├── README.md ├── LICENSE └── ML_Project_Coursera.ipynb /README.md: -------------------------------------------------------------------------------- 1 | # loan-repayment-prediction 2 | A Machine Learning Project to Predict the Loan Repayment Status of the Loan Holder on the basic of previous data analysis. 3 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /ML_Project_Coursera.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "metadata": { 6 | "button": false, 7 | "new_sheet": false, 8 | "run_control": { 9 | "read_only": false 10 | } 11 | }, 12 | "source": "\n\n

Loan Repayment Prediction

\n

A Machine Learning Project (Using classification in Python)

" 13 | }, 14 | { 15 | "cell_type": "markdown", 16 | "metadata": { 17 | "button": false, 18 | "new_sheet": false, 19 | "run_control": { 20 | "read_only": false 21 | } 22 | }, 23 | "source": "In this notebook we try to predict the Loan_Status of the customer whether he/she will be able to return the loan amount at the time or not by using all the classification algorithms and analysing the predictions.\n\nWe load a dataset using Pandas library, and apply the following algorithms, and find the best one for this specific dataset by accuracy evaluation methods.\n\nLets first load required libraries:" 24 | }, 25 | { 26 | "cell_type": "code", 27 | "execution_count": 1, 28 | "metadata": { 29 | "button": false, 30 | "new_sheet": false, 31 | "run_control": { 32 | "read_only": false 33 | } 34 | }, 35 | "outputs": [], 36 | "source": "import itertools\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom matplotlib.ticker import NullFormatter\nimport pandas as pd\nimport numpy as np\nimport matplotlib.ticker as ticker\nfrom sklearn import preprocessing\n%matplotlib inline" 37 | }, 38 | { 39 | "cell_type": "markdown", 40 | "metadata": { 41 | "button": false, 42 | "new_sheet": false, 43 | "run_control": { 44 | "read_only": false 45 | } 46 | }, 47 | "source": "### About dataset" 48 | }, 49 | { 50 | "cell_type": "markdown", 51 | "metadata": { 52 | "button": false, 53 | "new_sheet": false, 54 | "run_control": { 55 | "read_only": false 56 | } 57 | }, 58 | "source": "This dataset is about past loans. The __Loan_train.csv__ data set includes details of 346 customers whose loan are already paid off or defaulted. It includes following fields:\n\n| Field | Description |\n|----------------|---------------------------------------------------------------------------------------|\n| Loan_status | Whether a loan is paid off on in collection |\n| Principal | Basic principal loan amount at the |\n| Terms | Origination terms which can be weekly (7 days), biweekly, and monthly payoff schedule |\n| Effective_date | When the loan got originated and took effects |\n| Due_date | Since it\u2019s one-time payoff schedule, each loan has one single due date |\n| Age | Age of applicant |\n| Education | Education of applicant |\n| Gender | The gender of applicant |" 59 | }, 60 | { 61 | "cell_type": "markdown", 62 | "metadata": { 63 | "button": false, 64 | "new_sheet": false, 65 | "run_control": { 66 | "read_only": false 67 | } 68 | }, 69 | "source": "Lets download the dataset" 70 | }, 71 | { 72 | "cell_type": "code", 73 | "execution_count": 2, 74 | "metadata": { 75 | "button": false, 76 | "new_sheet": false, 77 | "run_control": { 78 | "read_only": false 79 | } 80 | }, 81 | "outputs": [ 82 | { 83 | "name": "stdout", 84 | "output_type": "stream", 85 | "text": "--2020-01-06 09:08:28-- https://s3-api.us-geo.objectstorage.softlayer.net/cf-courses-data/CognitiveClass/ML0101ENv3/labs/loan_train.csv\nResolving s3-api.us-geo.objectstorage.softlayer.net (s3-api.us-geo.objectstorage.softlayer.net)... 