-item::before, #sk-container-id-2 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-2 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-2 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-2 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-2 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-2 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-2 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-2 div.sk-label-container {text-align: center;}#sk-container-id-2 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-2 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>Lasso()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" checked><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">Lasso</label><div class=\"sk-toggleable__content\"><pre>Lasso()</pre></div></div></div></div></div>"
727 |             ],
728 |             "text/plain": [
729 |               "Lasso()"
730 |             ]
731 |           },
732 |           "execution_count": 22,
733 |           "metadata": {},
734 |           "output_type": "execute_result"
735 |         }
736 |       ],
737 |       "source": [
738 |         "from sklearn.linear_model import Lasso, Ridge\n",
739 |         "\n",
740 |         "model = Lasso()\n",
741 |         "model.fit(Xtrain,Ytrain)\n",
742 |         "\n",
743 |         "Lasso()"
744 |       ]
745 |     }
746 |   ],
747 |   "metadata": {
748 |     "colab": {
749 |       "provenance": []
750 |     },
751 |     "kernelspec": {
752 |       "display_name": "Python 3.10.6 64-bit",
753 |       "language": "python",
754 |       "name": "python3"
755 |     },
756 |     "language_info": {
757 |       "codemirror_mode": {
758 |         "name": "ipython",
759 |         "version": 3
760 |       },
761 |       "file_extension": ".py",
762 |       "mimetype": "text/x-python",
763 |       "name": "python",
764 |       "nbconvert_exporter": "python",
765 |       "pygments_lexer": "ipython3",
766 |       "version": "3.10.6"
767 |     },
768 |     "vscode": {
769 |       "interpreter": {
770 |         "hash": "aee8b7b246df8f9039afb4144a1f6fd8d2ca17a180786b69acc140d282b71a49"
771 |       }
772 |     }
773 |   },
774 |   "nbformat": 4,
775 |   "nbformat_minor": 0
776 | }
777 | 


--------------------------------------------------------------------------------
/linear_regression/price_prediction.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 1,
  6 |    "metadata": {},
  7 |    "outputs": [],
  8 |    "source": [
  9 |     "import pandas as pd\n",
 10 |     "import numpy as np"
 11 |    ]
 12 |   },
 13 |   {
 14 |    "cell_type": "code",
 15 |    "execution_count": 2,
 16 |    "metadata": {},
 17 |    "outputs": [
 18 |     {
 19 |      "data": {
 20 |       "text/html": [
 21 |        "<div>\n",
 22 |        "<style scoped>\n",
 23 |        "    .dataframe tbody tr th:only-of-type {\n",
 24 |        "        vertical-align: middle;\n",
 25 |        "    }\n",
 26 |        "\n",
 27 |        "    .dataframe tbody tr th {\n",
 28 |        "        vertical-align: top;\n",
 29 |        "    }\n",
 30 |        "\n",
 31 |        "    .dataframe thead th {\n",
 32 |        "        text-align: right;\n",
 33 |        "    }\n",
 34 |        "</style>\n",
 35 |        "<table border=\"1\" class=\"dataframe\">\n",
 36 |        "  <thead>\n",
 37 |        "    <tr style=\"text-align: right;\">\n",
 38 |        "      <th></th>\n",
 39 |        "      <th>longitude</th>\n",
 40 |        "      <th>latitude</th>\n",
 41 |        "      <th>housing_median_age</th>\n",
 42 |        "      <th>total_rooms</th>\n",
 43 |        "      <th>total_bedrooms</th>\n",
 44 |        "      <th>population</th>\n",
 45 |        "      <th>households</th>\n",
 46 |        "      <th>median_income</th>\n",
 47 |        "      <th>median_house_value</th>\n",
 48 |        "    </tr>\n",
 49 |        "  </thead>\n",
 50 |        "  <tbody>\n",
 51 |        "    <tr>\n",
 52 |        "      <th>0</th>\n",
 53 |        "      <td>-114.31</td>\n",
 54 |        "      <td>34.19</td>\n",
 55 |        "      <td>15.0</td>\n",
 56 |        "      <td>5612.0</td>\n",
 57 |        "      <td>1283.0</td>\n",
 58 |        "      <td>1015.0</td>\n",
 59 |        "      <td>472.0</td>\n",
 60 |        "      <td>1.4936</td>\n",
 61 |        "      <td>66900.0</td>\n",
 62 |        "    </tr>\n",
 63 |        "    <tr>\n",
 64 |        "      <th>1</th>\n",
 65 |        "      <td>-114.47</td>\n",
 66 |        "      <td>34.40</td>\n",
 67 |        "      <td>19.0</td>\n",
 68 |        "      <td>7650.0</td>\n",
 69 |        "      <td>1901.0</td>\n",
 70 |        "      <td>1129.0</td>\n",
 71 |        "      <td>463.0</td>\n",
 72 |        "      <td>1.8200</td>\n",
 73 |        "      <td>80100.0</td>\n",
 74 |        "    </tr>\n",
 75 |        "    <tr>\n",
 76 |        "      <th>2</th>\n",
 77 |        "      <td>-114.56</td>\n",
 78 |        "      <td>33.69</td>\n",
 79 |        "      <td>17.0</td>\n",
 80 |        "      <td>720.0</td>\n",
 81 |        "      <td>174.0</td>\n",
 82 |        "      <td>333.0</td>\n",
 83 |        "      <td>117.0</td>\n",
 84 |        "      <td>1.6509</td>\n",
 85 |        "      <td>85700.0</td>\n",
 86 |        "    </tr>\n",
 87 |        "    <tr>\n",
 88 |        "      <th>3</th>\n",
 89 |        "      <td>-114.57</td>\n",
 90 |        "      <td>33.64</td>\n",
 91 |        "      <td>14.0</td>\n",
 92 |        "      <td>1501.0</td>\n",
 93 |        "      <td>337.0</td>\n",
 94 |        "      <td>515.0</td>\n",
 95 |        "      <td>226.0</td>\n",
 96 |        "      <td>3.1917</td>\n",
 97 |        "      <td>73400.0</td>\n",
 98 |        "    </tr>\n",
 99 |        "    <tr>\n",
100 |        "      <th>4</th>\n",
101 |        "      <td>-114.57</td>\n",
102 |        "      <td>33.57</td>\n",
103 |        "      <td>20.0</td>\n",
104 |        "      <td>1454.0</td>\n",
105 |        "      <td>326.0</td>\n",
106 |        "      <td>624.0</td>\n",
107 |        "      <td>262.0</td>\n",
108 |        "      <td>1.9250</td>\n",
109 |        "      <td>65500.0</td>\n",
110 |        "    </tr>\n",
111 |        "  </tbody>\n",
112 |        "</table>\n",
113 |        "</div>"
114 |       ],
115 |       "text/plain": [
116 |        "   longitude  latitude  housing_median_age  total_rooms  total_bedrooms  \\\n",
117 |        "0    -114.31     34.19                15.0       5612.0          1283.0   \n",
118 |        "1    -114.47     34.40                19.0       7650.0          1901.0   \n",
