├── .gitignore
├── Untitled.ipynb
├── Datasets
    ├── readme.txt
    ├── shakes-mapping.json
    └── Churn Data Description.txt
├── README.md
├── 6. Credit Card Fraud Detection
    └── Machine_Learning_06_Credit_Card_Fraud_Detection.ipynb
└── 4. Minimizing Churn Rate Through Analysis of Financial Habits
    └── Machine_Learning_04_Minimizing_Churn_Rate_Through_Analysis_of_Financial_Habits (Part 2).ipynb


/.gitignore:
--------------------------------------------------------------------------------
1 | *.CSV
2 | *.xlx
3 | *.xlxs
4 | 
5 | #folders
6 | 
7 | .ipynb_checkpoints/
8 | .ipynb_checkpoints
9 | 


--------------------------------------------------------------------------------
/Untitled.ipynb:
--------------------------------------------------------------------------------
1 | {
2 |  "cells": [],
3 |  "metadata": {},
4 |  "nbformat": 4,
5 |  "nbformat_minor": 2
6 | }
7 | 


--------------------------------------------------------------------------------
/Datasets/readme.txt:
--------------------------------------------------------------------------------
1 | The dataset were donwload from : https://www.superdatascience.com/pages/machine-learning-practical


--------------------------------------------------------------------------------
/Datasets/shakes-mapping.json:
--------------------------------------------------------------------------------
 1 | {
 2 | 	"mappings" : {
 3 |  		"_default_" : {
 4 | 			"properties" : {
 5 | 				"speaker" : {"type": "string", "index" : "not_analyzed" },
 6 | 				"play_name" : {"type": "string", "index" : "not_analyzed" },
 7 | 				"line_id" : { "type" : "integer" },
 8 | 				"speech_number" : { "type" : "integer" }
 9 | 			}
10 | 		}
11 | 	}
12 | }
13 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | # Machine Learning Practical: 6 real-world Aplications
 2 | 
 3 | This repository contains the code from 6 practical real cases solved with Machine Learning. The contend is related with the course [Machine Learning Practical: 6 Real-World Applications](https://www.udemy.com/machine-learning-practical/) created / dictated by Kirill Eremenko, Hadelin de Ponteves, Dr. Ryan Ahmed, Ph.D., MBA, SuperDataScience Team and Rony Sulca.   
 4 | 
 5 | List of solved cases included in this this repo:
 6 | - diagnosing diabetes in the early stages
 7 | - directing customers to subscription products with app usage analysis (Linear Regression [L1])
 8 | - minimizing churn rate in finance
 9 | - predicting customer location with GPS data
10 | - forecasting future currency exchange rates
11 | - classifying fashion (Deep Learning)
12 | - predicting breast cancer (Support Vector Machine - SVM)
13 | 
14 | ## Datasets
15 | 
16 | All the datasets used in this course were downloaded from [datasets & Code Course](https://www.superdatascience.com/pages/machine-learning-practical)
17 | 


--------------------------------------------------------------------------------
/Datasets/Churn Data Description.txt:
--------------------------------------------------------------------------------
 1 | Description of each Columns
 2 | userid - MongoDB userid
 3 | churn  - Active = No | Suspended < 30 = No Else Churn = Yes
 4 | age - age of the customer
 5 | city - city of the customer
 6 | state- state where the customer lives
 7 | postal_code - zip code of the customer
 8 | zodiac_sign- zodiac sign of the customer
 9 | rent_or_own - Does the customer rents or owns a house 
10 | more_than_one_mobile_device - does the customer use more than one mobile device
11 | payFreq- Pay Frequency of the cusomter
12 | in_collections - is the customer in collections
13 | loan_pending - is the loan pending
14 | withdrawn_application - has the customer withdrawn the loan applicaiton 
15 | paid_off_loan- has the customer paid of the loan
16 | did_not_accept_funding - customer did not accept funding
17 | cash_back_engagement - Sum of cash back dollars received by a customer / No of days in the app
18 | cash_back_amount - Sum of cash back dollars received by a customer
19 | used_ios- Has the user used an iphone
20 | used_android - Has the user used a android based phone
21 | has_used_mobile_and_web - Has the user used mobile and web platforms
22 | has_used_web - Has the user used MoneyLion Web app
23 | has_used_mobile - as the user used MoneyLion  app
24 | has_reffered- Has the user referred
25 | cards_clicked - How many times a user has clicked the cards
26 | cards_not_helpful- How helpful was the cards
27 | cards_helpful- How helpful was the cards
28 | cards_viewed- How many times a user viewed the cards
29 | cards_share- How many times a user shared his cards
30 | trivia_view_results-How many times a user viewed trivia results
31 | trivia_view_unlocked- How many times a user viewed trivia view unlocked screen
32 | trivia_view_locked - How many times a user viewed trivia view locked screen
33 | trivia_shared_results- How many times a user shared trivia results 
34 | trivia_played - How many times a user played trivia 
35 | re_linked_account- Has the user re linked account
36 | un_linked_account - Has the user un linked account
37 | credit_score - Customer's credit score


--------------------------------------------------------------------------------
/6. Credit Card Fraud Detection/Machine_Learning_06_Credit_Card_Fraud_Detection.ipynb:
--------------------------------------------------------------------------------
   1 | {
   2 |  "cells": [
   3 |   {
   4 |    "cell_type": "code",
   5 |    "execution_count": 37,
   6 |    "metadata": {},
   7 |    "outputs": [],
   8 |    "source": [
   9 |     "## importing libraries & data\n",
  10 |     "\n",
  11 |     "# import libraries\n",
  12 |     "import pandas as pd\n",
  13 |     "import numpy as np\n",
  14 |     "import seaborn as sns\n",
  15 |     "import matplotlib.pyplot as plt\n",
  16 |     "import random\n",
  17 |     "import time\n",
  18 |     "\n",
  19 |     "# TensorFlow and tf.keras\n",
  20 |     "import tensorflow as tf\n",
  21 |     "from tensorflow import keras\n",
  22 |     "\n",
  23 |     "np.random.seed(2)"
  24 |    ]
  25 |   },
  26 |   {
  27 |    "cell_type": "code",
  28 |    "execution_count": 2,
  29 |    "metadata": {},
  30 |    "outputs": [],
  31 |    "source": [
  32 |     "path = \"../Datasets\"\n",
  33 |     "\n",
  34 |     "import os\n",
  35 |     "#Actual absolute path\n",
  36 |     "cwd = os.getcwd()\n",
  37 |     "#print(cwd)"
  38 |    ]
  39 |   },
  40 |   {
  41 |    "cell_type": "code",
  42 |    "execution_count": 3,
  43 |    "metadata": {},
  44 |    "outputs": [],
  45 |    "source": [
  46 |     "# one level up directory. Datasets directory\n",
  47 |     "os.chdir(path)\n",
  48 |     "#Actual absolute path\n",
  49 |     "cwd = os.getcwd()\n",
  50 |     "#print(cwd)"
  51 |    ]
  52 |   },
  53 |   {
  54 |    "cell_type": "code",
  55 |    "execution_count": 4,
  56 |    "metadata": {},
  57 |    "outputs": [],
  58 |    "source": [
  59 |     "# path file current dir + file name\n",
  60 |     "path_file = cwd + '/creditcard.csv'\n",
  61 |     "# print(path_file)"
  62 |    ]
  63 |   },
  64 |   {
  65 |    "cell_type": "code",
  66 |    "execution_count": 5,
  67 |    "metadata": {},
  68 |    "outputs": [
  69 |     {
  70 |      "data": {
  71 |       "text/html": [
  72 |        "<div>\n",
  73 |        "<style scoped>\n",
  74 |        "    .dataframe tbody tr th:only-of-type {\n",
  75 |        "        vertical-align: middle;\n",
  76 |        "    }\n",
  77 |        "\n",
  78 |        "    .dataframe tbody tr th {\n",
  79 |        "        vertical-align: top;\n",
  80 |        "    }\n",
  81 |        "\n",
  82 |        "    .dataframe thead th {\n",
  83 |        "        text-align: right;\n",
  84 |        "    }\n",
  85 |        "</style>\n",
  86 |        "<table border=\"1\" class=\"dataframe\">\n",
  87 |        "  <thead>\n",
  88 |        "    <tr style=\"text-align: right;\">\n",
  89 |        "      <th></th>\n",
  90 |        "      <th>Time</th>\n",
  91 |        "      <th>V1</th>\n",
  92 |        "      <th>V2</th>\n",
  93 |        "      <th>V3</th>\n",
  94 |        "      <th>V4</th>\n",
  95 |        "      <th>V5</th>\n",
  96 |        "      <th>V6</th>\n",
  97 |        "      <th>V7</th>\n",
  98 |        "      <th>V8</th>\n",
  99 |        "      <th>V9</th>\n",
 100 |        "      <th>...</th>\n",
 101 |        "      <th>V21</th>\n",
 102 |        "      <th>V22</th>\n",
 103 |        "      <th>V23</th>\n",
 104 |        "      <th>V24</th>\n",
 105 |        "      <th>V25</th>\n",
 106 |        "      <th>V26</th>\n",
 107 |        "      <th>V27</th>\n",
 108 |        "      <th>V28</th>\n",
 109 |        "      <th>Amount</th>\n",
 110 |        "      <th>Class</th>\n",
 111 |        "    </tr>\n",
 112 |        "  </thead>\n",
 113 |        "  <tbody>\n",
 114 |        "    <tr>\n",
 115 |        "      <th>0</th>\n",
 116 |        "      <td>0.0</td>\n",
 117 |        "      <td>-1.359807</td>\n",
 118 |        "      <td>-0.072781</td>\n",
 119 |        "      <td>2.536347</td>\n",
 120 |        "      <td>1.378155</td>\n",
 121 |        "      <td>-0.338321</td>\n",
 122 |        "      <td>0.462388</td>\n",
 123 |        "      <td>0.239599</td>\n",
 124 |        "      <td>0.098698</td>\n",
 125 |        "      <td>0.363787</td>\n",
 126 |        "      <td>...</td>\n",
 127 |        "      <td>-0.018307</td>\n",
 128 |        "      <td>0.277838</td>\n",
 129 |        "      <td>-0.110474</td>\n",
 130 |        "      <td>0.066928</td>\n",
 131 |        "      <td>0.128539</td>\n",
 132 |        "      <td>-0.189115</td>\n",
 133 |        "      <td>0.133558</td>\n",
 134 |        "      <td>-0.021053</td>\n",
 135 |        "      <td>149.62</td>\n",
 136 |        "      <td>0</td>\n",
 137 |        "    </tr>\n",
 138 |        "    <tr>\n",
 139 |        "      <th>1</th>\n",
 140 |        "      <td>0.0</td>\n",
 141 |        "      <td>1.191857</td>\n",
 142 |        "      <td>0.266151</td>\n",
 143 |        "      <td>0.166480</td>\n",
 144 |        "      <td>0.448154</td>\n",
 145 |        "      <td>0.060018</td>\n",
 146 |        "      <td>-0.082361</td>\n",
 147 |        "      <td>-0.078803</td>\n",
 148 |        "      <td>0.085102</td>\n",
 149 |        "      <td>-0.255425</td>\n",
 150 |        "      <td>...</td>\n",
 151 |        "      <td>-0.225775</td>\n",
 152 |        "      <td>-0.638672</td>\n",
 153 |        "      <td>0.101288</td>\n",
 154 |        "      <td>-0.339846</td>\n",
 155 |        "      <td>0.167170</td>\n",
 156 |        "      <td>0.125895</td>\n",
 157 |        "      <td>-0.008983</td>\n",
 158 |        "      <td>0.014724</td>\n",
 159 |        "      <td>2.69</td>\n",
 160 |        "      <td>0</td>\n",
 161 |        "    </tr>\n",
 162 |        "    <tr>\n",
 163 |        "      <th>2</th>\n",
 164 |        "      <td>1.0</td>\n",
 165 |        "      <td>-1.358354</td>\n",
 166 |        "      <td>-1.340163</td>\n",
 167 |        "      <td>1.773209</td>\n",
 168 |        "      <td>0.379780</td>\n",
 169 |        "      <td>-0.503198</td>\n",
 170 |        "      <td>1.800499</td>\n",
 171 |        "      <td>0.791461</td>\n",
 172 |        "      <td>0.247676</td>\n",
 173 |        "      <td>-1.514654</td>\n",
 174 |        "      <td>...</td>\n",
 175 |        "      <td>0.247998</td>\n",
 176 |        "      <td>0.771679</td>\n",
 177 |        "      <td>0.909412</td>\n",
 178 |        "      <td>-0.689281</td>\n",
 179 |        "      <td>-0.327642</td>\n",
 180 |        "      <td>-0.139097</td>\n",
 181 |        "      <td>-0.055353</td>\n",
 182 |        "      <td>-0.059752</td>\n",
 183 |        "      <td>378.66</td>\n",
 184 |        "      <td>0</td>\n",
 185 |        "    </tr>\n",
 186 |        "    <tr>\n",
 187 |        "      <th>3</th>\n",
 188 |        "      <td>1.0</td>\n",
 189 |        "      <td>-0.966272</td>\n",
 190 |        "      <td>-0.185226</td>\n",
 191 |        "      <td>1.792993</td>\n",
 192 |        "      <td>-0.863291</td>\n",
 193 |        "      <td>-0.010309</td>\n",
 194 |        "      <td>1.247203</td>\n",
 195 |        "      <td>0.237609</td>\n",
 196 |        "      <td>0.377436</td>\n",
 197 |        "      <td>-1.387024</td>\n",
 198 |        "      <td>...</td>\n",
 199 |        "      <td>-0.108300</td>\n",
 200 |        "      <td>0.005274</td>\n",
 201 |        "      <td>-0.190321</td>\n",
 202 |        "      <td>-1.175575</td>\n",
 203 |        "      <td>0.647376</td>\n",
 204 |        "      <td>-0.221929</td>\n",
 205 |        "      <td>0.062723</td>\n",
 206 |        "      <td>0.061458</td>\n",
 207 |        "      <td>123.50</td>\n",
 208 |        "      <td>0</td>\n",
 209 |        "    </tr>\n",
 210 |        "    <tr>\n",
 211 |        "      <th>4</th>\n",
 212 |        "      <td>2.0</td>\n",
 213 |        "      <td>-1.158233</td>\n",
 214 |        "      <td>0.877737</td>\n",
 215 |        "      <td>1.548718</td>\n",
 216 |        "      <td>0.403034</td>\n",
 217 |        "      <td>-0.407193</td>\n",
 218 |        "      <td>0.095921</td>\n",
 219 |        "      <td>0.592941</td>\n",
 220 |        "      <td>-0.270533</td>\n",
 221 |        "      <td>0.817739</td>\n",
 222 |        "      <td>...</td>\n",
 223 |        "      <td>-0.009431</td>\n",
 224 |        "      <td>0.798278</td>\n",
 225 |        "      <td>-0.137458</td>\n",
 226 |        "      <td>0.141267</td>\n",
 227 |        "      <td>-0.206010</td>\n",
 228 |        "      <td>0.502292</td>\n",
 229 |        "      <td>0.219422</td>\n",
 230 |        "      <td>0.215153</td>\n",
 231 |        "      <td>69.99</td>\n",
 232 |        "      <td>0</td>\n",
 233 |        "    </tr>\n",
 234 |        "  </tbody>\n",
 235 |        "</table>\n",
 236 |        "<p>5 rows × 31 columns</p>\n",
 237 |        "</div>"
 238 |       ],
 239 |       "text/plain": [
 240 |        "   Time        V1        V2        V3        V4        V5        V6        V7  \\\n",
 241 |        "0   0.0 -1.359807 -0.072781  2.536347  1.378155 -0.338321  0.462388  0.239599   \n",
 242 |        "1   0.0  1.191857  0.266151  0.166480  0.448154  0.060018 -0.082361 -0.078803   \n",
 243 |        "2   1.0 -1.358354 -1.340163  1.773209  0.379780 -0.503198  1.800499  0.791461   \n",
 244 |        "3   1.0 -0.966272 -0.185226  1.792993 -0.863291 -0.010309  1.247203  0.237609   \n",
 245 |        "4   2.0 -1.158233  0.877737  1.548718  0.403034 -0.407193  0.095921  0.592941   \n",
 246 |        "\n",
 247 |        "         V8        V9  ...       V21       V22       V23       V24       V25  \\\n",
 248 |        "0  0.098698  0.363787  ... -0.018307  0.277838 -0.110474  0.066928  0.128539   \n",
 249 |        "1  0.085102 -0.255425  ... -0.225775 -0.638672  0.101288 -0.339846  0.167170   \n",
 250 |        "2  0.247676 -1.514654  ...  0.247998  0.771679  0.909412 -0.689281 -0.327642   \n",
 251 |        "3  0.377436 -1.387024  ... -0.108300  0.005274 -0.190321 -1.175575  0.647376   \n",
 252 |        "4 -0.270533  0.817739  ... -0.009431  0.798278 -0.137458  0.141267 -0.206010   \n",
 253 |        "\n",
 254 |        "        V26       V27       V28  Amount  Class  \n",
 255 |        "0 -0.189115  0.133558 -0.021053  149.62      0  \n",
 256 |        "1  0.125895 -0.008983  0.014724    2.69      0  \n",
 257 |        "2 -0.139097 -0.055353 -0.059752  378.66      0  \n",
 258 |        "3 -0.221929  0.062723  0.061458  123.50      0  \n",
 259 |        "4  0.502292  0.219422  0.215153   69.99      0  \n",
 260 |        "\n",
 261 |        "[5 rows x 31 columns]"
 262 |       ]
 263 |      },
 264 |      "execution_count": 5,
 265 |      "metadata": {},
 266 |      "output_type": "execute_result"
 267 |     }
 268 |    ],
 269 |    "source": [
 270 |     "### EDA ###\n",
 271 |     "\n",
 272 |     "# import dataset\n",
 273 |     "\n",
 274 |     "dataset = pd.read_csv(path_file)\n",
 275 |     "dataset.head()\n",
 276 |     "\n",
 277 |     "# If the Class column is 1 the transaction is Fraudulent\n",
 278 |     "# The IP Address was deleted from the dataset to preserve the anonymity"
 279 |    ]
 280 |   },
 281 |   {
 282 |    "cell_type": "code",
 283 |    "execution_count": 6,
 284 |    "metadata": {},
 285 |    "outputs": [
 286 |     {
 287 |      "data": {
 288 |       "text/html": [
 289 |        "<div>\n",
 290 |        "<style scoped>\n",
 291 |        "    .dataframe tbody tr th:only-of-type {\n",
 292 |        "        vertical-align: middle;\n",
 293 |        "    }\n",
 294 |        "\n",
 295 |        "    .dataframe tbody tr th {\n",
 296 |        "        vertical-align: top;\n",
 297 |        "    }\n",
 298 |        "\n",
 299 |        "    .dataframe thead th {\n",
 300 |        "        text-align: right;\n",
 301 |        "    }\n",
 302 |        "</style>\n",
 303 |        "<table border=\"1\" class=\"dataframe\">\n",
 304 |        "  <thead>\n",
 305 |        "    <tr style=\"text-align: right;\">\n",
 306 |        "      <th></th>\n",
 307 |        "      <th>Time</th>\n",
 308 |        "      <th>V1</th>\n",
 309 |        "      <th>V2</th>\n",
 310 |        "      <th>V3</th>\n",
 311 |        "      <th>V4</th>\n",
 312 |        "      <th>V5</th>\n",
 313 |        "      <th>V6</th>\n",
 314 |        "      <th>V7</th>\n",
 315 |        "      <th>V8</th>\n",
 316 |        "      <th>V9</th>\n",
 317 |        "      <th>...</th>\n",
 318 |        "      <th>V21</th>\n",
 319 |        "      <th>V22</th>\n",
 320 |        "      <th>V23</th>\n",
 321 |        "      <th>V24</th>\n",
 322 |        "      <th>V25</th>\n",
 323 |        "      <th>V26</th>\n",
 324 |        "      <th>V27</th>\n",
 325 |        "      <th>V28</th>\n",
 326 |        "      <th>Amount</th>\n",
 327 |        "      <th>Class</th>\n",
 328 |        "    </tr>\n",
 329 |        "  </thead>\n",
 330 |        "  <tbody>\n",
 331 |        "    <tr>\n",
 332 |        "      <th>count</th>\n",
 333 |        "      <td>284807.000000</td>\n",
 334 |        "      <td>2.848070e+05</td>\n",
 335 |        "      <td>2.848070e+05</td>\n",
 336 |        "      <td>2.848070e+05</td>\n",
 337 |        "      <td>2.848070e+05</td>\n",
 338 |        "      <td>2.848070e+05</td>\n",
 339 |        "      <td>2.848070e+05</td>\n",
 340 |        "      <td>2.848070e+05</td>\n",
 341 |        "      <td>2.848070e+05</td>\n",
 342 |        "      <td>2.848070e+05</td>\n",
 343 |        "      <td>...</td>\n",
 344 |        "      <td>2.848070e+05</td>\n",
 345 |        "      <td>2.848070e+05</td>\n",
 346 |        "      <td>2.848070e+05</td>\n",
 347 |        "      <td>2.848070e+05</td>\n",
 348 |        "      <td>2.848070e+05</td>\n",
 349 |        "      <td>2.848070e+05</td>\n",
 350 |        "      <td>2.848070e+05</td>\n",
 351 |        "      <td>2.848070e+05</td>\n",
 352 |        "      <td>284807.000000</td>\n",
 353 |        "      <td>284807.000000</td>\n",
 354 |        "    </tr>\n",
 355 |        "    <tr>\n",
 356 |        "      <th>mean</th>\n",
 357 |        "      <td>94813.859575</td>\n",
 358 |        "      <td>3.919560e-15</td>\n",
 359 |        "      <td>5.688174e-16</td>\n",
 360 |        "      <td>-8.769071e-15</td>\n",
 361 |        "      <td>2.782312e-15</td>\n",
 362 |        "      <td>-1.552563e-15</td>\n",
 363 |        "      <td>2.010663e-15</td>\n",
 364 |        "      <td>-1.694249e-15</td>\n",
 365 |        "      <td>-1.927028e-16</td>\n",
 366 |        "      <td>-3.137024e-15</td>\n",
 367 |        "      <td>...</td>\n",
 368 |        "      <td>1.537294e-16</td>\n",
 369 |        "      <td>7.959909e-16</td>\n",
 370 |        "      <td>5.367590e-16</td>\n",
 371 |        "      <td>4.458112e-15</td>\n",
 372 |        "      <td>1.453003e-15</td>\n",
 373 |        "      <td>1.699104e-15</td>\n",
 374 |        "      <td>-3.660161e-16</td>\n",
 375 |        "      <td>-1.206049e-16</td>\n",
 376 |        "      <td>88.349619</td>\n",
 377 |        "      <td>0.001727</td>\n",
 378 |        "    </tr>\n",
 379 |        "    <tr>\n",
 380 |        "      <th>std</th>\n",
 381 |        "      <td>47488.145955</td>\n",
 382 |        "      <td>1.958696e+00</td>\n",
 383 |        "      <td>1.651309e+00</td>\n",
 384 |        "      <td>1.516255e+00</td>\n",
 385 |        "      <td>1.415869e+00</td>\n",
 386 |        "      <td>1.380247e+00</td>\n",
 387 |        "      <td>1.332271e+00</td>\n",
 388 |        "      <td>1.237094e+00</td>\n",
 389 |        "      <td>1.194353e+00</td>\n",
 390 |        "      <td>1.098632e+00</td>\n",
 391 |        "      <td>...</td>\n",
 392 |        "      <td>7.345240e-01</td>\n",
 393 |        "      <td>7.257016e-01</td>\n",
 394 |        "      <td>6.244603e-01</td>\n",
 395 |        "      <td>6.056471e-01</td>\n",
 396 |        "      <td>5.212781e-01</td>\n",
 397 |        "      <td>4.822270e-01</td>\n",
 398 |        "      <td>4.036325e-01</td>\n",
 399 |        "      <td>3.300833e-01</td>\n",
 400 |        "      <td>250.120109</td>\n",
 401 |        "      <td>0.041527</td>\n",
 402 |        "    </tr>\n",
 403 |        "    <tr>\n",
 404 |        "      <th>min</th>\n",
 405 |        "      <td>0.000000</td>\n",
 406 |        "      <td>-5.640751e+01</td>\n",
 407 |        "      <td>-7.271573e+01</td>\n",
 408 |        "      <td>-4.832559e+01</td>\n",
 409 |        "      <td>-5.683171e+00</td>\n",
 410 |        "      <td>-1.137433e+02</td>\n",
 411 |        "      <td>-2.616051e+01</td>\n",
 412 |        "      <td>-4.355724e+01</td>\n",
 413 |        "      <td>-7.321672e+01</td>\n",
 414 |        "      <td>-1.343407e+01</td>\n",
 415 |        "      <td>...</td>\n",
 416 |        "      <td>-3.483038e+01</td>\n",
 417 |        "      <td>-1.093314e+01</td>\n",
 418 |        "      <td>-4.480774e+01</td>\n",
 419 |        "      <td>-2.836627e+00</td>\n",
 420 |        "      <td>-1.029540e+01</td>\n",
 421 |        "      <td>-2.604551e+00</td>\n",
 422 |        "      <td>-2.256568e+01</td>\n",
 423 |        "      <td>-1.543008e+01</td>\n",
 424 |        "      <td>0.000000</td>\n",
 425 |        "      <td>0.000000</td>\n",
 426 |        "    </tr>\n",
 427 |        "    <tr>\n",
 428 |        "      <th>25%</th>\n",
 429 |        "      <td>54201.500000</td>\n",
 430 |        "      <td>-9.203734e-01</td>\n",
 431 |        "      <td>-5.985499e-01</td>\n",
 432 |        "      <td>-8.903648e-01</td>\n",
 433 |        "      <td>-8.486401e-01</td>\n",
 434 |        "      <td>-6.915971e-01</td>\n",
 435 |        "      <td>-7.682956e-01</td>\n",
 436 |        "      <td>-5.540759e-01</td>\n",
 437 |        "      <td>-2.086297e-01</td>\n",
 438 |        "      <td>-6.430976e-01</td>\n",
 439 |        "      <td>...</td>\n",
 440 |        "      <td>-2.283949e-01</td>\n",
 441 |        "      <td>-5.423504e-01</td>\n",
 442 |        "      <td>-1.618463e-01</td>\n",
 443 |        "      <td>-3.545861e-01</td>\n",
 444 |        "      <td>-3.171451e-01</td>\n",
 445 |        "      <td>-3.269839e-01</td>\n",
 446 |        "      <td>-7.083953e-02</td>\n",
 447 |        "      <td>-5.295979e-02</td>\n",
 448 |        "      <td>5.600000</td>\n",
 449 |        "      <td>0.000000</td>\n",
 450 |        "    </tr>\n",
 451 |        "    <tr>\n",
 452 |        "      <th>50%</th>\n",
 453 |        "      <td>84692.000000</td>\n",
 454 |        "      <td>1.810880e-02</td>\n",
 455 |        "      <td>6.548556e-02</td>\n",
 456 |        "      <td>1.798463e-01</td>\n",
 457 |        "      <td>-1.984653e-02</td>\n",
 458 |        "      <td>-5.433583e-02</td>\n",
 459 |        "      <td>-2.741871e-01</td>\n",
 460 |        "      <td>4.010308e-02</td>\n",
 461 |        "      <td>2.235804e-02</td>\n",
 462 |        "      <td>-5.142873e-02</td>\n",
 463 |        "      <td>...</td>\n",
 464 |        "      <td>-2.945017e-02</td>\n",
 465 |        "      <td>6.781943e-03</td>\n",
 466 |        "      <td>-1.119293e-02</td>\n",
 467 |        "      <td>4.097606e-02</td>\n",
 468 |        "      <td>1.659350e-02</td>\n",
 469 |        "      <td>-5.213911e-02</td>\n",
 470 |        "      <td>1.342146e-03</td>\n",
 471 |        "      <td>1.124383e-02</td>\n",
 472 |        "      <td>22.000000</td>\n",
 473 |        "      <td>0.000000</td>\n",
 474 |        "    </tr>\n",
 475 |        "    <tr>\n",
 476 |        "      <th>75%</th>\n",
 477 |        "      <td>139320.500000</td>\n",
 478 |        "      <td>1.315642e+00</td>\n",
 479 |        "      <td>8.037239e-01</td>\n",
 480 |        "      <td>1.027196e+00</td>\n",
 481 |        "      <td>7.433413e-01</td>\n",
 482 |        "      <td>6.119264e-01</td>\n",
 483 |        "      <td>3.985649e-01</td>\n",
 484 |        "      <td>5.704361e-01</td>\n",
 485 |        "      <td>3.273459e-01</td>\n",
 486 |        "      <td>5.971390e-01</td>\n",
 487 |        "      <td>...</td>\n",
 488 |        "      <td>1.863772e-01</td>\n",
 489 |        "      <td>5.285536e-01</td>\n",
 490 |        "      <td>1.476421e-01</td>\n",
 491 |        "      <td>4.395266e-01</td>\n",
 492 |        "      <td>3.507156e-01</td>\n",
 493 |        "      <td>2.409522e-01</td>\n",
 494 |        "      <td>9.104512e-02</td>\n",
 495 |        "      <td>7.827995e-02</td>\n",
 496 |        "      <td>77.165000</td>\n",
 497 |        "      <td>0.000000</td>\n",
 498 |        "    </tr>\n",
 499 |        "    <tr>\n",
 500 |        "      <th>max</th>\n",
 501 |        "      <td>172792.000000</td>\n",
 502 |        "      <td>2.454930e+00</td>\n",
 503 |        "      <td>2.205773e+01</td>\n",
 504 |        "      <td>9.382558e+00</td>\n",
 505 |        "      <td>1.687534e+01</td>\n",
 506 |        "      <td>3.480167e+01</td>\n",
 507 |        "      <td>7.330163e+01</td>\n",
 508 |        "      <td>1.205895e+02</td>\n",
 509 |        "      <td>2.000721e+01</td>\n",