67.228.254.196\nConnecting to s3-api.us-geo.objectstorage.softlayer.net (s3-api.us-geo.objectstorage.softlayer.net)|67.228.254.196|:443... connected.\nHTTP request sent, awaiting response... 200 OK\nLength: 23101 (23K) [text/csv]\nSaving to: \u2018loan_train.csv\u2019\n\n100%[======================================>] 23,101 --.-K/s in 0.07s \n\n2020-01-06 09:08:29 (304 KB/s) - \u2018loan_train.csv\u2019 saved [23101/23101]\n\n" 86 | } 87 | ], 88 | "source": "!wget -O loan_train.csv https://s3-api.us-geo.objectstorage.softlayer.net/cf-courses-data/CognitiveClass/ML0101ENv3/labs/loan_train.csv" 89 | }, 90 | { 91 | "cell_type": "markdown", 92 | "metadata": { 93 | "button": false, 94 | "new_sheet": false, 95 | "run_control": { 96 | "read_only": false 97 | } 98 | }, 99 | "source": "### Load Data From CSV File " 100 | }, 101 | { 102 | "cell_type": "code", 103 | "execution_count": 3, 104 | "metadata": { 105 | "button": false, 106 | "new_sheet": false, 107 | "run_control": { 108 | "read_only": false 109 | } 110 | }, 111 | "outputs": [ 112 | { 113 | "data": { 114 | "text/html": "
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Unnamed: 0Unnamed: 0.1loan_statusPrincipaltermseffective_datedue_dateageeducationGender
000PAIDOFF1000309/8/201610/7/201645High School or Belowmale
122PAIDOFF1000309/8/201610/7/201633Bechalorfemale
233PAIDOFF1000159/8/20169/22/201627collegemale
344PAIDOFF1000309/9/201610/8/201628collegefemale
466PAIDOFF1000309/9/201610/8/201629collegemale
\n
", 115 | "text/plain": " Unnamed: 0 Unnamed: 0.1 loan_status Principal terms effective_date \\\n0 0 0 PAIDOFF 1000 30 9/8/2016 \n1 2 2 PAIDOFF 1000 30 9/8/2016 \n2 3 3 PAIDOFF 1000 15 9/8/2016 \n3 4 4 PAIDOFF 1000 30 9/9/2016 \n4 6 6 PAIDOFF 1000 30 9/9/2016 \n\n due_date age education Gender \n0 10/7/2016 45 High School or Below male \n1 10/7/2016 33 Bechalor female \n2 9/22/2016 27 college male \n3 10/8/2016 28 college female \n4 10/8/2016 29 college male " 116 | }, 117 | "execution_count": 3, 118 | "metadata": {}, 119 | "output_type": "execute_result" 120 | } 121 | ], 122 | "source": "df = pd.read_csv('loan_train.csv')\ndf.head()" 123 | }, 124 | { 125 | "cell_type": "code", 126 | "execution_count": 4, 127 | "metadata": {}, 128 | "outputs": [ 129 | { 130 | "data": { 131 | "text/plain": "(346, 10)" 132 | }, 133 | "execution_count": 4, 134 | "metadata": {}, 135 | "output_type": "execute_result" 136 | } 137 | ], 138 | "source": "df.shape" 139 | }, 140 | { 141 | "cell_type": "markdown", 142 | "metadata": { 143 | "button": false, 144 | "new_sheet": false, 145 | "run_control": { 146 | "read_only": false 147 | } 148 | }, 149 | "source": "### Convert to date time object " 150 | }, 151 | { 152 | "cell_type": "code", 153 | "execution_count": 5, 154 | "metadata": { 155 | "button": false, 156 | "new_sheet": false, 157 | "run_control": { 158 | "read_only": false 159 | } 160 | }, 161 | "outputs": [ 162 | { 163 | "data": { 164 | "text/html": "