119 |        "2    -114.56     33.69                17.0        720.0           174.0   \n",
120 |        "3    -114.57     33.64                14.0       1501.0           337.0   \n",
121 |        "4    -114.57     33.57                20.0       1454.0           326.0   \n",
122 |        "\n",
123 |        "   population  households  median_income  median_house_value  \n",
124 |        "0      1015.0       472.0         1.4936             66900.0  \n",
125 |        "1      1129.0       463.0         1.8200             80100.0  \n",
126 |        "2       333.0       117.0         1.6509             85700.0  \n",
127 |        "3       515.0       226.0         3.1917             73400.0  \n",
128 |        "4       624.0       262.0         1.9250             65500.0  "
129 |       ]
130 |      },
131 |      "execution_count": 2,
132 |      "metadata": {},
133 |      "output_type": "execute_result"
134 |     }
135 |    ],
136 |    "source": [
137 |     "data = pd.read_csv(\"california_housing_train.csv\")\n",
138 |     "data.head()"
139 |    ]
140 |   },
141 |   {
142 |    "cell_type": "code",
143 |    "execution_count": 3,
144 |    "metadata": {},
145 |    "outputs": [
146 |     {
147 |      "data": {
148 |       "text/plain": [
149 |        "longitude             0\n",
150 |        "latitude              0\n",
151 |        "housing_median_age    0\n",
152 |        "total_rooms           0\n",
153 |        "total_bedrooms        0\n",
154 |        "population            0\n",
155 |        "households            0\n",
156 |        "median_income         0\n",
157 |        "median_house_value    0\n",
158 |        "dtype: int64"
159 |       ]
160 |      },
161 |      "execution_count": 3,
162 |      "metadata": {},
163 |      "output_type": "execute_result"
164 |     }
165 |    ],
166 |    "source": [
167 |     "data.isnull().sum()"
168 |    ]
169 |   },
170 |   {
171 |    "cell_type": "code",
172 |    "execution_count": 4,
173 |    "metadata": {},
174 |    "outputs": [
175 |     {
176 |      "name": "stdout",
177 |      "output_type": "stream",
178 |      "text": [
179 |       "<class 'pandas.core.frame.DataFrame'>\n",
180 |       "RangeIndex: 17000 entries, 0 to 16999\n",
181 |       "Data columns (total 9 columns):\n",
182 |       " #   Column              Non-Null Count  Dtype  \n",
183 |       "---  ------              --------------  -----  \n",
184 |       " 0   longitude           17000 non-null  float64\n",
185 |       " 1   latitude            17000 non-null  float64\n",
186 |       " 2   housing_median_age  17000 non-null  float64\n",
187 |       " 3   total_rooms         17000 non-null  float64\n",
188 |       " 4   total_bedrooms      17000 non-null  float64\n",
189 |       " 5   population          17000 non-null  float64\n",
190 |       " 6   households          17000 non-null  float64\n",
191 |       " 7   median_income       17000 non-null  float64\n",
192 |       " 8   median_house_value  17000 non-null  float64\n",
193 |       "dtypes: float64(9)\n",
194 |       "memory usage: 1.2 MB\n"
195 |      ]
196 |     }
197 |    ],
198 |    "source": [
199 |     "data.info()"
200 |    ]
201 |   },
202 |   {
203 |    "cell_type": "code",
204 |    "execution_count": 5,
205 |    "metadata": {},
206 |    "outputs": [],
207 |    "source": [
208 |     "# scale the data\n",
209 |     "\n",
210 |     "from sklearn.preprocessing import MinMaxScaler\n",
211 |     "scaler = MinMaxScaler()\n",
212 |     "data.iloc[:,:] = scaler.fit_transform(data)"
213 |    ]
214 |   },
215 |   {
216 |    "cell_type": "code",
217 |    "execution_count": 6,
218 |    "metadata": {},
219 |    "outputs": [
220 |     {
221 |      "data": {
222 |       "text/html": [
223 |        "<div>\n",
224 |        "<style scoped>\n",
225 |        "    .dataframe tbody tr th:only-of-type {\n",
226 |        "        vertical-align: middle;\n",
227 |        "    }\n",
228 |        "\n",
229 |        "    .dataframe tbody tr th {\n",
230 |        "        vertical-align: top;\n",
231 |        "    }\n",
232 |        "\n",
233 |        "    .dataframe thead th {\n",
234 |        "        text-align: right;\n",
235 |        "    }\n",
236 |        "</style>\n",
237 |        "<table border=\"1\" class=\"dataframe\">\n",
238 |        "  <thead>\n",
239 |        "    <tr style=\"text-align: right;\">\n",
240 |        "      <th></th>\n",
241 |        "      <th>longitude</th>\n",
242 |        "      <th>latitude</th>\n",
243 |        "      <th>housing_median_age</th>\n",
244 |        "      <th>total_rooms</th>\n",
245 |        "      <th>total_bedrooms</th>\n",
246 |        "      <th>population</th>\n",
247 |        "      <th>households</th>\n",
248 |        "      <th>median_income</th>\n",
249 |        "      <th>median_house_value</th>\n",
250 |        "    </tr>\n",
251 |        "  </thead>\n",
252 |        "  <tbody>\n",
253 |        "    <tr>\n",
254 |        "      <th>0</th>\n",
255 |        "      <td>1.000000</td>\n",
256 |        "      <td>0.175345</td>\n",
257 |        "      <td>0.274510</td>\n",
258 |        "      <td>0.147885</td>\n",
259 |        "      <td>0.198945</td>\n",
260 |        "      <td>0.028364</td>\n",
261 |        "      <td>0.077454</td>\n",
262 |        "      <td>0.068530</td>\n",
263 |        "      <td>0.107012</td>\n",
264 |        "    </tr>\n",
265 |        "    <tr>\n",
266 |        "      <th>1</th>\n",
267 |        "      <td>0.984064</td>\n",
268 |        "      <td>0.197662</td>\n",
269 |        "      <td>0.352941</td>\n",
270 |        "      <td>0.201608</td>\n",
271 |        "      <td>0.294848</td>\n",
272 |        "      <td>0.031559</td>\n",
273 |        "      <td>0.075974</td>\n",
274 |        "      <td>0.091040</td>\n",
275 |        "      <td>0.134228</td>\n",
276 |        "    </tr>\n",
277 |        "    <tr>\n",
278 |        "      <th>2</th>\n",
279 |        "      <td>0.975100</td>\n",
280 |        "      <td>0.122210</td>\n",
281 |        "      <td>0.313725</td>\n",
282 |        "      <td>0.018927</td>\n",
283 |        "      <td>0.026847</td>\n",
284 |        "      <td>0.009249</td>\n",
285 |        "      <td>0.019076</td>\n",
286 |        "      <td>0.079378</td>\n",
287 |        "      <td>0.145775</td>\n",
288 |        "    </tr>\n",
289 |        "    <tr>\n",
290 |        "      <th>3</th>\n",
291 |        "      <td>0.974104</td>\n",
292 |        "      <td>0.116897</td>\n",
293 |        "      <td>0.254902</td>\n",
294 |        "      <td>0.039515</td>\n",
295 |        "      <td>0.052142</td>\n",
296 |        "      <td>0.014350</td>\n",