 510 |        "      <td>1.559499e+01</td>\n",
 511 |        "      <td>...</td>\n",
 512 |        "      <td>2.720284e+01</td>\n",
 513 |        "      <td>1.050309e+01</td>\n",
 514 |        "      <td>2.252841e+01</td>\n",
 515 |        "      <td>4.584549e+00</td>\n",
 516 |        "      <td>7.519589e+00</td>\n",
 517 |        "      <td>3.517346e+00</td>\n",
 518 |        "      <td>3.161220e+01</td>\n",
 519 |        "      <td>3.384781e+01</td>\n",
 520 |        "      <td>25691.160000</td>\n",
 521 |        "      <td>1.000000</td>\n",
 522 |        "    </tr>\n",
 523 |        "  </tbody>\n",
 524 |        "</table>\n",
 525 |        "<p>8 rows × 31 columns</p>\n",
 526 |        "</div>"
 527 |       ],
 528 |       "text/plain": [
 529 |        "                Time            V1            V2            V3            V4  \\\n",
 530 |        "count  284807.000000  2.848070e+05  2.848070e+05  2.848070e+05  2.848070e+05   \n",
 531 |        "mean    94813.859575  3.919560e-15  5.688174e-16 -8.769071e-15  2.782312e-15   \n",
 532 |        "std     47488.145955  1.958696e+00  1.651309e+00  1.516255e+00  1.415869e+00   \n",
 533 |        "min         0.000000 -5.640751e+01 -7.271573e+01 -4.832559e+01 -5.683171e+00   \n",
 534 |        "25%     54201.500000 -9.203734e-01 -5.985499e-01 -8.903648e-01 -8.486401e-01   \n",
 535 |        "50%     84692.000000  1.810880e-02  6.548556e-02  1.798463e-01 -1.984653e-02   \n",
 536 |        "75%    139320.500000  1.315642e+00  8.037239e-01  1.027196e+00  7.433413e-01   \n",
 537 |        "max    172792.000000  2.454930e+00  2.205773e+01  9.382558e+00  1.687534e+01   \n",
 538 |        "\n",
 539 |        "                 V5            V6            V7            V8            V9  \\\n",
 540 |        "count  2.848070e+05  2.848070e+05  2.848070e+05  2.848070e+05  2.848070e+05   \n",
 541 |        "mean  -1.552563e-15  2.010663e-15 -1.694249e-15 -1.927028e-16 -3.137024e-15   \n",
 542 |        "std    1.380247e+00  1.332271e+00  1.237094e+00  1.194353e+00  1.098632e+00   \n",
 543 |        "min   -1.137433e+02 -2.616051e+01 -4.355724e+01 -7.321672e+01 -1.343407e+01   \n",
 544 |        "25%   -6.915971e-01 -7.682956e-01 -5.540759e-01 -2.086297e-01 -6.430976e-01   \n",
 545 |        "50%   -5.433583e-02 -2.741871e-01  4.010308e-02  2.235804e-02 -5.142873e-02   \n",
 546 |        "75%    6.119264e-01  3.985649e-01  5.704361e-01  3.273459e-01  5.971390e-01   \n",
 547 |        "max    3.480167e+01  7.330163e+01  1.205895e+02  2.000721e+01  1.559499e+01   \n",
 548 |        "\n",
 549 |        "       ...           V21           V22           V23           V24  \\\n",
 550 |        "count  ...  2.848070e+05  2.848070e+05  2.848070e+05  2.848070e+05   \n",
 551 |        "mean   ...  1.537294e-16  7.959909e-16  5.367590e-16  4.458112e-15   \n",
 552 |        "std    ...  7.345240e-01  7.257016e-01  6.244603e-01  6.056471e-01   \n",
 553 |        "min    ... -3.483038e+01 -1.093314e+01 -4.480774e+01 -2.836627e+00   \n",
 554 |        "25%    ... -2.283949e-01 -5.423504e-01 -1.618463e-01 -3.545861e-01   \n",
 555 |        "50%    ... -2.945017e-02  6.781943e-03 -1.119293e-02  4.097606e-02   \n",
 556 |        "75%    ...  1.863772e-01  5.285536e-01  1.476421e-01  4.395266e-01   \n",
 557 |        "max    ...  2.720284e+01  1.050309e+01  2.252841e+01  4.584549e+00   \n",
 558 |        "\n",
 559 |        "                V25           V26           V27           V28         Amount  \\\n",
 560 |        "count  2.848070e+05  2.848070e+05  2.848070e+05  2.848070e+05  284807.000000   \n",
 561 |        "mean   1.453003e-15  1.699104e-15 -3.660161e-16 -1.206049e-16      88.349619   \n",
 562 |        "std    5.212781e-01  4.822270e-01  4.036325e-01  3.300833e-01     250.120109   \n",
 563 |        "min   -1.029540e+01 -2.604551e+00 -2.256568e+01 -1.543008e+01       0.000000   \n",
 564 |        "25%   -3.171451e-01 -3.269839e-01 -7.083953e-02 -5.295979e-02       5.600000   \n",
 565 |        "50%    1.659350e-02 -5.213911e-02  1.342146e-03  1.124383e-02      22.000000   \n",
 566 |        "75%    3.507156e-01  2.409522e-01  9.104512e-02  7.827995e-02      77.165000   \n",
 567 |        "max    7.519589e+00  3.517346e+00  3.161220e+01  3.384781e+01   25691.160000   \n",
 568 |        "\n",
 569 |        "               Class  \n",
 570 |        "count  284807.000000  \n",
 571 |        "mean        0.001727  \n",
 572 |        "std         0.041527  \n",
 573 |        "min         0.000000  \n",
 574 |        "25%         0.000000  \n",
 575 |        "50%         0.000000  \n",
 576 |        "75%         0.000000  \n",
 577 |        "max         1.000000  \n",
 578 |        "\n",
 579 |        "[8 rows x 31 columns]"
 580 |       ]
 581 |      },
 582 |      "execution_count": 6,
 583 |      "metadata": {},
 584 |      "output_type": "execute_result"
 585 |     }
 586 |    ],
 587 |    "source": [
 588 |     "dataset.describe()"
 589 |    ]
 590 |   },
 591 |   {
 592 |    "cell_type": "code",
 593 |    "execution_count": 7,
 594 |    "metadata": {},
 595 |    "outputs": [
 596 |     {
 597 |      "data": {
 598 |       "text/plain": [
 599 |        "Index(['Time', 'V1', 'V2', 'V3', 'V4', 'V5', 'V6', 'V7', 'V8', 'V9', 'V10',\n",
 600 |        "       'V11', 'V12', 'V13', 'V14', 'V15', 'V16', 'V17', 'V18', 'V19', 'V20',\n",
 601 |        "       'V21', 'V22', 'V23', 'V24', 'V25', 'V26', 'V27', 'V28', 'Amount',\n",
 602 |        "       'Class'],\n",
 603 |        "      dtype='object')"
 604 |       ]
 605 |      },
 606 |      "execution_count": 7,
 607 |      "metadata": {},
 608 |      "output_type": "execute_result"
 609 |     }
 610 |    ],
 611 |    "source": [
 612 |     "dataset.columns"
 613 |    ]
 614 |   },
 615 |   {
 616 |    "cell_type": "code",
 617 |    "execution_count": 12,
 618 |    "metadata": {},
 619 |    "outputs": [
 620 |     {
 621 |      "data": {
 622 |       "text/html": [
 623 |        "<div>\n",
 624 |        "<style scoped>\n",
 625 |        "    .dataframe tbody tr th:only-of-type {\n",
 626 |        "        vertical-align: middle;\n",
 627 |        "    }\n",
 628 |        "\n",
 629 |        "    .dataframe tbody tr th {\n",
 630 |        "        vertical-align: top;\n",
 631 |        "    }\n",
 632 |        "\n",
 633 |        "    .dataframe thead th {\n",
 634 |        "        text-align: right;\n",
 635 |        "    }\n",
 636 |        "</style>\n",
 637 |        "<table border=\"1\" class=\"dataframe\">\n",
 638 |        "  <thead>\n",
 639 |        "    <tr style=\"text-align: right;\">\n",
 640 |        "      <th></th>\n",
 641 |        "      <th>V1</th>\n",
 642 |        "      <th>V2</th>\n",
 643 |        "      <th>V3</th>\n",
 644 |        "      <th>V4</th>\n",
 645 |        "      <th>V5</th>\n",
 646 |        "      <th>V6</th>\n",
 647 |        "      <th>V7</th>\n",
 648 |        "      <th>V8</th>\n",
 649 |        "      <th>V9</th>\n",
 650 |        "      <th>V10</th>\n",
 651 |        "      <th>...</th>\n",
 652 |        "      <th>V21</th>\n",
 653 |        "      <th>V22</th>\n",
 654 |        "      <th>V23</th>\n",
 655 |        "      <th>V24</th>\n",
 656 |        "      <th>V25</th>\n",
 657 |        "      <th>V26</th>\n",
 658 |        "      <th>V27</th>\n",
 659 |        "      <th>V28</th>\n",
 660 |        "      <th>Class</th>\n",
 661 |        "      <th>normalizedAmount</th>\n",
 662 |        "    </tr>\n",
 663 |        "  </thead>\n",
 664 |        "  <tbody>\n",
 665 |        "    <tr>\n",
 666 |        "      <th>0</th>\n",
 667 |        "      <td>-1.359807</td>\n",
 668 |        "      <td>-0.072781</td>\n",
 669 |        "      <td>2.536347</td>\n",
 670 |        "      <td>1.378155</td>\n",
 671 |        "      <td>-0.338321</td>\n",
 672 |        "      <td>0.462388</td>\n",
 673 |        "      <td>0.239599</td>\n",
 674 |        "      <td>0.098698</td>\n",
 675 |        "      <td>0.363787</td>\n",
 676 |        "      <td>0.090794</td>\n",
 677 |        "      <td>...</td>\n",
 678 |        "      <td>-0.018307</td>\n",
 679 |        "      <td>0.277838</td>\n",
 680 |        "      <td>-0.110474</td>\n",
 681 |        "      <td>0.066928</td>\n",
 682 |        "      <td>0.128539</td>\n",
 683 |        "      <td>-0.189115</td>\n",
 684 |        "      <td>0.133558</td>\n",
 685 |        "      <td>-0.021053</td>\n",
 686 |        "      <td>0</td>\n",
 687 |        "      <td>0.244964</td>\n",
 688 |        "    </tr>\n",
 689 |        "    <tr>\n",
 690 |        "      <th>1</th>\n",
 691 |        "      <td>1.191857</td>\n",
 692 |        "      <td>0.266151</td>\n",
 693 |        "      <td>0.166480</td>\n",
 694 |        "      <td>0.448154</td>\n",
 695 |        "      <td>0.060018</td>\n",
 696 |        "      <td>-0.082361</td>\n",
 697 |        "      <td>-0.078803</td>\n",
 698 |        "      <td>0.085102</td>\n",
 699 |        "      <td>-0.255425</td>\n",
 700 |        "      <td>-0.166974</td>\n",
 701 |        "      <td>...</td>\n",
 702 |        "      <td>-0.225775</td>\n",
 703 |        "      <td>-0.638672</td>\n",
 704 |        "      <td>0.101288</td>\n",
 705 |        "      <td>-0.339846</td>\n",
 706 |        "      <td>0.167170</td>\n",
 707 |        "      <td>0.125895</td>\n",
 708 |        "      <td>-0.008983</td>\n",
 709 |        "      <td>0.014724</td>\n",
 710 |        "      <td>0</td>\n",
 711 |        "      <td>-0.342475</td>\n",
 712 |        "    </tr>\n",
 713 |        "    <tr>\n",
 714 |        "      <th>2</th>\n",
 715 |        "      <td>-1.358354</td>\n",
 716 |        "      <td>-1.340163</td>\n",
 717 |        "      <td>1.773209</td>\n",
 718 |        "      <td>0.379780</td>\n",
 719 |        "      <td>-0.503198</td>\n",
 720 |        "      <td>1.800499</td>\n",
 721 |        "      <td>0.791461</td>\n",
 722 |        "      <td>0.247676</td>\n",
 723 |        "      <td>-1.514654</td>\n",
 724 |        "      <td>0.207643</td>\n",
 725 |        "      <td>...</td>\n",
 726 |        "      <td>0.247998</td>\n",
 727 |        "      <td>0.771679</td>\n",
 728 |        "      <td>0.909412</td>\n",
 729 |        "      <td>-0.689281</td>\n",
 730 |        "      <td>-0.327642</td>\n",
 731 |        "      <td>-0.139097</td>\n",
 732 |        "      <td>-0.055353</td>\n",
 733 |        "      <td>-0.059752</td>\n",
 734 |        "      <td>0</td>\n",
 735 |        "      <td>1.160686</td>\n",
 736 |        "    </tr>\n",
 737 |        "    <tr>\n",
 738 |        "      <th>3</th>\n",
 739 |        "      <td>-0.966272</td>\n",
 740 |        "      <td>-0.185226</td>\n",
 741 |        "      <td>1.792993</td>\n",
 742 |        "      <td>-0.863291</td>\n",
 743 |        "      <td>-0.010309</td>\n",
 744 |        "      <td>1.247203</td>\n",
 745 |        "      <td>0.237609</td>\n",
 746 |        "      <td>0.377436</td>\n",
 747 |        "      <td>-1.387024</td>\n",
 748 |        "      <td>-0.054952</td>\n",
 749 |        "      <td>...</td>\n",
 750 |        "      <td>-0.108300</td>\n",
 751 |        "      <td>0.005274</td>\n",
 752 |        "      <td>-0.190321</td>\n",
 753 |        "      <td>-1.175575</td>\n",
 754 |        "      <td>0.647376</td>\n",
 755 |        "      <td>-0.221929</td>\n",
 756 |        "      <td>0.062723</td>\n",
 757 |        "      <td>0.061458</td>\n",
 758 |        "      <td>0</td>\n",
 759 |        "      <td>0.140534</td>\n",
 760 |        "    </tr>\n",
 761 |        "    <tr>\n",
 762 |        "      <th>4</th>\n",
 763 |        "      <td>-1.158233</td>\n",
 764 |        "      <td>0.877737</td>\n",
 765 |        "      <td>1.548718</td>\n",
 766 |        "      <td>0.403034</td>\n",
 767 |        "      <td>-0.407193</td>\n",
 768 |        "      <td>0.095921</td>\n",
 769 |        "      <td>0.592941</td>\n",
 770 |        "      <td>-0.270533</td>\n",
 771 |        "      <td>0.817739</td>\n",
 772 |        "      <td>0.753074</td>\n",
 773 |        "      <td>...</td>\n",
 774 |        "      <td>-0.009431</td>\n",
 775 |        "      <td>0.798278</td>\n",
 776 |        "      <td>-0.137458</td>\n",
 777 |        "      <td>0.141267</td>\n",
 778 |        "      <td>-0.206010</td>\n",
 779 |        "      <td>0.502292</td>\n",
 780 |        "      <td>0.219422</td>\n",
 781 |        "      <td>0.215153</td>\n",
 782 |        "      <td>0</td>\n",
 783 |        "      <td>-0.073403</td>\n",
 784 |        "    </tr>\n",
 785 |        "  </tbody>\n",
 786 |        "</table>\n",
 787 |        "<p>5 rows × 30 columns</p>\n",
 788 |        "</div>"
 789 |       ],
 790 |       "text/plain": [
 791 |        "         V1        V2        V3        V4        V5        V6        V7  \\\n",
 792 |        "0 -1.359807 -0.072781  2.536347  1.378155 -0.338321  0.462388  0.239599   \n",
 793 |        "1  1.191857  0.266151  0.166480  0.448154  0.060018 -0.082361 -0.078803   \n",
 794 |        "2 -1.358354 -1.340163  1.773209  0.379780 -0.503198  1.800499  0.791461   \n",
 795 |        "3 -0.966272 -0.185226  1.792993 -0.863291 -0.010309  1.247203  0.237609   \n",
 796 |        "4 -1.158233  0.877737  1.548718  0.403034 -0.407193  0.095921  0.592941   \n",
 797 |        "\n",
 798 |        "         V8        V9       V10  ...       V21       V22       V23       V24  \\\n",
 799 |        "0  0.098698  0.363787  0.090794  ... -0.018307  0.277838 -0.110474  0.066928   \n",
 800 |        "1  0.085102 -0.255425 -0.166974  ... -0.225775 -0.638672  0.101288 -0.339846   \n",
 801 |        "2  0.247676 -1.514654  0.207643  ...  0.247998  0.771679  0.909412 -0.689281   \n",
 802 |        "3  0.377436 -1.387024 -0.054952  ... -0.108300  0.005274 -0.190321 -1.175575   \n",
 803 |        "4 -0.270533  0.817739  0.753074  ... -0.009431  0.798278 -0.137458  0.141267   \n",
 804 |        "\n",
 805 |        "        V25       V26       V27       V28  Class  normalizedAmount  \n",
 806 |        "0  0.128539 -0.189115  0.133558 -0.021053      0          0.244964  \n",
 807 |        "1  0.167170  0.125895 -0.008983  0.014724      0         -0.342475  \n",
 808 |        "2 -0.327642 -0.139097 -0.055353 -0.059752      0          1.160686  \n",
 809 |        "3  0.647376 -0.221929  0.062723  0.061458      0          0.140534  \n",
 810 |        "4 -0.206010  0.502292  0.219422  0.215153      0         -0.073403  \n",
 811 |        "\n",
 812 |        "[5 rows x 30 columns]"
 813 |       ]
 814 |      },
 815 |      "execution_count": 12,
 816 |      "metadata": {},
 817 |      "output_type": "execute_result"
 818 |     }
 819 |    ],
 820 |    "source": [
 821 |     "## Prepocessing \n",
 822 |     "from sklearn.preprocessing import StandardScaler\n",
 823 |     "\n",
 824 |     "# Create a new copy\n",
 825 |     "dataset2 = dataset\n",
 826 |     "# Normalizace the Amount between -1,1\n",
 827 |     "dataset2['normalizedAmount'] = StandardScaler().fit_transform(dataset2['Amount'].values.reshape(-1,1))\n",
 828 |     "\n",
 829 |     "dataset2 = dataset2.drop(columns = ['Amount','Time'])\n",
 830 |     "dataset2.head()"
 831 |    ]
 832 |   },
 833 |   {
 834 |    "cell_type": "code",
 835 |    "execution_count": 14,
 836 |    "metadata": {},
 837 |    "outputs": [],
 838 |    "source": [
 839 |     "## Define the training data and the responde variable from the dataset\n",
 840 |     "y = dataset2['Class']\n",
 841 |     "X = dataset2.drop(columns = ['Class'])"
 842 |    ]
 843 |   },
 844 |   {
 845 |    "cell_type": "code",
 846 |    "execution_count": 17,
 847 |    "metadata": {},
 848 |    "outputs": [],
 849 |    "source": [
 850 |     "# Generate the Split train/test datasets\n",
 851 |     "from sklearn.model_selection import train_test_split\n",
 852 |     "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.3, random_state=0)"
 853 |    ]
 854 |   },
 855 |   {
 856 |    "cell_type": "code",
 857 |    "execution_count": 18,
 858 |    "metadata": {},
 859 |    "outputs": [
 860 |     {
 861 |      "data": {
 862 |       "text/plain": [
 863 |        "(199364, 29)"
 864 |       ]
 865 |      },
 866 |      "execution_count": 18,
 867 |      "metadata": {},
 868 |      "output_type": "execute_result"
 869 |     }
 870 |    ],
 871 |    "source": [
 872 |     "X_train.shape"
 873 |    ]
 874 |   },
 875 |   {
 876 |    "cell_type": "code",
 877 |    "execution_count": 19,
 878 |    "metadata": {},
 879 |    "outputs": [
 880 |     {
 881 |      "data": {
 882 |       "text/plain": [
 883 |        "(85443, 29)"
 884 |       ]
 885 |      },
 886 |      "execution_count": 19,
 887 |      "metadata": {},
 888 |      "output_type": "execute_result"
 889 |     }
 890 |    ],
 891 |    "source": [
 892 |     "X_test.shape"
 893 |    ]
 894 |   },
 895 |   {
 896 |    "cell_type": "code",
 897 |    "execution_count": 20,
 898 |    "metadata": {},
 899 |    "outputs": [],
 900 |    "source": [
 901 |     "# convert split sets to arrays\n",
 902 |     "X_train = np.array(X_train)\n",
 903 |     "X_test = np.array(X_test)\n",
 904 |     "y_train = np.array(y_train)\n",
 905 |     "y_test = np.array(y_test)"
 906 |    ]
 907 |   },
 908 |   {
 909 |    "cell_type": "code",
 910 |    "execution_count": 39,
 911 |    "metadata": {},
 912 |    "outputs": [],
 913 |    "source": [
 914 |     "### Deep Neural Network\n",
 915 |     "\n",
 916 |     "# import keras layers, optimizer & callbacks\n",
 917 |     "from tensorflow.keras import Sequential\n",
 918 |     "from tensorflow.keras.layers import Conv2D, MaxPooling2D, Dense, Flatten, Dropout"
 919 |    ]
 920 |   },
 921 |   {
 922 |    "cell_type": "code",
 923 |    "execution_count": 47,
 924 |    "metadata": {},
 925 |    "outputs": [
 926 |     {
 927 |      "name": "stdout",
 928 |      "output_type": "stream",
 929 |      "text": [
 930 |       "Model: \"sequential_5\"\n",
 931 |       "_________________________________________________________________\n",
 932 |       "Layer (type)                 Output Shape              Param #   \n",
 933 |       "=================================================================\n",
 934 |       "dense_19 (Dense)             (None, 16)                480       \n",
 935 |       "_________________________________________________________________\n",
 936 |       "dense_20 (Dense)             (None, 24)                408       \n",
 937 |       "_________________________________________________________________\n",
 938 |       "dropout_3 (Dropout)          (None, 24)                0         \n",
 939 |       "_________________________________________________________________\n",
 940 |       "dense_21 (Dense)             (None, 20)                500       \n",
 941 |       "_________________________________________________________________\n",
 942 |       "dense_22 (Dense)             (None, 24)                504       \n",
 943 |       "_________________________________________________________________\n",
 944 |       "dense_23 (Dense)             (None, 1)                 25        \n",
 945 |       "=================================================================\n",
 946 |       "Total params: 1,917\n",
 947 |       "Trainable params: 1,917\n",
 948 |       "Non-trainable params: 0\n",
 949 |       "_________________________________________________________________\n"
 950 |      ]
 951 |     }
 952 |    ],
 953 |    "source": [
 954 |     "# Create DNN model\n",
 955 |     "dnn_model = Sequential()\n",
 956 |     "\n",
 957 |     "# First stage of Dense layers\n",
 958 |     "dnn_model.add(Dense(units=16, input_dim=29,activation='relu'))\n",
 959 |     "dnn_model.add(Dense(units=24, activation='relu'))\n",
 960 |     "\n",
 961 |     "# Dropout to avoid oferfitting\n",
 962 |     "dnn_model.add(Dropout(rate=0.4))\n",
 963 |     "\n",
 964 |     "# Second stage of Dense layers\n",
 965 |     "dnn_model.add(Dense(units=20,activation='relu'))\n",
 966 |     "dnn_model.add(Dense(units=24,activation='relu'))\n",
 967 |     "# Last layer with sigmoid activation. Binary decision\n",
 968 |     "dnn_model.add(Dense(units=1,activation='sigmoid'))\n",
 969 |     "\n",
 970 |     "#Summary the model\n",
 971 |     "dnn_model.summary() \n"
 972 |    ]
 973 |   },
 974 |   {
 975 |    "cell_type": "code",
 976 |    "execution_count": 50,
 977 |    "metadata": {},
 978 |    "outputs": [],
 979 |    "source": [
 980 |     "### Training ###\n",
 981 |     "\n",
 982 |     "# Define the compile trainning params\n",
 983 |     "dnn_model.compile(optimizer='adam',loss='binary_crossentropy',metrics=['accuracy'])"
 984 |    ]
 985 |   },
 986 |   {
 987 |    "cell_type": "code",
 988 |    "execution_count": 53,
 989 |    "metadata": {},
 990 |    "outputs": [
 991 |     {
 992 |      "name": "stdout",
 993 |      "output_type": "stream",
 994 |      "text": [
 995 |       "Epoch 1/5\n",
 996 |       "199364/199364 [==============================] - 15s 76us/sample - loss: 0.0038 - acc: 0.9993\n",
 997 |       "Epoch 2/5\n",
 998 |       "199364/199364 [==============================] - 16s 80us/sample - loss: 0.0036 - acc: 0.9994\n",
 999 |       "Epoch 3/5\n",
1000 |       "199364/199364 [==============================] - 16s 81us/sample - loss: 0.0034 - acc: 0.9994\n",
1001 |       "Epoch 4/5\n",
1002 |       "199364/199364 [==============================] - 16s 81us/sample - loss: 0.0032 - acc: 0.9994\n",
1003 |       "Epoch 5/5\n",
1004 |       "199364/199364 [==============================] - 15s 77us/sample - loss: 0.0032 - acc: 0.9994\n"
1005 |      ]
1006 |     },
1007 |     {
1008 |      "data": {
1009 |       "text/plain": [
1010 |        "<tensorflow.python.keras.callbacks.History at 0x23e822b24c8>"
1011 |       ]
1012 |      },
1013 |      "execution_count": 53,
1014 |      "metadata": {},
1015 |      "output_type": "execute_result"
1016 |     }
1017 |    ],
1018 |    "source": [
1019 |     "# train the model\n",
1020 |     "dnn_model.fit(X_train, \n",
1021 |     "              y_train, \n",
1022 |     "              batch_size= 15,\n",
1023 |     "              epochs = 5)"
1024 |    ]
1025 |   },
1026 |   {
1027 |    "cell_type": "code",
1028 |    "execution_count": 54,
1029 |    "metadata": {},
1030 |    "outputs": [
1031 |     {
1032 |      "name": "stdout",
1033 |      "output_type": "stream",
1034 |      "text": [
1035 |       "85443/85443 [==============================] - 2s 18us/sample - loss: 0.0039 - acc: 0.9994\n"
1036 |      ]
1037 |     }
1038 |    ],
1039 |    "source": [
1040 |     "## DNN model evaluation\n",
1041 |     "score = dnn_model.evaluate(X_test,y_test)"
1042 |    ]
1043 |   },
1044 |   {
1045 |    "cell_type": "code",
1046 |    "execution_count": 55,
1047 |    "metadata": {},
1048 |    "outputs": [
1049 |     {
1050 |      "name": "stdout",
1051 |      "output_type": "stream",
1052 |      "text": [
1053 |       "[0.003928133984745635, 0.99939144]\n"
1054 |      ]
1055 |     }
1056 |    ],
1057 |    "source": [
1058 |     "# Print eval result \n",
1059 |     "print(score)"
1060 |    ]
1061 |   },
1062 |   {
1063 |    "cell_type": "code",
1064 |    "execution_count": null,
1065 |    "metadata": {},
1066 |    "outputs": [],
1067 |    "source": [
1068 |     "## Metrics -->\n",
1069 |     "\n",
1070 |     "# Accuracy: (TRUE Positives + TRUE Negatives) / Total\n",
1071 |     "# Precision: TRUE Positives / (TRUE Positives + FALSE Positives)\n",
1072 |     "# Specificity: TRUE Negatives / (FALSE Positives + TRUE Negatives)\n",
1073 |     "# Recall: TRUE Positives / (TRUE Positives + FALSE Negatives)\n",
1074 |     "# F1-score:"
1075 |    ]
1076 |   },
1077 |   {
1078 |    "cell_type": "code",
1079 |    "execution_count": 75,
1080 |    "metadata": {},
1081 |    "outputs": [],
1082 |    "source": [
1083 |     "# Getting the prediction from the test dataset\n",
1084 |     "y_pred = dnn_model.predict(X_test).round()\n",
1085 |     "# convert array to dataframe\n",
1086 |     "y_test = pd.DataFrame(y_test)"
1087 |    ]
1088 |   },
1089 |   {
1090 |    "cell_type": "code",
1091 |    "execution_count": 78,
1092 |    "metadata": {},
1093 |    "outputs": [],
1094 |    "source": [
1095 |     "# Evaluate the quality of the model\n",
1096 |     "from sklearn.metrics import confusion_matrix, accuracy_score, f1_score, precision_score, recall_score\n",
1097 |     "\n",
1098 |     "cnf_matrix = confusion_matrix(y_test, y_pred)"
1099 |    ]
1100 |   },
1101 |   {
1102 |    "cell_type": "code",
1103 |    "execution_count": 79,
1104 |    "metadata": {},
1105 |    "outputs": [],
1106 |    "source": [
1107 |     "# Accuracy score\n",
1108 |     "acc = accuracy_score(y_test, y_pred)"
1109 |    ]
1110 |   },
1111 |   {
1112 |    "cell_type": "code",
1113 |    "execution_count": 80,
1114 |    "metadata": {},
1115 |    "outputs": [],
1116 |    "source": [
1117 |     "# precision score (When is 0 and should be 1 and the other way round)\n",
1118 |     "pre = precision_score(y_test, y_pred)"
1119 |    ]
1120 |   },
1121 |   {
1122 |    "cell_type": "code",
1123 |    "execution_count": 81,
1124 |    "metadata": {},
1125 |    "outputs": [],
1126 |    "source": [
1127 |     "# recall score\n",
1128 |     "rec = recall_score(y_test, y_pred)"
1129 |    ]
1130 |   },
1131 |   {
1132 |    "cell_type": "code",
1133 |    "execution_count": 82,
1134 |    "metadata": {},
1135 |    "outputs": [],
1136 |    "source": [
1137 |     "f1 = f1_score(y_test, y_pred)"
1138 |    ]
1139 |   },
1140 |   {
1141 |    "cell_type": "code",
1142 |    "execution_count": 83,
1143 |    "metadata": {},
1144 |    "outputs": [
1145 |     {
1146 |      "data": {
1147 |       "text/html": [
1148 |        "<div>\n",
1149 |        "<style scoped>\n",
1150 |        "    .dataframe tbody tr th:only-of-type {\n",
1151 |        "        vertical-align: middle;\n",
1152 |        "    }\n",
1153 |        "\n",
1154 |        "    .dataframe tbody tr th {\n",
1155 |        "        vertical-align: top;\n",
1156 |        "    }\n",