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Unnamed: 0Unnamed: 0.1loan_statusPrincipaltermseffective_datedue_dateageeducationGender
000PAIDOFF1000302016-09-082016-10-0745High School or Belowmale
122PAIDOFF1000302016-09-082016-10-0733Bechalorfemale
233PAIDOFF1000152016-09-082016-09-2227collegemale
344PAIDOFF1000302016-09-092016-10-0828collegefemale
466PAIDOFF1000302016-09-092016-10-0829collegemale
\n
", 165 | "text/plain": " Unnamed: 0 Unnamed: 0.1 loan_status Principal terms effective_date \\\n0 0 0 PAIDOFF 1000 30 2016-09-08 \n1 2 2 PAIDOFF 1000 30 2016-09-08 \n2 3 3 PAIDOFF 1000 15 2016-09-08 \n3 4 4 PAIDOFF 1000 30 2016-09-09 \n4 6 6 PAIDOFF 1000 30 2016-09-09 \n\n due_date age education Gender \n0 2016-10-07 45 High School or Below male \n1 2016-10-07 33 Bechalor female \n2 2016-09-22 27 college male \n3 2016-10-08 28 college female \n4 2016-10-08 29 college male " 166 | }, 167 | "execution_count": 5, 168 | "metadata": {}, 169 | "output_type": "execute_result" 170 | } 171 | ], 172 | "source": "df['due_date'] = pd.to_datetime(df['due_date'])\ndf['effective_date'] = pd.to_datetime(df['effective_date'])\ndf.head()" 173 | }, 174 | { 175 | "cell_type": "markdown", 176 | "metadata": { 177 | "button": false, 178 | "new_sheet": false, 179 | "run_control": { 180 | "read_only": false 181 | } 182 | }, 183 | "source": "# Data visualization and pre-processing\n\n" 184 | }, 185 | { 186 | "cell_type": "markdown", 187 | "metadata": { 188 | "button": false, 189 | "new_sheet": false, 190 | "run_control": { 191 | "read_only": false 192 | } 193 | }, 194 | "source": "Let\u2019s see how many of each class is in our data set " 195 | }, 196 | { 197 | "cell_type": "code", 198 | "execution_count": 6, 199 | "metadata": { 200 | "button": false, 201 | "new_sheet": false, 202 | "run_control": { 203 | "read_only": false 204 | } 205 | }, 206 | "outputs": [ 207 | { 208 | "data": { 209 | "text/plain": "PAIDOFF 260\nCOLLECTION 86\nName: loan_status, dtype: int64" 210 | }, 211 | "execution_count": 6, 212 | "metadata": {}, 213 | "output_type": "execute_result" 214 | } 215 | ], 216 | "source": "df['loan_status'].value_counts()" 217 | }, 218 | { 219 | "cell_type": "markdown", 220 | "metadata": { 221 | "button": false, 222 | "new_sheet": false, 223 | "run_control": { 224 | "read_only": false 225 | } 226 | }, 227 | "source": "260 people have paid off the loan on time while 86 have gone into collection \n" 228 | }, 229 | { 230 | "cell_type": "markdown", 231 | "metadata": {}, 232 | "source": "Lets plot some columns to underestand data better:" 233 | }, 234 | { 235 | "cell_type": "code", 236 | "execution_count": 7, 237 | "metadata": {}, 238 | "outputs": [], 239 | "source": "# notice: installing seaborn might takes a few minutes\n!conda install -c anaconda seaborn -y" 240 | }, 241 | { 242 | "cell_type": "code", 243 | "execution_count": 8, 244 | "metadata": {}, 245 | "outputs": [ 246 | { 247 | "data": { 248 | "image/png": "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\n", 249 | "text/plain": "
