├── LICENSE
├── README.md
├── Gaussian Naive Bayes Classifier.ipynb
├── K Nearest Neighbours.ipynb
├── Logistic Regression Classifier.ipynb
├── Random Forest Classifier.ipynb
├── Neural Network Classifier.ipynb
└── Multiple Linear Regression.ipynb


/LICENSE:
--------------------------------------------------------------------------------
 1 | MIT License
 2 | 
 3 | Copyright (c) 2020 Azhan Mohammed
 4 | 
 5 | Permission is hereby granted, free of charge, to any person obtaining a copy
 6 | of this software and associated documentation files (the "Software"), to deal
 7 | in the Software without restriction, including without limitation the rights
 8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 9 | copies of the Software, and to permit persons to whom the Software is
10 | furnished to do so, subject to the following conditions:
11 | 
12 | The above copyright notice and this permission notice shall be included in all
13 | copies or substantial portions of the Software.
14 | 
15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
21 | SOFTWARE.
22 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | <p style="text-align: center;"></p>
 2 | <span align="center"> <h2> Credit-Card-Fraud-Detection-using-Machine-Learning-and-Deep-Learning-Techniques </h2> </span>
 3 | <p style="text-align: center;"></p>
 4 | <span align="center"> <h3> <a href="https://azhanmohammed.netlify.app">Azhan Mohammed</a>, Shazli Meraj</h3> </span>
 5 | 
 6 | 
 7 | This repository contains the files for various machine learning and deep learning algorithms that have been used in our submission for Credit Card Fraud Detection using Machine Learning and Deep Learning Techniques paper at 2020 3rd International Conference on Intelligent Sustainable Systems (ICISS). The paper can be found [here](https://ieeexplore.ieee.org/abstract/document/9316002).  
 8 | A list of the ML and DL algorithms that have been used are:  
 9 | - [Multiple Linear Regression](https://github.com/sheikhazhanmohammed/Credit-Card-Fraud-Detection-using-Machine-Learning-and-Deep-Learning-Techniques/blob/main/Multiple%20Linear%20Regression.ipynb)
10 | - [Logistic Regression](https://github.com/sheikhazhanmohammed/Credit-Card-Fraud-Detection-using-Machine-Learning-and-Deep-Learning-Techniques/blob/main/Logistic%20Regression%20Classifier.ipynb)
11 | - [K Nearest Neighbours](https://github.com/sheikhazhanmohammed/Credit-Card-Fraud-Detection-using-Machine-Learning-and-Deep-Learning-Techniques/blob/main/K%20Nearest%20Neighbours.ipynb)
12 | - [Naive Bayes Classifier](https://github.com/sheikhazhanmohammed/Credit-Card-Fraud-Detection-using-Machine-Learning-and-Deep-Learning-Techniques/blob/main/Gaussian%20Naive%20Bayes%20Classifier.ipynb)
13 | - [Random Forest Classifier](https://github.com/sheikhazhanmohammed/Credit-Card-Fraud-Detection-using-Machine-Learning-and-Deep-Learning-Techniques/blob/main/Random%20Forest%20Classifier.ipynb)
14 | - [Neural Network Classifier](https://github.com/sheikhazhanmohammed/Credit-Card-Fraud-Detection-using-Machine-Learning-and-Deep-Learning-Techniques/blob/main/Neural%20Network%20Classifier.ipynb)
15 | 
16 | The neural network classifier contains a custom loss function, which helps to deal with the dataset imbalance. The dataset is taken from Kaggle, and is available in the Dataset folder.
17 | 
18 | #### Contact
19 | 
20 | - Azhan Mohammed: azhanmohammed1999@gmail.com
21 | - Shazli Meraj: shazlimeraj@gmail.com
22 | 


--------------------------------------------------------------------------------
/Gaussian Naive Bayes Classifier.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 1,
  6 |    "metadata": {},
  7 |    "outputs": [],
  8 |    "source": [
  9 |     "#import important libraries\n",
 10 |     "import pandas as pd\n",
 11 |     "import numpy as np\n",
 12 |     "import seaborn as sns\n",
 13 |     "from sklearn.metrics import classification_report\n",
 14 |     "from sklearn.metrics import roc_auc_score as roc\n",
 15 |     "from sklearn.model_selection import train_test_split as tts\n",
 16 |     "from sklearn.preprocessing import StandardScaler\n",
 17 |     "from sklearn.naive_bayes import GaussianNB"
 18 |    ]
 19 |   },
 20 |   {
 21 |    "cell_type": "code",
 22 |    "execution_count": 2,
 23 |    "metadata": {},
 24 |    "outputs": [
 25 |     {
 26 |      "data": {
 27 |       "text/html": [
 28 |        "<div>\n",
 29 |        "<style scoped>\n",
 30 |        "    .dataframe tbody tr th:only-of-type {\n",
 31 |        "        vertical-align: middle;\n",
 32 |        "    }\n",
 33 |        "\n",
 34 |        "    .dataframe tbody tr th {\n",
 35 |        "        vertical-align: top;\n",
 36 |        "    }\n",
 37 |        "\n",
 38 |        "    .dataframe thead th {\n",
 39 |        "        text-align: right;\n",
 40 |        "    }\n",
 41 |        "</style>\n",
 42 |        "<table border=\"1\" class=\"dataframe\">\n",
 43 |        "  <thead>\n",
 44 |        "    <tr style=\"text-align: right;\">\n",
 45 |        "      <th></th>\n",
 46 |        "      <th>Time</th>\n",
 47 |        "      <th>V1</th>\n",
 48 |        "      <th>V2</th>\n",
 49 |        "      <th>V3</th>\n",
 50 |        "      <th>V4</th>\n",
 51 |        "      <th>V5</th>\n",
 52 |        "      <th>V6</th>\n",
 53 |        "      <th>V7</th>\n",
 54 |        "      <th>V8</th>\n",
 55 |        "      <th>V9</th>\n",
 56 |        "      <th>...</th>\n",
 57 |        "      <th>V21</th>\n",
 58 |        "      <th>V22</th>\n",
 59 |        "      <th>V23</th>\n",
 60 |        "      <th>V24</th>\n",
 61 |        "      <th>V25</th>\n",
 62 |        "      <th>V26</th>\n",
 63 |        "      <th>V27</th>\n",
 64 |        "      <th>V28</th>\n",
 65 |        "      <th>Amount</th>\n",
 66 |        "      <th>Class</th>\n",
 67 |        "    </tr>\n",
 68 |        "  </thead>\n",
 69 |        "  <tbody>\n",
 70 |        "    <tr>\n",
 71 |        "      <th>0</th>\n",
 72 |        "      <td>0.0</td>\n",
 73 |        "      <td>-1.359807</td>\n",
 74 |        "      <td>-0.072781</td>\n",
 75 |        "      <td>2.536347</td>\n",
 76 |        "      <td>1.378155</td>\n",
 77 |        "      <td>-0.338321</td>\n",
 78 |        "      <td>0.462388</td>\n",
 79 |        "      <td>0.239599</td>\n",
 80 |        "      <td>0.098698</td>\n",
 81 |        "      <td>0.363787</td>\n",
 82 |        "      <td>...</td>\n",
 83 |        "      <td>-0.018307</td>\n",
 84 |        "      <td>0.277838</td>\n",
 85 |        "      <td>-0.110474</td>\n",
 86 |        "      <td>0.066928</td>\n",
 87 |        "      <td>0.128539</td>\n",
 88 |        "      <td>-0.189115</td>\n",
 89 |        "      <td>0.133558</td>\n",
 90 |        "      <td>-0.021053</td>\n",
 91 |        "      <td>149.62</td>\n",
 92 |        "      <td>0</td>\n",
 93 |        "    </tr>\n",
 94 |        "    <tr>\n",
 95 |        "      <th>1</th>\n",
 96 |        "      <td>0.0</td>\n",
 97 |        "      <td>1.191857</td>\n",
 98 |        "      <td>0.266151</td>\n",
 99 |        "      <td>0.166480</td>\n",
100 |        "      <td>0.448154</td>\n",
101 |        "      <td>0.060018</td>\n",
102 |        "      <td>-0.082361</td>\n",
103 |        "      <td>-0.078803</td>\n",
104 |        "      <td>0.085102</td>\n",
105 |        "      <td>-0.255425</td>\n",
106 |        "      <td>...</td>\n",
107 |        "      <td>-0.225775</td>\n",
108 |        "      <td>-0.638672</td>\n",
109 |        "      <td>0.101288</td>\n",
110 |        "      <td>-0.339846</td>\n",
111 |        "      <td>0.167170</td>\n",
112 |        "      <td>0.125895</td>\n",
113 |        "      <td>-0.008983</td>\n",
114 |        "      <td>0.014724</td>\n",
115 |        "      <td>2.69</td>\n",
116 |        "      <td>0</td>\n",
117 |        "    </tr>\n",
118 |        "    <tr>\n",
119 |        "      <th>2</th>\n",
120 |        "      <td>1.0</td>\n",
121 |        "      <td>-1.358354</td>\n",
122 |        "      <td>-1.340163</td>\n",
123 |        "      <td>1.773209</td>\n",
124 |        "      <td>0.379780</td>\n",
125 |        "      <td>-0.503198</td>\n",
126 |        "      <td>1.800499</td>\n",
127 |        "      <td>0.791461</td>\n",
128 |        "      <td>0.247676</td>\n",
129 |        "      <td>-1.514654</td>\n",
130 |        "      <td>...</td>\n",
131 |        "      <td>0.247998</td>\n",
132 |        "      <td>0.771679</td>\n",
133 |        "      <td>0.909412</td>\n",
134 |        "      <td>-0.689281</td>\n",
135 |        "      <td>-0.327642</td>\n",
136 |        "      <td>-0.139097</td>\n",
137 |        "      <td>-0.055353</td>\n",
138 |        "      <td>-0.059752</td>\n",
139 |        "      <td>378.66</td>\n",
140 |        "      <td>0</td>\n",
141 |        "    </tr>\n",
142 |        "    <tr>\n",
143 |        "      <th>3</th>\n",
144 |        "      <td>1.0</td>\n",
145 |        "      <td>-0.966272</td>\n",
146 |        "      <td>-0.185226</td>\n",
147 |        "      <td>1.792993</td>\n",
148 |        "      <td>-0.863291</td>\n",
149 |        "      <td>-0.010309</td>\n",
150 |        "      <td>1.247203</td>\n",
151 |        "      <td>0.237609</td>\n",
152 |        "      <td>0.377436</td>\n",
153 |        "      <td>-1.387024</td>\n",
154 |        "      <td>...</td>\n",
155 |        "      <td>-0.108300</td>\n",
156 |        "      <td>0.005274</td>\n",
157 |        "      <td>-0.190321</td>\n",
158 |        "      <td>-1.175575</td>\n",
159 |        "      <td>0.647376</td>\n",
160 |        "      <td>-0.221929</td>\n",
161 |        "      <td>0.062723</td>\n",
162 |        "      <td>0.061458</td>\n",
163 |        "      <td>123.50</td>\n",
164 |        "      <td>0</td>\n",
165 |        "    </tr>\n",
166 |        "    <tr>\n",
167 |        "      <th>4</th>\n",
168 |        "      <td>2.0</td>\n",
169 |        "      <td>-1.158233</td>\n",
170 |        "      <td>0.877737</td>\n",
171 |        "      <td>1.548718</td>\n",
172 |        "      <td>0.403034</td>\n",
173 |        "      <td>-0.407193</td>\n",
174 |        "      <td>0.095921</td>\n",
175 |        "      <td>0.592941</td>\n",
176 |        "      <td>-0.270533</td>\n",
177 |        "      <td>0.817739</td>\n",
178 |        "      <td>...</td>\n",
179 |        "      <td>-0.009431</td>\n",
180 |        "      <td>0.798278</td>\n",
181 |        "      <td>-0.137458</td>\n",
182 |        "      <td>0.141267</td>\n",
183 |        "      <td>-0.206010</td>\n",
184 |        "      <td>0.502292</td>\n",
185 |        "      <td>0.219422</td>\n",
186 |        "      <td>0.215153</td>\n",
187 |        "      <td>69.99</td>\n",
188 |        "      <td>0</td>\n",
189 |        "    </tr>\n",
190 |        "  </tbody>\n",
191 |        "</table>\n",
192 |        "<p>5 rows × 31 columns</p>\n",
193 |        "</div>"
194 |       ],
195 |       "text/plain": [
196 |        "   Time        V1        V2        V3        V4        V5        V6        V7  \\\n",
197 |        "0   0.0 -1.359807 -0.072781  2.536347  1.378155 -0.338321  0.462388  0.239599   \n",
198 |        "1   0.0  1.191857  0.266151  0.166480  0.448154  0.060018 -0.082361 -0.078803   \n",
199 |        "2   1.0 -1.358354 -1.340163  1.773209  0.379780 -0.503198  1.800499  0.791461   \n",
200 |        "3   1.0 -0.966272 -0.185226  1.792993 -0.863291 -0.010309  1.247203  0.237609   \n",
201 |        "4   2.0 -1.158233  0.877737  1.548718  0.403034 -0.407193  0.095921  0.592941   \n",
202 |        "\n",
203 |        "         V8        V9  ...       V21       V22       V23       V24       V25  \\\n",
204 |        "0  0.098698  0.363787  ... -0.018307  0.277838 -0.110474  0.066928  0.128539   \n",
205 |        "1  0.085102 -0.255425  ... -0.225775 -0.638672  0.101288 -0.339846  0.167170   \n",
206 |        "2  0.247676 -1.514654  ...  0.247998  0.771679  0.909412 -0.689281 -0.327642   \n",
207 |        "3  0.377436 -1.387024  ... -0.108300  0.005274 -0.190321 -1.175575  0.647376   \n",
208 |        "4 -0.270533  0.817739  ... -0.009431  0.798278 -0.137458  0.141267 -0.206010   \n",
209 |        "\n",
210 |        "        V26       V27       V28  Amount  Class  \n",
211 |        "0 -0.189115  0.133558 -0.021053  149.62      0  \n",
212 |        "1  0.125895 -0.008983  0.014724    2.69      0  \n",
213 |        "2 -0.139097 -0.055353 -0.059752  378.66      0  \n",
214 |        "3 -0.221929  0.062723  0.061458  123.50      0  \n",
215 |        "4  0.502292  0.219422  0.215153   69.99      0  \n",
216 |        "\n",
217 |        "[5 rows x 31 columns]"
218 |       ]
219 |      },
220 |      "execution_count": 2,
221 |      "metadata": {},
222 |      "output_type": "execute_result"
223 |     }
224 |    ],
225 |    "source": [
226 |     "#import the dataset and visualize the dataset\n",
227 |     "dataset = pd.read_csv('./dataset/creditcard.csv')\n",
228 |     "dataset.head()"
229 |    ]
230 |   },
231 |   {
232 |    "cell_type": "code",
233 |    "execution_count": 3,
234 |    "metadata": {},
235 |    "outputs": [
236 |     {
237 |      "data": {
238 |       "text/plain": [
239 |        "<matplotlib.axes._subplots.AxesSubplot at 0x7f6d7b174190>"
240 |       ]
241 |      },
242 |      "execution_count": 3,
243 |      "metadata": {},
244 |      "output_type": "execute_result"
245 |     },
246 |     {
247 |      "data": {
248 |       "image/png": "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\n",
249 |       "text/plain": [
250 |        "<Figure size 432x288 with 1 Axes>"
251 |       ]
252 |      },
253 |      "metadata": {
254 |       "needs_background": "light"
255 |      },
256 |      "output_type": "display_data"
257 |     }
258 |    ],
259 |    "source": [
260 |     "#visualize the target class 'Class'\n",
261 |     "sns.countplot(x='Class', data=dataset)"
262 |    ]
263 |   },
264 |   {
265 |    "cell_type": "code",
266 |    "execution_count": 4,
267 |    "metadata": {},
268 |    "outputs": [],
269 |    "source": [
270 |     "#seperating positive and negative classes\n",
271 |     "positiveDataset = dataset.loc[dataset['Class'] == 1]\n",
272 |     "negativeDataset = dataset.loc[dataset['Class'] == 0]"
273 |    ]
274 |   },
275 |   {
276 |    "cell_type": "code",
277 |    "execution_count": 5,
278 |    "metadata": {},
279 |    "outputs": [],
280 |    "source": [
281 |     "#creating training and testing set with negative class split 1:1 and positive class split 4:1, also keeping random_state constant so that all splits are same\n",
282 |     "positiveTrain, positiveTest = tts(positiveDataset, test_size=0.2, random_state=21)\n",
283 |     "negativeTrain, negativeTest = tts(negativeDataset, test_size=0.5)\n",
284 |     "trainDataset = positiveTrain.append(negativeTrain)\n",
285 |     "testDataset = positiveTest.append(negativeTest)"
286 |    ]
287 |   },
288 |   {
289 |    "cell_type": "code",
290 |    "execution_count": 6,
291 |    "metadata": {},
292 |    "outputs": [],
293 |    "source": [
294 |     "#create Regression object and scale the dataset\n",
295 |     "classifier = GaussianNB()\n",
296 |     "yTrain = trainDataset['Class']\n",
297 |     "yTest = testDataset['Class']\n",