297 |        "      <td>0.037000</td>\n",
298 |        "      <td>0.185639</td>\n",
299 |        "      <td>0.120414</td>\n",
300 |        "    </tr>\n",
301 |        "    <tr>\n",
302 |        "      <th>4</th>\n",
303 |        "      <td>0.974104</td>\n",
304 |        "      <td>0.109458</td>\n",
305 |        "      <td>0.372549</td>\n",
306 |        "      <td>0.038276</td>\n",
307 |        "      <td>0.050435</td>\n",
308 |        "      <td>0.017405</td>\n",
309 |        "      <td>0.042921</td>\n",
310 |        "      <td>0.098281</td>\n",
311 |        "      <td>0.104125</td>\n",
312 |        "    </tr>\n",
313 |        "  </tbody>\n",
314 |        "</table>\n",
315 |        "</div>"
316 |       ],
317 |       "text/plain": [
318 |        "   longitude  latitude  housing_median_age  total_rooms  total_bedrooms  \\\n",
319 |        "0   1.000000  0.175345            0.274510     0.147885        0.198945   \n",
320 |        "1   0.984064  0.197662            0.352941     0.201608        0.294848   \n",
321 |        "2   0.975100  0.122210            0.313725     0.018927        0.026847   \n",
322 |        "3   0.974104  0.116897            0.254902     0.039515        0.052142   \n",
323 |        "4   0.974104  0.109458            0.372549     0.038276        0.050435   \n",
324 |        "\n",
325 |        "   population  households  median_income  median_house_value  \n",
326 |        "0    0.028364    0.077454       0.068530            0.107012  \n",
327 |        "1    0.031559    0.075974       0.091040            0.134228  \n",
328 |        "2    0.009249    0.019076       0.079378            0.145775  \n",
329 |        "3    0.014350    0.037000       0.185639            0.120414  \n",
330 |        "4    0.017405    0.042921       0.098281            0.104125  "
331 |       ]
332 |      },
333 |      "execution_count": 6,
334 |      "metadata": {},
335 |      "output_type": "execute_result"
336 |     }
337 |    ],
338 |    "source": [
339 |     "data.head()"
340 |    ]
341 |   },
342 |   {
343 |    "cell_type": "code",
344 |    "execution_count": 7,
345 |    "metadata": {},
346 |    "outputs": [],
347 |    "source": [
348 |     "X = data.iloc[:,:-1].values #features\n",
349 |     "Y = data.iloc[:,-1].values #target/output"
350 |    ]
351 |   },
352 |   {
353 |    "cell_type": "code",
354 |    "execution_count": 8,
355 |    "metadata": {},
356 |    "outputs": [
357 |     {
358 |      "data": {
359 |       "text/plain": [
360 |        "((17000, 8), (17000,))"
361 |       ]
362 |      },
363 |      "execution_count": 8,
364 |      "metadata": {},
365 |      "output_type": "execute_result"
366 |     }
367 |    ],
368 |    "source": [
369 |     "X.shape, Y.shape"
370 |    ]
371 |   },
372 |   {
373 |    "cell_type": "code",
374 |    "execution_count": 10,
375 |    "metadata": {},
376 |    "outputs": [],
377 |    "source": [
378 |     "from sklearn.model_selection import train_test_split\n",
379 |     "\n",
380 |     "Xtrain, Xtest, Ytrain, Ytest = train_test_split(X, Y, test_size = 0.2, shuffle=True, random_state=4)"
381 |    ]
382 |   },
383 |   {
384 |    "cell_type": "code",
385 |    "execution_count": 11,
386 |    "metadata": {},
387 |    "outputs": [
388 |     {
389 |      "data": {
390 |       "text/html": [
391 |        "<style>#sk-container-id-1 {color: black;background-color: white;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>LinearRegression()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">LinearRegression</label><div class=\"sk-toggleable__content\"><pre>LinearRegression()</pre></div></div></div></div></div>"
392 |       ],
393 |       "text/plain": [
394 |        "LinearRegression()"
395 |       ]
396 |      },
397 |      "execution_count": 11,
398 |      "metadata": {},
399 |      "output_type": "execute_result"
400 |     }
401 |    ],
402 |    "source": [
403 |     "from sklearn.linear_model import LinearRegression\n",
404 |     "\n",
405 |     "model = LinearRegression()\n",
406 |     "model.fit(Xtrain, Ytrain)"
407 |    ]
408 |   },
409 |   {
410 |    "cell_type": "code",
411 |    "execution_count": 12,
412 |    "metadata": {},
413 |    "outputs": [],
414 |    "source": [
415 |     "# MSE\n",
416 |     "# mean of squared differences between actual and predictions\n",
417 |     "\n",
418 |     "def MSE(actual, prediction):\n",
419 |     "    error = actual - prediction\n",
420 |     "    squared = np.square(error)\n",
421 |     "    return np.mean(squared)"
422 |    ]
423 |   },
424 |   {
425 |    "cell_type": "code",
426 |    "execution_count": 13,
427 |    "metadata": {},
428 |    "outputs": [
429 |     {
430 |      "data": {
431 |       "text/plain": [
432 |        "0.02000868218950632"
433 |       ]
434 |      },
435 |      "execution_count": 13,
436 |      "metadata": {},
437 |      "output_type": "execute_result"
438 |     }
439 |    ],
440 |    "source": [
441 |     "prediction_testing = model.predict(Xtest)\n",
442 |     "\n",
443 |     "MSE(Ytest, prediction_testing)"
444 |    ]
445 |   },
446 |   {
447 |    "cell_type": "code",
448 |    "execution_count": 14,
449 |    "metadata": {},
450 |    "outputs": [
451 |     {
452 |      "data": {
453 |       "text/plain": [
454 |        "array([-0.91447718, -0.84873666,  0.11771612, -0.66327286,  1.57499784,\n",
455 |        "       -2.68089479,  0.50641965,  1.20543441])"
456 |       ]
457 |      },
458 |      "execution_count": 14,
459 |      "metadata": {},
460 |      "output_type": "execute_result"
461 |     }
462 |    ],
463 |    "source": [
464 |     "model.coef_"
465 |    ]
466 |   },
467 |   {
468 |    "cell_type": "code",
469 |    "execution_count": 15,
470 |    "metadata": {},
471 |    "outputs": [
472 |     {
473 |      "data": {
474 |       "text/plain": [
475 |        "0.7461423305403194"
476 |       ]
477 |      },
478 |      "execution_count": 15,
479 |      "metadata": {},
480 |      "output_type": "execute_result"
481 |     }
482 |    ],
483 |    "source": [
484 |     "model.intercept_"
485 |    ]
486 |   },
487 |   {
488 |    "cell_type": "code",
489 |    "execution_count": 16,
490 |    "metadata": {},
491 |    "outputs": [],
492 |    "source": [
493 |     "def prediction(x, weights, b):\n",
494 |     "    return x.dot(weights) + b"
495 |    ]
496 |   },
497 |   {
498 |    "cell_type": "code",
499 |    "execution_count": 17,
500 |    "metadata": {},
501 |    "outputs": [
502 |     {
503 |      "data": {
504 |       "text/plain": [
505 |        "array([0.28914931, 0.44840173, 0.55358487, ..., 0.20538748, 0.52725745,\n",