1157 |        "\n",
1158 |        "    .dataframe thead th {\n",
1159 |        "        text-align: right;\n",
1160 |        "    }\n",
1161 |        "</style>\n",
1162 |        "<table border=\"1\" class=\"dataframe\">\n",
1163 |        "  <thead>\n",
1164 |        "    <tr style=\"text-align: right;\">\n",
1165 |        "      <th></th>\n",
1166 |        "      <th>Model</th>\n",
1167 |        "      <th>Accuracy</th>\n",
1168 |        "      <th>Precision</th>\n",
1169 |        "      <th>Recall</th>\n",
1170 |        "      <th>F1 score</th>\n",
1171 |        "    </tr>\n",
1172 |        "  </thead>\n",
1173 |        "  <tbody>\n",
1174 |        "    <tr>\n",
1175 |        "      <th>0</th>\n",
1176 |        "      <td>Deep Neural Network</td>\n",
1177 |        "      <td>0.999391</td>\n",
1178 |        "      <td>0.836879</td>\n",
1179 |        "      <td>0.802721</td>\n",
1180 |        "      <td>0.819444</td>\n",
1181 |        "    </tr>\n",
1182 |        "  </tbody>\n",
1183 |        "</table>\n",
1184 |        "</div>"
1185 |       ],
1186 |       "text/plain": [
1187 |        "                 Model  Accuracy  Precision    Recall  F1 score\n",
1188 |        "0  Deep Neural Network  0.999391   0.836879  0.802721  0.819444"
1189 |       ]
1190 |      },
1191 |      "execution_count": 83,
1192 |      "metadata": {},
1193 |      "output_type": "execute_result"
1194 |     }
1195 |    ],
1196 |    "source": [
1197 |     "# Metrics\n",
1198 |     "results = pd.DataFrame([['Deep Neural Network', acc, pre, rec, f1]],\n",
1199 |     "              columns = ['Model','Accuracy','Precision','Recall','F1 score'])\n",
1200 |     "\n",
1201 |     "results"
1202 |    ]
1203 |   },
1204 |   {
1205 |    "cell_type": "code",
1206 |    "execution_count": 84,
1207 |    "metadata": {},
1208 |    "outputs": [
1209 |     {
1210 |      "name": "stdout",
1211 |      "output_type": "stream",
1212 |      "text": [
1213 |       "Accuracy 0.9994\n"
1214 |      ]
1215 |     },
1216 |     {
1217 |      "data": {
1218 |       "image/png": "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\n",
1219 |       "text/plain": [
1220 |        "<Figure size 432x288 with 2 Axes>"
1221 |       ]
1222 |      },
1223 |      "metadata": {
1224 |       "needs_background": "light"
1225 |      },
1226 |      "output_type": "display_data"
1227 |     }
1228 |    ],
1229 |    "source": [
1230 |     "# Plot the confussion Matrix\n",
1231 |     "\n",
1232 |     "class_names=[0,1] # name  of classes\n",
1233 |     "fig, ax = plt.subplots()\n",
1234 |     "tick_marks = np.arange(len(class_names))\n",
1235 |     "plt.xticks(tick_marks, class_names)\n",
1236 |     "plt.yticks(tick_marks, class_names)\n",
1237 |     "\n",
1238 |     "# create heatmap\n",
1239 |     "sns.heatmap(pd.DataFrame(cnf_matrix), annot=True, cmap=\"YlGnBu\" ,fmt='g')\n",
1240 |     "ax.xaxis.set_label_position(\"top\")\n",
1241 |     "plt.tight_layout()\n",
1242 |     "plt.title('Confusion matrix', y=1.1)\n",
1243 |     "plt.ylabel('Actual label')\n",
1244 |     "plt.xlabel('Predicted label')\n",
1245 |     "print(\"Accuracy %0.4f\" % accuracy_score(y_test, y_pred))"
1246 |    ]
1247 |   },
1248 |   {
1249 |    "cell_type": "code",
1250 |    "execution_count": 87,
1251 |    "metadata": {},
1252 |    "outputs": [],
1253 |    "source": [
1254 |     "## Round 2: Random Forest Classification\n",
1255 |     "from sklearn.ensemble import RandomForestClassifier"
1256 |    ]
1257 |   },
1258 |   {
1259 |    "cell_type": "code",
1260 |    "execution_count": 89,
1261 |    "metadata": {},
1262 |    "outputs": [
1263 |     {
1264 |      "data": {
1265 |       "text/plain": [
1266 |        "RandomForestClassifier(bootstrap=True, class_weight=None, criterion='entropy',\n",
1267 |        "                       max_depth=None, max_features='auto', max_leaf_nodes=None,\n",
1268 |        "                       min_impurity_decrease=0.0, min_impurity_split=None,\n",
1269 |        "                       min_samples_leaf=1, min_samples_split=2,\n",
1270 |        "                       min_weight_fraction_leaf=0.0, n_estimators=100,\n",
1271 |        "                       n_jobs=None, oob_score=False, random_state=0, verbose=0,\n",
1272 |        "                       warm_start=False)"
1273 |       ]
1274 |      },
1275 |      "execution_count": 89,
1276 |      "metadata": {},
1277 |      "output_type": "execute_result"
1278 |     }
1279 |    ],
1280 |    "source": [
1281 |     "# set parameters of RF and Fit\n",
1282 |     "random_forest = RandomForestClassifier(n_estimators = 100)\n",
1283 |     "\n",
1284 |     "classifier = RandomForestClassifier(random_state=0, n_estimators = 100,\n",
1285 |     "                                   criterion = 'entropy')\n",
1286 |     "classifier.fit(X_train, y_train)"
1287 |    ]
1288 |   },
1289 |   {
1290 |    "cell_type": "code",
1291 |    "execution_count": 90,
1292 |    "metadata": {},
1293 |    "outputs": [],
1294 |    "source": [
1295 |     "# Evaluating Test set\n",
1296 |     "y_pred = classifier.predict(X_test)"
1297 |    ]
1298 |   },
1299 |   {
1300 |    "cell_type": "code",
1301 |    "execution_count": 91,
1302 |    "metadata": {},
1303 |    "outputs": [],
1304 |    "source": [
1305 |     "# Calculation of metrics\n",
1306 |     "\n",
1307 |     "# Accuracy score\n",
1308 |     "acc = accuracy_score(y_test, y_pred)\n",
1309 |     "\n",
1310 |     "# precision score (When is 0 and should be 1 and the other way round)\n",
1311 |     "pre = precision_score(y_test, y_pred)\n",
1312 |     "\n",
1313 |     "# recall score\n",
1314 |     "rec = recall_score(y_test, y_pred)\n",
1315 |     "\n",
1316 |     "f1 = f1_score(y_test, y_pred)"
1317 |    ]
1318 |   },
1319 |   {
1320 |    "cell_type": "code",
1321 |    "execution_count": 92,
1322 |    "metadata": {},
1323 |    "outputs": [],
1324 |    "source": [
1325 |     "# Metrics \n",
1326 |     "rf_results = pd.DataFrame([['Random Forest (n=100, GSx2 + Entropy)', acc, pre, rec, f1]],\n",
1327 |     "              columns = ['Model','Accuracy','Precision','Recall','F1 score'])"
1328 |    ]
1329 |   },
1330 |   {
1331 |    "cell_type": "code",
1332 |    "execution_count": 93,
1333 |    "metadata": {
1334 |     "scrolled": true
1335 |    },
1336 |    "outputs": [
1337 |     {
1338 |      "data": {
1339 |       "text/html": [
1340 |        "<div>\n",
1341 |        "<style scoped>\n",
1342 |        "    .dataframe tbody tr th:only-of-type {\n",
1343 |        "        vertical-align: middle;\n",
1344 |        "    }\n",
1345 |        "\n",
1346 |        "    .dataframe tbody tr th {\n",
1347 |        "        vertical-align: top;\n",
1348 |        "    }\n",
1349 |        "\n",
1350 |        "    .dataframe thead th {\n",
1351 |        "        text-align: right;\n",
1352 |        "    }\n",
1353 |        "</style>\n",
1354 |        "<table border=\"1\" class=\"dataframe\">\n",
1355 |        "  <thead>\n",
1356 |        "    <tr style=\"text-align: right;\">\n",
1357 |        "      <th></th>\n",
1358 |        "      <th>Model</th>\n",
1359 |        "      <th>Accuracy</th>\n",
1360 |        "      <th>Precision</th>\n",
1361 |        "      <th>Recall</th>\n",
1362 |        "      <th>F1 score</th>\n",
1363 |        "    </tr>\n",
1364 |        "  </thead>\n",
1365 |        "  <tbody>\n",
1366 |        "    <tr>\n",
1367 |        "      <th>0</th>\n",
1368 |        "      <td>Deep Neural Network</td>\n",
1369 |        "      <td>0.999391</td>\n",
1370 |        "      <td>0.836879</td>\n",
1371 |        "      <td>0.802721</td>\n",
1372 |        "      <td>0.819444</td>\n",
1373 |        "    </tr>\n",
1374 |        "    <tr>\n",
1375 |        "      <th>1</th>\n",
1376 |        "      <td>Random Forest (n=100, GSx2 + Entropy)</td>\n",
1377 |        "      <td>0.999520</td>\n",
1378 |        "      <td>0.941667</td>\n",
1379 |        "      <td>0.768707</td>\n",
1380 |        "      <td>0.846442</td>\n",
1381 |        "    </tr>\n",
1382 |        "  </tbody>\n",
1383 |        "</table>\n",
1384 |        "</div>"
1385 |       ],
1386 |       "text/plain": [
1387 |        "                                   Model  Accuracy  Precision    Recall  \\\n",
1388 |        "0                    Deep Neural Network  0.999391   0.836879  0.802721   \n",
1389 |        "1  Random Forest (n=100, GSx2 + Entropy)  0.999520   0.941667  0.768707   \n",
1390 |        "\n",
1391 |        "   F1 score  \n",
1392 |        "0  0.819444  \n",
1393 |        "1  0.846442  "
1394 |       ]
1395 |      },
1396 |      "execution_count": 93,
1397 |      "metadata": {},
1398 |      "output_type": "execute_result"
1399 |     }
1400 |    ],
1401 |    "source": [
1402 |     "# Showing the comparizon between the Models\n",
1403 |     "\n",
1404 |     "results = results.append(rf_results, ignore_index = True)\n",
1405 |     "\n",
1406 |     "results "
1407 |    ]
1408 |   },
1409 |   {
1410 |    "cell_type": "code",
1411 |    "execution_count": 94,
1412 |    "metadata": {},
1413 |    "outputs": [],
1414 |    "source": [
1415 |     "## Round 3: Decision Tree\n",
1416 |     "from sklearn.tree import DecisionTreeClassifier"
1417 |    ]
1418 |   },
1419 |   {
1420 |    "cell_type": "code",
1421 |    "execution_count": 95,
1422 |    "metadata": {},
1423 |    "outputs": [
1424 |     {
1425 |      "data": {
1426 |       "text/plain": [
1427 |        "DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,\n",
1428 |        "                       max_features=None, max_leaf_nodes=None,\n",
1429 |        "                       min_impurity_decrease=0.0, min_impurity_split=None,\n",
1430 |        "                       min_samples_leaf=1, min_samples_split=2,\n",
1431 |        "                       min_weight_fraction_leaf=0.0, presort=False,\n",
1432 |        "                       random_state=None, splitter='best')"
1433 |       ]
1434 |      },
1435 |      "execution_count": 95,
1436 |      "metadata": {},
1437 |      "output_type": "execute_result"
1438 |     }
1439 |    ],
1440 |    "source": [
1441 |     "# set parameters of DecisionTree and Fit\n",
1442 |     "classifier = DecisionTreeClassifier()\n",
1443 |     "classifier.fit(X_train, y_train)"
1444 |    ]
1445 |   },
1446 |   {
1447 |    "cell_type": "code",
1448 |    "execution_count": 96,
1449 |    "metadata": {},
1450 |    "outputs": [],
1451 |    "source": [
1452 |     "# Evaluating Test set\n",
1453 |     "y_pred = classifier.predict(X_test)"
1454 |    ]
1455 |   },
1456 |   {
1457 |    "cell_type": "code",
1458 |    "execution_count": 97,
1459 |    "metadata": {},
1460 |    "outputs": [],
1461 |    "source": [
1462 |     "# Calculation of metrics\n",
1463 |     "\n",
1464 |     "# Accuracy score\n",
1465 |     "acc = accuracy_score(y_test, y_pred)\n",
1466 |     "\n",
1467 |     "# precision score (When is 0 and should be 1 and the other way round)\n",
1468 |     "pre = precision_score(y_test, y_pred)\n",
1469 |     "\n",
1470 |     "# recall score\n",
1471 |     "rec = recall_score(y_test, y_pred)\n",
1472 |     "\n",
1473 |     "f1 = f1_score(y_test, y_pred)"
1474 |    ]
1475 |   },
1476 |   {
1477 |    "cell_type": "code",
1478 |    "execution_count": 99,
1479 |    "metadata": {},
1480 |    "outputs": [],
1481 |    "source": [
1482 |     "# Metrics \n",
1483 |     "dt_results = pd.DataFrame([['Decision Trees', acc, pre, rec, f1]],\n",
1484 |     "              columns = ['Model','Accuracy','Precision','Recall','F1 score'])"
1485 |    ]
1486 |   },
1487 |   {
1488 |    "cell_type": "code",
1489 |    "execution_count": 100,
1490 |    "metadata": {
1491 |     "scrolled": true
1492 |    },
1493 |    "outputs": [
1494 |     {
1495 |      "data": {
1496 |       "text/html": [
1497 |        "<div>\n",
1498 |        "<style scoped>\n",
1499 |        "    .dataframe tbody tr th:only-of-type {\n",
1500 |        "        vertical-align: middle;\n",
1501 |        "    }\n",
1502 |        "\n",
1503 |        "    .dataframe tbody tr th {\n",
1504 |        "        vertical-align: top;\n",
1505 |        "    }\n",
1506 |        "\n",
1507 |        "    .dataframe thead th {\n",
1508 |        "        text-align: right;\n",
1509 |        "    }\n",
1510 |        "</style>\n",
1511 |        "<table border=\"1\" class=\"dataframe\">\n",
1512 |        "  <thead>\n",
1513 |        "    <tr style=\"text-align: right;\">\n",
1514 |        "      <th></th>\n",
1515 |        "      <th>Model</th>\n",
1516 |        "      <th>Accuracy</th>\n",
1517 |        "      <th>Precision</th>\n",
1518 |        "      <th>Recall</th>\n",
1519 |        "      <th>F1 score</th>\n",
1520 |        "    </tr>\n",
1521 |        "  </thead>\n",
1522 |        "  <tbody>\n",
1523 |        "    <tr>\n",
1524 |        "      <th>0</th>\n",
1525 |        "      <td>Deep Neural Network</td>\n",
1526 |        "      <td>0.999391</td>\n",
1527 |        "      <td>0.836879</td>\n",
1528 |        "      <td>0.802721</td>\n",
1529 |        "      <td>0.819444</td>\n",
1530 |        "    </tr>\n",
1531 |        "    <tr>\n",
1532 |        "      <th>1</th>\n",
1533 |        "      <td>Random Forest (n=100, GSx2 + Entropy)</td>\n",
1534 |        "      <td>0.999520</td>\n",
1535 |        "      <td>0.941667</td>\n",
1536 |        "      <td>0.768707</td>\n",
1537 |        "      <td>0.846442</td>\n",
1538 |        "    </tr>\n",
1539 |        "    <tr>\n",
1540 |        "      <th>2</th>\n",
1541 |        "      <td>Decision Trees</td>\n",
1542 |        "      <td>0.999216</td>\n",
1543 |        "      <td>0.785714</td>\n",
1544 |        "      <td>0.748299</td>\n",
1545 |        "      <td>0.766551</td>\n",
1546 |        "    </tr>\n",
1547 |        "  </tbody>\n",
1548 |        "</table>\n",
1549 |        "</div>"
1550 |       ],
1551 |       "text/plain": [
1552 |        "                                   Model  Accuracy  Precision    Recall  \\\n",
1553 |        "0                    Deep Neural Network  0.999391   0.836879  0.802721   \n",
1554 |        "1  Random Forest (n=100, GSx2 + Entropy)  0.999520   0.941667  0.768707   \n",
1555 |        "2                         Decision Trees  0.999216   0.785714  0.748299   \n",
1556 |        "\n",
1557 |        "   F1 score  \n",
1558 |        "0  0.819444  \n",
1559 |        "1  0.846442  \n",
1560 |        "2  0.766551  "
1561 |       ]
1562 |      },
1563 |      "execution_count": 100,
1564 |      "metadata": {},
1565 |      "output_type": "execute_result"
1566 |     }
1567 |    ],
1568 |    "source": [
1569 |     "# Showing the comparizon between the Models\n",
1570 |     "\n",
1571 |     "results = results.append(dt_results, ignore_index = True)\n",
1572 |     "\n",
1573 |     "results "
1574 |    ]
1575 |   },
1576 |   {
1577 |    "cell_type": "code",
1578 |    "execution_count": 104,
1579 |    "metadata": {},
1580 |    "outputs": [],
1581 |    "source": [
1582 |     "# Round 4: BALANCING THE DATASET\n",
1583 |     "\n",
1584 |     "# Splitting into train and Test set\n",
1585 |     "from sklearn.model_selection import train_test_split\n",
1586 |     "\n",
1587 |     "X_train, X_test, y_train, y_test = train_test_split(X,\n",
1588 |     "                                                   y,\n",
1589 |     "                                                   test_size = 0.3,\n",
1590 |     "                                                   random_state = 0)"
1591 |    ]
1592 |   },
1593 |   {
1594 |    "cell_type": "code",
1595 |    "execution_count": 105,
1596 |    "metadata": {},
1597 |    "outputs": [
1598 |     {
1599 |      "data": {
1600 |       "text/plain": [
1601 |        "0    199019\n",
1602 |        "1       345\n",
1603 |        "Name: Class, dtype: int64"
1604 |       ]
1605 |      },
1606 |      "execution_count": 105,
1607 |      "metadata": {},
1608 |      "output_type": "execute_result"
1609 |     }
1610 |    ],
1611 |    "source": [
1612 |     "# Round 4 \n",
1613 |     "\n",
1614 |     "#BALANCING THE DATASET:\n",
1615 |     "\n",
1616 |     "# # To Avoid the skewed on the total \n",
1617 |     "\n",
1618 |     "# Counting and watching the Y_train distribution \n",
1619 |     "y_train.value_counts()"
1620 |    ]
1621 |   },
1622 |   {
1623 |    "cell_type": "code",
1624 |    "execution_count": 106,
1625 |    "metadata": {},
1626 |    "outputs": [],
1627 |    "source": [
1628 |     "# The expecting distribution to avoid a Bias is to have a 50/50 (0/1)\n",
1629 |     "#This balancing ensure that the model is accuracy\n",
1630 |     "\n",
1631 |     "#pos and neg index values\n",
1632 |     "pos_index = y_train[y_train.values == 1].index\n",
1633 |     "neg_index = y_train[y_train.values == 0].index\n",
1634 |     "\n",
1635 |     "if len(pos_index) > len(neg_index):\n",
1636 |     "    higher = pos_index\n",
1637 |     "    lower = neg_index\n",
1638 |     "else:\n",
1639 |     "    lower = pos_index\n",
1640 |     "    higher = neg_index\n",
1641 |     "    \n",
1642 |     "#Create random index selection\n",
1643 |     "random.seed(0)\n",
1644 |     "# random select index record up to the same size of lower index\n",
1645 |     "higher = np.random.choice(higher, size = len(lower))\n",
1646 |     "# select the lower index and convert to a numpy array\n",
1647 |     "lower = np.asarray(lower)\n",
1648 |     "# create the new index as a combination \n",
1649 |     "new_indexes = np.concatenate((lower,higher))\n",
1650 |     "\n",
1651 |     "# Reselect the X_train, y_train dataset using the new indexes\n",
1652 |     "X_train = X_train.loc[new_indexes, ]\n",
1653 |     "y_train = y_train[new_indexes]"
1654 |    ]
1655 |   },
1656 |   {
1657 |    "cell_type": "code",
1658 |    "execution_count": 107,
1659 |    "metadata": {},
1660 |    "outputs": [
1661 |     {
1662 |      "data": {
1663 |       "text/plain": [
1664 |        "1    345\n",
1665 |        "0    345\n",
1666 |        "Name: Class, dtype: int64"
1667 |       ]
1668 |      },
1669 |      "execution_count": 107,
1670 |      "metadata": {},
1671 |      "output_type": "execute_result"
1672 |     }
1673 |    ],
1674 |    "source": [
1675 |     "# checking the balancing of the training Set\n",
1676 |     "\n",
1677 |     "#Counting and watching the Y_train distribution \n",
1678 |     "y_train.value_counts()"
1679 |    ]
1680 |   },
1681 |   {
1682 |    "cell_type": "code",
1683 |    "execution_count": 108,
1684 |    "metadata": {},
1685 |    "outputs": [
1686 |     {
1687 |      "name": "stdout",
1688 |      "output_type": "stream",
1689 |      "text": [
1690 |       "Epoch 1/5\n",
1691 |       "690/690 [==============================] - 0s 109us/sample - loss: 0.2002 - acc: 0.9319\n",
1692 |       "Epoch 2/5\n",
1693 |       "690/690 [==============================] - 0s 94us/sample - loss: 0.1285 - acc: 0.9435\n",
1694 |       "Epoch 3/5\n",
1695 |       "690/690 [==============================] - 0s 88us/sample - loss: 0.1055 - acc: 0.9493\n",
1696 |       "Epoch 4/5\n",
1697 |       "690/690 [==============================] - 0s 87us/sample - loss: 0.1052 - acc: 0.9493\n",
1698 |       "Epoch 5/5\n",
1699 |       "690/690 [==============================] - 0s 108us/sample - loss: 0.0964 - acc: 0.9536\n"
1700 |      ]
1701 |     },
1702 |     {
1703 |      "data": {
1704 |       "text/plain": [
1705 |        "<tensorflow.python.keras.callbacks.History at 0x23e825a9648>"
1706 |       ]
1707 |      },
1708 |      "execution_count": 108,
1709 |      "metadata": {},
1710 |      "output_type": "execute_result"
1711 |     }
1712 |    ],
1713 |    "source": [
1714 |     "# train the DNN model \n",
1715 |     "dnn_model.fit(X_train, \n",
1716 |     "              y_train, \n",
1717 |     "              batch_size= 15,\n",
1718 |     "              epochs = 5)"
1719 |    ]
1720 |   },
1721 |   {
1722 |    "cell_type": "code",
1723 |    "execution_count": 109,
1724 |    "metadata": {},
1725 |    "outputs": [
1726 |     {
1727 |      "name": "stdout",
1728 |      "output_type": "stream",
1729 |      "text": [
1730 |       "85443/85443 [==============================] - 1s 16us/sample - loss: 0.0857 - acc: 0.9971\n"
1731 |      ]
1732 |     }
1733 |    ],
1734 |    "source": [
1735 |     "## DNN model evaluation\n",
1736 |     "score = dnn_model.evaluate(X_test,y_test)"
1737 |    ]
1738 |   },
1739 |   {
1740 |    "cell_type": "code",
1741 |    "execution_count": 110,
1742 |    "metadata": {},
1743 |    "outputs": [
1744 |     {
1745 |      "name": "stdout",
1746 |      "output_type": "stream",
1747 |      "text": [
1748 |       "[0.08572872194509909, 0.99707407]\n"
1749 |      ]
1750 |     }
1751 |    ],
1752 |    "source": [
1753 |     "# Print eval result \n",
1754 |     "print(score)"
1755 |    ]
1756 |   },
1757 |   {
1758 |    "cell_type": "code",
1759 |    "execution_count": 112,
1760 |    "metadata": {},
1761 |    "outputs": [],
1762 |    "source": [
1763 |     "## Metrics -->\n",
1764 |     "\n",
1765 |     "# Accuracy: (TRUE Positives + TRUE Negatives) / Total\n",
1766 |     "# Precision: TRUE Positives / (TRUE Positives + FALSE Positives)\n",
1767 |     "# Specificity: TRUE Negatives / (FALSE Positives + TRUE Negatives)\n",
1768 |     "# Recall: TRUE Positives / (TRUE Positives + FALSE Negatives)\n",
1769 |     "# F1-score:"
1770 |    ]
1771 |   },
1772 |   {
1773 |    "cell_type": "code",
1774 |    "execution_count": 113,
1775 |    "metadata": {},
1776 |    "outputs": [],
1777 |    "source": [
1778 |     "# Getting the prediction from the test dataset\n",
1779 |     "y_pred = dnn_model.predict(X_test).round()\n",
1780 |     "# convert array to dataframe\n",
1781 |     "y_test = pd.DataFrame(y_test)"
1782 |    ]
1783 |   },
1784 |   {
1785 |    "cell_type": "code",
1786 |    "execution_count": 114,
1787 |    "metadata": {},
1788 |    "outputs": [],
1789 |    "source": [
1790 |     "# Evaluating Test set\n",
1791 |     "y_pred = classifier.predict(X_test)"
1792 |    ]
1793 |   },
1794 |   {
1795 |    "cell_type": "code",
1796 |    "execution_count": 116,
1797 |    "metadata": {},
1798 |    "outputs": [],
1799 |    "source": [
1800 |     "# Calculation of metrics\n",
1801 |     "\n",
1802 |     "# Accuracy score\n",
1803 |     "acc = accuracy_score(y_test, y_pred)\n",
1804 |     "\n",
1805 |     "# precision score (When is 0 and should be 1 and the other way round)\n",
1806 |     "pre = precision_score(y_test, y_pred)\n",
1807 |     "\n",
1808 |     "# recall score\n",
1809 |     "rec = recall_score(y_test, y_pred)\n",
1810 |     "\n",
1811 |     "f1 = f1_score(y_test, y_pred)"
1812 |    ]
1813 |   },
1814 |   {
1815 |    "cell_type": "code",
1816 |    "execution_count": 117,
1817 |    "metadata": {},
1818 |    "outputs": [],
1819 |    "source": [
1820 |     "# Metrics \n",
1821 |     "dnn_results = pd.DataFrame([['Deep Neural Network (Undersampling & balanced)', acc, pre, rec, f1]],\n",
1822 |     "              columns = ['Model','Accuracy','Precision','Recall','F1 score'])"
1823 |    ]
1824 |   },
1825 |   {
1826 |    "cell_type": "code",
1827 |    "execution_count": 118,
1828 |    "metadata": {
1829 |     "scrolled": true
1830 |    },
1831 |    "outputs": [
1832 |     {
1833 |      "data": {
1834 |       "text/html": [
1835 |        "<div>\n",
1836 |        "<style scoped>\n",
1837 |        "    .dataframe tbody tr th:only-of-type {\n",
1838 |        "        vertical-align: middle;\n",
1839 |        "    }\n",
1840 |        "\n",
1841 |        "    .dataframe tbody tr th {\n",
1842 |        "        vertical-align: top;\n",
1843 |        "    }\n",
1844 |        "\n",
1845 |        "    .dataframe thead th {\n",
1846 |        "        text-align: right;\n",
1847 |        "    }\n",
1848 |        "</style>\n",
1849 |        "<table border=\"1\" class=\"dataframe\">\n",
1850 |        "  <thead>\n",
1851 |        "    <tr style=\"text-align: right;\">\n",
1852 |        "      <th></th>\n",
1853 |        "      <th>Model</th>\n",
1854 |        "      <th>Accuracy</th>\n",
1855 |        "      <th>Precision</th>\n",
1856 |        "      <th>Recall</th>\n",
1857 |        "      <th>F1 score</th>\n",
1858 |        "    </tr>\n",
1859 |        "  </thead>\n",
1860 |        "  <tbody>\n",
1861 |        "    <tr>\n",
1862 |        "      <th>0</th>\n",
1863 |        "      <td>Deep Neural Network</td>\n",
1864 |        "      <td>0.999391</td>\n",
1865 |        "      <td>0.836879</td>\n",
1866 |        "      <td>0.802721</td>\n",
1867 |        "      <td>0.819444</td>\n",
1868 |        "    </tr>\n",
1869 |        "    <tr>\n",
1870 |        "      <th>1</th>\n",
1871 |        "      <td>Random Forest (n=100, GSx2 + Entropy)</td>\n",
1872 |        "      <td>0.999520</td>\n",
1873 |        "      <td>0.941667</td>\n",
1874 |        "      <td>0.768707</td>\n",
1875 |        "      <td>0.846442</td>\n",
1876 |        "    </tr>\n",
1877 |        "    <tr>\n",
1878 |        "      <th>2</th>\n",
1879 |        "      <td>Decision Trees</td>\n",
1880 |        "      <td>0.999216</td>\n",
1881 |        "      <td>0.785714</td>\n",
1882 |        "      <td>0.748299</td>\n",
1883 |        "      <td>0.766551</td>\n",
1884 |        "    </tr>\n",
1885 |        "    <tr>\n",
1886 |        "      <th>3</th>\n",
1887 |        "      <td>Deep Neural Network (Undersampling &amp; balanced)</td>\n",
1888 |        "      <td>0.999216</td>\n",
1889 |        "      <td>0.785714</td>\n",
1890 |        "      <td>0.748299</td>\n",
1891 |        "      <td>0.766551</td>\n",
1892 |        "    </tr>\n",
1893 |        "  </tbody>\n",
1894 |        "</table>\n",
1895 |        "</div>"
1896 |       ],
1897 |       "text/plain": [
1898 |        "                                            Model  Accuracy  Precision  \\\n",
1899 |        "0                             Deep Neural Network  0.999391   0.836879   \n",
1900 |        "1           Random Forest (n=100, GSx2 + Entropy)  0.999520   0.941667   \n",
1901 |        "2                                  Decision Trees  0.999216   0.785714   \n",