298 |     "xTrain = trainDataset.drop(columns=['Class'])\n",
299 |     "xTest = testDataset.drop(columns=['Class'])\n",
300 |     "scaler = StandardScaler()\n",
301 |     "xTrain = scaler.fit_transform(xTrain)\n",
302 |     "xTest = scaler.fit_transform(xTest)"
303 |    ]
304 |   },
305 |   {
306 |    "cell_type": "code",
307 |    "execution_count": 7,
308 |    "metadata": {},
309 |    "outputs": [
310 |     {
311 |      "data": {
312 |       "text/plain": [
313 |        "GaussianNB()"
314 |       ]
315 |      },
316 |      "execution_count": 7,
317 |      "metadata": {},
318 |      "output_type": "execute_result"
319 |     }
320 |    ],
321 |    "source": [
322 |     "#fit the dataset to the train values\n",
323 |     "classifier.fit(xTrain, yTrain)"
324 |    ]
325 |   },
326 |   {
327 |    "cell_type": "code",
328 |    "execution_count": 8,
329 |    "metadata": {},
330 |    "outputs": [
331 |     {
332 |      "name": "stdout",
333 |      "output_type": "stream",
334 |      "text": [
335 |       "              precision    recall  f1-score   support\n",
336 |       "\n",
337 |       "           0       1.00      0.98      0.99    142157\n",
338 |       "           1       0.10      0.83      0.17       393\n",
339 |       "\n",
340 |       "    accuracy                           0.98    142550\n",
341 |       "   macro avg       0.55      0.90      0.58    142550\n",
342 |       "weighted avg       1.00      0.98      0.99    142550\n",
343 |       "\n",
344 |       "ROC AUC Score:  0.90383724578178\n"
345 |      ]
346 |     }
347 |    ],
348 |    "source": [
349 |     "#predict the model on the train values and check results\n",
350 |     "predTrain = classifier.predict(xTrain)\n",
351 |     "print(classification_report(yTrain, predTrain))\n",
352 |     "print('ROC AUC Score: ',roc(yTrain, predTrain))"
353 |    ]
354 |   },
355 |   {
356 |    "cell_type": "code",
357 |    "execution_count": 9,
358 |    "metadata": {},
359 |    "outputs": [
360 |     {
361 |      "name": "stdout",
362 |      "output_type": "stream",
363 |      "text": [
364 |       "              precision    recall  f1-score   support\n",
365 |       "\n",
366 |       "           0       1.00      0.98      0.99    142158\n",
367 |       "           1       0.02      0.86      0.05        99\n",
368 |       "\n",
369 |       "    accuracy                           0.98    142257\n",
370 |       "   macro avg       0.51      0.92      0.52    142257\n",
371 |       "weighted avg       1.00      0.98      0.99    142257\n",
372 |       "\n",
373 |       "ROC AUC Score:  0.9173062665655414\n"
374 |      ]
375 |     }
376 |    ],
377 |    "source": [
378 |     "#predict test values and check results\n",
379 |     "predTest = classifier.predict(xTest)\n",
380 |     "print(classification_report(yTest, predTest))\n",
381 |     "print('ROC AUC Score: ',roc(yTest, predTest))"
382 |    ]
383 |   }
384 |  ],
385 |  "metadata": {
386 |   "kernelspec": {
387 |    "display_name": "Python 3",
388 |    "language": "python",
389 |    "name": "python3"
390 |   },
391 |   "language_info": {
392 |    "codemirror_mode": {
393 |     "name": "ipython",
394 |     "version": 3
395 |    },
396 |    "file_extension": ".py",
397 |    "mimetype": "text/x-python",
398 |    "name": "python",
399 |    "nbconvert_exporter": "python",
400 |    "pygments_lexer": "ipython3",
401 |    "version": "3.8.3"
402 |   }
403 |  },
404 |  "nbformat": 4,
405 |  "nbformat_minor": 4
406 | }
407 | 


--------------------------------------------------------------------------------
/K Nearest Neighbours.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 1,
  6 |    "metadata": {},
  7 |    "outputs": [],
  8 |    "source": [
  9 |     "#import important libraries\n",
 10 |     "import pandas as pd\n",
 11 |     "import numpy as np\n",
 12 |     "import seaborn as sns\n",
 13 |     "from sklearn.metrics import classification_report\n",
 14 |     "from sklearn.metrics import roc_auc_score as roc\n",
 15 |     "from sklearn.model_selection import train_test_split as tts\n",
 16 |     "from sklearn.preprocessing import StandardScaler\n",
 17 |     "from sklearn.neighbors import KNeighborsClassifier"
 18 |    ]
 19 |   },
 20 |   {
 21 |    "cell_type": "code",
 22 |    "execution_count": 2,
 23 |    "metadata": {},
 24 |    "outputs": [
 25 |     {
 26 |      "data": {
 27 |       "text/html": [
 28 |        "<div>\n",
 29 |        "<style scoped>\n",
 30 |        "    .dataframe tbody tr th:only-of-type {\n",
 31 |        "        vertical-align: middle;\n",
 32 |        "    }\n",
 33 |        "\n",
 34 |        "    .dataframe tbody tr th {\n",
 35 |        "        vertical-align: top;\n",
 36 |        "    }\n",
 37 |        "\n",
 38 |        "    .dataframe thead th {\n",
 39 |        "        text-align: right;\n",
 40 |        "    }\n",
 41 |        "</style>\n",
 42 |        "<table border=\"1\" class=\"dataframe\">\n",
 43 |        "  <thead>\n",
 44 |        "    <tr style=\"text-align: right;\">\n",
 45 |        "      <th></th>\n",
 46 |        "      <th>Time</th>\n",
 47 |        "      <th>V1</th>\n",
 48 |        "      <th>V2</th>\n",
 49 |        "      <th>V3</th>\n",
 50 |        "      <th>V4</th>\n",
 51 |        "      <th>V5</th>\n",
 52 |        "      <th>V6</th>\n",
 53 |        "      <th>V7</th>\n",
 54 |        "      <th>V8</th>\n",
 55 |        "      <th>V9</th>\n",
 56 |        "      <th>...</th>\n",
 57 |        "      <th>V21</th>\n",
 58 |        "      <th>V22</th>\n",
 59 |        "      <th>V23</th>\n",
 60 |        "      <th>V24</th>\n",
 61 |        "      <th>V25</th>\n",
 62 |        "      <th>V26</th>\n",
 63 |        "      <th>V27</th>\n",
 64 |        "      <th>V28</th>\n",
 65 |        "      <th>Amount</th>\n",
 66 |        "      <th>Class</th>\n",
 67 |        "    </tr>\n",
 68 |        "  </thead>\n",
 69 |        "  <tbody>\n",
 70 |        "    <tr>\n",
 71 |        "      <th>0</th>\n",
 72 |        "      <td>0.0</td>\n",
 73 |        "      <td>-1.359807</td>\n",
 74 |        "      <td>-0.072781</td>\n",
 75 |        "      <td>2.536347</td>\n",
 76 |        "      <td>1.378155</td>\n",
 77 |        "      <td>-0.338321</td>\n",
 78 |        "      <td>0.462388</td>\n",
 79 |        "      <td>0.239599</td>\n",
 80 |        "      <td>0.098698</td>\n",
 81 |        "      <td>0.363787</td>\n",
 82 |        "      <td>...</td>\n",
 83 |        "      <td>-0.018307</td>\n",
 84 |        "      <td>0.277838</td>\n",
 85 |        "      <td>-0.110474</td>\n",
 86 |        "      <td>0.066928</td>\n",
 87 |        "      <td>0.128539</td>\n",
 88 |        "      <td>-0.189115</td>\n",
 89 |        "      <td>0.133558</td>\n",
 90 |        "      <td>-0.021053</td>\n",
 91 |        "      <td>149.62</td>\n",
 92 |        "      <td>0</td>\n",
 93 |        "    </tr>\n",
 94 |        "    <tr>\n",
 95 |        "      <th>1</th>\n",
 96 |        "      <td>0.0</td>\n",
 97 |        "      <td>1.191857</td>\n",
 98 |        "      <td>0.266151</td>\n",
 99 |        "      <td>0.166480</td>\n",
100 |        "      <td>0.448154</td>\n",
101 |        "      <td>0.060018</td>\n",
102 |        "      <td>-0.082361</td>\n",
103 |        "      <td>-0.078803</td>\n",
104 |        "      <td>0.085102</td>\n",
105 |        "      <td>-0.255425</td>\n",
106 |        "      <td>...</td>\n",
107 |        "      <td>-0.225775</td>\n",
108 |        "      <td>-0.638672</td>\n",
109 |        "      <td>0.101288</td>\n",
110 |        "      <td>-0.339846</td>\n",
111 |        "      <td>0.167170</td>\n",
112 |        "      <td>0.125895</td>\n",
113 |        "      <td>-0.008983</td>\n",
114 |        "      <td>0.014724</td>\n",
115 |        "      <td>2.69</td>\n",
116 |        "      <td>0</td>\n",
117 |        "    </tr>\n",
118 |        "    <tr>\n",
119 |        "      <th>2</th>\n",
120 |        "      <td>1.0</td>\n",
121 |        "      <td>-1.358354</td>\n",
122 |        "      <td>-1.340163</td>\n",
123 |        "      <td>1.773209</td>\n",
124 |        "      <td>0.379780</td>\n",
125 |        "      <td>-0.503198</td>\n",
126 |        "      <td>1.800499</td>\n",
127 |        "      <td>0.791461</td>\n",
128 |        "      <td>0.247676</td>\n",
129 |        "      <td>-1.514654</td>\n",
130 |        "      <td>...</td>\n",
131 |        "      <td>0.247998</td>\n",
132 |        "      <td>0.771679</td>\n",
133 |        "      <td>0.909412</td>\n",
134 |        "      <td>-0.689281</td>\n",
135 |        "      <td>-0.327642</td>\n",
136 |        "      <td>-0.139097</td>\n",
137 |        "      <td>-0.055353</td>\n",
138 |        "      <td>-0.059752</td>\n",
139 |        "      <td>378.66</td>\n",
140 |        "      <td>0</td>\n",
141 |        "    </tr>\n",
142 |        "    <tr>\n",
143 |        "      <th>3</th>\n",
144 |        "      <td>1.0</td>\n",
145 |        "      <td>-0.966272</td>\n",
146 |        "      <td>-0.185226</td>\n",
147 |        "      <td>1.792993</td>\n",
148 |        "      <td>-0.863291</td>\n",
149 |        "      <td>-0.010309</td>\n",
150 |        "      <td>1.247203</td>\n",
151 |        "      <td>0.237609</td>\n",
152 |        "      <td>0.377436</td>\n",
153 |        "      <td>-1.387024</td>\n",
154 |        "      <td>...</td>\n",
155 |        "      <td>-0.108300</td>\n",
156 |        "      <td>0.005274</td>\n",
157 |        "      <td>-0.190321</td>\n",
158 |        "      <td>-1.175575</td>\n",
159 |        "      <td>0.647376</td>\n",
160 |        "      <td>-0.221929</td>\n",
161 |        "      <td>0.062723</td>\n",
162 |        "      <td>0.061458</td>\n",
163 |        "      <td>123.50</td>\n",
164 |        "      <td>0</td>\n",
165 |        "    </tr>\n",
166 |        "    <tr>\n",
167 |        "      <th>4</th>\n",
168 |        "      <td>2.0</td>\n",
169 |        "      <td>-1.158233</td>\n",
170 |        "      <td>0.877737</td>\n",
171 |        "      <td>1.548718</td>\n",
172 |        "      <td>0.403034</td>\n",
173 |        "      <td>-0.407193</td>\n",
174 |        "      <td>0.095921</td>\n",
175 |        "      <td>0.592941</td>\n",
176 |        "      <td>-0.270533</td>\n",
177 |        "      <td>0.817739</td>\n",
178 |        "      <td>...</td>\n",
179 |        "      <td>-0.009431</td>\n",
180 |        "      <td>0.798278</td>\n",
181 |        "      <td>-0.137458</td>\n",
182 |        "      <td>0.141267</td>\n",
183 |        "      <td>-0.206010</td>\n",
184 |        "      <td>0.502292</td>\n",
185 |        "      <td>0.219422</td>\n",
186 |        "      <td>0.215153</td>\n",
187 |        "      <td>69.99</td>\n",
188 |        "      <td>0</td>\n",
189 |        "    </tr>\n",
190 |        "  </tbody>\n",
191 |        "</table>\n",
192 |        "<p>5 rows × 31 columns</p>\n",
193 |        "</div>"
194 |       ],
195 |       "text/plain": [
196 |        "   Time        V1        V2        V3        V4        V5        V6        V7  \\\n",
197 |        "0   0.0 -1.359807 -0.072781  2.536347  1.378155 -0.338321  0.462388  0.239599   \n",
198 |        "1   0.0  1.191857  0.266151  0.166480  0.448154  0.060018 -0.082361 -0.078803   \n",
199 |        "2   1.0 -1.358354 -1.340163  1.773209  0.379780 -0.503198  1.800499  0.791461   \n",
200 |        "3   1.0 -0.966272 -0.185226  1.792993 -0.863291 -0.010309  1.247203  0.237609   \n",
201 |        "4   2.0 -1.158233  0.877737  1.548718  0.403034 -0.407193  0.095921  0.592941   \n",
202 |        "\n",
203 |        "         V8        V9  ...       V21       V22       V23       V24       V25  \\\n",
204 |        "0  0.098698  0.363787  ... -0.018307  0.277838 -0.110474  0.066928  0.128539   \n",
205 |        "1  0.085102 -0.255425  ... -0.225775 -0.638672  0.101288 -0.339846  0.167170   \n",
206 |        "2  0.247676 -1.514654  ...  0.247998  0.771679  0.909412 -0.689281 -0.327642   \n",
207 |        "3  0.377436 -1.387024  ... -0.108300  0.005274 -0.190321 -1.175575  0.647376   \n",
208 |        "4 -0.270533  0.817739  ... -0.009431  0.798278 -0.137458  0.141267 -0.206010   \n",
209 |        "\n",
210 |        "        V26       V27       V28  Amount  Class  \n",
211 |        "0 -0.189115  0.133558 -0.021053  149.62      0  \n",
212 |        "1  0.125895 -0.008983  0.014724    2.69      0  \n",
213 |        "2 -0.139097 -0.055353 -0.059752  378.66      0  \n",
214 |        "3 -0.221929  0.062723  0.061458  123.50      0  \n",
215 |        "4  0.502292  0.219422  0.215153   69.99      0  \n",
216 |        "\n",
217 |        "[5 rows x 31 columns]"
218 |       ]
219 |      },
220 |      "execution_count": 2,
221 |      "metadata": {},
222 |      "output_type": "execute_result"
223 |     }
224 |    ],
225 |    "source": [
226 |     "#import the dataset and visualize the dataset\n",
227 |     "dataset = pd.read_csv('./dataset/creditcard.csv')\n",
228 |     "dataset.head()"
229 |    ]
230 |   },
231 |   {
232 |    "cell_type": "code",
233 |    "execution_count": 3,
234 |    "metadata": {},
235 |    "outputs": [
236 |     {
237 |      "data": {
238 |       "text/plain": [
239 |        "<matplotlib.axes._subplots.AxesSubplot at 0x7fe069284700>"
240 |       ]
241 |      },
242 |      "execution_count": 3,
243 |      "metadata": {},
244 |      "output_type": "execute_result"
245 |     },
246 |     {
247 |      "data": {
248 |       "image/png": "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\n",
249 |       "text/plain": [
250 |        "<Figure size 432x288 with 1 Axes>"
251 |       ]
252 |      },
253 |      "metadata": {
254 |       "needs_background": "light"
255 |      },
256 |      "output_type": "display_data"
257 |     }
258 |    ],
259 |    "source": [
260 |     "#visualize the target class 'Class'\n",
261 |     "sns.countplot(x='Class', data=dataset)"
262 |    ]
263 |   },
264 |   {
265 |    "cell_type": "code",
266 |    "execution_count": 4,
267 |    "metadata": {},
268 |    "outputs": [],
269 |    "source": [
270 |     "#seperating positive and negative classes\n",
271 |     "positiveDataset = dataset.loc[dataset['Class'] == 1]\n",
272 |     "negativeDataset = dataset.loc[dataset['Class'] == 0]"
273 |    ]
274 |   },
275 |   {
276 |    "cell_type": "code",
277 |    "execution_count": 5,
278 |    "metadata": {},
279 |    "outputs": [],
280 |    "source": [
281 |     "#creating training and testing set with negative class split 1:1 and positive class split 4:1, also keeping random_state constant so that all splits are same\n",
282 |     "positiveTrain, positiveTest = tts(positiveDataset, test_size=0.2, random_state=21)\n",
283 |     "negativeTrain, negativeTest = tts(negativeDataset, test_size=0.5)\n",
284 |     "trainDataset = positiveTrain.append(negativeTrain)\n",
285 |     "testDataset = positiveTest.append(negativeTest)"
286 |    ]
287 |   },
288 |   {
289 |    "cell_type": "code",
290 |    "execution_count": 6,
291 |    "metadata": {},
292 |    "outputs": [],
293 |    "source": [
294 |     "#create Regression object and scale the dataset\n",
295 |     "classifier = KNeighborsClassifier(n_neighbors=5)\n",
296 |     "yTrain = trainDataset['Class']\n",