506 |        "       0.75157992])"
507 |       ]
508 |      },
509 |      "execution_count": 17,
510 |      "metadata": {},
511 |      "output_type": "execute_result"
512 |     }
513 |    ],
514 |    "source": [
515 |     "prediction(Xtest, model.coef_, model.intercept_)"
516 |    ]
517 |   },
518 |   {
519 |    "cell_type": "code",
520 |    "execution_count": 18,
521 |    "metadata": {},
522 |    "outputs": [
523 |     {
524 |      "data": {
525 |       "text/plain": [
526 |        "array([0.28914931, 0.44840173, 0.55358487, ..., 0.20538748, 0.52725745,\n",
527 |        "       0.75157992])"
528 |       ]
529 |      },
530 |      "execution_count": 18,
531 |      "metadata": {},
532 |      "output_type": "execute_result"
533 |     }
534 |    ],
535 |    "source": [
536 |     "prediction_testing"
537 |    ]
538 |   },
539 |   {
540 |    "cell_type": "code",
541 |    "execution_count": null,
542 |    "metadata": {},
543 |    "outputs": [],
544 |    "source": []
545 |   }
546 |  ],
547 |  "metadata": {
548 |   "kernelspec": {
549 |    "display_name": "Python 3.10.6 64-bit",
550 |    "language": "python",
551 |    "name": "python3"
552 |   },
553 |   "language_info": {
554 |    "codemirror_mode": {
555 |     "name": "ipython",
556 |     "version": 3
557 |    },
558 |    "file_extension": ".py",
559 |    "mimetype": "text/x-python",
560 |    "name": "python",
561 |    "nbconvert_exporter": "python",
562 |    "pygments_lexer": "ipython3",
563 |    "version": "3.10.6"
564 |   },
565 |   "orig_nbformat": 4,
566 |   "vscode": {
567 |    "interpreter": {
568 |     "hash": "aee8b7b246df8f9039afb4144a1f6fd8d2ca17a180786b69acc140d282b71a49"
569 |    }
570 |   }
571 |  },
572 |  "nbformat": 4,
573 |  "nbformat_minor": 2
574 | }
575 | 


--------------------------------------------------------------------------------
/linear_regression/regression.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 26,
  6 |    "metadata": {},
  7 |    "outputs": [],
  8 |    "source": [
  9 |     "import pandas as pd\n",
 10 |     "import numpy as np"
 11 |    ]
 12 |   },
 13 |   {
 14 |    "cell_type": "code",
 15 |    "execution_count": 27,
 16 |    "metadata": {},
 17 |    "outputs": [
 18 |     {
 19 |      "data": {
 20 |       "text/html": [
 21 |        "<div>\n",
 22 |        "<style scoped>\n",
 23 |        "    .dataframe tbody tr th:only-of-type {\n",
 24 |        "        vertical-align: middle;\n",
 25 |        "    }\n",
 26 |        "\n",
 27 |        "    .dataframe tbody tr th {\n",
 28 |        "        vertical-align: top;\n",
 29 |        "    }\n",
 30 |        "\n",
 31 |        "    .dataframe thead th {\n",
 32 |        "        text-align: right;\n",
 33 |        "    }\n",
 34 |        "</style>\n",
 35 |        "<table border=\"1\" class=\"dataframe\">\n",
 36 |        "  <thead>\n",
 37 |        "    <tr style=\"text-align: right;\">\n",
 38 |        "      <th></th>\n",
 39 |        "      <th>longitude</th>\n",
 40 |        "      <th>latitude</th>\n",
 41 |        "      <th>housing_median_age</th>\n",
 42 |        "      <th>total_rooms</th>\n",
 43 |        "      <th>total_bedrooms</th>\n",
 44 |        "      <th>population</th>\n",
 45 |        "      <th>households</th>\n",
 46 |        "      <th>median_income</th>\n",
 47 |        "      <th>median_house_value</th>\n",
 48 |        "    </tr>\n",
 49 |        "  </thead>\n",
 50 |        "  <tbody>\n",
 51 |        "    <tr>\n",
 52 |        "      <th>0</th>\n",
 53 |        "      <td>-114.31</td>\n",
 54 |        "      <td>34.19</td>\n",
 55 |        "      <td>15.0</td>\n",
 56 |        "      <td>5612.0</td>\n",
 57 |        "      <td>1283.0</td>\n",
 58 |        "      <td>1015.0</td>\n",
 59 |        "      <td>472.0</td>\n",
 60 |        "      <td>1.4936</td>\n",
 61 |        "      <td>66900.0</td>\n",
 62 |        "    </tr>\n",
 63 |        "    <tr>\n",
 64 |        "      <th>1</th>\n",
 65 |        "      <td>-114.47</td>\n",
 66 |        "      <td>34.40</td>\n",
 67 |        "      <td>19.0</td>\n",
 68 |        "      <td>7650.0</td>\n",
 69 |        "      <td>1901.0</td>\n",
 70 |        "      <td>1129.0</td>\n",
 71 |        "      <td>463.0</td>\n",
 72 |        "      <td>1.8200</td>\n",
 73 |        "      <td>80100.0</td>\n",
 74 |        "    </tr>\n",
 75 |        "    <tr>\n",
 76 |        "      <th>2</th>\n",
 77 |        "      <td>-114.56</td>\n",
 78 |        "      <td>33.69</td>\n",
 79 |        "      <td>17.0</td>\n",
 80 |        "      <td>720.0</td>\n",
 81 |        "      <td>174.0</td>\n",
 82 |        "      <td>333.0</td>\n",
 83 |        "      <td>117.0</td>\n",
 84 |        "      <td>1.6509</td>\n",
 85 |        "      <td>85700.0</td>\n",
 86 |        "    </tr>\n",
 87 |        "    <tr>\n",
 88 |        "      <th>3</th>\n",
 89 |        "      <td>-114.57</td>\n",
 90 |        "      <td>33.64</td>\n",
 91 |        "      <td>14.0</td>\n",
 92 |        "      <td>1501.0</td>\n",
 93 |        "      <td>337.0</td>\n",
 94 |        "      <td>515.0</td>\n",
 95 |        "      <td>226.0</td>\n",
 96 |        "      <td>3.1917</td>\n",
 97 |        "      <td>73400.0</td>\n",
 98 |        "    </tr>\n",
 99 |        "    <tr>\n",
100 |        "      <th>4</th>\n",
101 |        "      <td>-114.57</td>\n",
102 |        "      <td>33.57</td>\n",
103 |        "      <td>20.0</td>\n",
104 |        "      <td>1454.0</td>\n",
105 |        "      <td>326.0</td>\n",
106 |        "      <td>624.0</td>\n",
107 |        "      <td>262.0</td>\n",
108 |        "      <td>1.9250</td>\n",
109 |        "      <td>65500.0</td>\n",
110 |        "    </tr>\n",
111 |        "  </tbody>\n",
112 |        "</table>\n",
113 |        "</div>"
114 |       ],
115 |       "text/plain": [
116 |        "   longitude  latitude  housing_median_age  total_rooms  total_bedrooms  \\\n",
117 |        "0    -114.31     34.19                15.0       5612.0          1283.0   \n",
118 |        "1    -114.47     34.40                19.0       7650.0          1901.0   \n",
119 |        "2    -114.56     33.69                17.0        720.0           174.0   \n",
120 |        "3    -114.57     33.64                14.0       1501.0           337.0   \n",
121 |        "4    -114.57     33.57                20.0       1454.0           326.0   \n",
122 |        "\n",
123 |        "   population  households  median_income  median_house_value  \n",
124 |        "0      1015.0       472.0         1.4936             66900.0  \n",
125 |        "1      1129.0       463.0         1.8200             80100.0  \n",