1902 |        "3  Deep Neural Network (Undersampling & balanced)  0.999216   0.785714   \n",
1903 |        "\n",
1904 |        "     Recall  F1 score  \n",
1905 |        "0  0.802721  0.819444  \n",
1906 |        "1  0.768707  0.846442  \n",
1907 |        "2  0.748299  0.766551  \n",
1908 |        "3  0.748299  0.766551  "
1909 |       ]
1910 |      },
1911 |      "execution_count": 118,
1912 |      "metadata": {},
1913 |      "output_type": "execute_result"
1914 |     }
1915 |    ],
1916 |    "source": [
1917 |     "# Showing the comparizon between the Models\n",
1918 |     "\n",
1919 |     "results = results.append(dnn_results, ignore_index = True)\n",
1920 |     "\n",
1921 |     "results "
1922 |    ]
1923 |   },
1924 |   {
1925 |    "cell_type": "markdown",
1926 |    "metadata": {},
1927 |    "source": [
1928 |     "## Final Remarks\n",
1929 |     "\n",
1930 |     "On this case study we try to create a model for the detection of Fraudulent Card transaction. We tried severals Models and the best of thoughs model was the Random Forest model with this particular Metrics score:\n",
1931 |     "\n",
1932 |     "- Accuracy score: 0.999391\n",
1933 |     "- Precision score: 0.836879\n",
1934 |     "- Recall score: 0.802721\n",
1935 |     "- F1 score: 0.819444\n",
1936 |     "\n",
1937 |     "\n"
1938 |    ]
1939 |   }
1940 |  ],
1941 |  "metadata": {
1942 |   "kernelspec": {
1943 |    "display_name": "Python 3",
1944 |    "language": "python",
1945 |    "name": "python3"
1946 |   },
1947 |   "language_info": {
1948 |    "codemirror_mode": {
1949 |     "name": "ipython",
1950 |     "version": 3
1951 |    },
1952 |    "file_extension": ".py",
1953 |    "mimetype": "text/x-python",
1954 |    "name": "python",
1955 |    "nbconvert_exporter": "python",
1956 |    "pygments_lexer": "ipython3",
1957 |    "version": "3.7.4"
1958 |   }
1959 |  },
1960 |  "nbformat": 4,
1961 |  "nbformat_minor": 2
1962 | }
1963 | 


--------------------------------------------------------------------------------
/4. Minimizing Churn Rate Through Analysis of Financial Habits/Machine_Learning_04_Minimizing_Churn_Rate_Through_Analysis_of_Financial_Habits (Part 2).ipynb:
--------------------------------------------------------------------------------
   1 | {
   2 |  "cells": [
   3 |   {
   4 |    "cell_type": "code",
   5 |    "execution_count": 1,
   6 |    "metadata": {},
   7 |    "outputs": [],
   8 |    "source": [
   9 |     "## importing lbiraries & data\n",
  10 |     "\n",
  11 |     "# import libraries\n",
  12 |     "import pandas as pd\n",
  13 |     "import random\n",
  14 |     "import numpy as np\n",
  15 |     "import seaborn as sns\n",
  16 |     "import matplotlib.pyplot as plt"
  17 |    ]
  18 |   },
  19 |   {
  20 |    "cell_type": "code",
  21 |    "execution_count": 2,
  22 |    "metadata": {},
  23 |    "outputs": [],
  24 |    "source": [
  25 |     "path = \"../Datasets\"\n",
  26 |     "\n",
  27 |     "import os\n",
  28 |     "#Actual absolute path\n",
  29 |     "cwd = os.getcwd()\n",
  30 |     "#print(cwd)"
  31 |    ]
  32 |   },
  33 |   {
  34 |    "cell_type": "code",
  35 |    "execution_count": 3,
  36 |    "metadata": {},
  37 |    "outputs": [],
  38 |    "source": [
  39 |     "# one level up directory. Datasets directory\n",
  40 |     "os.chdir(path)\n",
  41 |     "#Actual absolute path\n",
  42 |     "cwd = os.getcwd()\n",
  43 |     "#print(cwd)"
  44 |    ]
  45 |   },
  46 |   {
  47 |    "cell_type": "code",
  48 |    "execution_count": 4,
  49 |    "metadata": {},
  50 |    "outputs": [],
  51 |    "source": [
  52 |     "# path file current dir + file name\n",
  53 |     "path_file = cwd + '/new_churn_data.csv'\n",
  54 |     "#print(path_file)"
  55 |    ]
  56 |   },
  57 |   {
  58 |    "cell_type": "code",
  59 |    "execution_count": 5,
  60 |    "metadata": {},
  61 |    "outputs": [
  62 |     {
  63 |      "data": {
  64 |       "text/html": [
  65 |        "<div>\n",
  66 |        "<style scoped>\n",
  67 |        "    .dataframe tbody tr th:only-of-type {\n",
  68 |        "        vertical-align: middle;\n",
  69 |        "    }\n",
  70 |        "\n",
  71 |        "    .dataframe tbody tr th {\n",
  72 |        "        vertical-align: top;\n",
  73 |        "    }\n",
  74 |        "\n",
  75 |        "    .dataframe thead th {\n",
  76 |        "        text-align: right;\n",
  77 |        "    }\n",
  78 |        "</style>\n",
  79 |        "<table border=\"1\" class=\"dataframe\">\n",
  80 |        "  <thead>\n",
  81 |        "    <tr style=\"text-align: right;\">\n",
  82 |        "      <th></th>\n",
  83 |        "      <th>user</th>\n",
  84 |        "      <th>churn</th>\n",
  85 |        "      <th>age</th>\n",
  86 |        "      <th>housing</th>\n",
  87 |        "      <th>deposits</th>\n",
  88 |        "      <th>withdrawal</th>\n",
  89 |        "      <th>purchases_partners</th>\n",
  90 |        "      <th>purchases</th>\n",
  91 |        "      <th>cc_taken</th>\n",
  92 |        "      <th>cc_recommended</th>\n",
  93 |        "      <th>...</th>\n",
  94 |        "      <th>payment_type</th>\n",
  95 |        "      <th>waiting_4_loan</th>\n",
  96 |        "      <th>cancelled_loan</th>\n",
  97 |        "      <th>received_loan</th>\n",
  98 |        "      <th>rejected_loan</th>\n",
  99 |        "      <th>zodiac_sign</th>\n",
 100 |        "      <th>left_for_two_month_plus</th>\n",
 101 |        "      <th>left_for_one_month</th>\n",
 102 |        "      <th>reward_rate</th>\n",
 103 |        "      <th>is_referred</th>\n",
 104 |        "    </tr>\n",
 105 |        "  </thead>\n",
 106 |        "  <tbody>\n",
 107 |        "    <tr>\n",
 108 |        "      <th>0</th>\n",
 109 |        "      <td>55409</td>\n",
 110 |        "      <td>0</td>\n",
 111 |        "      <td>37.0</td>\n",
 112 |        "      <td>na</td>\n",
 113 |        "      <td>0</td>\n",
 114 |        "      <td>0</td>\n",
 115 |        "      <td>0</td>\n",
 116 |        "      <td>0</td>\n",
 117 |        "      <td>0</td>\n",
 118 |        "      <td>0</td>\n",
 119 |        "      <td>...</td>\n",
 120 |        "      <td>Bi-Weekly</td>\n",
 121 |        "      <td>0</td>\n",
 122 |        "      <td>0</td>\n",
 123 |        "      <td>0</td>\n",
 124 |        "      <td>0</td>\n",
 125 |        "      <td>Leo</td>\n",
 126 |        "      <td>1</td>\n",
 127 |        "      <td>0</td>\n",
 128 |        "      <td>0.00</td>\n",
 129 |        "      <td>0</td>\n",
 130 |        "    </tr>\n",
 131 |        "    <tr>\n",
 132 |        "      <th>1</th>\n",
 133 |        "      <td>23547</td>\n",
 134 |        "      <td>0</td>\n",
 135 |        "      <td>28.0</td>\n",
 136 |        "      <td>R</td>\n",
 137 |        "      <td>0</td>\n",
 138 |        "      <td>0</td>\n",
 139 |        "      <td>1</td>\n",
 140 |        "      <td>0</td>\n",
 141 |        "      <td>0</td>\n",
 142 |        "      <td>96</td>\n",
 143 |        "      <td>...</td>\n",
 144 |        "      <td>Weekly</td>\n",
 145 |        "      <td>0</td>\n",
 146 |        "      <td>0</td>\n",
 147 |        "      <td>0</td>\n",
 148 |        "      <td>0</td>\n",
 149 |        "      <td>Leo</td>\n",
 150 |        "      <td>0</td>\n",
 151 |        "      <td>0</td>\n",
 152 |        "      <td>1.47</td>\n",
 153 |        "      <td>1</td>\n",
 154 |        "    </tr>\n",
 155 |        "    <tr>\n",
 156 |        "      <th>2</th>\n",
 157 |        "      <td>58313</td>\n",
 158 |        "      <td>0</td>\n",
 159 |        "      <td>35.0</td>\n",
 160 |        "      <td>R</td>\n",
 161 |        "      <td>47</td>\n",
 162 |        "      <td>2</td>\n",
 163 |        "      <td>86</td>\n",
 164 |        "      <td>47</td>\n",
 165 |        "      <td>0</td>\n",
 166 |        "      <td>285</td>\n",
 167 |        "      <td>...</td>\n",
 168 |        "      <td>Semi-Monthly</td>\n",
 169 |        "      <td>0</td>\n",
 170 |        "      <td>0</td>\n",
 171 |        "      <td>0</td>\n",
 172 |        "      <td>0</td>\n",
 173 |        "      <td>Capricorn</td>\n",
 174 |        "      <td>1</td>\n",
 175 |        "      <td>0</td>\n",
 176 |        "      <td>2.17</td>\n",
 177 |        "      <td>0</td>\n",
 178 |        "    </tr>\n",
 179 |        "    <tr>\n",
 180 |        "      <th>3</th>\n",
 181 |        "      <td>8095</td>\n",
 182 |        "      <td>0</td>\n",
 183 |        "      <td>26.0</td>\n",
 184 |        "      <td>R</td>\n",
 185 |        "      <td>26</td>\n",
 186 |        "      <td>3</td>\n",
 187 |        "      <td>38</td>\n",
 188 |        "      <td>25</td>\n",
 189 |        "      <td>0</td>\n",
 190 |        "      <td>74</td>\n",
 191 |        "      <td>...</td>\n",
 192 |        "      <td>Bi-Weekly</td>\n",
 193 |        "      <td>0</td>\n",
 194 |        "      <td>0</td>\n",
 195 |        "      <td>0</td>\n",
 196 |        "      <td>0</td>\n",
 197 |        "      <td>Capricorn</td>\n",
 198 |        "      <td>0</td>\n",
 199 |        "      <td>0</td>\n",
 200 |        "      <td>1.10</td>\n",
 201 |        "      <td>1</td>\n",
 202 |        "    </tr>\n",
 203 |        "    <tr>\n",
 204 |        "      <th>4</th>\n",
 205 |        "      <td>61353</td>\n",
 206 |        "      <td>1</td>\n",
 207 |        "      <td>27.0</td>\n",
 208 |        "      <td>na</td>\n",
 209 |        "      <td>0</td>\n",
 210 |        "      <td>0</td>\n",
 211 |        "      <td>2</td>\n",
 212 |        "      <td>0</td>\n",
 213 |        "      <td>0</td>\n",
 214 |        "      <td>0</td>\n",
 215 |        "      <td>...</td>\n",
 216 |        "      <td>Bi-Weekly</td>\n",
 217 |        "      <td>0</td>\n",
 218 |        "      <td>0</td>\n",
 219 |        "      <td>0</td>\n",
 220 |        "      <td>0</td>\n",
 221 |        "      <td>Aries</td>\n",
 222 |        "      <td>1</td>\n",
 223 |        "      <td>0</td>\n",
 224 |        "      <td>0.03</td>\n",
 225 |        "      <td>0</td>\n",
 226 |        "    </tr>\n",
 227 |        "  </tbody>\n",
 228 |        "</table>\n",
 229 |        "<p>5 rows × 28 columns</p>\n",
 230 |        "</div>"
 231 |       ],
 232 |       "text/plain": [
 233 |        "    user  churn   age housing  deposits  withdrawal  purchases_partners  \\\n",
 234 |        "0  55409      0  37.0      na         0           0                   0   \n",
 235 |        "1  23547      0  28.0       R         0           0                   1   \n",
 236 |        "2  58313      0  35.0       R        47           2                  86   \n",
 237 |        "3   8095      0  26.0       R        26           3                  38   \n",
 238 |        "4  61353      1  27.0      na         0           0                   2   \n",
 239 |        "\n",
 240 |        "   purchases  cc_taken  cc_recommended     ...       payment_type  \\\n",
 241 |        "0          0         0               0     ...          Bi-Weekly   \n",
 242 |        "1          0         0              96     ...             Weekly   \n",
 243 |        "2         47         0             285     ...       Semi-Monthly   \n",
 244 |        "3         25         0              74     ...          Bi-Weekly   \n",
 245 |        "4          0         0               0     ...          Bi-Weekly   \n",
 246 |        "\n",
 247 |        "   waiting_4_loan  cancelled_loan  received_loan  rejected_loan  zodiac_sign  \\\n",
 248 |        "0               0               0              0              0          Leo   \n",
 249 |        "1               0               0              0              0          Leo   \n",
 250 |        "2               0               0              0              0    Capricorn   \n",
 251 |        "3               0               0              0              0    Capricorn   \n",
 252 |        "4               0               0              0              0        Aries   \n",
 253 |        "\n",
 254 |        "   left_for_two_month_plus  left_for_one_month reward_rate  is_referred  \n",
 255 |        "0                        1                   0        0.00            0  \n",
 256 |        "1                        0                   0        1.47            1  \n",
 257 |        "2                        1                   0        2.17            0  \n",
 258 |        "3                        0                   0        1.10            1  \n",
 259 |        "4                        1                   0        0.03            0  \n",
 260 |        "\n",
 261 |        "[5 rows x 28 columns]"
 262 |       ]
 263 |      },
 264 |      "execution_count": 5,
 265 |      "metadata": {},
 266 |      "output_type": "execute_result"
 267 |     }
 268 |    ],
 269 |    "source": [
 270 |     "# import dataset\n",
 271 |     "\n",
 272 |     "dataset = pd.read_csv(path_file)\n",
 273 |     "dataset.head()"
 274 |    ]
 275 |   },
 276 |   {
 277 |    "cell_type": "code",
 278 |    "execution_count": 6,
 279 |    "metadata": {},
 280 |    "outputs": [
 281 |     {
 282 |      "data": {
 283 |       "text/plain": [
 284 |        "Index(['user', 'churn', 'age', 'housing', 'deposits', 'withdrawal',\n",
 285 |        "       'purchases_partners', 'purchases', 'cc_taken', 'cc_recommended',\n",
 286 |        "       'cc_disliked', 'cc_liked', 'cc_application_begin', 'app_downloaded',\n",
 287 |        "       'web_user', 'ios_user', 'android_user', 'registered_phones',\n",
 288 |        "       'payment_type', 'waiting_4_loan', 'cancelled_loan', 'received_loan',\n",
 289 |        "       'rejected_loan', 'zodiac_sign', 'left_for_two_month_plus',\n",
 290 |        "       'left_for_one_month', 'reward_rate', 'is_referred'],\n",
 291 |        "      dtype='object')"
 292 |       ]
 293 |      },
 294 |      "execution_count": 6,
 295 |      "metadata": {},
 296 |      "output_type": "execute_result"
 297 |     }
 298 |    ],
 299 |    "source": [
 300 |     "dataset.columns"
 301 |    ]
 302 |   },
 303 |   {
 304 |    "cell_type": "code",
 305 |    "execution_count": 7,
 306 |    "metadata": {},
 307 |    "outputs": [
 308 |     {
 309 |      "data": {
 310 |       "text/plain": [
 311 |        "(26996, 28)"
 312 |       ]
 313 |      },
 314 |      "execution_count": 7,
 315 |      "metadata": {},
 316 |      "output_type": "execute_result"
 317 |     }
 318 |    ],
 319 |    "source": [
 320 |     "dataset.shape # 31 x columns - 27000 records"
 321 |    ]
 322 |   },
 323 |   {
 324 |    "cell_type": "code",
 325 |    "execution_count": 8,
 326 |    "metadata": {},
 327 |    "outputs": [
 328 |     {
 329 |      "data": {
 330 |       "text/html": [
 331 |        "<div>\n",
 332 |        "<style scoped>\n",
 333 |        "    .dataframe tbody tr th:only-of-type {\n",
 334 |        "        vertical-align: middle;\n",
 335 |        "    }\n",
 336 |        "\n",
 337 |        "    .dataframe tbody tr th {\n",
 338 |        "        vertical-align: top;\n",
 339 |        "    }\n",
 340 |        "\n",
 341 |        "    .dataframe thead th {\n",
 342 |        "        text-align: right;\n",
 343 |        "    }\n",
 344 |        "</style>\n",
 345 |        "<table border=\"1\" class=\"dataframe\">\n",
 346 |        "  <thead>\n",
 347 |        "    <tr style=\"text-align: right;\">\n",
 348 |        "      <th></th>\n",
 349 |        "      <th>churn</th>\n",
 350 |        "      <th>age</th>\n",
 351 |        "      <th>housing</th>\n",
 352 |        "      <th>deposits</th>\n",
 353 |        "      <th>withdrawal</th>\n",
 354 |        "      <th>purchases_partners</th>\n",
 355 |        "      <th>purchases</th>\n",
 356 |        "      <th>cc_taken</th>\n",
 357 |        "      <th>cc_recommended</th>\n",
 358 |        "      <th>cc_disliked</th>\n",
 359 |        "      <th>...</th>\n",
 360 |        "      <th>payment_type</th>\n",
 361 |        "      <th>waiting_4_loan</th>\n",
 362 |        "      <th>cancelled_loan</th>\n",
 363 |        "      <th>received_loan</th>\n",
 364 |        "      <th>rejected_loan</th>\n",
 365 |        "      <th>zodiac_sign</th>\n",
 366 |        "      <th>left_for_two_month_plus</th>\n",
 367 |        "      <th>left_for_one_month</th>\n",
 368 |        "      <th>reward_rate</th>\n",
 369 |        "      <th>is_referred</th>\n",
 370 |        "    </tr>\n",
 371 |        "  </thead>\n",
 372 |        "  <tbody>\n",
 373 |        "    <tr>\n",
 374 |        "      <th>0</th>\n",
 375 |        "      <td>0</td>\n",
 376 |        "      <td>37.0</td>\n",
 377 |        "      <td>na</td>\n",
 378 |        "      <td>0</td>\n",
 379 |        "      <td>0</td>\n",
 380 |        "      <td>0</td>\n",
 381 |        "      <td>0</td>\n",
 382 |        "      <td>0</td>\n",
 383 |        "      <td>0</td>\n",
 384 |        "      <td>0</td>\n",
 385 |        "      <td>...</td>\n",
 386 |        "      <td>Bi-Weekly</td>\n",
 387 |        "      <td>0</td>\n",
 388 |        "      <td>0</td>\n",
 389 |        "      <td>0</td>\n",
 390 |        "      <td>0</td>\n",
 391 |        "      <td>Leo</td>\n",
 392 |        "      <td>1</td>\n",
 393 |        "      <td>0</td>\n",
 394 |        "      <td>0.00</td>\n",
 395 |        "      <td>0</td>\n",
 396 |        "    </tr>\n",
 397 |        "    <tr>\n",
 398 |        "      <th>1</th>\n",
 399 |        "      <td>0</td>\n",
 400 |        "      <td>28.0</td>\n",
 401 |        "      <td>R</td>\n",
 402 |        "      <td>0</td>\n",
 403 |        "      <td>0</td>\n",
 404 |        "      <td>1</td>\n",
 405 |        "      <td>0</td>\n",
 406 |        "      <td>0</td>\n",
 407 |        "      <td>96</td>\n",
 408 |        "      <td>0</td>\n",
 409 |        "      <td>...</td>\n",
 410 |        "      <td>Weekly</td>\n",
 411 |        "      <td>0</td>\n",
 412 |        "      <td>0</td>\n",
 413 |        "      <td>0</td>\n",
 414 |        "      <td>0</td>\n",
 415 |        "      <td>Leo</td>\n",
 416 |        "      <td>0</td>\n",
 417 |        "      <td>0</td>\n",
 418 |        "      <td>1.47</td>\n",
 419 |        "      <td>1</td>\n",
 420 |        "    </tr>\n",
 421 |        "    <tr>\n",
 422 |        "      <th>2</th>\n",
 423 |        "      <td>0</td>\n",
 424 |        "      <td>35.0</td>\n",
 425 |        "      <td>R</td>\n",
 426 |        "      <td>47</td>\n",
 427 |        "      <td>2</td>\n",
 428 |        "      <td>86</td>\n",
 429 |        "      <td>47</td>\n",
 430 |        "      <td>0</td>\n",
 431 |        "      <td>285</td>\n",
 432 |        "      <td>0</td>\n",
 433 |        "      <td>...</td>\n",
 434 |        "      <td>Semi-Monthly</td>\n",
 435 |        "      <td>0</td>\n",
 436 |        "      <td>0</td>\n",
 437 |        "      <td>0</td>\n",
 438 |        "      <td>0</td>\n",
 439 |        "      <td>Capricorn</td>\n",
 440 |        "      <td>1</td>\n",
 441 |        "      <td>0</td>\n",
 442 |        "      <td>2.17</td>\n",
 443 |        "      <td>0</td>\n",
 444 |        "    </tr>\n",
 445 |        "    <tr>\n",
 446 |        "      <th>3</th>\n",
 447 |        "      <td>0</td>\n",
 448 |        "      <td>26.0</td>\n",
 449 |        "      <td>R</td>\n",
 450 |        "      <td>26</td>\n",
 451 |        "      <td>3</td>\n",
 452 |        "      <td>38</td>\n",
 453 |        "      <td>25</td>\n",
 454 |        "      <td>0</td>\n",
 455 |        "      <td>74</td>\n",
 456 |        "      <td>0</td>\n",
 457 |        "      <td>...</td>\n",
 458 |        "      <td>Bi-Weekly</td>\n",
 459 |        "      <td>0</td>\n",
 460 |        "      <td>0</td>\n",
 461 |        "      <td>0</td>\n",
 462 |        "      <td>0</td>\n",
 463 |        "      <td>Capricorn</td>\n",
 464 |        "      <td>0</td>\n",
 465 |        "      <td>0</td>\n",
 466 |        "      <td>1.10</td>\n",
 467 |        "      <td>1</td>\n",
 468 |        "    </tr>\n",
 469 |        "    <tr>\n",
 470 |        "      <th>4</th>\n",
 471 |        "      <td>1</td>\n",
 472 |        "      <td>27.0</td>\n",
 473 |        "      <td>na</td>\n",
 474 |        "      <td>0</td>\n",
 475 |        "      <td>0</td>\n",
 476 |        "      <td>2</td>\n",
 477 |        "      <td>0</td>\n",
 478 |        "      <td>0</td>\n",
 479 |        "      <td>0</td>\n",
 480 |        "      <td>0</td>\n",
 481 |        "      <td>...</td>\n",
 482 |        "      <td>Bi-Weekly</td>\n",
 483 |        "      <td>0</td>\n",
 484 |        "      <td>0</td>\n",
 485 |        "      <td>0</td>\n",
 486 |        "      <td>0</td>\n",
 487 |        "      <td>Aries</td>\n",
 488 |        "      <td>1</td>\n",
 489 |        "      <td>0</td>\n",
 490 |        "      <td>0.03</td>\n",
 491 |        "      <td>0</td>\n",
 492 |        "    </tr>\n",
 493 |        "    <tr>\n",
 494 |        "      <th>5</th>\n",
 495 |        "      <td>1</td>\n",
 496 |        "      <td>32.0</td>\n",
 497 |        "      <td>R</td>\n",
 498 |        "      <td>5</td>\n",
 499 |        "      <td>3</td>\n",
 500 |        "      <td>111</td>\n",
 501 |        "      <td>5</td>\n",
 502 |        "      <td>0</td>\n",
 503 |        "      <td>227</td>\n",
 504 |        "      <td>0</td>\n",
 505 |        "      <td>...</td>\n",
 506 |        "      <td>Bi-Weekly</td>\n",
 507 |        "      <td>0</td>\n",
 508 |        "      <td>0</td>\n",
 509 |        "      <td>0</td>\n",
 510 |        "      <td>0</td>\n",
 511 |        "      <td>Taurus</td>\n",
 512 |        "      <td>0</td>\n",
 513 |        "      <td>0</td>\n",
 514 |        "      <td>1.83</td>\n",
 515 |        "      <td>0</td>\n",
 516 |        "    </tr>\n",
 517 |        "    <tr>\n",
 518 |        "      <th>6</th>\n",
 519 |        "      <td>0</td>\n",
 520 |        "      <td>21.0</td>\n",
 521 |        "      <td>na</td>\n",
 522 |        "      <td>0</td>\n",
 523 |        "      <td>0</td>\n",
 524 |        "      <td>4</td>\n",
 525 |        "      <td>0</td>\n",
 526 |        "      <td>0</td>\n",
 527 |        "      <td>0</td>\n",
 528 |        "      <td>0</td>\n",
 529 |        "      <td>...</td>\n",
 530 |        "      <td>Bi-Weekly</td>\n",
 531 |        "      <td>0</td>\n",
 532 |        "      <td>0</td>\n",
 533 |        "      <td>0</td>\n",
 534 |        "      <td>0</td>\n",
 535 |        "      <td>Cancer</td>\n",
 536 |        "      <td>0</td>\n",
 537 |        "      <td>0</td>\n",
 538 |        "      <td>0.07</td>\n",
 539 |        "      <td>0</td>\n",
 540 |        "    </tr>\n",
 541 |        "    <tr>\n",
 542 |        "      <th>7</th>\n",
 543 |        "      <td>0</td>\n",
 544 |        "      <td>24.0</td>\n",
 545 |        "      <td>na</td>\n",
 546 |        "      <td>0</td>\n",
 547 |        "      <td>0</td>\n",
 548 |        "      <td>2</td>\n",
 549 |        "      <td>0</td>\n",
 550 |        "      <td>0</td>\n",
 551 |        "      <td>0</td>\n",
 552 |        "      <td>0</td>\n",
 553 |        "      <td>...</td>\n",
 554 |        "      <td>na</td>\n",
 555 |        "      <td>0</td>\n",
 556 |        "      <td>0</td>\n",
 557 |        "      <td>0</td>\n",
 558 |        "      <td>0</td>\n",
 559 |        "      <td>Leo</td>\n",
 560 |        "      <td>0</td>\n",
 561 |        "      <td>0</td>\n",
 562 |        "      <td>0.11</td>\n",
 563 |        "      <td>0</td>\n",
 564 |        "    </tr>\n",
 565 |        "    <tr>\n",
 566 |        "      <th>8</th>\n",
 567 |        "      <td>0</td>\n",
 568 |        "      <td>28.0</td>\n",
 569 |        "      <td>R</td>\n",
 570 |        "      <td>0</td>\n",
 571 |        "      <td>0</td>\n",
 572 |        "      <td>0</td>\n",
 573 |        "      <td>0</td>\n",
 574 |        "      <td>2</td>\n",
 575 |        "      <td>47</td>\n",
 576 |        "      <td>1</td>\n",
 577 |        "      <td>...</td>\n",
 578 |        "      <td>Bi-Weekly</td>\n",
 579 |        "      <td>0</td>\n",
 580 |        "      <td>0</td>\n",
 581 |        "      <td>0</td>\n",
 582 |        "      <td>0</td>\n",
 583 |        "      <td>Sagittarius</td>\n",
 584 |        "      <td>0</td>\n",
 585 |        "      <td>0</td>\n",
 586 |        "      <td>0.87</td>\n",
 587 |        "      <td>1</td>\n",
 588 |        "    </tr>\n",
 589 |        "    <tr>\n",
 590 |        "      <th>9</th>\n",
 591 |        "      <td>0</td>\n",
 592 |        "      <td>23.0</td>\n",
 593 |        "      <td>na</td>\n",
 594 |        "      <td>1</td>\n",
 595 |        "      <td>0</td>\n",
 596 |        "      <td>87</td>\n",
 597 |        "      <td>1</td>\n",
 598 |        "      <td>0</td>\n",
 599 |        "      <td>125</td>\n",
 600 |        "      <td>0</td>\n",
 601 |        "      <td>...</td>\n",
 602 |        "      <td>Bi-Weekly</td>\n",
 603 |        "      <td>0</td>\n",
 604 |        "      <td>0</td>\n",
 605 |        "      <td>0</td>\n",
 606 |        "      <td>0</td>\n",
 607 |        "      <td>Aquarius</td>\n",
 608 |        "      <td>0</td>\n",
 609 |        "      <td>0</td>\n",
 610 |        "      <td>1.07</td>\n",
 611 |        "      <td>0</td>\n",
 612 |        "    </tr>\n",
 613 |        "    <tr>\n",
 614 |        "      <th>10</th>\n",
 615 |        "      <td>0</td>\n",
 616 |        "      <td>32.0</td>\n",
 617 |        "      <td>R</td>\n",
 618 |        "      <td>0</td>\n",
 619 |        "      <td>0</td>\n",
 620 |        "      <td>30</td>\n",
 621 |        "      <td>0</td>\n",
 622 |        "      <td>0</td>\n",
 623 |        "      <td>70</td>\n",
 624 |        "      <td>0</td>\n",
 625 |        "      <td>...</td>\n",
 626 |        "      <td>Monthly</td>\n",
 627 |        "      <td>0</td>\n",
 628 |        "      <td>0</td>\n",
 629 |        "      <td>0</td>\n",
 630 |        "      <td>0</td>\n",
 631 |        "      <td>Virgo</td>\n",
 632 |        "      <td>0</td>\n",
 633 |        "      <td>0</td>\n",
 634 |        "      <td>0.83</td>\n",