297 |     "yTest = testDataset['Class']\n",
298 |     "xTrain = trainDataset.drop(columns=['Class'])\n",
299 |     "xTest = testDataset.drop(columns=['Class'])\n",
300 |     "scaler = StandardScaler()\n",
301 |     "xTrain = scaler.fit_transform(xTrain)\n",
302 |     "xTest = scaler.fit_transform(xTest)"
303 |    ]
304 |   },
305 |   {
306 |    "cell_type": "code",
307 |    "execution_count": 7,
308 |    "metadata": {},
309 |    "outputs": [
310 |     {
311 |      "data": {
312 |       "text/plain": [
313 |        "KNeighborsClassifier()"
314 |       ]
315 |      },
316 |      "execution_count": 7,
317 |      "metadata": {},
318 |      "output_type": "execute_result"
319 |     }
320 |    ],
321 |    "source": [
322 |     "#fit the dataset to the train values\n",
323 |     "classifier.fit(xTrain, yTrain)"
324 |    ]
325 |   },
326 |   {
327 |    "cell_type": "code",
328 |    "execution_count": 8,
329 |    "metadata": {},
330 |    "outputs": [
331 |     {
332 |      "name": "stdout",
333 |      "output_type": "stream",
334 |      "text": [
335 |       "              precision    recall  f1-score   support\n",
336 |       "\n",
337 |       "           0       1.00      1.00      1.00    142157\n",
338 |       "           1       0.94      0.81      0.87       393\n",
339 |       "\n",
340 |       "    accuracy                           1.00    142550\n",
341 |       "   macro avg       0.97      0.90      0.93    142550\n",
342 |       "weighted avg       1.00      1.00      1.00    142550\n",
343 |       "\n",
344 |       "ROC AUC Score:  0.9045098079120887\n"
345 |      ]
346 |     }
347 |    ],
348 |    "source": [
349 |     "#predict the model on the train values and check results\n",
350 |     "predTrain = classifier.predict(xTrain)\n",
351 |     "print(classification_report(yTrain, predTrain))\n",
352 |     "print('ROC AUC Score: ',roc(yTrain, predTrain))"
353 |    ]
354 |   },
355 |   {
356 |    "cell_type": "code",
357 |    "execution_count": 9,
358 |    "metadata": {},
359 |    "outputs": [
360 |     {
361 |      "name": "stdout",
362 |      "output_type": "stream",
363 |      "text": [
364 |       "              precision    recall  f1-score   support\n",
365 |       "\n",
366 |       "           0       1.00      1.00      1.00    142158\n",
367 |       "           1       0.75      0.81      0.78        99\n",
368 |       "\n",
369 |       "    accuracy                           1.00    142257\n",
370 |       "   macro avg       0.88      0.90      0.89    142257\n",
371 |       "weighted avg       1.00      1.00      1.00    142257\n",
372 |       "\n",
373 |       "ROC AUC Score:  0.9039489564961224\n"
374 |      ]
375 |     }
376 |    ],
377 |    "source": [
378 |     "#predict test values and check results\n",
379 |     "predTest = classifier.predict(xTest)\n",
380 |     "print(classification_report(yTest, predTest))\n",
381 |     "print('ROC AUC Score: ',roc(yTest, predTest))"
382 |    ]
383 |   }
384 |  ],
385 |  "metadata": {
386 |   "kernelspec": {
387 |    "display_name": "Python 3",
388 |    "language": "python",
389 |    "name": "python3"
390 |   },
391 |   "language_info": {
392 |    "codemirror_mode": {
393 |     "name": "ipython",
394 |     "version": 3
395 |    },
396 |    "file_extension": ".py",
397 |    "mimetype": "text/x-python",
398 |    "name": "python",
399 |    "nbconvert_exporter": "python",
400 |    "pygments_lexer": "ipython3",
401 |    "version": "3.8.3"
402 |   }
403 |  },
404 |  "nbformat": 4,
405 |  "nbformat_minor": 4
406 | }
407 | 


--------------------------------------------------------------------------------
/Logistic Regression Classifier.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 1,
  6 |    "metadata": {},
  7 |    "outputs": [],
  8 |    "source": [
  9 |     "#import important libraries\n",
 10 |     "import pandas as pd\n",
 11 |     "import numpy as np\n",
 12 |     "import seaborn as sns\n",
 13 |     "from sklearn.metrics import classification_report\n",
 14 |     "from sklearn.metrics import roc_auc_score as roc\n",
 15 |     "from sklearn.model_selection import train_test_split as tts\n",
 16 |     "from sklearn.linear_model import LogisticRegression\n",
 17 |     "from sklearn.preprocessing import StandardScaler"
 18 |    ]
 19 |   },
 20 |   {
 21 |    "cell_type": "code",
 22 |    "execution_count": 2,
 23 |    "metadata": {},
 24 |    "outputs": [
 25 |     {
 26 |      "data": {
 27 |       "text/html": [
 28 |        "<div>\n",
 29 |        "<style scoped>\n",
 30 |        "    .dataframe tbody tr th:only-of-type {\n",
 31 |        "        vertical-align: middle;\n",
 32 |        "    }\n",
 33 |        "\n",
 34 |        "    .dataframe tbody tr th {\n",
 35 |        "        vertical-align: top;\n",
 36 |        "    }\n",
 37 |        "\n",
 38 |        "    .dataframe thead th {\n",
 39 |        "        text-align: right;\n",
 40 |        "    }\n",
 41 |        "</style>\n",
 42 |        "<table border=\"1\" class=\"dataframe\">\n",
 43 |        "  <thead>\n",
 44 |        "    <tr style=\"text-align: right;\">\n",
 45 |        "      <th></th>\n",
 46 |        "      <th>Time</th>\n",
 47 |        "      <th>V1</th>\n",
 48 |        "      <th>V2</th>\n",
 49 |        "      <th>V3</th>\n",
 50 |        "      <th>V4</th>\n",
 51 |        "      <th>V5</th>\n",
 52 |        "      <th>V6</th>\n",
 53 |        "      <th>V7</th>\n",
 54 |        "      <th>V8</th>\n",
 55 |        "      <th>V9</th>\n",
 56 |        "      <th>...</th>\n",
 57 |        "      <th>V21</th>\n",
 58 |        "      <th>V22</th>\n",
 59 |        "      <th>V23</th>\n",
 60 |        "      <th>V24</th>\n",
 61 |        "      <th>V25</th>\n",
 62 |        "      <th>V26</th>\n",
 63 |        "      <th>V27</th>\n",
 64 |        "      <th>V28</th>\n",
 65 |        "      <th>Amount</th>\n",
 66 |        "      <th>Class</th>\n",
 67 |        "    </tr>\n",
 68 |        "  </thead>\n",
 69 |        "  <tbody>\n",
 70 |        "    <tr>\n",
 71 |        "      <th>0</th>\n",
 72 |        "      <td>0.0</td>\n",
 73 |        "      <td>-1.359807</td>\n",
 74 |        "      <td>-0.072781</td>\n",
 75 |        "      <td>2.536347</td>\n",
 76 |        "      <td>1.378155</td>\n",
 77 |        "      <td>-0.338321</td>\n",
 78 |        "      <td>0.462388</td>\n",
 79 |        "      <td>0.239599</td>\n",
 80 |        "      <td>0.098698</td>\n",
 81 |        "      <td>0.363787</td>\n",
 82 |        "      <td>...</td>\n",
 83 |        "      <td>-0.018307</td>\n",
 84 |        "      <td>0.277838</td>\n",
 85 |        "      <td>-0.110474</td>\n",
 86 |        "      <td>0.066928</td>\n",
 87 |        "      <td>0.128539</td>\n",
 88 |        "      <td>-0.189115</td>\n",
 89 |        "      <td>0.133558</td>\n",
 90 |        "      <td>-0.021053</td>\n",
 91 |        "      <td>149.62</td>\n",
 92 |        "      <td>0</td>\n",
 93 |        "    </tr>\n",
 94 |        "    <tr>\n",
 95 |        "      <th>1</th>\n",
 96 |        "      <td>0.0</td>\n",
 97 |        "      <td>1.191857</td>\n",
 98 |        "      <td>0.266151</td>\n",
 99 |        "      <td>0.166480</td>\n",
100 |        "      <td>0.448154</td>\n",
101 |        "      <td>0.060018</td>\n",
102 |        "      <td>-0.082361</td>\n",
103 |        "      <td>-0.078803</td>\n",
104 |        "      <td>0.085102</td>\n",
105 |        "      <td>-0.255425</td>\n",
106 |        "      <td>...</td>\n",
107 |        "      <td>-0.225775</td>\n",
108 |        "      <td>-0.638672</td>\n",
109 |        "      <td>0.101288</td>\n",
110 |        "      <td>-0.339846</td>\n",
111 |        "      <td>0.167170</td>\n",
112 |        "      <td>0.125895</td>\n",
113 |        "      <td>-0.008983</td>\n",
114 |        "      <td>0.014724</td>\n",
115 |        "      <td>2.69</td>\n",
116 |        "      <td>0</td>\n",
117 |        "    </tr>\n",
118 |        "    <tr>\n",
119 |        "      <th>2</th>\n",
120 |        "      <td>1.0</td>\n",
121 |        "      <td>-1.358354</td>\n",
122 |        "      <td>-1.340163</td>\n",
123 |        "      <td>1.773209</td>\n",
124 |        "      <td>0.379780</td>\n",
125 |        "      <td>-0.503198</td>\n",
126 |        "      <td>1.800499</td>\n",
127 |        "      <td>0.791461</td>\n",
128 |        "      <td>0.247676</td>\n",
129 |        "      <td>-1.514654</td>\n",
130 |        "      <td>...</td>\n",
131 |        "      <td>0.247998</td>\n",
132 |        "      <td>0.771679</td>\n",
133 |        "      <td>0.909412</td>\n",
134 |        "      <td>-0.689281</td>\n",
135 |        "      <td>-0.327642</td>\n",
136 |        "      <td>-0.139097</td>\n",
137 |        "      <td>-0.055353</td>\n",
138 |        "      <td>-0.059752</td>\n",
139 |        "      <td>378.66</td>\n",
140 |        "      <td>0</td>\n",
141 |        "    </tr>\n",
142 |        "    <tr>\n",
143 |        "      <th>3</th>\n",
144 |        "      <td>1.0</td>\n",
145 |        "      <td>-0.966272</td>\n",
146 |        "      <td>-0.185226</td>\n",
147 |        "      <td>1.792993</td>\n",
148 |        "      <td>-0.863291</td>\n",
149 |        "      <td>-0.010309</td>\n",
150 |        "      <td>1.247203</td>\n",
151 |        "      <td>0.237609</td>\n",
152 |        "      <td>0.377436</td>\n",
153 |        "      <td>-1.387024</td>\n",
154 |        "      <td>...</td>\n",
155 |        "      <td>-0.108300</td>\n",
156 |        "      <td>0.005274</td>\n",
157 |        "      <td>-0.190321</td>\n",
158 |        "      <td>-1.175575</td>\n",
159 |        "      <td>0.647376</td>\n",
160 |        "      <td>-0.221929</td>\n",
161 |        "      <td>0.062723</td>\n",
162 |        "      <td>0.061458</td>\n",
163 |        "      <td>123.50</td>\n",
164 |        "      <td>0</td>\n",
165 |        "    </tr>\n",
166 |        "    <tr>\n",
167 |        "      <th>4</th>\n",
168 |        "      <td>2.0</td>\n",
169 |        "      <td>-1.158233</td>\n",
170 |        "      <td>0.877737</td>\n",
171 |        "      <td>1.548718</td>\n",
172 |        "      <td>0.403034</td>\n",
173 |        "      <td>-0.407193</td>\n",
174 |        "      <td>0.095921</td>\n",
175 |        "      <td>0.592941</td>\n",
176 |        "      <td>-0.270533</td>\n",
177 |        "      <td>0.817739</td>\n",
178 |        "      <td>...</td>\n",
179 |        "      <td>-0.009431</td>\n",
180 |        "      <td>0.798278</td>\n",
181 |        "      <td>-0.137458</td>\n",
182 |        "      <td>0.141267</td>\n",
183 |        "      <td>-0.206010</td>\n",
184 |        "      <td>0.502292</td>\n",
185 |        "      <td>0.219422</td>\n",
186 |        "      <td>0.215153</td>\n",
187 |        "      <td>69.99</td>\n",
188 |        "      <td>0</td>\n",
189 |        "    </tr>\n",
190 |        "  </tbody>\n",
191 |        "</table>\n",
192 |        "<p>5 rows × 31 columns</p>\n",
193 |        "</div>"
194 |       ],
195 |       "text/plain": [
196 |        "   Time        V1        V2        V3        V4        V5        V6        V7  \\\n",
197 |        "0   0.0 -1.359807 -0.072781  2.536347  1.378155 -0.338321  0.462388  0.239599   \n",
198 |        "1   0.0  1.191857  0.266151  0.166480  0.448154  0.060018 -0.082361 -0.078803   \n",
199 |        "2   1.0 -1.358354 -1.340163  1.773209  0.379780 -0.503198  1.800499  0.791461   \n",
200 |        "3   1.0 -0.966272 -0.185226  1.792993 -0.863291 -0.010309  1.247203  0.237609   \n",
201 |        "4   2.0 -1.158233  0.877737  1.548718  0.403034 -0.407193  0.095921  0.592941   \n",
202 |        "\n",
203 |        "         V8        V9  ...       V21       V22       V23       V24       V25  \\\n",
204 |        "0  0.098698  0.363787  ... -0.018307  0.277838 -0.110474  0.066928  0.128539   \n",
205 |        "1  0.085102 -0.255425  ... -0.225775 -0.638672  0.101288 -0.339846  0.167170   \n",
206 |        "2  0.247676 -1.514654  ...  0.247998  0.771679  0.909412 -0.689281 -0.327642   \n",
207 |        "3  0.377436 -1.387024  ... -0.108300  0.005274 -0.190321 -1.175575  0.647376   \n",
208 |        "4 -0.270533  0.817739  ... -0.009431  0.798278 -0.137458  0.141267 -0.206010   \n",
209 |        "\n",
210 |        "        V26       V27       V28  Amount  Class  \n",
211 |        "0 -0.189115  0.133558 -0.021053  149.62      0  \n",
212 |        "1  0.125895 -0.008983  0.014724    2.69      0  \n",
213 |        "2 -0.139097 -0.055353 -0.059752  378.66      0  \n",
214 |        "3 -0.221929  0.062723  0.061458  123.50      0  \n",
215 |        "4  0.502292  0.219422  0.215153   69.99      0  \n",
216 |        "\n",
217 |        "[5 rows x 31 columns]"
218 |       ]
219 |      },
220 |      "execution_count": 2,
221 |      "metadata": {},
222 |      "output_type": "execute_result"
223 |     }
224 |    ],
225 |    "source": [
226 |     "#import the dataset and visualize the dataset\n",
227 |     "dataset = pd.read_csv('./dataset/creditcard.csv')\n",
228 |     "dataset.head()"
229 |    ]
230 |   },
231 |   {
232 |    "cell_type": "code",
233 |    "execution_count": 3,
234 |    "metadata": {},
235 |    "outputs": [
236 |     {
237 |      "data": {
238 |       "text/plain": [
239 |        "<matplotlib.axes._subplots.AxesSubplot at 0x7f733b809730>"
240 |       ]
241 |      },
242 |      "execution_count": 3,
243 |      "metadata": {},
244 |      "output_type": "execute_result"
245 |     },
246 |     {
247 |      "data": {
248 |       "image/png": "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\n",
249 |       "text/plain": [
250 |        "<Figure size 432x288 with 1 Axes>"
251 |       ]
252 |      },
253 |      "metadata": {
254 |       "needs_background": "light"
255 |      },
256 |      "output_type": "display_data"
257 |     }
258 |    ],
259 |    "source": [
260 |     "#visualize the target class 'Class'\n",
261 |     "sns.countplot(x='Class', data=dataset)"
262 |    ]
263 |   },
264 |   {
265 |    "cell_type": "code",
266 |    "execution_count": 4,
267 |    "metadata": {},
268 |    "outputs": [],
269 |    "source": [
270 |     "#seperating positive and negative classes\n",
271 |     "positiveDataset = dataset.loc[dataset['Class'] == 1]\n",
272 |     "negativeDataset = dataset.loc[dataset['Class'] == 0]"
273 |    ]
274 |   },
275 |   {
276 |    "cell_type": "code",
277 |    "execution_count": 5,
278 |    "metadata": {},
279 |    "outputs": [],
280 |    "source": [
281 |     "#creating training and testing set with negative class split 1:1 and positive class split 4:1, also keeping random_state constant so that all splits are same\n",
282 |     "positiveTrain, positiveTest = tts(positiveDataset, test_size=0.2, random_state=21)\n",
283 |     "negativeTrain, negativeTest = tts(negativeDataset, test_size=0.5)\n",
284 |     "trainDataset = positiveTrain.append(negativeTrain)\n",
285 |     "testDataset = positiveTest.append(negativeTest)"
286 |    ]
287 |   },
288 |   {
289 |    "cell_type": "code",
290 |    "execution_count": 6,
291 |    "metadata": {},
292 |    "outputs": [],
293 |    "source": [
294 |     "#create Regression object and scale the dataset\n",