126 |        "2       333.0       117.0         1.6509             85700.0  \n",
127 |        "3       515.0       226.0         3.1917             73400.0  \n",
128 |        "4       624.0       262.0         1.9250             65500.0  "
129 |       ]
130 |      },
131 |      "execution_count": 27,
132 |      "metadata": {},
133 |      "output_type": "execute_result"
134 |     }
135 |    ],
136 |    "source": [
137 |     "data = pd.read_csv(\"california_housing_train.csv\")\n",
138 |     "data.head()"
139 |    ]
140 |   },
141 |   {
142 |    "cell_type": "code",
143 |    "execution_count": 28,
144 |    "metadata": {},
145 |    "outputs": [
146 |     {
147 |      "name": "stdout",
148 |      "output_type": "stream",
149 |      "text": [
150 |       "<class 'pandas.core.frame.DataFrame'>\n",
151 |       "RangeIndex: 17000 entries, 0 to 16999\n",
152 |       "Data columns (total 9 columns):\n",
153 |       " #   Column              Non-Null Count  Dtype  \n",
154 |       "---  ------              --------------  -----  \n",
155 |       " 0   longitude           17000 non-null  float64\n",
156 |       " 1   latitude            17000 non-null  float64\n",
157 |       " 2   housing_median_age  17000 non-null  float64\n",
158 |       " 3   total_rooms         17000 non-null  float64\n",
159 |       " 4   total_bedrooms      17000 non-null  float64\n",
160 |       " 5   population          17000 non-null  float64\n",
161 |       " 6   households          17000 non-null  float64\n",
162 |       " 7   median_income       17000 non-null  float64\n",
163 |       " 8   median_house_value  17000 non-null  float64\n",
164 |       "dtypes: float64(9)\n",
165 |       "memory usage: 1.2 MB\n"
166 |      ]
167 |     }
168 |    ],
169 |    "source": [
170 |     "data.info()"
171 |    ]
172 |   },
173 |   {
174 |    "cell_type": "code",
175 |    "execution_count": 29,
176 |    "metadata": {},
177 |    "outputs": [
178 |     {
179 |      "data": {
180 |       "text/plain": [
181 |        "False"
182 |       ]
183 |      },
184 |      "execution_count": 29,
185 |      "metadata": {},
186 |      "output_type": "execute_result"
187 |     }
188 |    ],
189 |    "source": [
190 |     "data.isnull().sum().any()"
191 |    ]
192 |   },
193 |   {
194 |    "cell_type": "code",
195 |    "execution_count": 30,
196 |    "metadata": {},
197 |    "outputs": [
198 |     {
199 |      "data": {
200 |       "text/html": [
201 |        "<div>\n",
202 |        "<style scoped>\n",
203 |        "    .dataframe tbody tr th:only-of-type {\n",
204 |        "        vertical-align: middle;\n",
205 |        "    }\n",
206 |        "\n",
207 |        "    .dataframe tbody tr th {\n",
208 |        "        vertical-align: top;\n",
209 |        "    }\n",
210 |        "\n",
211 |        "    .dataframe thead th {\n",
212 |        "        text-align: right;\n",
213 |        "    }\n",
214 |        "</style>\n",
215 |        "<table border=\"1\" class=\"dataframe\">\n",
216 |        "  <thead>\n",
217 |        "    <tr style=\"text-align: right;\">\n",
218 |        "      <th></th>\n",
219 |        "      <th>longitude</th>\n",
220 |        "      <th>latitude</th>\n",
221 |        "      <th>housing_median_age</th>\n",
222 |        "      <th>total_rooms</th>\n",
223 |        "      <th>total_bedrooms</th>\n",
224 |        "      <th>population</th>\n",
225 |        "      <th>households</th>\n",
226 |        "      <th>median_income</th>\n",
227 |        "      <th>median_house_value</th>\n",
228 |        "    </tr>\n",
229 |        "  </thead>\n",
230 |        "  <tbody>\n",
231 |        "    <tr>\n",
232 |        "      <th>0</th>\n",
233 |        "      <td>1.000000</td>\n",
234 |        "      <td>0.175345</td>\n",
235 |        "      <td>0.274510</td>\n",
236 |        "      <td>0.147885</td>\n",
237 |        "      <td>0.198945</td>\n",
238 |        "      <td>0.028364</td>\n",
239 |        "      <td>0.077454</td>\n",
240 |        "      <td>0.068530</td>\n",
241 |        "      <td>0.107012</td>\n",
242 |        "    </tr>\n",
243 |        "    <tr>\n",
244 |        "      <th>1</th>\n",
245 |        "      <td>0.984064</td>\n",
246 |        "      <td>0.197662</td>\n",
247 |        "      <td>0.352941</td>\n",
248 |        "      <td>0.201608</td>\n",
249 |        "      <td>0.294848</td>\n",
250 |        "      <td>0.031559</td>\n",
251 |        "      <td>0.075974</td>\n",
252 |        "      <td>0.091040</td>\n",
253 |        "      <td>0.134228</td>\n",
254 |        "    </tr>\n",
255 |        "    <tr>\n",
256 |        "      <th>2</th>\n",
257 |        "      <td>0.975100</td>\n",
258 |        "      <td>0.122210</td>\n",
259 |        "      <td>0.313725</td>\n",
260 |        "      <td>0.018927</td>\n",
261 |        "      <td>0.026847</td>\n",
262 |        "      <td>0.009249</td>\n",
263 |        "      <td>0.019076</td>\n",
264 |        "      <td>0.079378</td>\n",
265 |        "      <td>0.145775</td>\n",
266 |        "    </tr>\n",
267 |        "    <tr>\n",
268 |        "      <th>3</th>\n",
269 |        "      <td>0.974104</td>\n",
270 |        "      <td>0.116897</td>\n",
271 |        "      <td>0.254902</td>\n",
272 |        "      <td>0.039515</td>\n",
273 |        "      <td>0.052142</td>\n",
274 |        "      <td>0.014350</td>\n",
275 |        "      <td>0.037000</td>\n",
276 |        "      <td>0.185639</td>\n",
277 |        "      <td>0.120414</td>\n",
278 |        "    </tr>\n",
279 |        "    <tr>\n",
280 |        "      <th>4</th>\n",
281 |        "      <td>0.974104</td>\n",
282 |        "      <td>0.109458</td>\n",
283 |        "      <td>0.372549</td>\n",
284 |        "      <td>0.038276</td>\n",
285 |        "      <td>0.050435</td>\n",
286 |        "      <td>0.017405</td>\n",
287 |        "      <td>0.042921</td>\n",
288 |        "      <td>0.098281</td>\n",
289 |        "      <td>0.104125</td>\n",
290 |        "    </tr>\n",
291 |        "  </tbody>\n",
292 |        "</table>\n",
293 |        "</div>"
294 |       ],
295 |       "text/plain": [
296 |        "   longitude  latitude  housing_median_age  total_rooms  total_bedrooms  \\\n",
297 |        "0   1.000000  0.175345            0.274510     0.147885        0.198945   \n",
298 |        "1   0.984064  0.197662            0.352941     0.201608        0.294848   \n",
299 |        "2   0.975100  0.122210            0.313725     0.018927        0.026847   \n",
300 |        "3   0.974104  0.116897            0.254902     0.039515        0.052142   \n",