 635 |        "      <td>1</td>\n",
 636 |        "    </tr>\n",
 637 |        "    <tr>\n",
 638 |        "      <th>11</th>\n",
 639 |        "      <td>0</td>\n",
 640 |        "      <td>41.0</td>\n",
 641 |        "      <td>O</td>\n",
 642 |        "      <td>14</td>\n",
 643 |        "      <td>0</td>\n",
 644 |        "      <td>116</td>\n",
 645 |        "      <td>13</td>\n",
 646 |        "      <td>0</td>\n",
 647 |        "      <td>217</td>\n",
 648 |        "      <td>0</td>\n",
 649 |        "      <td>...</td>\n",
 650 |        "      <td>Semi-Monthly</td>\n",
 651 |        "      <td>0</td>\n",
 652 |        "      <td>0</td>\n",
 653 |        "      <td>0</td>\n",
 654 |        "      <td>0</td>\n",
 655 |        "      <td>Virgo</td>\n",
 656 |        "      <td>0</td>\n",
 657 |        "      <td>0</td>\n",
 658 |        "      <td>2.17</td>\n",
 659 |        "      <td>0</td>\n",
 660 |        "    </tr>\n",
 661 |        "    <tr>\n",
 662 |        "      <th>12</th>\n",
 663 |        "      <td>0</td>\n",
 664 |        "      <td>20.0</td>\n",
 665 |        "      <td>na</td>\n",
 666 |        "      <td>0</td>\n",
 667 |        "      <td>0</td>\n",
 668 |        "      <td>135</td>\n",
 669 |        "      <td>0</td>\n",
 670 |        "      <td>0</td>\n",
 671 |        "      <td>286</td>\n",
 672 |        "      <td>0</td>\n",
 673 |        "      <td>...</td>\n",
 674 |        "      <td>Bi-Weekly</td>\n",
 675 |        "      <td>0</td>\n",
 676 |        "      <td>0</td>\n",
 677 |        "      <td>0</td>\n",
 678 |        "      <td>0</td>\n",
 679 |        "      <td>Libra</td>\n",
 680 |        "      <td>0</td>\n",
 681 |        "      <td>0</td>\n",
 682 |        "      <td>2.20</td>\n",
 683 |        "      <td>1</td>\n",
 684 |        "    </tr>\n",
 685 |        "    <tr>\n",
 686 |        "      <th>13</th>\n",
 687 |        "      <td>0</td>\n",
 688 |        "      <td>27.0</td>\n",
 689 |        "      <td>O</td>\n",
 690 |        "      <td>2</td>\n",
 691 |        "      <td>1</td>\n",
 692 |        "      <td>48</td>\n",
 693 |        "      <td>2</td>\n",
 694 |        "      <td>0</td>\n",
 695 |        "      <td>127</td>\n",
 696 |        "      <td>0</td>\n",
 697 |        "      <td>...</td>\n",
 698 |        "      <td>Weekly</td>\n",
 699 |        "      <td>0</td>\n",
 700 |        "      <td>0</td>\n",
 701 |        "      <td>0</td>\n",
 702 |        "      <td>0</td>\n",
 703 |        "      <td>Gemini</td>\n",
 704 |        "      <td>0</td>\n",
 705 |        "      <td>0</td>\n",
 706 |        "      <td>1.00</td>\n",
 707 |        "      <td>0</td>\n",
 708 |        "    </tr>\n",
 709 |        "    <tr>\n",
 710 |        "      <th>14</th>\n",
 711 |        "      <td>0</td>\n",
 712 |        "      <td>47.0</td>\n",
 713 |        "      <td>na</td>\n",
 714 |        "      <td>11</td>\n",
 715 |        "      <td>1</td>\n",
 716 |        "      <td>20</td>\n",
 717 |        "      <td>11</td>\n",
 718 |        "      <td>0</td>\n",
 719 |        "      <td>30</td>\n",
 720 |        "      <td>0</td>\n",
 721 |        "      <td>...</td>\n",
 722 |        "      <td>Bi-Weekly</td>\n",
 723 |        "      <td>0</td>\n",
 724 |        "      <td>0</td>\n",
 725 |        "      <td>0</td>\n",
 726 |        "      <td>0</td>\n",
 727 |        "      <td>Virgo</td>\n",
 728 |        "      <td>0</td>\n",
 729 |        "      <td>0</td>\n",
 730 |        "      <td>0.69</td>\n",
 731 |        "      <td>1</td>\n",
 732 |        "    </tr>\n",
 733 |        "    <tr>\n",
 734 |        "      <th>15</th>\n",
 735 |        "      <td>1</td>\n",
 736 |        "      <td>44.0</td>\n",
 737 |        "      <td>na</td>\n",
 738 |        "      <td>0</td>\n",
 739 |        "      <td>0</td>\n",
 740 |        "      <td>0</td>\n",
 741 |        "      <td>0</td>\n",
 742 |        "      <td>1</td>\n",
 743 |        "      <td>4</td>\n",
 744 |        "      <td>0</td>\n",
 745 |        "      <td>...</td>\n",
 746 |        "      <td>Semi-Monthly</td>\n",
 747 |        "      <td>0</td>\n",
 748 |        "      <td>0</td>\n",
 749 |        "      <td>0</td>\n",
 750 |        "      <td>0</td>\n",
 751 |        "      <td>Libra</td>\n",
 752 |        "      <td>0</td>\n",
 753 |        "      <td>0</td>\n",
 754 |        "      <td>0.07</td>\n",
 755 |        "      <td>0</td>\n",
 756 |        "    </tr>\n",
 757 |        "    <tr>\n",
 758 |        "      <th>16</th>\n",
 759 |        "      <td>1</td>\n",
 760 |        "      <td>24.0</td>\n",
 761 |        "      <td>na</td>\n",
 762 |        "      <td>6</td>\n",
 763 |        "      <td>2</td>\n",
 764 |        "      <td>24</td>\n",
 765 |        "      <td>6</td>\n",
 766 |        "      <td>0</td>\n",
 767 |        "      <td>55</td>\n",
 768 |        "      <td>0</td>\n",
 769 |        "      <td>...</td>\n",
 770 |        "      <td>Weekly</td>\n",
 771 |        "      <td>0</td>\n",
 772 |        "      <td>0</td>\n",
 773 |        "      <td>0</td>\n",
 774 |        "      <td>0</td>\n",
 775 |        "      <td>Capricorn</td>\n",
 776 |        "      <td>0</td>\n",
 777 |        "      <td>0</td>\n",
 778 |        "      <td>0.90</td>\n",
 779 |        "      <td>0</td>\n",
 780 |        "    </tr>\n",
 781 |        "    <tr>\n",
 782 |        "      <th>17</th>\n",
 783 |        "      <td>0</td>\n",
 784 |        "      <td>31.0</td>\n",
 785 |        "      <td>R</td>\n",
 786 |        "      <td>17</td>\n",
 787 |        "      <td>2</td>\n",
 788 |        "      <td>62</td>\n",
 789 |        "      <td>17</td>\n",
 790 |        "      <td>0</td>\n",
 791 |        "      <td>180</td>\n",
 792 |        "      <td>0</td>\n",
 793 |        "      <td>...</td>\n",
 794 |        "      <td>na</td>\n",
 795 |        "      <td>0</td>\n",
 796 |        "      <td>0</td>\n",
 797 |        "      <td>0</td>\n",
 798 |        "      <td>0</td>\n",
 799 |        "      <td>Libra</td>\n",
 800 |        "      <td>0</td>\n",
 801 |        "      <td>0</td>\n",
 802 |        "      <td>1.43</td>\n",
 803 |        "      <td>0</td>\n",
 804 |        "    </tr>\n",
 805 |        "    <tr>\n",
 806 |        "      <th>18</th>\n",
 807 |        "      <td>0</td>\n",
 808 |        "      <td>20.0</td>\n",
 809 |        "      <td>na</td>\n",
 810 |        "      <td>0</td>\n",
 811 |        "      <td>0</td>\n",
 812 |        "      <td>0</td>\n",
 813 |        "      <td>0</td>\n",
 814 |        "      <td>0</td>\n",
 815 |        "      <td>0</td>\n",
 816 |        "      <td>0</td>\n",
 817 |        "      <td>...</td>\n",
 818 |        "      <td>Monthly</td>\n",
 819 |        "      <td>0</td>\n",
 820 |        "      <td>0</td>\n",
 821 |        "      <td>0</td>\n",
 822 |        "      <td>0</td>\n",
 823 |        "      <td>Sagittarius</td>\n",
 824 |        "      <td>1</td>\n",
 825 |        "      <td>0</td>\n",
 826 |        "      <td>0.00</td>\n",
 827 |        "      <td>0</td>\n",
 828 |        "    </tr>\n",
 829 |        "    <tr>\n",
 830 |        "      <th>19</th>\n",
 831 |        "      <td>1</td>\n",
 832 |        "      <td>30.0</td>\n",
 833 |        "      <td>na</td>\n",
 834 |        "      <td>2</td>\n",
 835 |        "      <td>1</td>\n",
 836 |        "      <td>0</td>\n",
 837 |        "      <td>2</td>\n",
 838 |        "      <td>0</td>\n",
 839 |        "      <td>9</td>\n",
 840 |        "      <td>0</td>\n",
 841 |        "      <td>...</td>\n",
 842 |        "      <td>Bi-Weekly</td>\n",
 843 |        "      <td>0</td>\n",
 844 |        "      <td>0</td>\n",
 845 |        "      <td>0</td>\n",
 846 |        "      <td>0</td>\n",
 847 |        "      <td>Libra</td>\n",
 848 |        "      <td>1</td>\n",
 849 |        "      <td>0</td>\n",
 850 |        "      <td>0.07</td>\n",
 851 |        "      <td>0</td>\n",
 852 |        "    </tr>\n",
 853 |        "    <tr>\n",
 854 |        "      <th>20</th>\n",
 855 |        "      <td>1</td>\n",
 856 |        "      <td>59.0</td>\n",
 857 |        "      <td>na</td>\n",
 858 |        "      <td>0</td>\n",
 859 |        "      <td>0</td>\n",
 860 |        "      <td>0</td>\n",
 861 |        "      <td>0</td>\n",
 862 |        "      <td>0</td>\n",
 863 |        "      <td>0</td>\n",
 864 |        "      <td>0</td>\n",
 865 |        "      <td>...</td>\n",
 866 |        "      <td>Bi-Weekly</td>\n",
 867 |        "      <td>0</td>\n",
 868 |        "      <td>0</td>\n",
 869 |        "      <td>0</td>\n",
 870 |        "      <td>0</td>\n",
 871 |        "      <td>Gemini</td>\n",
 872 |        "      <td>0</td>\n",
 873 |        "      <td>0</td>\n",
 874 |        "      <td>0.00</td>\n",
 875 |        "      <td>0</td>\n",
 876 |        "    </tr>\n",
 877 |        "    <tr>\n",
 878 |        "      <th>21</th>\n",
 879 |        "      <td>1</td>\n",
 880 |        "      <td>21.0</td>\n",
 881 |        "      <td>na</td>\n",
 882 |        "      <td>0</td>\n",
 883 |        "      <td>0</td>\n",
 884 |        "      <td>0</td>\n",
 885 |        "      <td>0</td>\n",
 886 |        "      <td>0</td>\n",
 887 |        "      <td>3</td>\n",
 888 |        "      <td>0</td>\n",
 889 |        "      <td>...</td>\n",
 890 |        "      <td>Bi-Weekly</td>\n",
 891 |        "      <td>0</td>\n",
 892 |        "      <td>0</td>\n",
 893 |        "      <td>0</td>\n",
 894 |        "      <td>0</td>\n",
 895 |        "      <td>Sagittarius</td>\n",
 896 |        "      <td>0</td>\n",
 897 |        "      <td>0</td>\n",
 898 |        "      <td>0.00</td>\n",
 899 |        "      <td>0</td>\n",
 900 |        "    </tr>\n",
 901 |        "    <tr>\n",
 902 |        "      <th>22</th>\n",
 903 |        "      <td>0</td>\n",
 904 |        "      <td>37.0</td>\n",
 905 |        "      <td>R</td>\n",
 906 |        "      <td>0</td>\n",
 907 |        "      <td>0</td>\n",
 908 |        "      <td>39</td>\n",
 909 |        "      <td>0</td>\n",
 910 |        "      <td>0</td>\n",
 911 |        "      <td>74</td>\n",
 912 |        "      <td>0</td>\n",
 913 |        "      <td>...</td>\n",
 914 |        "      <td>na</td>\n",
 915 |        "      <td>0</td>\n",
 916 |        "      <td>1</td>\n",
 917 |        "      <td>0</td>\n",
 918 |        "      <td>0</td>\n",
 919 |        "      <td>Scorpio</td>\n",
 920 |        "      <td>0</td>\n",
 921 |        "      <td>0</td>\n",
 922 |        "      <td>1.33</td>\n",
 923 |        "      <td>0</td>\n",
 924 |        "    </tr>\n",
 925 |        "    <tr>\n",
 926 |        "      <th>23</th>\n",
 927 |        "      <td>1</td>\n",
 928 |        "      <td>30.0</td>\n",
 929 |        "      <td>R</td>\n",
 930 |        "      <td>6</td>\n",
 931 |        "      <td>0</td>\n",
 932 |        "      <td>11</td>\n",
 933 |        "      <td>6</td>\n",
 934 |        "      <td>0</td>\n",
 935 |        "      <td>20</td>\n",
 936 |        "      <td>0</td>\n",
 937 |        "      <td>...</td>\n",
 938 |        "      <td>Bi-Weekly</td>\n",
 939 |        "      <td>0</td>\n",
 940 |        "      <td>0</td>\n",
 941 |        "      <td>0</td>\n",
 942 |        "      <td>0</td>\n",
 943 |        "      <td>Gemini</td>\n",
 944 |        "      <td>0</td>\n",
 945 |        "      <td>0</td>\n",
 946 |        "      <td>0.40</td>\n",
 947 |        "      <td>0</td>\n",
 948 |        "    </tr>\n",
 949 |        "    <tr>\n",
 950 |        "      <th>24</th>\n",
 951 |        "      <td>0</td>\n",
 952 |        "      <td>36.0</td>\n",
 953 |        "      <td>na</td>\n",
 954 |        "      <td>0</td>\n",
 955 |        "      <td>0</td>\n",
 956 |        "      <td>2</td>\n",
 957 |        "      <td>0</td>\n",
 958 |        "      <td>0</td>\n",
 959 |        "      <td>0</td>\n",
 960 |        "      <td>0</td>\n",
 961 |        "      <td>...</td>\n",
 962 |        "      <td>Bi-Weekly</td>\n",
 963 |        "      <td>0</td>\n",
 964 |        "      <td>0</td>\n",
 965 |        "      <td>0</td>\n",
 966 |        "      <td>0</td>\n",
 967 |        "      <td>Aquarius</td>\n",
 968 |        "      <td>0</td>\n",
 969 |        "      <td>0</td>\n",
 970 |        "      <td>0.50</td>\n",
 971 |        "      <td>0</td>\n",
 972 |        "    </tr>\n",
 973 |        "    <tr>\n",
 974 |        "      <th>25</th>\n",
 975 |        "      <td>1</td>\n",
 976 |        "      <td>44.0</td>\n",
 977 |        "      <td>O</td>\n",
 978 |        "      <td>0</td>\n",
 979 |        "      <td>0</td>\n",
 980 |        "      <td>0</td>\n",
 981 |        "      <td>0</td>\n",
 982 |        "      <td>3</td>\n",
 983 |        "      <td>4</td>\n",
 984 |        "      <td>3</td>\n",
 985 |        "      <td>...</td>\n",
 986 |        "      <td>Monthly</td>\n",
 987 |        "      <td>0</td>\n",
 988 |        "      <td>0</td>\n",
 989 |        "      <td>0</td>\n",
 990 |        "      <td>0</td>\n",
 991 |        "      <td>Scorpio</td>\n",
 992 |        "      <td>0</td>\n",
 993 |        "      <td>1</td>\n",
 994 |        "      <td>0.17</td>\n",
 995 |        "      <td>0</td>\n",
 996 |        "    </tr>\n",
 997 |        "    <tr>\n",
 998 |        "      <th>26</th>\n",
 999 |        "      <td>1</td>\n",
1000 |        "      <td>52.0</td>\n",
1001 |        "      <td>na</td>\n",
1002 |        "      <td>0</td>\n",
1003 |        "      <td>0</td>\n",
1004 |        "      <td>0</td>\n",
1005 |        "      <td>0</td>\n",
1006 |        "      <td>0</td>\n",
1007 |        "      <td>74</td>\n",
1008 |        "      <td>0</td>\n",
1009 |        "      <td>...</td>\n",
1010 |        "      <td>Bi-Weekly</td>\n",
1011 |        "      <td>0</td>\n",
1012 |        "      <td>0</td>\n",
1013 |        "      <td>0</td>\n",
1014 |        "      <td>0</td>\n",
1015 |        "      <td>Pisces</td>\n",
1016 |        "      <td>1</td>\n",
1017 |        "      <td>0</td>\n",
1018 |        "      <td>1.30</td>\n",
1019 |        "      <td>0</td>\n",
1020 |        "    </tr>\n",
1021 |        "    <tr>\n",
1022 |        "      <th>27</th>\n",
1023 |        "      <td>1</td>\n",
1024 |        "      <td>25.0</td>\n",
1025 |        "      <td>na</td>\n",
1026 |        "      <td>0</td>\n",
1027 |        "      <td>0</td>\n",
1028 |        "      <td>0</td>\n",
1029 |        "      <td>0</td>\n",
1030 |        "      <td>0</td>\n",
1031 |        "      <td>32</td>\n",
1032 |        "      <td>0</td>\n",
1033 |        "      <td>...</td>\n",
1034 |        "      <td>Monthly</td>\n",
1035 |        "      <td>0</td>\n",
1036 |        "      <td>0</td>\n",
1037 |        "      <td>0</td>\n",
1038 |        "      <td>0</td>\n",
1039 |        "      <td>Virgo</td>\n",
1040 |        "      <td>0</td>\n",
1041 |        "      <td>0</td>\n",
1042 |        "      <td>0.47</td>\n",
1043 |        "      <td>0</td>\n",
1044 |        "    </tr>\n",
1045 |        "    <tr>\n",
1046 |        "      <th>28</th>\n",
1047 |        "      <td>1</td>\n",
1048 |        "      <td>22.0</td>\n",
1049 |        "      <td>na</td>\n",
1050 |        "      <td>0</td>\n",
1051 |        "      <td>0</td>\n",
1052 |        "      <td>0</td>\n",
1053 |        "      <td>0</td>\n",
1054 |        "      <td>1</td>\n",
1055 |        "      <td>67</td>\n",
1056 |        "      <td>1</td>\n",
1057 |        "      <td>...</td>\n",
1058 |        "      <td>Bi-Weekly</td>\n",
1059 |        "      <td>0</td>\n",
1060 |        "      <td>0</td>\n",
1061 |        "      <td>0</td>\n",
1062 |        "      <td>0</td>\n",
1063 |        "      <td>Pisces</td>\n",
1064 |        "      <td>0</td>\n",
1065 |        "      <td>0</td>\n",
1066 |        "      <td>0.90</td>\n",
1067 |        "      <td>0</td>\n",
1068 |        "    </tr>\n",
1069 |        "    <tr>\n",
1070 |        "      <th>29</th>\n",
1071 |        "      <td>0</td>\n",
1072 |        "      <td>38.0</td>\n",
1073 |        "      <td>na</td>\n",
1074 |        "      <td>0</td>\n",
1075 |        "      <td>0</td>\n",
1076 |        "      <td>27</td>\n",
1077 |        "      <td>0</td>\n",
1078 |        "      <td>0</td>\n",
1079 |        "      <td>30</td>\n",
1080 |        "      <td>0</td>\n",
1081 |        "      <td>...</td>\n",
1082 |        "      <td>Bi-Weekly</td>\n",
1083 |        "      <td>0</td>\n",
1084 |        "      <td>0</td>\n",
1085 |        "      <td>0</td>\n",
1086 |        "      <td>0</td>\n",
1087 |        "      <td>Libra</td>\n",
1088 |        "      <td>0</td>\n",
1089 |        "      <td>0</td>\n",
1090 |        "      <td>1.00</td>\n",
1091 |        "      <td>0</td>\n",
1092 |        "    </tr>\n",
1093 |        "    <tr>\n",
1094 |        "      <th>...</th>\n",
1095 |        "      <td>...</td>\n",
1096 |        "      <td>...</td>\n",
1097 |        "      <td>...</td>\n",
1098 |        "      <td>...</td>\n",
1099 |        "      <td>...</td>\n",
1100 |        "      <td>...</td>\n",
1101 |        "      <td>...</td>\n",
1102 |        "      <td>...</td>\n",
1103 |        "      <td>...</td>\n",
1104 |        "      <td>...</td>\n",
1105 |        "      <td>...</td>\n",
1106 |        "      <td>...</td>\n",
1107 |        "      <td>...</td>\n",
1108 |        "      <td>...</td>\n",
1109 |        "      <td>...</td>\n",
1110 |        "      <td>...</td>\n",
1111 |        "      <td>...</td>\n",
1112 |        "      <td>...</td>\n",
1113 |        "      <td>...</td>\n",
1114 |        "      <td>...</td>\n",
1115 |        "      <td>...</td>\n",
1116 |        "    </tr>\n",
1117 |        "    <tr>\n",
1118 |        "      <th>26966</th>\n",
1119 |        "      <td>1</td>\n",
1120 |        "      <td>22.0</td>\n",
1121 |        "      <td>R</td>\n",
1122 |        "      <td>0</td>\n",
1123 |        "      <td>0</td>\n",
1124 |        "      <td>0</td>\n",
1125 |        "      <td>0</td>\n",
1126 |        "      <td>1</td>\n",
1127 |        "      <td>146</td>\n",
1128 |        "      <td>0</td>\n",
1129 |        "      <td>...</td>\n",
1130 |        "      <td>Weekly</td>\n",
1131 |        "      <td>0</td>\n",
1132 |        "      <td>0</td>\n",
1133 |        "      <td>0</td>\n",
1134 |        "      <td>0</td>\n",
1135 |        "      <td>Sagittarius</td>\n",
1136 |        "      <td>0</td>\n",
1137 |        "      <td>0</td>\n",
1138 |        "      <td>1.23</td>\n",
1139 |        "      <td>0</td>\n",
1140 |        "    </tr>\n",
1141 |        "    <tr>\n",
1142 |        "      <th>26967</th>\n",
1143 |        "      <td>1</td>\n",
1144 |        "      <td>25.0</td>\n",
1145 |        "      <td>na</td>\n",
1146 |        "      <td>0</td>\n",
1147 |        "      <td>0</td>\n",
1148 |        "      <td>4</td>\n",
1149 |        "      <td>0</td>\n",
1150 |        "      <td>0</td>\n",
1151 |        "      <td>0</td>\n",
1152 |        "      <td>0</td>\n",
1153 |        "      <td>...</td>\n",
1154 |        "      <td>Bi-Weekly</td>\n",
1155 |        "      <td>0</td>\n",
1156 |        "      <td>0</td>\n",
1157 |        "      <td>0</td>\n",
1158 |        "      <td>0</td>\n",
1159 |        "      <td>Virgo</td>\n",
1160 |        "      <td>0</td>\n",
1161 |        "      <td>0</td>\n",
1162 |        "      <td>0.00</td>\n",
1163 |        "      <td>0</td>\n",
1164 |        "    </tr>\n",
1165 |        "    <tr>\n",
1166 |        "      <th>26968</th>\n",
1167 |        "      <td>0</td>\n",
1168 |        "      <td>24.0</td>\n",
1169 |        "      <td>na</td>\n",
1170 |        "      <td>0</td>\n",
1171 |        "      <td>0</td>\n",
1172 |        "      <td>1</td>\n",
1173 |        "      <td>0</td>\n",
1174 |        "      <td>0</td>\n",
1175 |        "      <td>0</td>\n",
1176 |        "      <td>0</td>\n",
1177 |        "      <td>...</td>\n",
1178 |        "      <td>Bi-Weekly</td>\n",
1179 |        "      <td>0</td>\n",
1180 |        "      <td>0</td>\n",
1181 |        "      <td>0</td>\n",
1182 |        "      <td>0</td>\n",
1183 |        "      <td>Gemini</td>\n",
1184 |        "      <td>0</td>\n",
1185 |        "      <td>0</td>\n",
1186 |        "      <td>0.03</td>\n",
1187 |        "      <td>0</td>\n",
1188 |        "    </tr>\n",
1189 |        "    <tr>\n",
1190 |        "      <th>26969</th>\n",
1191 |        "      <td>1</td>\n",
1192 |        "      <td>25.0</td>\n",
1193 |        "      <td>R</td>\n",
1194 |        "      <td>29</td>\n",
1195 |        "      <td>1</td>\n",
1196 |        "      <td>70</td>\n",
1197 |        "      <td>29</td>\n",
1198 |        "      <td>0</td>\n",
1199 |        "      <td>192</td>\n",
1200 |        "      <td>0</td>\n",
1201 |        "      <td>...</td>\n",
1202 |        "      <td>Bi-Weekly</td>\n",
1203 |        "      <td>0</td>\n",
1204 |        "      <td>0</td>\n",
1205 |        "      <td>0</td>\n",
1206 |        "      <td>0</td>\n",
1207 |        "      <td>Scorpio</td>\n",
1208 |        "      <td>0</td>\n",
1209 |        "      <td>0</td>\n",
1210 |        "      <td>1.00</td>\n",
1211 |        "      <td>0</td>\n",
1212 |        "    </tr>\n",
1213 |        "    <tr>\n",
1214 |        "      <th>26970</th>\n",
1215 |        "      <td>0</td>\n",
1216 |        "      <td>26.0</td>\n",
1217 |        "      <td>na</td>\n",
1218 |        "      <td>0</td>\n",
1219 |        "      <td>0</td>\n",
1220 |        "      <td>3</td>\n",
1221 |        "      <td>0</td>\n",
1222 |        "      <td>0</td>\n",
1223 |        "      <td>0</td>\n",
1224 |        "      <td>0</td>\n",
1225 |        "      <td>...</td>\n",
1226 |        "      <td>Bi-Weekly</td>\n",
1227 |        "      <td>0</td>\n",
1228 |        "      <td>0</td>\n",
1229 |        "      <td>0</td>\n",
1230 |        "      <td>0</td>\n",
1231 |        "      <td>Libra</td>\n",
1232 |        "      <td>0</td>\n",
1233 |        "      <td>0</td>\n",
1234 |        "      <td>0.10</td>\n",
1235 |        "      <td>1</td>\n",
1236 |        "    </tr>\n",
1237 |        "    <tr>\n",
1238 |        "      <th>26971</th>\n",
1239 |        "      <td>0</td>\n",
1240 |        "      <td>32.0</td>\n",
1241 |        "      <td>na</td>\n",
1242 |        "      <td>0</td>\n",
1243 |        "      <td>0</td>\n",
1244 |        "      <td>0</td>\n",
1245 |        "      <td>0</td>\n",
1246 |        "      <td>0</td>\n",
1247 |        "      <td>0</td>\n",
1248 |        "      <td>0</td>\n",
1249 |        "      <td>...</td>\n",
1250 |        "      <td>Bi-Weekly</td>\n",
1251 |        "      <td>0</td>\n",
1252 |        "      <td>0</td>\n",
1253 |        "      <td>0</td>\n",
1254 |        "      <td>0</td>\n",
1255 |        "      <td>Leo</td>\n",
1256 |        "      <td>0</td>\n",
1257 |        "      <td>0</td>\n",
1258 |        "      <td>0.00</td>\n",
1259 |        "      <td>0</td>\n",
1260 |        "    </tr>\n",
1261 |        "    <tr>\n",
1262 |        "      <th>26972</th>\n",
1263 |        "      <td>0</td>\n",
1264 |        "      <td>52.0</td>\n",
1265 |        "      <td>R</td>\n",
1266 |        "      <td>0</td>\n",
1267 |        "      <td>0</td>\n",
1268 |        "      <td>10</td>\n",
1269 |        "      <td>0</td>\n",
1270 |        "      <td>0</td>\n",
1271 |        "      <td>203</td>\n",
1272 |        "      <td>0</td>\n",
1273 |        "      <td>...</td>\n",
1274 |        "      <td>Bi-Weekly</td>\n",
1275 |        "      <td>0</td>\n",
1276 |        "      <td>0</td>\n",
1277 |        "      <td>0</td>\n",
1278 |        "      <td>0</td>\n",
1279 |        "      <td>Leo</td>\n",
1280 |        "      <td>0</td>\n",
1281 |        "      <td>0</td>\n",
1282 |        "      <td>2.03</td>\n",
1283 |        "      <td>0</td>\n",
1284 |        "    </tr>\n",
1285 |        "    <tr>\n",
1286 |        "      <th>26973</th>\n",
1287 |        "      <td>1</td>\n",
1288 |        "      <td>22.0</td>\n",
1289 |        "      <td>R</td>\n",
1290 |        "      <td>0</td>\n",
1291 |        "      <td>0</td>\n",
1292 |        "      <td>2</td>\n",
1293 |        "      <td>0</td>\n",
1294 |        "      <td>1</td>\n",
1295 |        "      <td>134</td>\n",
1296 |        "      <td>0</td>\n",
1297 |        "      <td>...</td>\n",
1298 |        "      <td>Weekly</td>\n",
1299 |        "      <td>0</td>\n",
1300 |        "      <td>0</td>\n",
1301 |        "      <td>0</td>\n",
1302 |        "      <td>0</td>\n",
1303 |        "      <td>Pisces</td>\n",
1304 |        "      <td>0</td>\n",
1305 |        "      <td>0</td>\n",
1306 |        "      <td>1.00</td>\n",
1307 |        "      <td>1</td>\n",
1308 |        "    </tr>\n",
1309 |        "    <tr>\n",
1310 |        "      <th>26974</th>\n",
1311 |        "      <td>0</td>\n",
1312 |        "      <td>54.0</td>\n",
1313 |        "      <td>R</td>\n",
1314 |        "      <td>0</td>\n",
1315 |        "      <td>0</td>\n",
1316 |        "      <td>68</td>\n",
1317 |        "      <td>0</td>\n",
1318 |        "      <td>0</td>\n",
1319 |        "      <td>206</td>\n",
1320 |        "      <td>0</td>\n",
1321 |        "      <td>...</td>\n",
1322 |        "      <td>Bi-Weekly</td>\n",
1323 |        "      <td>0</td>\n",
1324 |        "      <td>0</td>\n",
1325 |        "      <td>0</td>\n",
1326 |        "      <td>0</td>\n",
1327 |        "      <td>Cancer</td>\n",
1328 |        "      <td>1</td>\n",
1329 |        "      <td>0</td>\n",
1330 |        "      <td>1.63</td>\n",
1331 |        "      <td>1</td>\n",
1332 |        "    </tr>\n",
1333 |        "    <tr>\n",
1334 |        "      <th>26975</th>\n",
1335 |        "      <td>1</td>\n",
1336 |        "      <td>33.0</td>\n",
1337 |        "      <td>na</td>\n",
1338 |        "      <td>0</td>\n",
1339 |        "      <td>0</td>\n",
1340 |        "      <td>3</td>\n",
1341 |        "      <td>0</td>\n",
1342 |        "      <td>0</td>\n",
1343 |        "      <td>0</td>\n",
1344 |        "      <td>0</td>\n",
1345 |        "      <td>...</td>\n",
1346 |        "      <td>Monthly</td>\n",
1347 |        "      <td>0</td>\n",