295 |     "classifier = LogisticRegression(random_state=21)\n",
296 |     "yTrain = trainDataset['Class']\n",
297 |     "yTest = testDataset['Class']\n",
298 |     "xTrain = trainDataset.drop(columns=['Class'])\n",
299 |     "xTest = testDataset.drop(columns=['Class'])\n",
300 |     "scaler = StandardScaler()\n",
301 |     "xTrain = scaler.fit_transform(xTrain)\n",
302 |     "xTest = scaler.fit_transform(xTest)"
303 |    ]
304 |   },
305 |   {
306 |    "cell_type": "code",
307 |    "execution_count": 7,
308 |    "metadata": {},
309 |    "outputs": [
310 |     {
311 |      "data": {
312 |       "text/plain": [
313 |        "LogisticRegression(random_state=21)"
314 |       ]
315 |      },
316 |      "execution_count": 7,
317 |      "metadata": {},
318 |      "output_type": "execute_result"
319 |     }
320 |    ],
321 |    "source": [
322 |     "#fit the dataset to the train values\n",
323 |     "classifier.fit(xTrain, yTrain)"
324 |    ]
325 |   },
326 |   {
327 |    "cell_type": "code",
328 |    "execution_count": 8,
329 |    "metadata": {},
330 |    "outputs": [
331 |     {
332 |      "name": "stdout",
333 |      "output_type": "stream",
334 |      "text": [
335 |       "              precision    recall  f1-score   support\n",
336 |       "\n",
337 |       "           0       1.00      1.00      1.00    142157\n",
338 |       "           1       0.91      0.72      0.80       393\n",
339 |       "\n",
340 |       "    accuracy                           1.00    142550\n",
341 |       "   macro avg       0.95      0.86      0.90    142550\n",
342 |       "weighted avg       1.00      1.00      1.00    142550\n",
343 |       "\n",
344 |       "ROC AUC Score:  0.8574078786596213\n"
345 |      ]
346 |     }
347 |    ],
348 |    "source": [
349 |     "#predict the model on the train values and check results\n",
350 |     "predTrain = classifier.predict(xTrain)\n",
351 |     "print(classification_report(yTrain, predTrain))\n",
352 |     "print('ROC AUC Score: ',roc(yTrain, predTrain))"
353 |    ]
354 |   },
355 |   {
356 |    "cell_type": "code",
357 |    "execution_count": 9,
358 |    "metadata": {},
359 |    "outputs": [
360 |     {
361 |      "name": "stdout",
362 |      "output_type": "stream",
363 |      "text": [
364 |       "              precision    recall  f1-score   support\n",
365 |       "\n",
366 |       "           0       1.00      1.00      1.00    142158\n",
367 |       "           1       0.66      0.76      0.70        99\n",
368 |       "\n",
369 |       "    accuracy                           1.00    142257\n",
370 |       "   macro avg       0.83      0.88      0.85    142257\n",
371 |       "weighted avg       1.00      1.00      1.00    142257\n",
372 |       "\n",
373 |       "ROC AUC Score:  0.8786507074714562\n"
374 |      ]
375 |     }
376 |    ],
377 |    "source": [
378 |     "#predict test values and check results\n",
379 |     "predTest = classifier.predict(xTest)\n",
380 |     "print(classification_report(yTest, predTest))\n",
381 |     "print('ROC AUC Score: ',roc(yTest, predTest))"
382 |    ]
383 |   }
384 |  ],
385 |  "metadata": {
386 |   "kernelspec": {
387 |    "display_name": "Python 3",
388 |    "language": "python",
389 |    "name": "python3"
390 |   },
391 |   "language_info": {
392 |    "codemirror_mode": {
393 |     "name": "ipython",
394 |     "version": 3
395 |    },
396 |    "file_extension": ".py",
397 |    "mimetype": "text/x-python",
398 |    "name": "python",
399 |    "nbconvert_exporter": "python",
400 |    "pygments_lexer": "ipython3",
401 |    "version": "3.8.3"
402 |   }
403 |  },
404 |  "nbformat": 4,
405 |  "nbformat_minor": 4
406 | }
407 | 


--------------------------------------------------------------------------------
/Random Forest Classifier.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 1,
  6 |    "metadata": {},
  7 |    "outputs": [],
  8 |    "source": [
  9 |     "#import important libraries\n",
 10 |     "import pandas as pd\n",
 11 |     "import numpy as np\n",
 12 |     "import seaborn as sns\n",
 13 |     "from sklearn.metrics import classification_report\n",
 14 |     "from sklearn.metrics import roc_auc_score as roc\n",
 15 |     "from sklearn.model_selection import train_test_split as tts\n",
 16 |     "from sklearn.preprocessing import StandardScaler\n",
 17 |     "from sklearn.ensemble import RandomForestClassifier"
 18 |    ]
 19 |   },
 20 |   {
 21 |    "cell_type": "code",
 22 |    "execution_count": 2,
 23 |    "metadata": {},
 24 |    "outputs": [
 25 |     {
 26 |      "data": {
 27 |       "text/html": [
 28 |        "<div>\n",
 29 |        "<style scoped>\n",
 30 |        "    .dataframe tbody tr th:only-of-type {\n",
 31 |        "        vertical-align: middle;\n",
 32 |        "    }\n",
 33 |        "\n",
 34 |        "    .dataframe tbody tr th {\n",
 35 |        "        vertical-align: top;\n",
 36 |        "    }\n",
 37 |        "\n",
 38 |        "    .dataframe thead th {\n",
 39 |        "        text-align: right;\n",
 40 |        "    }\n",
 41 |        "</style>\n",
 42 |        "<table border=\"1\" class=\"dataframe\">\n",
 43 |        "  <thead>\n",
 44 |        "    <tr style=\"text-align: right;\">\n",
 45 |        "      <th></th>\n",
 46 |        "      <th>Time</th>\n",
 47 |        "      <th>V1</th>\n",
 48 |        "      <th>V2</th>\n",
 49 |        "      <th>V3</th>\n",
 50 |        "      <th>V4</th>\n",
 51 |        "      <th>V5</th>\n",
 52 |        "      <th>V6</th>\n",
 53 |        "      <th>V7</th>\n",
 54 |        "      <th>V8</th>\n",
 55 |        "      <th>V9</th>\n",
 56 |        "      <th>...</th>\n",
 57 |        "      <th>V21</th>\n",
 58 |        "      <th>V22</th>\n",
 59 |        "      <th>V23</th>\n",
 60 |        "      <th>V24</th>\n",
 61 |        "      <th>V25</th>\n",
 62 |        "      <th>V26</th>\n",
 63 |        "      <th>V27</th>\n",
 64 |        "      <th>V28</th>\n",
 65 |        "      <th>Amount</th>\n",
 66 |        "      <th>Class</th>\n",
 67 |        "    </tr>\n",
 68 |        "  </thead>\n",
 69 |        "  <tbody>\n",
 70 |        "    <tr>\n",
 71 |        "      <th>0</th>\n",
 72 |        "      <td>0.0</td>\n",
 73 |        "      <td>-1.359807</td>\n",
 74 |        "      <td>-0.072781</td>\n",
 75 |        "      <td>2.536347</td>\n",
 76 |        "      <td>1.378155</td>\n",
 77 |        "      <td>-0.338321</td>\n",
 78 |        "      <td>0.462388</td>\n",
 79 |        "      <td>0.239599</td>\n",
 80 |        "      <td>0.098698</td>\n",
 81 |        "      <td>0.363787</td>\n",
 82 |        "      <td>...</td>\n",
 83 |        "      <td>-0.018307</td>\n",
 84 |        "      <td>0.277838</td>\n",
 85 |        "      <td>-0.110474</td>\n",
 86 |        "      <td>0.066928</td>\n",
 87 |        "      <td>0.128539</td>\n",
 88 |        "      <td>-0.189115</td>\n",
 89 |        "      <td>0.133558</td>\n",
 90 |        "      <td>-0.021053</td>\n",
 91 |        "      <td>149.62</td>\n",
 92 |        "      <td>0</td>\n",
 93 |        "    </tr>\n",
 94 |        "    <tr>\n",
 95 |        "      <th>1</th>\n",
 96 |        "      <td>0.0</td>\n",
 97 |        "      <td>1.191857</td>\n",
 98 |        "      <td>0.266151</td>\n",
 99 |        "      <td>0.166480</td>\n",
100 |        "      <td>0.448154</td>\n",
101 |        "      <td>0.060018</td>\n",
102 |        "      <td>-0.082361</td>\n",
103 |        "      <td>-0.078803</td>\n",
104 |        "      <td>0.085102</td>\n",
105 |        "      <td>-0.255425</td>\n",
106 |        "      <td>...</td>\n",
107 |        "      <td>-0.225775</td>\n",
108 |        "      <td>-0.638672</td>\n",
109 |        "      <td>0.101288</td>\n",
110 |        "      <td>-0.339846</td>\n",
111 |        "      <td>0.167170</td>\n",
112 |        "      <td>0.125895</td>\n",
113 |        "      <td>-0.008983</td>\n",
114 |        "      <td>0.014724</td>\n",
115 |        "      <td>2.69</td>\n",
116 |        "      <td>0</td>\n",
117 |        "    </tr>\n",
118 |        "    <tr>\n",
119 |        "      <th>2</th>\n",
120 |        "      <td>1.0</td>\n",
121 |        "      <td>-1.358354</td>\n",
122 |        "      <td>-1.340163</td>\n",
123 |        "      <td>1.773209</td>\n",
124 |        "      <td>0.379780</td>\n",
125 |        "      <td>-0.503198</td>\n",
126 |        "      <td>1.800499</td>\n",
127 |        "      <td>0.791461</td>\n",
128 |        "      <td>0.247676</td>\n",
129 |        "      <td>-1.514654</td>\n",
130 |        "      <td>...</td>\n",
131 |        "      <td>0.247998</td>\n",
132 |        "      <td>0.771679</td>\n",
133 |        "      <td>0.909412</td>\n",
134 |        "      <td>-0.689281</td>\n",
135 |        "      <td>-0.327642</td>\n",
136 |        "      <td>-0.139097</td>\n",
137 |        "      <td>-0.055353</td>\n",
138 |        "      <td>-0.059752</td>\n",
139 |        "      <td>378.66</td>\n",
140 |        "      <td>0</td>\n",
141 |        "    </tr>\n",
142 |        "    <tr>\n",
143 |        "      <th>3</th>\n",
144 |        "      <td>1.0</td>\n",
145 |        "      <td>-0.966272</td>\n",
146 |        "      <td>-0.185226</td>\n",
147 |        "      <td>1.792993</td>\n",
148 |        "      <td>-0.863291</td>\n",
149 |        "      <td>-0.010309</td>\n",
150 |        "      <td>1.247203</td>\n",
151 |        "      <td>0.237609</td>\n",
152 |        "      <td>0.377436</td>\n",
153 |        "      <td>-1.387024</td>\n",
154 |        "      <td>...</td>\n",
155 |        "      <td>-0.108300</td>\n",
156 |        "      <td>0.005274</td>\n",
157 |        "      <td>-0.190321</td>\n",
158 |        "      <td>-1.175575</td>\n",
159 |        "      <td>0.647376</td>\n",
160 |        "      <td>-0.221929</td>\n",
161 |        "      <td>0.062723</td>\n",
162 |        "      <td>0.061458</td>\n",
163 |        "      <td>123.50</td>\n",
164 |        "      <td>0</td>\n",
165 |        "    </tr>\n",
166 |        "    <tr>\n",
167 |        "      <th>4</th>\n",
168 |        "      <td>2.0</td>\n",
169 |        "      <td>-1.158233</td>\n",
170 |        "      <td>0.877737</td>\n",
171 |        "      <td>1.548718</td>\n",
172 |        "      <td>0.403034</td>\n",
173 |        "      <td>-0.407193</td>\n",
174 |        "      <td>0.095921</td>\n",
175 |        "      <td>0.592941</td>\n",
176 |        "      <td>-0.270533</td>\n",
177 |        "      <td>0.817739</td>\n",
178 |        "      <td>...</td>\n",
179 |        "      <td>-0.009431</td>\n",
180 |        "      <td>0.798278</td>\n",
181 |        "      <td>-0.137458</td>\n",
182 |        "      <td>0.141267</td>\n",
183 |        "      <td>-0.206010</td>\n",
184 |        "      <td>0.502292</td>\n",
185 |        "      <td>0.219422</td>\n",
186 |        "      <td>0.215153</td>\n",
187 |        "      <td>69.99</td>\n",
188 |        "      <td>0</td>\n",
189 |        "    </tr>\n",
190 |        "  </tbody>\n",
191 |        "</table>\n",
192 |        "<p>5 rows × 31 columns</p>\n",
193 |        "</div>"
194 |       ],
195 |       "text/plain": [
196 |        "   Time        V1        V2        V3        V4        V5        V6        V7  \\\n",
197 |        "0   0.0 -1.359807 -0.072781  2.536347  1.378155 -0.338321  0.462388  0.239599   \n",
198 |        "1   0.0  1.191857  0.266151  0.166480  0.448154  0.060018 -0.082361 -0.078803   \n",
199 |        "2   1.0 -1.358354 -1.340163  1.773209  0.379780 -0.503198  1.800499  0.791461   \n",
200 |        "3   1.0 -0.966272 -0.185226  1.792993 -0.863291 -0.010309  1.247203  0.237609   \n",
201 |        "4   2.0 -1.158233  0.877737  1.548718  0.403034 -0.407193  0.095921  0.592941   \n",
202 |        "\n",
203 |        "         V8        V9  ...       V21       V22       V23       V24       V25  \\\n",
204 |        "0  0.098698  0.363787  ... -0.018307  0.277838 -0.110474  0.066928  0.128539   \n",
205 |        "1  0.085102 -0.255425  ... -0.225775 -0.638672  0.101288 -0.339846  0.167170   \n",
206 |        "2  0.247676 -1.514654  ...  0.247998  0.771679  0.909412 -0.689281 -0.327642   \n",
207 |        "3  0.377436 -1.387024  ... -0.108300  0.005274 -0.190321 -1.175575  0.647376   \n",
208 |        "4 -0.270533  0.817739  ... -0.009431  0.798278 -0.137458  0.141267 -0.206010   \n",
209 |        "\n",
210 |        "        V26       V27       V28  Amount  Class  \n",
211 |        "0 -0.189115  0.133558 -0.021053  149.62      0  \n",
212 |        "1  0.125895 -0.008983  0.014724    2.69      0  \n",
213 |        "2 -0.139097 -0.055353 -0.059752  378.66      0  \n",
214 |        "3 -0.221929  0.062723  0.061458  123.50      0  \n",
215 |        "4  0.502292  0.219422  0.215153   69.99      0  \n",
216 |        "\n",
217 |        "[5 rows x 31 columns]"
218 |       ]
219 |      },
220 |      "execution_count": 2,
221 |      "metadata": {},
222 |      "output_type": "execute_result"
223 |     }
224 |    ],
225 |    "source": [
226 |     "#import the dataset and visualize the dataset\n",
227 |     "dataset = pd.read_csv('./dataset/creditcard.csv')\n",
228 |     "dataset.head()"
229 |    ]
230 |   },
231 |   {
232 |    "cell_type": "code",
233 |    "execution_count": 3,
234 |    "metadata": {},
235 |    "outputs": [
236 |     {
237 |      "data": {
238 |       "text/plain": [
239 |        "<matplotlib.axes._subplots.AxesSubplot at 0x7fee72144b20>"
240 |       ]
241 |      },
242 |      "execution_count": 3,
243 |      "metadata": {},
244 |      "output_type": "execute_result"
245 |     },
246 |     {
247 |      "data": {
248 |       "image/png": "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\n",
249 |       "text/plain": [
250 |        "<Figure size 432x288 with 1 Axes>"
251 |       ]
252 |      },
253 |      "metadata": {
254 |       "needs_background": "light"
255 |      },
256 |      "output_type": "display_data"
257 |     }
258 |    ],
259 |    "source": [
260 |     "#visualize the target class 'Class'\n",
261 |     "sns.countplot(x='Class', data=dataset)"
262 |    ]
263 |   },
264 |   {
265 |    "cell_type": "code",
266 |    "execution_count": 4,
267 |    "metadata": {},
268 |    "outputs": [],
269 |    "source": [
270 |     "#seperating positive and negative classes\n",
271 |     "positiveDataset = dataset.loc[dataset['Class'] == 1]\n",
272 |     "negativeDataset = dataset.loc[dataset['Class'] == 0]"
273 |    ]
274 |   },
275 |   {
276 |    "cell_type": "code",
277 |    "execution_count": 5,
278 |    "metadata": {},
279 |    "outputs": [],
280 |    "source": [
281 |     "#creating training and testing set with negative class split 1:1 and positive class split 4:1, also keeping random_state constant so that all splits are same\n",
282 |     "positiveTrain, positiveTest = tts(positiveDataset, test_size=0.2, random_state=21)\n",
283 |     "negativeTrain, negativeTest = tts(negativeDataset, test_size=0.5)\n",
284 |     "trainDataset = positiveTrain.append(negativeTrain)\n",
285 |     "testDataset = positiveTest.append(negativeTest)"
286 |    ]
287 |   },
288 |   {
289 |    "cell_type": "code",
290 |    "execution_count": 6,
291 |    "metadata": {},
292 |    "outputs": [],