301 |        "4   0.974104  0.109458            0.372549     0.038276        0.050435   \n",
302 |        "\n",
303 |        "   population  households  median_income  median_house_value  \n",
304 |        "0    0.028364    0.077454       0.068530            0.107012  \n",
305 |        "1    0.031559    0.075974       0.091040            0.134228  \n",
306 |        "2    0.009249    0.019076       0.079378            0.145775  \n",
307 |        "3    0.014350    0.037000       0.185639            0.120414  \n",
308 |        "4    0.017405    0.042921       0.098281            0.104125  "
309 |       ]
310 |      },
311 |      "execution_count": 30,
312 |      "metadata": {},
313 |      "output_type": "execute_result"
314 |     }
315 |    ],
316 |    "source": [
317 |     "from sklearn.preprocessing import MinMaxScaler\n",
318 |     "\n",
319 |     "scaler = MinMaxScaler()\n",
320 |     "data.iloc[:,:] = scaler.fit_transform(data)\n",
321 |     "\n",
322 |     "data.head()"
323 |    ]
324 |   },
325 |   {
326 |    "cell_type": "code",
327 |    "execution_count": 31,
328 |    "metadata": {},
329 |    "outputs": [],
330 |    "source": [
331 |     "X = data.iloc[:, :-1].values\n",
332 |     "\n",
333 |     "Y = data.iloc[:, -1].values"
334 |    ]
335 |   },
336 |   {
337 |    "cell_type": "code",
338 |    "execution_count": 32,
339 |    "metadata": {},
340 |    "outputs": [],
341 |    "source": [
342 |     "from sklearn.model_selection import train_test_split\n",
343 |     "Xtrain, Xtest, Ytrain, Ytest = train_test_split(X, Y, test_size=0.2, shuffle=True, random_state=4)"
344 |    ]
345 |   },
346 |   {
347 |    "cell_type": "code",
348 |    "execution_count": 33,
349 |    "metadata": {},
350 |    "outputs": [
351 |     {
352 |      "data": {
353 |       "text/html": [
354 |        "<style>#sk-container-id-4 {color: black;background-color: white;}#sk-container-id-4 pre{padding: 0;}#sk-container-id-4 div.sk-toggleable {background-color: white;}#sk-container-id-4 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-4 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-4 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-4 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-4 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-4 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-4 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-4 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-4 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-4 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-4 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-4 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-4 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-4 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-4 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-4 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-4 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-4 div.sk-item {position: relative;z-index: 1;}#sk-container-id-4 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-4 div.sk-item::before, #sk-container-id-4 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-4 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-4 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-4 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-4 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-4 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-4 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-4 div.sk-label-container {text-align: center;}#sk-container-id-4 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-4 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-4\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>LinearRegression()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-4\" type=\"checkbox\" checked><label for=\"sk-estimator-id-4\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">LinearRegression</label><div class=\"sk-toggleable__content\"><pre>LinearRegression()</pre></div></div></div></div></div>"
355 |       ],
356 |       "text/plain": [
357 |        "LinearRegression()"
358 |       ]
359 |      },
360 |      "execution_count": 33,
361 |      "metadata": {},
362 |      "output_type": "execute_result"
363 |     }
364 |    ],
365 |    "source": [
366 |     "from sklearn.linear_model import LinearRegression\n",
367 |     "\n",
368 |     "model = LinearRegression()\n",
369 |     "model.fit(Xtrain, Ytrain)"
370 |    ]
371 |   },
372 |   {
373 |    "cell_type": "code",
374 |    "execution_count": 34,
375 |    "metadata": {},
376 |    "outputs": [],
377 |    "source": [
378 |     "prediction_testing = model.predict(Xtest)"
379 |    ]
380 |   },
381 |   {
382 |    "cell_type": "code",
383 |    "execution_count": 35,
384 |    "metadata": {},
385 |    "outputs": [],
386 |    "source": [
387 |     "def MSE(actual, prediction):\n",
388 |     "    error = actual - prediction\n",
389 |     "    squared = np.square(error)\n",
390 |     "    return np.mean(squared)"
391 |    ]
392 |   },
393 |   {
394 |    "cell_type": "code",
395 |    "execution_count": 36,
396 |    "metadata": {},
397 |    "outputs": [
398 |     {
399 |      "data": {
400 |       "text/plain": [
401 |        "0.02000868218950632"
402 |       ]
403 |      },
404 |      "execution_count": 36,
405 |      "metadata": {},
406 |      "output_type": "execute_result"
407 |     }
408 |    ],
409 |    "source": [
410 |     "MSE(Ytest, prediction_testing)"
411 |    ]
412 |   },
413 |   {
414 |    "cell_type": "code",
415 |    "execution_count": 37,
416 |    "metadata": {},
417 |    "outputs": [],
418 |    "source": [
419 |     "def RMSE(y_actual, y_prediction):\n",
420 |     "    return np.sqrt(MSE(y_actual, y_prediction))\n",
421 |     "\n",
422 |     "def MAE(actual, prediction):\n",
423 |     "    error = actual - prediction\n",
424 |     "    absolute = np.abs(error)\n",
425 |     "    return np.mean(absolute)\n",
426 |     "\n",
427 |     "def R2Score(y_actual, y_predicted):\n",
428 |     "\t\t\tmean = np.mean(y_actual)\n",
429 |     "\t\t\tr2score = 1- np.mean(np.square(y_actual - y_predicted))/np.mean(np.square(y_actual - mean))\n",
430 |     "\t\t\treturn r2score"
431 |    ]
432 |   },
433 |   {
434 |    "cell_type": "code",
435 |    "execution_count": 38,
436 |    "metadata": {},
437 |    "outputs": [
438 |     {
439 |      "name": "stdout",
440 |      "output_type": "stream",
441 |      "text": [
442 |       " MSE :  0.02000868218950632\n",
443 |       " RMSE :  0.14145204908203457\n",
444 |       " MAE :  0.10454649510468285\n",