1348 |        "      <td>0</td>\n",
1349 |        "      <td>0</td>\n",
1350 |        "      <td>0</td>\n",
1351 |        "      <td>Cancer</td>\n",
1352 |        "      <td>0</td>\n",
1353 |        "      <td>0</td>\n",
1354 |        "      <td>1.00</td>\n",
1355 |        "      <td>0</td>\n",
1356 |        "    </tr>\n",
1357 |        "    <tr>\n",
1358 |        "      <th>26976</th>\n",
1359 |        "      <td>0</td>\n",
1360 |        "      <td>33.0</td>\n",
1361 |        "      <td>na</td>\n",
1362 |        "      <td>0</td>\n",
1363 |        "      <td>0</td>\n",
1364 |        "      <td>0</td>\n",
1365 |        "      <td>0</td>\n",
1366 |        "      <td>0</td>\n",
1367 |        "      <td>0</td>\n",
1368 |        "      <td>0</td>\n",
1369 |        "      <td>...</td>\n",
1370 |        "      <td>Bi-Weekly</td>\n",
1371 |        "      <td>0</td>\n",
1372 |        "      <td>0</td>\n",
1373 |        "      <td>0</td>\n",
1374 |        "      <td>0</td>\n",
1375 |        "      <td>na</td>\n",
1376 |        "      <td>0</td>\n",
1377 |        "      <td>0</td>\n",
1378 |        "      <td>0.00</td>\n",
1379 |        "      <td>0</td>\n",
1380 |        "    </tr>\n",
1381 |        "    <tr>\n",
1382 |        "      <th>26977</th>\n",
1383 |        "      <td>0</td>\n",
1384 |        "      <td>48.0</td>\n",
1385 |        "      <td>na</td>\n",
1386 |        "      <td>0</td>\n",
1387 |        "      <td>0</td>\n",
1388 |        "      <td>24</td>\n",
1389 |        "      <td>0</td>\n",
1390 |        "      <td>0</td>\n",
1391 |        "      <td>32</td>\n",
1392 |        "      <td>0</td>\n",
1393 |        "      <td>...</td>\n",
1394 |        "      <td>Weekly</td>\n",
1395 |        "      <td>0</td>\n",
1396 |        "      <td>0</td>\n",
1397 |        "      <td>0</td>\n",
1398 |        "      <td>0</td>\n",
1399 |        "      <td>Leo</td>\n",
1400 |        "      <td>0</td>\n",
1401 |        "      <td>0</td>\n",
1402 |        "      <td>0.43</td>\n",
1403 |        "      <td>0</td>\n",
1404 |        "    </tr>\n",
1405 |        "    <tr>\n",
1406 |        "      <th>26978</th>\n",
1407 |        "      <td>0</td>\n",
1408 |        "      <td>38.0</td>\n",
1409 |        "      <td>O</td>\n",
1410 |        "      <td>2</td>\n",
1411 |        "      <td>0</td>\n",
1412 |        "      <td>0</td>\n",
1413 |        "      <td>2</td>\n",
1414 |        "      <td>0</td>\n",
1415 |        "      <td>40</td>\n",
1416 |        "      <td>0</td>\n",
1417 |        "      <td>...</td>\n",
1418 |        "      <td>Bi-Weekly</td>\n",
1419 |        "      <td>0</td>\n",
1420 |        "      <td>0</td>\n",
1421 |        "      <td>0</td>\n",
1422 |        "      <td>0</td>\n",
1423 |        "      <td>Pisces</td>\n",
1424 |        "      <td>0</td>\n",
1425 |        "      <td>0</td>\n",
1426 |        "      <td>0.63</td>\n",
1427 |        "      <td>1</td>\n",
1428 |        "    </tr>\n",
1429 |        "    <tr>\n",
1430 |        "      <th>26979</th>\n",
1431 |        "      <td>1</td>\n",
1432 |        "      <td>34.0</td>\n",
1433 |        "      <td>na</td>\n",
1434 |        "      <td>0</td>\n",
1435 |        "      <td>0</td>\n",
1436 |        "      <td>0</td>\n",
1437 |        "      <td>0</td>\n",
1438 |        "      <td>0</td>\n",
1439 |        "      <td>0</td>\n",
1440 |        "      <td>0</td>\n",
1441 |        "      <td>...</td>\n",
1442 |        "      <td>Monthly</td>\n",
1443 |        "      <td>0</td>\n",
1444 |        "      <td>0</td>\n",
1445 |        "      <td>0</td>\n",
1446 |        "      <td>0</td>\n",
1447 |        "      <td>Scorpio</td>\n",
1448 |        "      <td>0</td>\n",
1449 |        "      <td>0</td>\n",
1450 |        "      <td>0.00</td>\n",
1451 |        "      <td>0</td>\n",
1452 |        "    </tr>\n",
1453 |        "    <tr>\n",
1454 |        "      <th>26980</th>\n",
1455 |        "      <td>0</td>\n",
1456 |        "      <td>25.0</td>\n",
1457 |        "      <td>R</td>\n",
1458 |        "      <td>0</td>\n",
1459 |        "      <td>0</td>\n",
1460 |        "      <td>0</td>\n",
1461 |        "      <td>0</td>\n",
1462 |        "      <td>0</td>\n",
1463 |        "      <td>210</td>\n",
1464 |        "      <td>0</td>\n",
1465 |        "      <td>...</td>\n",
1466 |        "      <td>Weekly</td>\n",
1467 |        "      <td>0</td>\n",
1468 |        "      <td>0</td>\n",
1469 |        "      <td>1</td>\n",
1470 |        "      <td>0</td>\n",
1471 |        "      <td>Aquarius</td>\n",
1472 |        "      <td>0</td>\n",
1473 |        "      <td>0</td>\n",
1474 |        "      <td>2.00</td>\n",
1475 |        "      <td>0</td>\n",
1476 |        "    </tr>\n",
1477 |        "    <tr>\n",
1478 |        "      <th>26981</th>\n",
1479 |        "      <td>0</td>\n",
1480 |        "      <td>23.0</td>\n",
1481 |        "      <td>na</td>\n",
1482 |        "      <td>0</td>\n",
1483 |        "      <td>0</td>\n",
1484 |        "      <td>48</td>\n",
1485 |        "      <td>0</td>\n",
1486 |        "      <td>0</td>\n",
1487 |        "      <td>124</td>\n",
1488 |        "      <td>0</td>\n",
1489 |        "      <td>...</td>\n",
1490 |        "      <td>Weekly</td>\n",
1491 |        "      <td>0</td>\n",
1492 |        "      <td>0</td>\n",
1493 |        "      <td>0</td>\n",
1494 |        "      <td>0</td>\n",
1495 |        "      <td>Aries</td>\n",
1496 |        "      <td>0</td>\n",
1497 |        "      <td>0</td>\n",
1498 |        "      <td>1.60</td>\n",
1499 |        "      <td>1</td>\n",
1500 |        "    </tr>\n",
1501 |        "    <tr>\n",
1502 |        "      <th>26982</th>\n",
1503 |        "      <td>0</td>\n",
1504 |        "      <td>35.0</td>\n",
1505 |        "      <td>na</td>\n",
1506 |        "      <td>0</td>\n",
1507 |        "      <td>0</td>\n",
1508 |        "      <td>57</td>\n",
1509 |        "      <td>0</td>\n",
1510 |        "      <td>0</td>\n",
1511 |        "      <td>156</td>\n",
1512 |        "      <td>0</td>\n",
1513 |        "      <td>...</td>\n",
1514 |        "      <td>Weekly</td>\n",
1515 |        "      <td>0</td>\n",
1516 |        "      <td>0</td>\n",
1517 |        "      <td>0</td>\n",
1518 |        "      <td>0</td>\n",
1519 |        "      <td>Leo</td>\n",
1520 |        "      <td>0</td>\n",
1521 |        "      <td>0</td>\n",
1522 |        "      <td>1.47</td>\n",
1523 |        "      <td>1</td>\n",
1524 |        "    </tr>\n",
1525 |        "    <tr>\n",
1526 |        "      <th>26983</th>\n",
1527 |        "      <td>0</td>\n",
1528 |        "      <td>23.0</td>\n",
1529 |        "      <td>na</td>\n",
1530 |        "      <td>0</td>\n",
1531 |        "      <td>0</td>\n",
1532 |        "      <td>50</td>\n",
1533 |        "      <td>0</td>\n",
1534 |        "      <td>0</td>\n",
1535 |        "      <td>152</td>\n",
1536 |        "      <td>0</td>\n",
1537 |        "      <td>...</td>\n",
1538 |        "      <td>Bi-Weekly</td>\n",
1539 |        "      <td>0</td>\n",
1540 |        "      <td>0</td>\n",
1541 |        "      <td>0</td>\n",
1542 |        "      <td>0</td>\n",
1543 |        "      <td>Leo</td>\n",
1544 |        "      <td>0</td>\n",
1545 |        "      <td>0</td>\n",
1546 |        "      <td>1.07</td>\n",
1547 |        "      <td>1</td>\n",
1548 |        "    </tr>\n",
1549 |        "    <tr>\n",
1550 |        "      <th>26984</th>\n",
1551 |        "      <td>0</td>\n",
1552 |        "      <td>24.0</td>\n",
1553 |        "      <td>R</td>\n",
1554 |        "      <td>0</td>\n",
1555 |        "      <td>0</td>\n",
1556 |        "      <td>62</td>\n",
1557 |        "      <td>0</td>\n",
1558 |        "      <td>0</td>\n",
1559 |        "      <td>136</td>\n",
1560 |        "      <td>0</td>\n",
1561 |        "      <td>...</td>\n",
1562 |        "      <td>Bi-Weekly</td>\n",
1563 |        "      <td>0</td>\n",
1564 |        "      <td>0</td>\n",
1565 |        "      <td>0</td>\n",
1566 |        "      <td>0</td>\n",
1567 |        "      <td>Virgo</td>\n",
1568 |        "      <td>0</td>\n",
1569 |        "      <td>0</td>\n",
1570 |        "      <td>1.60</td>\n",
1571 |        "      <td>0</td>\n",
1572 |        "    </tr>\n",
1573 |        "    <tr>\n",
1574 |        "      <th>26985</th>\n",
1575 |        "      <td>0</td>\n",
1576 |        "      <td>31.0</td>\n",
1577 |        "      <td>R</td>\n",
1578 |        "      <td>0</td>\n",
1579 |        "      <td>0</td>\n",
1580 |        "      <td>22</td>\n",
1581 |        "      <td>0</td>\n",
1582 |        "      <td>0</td>\n",
1583 |        "      <td>138</td>\n",
1584 |        "      <td>0</td>\n",
1585 |        "      <td>...</td>\n",
1586 |        "      <td>Monthly</td>\n",
1587 |        "      <td>0</td>\n",
1588 |        "      <td>0</td>\n",
1589 |        "      <td>0</td>\n",
1590 |        "      <td>0</td>\n",
1591 |        "      <td>Virgo</td>\n",
1592 |        "      <td>0</td>\n",
1593 |        "      <td>0</td>\n",
1594 |        "      <td>1.63</td>\n",
1595 |        "      <td>0</td>\n",
1596 |        "    </tr>\n",
1597 |        "    <tr>\n",
1598 |        "      <th>26986</th>\n",
1599 |        "      <td>0</td>\n",
1600 |        "      <td>29.0</td>\n",
1601 |        "      <td>R</td>\n",
1602 |        "      <td>1</td>\n",
1603 |        "      <td>1</td>\n",
1604 |        "      <td>70</td>\n",
1605 |        "      <td>1</td>\n",
1606 |        "      <td>0</td>\n",
1607 |        "      <td>147</td>\n",
1608 |        "      <td>0</td>\n",
1609 |        "      <td>...</td>\n",
1610 |        "      <td>Bi-Weekly</td>\n",
1611 |        "      <td>0</td>\n",
1612 |        "      <td>0</td>\n",
1613 |        "      <td>0</td>\n",
1614 |        "      <td>0</td>\n",
1615 |        "      <td>Cancer</td>\n",
1616 |        "      <td>0</td>\n",
1617 |        "      <td>0</td>\n",
1618 |        "      <td>1.07</td>\n",
1619 |        "      <td>1</td>\n",
1620 |        "    </tr>\n",
1621 |        "    <tr>\n",
1622 |        "      <th>26987</th>\n",
1623 |        "      <td>0</td>\n",
1624 |        "      <td>30.0</td>\n",
1625 |        "      <td>na</td>\n",
1626 |        "      <td>0</td>\n",
1627 |        "      <td>0</td>\n",
1628 |        "      <td>2</td>\n",
1629 |        "      <td>0</td>\n",
1630 |        "      <td>0</td>\n",
1631 |        "      <td>4</td>\n",
1632 |        "      <td>0</td>\n",
1633 |        "      <td>...</td>\n",
1634 |        "      <td>Bi-Weekly</td>\n",
1635 |        "      <td>0</td>\n",
1636 |        "      <td>0</td>\n",
1637 |        "      <td>0</td>\n",
1638 |        "      <td>0</td>\n",
1639 |        "      <td>Leo</td>\n",
1640 |        "      <td>0</td>\n",
1641 |        "      <td>0</td>\n",
1642 |        "      <td>0.03</td>\n",
1643 |        "      <td>0</td>\n",
1644 |        "    </tr>\n",
1645 |        "    <tr>\n",
1646 |        "      <th>26988</th>\n",
1647 |        "      <td>1</td>\n",
1648 |        "      <td>20.0</td>\n",
1649 |        "      <td>R</td>\n",
1650 |        "      <td>0</td>\n",
1651 |        "      <td>0</td>\n",
1652 |        "      <td>2</td>\n",
1653 |        "      <td>0</td>\n",
1654 |        "      <td>0</td>\n",
1655 |        "      <td>5</td>\n",
1656 |        "      <td>0</td>\n",
1657 |        "      <td>...</td>\n",
1658 |        "      <td>Bi-Weekly</td>\n",
1659 |        "      <td>0</td>\n",
1660 |        "      <td>0</td>\n",
1661 |        "      <td>0</td>\n",
1662 |        "      <td>0</td>\n",
1663 |        "      <td>Leo</td>\n",
1664 |        "      <td>1</td>\n",
1665 |        "      <td>0</td>\n",
1666 |        "      <td>0.13</td>\n",
1667 |        "      <td>0</td>\n",
1668 |        "    </tr>\n",
1669 |        "    <tr>\n",
1670 |        "      <th>26989</th>\n",
1671 |        "      <td>0</td>\n",
1672 |        "      <td>29.0</td>\n",
1673 |        "      <td>na</td>\n",
1674 |        "      <td>1</td>\n",
1675 |        "      <td>1</td>\n",
1676 |        "      <td>5</td>\n",
1677 |        "      <td>1</td>\n",
1678 |        "      <td>0</td>\n",
1679 |        "      <td>5</td>\n",
1680 |        "      <td>0</td>\n",
1681 |        "      <td>...</td>\n",
1682 |        "      <td>Bi-Weekly</td>\n",
1683 |        "      <td>0</td>\n",
1684 |        "      <td>0</td>\n",
1685 |        "      <td>0</td>\n",
1686 |        "      <td>0</td>\n",
1687 |        "      <td>Scorpio</td>\n",
1688 |        "      <td>1</td>\n",
1689 |        "      <td>0</td>\n",
1690 |        "      <td>0.03</td>\n",
1691 |        "      <td>0</td>\n",
1692 |        "    </tr>\n",
1693 |        "    <tr>\n",
1694 |        "      <th>26990</th>\n",
1695 |        "      <td>1</td>\n",
1696 |        "      <td>28.0</td>\n",
1697 |        "      <td>R</td>\n",
1698 |        "      <td>0</td>\n",
1699 |        "      <td>0</td>\n",
1700 |        "      <td>26</td>\n",
1701 |        "      <td>0</td>\n",
1702 |        "      <td>0</td>\n",
1703 |        "      <td>31</td>\n",
1704 |        "      <td>0</td>\n",
1705 |        "      <td>...</td>\n",
1706 |        "      <td>Monthly</td>\n",
1707 |        "      <td>0</td>\n",
1708 |        "      <td>0</td>\n",
1709 |        "      <td>0</td>\n",
1710 |        "      <td>0</td>\n",
1711 |        "      <td>Virgo</td>\n",
1712 |        "      <td>0</td>\n",
1713 |        "      <td>0</td>\n",
1714 |        "      <td>0.60</td>\n",
1715 |        "      <td>0</td>\n",
1716 |        "    </tr>\n",
1717 |        "    <tr>\n",
1718 |        "      <th>26991</th>\n",
1719 |        "      <td>1</td>\n",
1720 |        "      <td>24.0</td>\n",
1721 |        "      <td>R</td>\n",
1722 |        "      <td>0</td>\n",
1723 |        "      <td>0</td>\n",
1724 |        "      <td>0</td>\n",
1725 |        "      <td>0</td>\n",
1726 |        "      <td>0</td>\n",
1727 |        "      <td>81</td>\n",
1728 |        "      <td>0</td>\n",
1729 |        "      <td>...</td>\n",
1730 |        "      <td>Weekly</td>\n",
1731 |        "      <td>0</td>\n",
1732 |        "      <td>0</td>\n",
1733 |        "      <td>0</td>\n",
1734 |        "      <td>0</td>\n",
1735 |        "      <td>Leo</td>\n",
1736 |        "      <td>0</td>\n",
1737 |        "      <td>0</td>\n",
1738 |        "      <td>1.07</td>\n",
1739 |        "      <td>1</td>\n",
1740 |        "    </tr>\n",
1741 |        "    <tr>\n",
1742 |        "      <th>26992</th>\n",
1743 |        "      <td>1</td>\n",
1744 |        "      <td>26.0</td>\n",
1745 |        "      <td>na</td>\n",
1746 |        "      <td>0</td>\n",
1747 |        "      <td>0</td>\n",
1748 |        "      <td>2</td>\n",
1749 |        "      <td>0</td>\n",
1750 |        "      <td>0</td>\n",
1751 |        "      <td>1</td>\n",
1752 |        "      <td>0</td>\n",
1753 |        "      <td>...</td>\n",
1754 |        "      <td>Bi-Weekly</td>\n",
1755 |        "      <td>0</td>\n",
1756 |        "      <td>0</td>\n",
1757 |        "      <td>0</td>\n",
1758 |        "      <td>1</td>\n",
1759 |        "      <td>Cancer</td>\n",
1760 |        "      <td>1</td>\n",
1761 |        "      <td>0</td>\n",
1762 |        "      <td>0.67</td>\n",
1763 |        "      <td>0</td>\n",
1764 |        "    </tr>\n",
1765 |        "    <tr>\n",
1766 |        "      <th>26993</th>\n",
1767 |        "      <td>0</td>\n",
1768 |        "      <td>22.0</td>\n",
1769 |        "      <td>na</td>\n",
1770 |        "      <td>0</td>\n",
1771 |        "      <td>0</td>\n",
1772 |        "      <td>37</td>\n",
1773 |        "      <td>0</td>\n",
1774 |        "      <td>0</td>\n",
1775 |        "      <td>98</td>\n",
1776 |        "      <td>0</td>\n",
1777 |        "      <td>...</td>\n",
1778 |        "      <td>Bi-Weekly</td>\n",
1779 |        "      <td>0</td>\n",
1780 |        "      <td>0</td>\n",
1781 |        "      <td>0</td>\n",
1782 |        "      <td>0</td>\n",
1783 |        "      <td>Taurus</td>\n",
1784 |        "      <td>0</td>\n",
1785 |        "      <td>0</td>\n",
1786 |        "      <td>0.93</td>\n",
1787 |        "      <td>0</td>\n",
1788 |        "    </tr>\n",
1789 |        "    <tr>\n",
1790 |        "      <th>26994</th>\n",
1791 |        "      <td>1</td>\n",
1792 |        "      <td>46.0</td>\n",
1793 |        "      <td>na</td>\n",
1794 |        "      <td>2</td>\n",
1795 |        "      <td>0</td>\n",
1796 |        "      <td>16</td>\n",
1797 |        "      <td>2</td>\n",
1798 |        "      <td>0</td>\n",
1799 |        "      <td>58</td>\n",
1800 |        "      <td>0</td>\n",
1801 |        "      <td>...</td>\n",
1802 |        "      <td>Semi-Monthly</td>\n",
1803 |        "      <td>0</td>\n",
1804 |        "      <td>0</td>\n",
1805 |        "      <td>0</td>\n",
1806 |        "      <td>0</td>\n",
1807 |        "      <td>Aries</td>\n",
1808 |        "      <td>1</td>\n",
1809 |        "      <td>0</td>\n",
1810 |        "      <td>0.90</td>\n",
1811 |        "      <td>1</td>\n",
1812 |        "    </tr>\n",
1813 |        "    <tr>\n",
1814 |        "      <th>26995</th>\n",
1815 |        "      <td>1</td>\n",
1816 |        "      <td>34.0</td>\n",
1817 |        "      <td>na</td>\n",
1818 |        "      <td>0</td>\n",
1819 |        "      <td>0</td>\n",
1820 |        "      <td>4</td>\n",
1821 |        "      <td>0</td>\n",
1822 |        "      <td>0</td>\n",
1823 |        "      <td>11</td>\n",
1824 |        "      <td>0</td>\n",
1825 |        "      <td>...</td>\n",
1826 |        "      <td>na</td>\n",
1827 |        "      <td>0</td>\n",
1828 |        "      <td>0</td>\n",
1829 |        "      <td>0</td>\n",
1830 |        "      <td>0</td>\n",
1831 |        "      <td>Cancer</td>\n",
1832 |        "      <td>0</td>\n",
1833 |        "      <td>0</td>\n",
1834 |        "      <td>0.13</td>\n",
1835 |        "      <td>0</td>\n",
1836 |        "    </tr>\n",
1837 |        "  </tbody>\n",
1838 |        "</table>\n",
1839 |        "<p>26996 rows × 27 columns</p>\n",
1840 |        "</div>"
1841 |       ],
1842 |       "text/plain": [
1843 |        "       churn   age housing  deposits  withdrawal  purchases_partners  \\\n",
1844 |        "0          0  37.0      na         0           0                   0   \n",
1845 |        "1          0  28.0       R         0           0                   1   \n",
1846 |        "2          0  35.0       R        47           2                  86   \n",
1847 |        "3          0  26.0       R        26           3                  38   \n",
1848 |        "4          1  27.0      na         0           0                   2   \n",
1849 |        "5          1  32.0       R         5           3                 111   \n",
1850 |        "6          0  21.0      na         0           0                   4   \n",
1851 |        "7          0  24.0      na         0           0                   2   \n",
1852 |        "8          0  28.0       R         0           0                   0   \n",
1853 |        "9          0  23.0      na         1           0                  87   \n",
1854 |        "10         0  32.0       R         0           0                  30   \n",
1855 |        "11         0  41.0       O        14           0                 116   \n",
1856 |        "12         0  20.0      na         0           0                 135   \n",
1857 |        "13         0  27.0       O         2           1                  48   \n",
1858 |        "14         0  47.0      na        11           1                  20   \n",
1859 |        "15         1  44.0      na         0           0                   0   \n",
1860 |        "16         1  24.0      na         6           2                  24   \n",
1861 |        "17         0  31.0       R        17           2                  62   \n",
1862 |        "18         0  20.0      na         0           0                   0   \n",
1863 |        "19         1  30.0      na         2           1                   0   \n",
1864 |        "20         1  59.0      na         0           0                   0   \n",
1865 |        "21         1  21.0      na         0           0                   0   \n",
1866 |        "22         0  37.0       R         0           0                  39   \n",
1867 |        "23         1  30.0       R         6           0                  11   \n",
1868 |        "24         0  36.0      na         0           0                   2   \n",
1869 |        "25         1  44.0       O         0           0                   0   \n",
1870 |        "26         1  52.0      na         0           0                   0   \n",
1871 |        "27         1  25.0      na         0           0                   0   \n",
1872 |        "28         1  22.0      na         0           0                   0   \n",
1873 |        "29         0  38.0      na         0           0                  27   \n",
1874 |        "...      ...   ...     ...       ...         ...                 ...   \n",
1875 |        "26966      1  22.0       R         0           0                   0   \n",
1876 |        "26967      1  25.0      na         0           0                   4   \n",
1877 |        "26968      0  24.0      na         0           0                   1   \n",
1878 |        "26969      1  25.0       R        29           1                  70   \n",
1879 |        "26970      0  26.0      na         0           0                   3   \n",
1880 |        "26971      0  32.0      na         0           0                   0   \n",
1881 |        "26972      0  52.0       R         0           0                  10   \n",
1882 |        "26973      1  22.0       R         0           0                   2   \n",
1883 |        "26974      0  54.0       R         0           0                  68   \n",
1884 |        "26975      1  33.0      na         0           0                   3   \n",
1885 |        "26976      0  33.0      na         0           0                   0   \n",
1886 |        "26977      0  48.0      na         0           0                  24   \n",
1887 |        "26978      0  38.0       O         2           0                   0   \n",
1888 |        "26979      1  34.0      na         0           0                   0   \n",
1889 |        "26980      0  25.0       R         0           0                   0   \n",
1890 |        "26981      0  23.0      na         0           0                  48   \n",
1891 |        "26982      0  35.0      na         0           0                  57   \n",
1892 |        "26983      0  23.0      na         0           0                  50   \n",
1893 |        "26984      0  24.0       R         0           0                  62   \n",
1894 |        "26985      0  31.0       R         0           0                  22   \n",
1895 |        "26986      0  29.0       R         1           1                  70   \n",
1896 |        "26987      0  30.0      na         0           0                   2   \n",
1897 |        "26988      1  20.0       R         0           0                   2   \n",
1898 |        "26989      0  29.0      na         1           1                   5   \n",
1899 |        "26990      1  28.0       R         0           0                  26   \n",
1900 |        "26991      1  24.0       R         0           0                   0   \n",
1901 |        "26992      1  26.0      na         0           0                   2   \n",
1902 |        "26993      0  22.0      na         0           0                  37   \n",
1903 |        "26994      1  46.0      na         2           0                  16   \n",
1904 |        "26995      1  34.0      na         0           0                   4   \n",
1905 |        "\n",
1906 |        "       purchases  cc_taken  cc_recommended  cc_disliked     ...       \\\n",
1907 |        "0              0         0               0            0     ...        \n",
1908 |        "1              0         0              96            0     ...        \n",
1909 |        "2             47         0             285            0     ...        \n",
1910 |        "3             25         0              74            0     ...        \n",
1911 |        "4              0         0               0            0     ...        \n",
1912 |        "5              5         0             227            0     ...        \n",
1913 |        "6              0         0               0            0     ...        \n",
1914 |        "7              0         0               0            0     ...        \n",
1915 |        "8              0         2              47            1     ...        \n",
1916 |        "9              1         0             125            0     ...        \n",
1917 |        "10             0         0              70            0     ...        \n",
1918 |        "11            13         0             217            0     ...        \n",
1919 |        "12             0         0             286            0     ...        \n",
1920 |        "13             2         0             127            0     ...        \n",
1921 |        "14            11         0              30            0     ...        \n",
1922 |        "15             0         1               4            0     ...        \n",
1923 |        "16             6         0              55            0     ...        \n",
1924 |        "17            17         0             180            0     ...        \n",
1925 |        "18             0         0               0            0     ...        \n",
1926 |        "19             2         0               9            0     ...        \n",
1927 |        "20             0         0               0            0     ...        \n",
1928 |        "21             0         0               3            0     ...        \n",
1929 |        "22             0         0              74            0     ...        \n",
1930 |        "23             6         0              20            0     ...        \n",
1931 |        "24             0         0               0            0     ...        \n",