293 |    "source": [
294 |     "#create Regression object and scale the dataset\n",
295 |     "classifier = RandomForestClassifier(n_estimators=500, max_depth=3)\n",
296 |     "yTrain = trainDataset['Class']\n",
297 |     "yTest = testDataset['Class']\n",
298 |     "xTrain = trainDataset.drop(columns=['Class'])\n",
299 |     "xTest = testDataset.drop(columns=['Class'])\n",
300 |     "scaler = StandardScaler()\n",
301 |     "xTrain = scaler.fit_transform(xTrain)\n",
302 |     "xTest = scaler.fit_transform(xTest)"
303 |    ]
304 |   },
305 |   {
306 |    "cell_type": "code",
307 |    "execution_count": 7,
308 |    "metadata": {},
309 |    "outputs": [
310 |     {
311 |      "data": {
312 |       "text/plain": [
313 |        "RandomForestClassifier(max_depth=3, n_estimators=500)"
314 |       ]
315 |      },
316 |      "execution_count": 7,
317 |      "metadata": {},
318 |      "output_type": "execute_result"
319 |     }
320 |    ],
321 |    "source": [
322 |     "#fit the dataset to the train values\n",
323 |     "classifier.fit(xTrain, yTrain)"
324 |    ]
325 |   },
326 |   {
327 |    "cell_type": "code",
328 |    "execution_count": 8,
329 |    "metadata": {},
330 |    "outputs": [
331 |     {
332 |      "name": "stdout",
333 |      "output_type": "stream",
334 |      "text": [
335 |       "              precision    recall  f1-score   support\n",
336 |       "\n",
337 |       "           0       1.00      1.00      1.00    142157\n",
338 |       "           1       0.93      0.68      0.79       393\n",
339 |       "\n",
340 |       "    accuracy                           1.00    142550\n",
341 |       "   macro avg       0.96      0.84      0.89    142550\n",
342 |       "weighted avg       1.00      1.00      1.00    142550\n",
343 |       "\n",
344 |       "ROC AUC Score:  0.8421688409909691\n"
345 |      ]
346 |     }
347 |    ],
348 |    "source": [
349 |     "#predict the model on the train values and check results\n",
350 |     "predTrain = classifier.predict(xTrain)\n",
351 |     "print(classification_report(yTrain, predTrain))\n",
352 |     "print('ROC AUC Score: ',roc(yTrain, predTrain))"
353 |    ]
354 |   },
355 |   {
356 |    "cell_type": "code",
357 |    "execution_count": 9,
358 |    "metadata": {},
359 |    "outputs": [
360 |     {
361 |      "name": "stdout",
362 |      "output_type": "stream",
363 |      "text": [
364 |       "              precision    recall  f1-score   support\n",
365 |       "\n",
366 |       "           0       1.00      1.00      1.00    142158\n",
367 |       "           1       0.69      0.75      0.71        99\n",
368 |       "\n",
369 |       "    accuracy                           1.00    142257\n",
370 |       "   macro avg       0.84      0.87      0.86    142257\n",
371 |       "weighted avg       1.00      1.00      1.00    142257\n",
372 |       "\n",
373 |       "ROC AUC Score:  0.8736177884871592\n"
374 |      ]
375 |     }
376 |    ],
377 |    "source": [
378 |     "#predict test values and check results\n",
379 |     "predTest = classifier.predict(xTest)\n",
380 |     "print(classification_report(yTest, predTest))\n",
381 |     "print('ROC AUC Score: ',roc(yTest, predTest))"
382 |    ]
383 |   }
384 |  ],
385 |  "metadata": {
386 |   "kernelspec": {
387 |    "display_name": "Python 3",
388 |    "language": "python",
389 |    "name": "python3"
390 |   },
391 |   "language_info": {
392 |    "codemirror_mode": {
393 |     "name": "ipython",
394 |     "version": 3
395 |    },
396 |    "file_extension": ".py",
397 |    "mimetype": "text/x-python",
398 |    "name": "python",
399 |    "nbconvert_exporter": "python",
400 |    "pygments_lexer": "ipython3",
401 |    "version": "3.8.3"
402 |   }
403 |  },
404 |  "nbformat": 4,
405 |  "nbformat_minor": 4
406 | }
407 | 


--------------------------------------------------------------------------------
/Neural Network Classifier.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 1,
  6 |    "metadata": {},
  7 |    "outputs": [],
  8 |    "source": [
  9 |     "#import important libraries\n",
 10 |     "import pandas as pd\n",
 11 |     "import numpy as np\n",
 12 |     "import seaborn as sns\n",
 13 |     "from sklearn.metrics import classification_report\n",
 14 |     "from sklearn.metrics import roc_auc_score as roc\n",
 15 |     "from sklearn.model_selection import train_test_split as tts\n",
 16 |     "from sklearn.preprocessing import StandardScaler\n",
 17 |     "import tensorflow as tf\n",
 18 |     "from tensorflow import keras"
 19 |    ]
 20 |   },
 21 |   {
 22 |    "cell_type": "code",
 23 |    "execution_count": 2,
 24 |    "metadata": {},
 25 |    "outputs": [
 26 |     {
 27 |      "data": {
 28 |       "text/html": [
 29 |        "<div>\n",
 30 |        "<style scoped>\n",
 31 |        "    .dataframe tbody tr th:only-of-type {\n",
 32 |        "        vertical-align: middle;\n",
 33 |        "    }\n",
 34 |        "\n",
 35 |        "    .dataframe tbody tr th {\n",
 36 |        "        vertical-align: top;\n",
 37 |        "    }\n",
 38 |        "\n",
 39 |        "    .dataframe thead th {\n",
 40 |        "        text-align: right;\n",
 41 |        "    }\n",
 42 |        "</style>\n",
 43 |        "<table border=\"1\" class=\"dataframe\">\n",
 44 |        "  <thead>\n",
 45 |        "    <tr style=\"text-align: right;\">\n",
 46 |        "      <th></th>\n",
 47 |        "      <th>Time</th>\n",
 48 |        "      <th>V1</th>\n",
 49 |        "      <th>V2</th>\n",
 50 |        "      <th>V3</th>\n",
 51 |        "      <th>V4</th>\n",
 52 |        "      <th>V5</th>\n",
 53 |        "      <th>V6</th>\n",
 54 |        "      <th>V7</th>\n",
 55 |        "      <th>V8</th>\n",
 56 |        "      <th>V9</th>\n",
 57 |        "      <th>...</th>\n",
 58 |        "      <th>V21</th>\n",
 59 |        "      <th>V22</th>\n",
 60 |        "      <th>V23</th>\n",
 61 |        "      <th>V24</th>\n",
 62 |        "      <th>V25</th>\n",
 63 |        "      <th>V26</th>\n",
 64 |        "      <th>V27</th>\n",
 65 |        "      <th>V28</th>\n",
 66 |        "      <th>Amount</th>\n",
 67 |        "      <th>Class</th>\n",
 68 |        "    </tr>\n",
 69 |        "  </thead>\n",
 70 |        "  <tbody>\n",
 71 |        "    <tr>\n",
 72 |        "      <th>0</th>\n",
 73 |        "      <td>0.0</td>\n",
 74 |        "      <td>-1.359807</td>\n",
 75 |        "      <td>-0.072781</td>\n",
 76 |        "      <td>2.536347</td>\n",
 77 |        "      <td>1.378155</td>\n",
 78 |        "      <td>-0.338321</td>\n",
 79 |        "      <td>0.462388</td>\n",
 80 |        "      <td>0.239599</td>\n",
 81 |        "      <td>0.098698</td>\n",
 82 |        "      <td>0.363787</td>\n",
 83 |        "      <td>...</td>\n",
 84 |        "      <td>-0.018307</td>\n",
 85 |        "      <td>0.277838</td>\n",
 86 |        "      <td>-0.110474</td>\n",
 87 |        "      <td>0.066928</td>\n",
 88 |        "      <td>0.128539</td>\n",
 89 |        "      <td>-0.189115</td>\n",
 90 |        "      <td>0.133558</td>\n",
 91 |        "      <td>-0.021053</td>\n",
 92 |        "      <td>149.62</td>\n",
 93 |        "      <td>0</td>\n",
 94 |        "    </tr>\n",
 95 |        "    <tr>\n",
 96 |        "      <th>1</th>\n",
 97 |        "      <td>0.0</td>\n",
 98 |        "      <td>1.191857</td>\n",
 99 |        "      <td>0.266151</td>\n",
100 |        "      <td>0.166480</td>\n",
101 |        "      <td>0.448154</td>\n",
102 |        "      <td>0.060018</td>\n",
103 |        "      <td>-0.082361</td>\n",
104 |        "      <td>-0.078803</td>\n",
105 |        "      <td>0.085102</td>\n",
106 |        "      <td>-0.255425</td>\n",
107 |        "      <td>...</td>\n",
108 |        "      <td>-0.225775</td>\n",
109 |        "      <td>-0.638672</td>\n",
110 |        "      <td>0.101288</td>\n",
111 |        "      <td>-0.339846</td>\n",
112 |        "      <td>0.167170</td>\n",
113 |        "      <td>0.125895</td>\n",
114 |        "      <td>-0.008983</td>\n",
115 |        "      <td>0.014724</td>\n",
116 |        "      <td>2.69</td>\n",
117 |        "      <td>0</td>\n",
118 |        "    </tr>\n",
119 |        "    <tr>\n",
120 |        "      <th>2</th>\n",
121 |        "      <td>1.0</td>\n",
122 |        "      <td>-1.358354</td>\n",
123 |        "      <td>-1.340163</td>\n",
124 |        "      <td>1.773209</td>\n",
125 |        "      <td>0.379780</td>\n",
126 |        "      <td>-0.503198</td>\n",
127 |        "      <td>1.800499</td>\n",
128 |        "      <td>0.791461</td>\n",
129 |        "      <td>0.247676</td>\n",
130 |        "      <td>-1.514654</td>\n",
131 |        "      <td>...</td>\n",
132 |        "      <td>0.247998</td>\n",
133 |        "      <td>0.771679</td>\n",
134 |        "      <td>0.909412</td>\n",
135 |        "      <td>-0.689281</td>\n",
136 |        "      <td>-0.327642</td>\n",
137 |        "      <td>-0.139097</td>\n",
138 |        "      <td>-0.055353</td>\n",
139 |        "      <td>-0.059752</td>\n",
140 |        "      <td>378.66</td>\n",
141 |        "      <td>0</td>\n",
142 |        "    </tr>\n",
143 |        "    <tr>\n",
144 |        "      <th>3</th>\n",
145 |        "      <td>1.0</td>\n",
146 |        "      <td>-0.966272</td>\n",
147 |        "      <td>-0.185226</td>\n",
148 |        "      <td>1.792993</td>\n",
149 |        "      <td>-0.863291</td>\n",
150 |        "      <td>-0.010309</td>\n",
151 |        "      <td>1.247203</td>\n",
152 |        "      <td>0.237609</td>\n",
153 |        "      <td>0.377436</td>\n",
154 |        "      <td>-1.387024</td>\n",
155 |        "      <td>...</td>\n",
156 |        "      <td>-0.108300</td>\n",
157 |        "      <td>0.005274</td>\n",
158 |        "      <td>-0.190321</td>\n",
159 |        "      <td>-1.175575</td>\n",
160 |        "      <td>0.647376</td>\n",
161 |        "      <td>-0.221929</td>\n",
162 |        "      <td>0.062723</td>\n",
163 |        "      <td>0.061458</td>\n",
164 |        "      <td>123.50</td>\n",
165 |        "      <td>0</td>\n",
166 |        "    </tr>\n",
167 |        "    <tr>\n",
168 |        "      <th>4</th>\n",
169 |        "      <td>2.0</td>\n",
170 |        "      <td>-1.158233</td>\n",
171 |        "      <td>0.877737</td>\n",
172 |        "      <td>1.548718</td>\n",
173 |        "      <td>0.403034</td>\n",
174 |        "      <td>-0.407193</td>\n",
175 |        "      <td>0.095921</td>\n",
176 |        "      <td>0.592941</td>\n",
177 |        "      <td>-0.270533</td>\n",
178 |        "      <td>0.817739</td>\n",
179 |        "      <td>...</td>\n",
180 |        "      <td>-0.009431</td>\n",
181 |        "      <td>0.798278</td>\n",
182 |        "      <td>-0.137458</td>\n",
183 |        "      <td>0.141267</td>\n",
184 |        "      <td>-0.206010</td>\n",
185 |        "      <td>0.502292</td>\n",
186 |        "      <td>0.219422</td>\n",
187 |        "      <td>0.215153</td>\n",
188 |        "      <td>69.99</td>\n",
189 |        "      <td>0</td>\n",
190 |        "    </tr>\n",
191 |        "  </tbody>\n",
192 |        "</table>\n",
193 |        "<p>5 rows × 31 columns</p>\n",
194 |        "</div>"
195 |       ],
196 |       "text/plain": [
197 |        "   Time        V1        V2        V3        V4        V5        V6        V7  \\\n",
198 |        "0   0.0 -1.359807 -0.072781  2.536347  1.378155 -0.338321  0.462388  0.239599   \n",
199 |        "1   0.0  1.191857  0.266151  0.166480  0.448154  0.060018 -0.082361 -0.078803   \n",
200 |        "2   1.0 -1.358354 -1.340163  1.773209  0.379780 -0.503198  1.800499  0.791461   \n",
201 |        "3   1.0 -0.966272 -0.185226  1.792993 -0.863291 -0.010309  1.247203  0.237609   \n",
202 |        "4   2.0 -1.158233  0.877737  1.548718  0.403034 -0.407193  0.095921  0.592941   \n",
203 |        "\n",
204 |        "         V8        V9  ...       V21       V22       V23       V24       V25  \\\n",
205 |        "0  0.098698  0.363787  ... -0.018307  0.277838 -0.110474  0.066928  0.128539   \n",
206 |        "1  0.085102 -0.255425  ... -0.225775 -0.638672  0.101288 -0.339846  0.167170   \n",
207 |        "2  0.247676 -1.514654  ...  0.247998  0.771679  0.909412 -0.689281 -0.327642   \n",
208 |        "3  0.377436 -1.387024  ... -0.108300  0.005274 -0.190321 -1.175575  0.647376   \n",
209 |        "4 -0.270533  0.817739  ... -0.009431  0.798278 -0.137458  0.141267 -0.206010   \n",
210 |        "\n",
211 |        "        V26       V27       V28  Amount  Class  \n",
212 |        "0 -0.189115  0.133558 -0.021053  149.62      0  \n",
213 |        "1  0.125895 -0.008983  0.014724    2.69      0  \n",
214 |        "2 -0.139097 -0.055353 -0.059752  378.66      0  \n",
215 |        "3 -0.221929  0.062723  0.061458  123.50      0  \n",
216 |        "4  0.502292  0.219422  0.215153   69.99      0  \n",
217 |        "\n",
218 |        "[5 rows x 31 columns]"
219 |       ]
220 |      },
221 |      "execution_count": 2,
222 |      "metadata": {},
223 |      "output_type": "execute_result"
224 |     }
225 |    ],
226 |    "source": [
227 |     "#import the dataset and visualize the dataset\n",
228 |     "dataset = pd.read_csv('./dataset/creditcard.csv')\n",
229 |     "dataset.head()"
230 |    ]
231 |   },
232 |   {
233 |    "cell_type": "code",
234 |    "execution_count": 3,
235 |    "metadata": {},
236 |    "outputs": [
237 |     {
238 |      "data": {
239 |       "text/plain": [
240 |        "<matplotlib.axes._subplots.AxesSubplot at 0x7f491c2d14c0>"
241 |       ]
242 |      },
243 |      "execution_count": 3,
244 |      "metadata": {},
245 |      "output_type": "execute_result"
246 |     },
247 |     {
248 |      "data": {
249 |       "image/png": "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\n",
250 |       "text/plain": [
251 |        "<Figure size 432x288 with 1 Axes>"
252 |       ]
253 |      },
254 |      "metadata": {
255 |       "needs_background": "light"
256 |      },
257 |      "output_type": "display_data"
258 |     }
259 |    ],
260 |    "source": [
261 |     "#visualize the target class 'Class'\n",
262 |     "sns.countplot(x='Class', data=dataset)"
263 |    ]
264 |   },
265 |   {
266 |    "cell_type": "code",
267 |    "execution_count": 4,
268 |    "metadata": {},
269 |    "outputs": [],
270 |    "source": [
271 |     "#seperating positive and negative classes\n",
272 |     "positiveDataset = dataset.loc[dataset['Class'] == 1]\n",
273 |     "negativeDataset = dataset.loc[dataset['Class'] == 0]"
274 |    ]
275 |   },
276 |   {
277 |    "cell_type": "code",
278 |    "execution_count": 5,
279 |    "metadata": {},
280 |    "outputs": [],
281 |    "source": [
282 |     "#creating training and testing set with negative class split 1:1 and positive class split 4:1, also keeping random_state constant so that all splits are same\n",
283 |     "positiveTrain, positiveTest = tts(positiveDataset, test_size=0.2, random_state=21)\n",
284 |     "negativeTrain, negativeTest = tts(negativeDataset, test_size=0.5)\n",
285 |     "trainDataset = positiveTrain.append(negativeTrain)\n",
286 |     "testDataset = positiveTest.append(negativeTest)"
287 |    ]