445 |       " R2Score :  0.6463260859038824\n"
446 |      ]
447 |     }
448 |    ],
449 |    "source": [
450 |     "print(\" MSE : \",MSE(Ytest, prediction_testing))\n",
451 |     "print(\" RMSE : \",RMSE(Ytest, prediction_testing))\n",
452 |     "print(\" MAE : \",MAE(Ytest, prediction_testing))\n",
453 |     "print(\" R2Score : \",R2Score(Ytest, prediction_testing))\n",
454 |     "\n"
455 |    ]
456 |   },
457 |   {
458 |    "cell_type": "code",
459 |    "execution_count": 39,
460 |    "metadata": {},
461 |    "outputs": [
462 |     {
463 |      "data": {
464 |       "text/plain": [
465 |        "array([-0.91447718, -0.84873666,  0.11771612, -0.66327286,  1.57499784,\n",
466 |        "       -2.68089479,  0.50641965,  1.20543441])"
467 |       ]
468 |      },
469 |      "execution_count": 39,
470 |      "metadata": {},
471 |      "output_type": "execute_result"
472 |     }
473 |    ],
474 |    "source": [
475 |     "model.coef_"
476 |    ]
477 |   },
478 |   {
479 |    "cell_type": "code",
480 |    "execution_count": 40,
481 |    "metadata": {},
482 |    "outputs": [
483 |     {
484 |      "data": {
485 |       "text/plain": [
486 |        "0.7461423305403194"
487 |       ]
488 |      },
489 |      "execution_count": 40,
490 |      "metadata": {},
491 |      "output_type": "execute_result"
492 |     }
493 |    ],
494 |    "source": [
495 |     "model.intercept_"
496 |    ]
497 |   },
498 |   {
499 |    "cell_type": "code",
500 |    "execution_count": 41,
501 |    "metadata": {},
502 |    "outputs": [],
503 |    "source": [
504 |     "def prediction(x, weights, b):\n",
505 |     "    return x.dot(weights) + b"
506 |    ]
507 |   },
508 |   {
509 |    "cell_type": "code",
510 |    "execution_count": 42,
511 |    "metadata": {},
512 |    "outputs": [
513 |     {
514 |      "data": {
515 |       "text/plain": [
516 |        "array([0.28914931, 0.44840173, 0.55358487, ..., 0.20538748, 0.52725745,\n",
517 |        "       0.75157992])"
518 |       ]
519 |      },
520 |      "execution_count": 42,
521 |      "metadata": {},
522 |      "output_type": "execute_result"
523 |     }
524 |    ],
525 |    "source": [
526 |     "prediction(Xtest, model.coef_, model.intercept_)"
527 |    ]
528 |   },
529 |   {
530 |    "cell_type": "code",
531 |    "execution_count": 43,
532 |    "metadata": {},
533 |    "outputs": [
534 |     {
535 |      "data": {
536 |       "text/plain": [
537 |        "array([0.28914931, 0.44840173, 0.55358487, ..., 0.20538748, 0.52725745,\n",
538 |        "       0.75157992])"
539 |       ]
540 |      },
541 |      "execution_count": 43,
542 |      "metadata": {},
543 |      "output_type": "execute_result"
544 |     }
545 |    ],
546 |    "source": [
547 |     "prediction_testing"
548 |    ]
549 |   },
550 |   {
551 |    "cell_type": "code",
552 |    "execution_count": 44,
553 |    "metadata": {},
554 |    "outputs": [
555 |     {
556 |      "data": {
557 |       "text/html": [
558 |        "<style>#sk-container-id-5 {color: black;background-color: white;}#sk-container-id-5 pre{padding: 0;}#sk-container-id-5 div.sk-toggleable {background-color: white;}#sk-container-id-5 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-5 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-5 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-5 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-5 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-5 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-5 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-5 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-5 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-5 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-5 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-5 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-5 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-5 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-5 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-5 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-5 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-5 div.sk-item {position: relative;z-index: 1;}#sk-container-id-5 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-5 div.sk-item::before, #sk-container-id-5 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-5 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-5 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-5 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-5 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-5 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-5 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-5 div.sk-label-container {text-align: center;}#sk-container-id-5 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-5 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-5\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>Lasso()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-5\" type=\"checkbox\" checked><label for=\"sk-estimator-id-5\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">Lasso</label><div class=\"sk-toggleable__content\"><pre>Lasso()</pre></div></div></div></div></div>"
559 |       ],
560 |       "text/plain": [
561 |        "Lasso()"
562 |       ]
563 |      },
564 |      "execution_count": 44,
565 |      "metadata": {},
566 |      "output_type": "execute_result"
567 |     }
568 |    ],
569 |    "source": [
570 |     "# lasso and ridge regression\n",
571 |     "\n",
572 |     "from sklearn.linear_model import Lasso\n",
573 |     "\n",
574 |     "model = Lasso()\n",
575 |     "\n",
576 |     "model.fit(Xtrain, Ytrain)\n"
577 |    ]
578 |   },
579 |   {
580 |    "cell_type": "code",
581 |    "execution_count": 45,
582 |    "metadata": {},
583 |    "outputs": [
584 |     {
585 |      "name": "stdout",
586 |      "output_type": "stream",
587 |      "text": [
588 |       "==Lasso Regression==\n",
589 |       " MSE :  0.05657465206027041\n",
590 |       " RMSE :  0.23785426643276847\n",
591 |       " MAE :  0.18771396740146856\n",
592 |       " R2Score :  -1.4815732125361691e-05\n"
593 |      ]
594 |     }
595 |    ],
596 |    "source": [
597 |     "prediction_testing = model.predict(Xtest)\n",
598 |     "\n",
599 |     "print(\"==Lasso Regression==\")\n",
600 |     "print(\" MSE : \",MSE(Ytest, prediction_testing))\n",
601 |     "print(\" RMSE : \",RMSE(Ytest, prediction_testing))\n",
602 |     "print(\" MAE : \",MAE(Ytest, prediction_testing))\n",
603 |     "print(\" R2Score : \",R2Score(Ytest, prediction_testing))"
604 |    ]
605 |   },
606 |   {