1932 |        "25             0         3               4            3     ...        \n",
1933 |        "26             0         0              74            0     ...        \n",
1934 |        "27             0         0              32            0     ...        \n",
1935 |        "28             0         1              67            1     ...        \n",
1936 |        "29             0         0              30            0     ...        \n",
1937 |        "...          ...       ...             ...          ...     ...        \n",
1938 |        "26966          0         1             146            0     ...        \n",
1939 |        "26967          0         0               0            0     ...        \n",
1940 |        "26968          0         0               0            0     ...        \n",
1941 |        "26969         29         0             192            0     ...        \n",
1942 |        "26970          0         0               0            0     ...        \n",
1943 |        "26971          0         0               0            0     ...        \n",
1944 |        "26972          0         0             203            0     ...        \n",
1945 |        "26973          0         1             134            0     ...        \n",
1946 |        "26974          0         0             206            0     ...        \n",
1947 |        "26975          0         0               0            0     ...        \n",
1948 |        "26976          0         0               0            0     ...        \n",
1949 |        "26977          0         0              32            0     ...        \n",
1950 |        "26978          2         0              40            0     ...        \n",
1951 |        "26979          0         0               0            0     ...        \n",
1952 |        "26980          0         0             210            0     ...        \n",
1953 |        "26981          0         0             124            0     ...        \n",
1954 |        "26982          0         0             156            0     ...        \n",
1955 |        "26983          0         0             152            0     ...        \n",
1956 |        "26984          0         0             136            0     ...        \n",
1957 |        "26985          0         0             138            0     ...        \n",
1958 |        "26986          1         0             147            0     ...        \n",
1959 |        "26987          0         0               4            0     ...        \n",
1960 |        "26988          0         0               5            0     ...        \n",
1961 |        "26989          1         0               5            0     ...        \n",
1962 |        "26990          0         0              31            0     ...        \n",
1963 |        "26991          0         0              81            0     ...        \n",
1964 |        "26992          0         0               1            0     ...        \n",
1965 |        "26993          0         0              98            0     ...        \n",
1966 |        "26994          2         0              58            0     ...        \n",
1967 |        "26995          0         0              11            0     ...        \n",
1968 |        "\n",
1969 |        "       payment_type  waiting_4_loan  cancelled_loan  received_loan  \\\n",
1970 |        "0         Bi-Weekly               0               0              0   \n",
1971 |        "1            Weekly               0               0              0   \n",
1972 |        "2      Semi-Monthly               0               0              0   \n",
1973 |        "3         Bi-Weekly               0               0              0   \n",
1974 |        "4         Bi-Weekly               0               0              0   \n",
1975 |        "5         Bi-Weekly               0               0              0   \n",
1976 |        "6         Bi-Weekly               0               0              0   \n",
1977 |        "7                na               0               0              0   \n",
1978 |        "8         Bi-Weekly               0               0              0   \n",
1979 |        "9         Bi-Weekly               0               0              0   \n",
1980 |        "10          Monthly               0               0              0   \n",
1981 |        "11     Semi-Monthly               0               0              0   \n",
1982 |        "12        Bi-Weekly               0               0              0   \n",
1983 |        "13           Weekly               0               0              0   \n",
1984 |        "14        Bi-Weekly               0               0              0   \n",
1985 |        "15     Semi-Monthly               0               0              0   \n",
1986 |        "16           Weekly               0               0              0   \n",
1987 |        "17               na               0               0              0   \n",
1988 |        "18          Monthly               0               0              0   \n",
1989 |        "19        Bi-Weekly               0               0              0   \n",
1990 |        "20        Bi-Weekly               0               0              0   \n",
1991 |        "21        Bi-Weekly               0               0              0   \n",
1992 |        "22               na               0               1              0   \n",
1993 |        "23        Bi-Weekly               0               0              0   \n",
1994 |        "24        Bi-Weekly               0               0              0   \n",
1995 |        "25          Monthly               0               0              0   \n",
1996 |        "26        Bi-Weekly               0               0              0   \n",
1997 |        "27          Monthly               0               0              0   \n",
1998 |        "28        Bi-Weekly               0               0              0   \n",
1999 |        "29        Bi-Weekly               0               0              0   \n",
2000 |        "...             ...             ...             ...            ...   \n",
2001 |        "26966        Weekly               0               0              0   \n",
2002 |        "26967     Bi-Weekly               0               0              0   \n",
2003 |        "26968     Bi-Weekly               0               0              0   \n",
2004 |        "26969     Bi-Weekly               0               0              0   \n",
2005 |        "26970     Bi-Weekly               0               0              0   \n",
2006 |        "26971     Bi-Weekly               0               0              0   \n",
2007 |        "26972     Bi-Weekly               0               0              0   \n",
2008 |        "26973        Weekly               0               0              0   \n",
2009 |        "26974     Bi-Weekly               0               0              0   \n",
2010 |        "26975       Monthly               0               0              0   \n",
2011 |        "26976     Bi-Weekly               0               0              0   \n",
2012 |        "26977        Weekly               0               0              0   \n",
2013 |        "26978     Bi-Weekly               0               0              0   \n",
2014 |        "26979       Monthly               0               0              0   \n",
2015 |        "26980        Weekly               0               0              1   \n",
2016 |        "26981        Weekly               0               0              0   \n",
2017 |        "26982        Weekly               0               0              0   \n",
2018 |        "26983     Bi-Weekly               0               0              0   \n",
2019 |        "26984     Bi-Weekly               0               0              0   \n",
2020 |        "26985       Monthly               0               0              0   \n",
2021 |        "26986     Bi-Weekly               0               0              0   \n",
2022 |        "26987     Bi-Weekly               0               0              0   \n",
2023 |        "26988     Bi-Weekly               0               0              0   \n",
2024 |        "26989     Bi-Weekly               0               0              0   \n",
2025 |        "26990       Monthly               0               0              0   \n",
2026 |        "26991        Weekly               0               0              0   \n",
2027 |        "26992     Bi-Weekly               0               0              0   \n",
2028 |        "26993     Bi-Weekly               0               0              0   \n",
2029 |        "26994  Semi-Monthly               0               0              0   \n",
2030 |        "26995            na               0               0              0   \n",
2031 |        "\n",
2032 |        "       rejected_loan  zodiac_sign  left_for_two_month_plus left_for_one_month  \\\n",
2033 |        "0                  0          Leo                        1                  0   \n",
2034 |        "1                  0          Leo                        0                  0   \n",
2035 |        "2                  0    Capricorn                        1                  0   \n",
2036 |        "3                  0    Capricorn                        0                  0   \n",
2037 |        "4                  0        Aries                        1                  0   \n",
2038 |        "5                  0       Taurus                        0                  0   \n",
2039 |        "6                  0       Cancer                        0                  0   \n",
2040 |        "7                  0          Leo                        0                  0   \n",
2041 |        "8                  0  Sagittarius                        0                  0   \n",
2042 |        "9                  0     Aquarius                        0                  0   \n",
2043 |        "10                 0        Virgo                        0                  0   \n",
2044 |        "11                 0        Virgo                        0                  0   \n",
2045 |        "12                 0        Libra                        0                  0   \n",
2046 |        "13                 0       Gemini                        0                  0   \n",
2047 |        "14                 0        Virgo                        0                  0   \n",
2048 |        "15                 0        Libra                        0                  0   \n",
2049 |        "16                 0    Capricorn                        0                  0   \n",
2050 |        "17                 0        Libra                        0                  0   \n",
2051 |        "18                 0  Sagittarius                        1                  0   \n",
2052 |        "19                 0        Libra                        1                  0   \n",
2053 |        "20                 0       Gemini                        0                  0   \n",
2054 |        "21                 0  Sagittarius                        0                  0   \n",
2055 |        "22                 0      Scorpio                        0                  0   \n",
2056 |        "23                 0       Gemini                        0                  0   \n",
2057 |        "24                 0     Aquarius                        0                  0   \n",
2058 |        "25                 0      Scorpio                        0                  1   \n",
2059 |        "26                 0       Pisces                        1                  0   \n",
2060 |        "27                 0        Virgo                        0                  0   \n",
2061 |        "28                 0       Pisces                        0                  0   \n",
2062 |        "29                 0        Libra                        0                  0   \n",
2063 |        "...              ...          ...                      ...                ...   \n",
2064 |        "26966              0  Sagittarius                        0                  0   \n",
2065 |        "26967              0        Virgo                        0                  0   \n",
2066 |        "26968              0       Gemini                        0                  0   \n",
2067 |        "26969              0      Scorpio                        0                  0   \n",
2068 |        "26970              0        Libra                        0                  0   \n",
2069 |        "26971              0          Leo                        0                  0   \n",
2070 |        "26972              0          Leo                        0                  0   \n",
2071 |        "26973              0       Pisces                        0                  0   \n",
2072 |        "26974              0       Cancer                        1                  0   \n",
2073 |        "26975              0       Cancer                        0                  0   \n",
2074 |        "26976              0           na                        0                  0   \n",
2075 |        "26977              0          Leo                        0                  0   \n",
2076 |        "26978              0       Pisces                        0                  0   \n",
2077 |        "26979              0      Scorpio                        0                  0   \n",
2078 |        "26980              0     Aquarius                        0                  0   \n",
2079 |        "26981              0        Aries                        0                  0   \n",
2080 |        "26982              0          Leo                        0                  0   \n",
2081 |        "26983              0          Leo                        0                  0   \n",
2082 |        "26984              0        Virgo                        0                  0   \n",
2083 |        "26985              0        Virgo                        0                  0   \n",
2084 |        "26986              0       Cancer                        0                  0   \n",
2085 |        "26987              0          Leo                        0                  0   \n",
2086 |        "26988              0          Leo                        1                  0   \n",
2087 |        "26989              0      Scorpio                        1                  0   \n",
2088 |        "26990              0        Virgo                        0                  0   \n",
2089 |        "26991              0          Leo                        0                  0   \n",
2090 |        "26992              1       Cancer                        1                  0   \n",
2091 |        "26993              0       Taurus                        0                  0   \n",
2092 |        "26994              0        Aries                        1                  0   \n",
2093 |        "26995              0       Cancer                        0                  0   \n",
2094 |        "\n",
2095 |        "       reward_rate  is_referred  \n",
2096 |        "0             0.00            0  \n",
2097 |        "1             1.47            1  \n",
2098 |        "2             2.17            0  \n",
2099 |        "3             1.10            1  \n",
2100 |        "4             0.03            0  \n",
2101 |        "5             1.83            0  \n",
2102 |        "6             0.07            0  \n",
2103 |        "7             0.11            0  \n",
2104 |        "8             0.87            1  \n",
2105 |        "9             1.07            0  \n",
2106 |        "10            0.83            1  \n",
2107 |        "11            2.17            0  \n",
2108 |        "12            2.20            1  \n",
2109 |        "13            1.00            0  \n",
2110 |        "14            0.69            1  \n",
2111 |        "15            0.07            0  \n",
2112 |        "16            0.90            0  \n",
2113 |        "17            1.43            0  \n",
2114 |        "18            0.00            0  \n",
2115 |        "19            0.07            0  \n",
2116 |        "20            0.00            0  \n",
2117 |        "21            0.00            0  \n",
2118 |        "22            1.33            0  \n",
2119 |        "23            0.40            0  \n",
2120 |        "24            0.50            0  \n",
2121 |        "25            0.17            0  \n",
2122 |        "26            1.30            0  \n",
2123 |        "27            0.47            0  \n",
2124 |        "28            0.90            0  \n",
2125 |        "29            1.00            0  \n",
2126 |        "...            ...          ...  \n",
2127 |        "26966         1.23            0  \n",
2128 |        "26967         0.00            0  \n",
2129 |        "26968         0.03            0  \n",
2130 |        "26969         1.00            0  \n",
2131 |        "26970         0.10            1  \n",
2132 |        "26971         0.00            0  \n",
2133 |        "26972         2.03            0  \n",
2134 |        "26973         1.00            1  \n",
2135 |        "26974         1.63            1  \n",
2136 |        "26975         1.00            0  \n",
2137 |        "26976         0.00            0  \n",
2138 |        "26977         0.43            0  \n",
2139 |        "26978         0.63            1  \n",
2140 |        "26979         0.00            0  \n",
2141 |        "26980         2.00            0  \n",
2142 |        "26981         1.60            1  \n",
2143 |        "26982         1.47            1  \n",
2144 |        "26983         1.07            1  \n",
2145 |        "26984         1.60            0  \n",
2146 |        "26985         1.63            0  \n",
2147 |        "26986         1.07            1  \n",
2148 |        "26987         0.03            0  \n",
2149 |        "26988         0.13            0  \n",
2150 |        "26989         0.03            0  \n",
2151 |        "26990         0.60            0  \n",
2152 |        "26991         1.07            1  \n",
2153 |        "26992         0.67            0  \n",
2154 |        "26993         0.93            0  \n",
2155 |        "26994         0.90            1  \n",
2156 |        "26995         0.13            0  \n",
2157 |        "\n",
2158 |        "[26996 rows x 27 columns]"
2159 |       ]
2160 |      },
2161 |      "execution_count": 8,
2162 |      "metadata": {},
2163 |      "output_type": "execute_result"
2164 |     }
2165 |    ],
2166 |    "source": [
2167 |     "## Data preparation \n",
2168 |     "user_identifier = dataset['user']\n",
2169 |     "\n",
2170 |     "#Remove the user from the dataset\n",
2171 |     "dataset.drop(columns = ['user'])"
2172 |    ]
2173 |   },
2174 |   {
2175 |    "cell_type": "code",
2176 |    "execution_count": 9,
2177 |    "metadata": {},
2178 |    "outputs": [],
2179 |    "source": [
2180 |     "# One-hot Encoding\n",
2181 |     "dataset = pd.get_dummies(dataset)\n",
2182 |     "\n",
2183 |     "#dataset.housing.value_counts()"
2184 |    ]
2185 |   },
2186 |   {
2187 |    "cell_type": "code",
2188 |    "execution_count": 10,
2189 |    "metadata": {},
2190 |    "outputs": [
2191 |     {
2192 |      "data": {
2193 |       "text/plain": [
2194 |        "Index(['user', 'churn', 'age', 'deposits', 'withdrawal', 'purchases_partners',\n",
2195 |        "       'purchases', 'cc_taken', 'cc_recommended', 'cc_disliked', 'cc_liked',\n",
2196 |        "       'cc_application_begin', 'app_downloaded', 'web_user', 'ios_user',\n",
2197 |        "       'android_user', 'registered_phones', 'waiting_4_loan', 'cancelled_loan',\n",
2198 |        "       'received_loan', 'rejected_loan', 'left_for_two_month_plus',\n",
2199 |        "       'left_for_one_month', 'reward_rate', 'is_referred', 'housing_O',\n",
2200 |        "       'housing_R', 'housing_na', 'payment_type_Bi-Weekly',\n",
2201 |        "       'payment_type_Monthly', 'payment_type_Semi-Monthly',\n",
2202 |        "       'payment_type_Weekly', 'payment_type_na', 'zodiac_sign_Aquarius',\n",
2203 |        "       'zodiac_sign_Aries', 'zodiac_sign_Cancer', 'zodiac_sign_Capricorn',\n",
2204 |        "       'zodiac_sign_Gemini', 'zodiac_sign_Leo', 'zodiac_sign_Libra',\n",
2205 |        "       'zodiac_sign_Pisces', 'zodiac_sign_Sagittarius', 'zodiac_sign_Scorpio',\n",
2206 |        "       'zodiac_sign_Taurus', 'zodiac_sign_Virgo', 'zodiac_sign_na'],\n",
2207 |        "      dtype='object')"
2208 |       ]
2209 |      },
2210 |      "execution_count": 10,
2211 |      "metadata": {},
2212 |      "output_type": "execute_result"
2213 |     }
2214 |    ],
2215 |    "source": [
2216 |     "# shows how many new columns have been created using the get_dummies function\n",
2217 |     "dataset.columns"
2218 |    ]
2219 |   },
2220 |   {
2221 |    "cell_type": "code",
2222 |    "execution_count": 11,
2223 |    "metadata": {},
2224 |    "outputs": [],
2225 |    "source": [
2226 |     "# To avoid correlated variables we drop some columns\n",
2227 |     "dataset = dataset.drop(columns = ['housing_na','zodiac_sign_na','payment_type_na'])"
2228 |    ]
2229 |   },
2230 |   {
2231 |    "cell_type": "code",
2232 |    "execution_count": 12,
2233 |    "metadata": {},
2234 |    "outputs": [],
2235 |    "source": [
2236 |     "# spliting the dataset into Training and Test set\n",
2237 |     "from sklearn.model_selection import train_test_split\n",
2238 |     "\n",
2239 |     "# generate the datasets for training. Test 20%\n",
2240 |     "X_train, X_test, y_train, y_test = train_test_split(dataset.drop(columns = 'churn'),\n",
2241 |     "                                                   dataset['churn'],\n",
2242 |     "                                                   test_size = 0.2,\n",
2243 |     "                                                   random_state = 0)"
2244 |    ]
2245 |   },
2246 |   {
2247 |    "cell_type": "code",
2248 |    "execution_count": 13,
2249 |    "metadata": {},
2250 |    "outputs": [
2251 |     {
2252 |      "data": {
2253 |       "text/plain": [
2254 |        "0    12656\n",
2255 |        "1     8940\n",
2256 |        "Name: churn, dtype: int64"
2257 |       ]
2258 |      },
2259 |      "execution_count": 13,
2260 |      "metadata": {},
2261 |      "output_type": "execute_result"
2262 |     }
2263 |    ],
2264 |    "source": [
2265 |     "# balancing the training Set\n",
2266 |     "\n",
2267 |     "#Counting and watching the Y_train distribution \n",
2268 |     "y_train.value_counts()"
2269 |    ]
2270 |   },
2271 |   {
2272 |    "cell_type": "code",
2273 |    "execution_count": 14,
2274 |    "metadata": {},
2275 |    "outputs": [],
2276 |    "source": [
2277 |     "# The expecting distribution to avoid a Bias is to have a 50/50 (0/1)\n",
2278 |     "#This balancing ensure that the model is accuracy\n",
2279 |     "\n",
2280 |     "#pos and neg index values\n",
2281 |     "pos_index = y_train[y_train.values == 1].index\n",
2282 |     "neg_index = y_train[y_train.values == 0].index\n",
2283 |     "\n",
2284 |     "if len(pos_index) > len(neg_index):\n",
2285 |     "    higher = pos_index\n",
2286 |     "    lower = neg_index\n",
2287 |     "else:\n",
2288 |     "    lower = pos_index\n",
2289 |     "    higher = neg_index\n",
2290 |     "    \n",
2291 |     "#Create random index selection\n",
2292 |     "random.seed(0)\n",
2293 |     "# random select index record up to the same size of lower index\n",
2294 |     "higher = np.random.choice(higher, size = len(lower))\n",
2295 |     "# select the lower index and convert to a numpy array\n",
2296 |     "lower = np.asarray(lower)\n",
2297 |     "# create the new index as a combination \n",
2298 |     "new_indexes = np.concatenate((lower,higher))\n",
2299 |     "\n",
2300 |     "# Reselect the X_train, y_train dataset using the new indexes\n",
2301 |     "X_train = X_train.loc[new_indexes, ]\n",
2302 |     "y_train = y_train[new_indexes]"
2303 |    ]
2304 |   },
2305 |   {
2306 |    "cell_type": "code",
2307 |    "execution_count": 15,
2308 |    "metadata": {},
2309 |    "outputs": [
2310 |     {
2311 |      "name": "stderr",
2312 |      "output_type": "stream",
2313 |      "text": [
2314 |       "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\preprocessing\\data.py:625: DataConversionWarning: Data with input dtype uint8, int64, float64 were all converted to float64 by StandardScaler.\n",
2315 |       "  return self.partial_fit(X, y)\n",
2316 |       "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\base.py:462: DataConversionWarning: Data with input dtype uint8, int64, float64 were all converted to float64 by StandardScaler.\n",
2317 |       "  return self.fit(X, **fit_params).transform(X)\n",
2318 |       "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\preprocessing\\data.py:625: DataConversionWarning: Data with input dtype uint8, int64, float64 were all converted to float64 by StandardScaler.\n",
2319 |       "  return self.partial_fit(X, y)\n",
2320 |       "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\base.py:462: DataConversionWarning: Data with input dtype uint8, int64, float64 were all converted to float64 by StandardScaler.\n",
2321 |       "  return self.fit(X, **fit_params).transform(X)\n"
2322 |      ]
2323 |     }
2324 |    ],
2325 |    "source": [
2326 |     "# Feature scaling\n",
2327 |     "from sklearn.preprocessing import StandardScaler\n",
2328 |     "# generate an standarScalar\n",
2329 |     "sc_X = StandardScaler()\n",
2330 |     "\n",
2331 |     "#StandardScaler return a Numpy Array so we need to convert to a Dataframe\n",
2332 |     "X_train2= pd.DataFrame(sc_X.fit_transform(X_train))\n",
2333 |     "X_test2 = pd.DataFrame(sc_X.fit_transform(X_test))\n",
2334 |     "\n",
2335 |     "#copy columns name to the new traning and testing dataset\n",
2336 |     "X_train2.columns = X_train.columns.values\n",