288 |   },
289 |   {
290 |    "cell_type": "code",
291 |    "execution_count": 6,
292 |    "metadata": {},
293 |    "outputs": [],
294 |    "source": [
295 |     "#create classifier\n",
296 |     "def classifierCreator():\n",
297 |     "    clf = keras.models.Sequential()\n",
298 |     "    clf.add(keras.layers.Dense(10, activation='relu'))\n",
299 |     "    clf.add(keras.layers.Dense(5, activation='relu'))\n",
300 |     "    clf.add(keras.layers.Dense(1, activation='sigmoid'))\n",
301 |     "    return clf"
302 |    ]
303 |   },
304 |   {
305 |    "cell_type": "code",
306 |    "execution_count": 7,
307 |    "metadata": {},
308 |    "outputs": [],
309 |    "source": [
310 |     "#create Classifier object and scale the dataset\n",
311 |     "classifier = classifierCreator()\n",
312 |     "classifier.compile(loss='binary_crossentropy', optimizer='sgd')\n",
313 |     "yTrain = trainDataset['Class']\n",
314 |     "yTest = testDataset['Class']\n",
315 |     "xTrain = trainDataset.drop(columns=['Class'])\n",
316 |     "xTest = testDataset.drop(columns=['Class'])\n",
317 |     "scaler = StandardScaler()\n",
318 |     "xTrain = scaler.fit_transform(xTrain)\n",
319 |     "xTest = scaler.fit_transform(xTest)"
320 |    ]
321 |   },
322 |   {
323 |    "cell_type": "code",
324 |    "execution_count": 26,
325 |    "metadata": {},
326 |    "outputs": [],
327 |    "source": [
328 |     "#fit the dataset to the train values\n",
329 |     "weights = {0:1, 1:1.5}\n",
330 |     "history = classifier.fit(xTrain, yTrain, class_weight=weights, epochs=15, verbose=0)"
331 |    ]
332 |   },
333 |   {
334 |    "cell_type": "code",
335 |    "execution_count": 27,
336 |    "metadata": {},
337 |    "outputs": [
338 |     {
339 |      "name": "stdout",
340 |      "output_type": "stream",
341 |      "text": [
342 |       "              precision    recall  f1-score   support\n",
343 |       "\n",
344 |       "           0       1.00      1.00      1.00    142157\n",
345 |       "           1       0.86      0.85      0.86       393\n",
346 |       "\n",
347 |       "    accuracy                           1.00    142550\n",
348 |       "   macro avg       0.93      0.93      0.93    142550\n",
349 |       "weighted avg       1.00      1.00      1.00    142550\n",
350 |       "\n",
351 |       "ROC AUC Score:  0.9272909851794332\n"
352 |      ]
353 |     }
354 |    ],
355 |    "source": [
356 |     "#predict the model on the train values and check results\n",
357 |     "predTrain = classifier.predict_classes(xTrain)\n",
358 |     "print(classification_report(yTrain, predTrain))\n",
359 |     "print('ROC AUC Score: ',roc(yTrain, predTrain))"
360 |    ]
361 |   },
362 |   {
363 |    "cell_type": "code",
364 |    "execution_count": 28,
365 |    "metadata": {},
366 |    "outputs": [
367 |     {
368 |      "name": "stdout",
369 |      "output_type": "stream",
370 |      "text": [
371 |       "              precision    recall  f1-score   support\n",
372 |       "\n",
373 |       "           0       1.00      1.00      1.00    142158\n",
374 |       "           1       0.58      0.83      0.68        99\n",
375 |       "\n",
376 |       "    accuracy                           1.00    142257\n",
377 |       "   macro avg       0.79      0.91      0.84    142257\n",
378 |       "weighted avg       1.00      1.00      1.00    142257\n",
379 |       "\n",
380 |       "ROC AUC Score:  0.9139338985601595\n"
381 |      ]
382 |     }
383 |    ],
384 |    "source": [
385 |     "#predict test values and check results\n",
386 |     "predTest = classifier.predict_classes(xTest)\n",
387 |     "print(classification_report(yTest, predTest))\n",
388 |     "print('ROC AUC Score: ',roc(yTest, predTest))"
389 |    ]
390 |   },
391 |   {
392 |    "cell_type": "code",
393 |    "execution_count": 32,
394 |    "metadata": {},
395 |    "outputs": [
396 |     {
397 |      "name": "stdout",
398 |      "output_type": "stream",
399 |      "text": [
400 |       "Ratio of weights: 1: 1.01\n",
401 |       "              precision    recall  f1-score   support\n",
402 |       "\n",
403 |       "           0       1.00      1.00      1.00    142157\n",
404 |       "           1       0.91      0.78      0.84       393\n",
405 |       "\n",
406 |       "    accuracy                           1.00    142550\n",
407 |       "   macro avg       0.95      0.89      0.92    142550\n",
408 |       "weighted avg       1.00      1.00      1.00    142550\n",
409 |       "\n",
410 |       "ROC AUC Score:  0.887928160852726\n",
411 |       "              precision    recall  f1-score   support\n",
412 |       "\n",
413 |       "           0       1.00      1.00      1.00    142158\n",
414 |       "           1       0.74      0.80      0.77        99\n",
415 |       "\n",
416 |       "    accuracy                           1.00    142257\n",
417 |       "   macro avg       0.87      0.90      0.88    142257\n",
418 |       "weighted avg       1.00      1.00      1.00    142257\n",
419 |       "\n",
420 |       "ROC AUC Score:  0.8988914170191341\n",
421 |       "Ratio of weights: 1: 1.02\n",
422 |       "              precision    recall  f1-score   support\n",
423 |       "\n",
424 |       "           0       1.00      1.00      1.00    142157\n",
425 |       "           1       0.90      0.81      0.85       393\n",
426 |       "\n",
427 |       "    accuracy                           1.00    142550\n",
428 |       "   macro avg       0.95      0.90      0.92    142550\n",
429 |       "weighted avg       1.00      1.00      1.00    142550\n",
430 |       "\n",
431 |       "ROC AUC Score:  0.9031812674733117\n",
432 |       "              precision    recall  f1-score   support\n",
433 |       "\n",
434 |       "           0       1.00      1.00      1.00    142158\n",
435 |       "           1       0.72      0.81      0.76        99\n",
436 |       "\n",
437 |       "    accuracy                           1.00    142257\n",
438 |       "   macro avg       0.86      0.90      0.88    142257\n",
439 |       "weighted avg       1.00      1.00      1.00    142257\n",
440 |       "\n",
441 |       "ROC AUC Score:  0.9039313704299141\n",
442 |       "Ratio of weights: 1: 1.03\n"
443 |      ]
444 |     },
445 |     {
446 |      "name": "stderr",
447 |      "output_type": "stream",
448 |      "text": [
449 |       "/home/azhanmohammed/anaconda3/lib/python3.8/site-packages/sklearn/metrics/_classification.py:1221: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
450 |       "  _warn_prf(average, modifier, msg_start, len(result))\n"
451 |      ]
452 |     },
453 |     {
454 |      "name": "stdout",
455 |      "output_type": "stream",
456 |      "text": [
457 |       "              precision    recall  f1-score   support\n",
458 |       "\n",
459 |       "           0       1.00      1.00      1.00    142157\n",
460 |       "           1       0.00      0.00      0.00       393\n",
461 |       "\n",
462 |       "    accuracy                           1.00    142550\n",
463 |       "   macro avg       0.50      0.50      0.50    142550\n",
464 |       "weighted avg       0.99      1.00      1.00    142550\n",
465 |       "\n",
466 |       "ROC AUC Score:  0.5\n"
467 |      ]
468 |     },
469 |     {
470 |      "name": "stderr",
471 |      "output_type": "stream",
472 |      "text": [
473 |       "/home/azhanmohammed/anaconda3/lib/python3.8/site-packages/sklearn/metrics/_classification.py:1221: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
474 |       "  _warn_prf(average, modifier, msg_start, len(result))\n"
475 |      ]
476 |     },
477 |     {
478 |      "name": "stdout",
479 |      "output_type": "stream",
480 |      "text": [
481 |       "              precision    recall  f1-score   support\n",
482 |       "\n",
483 |       "           0       1.00      1.00      1.00    142158\n",
484 |       "           1       0.00      0.00      0.00        99\n",
485 |       "\n",
486 |       "    accuracy                           1.00    142257\n",
487 |       "   macro avg       0.50      0.50      0.50    142257\n",
488 |       "weighted avg       1.00      1.00      1.00    142257\n",
489 |       "\n",
490 |       "ROC AUC Score:  0.5\n",
491 |       "Ratio of weights: 1: 1.04\n",
492 |       "              precision    recall  f1-score   support\n",
493 |       "\n",
494 |       "           0       1.00      1.00      1.00    142157\n",
495 |       "           1       0.92      0.76      0.83       393\n",
496 |       "\n",
497 |       "    accuracy                           1.00    142550\n",
498 |       "   macro avg       0.96      0.88      0.92    142550\n",
499 |       "weighted avg       1.00      1.00      1.00    142550\n",
500 |       "\n",
501 |       "ROC AUC Score:  0.8815879411254097\n",
502 |       "              precision    recall  f1-score   support\n",
503 |       "\n",
504 |       "           0       1.00      1.00      1.00    142158\n",
505 |       "           1       0.75      0.81      0.78        99\n",
506 |       "\n",
507 |       "    accuracy                           1.00    142257\n",
508 |       "   macro avg       0.87      0.90      0.89    142257\n",
509 |       "weighted avg       1.00      1.00      1.00    142257\n",
510 |       "\n",
511 |       "ROC AUC Score:  0.9039454392828807\n",
512 |       "Ratio of weights: 1: 1.05\n",
513 |       "              precision    recall  f1-score   support\n",
514 |       "\n",
515 |       "           0       1.00      1.00      1.00    142157\n",
516 |       "           1       0.91      0.63      0.75       393\n",
517 |       "\n",
518 |       "    accuracy                           1.00    142550\n",
519 |       "   macro avg       0.95      0.82      0.87    142550\n",
520 |       "weighted avg       1.00      1.00      1.00    142550\n",
521 |       "\n",
522 |       "ROC AUC Score:  0.8167024449422036\n",
523 |       "              precision    recall  f1-score   support\n",
524 |       "\n",
525 |       "           0       1.00      1.00      1.00    142158\n",
526 |       "           1       0.75      0.63      0.68        99\n",
527 |       "\n",
528 |       "    accuracy                           1.00    142257\n",
529 |       "   macro avg       0.87      0.81      0.84    142257\n",
530 |       "weighted avg       1.00      1.00      1.00    142257\n",
531 |       "\n",
532 |       "ROC AUC Score:  0.8130574516532395\n",
533 |       "Ratio of weights: 1: 1.06\n",
534 |       "              precision    recall  f1-score   support\n",
535 |       "\n",
536 |       "           0       1.00      1.00      1.00    142157\n",
537 |       "           1       0.90      0.79      0.84       393\n",
538 |       "\n",
539 |       "    accuracy                           1.00    142550\n",
540 |       "   macro avg       0.95      0.90      0.92    142550\n",
541 |       "weighted avg       1.00      1.00      1.00    142550\n",
542 |       "\n",
543 |       "ROC AUC Score:  0.8955476796870521\n",
544 |       "              precision    recall  f1-score   support\n",
545 |       "\n",
546 |       "           0       1.00      1.00      1.00    142158\n",
547 |       "           1       0.72      0.79      0.75        99\n",
548 |       "\n",
549 |       "    accuracy                           1.00    142257\n",
550 |       "   macro avg       0.86      0.89      0.88    142257\n",
551 |       "weighted avg       1.00      1.00      1.00    142257\n",
552 |       "\n",
553 |       "ROC AUC Score:  0.8938338775421458\n",
554 |       "Ratio of weights: 1: 1.07\n",
555 |       "              precision    recall  f1-score   support\n",
556 |       "\n",
557 |       "           0       1.00      1.00      1.00    142157\n",
558 |       "           1       0.90      0.76      0.83       393\n",
559 |       "\n",
560 |       "    accuracy                           1.00    142550\n",
561 |       "   macro avg       0.95      0.88      0.91    142550\n",
562 |       "weighted avg       1.00      1.00      1.00    142550\n",
563 |       "\n",
564 |       "ROC AUC Score:  0.8815668376975097\n",
565 |       "              precision    recall  f1-score   support\n",
566 |       "\n",
567 |       "           0       1.00      1.00      1.00    142158\n",
568 |       "           1       0.73      0.79      0.76        99\n",
569 |       "\n",
570 |       "    accuracy                           1.00    142257\n",
571 |       "   macro avg       0.86      0.89      0.88    142257\n",
572 |       "weighted avg       1.00      1.00      1.00    142257\n",
573 |       "\n",
574 |       "ROC AUC Score:  0.8938373947553874\n",
575 |       "Ratio of weights: 1: 1.08\n",
576 |       "              precision    recall  f1-score   support\n",
577 |       "\n",
578 |       "           0       1.00      1.00      1.00    142157\n",
579 |       "           1       0.90      0.72      0.80       393\n",
580 |       "\n",
581 |       "    accuracy                           1.00    142550\n",
582 |       "   macro avg       0.95      0.86      0.90    142550\n",
583 |       "weighted avg       1.00      1.00      1.00    142550\n",
584 |       "\n",
585 |       "ROC AUC Score:  0.8612141208388009\n",
586 |       "              precision    recall  f1-score   support\n",
587 |       "\n",
588 |       "           0       1.00      1.00      1.00    142158\n",
589 |       "           1       0.75      0.76      0.75        99\n",
590 |       "\n",
591 |       "    accuracy                           1.00    142257\n",
592 |       "   macro avg       0.87      0.88      0.88    142257\n",
593 |       "weighted avg       1.00      1.00      1.00    142257\n",
594 |       "\n",
595 |       "ROC AUC Score:  0.8786999484568386\n",
596 |       "Ratio of weights: 1: 1.09\n",
597 |       "              precision    recall  f1-score   support\n",
598 |       "\n",
599 |       "           0       1.00      1.00      1.00    142157\n",
600 |       "           1       0.90      0.79      0.84       393\n",
601 |       "\n",
602 |       "    accuracy                           1.00    142550\n",
603 |       "   macro avg       0.95      0.90      0.92    142550\n",
604 |       "weighted avg       1.00      1.00      1.00    142550\n",
605 |       "\n",
606 |       "ROC AUC Score:  0.8955476796870521\n",
607 |       "              precision    recall  f1-score   support\n",
608 |       "\n",
609 |       "           0       1.00      1.00      1.00    142158\n",
610 |       "           1       0.74      0.79      0.76        99\n",
611 |       "\n",
612 |       "    accuracy                           1.00    142257\n",
613 |       "   macro avg       0.87      0.89      0.88    142257\n",
614 |       "weighted avg       1.00      1.00      1.00    142257\n",
615 |       "\n",
616 |       "ROC AUC Score:  0.8938444291818706\n"
617 |      ]
618 |     }
619 |    ],
620 |    "source": [
621 |     "#finding the best weight ratio\n",
622 |     "for i in range(1, 10, 1):\n",
623 |     "    print('Ratio of weights: 1:',1+(i*0.01))\n",
624 |     "    classifier = classifierCreator()\n",