607 |    "cell_type": "code",
608 |    "execution_count": 46,
609 |    "metadata": {},
610 |    "outputs": [
611 |     {
612 |      "data": {
613 |       "text/html": [
614 |        "<style>#sk-container-id-6 {color: black;background-color: white;}#sk-container-id-6 pre{padding: 0;}#sk-container-id-6 div.sk-toggleable {background-color: white;}#sk-container-id-6 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-6 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-6 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-6 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-6 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-6 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-6 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-6 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-6 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-6 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-6 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-6 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-6 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-6 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-6 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-6 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-6 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-6 div.sk-item {position: relative;z-index: 1;}#sk-container-id-6 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-6 div.sk-item::before, #sk-container-id-6 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-6 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-6 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-6 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-6 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-6 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-6 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-6 div.sk-label-container {text-align: center;}#sk-container-id-6 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-6 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-6\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>Ridge()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-6\" type=\"checkbox\" checked><label for=\"sk-estimator-id-6\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">Ridge</label><div class=\"sk-toggleable__content\"><pre>Ridge()</pre></div></div></div></div></div>"
615 |       ],
616 |       "text/plain": [
617 |        "Ridge()"
618 |       ]
619 |      },
620 |      "execution_count": 46,
621 |      "metadata": {},
622 |      "output_type": "execute_result"
623 |     }
624 |    ],
625 |    "source": [
626 |     "from sklearn.linear_model import Ridge\n",
627 |     "\n",
628 |     "model = Ridge()\n",
629 |     "\n",
630 |     "model.fit(Xtrain, Ytrain)"
631 |    ]
632 |   },
633 |   {
634 |    "cell_type": "code",
635 |    "execution_count": 47,
636 |    "metadata": {},
637 |    "outputs": [
638 |     {
639 |      "name": "stdout",
640 |      "output_type": "stream",
641 |      "text": [
642 |       "==Ridge Regression==\n",
643 |       " MSE :  0.020316486450436506\n",
644 |       " RMSE :  0.14253591284457579\n",
645 |       " MAE :  0.10540829325059124\n",
646 |       " R2Score :  0.6408853309002502\n"
647 |      ]
648 |     }
649 |    ],
650 |    "source": [
651 |     "prediction_testing = model.predict(Xtest)\n",
652 |     "\n",
653 |     "print(\"==Ridge Regression==\")\n",
654 |     "print(\" MSE : \",MSE(Ytest, prediction_testing))\n",
655 |     "print(\" RMSE : \",RMSE(Ytest, prediction_testing))\n",
656 |     "print(\" MAE : \",MAE(Ytest, prediction_testing))\n",
657 |     "print(\" R2Score : \",R2Score(Ytest, prediction_testing))"
658 |    ]
659 |   },
660 |   {
661 |    "cell_type": "code",
662 |    "execution_count": 48,
663 |    "metadata": {},
664 |    "outputs": [
665 |     {
666 |      "name": "stdout",
667 |      "output_type": "stream",
668 |      "text": [
669 |       "---- Ridge Regression Lambda =  1.7  ----\n",
670 |       " MSE :  0.02052184410992044\n",
671 |       " RMSE :  0.14325447326321242\n",
672 |       " MAE :  0.10599064844968335\n",
673 |       " R2Score :  0.6372554243161278\n",
674 |       "---- Ridge Regression Lambda =  2.0  ----\n",
675 |       " MSE :  0.02060155172442634\n",
676 |       " RMSE :  0.14353240653046384\n",
677 |       " MAE :  0.10621516994931038\n",
678 |       " R2Score :  0.6358465107385834\n",
679 |       "---- Ridge Regression Lambda =  0.5  ----\n",
680 |       " MSE :  0.020158152266279827\n",
681 |       " RMSE :  0.14197940789522903\n",
682 |       " MAE :  0.10495745493793113\n",
683 |       " R2Score :  0.6436840494822904\n",
684 |       "---- Ridge Regression Lambda =  0.2  ----\n",
685 |       " MSE :  0.020065160155331427\n",
686 |       " RMSE :  0.14165154483919837\n",
687 |       " MAE :  0.10470406142416774\n",
688 |       " R2Score :  0.6453277801162064\n",
689 |       "---- Ridge Regression Lambda =  0.1  ----\n",
690 |       " MSE :  0.0200360696805774\n",
691 |       " RMSE :  0.14154882437017058\n",
692 |       " MAE :  0.10462429756247424\n",
693 |       " R2Score :  0.6458419839988873\n"
694 |      ]
695 |     }
696 |    ],
697 |    "source": [
698 |     "for i in [1.7, 2.0, 0.5, 0.2, 0.1]:\n",
699 |     "    model = Ridge(alpha=i)\n",
700 |     "    model.fit(Xtrain, Ytrain)\n",
701 |     "    predictedvalue = model.predict(Xtest)\n",
702 |     "    print(\"---- Ridge Regression Lambda = \", i,\" ----\")\n",
703 |     "    print(\" MSE : \",MSE(Ytest, predictedvalue))\n",
704 |     "    print(\" RMSE : \",RMSE(Ytest, predictedvalue))\n",
705 |     "    print(\" MAE : \",MAE(Ytest, predictedvalue))\n",
706 |     "    print(\" R2Score : \",R2Score(Ytest, predictedvalue))"
707 |    ]
708 |   }
709 |  ],
710 |  "metadata": {
711 |   "kernelspec": {
712 |    "display_name": "Python 3.10.6 64-bit",
713 |    "language": "python",
714 |    "name": "python3"
715 |   },
716 |   "language_info": {
717 |    "codemirror_mode": {
718 |     "name": "ipython",
719 |     "version": 3
720 |    },
721 |    "file_extension": ".py",
722 |    "mimetype": "text/x-python",
723 |    "name": "python",
724 |    "nbconvert_exporter": "python",
725 |    "pygments_lexer": "ipython3",
726 |    "version": "3.10.6"
727 |   },
728 |   "orig_nbformat": 4,
729 |   "vscode": {
730 |    "interpreter": {
731 |     "hash": "aee8b7b246df8f9039afb4144a1f6fd8d2ca17a180786b69acc140d282b71a49"
732 |    }
733 |   }
734 |  },
735 |  "nbformat": 4,
736 |  "nbformat_minor": 2
737 | }
738 | 


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