2337 |     "X_test2.columns = X_test.columns.values\n",
2338 |     "\n",
2339 |     "#copy index to the new traning and testing dataset\n",
2340 |     "X_train2.index = X_train.index.values\n",
2341 |     "X_test2.index = X_test.index.values\n",
2342 |     "\n",
2343 |     "# reasigned copy dataset to original\n",
2344 |     "X_train = X_train2\n",
2345 |     "X_test = X_test2"
2346 |    ]
2347 |   },
2348 |   {
2349 |    "cell_type": "code",
2350 |    "execution_count": 16,
2351 |    "metadata": {},
2352 |    "outputs": [
2353 |     {
2354 |      "data": {
2355 |       "text/plain": [
2356 |        "LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,\n",
2357 |        "          intercept_scaling=1, max_iter=100, multi_class='warn',\n",
2358 |        "          n_jobs=None, penalty='l2', random_state=0, solver='lbfgs',\n",
2359 |        "          tol=0.0001, verbose=0, warm_start=False)"
2360 |       ]
2361 |      },
2362 |      "execution_count": 16,
2363 |      "metadata": {},
2364 |      "output_type": "execute_result"
2365 |     }
2366 |    ],
2367 |    "source": [
2368 |     "### Model building ###\n",
2369 |     "\n",
2370 |     "# Fitting Model to the Traninig Set\n",
2371 |     "from sklearn.linear_model import LogisticRegression\n",
2372 |     "classifier = LogisticRegression(random_state=0, solver='lbfgs')\n",
2373 |     "classifier.fit(X_train, y_train)"
2374 |    ]
2375 |   },
2376 |   {
2377 |    "cell_type": "code",
2378 |    "execution_count": 17,
2379 |    "metadata": {},
2380 |    "outputs": [],
2381 |    "source": [
2382 |     "# Evaluating Test set\n",
2383 |     "y_pred = classifier.predict(X_test)"
2384 |    ]
2385 |   },
2386 |   {
2387 |    "cell_type": "code",
2388 |    "execution_count": 18,
2389 |    "metadata": {},
2390 |    "outputs": [],
2391 |    "source": [
2392 |     "# Evaluating Result\n",
2393 |     "from sklearn.metrics import confusion_matrix, accuracy_score, f1_score, precision_score, recall_score\n",
2394 |     "cnf_matrix = confusion_matrix(y_test, y_pred)"
2395 |    ]
2396 |   },
2397 |   {
2398 |    "cell_type": "code",
2399 |    "execution_count": 19,
2400 |    "metadata": {},
2401 |    "outputs": [
2402 |     {
2403 |      "data": {
2404 |       "text/plain": [
2405 |        "0.612037037037037"
2406 |       ]
2407 |      },
2408 |      "execution_count": 19,
2409 |      "metadata": {},
2410 |      "output_type": "execute_result"
2411 |     }
2412 |    ],
2413 |    "source": [
2414 |     "# Accuracy score\n",
2415 |     "accuracy_score(y_test, y_pred)"
2416 |    ]
2417 |   },
2418 |   {
2419 |    "cell_type": "code",
2420 |    "execution_count": 20,
2421 |    "metadata": {},
2422 |    "outputs": [
2423 |     {
2424 |      "data": {
2425 |       "text/plain": [
2426 |        "0.5213911972914743"
2427 |       ]
2428 |      },
2429 |      "execution_count": 20,
2430 |      "metadata": {},
2431 |      "output_type": "execute_result"
2432 |     }
2433 |    ],
2434 |    "source": [
2435 |     "# precision score (When is 0 and should be 1 and the other way round)\n",
2436 |     "precision_score(y_test, y_pred)"
2437 |    ]
2438 |   },
2439 |   {
2440 |    "cell_type": "code",
2441 |    "execution_count": 21,
2442 |    "metadata": {},
2443 |    "outputs": [
2444 |     {
2445 |      "data": {
2446 |       "text/plain": [
2447 |        "0.7582811101163832"
2448 |       ]
2449 |      },
2450 |      "execution_count": 21,
2451 |      "metadata": {},
2452 |      "output_type": "execute_result"
2453 |     }
2454 |    ],
2455 |    "source": [
2456 |     "# recall score\n",
2457 |     "recall_score(y_test, y_pred)"
2458 |    ]
2459 |   },
2460 |   {
2461 |    "cell_type": "code",
2462 |    "execution_count": 22,
2463 |    "metadata": {},
2464 |    "outputs": [
2465 |     {
2466 |      "data": {
2467 |       "text/plain": [
2468 |        "0.617909903337589"
2469 |       ]
2470 |      },
2471 |      "execution_count": 22,
2472 |      "metadata": {},
2473 |      "output_type": "execute_result"
2474 |     }
2475 |    ],
2476 |    "source": [
2477 |     "f1_score(y_test, y_pred)"
2478 |    ]
2479 |   },
2480 |   {
2481 |    "cell_type": "code",
2482 |    "execution_count": 23,
2483 |    "metadata": {},
2484 |    "outputs": [
2485 |     {
2486 |      "name": "stdout",
2487 |      "output_type": "stream",
2488 |      "text": [
2489 |       "Accuracy 0.6120\n"
2490 |      ]
2491 |     },
2492 |     {
2493 |      "data": {
2494 |       "image/png": "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\n",
2495 |       "text/plain": [
2496 |        "<Figure size 432x288 with 2 Axes>"
2497 |       ]
2498 |      },
2499 |      "metadata": {
2500 |       "needs_background": "light"
2501 |      },
2502 |      "output_type": "display_data"
2503 |     }
2504 |    ],
2505 |    "source": [
2506 |     "class_names=[0,1] # name  of classes\n",
2507 |     "fig, ax = plt.subplots()\n",
2508 |     "tick_marks = np.arange(len(class_names))\n",
2509 |     "plt.xticks(tick_marks, class_names)\n",
2510 |     "plt.yticks(tick_marks, class_names)\n",
2511 |     "# create heatmap\n",
2512 |     "sns.heatmap(pd.DataFrame(cnf_matrix), annot=True, cmap=\"YlGnBu\" ,fmt='g')\n",
2513 |     "ax.xaxis.set_label_position(\"top\")\n",
2514 |     "plt.tight_layout()\n",
2515 |     "plt.title('Confusion matrix', y=1.1)\n",
2516 |     "plt.ylabel('Actual label')\n",
2517 |     "plt.xlabel('Predicted label')\n",
2518 |     "print(\"Accuracy %0.4f\" % accuracy_score(y_test, y_pred))"
2519 |    ]
2520 |   },
2521 |   {
2522 |    "cell_type": "code",
2523 |    "execution_count": 24,
2524 |    "metadata": {},
2525 |    "outputs": [
2526 |     {
2527 |      "data": {
2528 |       "text/plain": [
2529 |        "array([0.65995526, 0.66778523, 0.65380313, 0.63199105, 0.6442953 ,\n",
2530 |        "       0.66331096, 0.6582774 , 0.65659955, 0.64597315, 0.64261745])"
2531 |       ]
2532 |      },
2533 |      "execution_count": 24,
2534 |      "metadata": {},
2535 |      "output_type": "execute_result"
2536 |     }
2537 |    ],
2538 |    "source": [
2539 |     "#Appliyng K-fold Cross Validation\n",
2540 |     "from sklearn.model_selection import cross_val_score\n",
2541 |     "accuracies = cross_val_score(estimator = classifier,\n",
2542 |     "                             X = X_train,\n",
2543 |     "                             y = y_train,\n",
2544 |     "                             cv = 10)\n",
2545 |     "\n",
2546 |     "# Showing Accuracies to validate the model estimation\n",
2547 |     "accuracies"
2548 |    ]
2549 |   },
2550 |   {
2551 |    "cell_type": "code",
2552 |    "execution_count": 25,
2553 |    "metadata": {},
2554 |    "outputs": [
2555 |     {
2556 |      "data": {
2557 |       "text/plain": [
2558 |        "0.6524608501118567"
2559 |       ]
2560 |      },
2561 |      "execution_count": 25,
2562 |      "metadata": {},
2563 |      "output_type": "execute_result"
2564 |     }
2565 |    ],
2566 |    "source": [
2567 |     "accuracies.mean()"
2568 |    ]
2569 |   },
2570 |   {
2571 |    "cell_type": "code",
2572 |    "execution_count": 26,
2573 |    "metadata": {},
2574 |    "outputs": [
2575 |     {
2576 |      "data": {
2577 |       "text/html": [
2578 |        "<div>\n",
2579 |        "<style scoped>\n",
2580 |        "    .dataframe tbody tr th:only-of-type {\n",
2581 |        "        vertical-align: middle;\n",
2582 |        "    }\n",
2583 |        "\n",
2584 |        "    .dataframe tbody tr th {\n",
2585 |        "        vertical-align: top;\n",
2586 |        "    }\n",
2587 |        "\n",
2588 |        "    .dataframe thead th {\n",
2589 |        "        text-align: right;\n",
2590 |        "    }\n",
2591 |        "</style>\n",
2592 |        "<table border=\"1\" class=\"dataframe\">\n",
2593 |        "  <thead>\n",
2594 |        "    <tr style=\"text-align: right;\">\n",
2595 |        "      <th></th>\n",
2596 |        "      <th>features</th>\n",
2597 |        "      <th>coef</th>\n",
2598 |        "    </tr>\n",
2599 |        "  </thead>\n",
2600 |        "  <tbody>\n",
2601 |        "    <tr>\n",
2602 |        "      <th>0</th>\n",
2603 |        "      <td>user</td>\n",
2604 |        "      <td>-0.117347</td>\n",
2605 |        "    </tr>\n",
2606 |        "    <tr>\n",
2607 |        "      <th>1</th>\n",
2608 |        "      <td>age</td>\n",
2609 |        "      <td>-0.168296</td>\n",
2610 |        "    </tr>\n",
2611 |        "    <tr>\n",
2612 |        "      <th>2</th>\n",
2613 |        "      <td>deposits</td>\n",
2614 |        "      <td>0.448547</td>\n",
2615 |        "    </tr>\n",
2616 |        "    <tr>\n",
2617 |        "      <th>3</th>\n",
2618 |        "      <td>withdrawal</td>\n",
2619 |        "      <td>0.077879</td>\n",
2620 |        "    </tr>\n",
2621 |        "    <tr>\n",
2622 |        "      <th>4</th>\n",
2623 |        "      <td>purchases_partners</td>\n",
2624 |        "      <td>-0.724259</td>\n",
2625 |        "    </tr>\n",
2626 |        "    <tr>\n",
2627 |        "      <th>5</th>\n",
2628 |        "      <td>purchases</td>\n",
2629 |        "      <td>-0.603786</td>\n",
2630 |        "    </tr>\n",
2631 |        "    <tr>\n",
2632 |        "      <th>6</th>\n",
2633 |        "      <td>cc_taken</td>\n",
2634 |        "      <td>0.074629</td>\n",
2635 |        "    </tr>\n",
2636 |        "    <tr>\n",
2637 |        "      <th>7</th>\n",
2638 |        "      <td>cc_recommended</td>\n",
2639 |        "      <td>-0.003146</td>\n",
2640 |        "    </tr>\n",
2641 |        "    <tr>\n",
2642 |        "      <th>8</th>\n",
2643 |        "      <td>cc_disliked</td>\n",
2644 |        "      <td>0.003458</td>\n",
2645 |        "    </tr>\n",
2646 |        "    <tr>\n",
2647 |        "      <th>9</th>\n",
2648 |        "      <td>cc_liked</td>\n",
2649 |        "      <td>0.009891</td>\n",
2650 |        "    </tr>\n",
2651 |        "    <tr>\n",
2652 |        "      <th>10</th>\n",
2653 |        "      <td>cc_application_begin</td>\n",
2654 |        "      <td>0.027898</td>\n",
2655 |        "    </tr>\n",
2656 |        "    <tr>\n",
2657 |        "      <th>11</th>\n",
2658 |        "      <td>app_downloaded</td>\n",
2659 |        "      <td>-0.017686</td>\n",
2660 |        "    </tr>\n",
2661 |        "    <tr>\n",
2662 |        "      <th>12</th>\n",
2663 |        "      <td>web_user</td>\n",
2664 |        "      <td>0.143757</td>\n",
2665 |        "    </tr>\n",
2666 |        "    <tr>\n",
2667 |        "      <th>13</th>\n",
2668 |        "      <td>ios_user</td>\n",
2669 |        "      <td>0.081419</td>\n",
2670 |        "    </tr>\n",
2671 |        "    <tr>\n",
2672 |        "      <th>14</th>\n",
2673 |        "      <td>android_user</td>\n",
2674 |        "      <td>-0.019784</td>\n",
2675 |        "    </tr>\n",
2676 |        "    <tr>\n",
2677 |        "      <th>15</th>\n",
2678 |        "      <td>registered_phones</td>\n",
2679 |        "      <td>0.102284</td>\n",
2680 |        "    </tr>\n",
2681 |        "    <tr>\n",
2682 |        "      <th>16</th>\n",
2683 |        "      <td>waiting_4_loan</td>\n",
2684 |        "      <td>-0.028444</td>\n",
2685 |        "    </tr>\n",
2686 |        "    <tr>\n",
2687 |        "      <th>17</th>\n",
2688 |        "      <td>cancelled_loan</td>\n",
2689 |        "      <td>0.078268</td>\n",
2690 |        "    </tr>\n",
2691 |        "    <tr>\n",
2692 |        "      <th>18</th>\n",
2693 |        "      <td>received_loan</td>\n",
2694 |        "      <td>0.103427</td>\n",
2695 |        "    </tr>\n",
2696 |        "    <tr>\n",
2697 |        "      <th>19</th>\n",
2698 |        "      <td>rejected_loan</td>\n",
2699 |        "      <td>0.103366</td>\n",
2700 |        "    </tr>\n",
2701 |        "    <tr>\n",
2702 |        "      <th>20</th>\n",
2703 |        "      <td>left_for_two_month_plus</td>\n",
2704 |        "      <td>0.063179</td>\n",
2705 |        "    </tr>\n",
2706 |        "    <tr>\n",
2707 |        "      <th>21</th>\n",
2708 |        "      <td>left_for_one_month</td>\n",
2709 |        "      <td>0.046261</td>\n",
2710 |        "    </tr>\n",
2711 |        "    <tr>\n",
2712 |        "      <th>22</th>\n",
2713 |        "      <td>reward_rate</td>\n",
2714 |        "      <td>-0.223845</td>\n",
2715 |        "    </tr>\n",
2716 |        "    <tr>\n",
2717 |        "      <th>23</th>\n",
2718 |        "      <td>is_referred</td>\n",
2719 |        "      <td>0.013839</td>\n",
2720 |        "    </tr>\n",
2721 |        "    <tr>\n",
2722 |        "      <th>24</th>\n",
2723 |        "      <td>housing_O</td>\n",
2724 |        "      <td>-0.034252</td>\n",
2725 |        "    </tr>\n",
2726 |        "    <tr>\n",
2727 |        "      <th>25</th>\n",
2728 |        "      <td>housing_R</td>\n",
2729 |        "      <td>0.036926</td>\n",
2730 |        "    </tr>\n",
2731 |        "    <tr>\n",
2732 |        "      <th>26</th>\n",
2733 |        "      <td>payment_type_Bi-Weekly</td>\n",
2734 |        "      <td>-0.048699</td>\n",
2735 |        "    </tr>\n",
2736 |        "    <tr>\n",
2737 |        "      <th>27</th>\n",
2738 |        "      <td>payment_type_Monthly</td>\n",
2739 |        "      <td>-0.002895</td>\n",
2740 |        "    </tr>\n",
2741 |        "    <tr>\n",
2742 |        "      <th>28</th>\n",
2743 |        "      <td>payment_type_Semi-Monthly</td>\n",
2744 |        "      <td>-0.036323</td>\n",
2745 |        "    </tr>\n",
2746 |        "    <tr>\n",
2747 |        "      <th>29</th>\n",
2748 |        "      <td>payment_type_Weekly</td>\n",
2749 |        "      <td>0.039683</td>\n",
2750 |        "    </tr>\n",
2751 |        "    <tr>\n",
2752 |        "      <th>30</th>\n",
2753 |        "      <td>zodiac_sign_Aquarius</td>\n",
2754 |        "      <td>-0.016194</td>\n",
2755 |        "    </tr>\n",
2756 |        "    <tr>\n",
2757 |        "      <th>31</th>\n",
2758 |        "      <td>zodiac_sign_Aries</td>\n",
2759 |        "      <td>0.004264</td>\n",
2760 |        "    </tr>\n",
2761 |        "    <tr>\n",
2762 |        "      <th>32</th>\n",
2763 |        "      <td>zodiac_sign_Cancer</td>\n",
2764 |        "      <td>0.026928</td>\n",
2765 |        "    </tr>\n",
2766 |        "    <tr>\n",
2767 |        "      <th>33</th>\n",
2768 |        "      <td>zodiac_sign_Capricorn</td>\n",
2769 |        "      <td>0.023683</td>\n",
2770 |        "    </tr>\n",
2771 |        "    <tr>\n",
2772 |        "      <th>34</th>\n",
2773 |        "      <td>zodiac_sign_Gemini</td>\n",
2774 |        "      <td>-0.011197</td>\n",
2775 |        "    </tr>\n",
2776 |        "    <tr>\n",
2777 |        "      <th>35</th>\n",
2778 |        "      <td>zodiac_sign_Leo</td>\n",
2779 |        "      <td>0.003228</td>\n",
2780 |        "    </tr>\n",
2781 |        "    <tr>\n",
2782 |        "      <th>36</th>\n",
2783 |        "      <td>zodiac_sign_Libra</td>\n",
2784 |        "      <td>-0.014704</td>\n",
2785 |        "    </tr>\n",
2786 |        "    <tr>\n",
2787 |        "      <th>37</th>\n",
2788 |        "      <td>zodiac_sign_Pisces</td>\n",
2789 |        "      <td>0.024610</td>\n",
2790 |        "    </tr>\n",
2791 |        "    <tr>\n",
2792 |        "      <th>38</th>\n",
2793 |        "      <td>zodiac_sign_Sagittarius</td>\n",
2794 |        "      <td>0.021215</td>\n",
2795 |        "    </tr>\n",
2796 |        "    <tr>\n",
2797 |        "      <th>39</th>\n",
2798 |        "      <td>zodiac_sign_Scorpio</td>\n",
2799 |        "      <td>-0.023309</td>\n",
2800 |        "    </tr>\n",
2801 |        "    <tr>\n",
2802 |        "      <th>40</th>\n",
2803 |        "      <td>zodiac_sign_Taurus</td>\n",
2804 |        "      <td>0.011366</td>\n",
2805 |        "    </tr>\n",
2806 |        "    <tr>\n",
2807 |        "      <th>41</th>\n",
2808 |        "      <td>zodiac_sign_Virgo</td>\n",
2809 |        "      <td>0.015451</td>\n",
2810 |        "    </tr>\n",
2811 |        "  </tbody>\n",
2812 |        "</table>\n",
2813 |        "</div>"
2814 |       ],
2815 |       "text/plain": [
2816 |        "                     features      coef\n",
2817 |        "0                        user -0.117347\n",
2818 |        "1                         age -0.168296\n",
2819 |        "2                    deposits  0.448547\n",
2820 |        "3                  withdrawal  0.077879\n",
2821 |        "4          purchases_partners -0.724259\n",
2822 |        "5                   purchases -0.603786\n",
2823 |        "6                    cc_taken  0.074629\n",
2824 |        "7              cc_recommended -0.003146\n",
2825 |        "8                 cc_disliked  0.003458\n",
2826 |        "9                    cc_liked  0.009891\n",
2827 |        "10       cc_application_begin  0.027898\n",
2828 |        "11             app_downloaded -0.017686\n",
2829 |        "12                   web_user  0.143757\n",
2830 |        "13                   ios_user  0.081419\n",
2831 |        "14               android_user -0.019784\n",
2832 |        "15          registered_phones  0.102284\n",
2833 |        "16             waiting_4_loan -0.028444\n",
2834 |        "17             cancelled_loan  0.078268\n",
2835 |        "18              received_loan  0.103427\n",
2836 |        "19              rejected_loan  0.103366\n",
2837 |        "20    left_for_two_month_plus  0.063179\n",
2838 |        "21         left_for_one_month  0.046261\n",
2839 |        "22                reward_rate -0.223845\n",
2840 |        "23                is_referred  0.013839\n",
2841 |        "24                  housing_O -0.034252\n",
2842 |        "25                  housing_R  0.036926\n",
2843 |        "26     payment_type_Bi-Weekly -0.048699\n",
2844 |        "27       payment_type_Monthly -0.002895\n",
2845 |        "28  payment_type_Semi-Monthly -0.036323\n",
2846 |        "29        payment_type_Weekly  0.039683\n",
2847 |        "30       zodiac_sign_Aquarius -0.016194\n",
2848 |        "31          zodiac_sign_Aries  0.004264\n",
2849 |        "32         zodiac_sign_Cancer  0.026928\n",
2850 |        "33      zodiac_sign_Capricorn  0.023683\n",
2851 |        "34         zodiac_sign_Gemini -0.011197\n",
2852 |        "35            zodiac_sign_Leo  0.003228\n",
2853 |        "36          zodiac_sign_Libra -0.014704\n",
2854 |        "37         zodiac_sign_Pisces  0.024610\n",
2855 |        "38    zodiac_sign_Sagittarius  0.021215\n",
2856 |        "39        zodiac_sign_Scorpio -0.023309\n",
2857 |        "40         zodiac_sign_Taurus  0.011366\n",
2858 |        "41          zodiac_sign_Virgo  0.015451"
2859 |       ]
2860 |      },
2861 |      "execution_count": 26,
2862 |      "metadata": {},
2863 |      "output_type": "execute_result"
2864 |     }
2865 |    ],
2866 |    "source": [
2867 |     "# Analyzing coefficients\n",
2868 |     "pd.concat([pd.DataFrame(X_train.columns, columns = [\"features\"]),\n",
2869 |     "          pd.DataFrame(np.transpose(classifier.coef_), columns = [\"coef\"])],\n",
2870 |     "axis = 1)"
2871 |    ]
2872 |   },
2873 |   {
2874 |    "cell_type": "code",
2875 |    "execution_count": 27,
2876 |    "metadata": {},
2877 |    "outputs": [
2878 |     {
2879 |      "data": {
2880 |       "text/plain": [
2881 |        "(17880, 42)"
2882 |       ]
2883 |      },
2884 |      "execution_count": 27,
2885 |      "metadata": {},
2886 |      "output_type": "execute_result"
2887 |     }
2888 |    ],
2889 |    "source": [
2890 |     "### Feature selection ###\n",
2891 |     "\n",
2892 |     "# how many columns we have on the X_train dataset?\n",
2893 |     "\n",
2894 |     "X_train.shape\n"
2895 |    ]
2896 |   },
2897 |   {
2898 |    "cell_type": "code",
2899 |    "execution_count": 28,
2900 |    "metadata": {},
2901 |    "outputs": [],
2902 |    "source": [
2903 |     "## Feature selection\n",
2904 |     "\n",
2905 |     "from sklearn.feature_selection import RFE\n",
2906 |     "from sklearn.linear_model import LogisticRegression"
2907 |    ]
2908 |   },
2909 |   {
2910 |    "cell_type": "code",
2911 |    "execution_count": 29,
2912 |    "metadata": {},
2913 |    "outputs": [],
2914 |    "source": [
2915 |     "# Model to test\n",
2916 |     "classifier = LogisticRegression(solver = 'lbfgs')\n",
2917 |     "# RFE(, N) the N is the Total Feature that we want to use for the clasification\n",
2918 |     "rfe = RFE(classifier, 20)\n",
2919 |     "rfe = rfe.fit(X_train, y_train)\n"
2920 |    ]
2921 |   },
2922 |   {
2923 |    "cell_type": "code",
2924 |    "execution_count": 30,
2925 |    "metadata": {},
2926 |    "outputs": [
2927 |     {
2928 |      "name": "stdout",
2929 |      "output_type": "stream",
2930 |      "text": [
2931 |       "[ True  True  True  True  True  True  True False False False False False\n",
2932 |       "  True  True  True  True False  True  True  True  True  True  True False\n",
2933 |       " False  True  True False False  True False False False False False False\n",
2934 |       " False False False False False False]\n"
2935 |      ]
2936 |     }
2937 |    ],
2938 |    "source": [
2939 |     "# sumarize the selection of the atributes\n",
2940 |     "print(rfe.support_)"
2941 |    ]
2942 |   },
2943 |   {
2944 |    "cell_type": "code",
2945 |    "execution_count": 33,
2946 |    "metadata": {},
2947 |    "outputs": [
2948 |     {
2949 |      "data": {
2950 |       "text/plain": [
2951 |        "Index(['user', 'age', 'deposits', 'withdrawal', 'purchases_partners',\n",
2952 |        "       'purchases', 'cc_taken', 'web_user', 'ios_user', 'android_user',\n",
2953 |        "       'registered_phones', 'cancelled_loan', 'received_loan', 'rejected_loan',\n",
2954 |        "       'left_for_two_month_plus', 'left_for_one_month', 'reward_rate',\n",
2955 |        "       'housing_R', 'payment_type_Bi-Weekly', 'payment_type_Weekly'],\n",
2956 |        "      dtype='object')"
2957 |       ]
2958 |      },
2959 |      "execution_count": 33,
2960 |      "metadata": {},
2961 |      "output_type": "execute_result"
2962 |     }
2963 |    ],
2964 |    "source": [
2965 |     "# show rfe columns names \n",
2966 |     "X_train.columns[rfe.support_]"
2967 |    ]
2968 |   },
2969 |   {
2970 |    "cell_type": "code",
2971 |    "execution_count": 35,
2972 |    "metadata": {},
2973 |    "outputs": [
2974 |     {
2975 |      "data": {
2976 |       "text/plain": [
2977 |        "LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,\n",
2978 |        "          intercept_scaling=1, max_iter=100, multi_class='warn',\n",
2979 |        "          n_jobs=None, penalty='l2', random_state=0, solver='lbfgs',\n",
2980 |        "          tol=0.0001, verbose=0, warm_start=False)"
2981 |       ]
2982 |      },
2983 |      "execution_count": 35,
2984 |      "metadata": {},
2985 |      "output_type": "execute_result"
2986 |     }
2987 |    ],
2988 |    "source": [
2989 |     "# Model building with Feature Selection \n",
2990 |     "# Fitting Moel to the Traninig Set\n",
2991 |     "from sklearn.linear_model import LogisticRegression\n",
2992 |     "classifier = LogisticRegression(random_state=0, solver='lbfgs')\n",
2993 |     "classifier.fit(X_train[X_train.columns[rfe.support_]], y_train)"
2994 |    ]
2995 |   },
2996 |   {
2997 |    "cell_type": "code",
2998 |    "execution_count": 37,
2999 |    "metadata": {},
3000 |    "outputs": [],
3001 |    "source": [
3002 |     "# Evaluating Test set with feature selection\n",
3003 |     "y_pred = classifier.predict(X_test[X_test.columns[rfe.support_]])"
3004 |    ]
3005 |   },
3006 |   {
3007 |    "cell_type": "code",
3008 |    "execution_count": 38,
3009 |    "metadata": {},
3010 |    "outputs": [],
3011 |    "source": [
3012 |     "# Evaluating Result with feature selection\n",
3013 |     "from sklearn.metrics import confusion_matrix, accuracy_score, f1_score, precision_score, recall_score\n",
3014 |     "cnf_matrix = confusion_matrix(y_test, y_pred)"
3015 |    ]
3016 |   },
3017 |   {
3018 |    "cell_type": "code",
3019 |    "execution_count": 39,
3020 |    "metadata": {},
3021 |    "outputs": [
3022 |     {
3023 |      "name": "stdout",
3024 |      "output_type": "stream",
3025 |      "text": [
3026 |       "Accuracy 0.6085\n"
3027 |      ]
3028 |     },
3029 |     {
3030 |      "data": {
3031 |       "image/png": "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\n",
3032 |       "text/plain": [
3033 |        "<Figure size 432x288 with 2 Axes>"
3034 |       ]
3035 |      },
3036 |      "metadata": {
3037 |       "needs_background": "light"
3038 |      },
3039 |      "output_type": "display_data"
3040 |     }
3041 |    ],
3042 |    "source": [
3043 |     "# cnf matrix drawing\n",
3044 |     "class_names=[0,1] # name  of classes\n",
3045 |     "fig, ax = plt.subplots()\n",
3046 |     "tick_marks = np.arange(len(class_names))\n",
3047 |     "plt.xticks(tick_marks, class_names)\n",
3048 |     "plt.yticks(tick_marks, class_names)\n",
3049 |     "# create heatmap\n",
3050 |     "sns.heatmap(pd.DataFrame(cnf_matrix), annot=True, cmap=\"YlGnBu\" ,fmt='g')\n",
3051 |     "ax.xaxis.set_label_position(\"top\")\n",
3052 |     "plt.tight_layout()\n",
3053 |     "plt.title('Confusion matrix', y=1.1)\n",
3054 |     "plt.ylabel('Actual label')\n",
3055 |     "plt.xlabel('Predicted label')\n",
3056 |     "print(\"Accuracy %0.4f\" % accuracy_score(y_test, y_pred))"
3057 |    ]
3058 |   }
3059 |  ],
3060 |  "metadata": {
3061 |   "kernelspec": {
3062 |    "display_name": "Python 3",
3063 |    "language": "python",
3064 |    "name": "python3"
3065 |   },
3066 |   "language_info": {
3067 |    "codemirror_mode": {
3068 |     "name": "ipython",
3069 |     "version": 3
3070 |    },
3071 |    "file_extension": ".py",
3072 |    "mimetype": "text/x-python",
3073 |    "name": "python",
3074 |    "nbconvert_exporter": "python",
3075 |    "pygments_lexer": "ipython3",
3076 |    "version": "3.7.3"
3077 |   }
3078 |  },
3079 |  "nbformat": 4,
3080 |  "nbformat_minor": 2
3081 | }
3082 | 


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