625 |     "    classifier.compile(loss='binary_crossentropy', optimizer='sgd')\n",
626 |     "    weights = {0:1, 1:1+(i*0.01)}\n",
627 |     "    history = classifier.fit(xTrain, yTrain, class_weight=weights, epochs=15, verbose=0)\n",
628 |     "    #predict the model on the train values and check results\n",
629 |     "    predTrain = classifier.predict_classes(xTrain)\n",
630 |     "    print(classification_report(yTrain, predTrain))\n",
631 |     "    print('ROC AUC Score: ',roc(yTrain, predTrain))\n",
632 |     "    #predict test values and check results\n",
633 |     "    predTest = classifier.predict_classes(xTest)\n",
634 |     "    print(classification_report(yTest, predTest))\n",
635 |     "    print('ROC AUC Score: ',roc(yTest, predTest))"
636 |    ]
637 |   },
638 |   {
639 |    "cell_type": "code",
640 |    "execution_count": null,
641 |    "metadata": {},
642 |    "outputs": [],
643 |    "source": []
644 |   }
645 |  ],
646 |  "metadata": {
647 |   "kernelspec": {
648 |    "display_name": "Python 3",
649 |    "language": "python",
650 |    "name": "python3"
651 |   },
652 |   "language_info": {
653 |    "codemirror_mode": {
654 |     "name": "ipython",
655 |     "version": 3
656 |    },
657 |    "file_extension": ".py",
658 |    "mimetype": "text/x-python",
659 |    "name": "python",
660 |    "nbconvert_exporter": "python",
661 |    "pygments_lexer": "ipython3",
662 |    "version": "3.8.3"
663 |   }
664 |  },
665 |  "nbformat": 4,
666 |  "nbformat_minor": 4
667 | }
668 | 


--------------------------------------------------------------------------------
/Multiple Linear Regression.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 1,
  6 |    "metadata": {},
  7 |    "outputs": [],
  8 |    "source": [
  9 |     "#import important libraries\n",
 10 |     "import pandas as pd\n",
 11 |     "import numpy as np\n",
 12 |     "import seaborn as sns\n",
 13 |     "from sklearn.metrics import classification_report\n",
 14 |     "from sklearn.metrics import roc_auc_score as roc\n",
 15 |     "from sklearn.model_selection import train_test_split as tts\n",
 16 |     "from sklearn.linear_model import LinearRegression\n",
 17 |     "from sklearn.preprocessing import StandardScaler"
 18 |    ]
 19 |   },
 20 |   {
 21 |    "cell_type": "code",
 22 |    "execution_count": 2,
 23 |    "metadata": {},
 24 |    "outputs": [
 25 |     {
 26 |      "data": {
 27 |       "text/html": [
 28 |        "<div>\n",
 29 |        "<style scoped>\n",
 30 |        "    .dataframe tbody tr th:only-of-type {\n",
 31 |        "        vertical-align: middle;\n",
 32 |        "    }\n",
 33 |        "\n",
 34 |        "    .dataframe tbody tr th {\n",
 35 |        "        vertical-align: top;\n",
 36 |        "    }\n",
 37 |        "\n",
 38 |        "    .dataframe thead th {\n",
 39 |        "        text-align: right;\n",
 40 |        "    }\n",
 41 |        "</style>\n",
 42 |        "<table border=\"1\" class=\"dataframe\">\n",
 43 |        "  <thead>\n",
 44 |        "    <tr style=\"text-align: right;\">\n",
 45 |        "      <th></th>\n",
 46 |        "      <th>Time</th>\n",
 47 |        "      <th>V1</th>\n",
 48 |        "      <th>V2</th>\n",
 49 |        "      <th>V3</th>\n",
 50 |        "      <th>V4</th>\n",
 51 |        "      <th>V5</th>\n",
 52 |        "      <th>V6</th>\n",
 53 |        "      <th>V7</th>\n",
 54 |        "      <th>V8</th>\n",
 55 |        "      <th>V9</th>\n",
 56 |        "      <th>...</th>\n",
 57 |        "      <th>V21</th>\n",
 58 |        "      <th>V22</th>\n",
 59 |        "      <th>V23</th>\n",
 60 |        "      <th>V24</th>\n",
 61 |        "      <th>V25</th>\n",
 62 |        "      <th>V26</th>\n",
 63 |        "      <th>V27</th>\n",
 64 |        "      <th>V28</th>\n",
 65 |        "      <th>Amount</th>\n",
 66 |        "      <th>Class</th>\n",
 67 |        "    </tr>\n",
 68 |        "  </thead>\n",
 69 |        "  <tbody>\n",
 70 |        "    <tr>\n",
 71 |        "      <th>0</th>\n",
 72 |        "      <td>0.0</td>\n",
 73 |        "      <td>-1.359807</td>\n",
 74 |        "      <td>-0.072781</td>\n",
 75 |        "      <td>2.536347</td>\n",
 76 |        "      <td>1.378155</td>\n",
 77 |        "      <td>-0.338321</td>\n",
 78 |        "      <td>0.462388</td>\n",
 79 |        "      <td>0.239599</td>\n",
 80 |        "      <td>0.098698</td>\n",
 81 |        "      <td>0.363787</td>\n",
 82 |        "      <td>...</td>\n",
 83 |        "      <td>-0.018307</td>\n",
 84 |        "      <td>0.277838</td>\n",
 85 |        "      <td>-0.110474</td>\n",
 86 |        "      <td>0.066928</td>\n",
 87 |        "      <td>0.128539</td>\n",
 88 |        "      <td>-0.189115</td>\n",
 89 |        "      <td>0.133558</td>\n",
 90 |        "      <td>-0.021053</td>\n",
 91 |        "      <td>149.62</td>\n",
 92 |        "      <td>0</td>\n",
 93 |        "    </tr>\n",
 94 |        "    <tr>\n",
 95 |        "      <th>1</th>\n",
 96 |        "      <td>0.0</td>\n",
 97 |        "      <td>1.191857</td>\n",
 98 |        "      <td>0.266151</td>\n",
 99 |        "      <td>0.166480</td>\n",
100 |        "      <td>0.448154</td>\n",
101 |        "      <td>0.060018</td>\n",
102 |        "      <td>-0.082361</td>\n",
103 |        "      <td>-0.078803</td>\n",
104 |        "      <td>0.085102</td>\n",
105 |        "      <td>-0.255425</td>\n",
106 |        "      <td>...</td>\n",
107 |        "      <td>-0.225775</td>\n",
108 |        "      <td>-0.638672</td>\n",
109 |        "      <td>0.101288</td>\n",
110 |        "      <td>-0.339846</td>\n",
111 |        "      <td>0.167170</td>\n",
112 |        "      <td>0.125895</td>\n",
113 |        "      <td>-0.008983</td>\n",
114 |        "      <td>0.014724</td>\n",
115 |        "      <td>2.69</td>\n",
116 |        "      <td>0</td>\n",
117 |        "    </tr>\n",
118 |        "    <tr>\n",
119 |        "      <th>2</th>\n",
120 |        "      <td>1.0</td>\n",
121 |        "      <td>-1.358354</td>\n",
122 |        "      <td>-1.340163</td>\n",
123 |        "      <td>1.773209</td>\n",
124 |        "      <td>0.379780</td>\n",
125 |        "      <td>-0.503198</td>\n",
126 |        "      <td>1.800499</td>\n",
127 |        "      <td>0.791461</td>\n",
128 |        "      <td>0.247676</td>\n",
129 |        "      <td>-1.514654</td>\n",
130 |        "      <td>...</td>\n",
131 |        "      <td>0.247998</td>\n",
132 |        "      <td>0.771679</td>\n",
133 |        "      <td>0.909412</td>\n",
134 |        "      <td>-0.689281</td>\n",
135 |        "      <td>-0.327642</td>\n",
136 |        "      <td>-0.139097</td>\n",
137 |        "      <td>-0.055353</td>\n",
138 |        "      <td>-0.059752</td>\n",
139 |        "      <td>378.66</td>\n",
140 |        "      <td>0</td>\n",
141 |        "    </tr>\n",
142 |        "    <tr>\n",
143 |        "      <th>3</th>\n",
144 |        "      <td>1.0</td>\n",
145 |        "      <td>-0.966272</td>\n",
146 |        "      <td>-0.185226</td>\n",
147 |        "      <td>1.792993</td>\n",
148 |        "      <td>-0.863291</td>\n",
149 |        "      <td>-0.010309</td>\n",
150 |        "      <td>1.247203</td>\n",
151 |        "      <td>0.237609</td>\n",
152 |        "      <td>0.377436</td>\n",
153 |        "      <td>-1.387024</td>\n",
154 |        "      <td>...</td>\n",
155 |        "      <td>-0.108300</td>\n",
156 |        "      <td>0.005274</td>\n",
157 |        "      <td>-0.190321</td>\n",
158 |        "      <td>-1.175575</td>\n",
159 |        "      <td>0.647376</td>\n",
160 |        "      <td>-0.221929</td>\n",
161 |        "      <td>0.062723</td>\n",
162 |        "      <td>0.061458</td>\n",
163 |        "      <td>123.50</td>\n",
164 |        "      <td>0</td>\n",
165 |        "    </tr>\n",
166 |        "    <tr>\n",
167 |        "      <th>4</th>\n",
168 |        "      <td>2.0</td>\n",
169 |        "      <td>-1.158233</td>\n",
170 |        "      <td>0.877737</td>\n",
171 |        "      <td>1.548718</td>\n",
172 |        "      <td>0.403034</td>\n",
173 |        "      <td>-0.407193</td>\n",
174 |        "      <td>0.095921</td>\n",
175 |        "      <td>0.592941</td>\n",
176 |        "      <td>-0.270533</td>\n",
177 |        "      <td>0.817739</td>\n",
178 |        "      <td>...</td>\n",
179 |        "      <td>-0.009431</td>\n",
180 |        "      <td>0.798278</td>\n",
181 |        "      <td>-0.137458</td>\n",
182 |        "      <td>0.141267</td>\n",
183 |        "      <td>-0.206010</td>\n",
184 |        "      <td>0.502292</td>\n",
185 |        "      <td>0.219422</td>\n",
186 |        "      <td>0.215153</td>\n",
187 |        "      <td>69.99</td>\n",
188 |        "      <td>0</td>\n",
189 |        "    </tr>\n",
190 |        "  </tbody>\n",
191 |        "</table>\n",
192 |        "<p>5 rows × 31 columns</p>\n",
193 |        "</div>"
194 |       ],
195 |       "text/plain": [
196 |        "   Time        V1        V2        V3        V4        V5        V6        V7  \\\n",
197 |        "0   0.0 -1.359807 -0.072781  2.536347  1.378155 -0.338321  0.462388  0.239599   \n",
198 |        "1   0.0  1.191857  0.266151  0.166480  0.448154  0.060018 -0.082361 -0.078803   \n",
199 |        "2   1.0 -1.358354 -1.340163  1.773209  0.379780 -0.503198  1.800499  0.791461   \n",
200 |        "3   1.0 -0.966272 -0.185226  1.792993 -0.863291 -0.010309  1.247203  0.237609   \n",
201 |        "4   2.0 -1.158233  0.877737  1.548718  0.403034 -0.407193  0.095921  0.592941   \n",
202 |        "\n",
203 |        "         V8        V9  ...       V21       V22       V23       V24       V25  \\\n",
204 |        "0  0.098698  0.363787  ... -0.018307  0.277838 -0.110474  0.066928  0.128539   \n",
205 |        "1  0.085102 -0.255425  ... -0.225775 -0.638672  0.101288 -0.339846  0.167170   \n",
206 |        "2  0.247676 -1.514654  ...  0.247998  0.771679  0.909412 -0.689281 -0.327642   \n",
207 |        "3  0.377436 -1.387024  ... -0.108300  0.005274 -0.190321 -1.175575  0.647376   \n",
208 |        "4 -0.270533  0.817739  ... -0.009431  0.798278 -0.137458  0.141267 -0.206010   \n",
209 |        "\n",
210 |        "        V26       V27       V28  Amount  Class  \n",
211 |        "0 -0.189115  0.133558 -0.021053  149.62      0  \n",
212 |        "1  0.125895 -0.008983  0.014724    2.69      0  \n",
213 |        "2 -0.139097 -0.055353 -0.059752  378.66      0  \n",
214 |        "3 -0.221929  0.062723  0.061458  123.50      0  \n",
215 |        "4  0.502292  0.219422  0.215153   69.99      0  \n",
216 |        "\n",
217 |        "[5 rows x 31 columns]"
218 |       ]
219 |      },
220 |      "execution_count": 2,
221 |      "metadata": {},
222 |      "output_type": "execute_result"
223 |     }
224 |    ],
225 |    "source": [
226 |     "#import the dataset and visualize the dataset\n",
227 |     "dataset = pd.read_csv('./dataset/creditcard.csv')\n",
228 |     "dataset.head()"
229 |    ]
230 |   },
231 |   {
232 |    "cell_type": "code",
233 |    "execution_count": 3,
234 |    "metadata": {},
235 |    "outputs": [
236 |     {
237 |      "data": {
238 |       "text/plain": [
239 |        "<matplotlib.axes._subplots.AxesSubplot at 0x7fbee9a84460>"
240 |       ]
241 |      },
242 |      "execution_count": 3,
243 |      "metadata": {},
244 |      "output_type": "execute_result"
245 |     },
246 |     {
247 |      "data": {
248 |       "image/png": "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\n",
249 |       "text/plain": [
250 |        "<Figure size 432x288 with 1 Axes>"
251 |       ]
252 |      },
253 |      "metadata": {
254 |       "needs_background": "light"
255 |      },
256 |      "output_type": "display_data"
257 |     }
258 |    ],
259 |    "source": [
260 |     "#visualize the target class 'Class'\n",
261 |     "sns.countplot(x='Class', data=dataset)"
262 |    ]
263 |   },
264 |   {
265 |    "cell_type": "code",
266 |    "execution_count": 4,
267 |    "metadata": {},
268 |    "outputs": [],
269 |    "source": [
270 |     "#seperating positive and negative classes\n",
271 |     "positiveDataset = dataset.loc[dataset['Class'] == 1]\n",
272 |     "negativeDataset = dataset.loc[dataset['Class'] == 0]"
273 |    ]
274 |   },
275 |   {
276 |    "cell_type": "code",
277 |    "execution_count": 5,
278 |    "metadata": {},
279 |    "outputs": [],
280 |    "source": [
281 |     "#creating training and testing set with negative class split 1:1 and positive class split 4:1, also keeping random_state constant so that all splits are same\n",
282 |     "positiveTrain, positiveTest = tts(positiveDataset, test_size=0.2, random_state=21)\n",
283 |     "negativeTrain, negativeTest = tts(negativeDataset, test_size=0.5)\n",
284 |     "trainDataset = positiveTrain.append(negativeTrain)\n",
285 |     "testDataset = positiveTest.append(negativeTest)"
286 |    ]
287 |   },
288 |   {
289 |    "cell_type": "code",
290 |    "execution_count": 6,
291 |    "metadata": {},
292 |    "outputs": [],
293 |    "source": [
294 |     "#create Regression object and scale the dataset\n",
295 |     "lr = LinearRegression()\n",
296 |     "yTrain = trainDataset['Class']\n",
297 |     "yTest = testDataset['Class']\n",
298 |     "xTrain = trainDataset.drop(columns=['Class'])\n",
299 |     "xTest = testDataset.drop(columns=['Class'])\n",
300 |     "scaler = StandardScaler()\n",
301 |     "xTrain = scaler.fit_transform(xTrain)\n",
302 |     "xTest = scaler.fit_transform(xTest)"
303 |    ]
304 |   },
305 |   {
306 |    "cell_type": "code",
307 |    "execution_count": 7,
308 |    "metadata": {},
309 |    "outputs": [
310 |     {
311 |      "data": {
312 |       "text/plain": [
313 |        "LinearRegression()"
314 |       ]
315 |      },
316 |      "execution_count": 7,
317 |      "metadata": {},
318 |      "output_type": "execute_result"
319 |     }
320 |    ],
321 |    "source": [
322 |     "#fit the dataset to the train values\n",
323 |     "lr.fit(xTrain, yTrain)"
324 |    ]
325 |   },
326 |   {
327 |    "cell_type": "code",
328 |    "execution_count": 8,
329 |    "metadata": {},
330 |    "outputs": [],
331 |    "source": [
332 |     "#predict the model on the train values\n",
333 |     "predTrain = lr.predict(xTrain)"
334 |    ]
335 |   },
336 |   {
337 |    "cell_type": "code",
338 |    "execution_count": 9,
339 |    "metadata": {},
340 |    "outputs": [
341 |     {
342 |      "name": "stdout",
343 |      "output_type": "stream",
344 |      "text": [
345 |       "              precision    recall  f1-score   support\n",
346 |       "\n",
347 |       "           0       1.00      1.00      1.00    142157\n",
348 |       "           1       0.88      0.45      0.60       393\n",
349 |       "\n",
350 |       "    accuracy                           1.00    142550\n",
351 |       "   macro avg       0.94      0.73      0.80    142550\n",
352 |       "weighted avg       1.00      1.00      1.00    142550\n",
353 |       "\n",
354 |       "ROC AUC Score:  0.7263751733761158\n"
355 |      ]
356 |     }
357 |    ],
358 |    "source": [
359 |     "#checking training records by applying 0.5 threshold\n",
360 |     "for i in range(0, len(predTrain)):\n",
361 |     "    if(predTrain[i]>=0.5):\n",
362 |     "        predTrain[i]=1\n",
363 |     "    else:\n",
364 |     "        predTrain[i]=0\n",
365 |     "print(classification_report(yTrain, predTrain))\n",
366 |     "print('ROC AUC Score: ',roc(yTrain, predTrain))"
367 |    ]
368 |   },
369 |   {
370 |    "cell_type": "code",
371 |    "execution_count": 10,
372 |    "metadata": {},
373 |    "outputs": [
374 |     {
375 |      "name": "stdout",
376 |      "output_type": "stream",
377 |      "text": [
378 |       "              precision    recall  f1-score   support\n",
379 |       "\n",
380 |       "           0       1.00      1.00      1.00    142158\n",
381 |       "           1       0.76      0.51      0.61        99\n",
382 |       "\n",
383 |       "    accuracy                           1.00    142257\n",
384 |       "   macro avg       0.88      0.75      0.80    142257\n",
385 |       "weighted avg       1.00      1.00      1.00    142257\n",
386 |       "\n",
387 |       "ROC AUC Score:  0.752468977113387\n"
388 |      ]
389 |     }
390 |    ],
391 |    "source": [
392 |     "#checking test records using 0.5 threshold\n",
393 |     "predTest = lr.predict(xTest)\n",
394 |     "for i in range(0, len(predTest)):\n",
395 |     "    if(predTest[i]>=0.5):\n",
396 |     "        predTest[i]=1\n",
397 |     "    else:\n",
398 |     "        predTest[i]=0\n",
399 |     "print(classification_report(yTest, predTest))\n",
400 |     "print('ROC AUC Score: ',roc(yTest, predTest))"
401 |    ]
402 |   },
403 |   {
404 |    "cell_type": "code",
405 |    "execution_count": 11,
406 |    "metadata": {},
407 |    "outputs": [
408 |     {
409 |      "name": "stdout",
410 |      "output_type": "stream",
411 |      "text": [
412 |       "Threshold set at:  0.1\n",
413 |       "              precision    recall  f1-score   support\n",
414 |       "\n",
415 |       "           0       1.00      1.00      1.00    142158\n",
416 |       "           1       0.66      0.80      0.72        99\n",
417 |       "\n",
418 |       "    accuracy                           1.00    142257\n",
419 |       "   macro avg       0.83      0.90      0.86    142257\n",
420 |       "weighted avg       1.00      1.00      1.00    142257\n",
421 |       "\n",
422 |       "ROC AUC Score:  0.8988492104602348\n",
423 |       "Threshold set at:  0.12\n",
424 |       "              precision    recall  f1-score   support\n",
425 |       "\n",
426 |       "           0       1.00      1.00      1.00    142158\n",
427 |       "           1       0.67      0.80      0.73        99\n",
428 |       "\n",
429 |       "    accuracy                           1.00    142257\n",
430 |       "   macro avg       0.83      0.90      0.86    142257\n",
431 |       "weighted avg       1.00      1.00      1.00    142257\n",
432 |       "\n",
433 |       "ROC AUC Score:  0.8988527276734765\n",
434 |       "Threshold set at:  0.14\n",
435 |       "              precision    recall  f1-score   support\n",
436 |       "\n",
437 |       "           0       1.00      1.00      1.00    142158\n",
438 |       "           1       0.67      0.80      0.73        99\n",
439 |       "\n",
440 |       "    accuracy                           1.00    142257\n",
441 |       "   macro avg       0.83      0.90      0.86    142257\n",
442 |       "weighted avg       1.00      1.00      1.00    142257\n",
443 |       "\n",
444 |       "ROC AUC Score:  0.8988527276734765\n",
445 |       "Threshold set at:  0.16\n",
446 |       "              precision    recall  f1-score   support\n",
447 |       "\n",
448 |       "           0       1.00      1.00      1.00    142158\n",
449 |       "           1       0.67      0.80      0.73        99\n",
450 |       "\n",
451 |       "    accuracy                           1.00    142257\n",
452 |       "   macro avg       0.83      0.90      0.86    142257\n",
453 |       "weighted avg       1.00      1.00      1.00    142257\n",
454 |       "\n",
455 |       "ROC AUC Score:  0.8988527276734765\n",
456 |       "Threshold set at:  0.18\n",
457 |       "              precision    recall  f1-score   support\n",
458 |       "\n",
459 |       "           0       1.00      1.00      1.00    142158\n",
460 |       "           1       0.67      0.80      0.73        99\n",
461 |       "\n",
462 |       "    accuracy                           1.00    142257\n",
463 |       "   macro avg       0.83      0.90      0.86    142257\n",
464 |       "weighted avg       1.00      1.00      1.00    142257\n",
465 |       "\n",
466 |       "ROC AUC Score:  0.8988527276734765\n",
467 |       "Threshold set at:  0.2\n",
468 |       "              precision    recall  f1-score   support\n",
469 |       "\n",
470 |       "           0       1.00      1.00      1.00    142158\n",
471 |       "           1       0.67      0.80      0.73        99\n",
472 |       "\n",
473 |       "    accuracy                           1.00    142257\n",
474 |       "   macro avg       0.83      0.90      0.86    142257\n",
475 |       "weighted avg       1.00      1.00      1.00    142257\n",
476 |       "\n",
477 |       "ROC AUC Score:  0.8988527276734765\n",
478 |       "Threshold set at:  0.22\n",
479 |       "              precision    recall  f1-score   support\n",
480 |       "\n",
481 |       "           0       1.00      1.00      1.00    142158\n",
482 |       "           1       0.69      0.80      0.74        99\n",
483 |       "\n",
484 |       "    accuracy                           1.00    142257\n",
485 |       "   macro avg       0.84      0.90      0.87    142257\n",
486 |       "weighted avg       1.00      1.00      1.00    142257\n",
487 |       "\n",
488 |       "ROC AUC Score:  0.8988632793132013\n",
489 |       "Threshold set at:  0.24\n",
490 |       "              precision    recall  f1-score   support\n",
491 |       "\n",
492 |       "           0       1.00      1.00      1.00    142158\n",
493 |       "           1       0.69      0.79      0.74        99\n",
494 |       "\n",
495 |       "    accuracy                           1.00    142257\n",
496 |       "   macro avg       0.85      0.89      0.87    142257\n",
497 |       "weighted avg       1.00      1.00      1.00    142257\n",
498 |       "\n",
499 |       "ROC AUC Score:  0.8938162914759378\n",
500 |       "Threshold set at:  0.26\n",
501 |       "              precision    recall  f1-score   support\n",
502 |       "\n",
503 |       "           0       1.00      1.00      1.00    142158\n",
504 |       "           1       0.71      0.79      0.75        99\n",
505 |       "\n",
506 |       "    accuracy                           1.00    142257\n",
507 |       "   macro avg       0.85      0.89      0.87    142257\n",
508 |       "weighted avg       1.00      1.00      1.00    142257\n",
509 |       "\n",
510 |       "ROC AUC Score:  0.8938268431156625\n",
511 |       "Threshold set at:  0.28\n",
512 |       "              precision    recall  f1-score   support\n",
513 |       "\n",
514 |       "           0       1.00      1.00      1.00    142158\n",
515 |       "           1       0.74      0.79      0.76        99\n",
516 |       "\n",
517 |       "    accuracy                           1.00    142257\n",
518 |       "   macro avg       0.87      0.89      0.88    142257\n",
519 |       "weighted avg       1.00      1.00      1.00    142257\n",
520 |       "\n",
521 |       "ROC AUC Score:  0.893840911968629\n",
522 |       "Threshold set at:  0.3\n",
523 |       "              precision    recall  f1-score   support\n",
524 |       "\n",
525 |       "           0       1.00      1.00      1.00    142158\n",
526 |       "           1       0.75      0.79      0.77        99\n",
527 |       "\n",
528 |       "    accuracy                           1.00    142257\n",
529 |       "   macro avg       0.87      0.89      0.88    142257\n",
530 |       "weighted avg       1.00      1.00      1.00    142257\n",
531 |       "\n",
532 |       "ROC AUC Score:  0.8938479463951122\n",
533 |       "Threshold set at:  0.32\n",
534 |       "              precision    recall  f1-score   support\n",
535 |       "\n",
536 |       "           0       1.00      1.00      1.00    142158\n",
537 |       "           1       0.73      0.73      0.73        99\n",
538 |       "\n",
539 |       "    accuracy                           1.00    142257\n",
540 |       "   macro avg       0.87      0.86      0.87    142257\n",
541 |       "weighted avg       1.00      1.00      1.00    142257\n",
542 |       "\n",
543 |       "ROC AUC Score:  0.863544916092082\n",
544 |       "Threshold set at:  0.34\n",
545 |       "              precision    recall  f1-score   support\n",
546 |       "\n",
547 |       "           0       1.00      1.00      1.00    142158\n",
548 |       "           1       0.75      0.72      0.73        99\n",
549 |       "\n",
550 |       "    accuracy                           1.00    142257\n",
551 |       "   macro avg       0.87      0.86      0.87    142257\n",
552 |       "weighted avg       1.00      1.00      1.00    142257\n",
553 |       "\n",
554 |       "ROC AUC Score:  0.8585014454680601\n",
555 |       "Threshold set at:  0.36\n",
556 |       "              precision    recall  f1-score   support\n",
557 |       "\n",
558 |       "           0       1.00      1.00      1.00    142158\n",
559 |       "           1       0.76      0.64      0.69        99\n",
560 |       "\n",
561 |       "    accuracy                           1.00    142257\n",
562 |       "   macro avg       0.88      0.82      0.85    142257\n",
563 |       "weighted avg       1.00      1.00      1.00    142257\n",
564 |       "\n",
565 |       "ROC AUC Score:  0.818111473916986\n",
566 |       "Threshold set at:  0.38\n",
567 |       "              precision    recall  f1-score   support\n",
568 |       "\n",
569 |       "           0       1.00      1.00      1.00    142158\n",
570 |       "           1       0.78      0.62      0.69        99\n",
571 |       "\n",
572 |       "    accuracy                           1.00    142257\n",
573 |       "   macro avg       0.89      0.81      0.84    142257\n",
574 |       "weighted avg       1.00      1.00      1.00    142257\n",
575 |       "\n",
576 |       "ROC AUC Score:  0.8080210154557008\n",
577 |       "Threshold set at:  0.4\n",
578 |       "              precision    recall  f1-score   support\n",
579 |       "\n",
580 |       "           0       1.00      1.00      1.00    142158\n",
581 |       "           1       0.79      0.62      0.69        99\n",
582 |       "\n",
583 |       "    accuracy                           1.00    142257\n",
584 |       "   macro avg       0.90      0.81      0.85    142257\n",
585 |       "weighted avg       1.00      1.00      1.00    142257\n",
586 |       "\n",
587 |       "ROC AUC Score:  0.8080245326689425\n",
588 |       "Threshold set at:  0.42\n",
589 |       "              precision    recall  f1-score   support\n",
590 |       "\n",
591 |       "           0       1.00      1.00      1.00    142158\n",
592 |       "           1       0.79      0.60      0.68        99\n",
593 |       "\n",
594 |       "    accuracy                           1.00    142257\n",
595 |       "   macro avg       0.89      0.80      0.84    142257\n",
596 |       "weighted avg       1.00      1.00      1.00    142257\n",
597 |       "\n",
598 |       "ROC AUC Score:  0.7979235225679323\n",
599 |       "Threshold set at:  0.44\n",
600 |       "              precision    recall  f1-score   support\n",
601 |       "\n",
602 |       "           0       1.00      1.00      1.00    142158\n",
603 |       "           1       0.78      0.59      0.67        99\n",
604 |       "\n",
605 |       "    accuracy                           1.00    142257\n",
606 |       "   macro avg       0.89      0.79      0.84    142257\n",
607 |       "weighted avg       1.00      1.00      1.00    142257\n",
608 |       "\n",
609 |       "ROC AUC Score:  0.7928730175174272\n",
610 |       "Threshold set at:  0.46\n",
611 |       "              precision    recall  f1-score   support\n",
612 |       "\n",
613 |       "           0       1.00      1.00      1.00    142158\n",
614 |       "           1       0.78      0.59      0.67        99\n",
615 |       "\n",
616 |       "    accuracy                           1.00    142257\n",
617 |       "   macro avg       0.89      0.79      0.84    142257\n",
618 |       "weighted avg       1.00      1.00      1.00    142257\n",
619 |       "\n",
620 |       "ROC AUC Score:  0.7928730175174272\n",
621 |       "Threshold set at:  0.48\n",
622 |       "              precision    recall  f1-score   support\n",
623 |       "\n",
624 |       "           0       1.00      1.00      1.00    142158\n",
625 |       "           1       0.78      0.58      0.66        99\n",
626 |       "\n",
627 |       "    accuracy                           1.00    142257\n",
628 |       "   macro avg       0.89      0.79      0.83    142257\n",
629 |       "weighted avg       1.00      1.00      1.00    142257\n",
630 |       "\n",
631 |       "ROC AUC Score:  0.7878225124669223\n",
632 |       "Threshold set at:  0.5\n",
633 |       "              precision    recall  f1-score   support\n",
634 |       "\n",
635 |       "           0       1.00      1.00      1.00    142158\n",
636 |       "           1       0.76      0.51      0.61        99\n",
637 |       "\n",
638 |       "    accuracy                           1.00    142257\n",
639 |       "   macro avg       0.88      0.75      0.80    142257\n",
640 |       "weighted avg       1.00      1.00      1.00    142257\n",
641 |       "\n",
642 |       "ROC AUC Score:  0.752468977113387\n"
643 |      ]
644 |     }
645 |    ],
646 |    "source": [
647 |     "#since the classes are highly imbalanced, varying thresholds from 0.1 to 0.5 in steps of 0.02 to find optimal threshold\n",
648 |     "for x in range(10, 51, 2):\n",
649 |     "    print('Threshold set at: ',x*0.01)\n",
650 |     "    predTest = lr.predict(xTest)\n",
651 |     "    for i in range(0, len(predTest)):\n",
652 |     "        if(predTest[i]>=(x*0.01)):\n",
653 |     "            predTest[i]=1\n",
654 |     "        else:\n",
655 |     "            predTest[i]=0\n",
656 |     "    print(classification_report(yTest, predTest))\n",
657 |     "    print('ROC AUC Score: ',roc(yTest, predTest)) "
658 |    ]
659 |   }
660 |  ],
661 |  "metadata": {
662 |   "kernelspec": {
663 |    "display_name": "Python 3",
664 |    "language": "python",
665 |    "name": "python3"
666 |   },
667 |   "language_info": {
668 |    "codemirror_mode": {
669 |     "name": "ipython",
670 |     "version": 3
671 |    },
672 |    "file_extension": ".py",
673 |    "mimetype": "text/x-python",
674 |    "name": "python",
675 |    "nbconvert_exporter": "python",
676 |    "pygments_lexer": "ipython3",
677 |    "version": "3.8.3"
678 |   }
679 |  },
680 |  "nbformat": 4,
681 |  "nbformat_minor": 4
682 | }
683 | 


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