" 250 | }, 251 | "metadata": { 252 | "needs_background": "light" 253 | }, 254 | "output_type": "display_data" 255 | } 256 | ], 257 | "source": "import seaborn as sns\n\nbins = np.linspace(df.Principal.min(), df.Principal.max(), 10)\ng = sns.FacetGrid(df, col=\"Gender\", hue=\"loan_status\", palette=\"Set1\", col_wrap=2)\ng.map(plt.hist, 'Principal', bins=bins, ec=\"k\")\n\ng.axes[-1].legend()\nplt.show()" 258 | }, 259 | { 260 | "cell_type": "code", 261 | "execution_count": 9, 262 | "metadata": { 263 | "button": false, 264 | "new_sheet": false, 265 | "run_control": { 266 | "read_only": false 267 | } 268 | }, 269 | "outputs": [ 270 | { 271 | "data": { 272 | "image/png": "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\n", 273 | "text/plain": "
" 274 | }, 275 | "metadata": { 276 | "needs_background": "light" 277 | }, 278 | "output_type": "display_data" 279 | } 280 | ], 281 | "source": "bins = np.linspace(df.age.min(), df.age.max(), 10)\ng = sns.FacetGrid(df, col=\"Gender\", hue=\"loan_status\", palette=\"Set1\", col_wrap=2)\ng.map(plt.hist, 'age', bins=bins, ec=\"k\")\n\ng.axes[-1].legend()\nplt.show()" 282 | }, 283 | { 284 | "cell_type": "markdown", 285 | "metadata": { 286 | "button": false, 287 | "new_sheet": false, 288 | "run_control": { 289 | "read_only": false 290 | } 291 | }, 292 | "source": "# Pre-processing: Feature selection/extraction" 293 | }, 294 | { 295 | "cell_type": "markdown", 296 | "metadata": { 297 | "button": false, 298 | "new_sheet": false, 299 | "run_control": { 300 | "read_only": false 301 | } 302 | }, 303 | "source": "### Lets look at the day of the week people get the loan " 304 | }, 305 | { 306 | "cell_type": "code", 307 | "execution_count": 10, 308 | "metadata": { 309 | "button": false, 310 | "new_sheet": false, 311 | "run_control": { 312 | "read_only": false 313 | } 314 | }, 315 | "outputs": [ 316 | { 317 | "data": { 318 | "image/png": "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\n", 319 | "text/plain": "
" 320 | }, 321 | "metadata": { 322 | "needs_background": "light" 323 | }, 324 | "output_type": "display_data" 325 | } 326 | ], 327 | "source": "df['dayofweek'] = df['effective_date'].dt.dayofweek\nbins = np.linspace(df.dayofweek.min(), df.dayofweek.max(), 10)\ng = sns.FacetGrid(df, col=\"Gender\", hue=\"loan_status\", palette=\"Set1\", col_wrap=2)\ng.map(plt.hist, 'dayofweek', bins=bins, ec=\"k\")\ng.axes[-1].legend()\nplt.show()\n" 328 | }, 329 | { 330 | "cell_type": "markdown", 331 | "metadata": { 332 | "button": false, 333 | "new_sheet": false, 334 | "run_control": { 335 | "read_only": false 336 | } 337 | }, 338 | "source": "We see that people who get the loan at the end of the week dont pay it off, so lets use Feature binarization to set a threshold values less then day 4 " 339 | }, 340 | { 341 | "cell_type": "code", 342 | "execution_count": 11, 343 | "metadata": { 344 | "button": false, 345 | "new_sheet": false, 346 | "run_control": { 347 | "read_only": false 348 | } 349 | }, 350 | "outputs": [ 351 | { 352 | "data": { 353 | "text/html": "
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Unnamed: 0Unnamed: 0.1loan_statusPrincipaltermseffective_datedue_dateageeducationGenderdayofweekweekend
000PAIDOFF1000302016-09-082016-10-0745High School or Belowmale30
122PAIDOFF1000302016-09-082016-10-0733Bechalorfemale30
233PAIDOFF1000152016-09-082016-09-2227collegemale30
344PAIDOFF1000302016-09-092016-10-0828collegefemale41
466PAIDOFF1000302016-09-092016-10-0829collegemale41
\n
", 354 | "text/plain": " Unnamed: 0 Unnamed: 0.1 loan_status Principal terms effective_date \\\n0 0 0 PAIDOFF 1000 30 2016-09-08 \n1 2 2 PAIDOFF 1000 30 2016-09-08 \n2 3 3 PAIDOFF 1000 15 2016-09-08 \n3 4 4 PAIDOFF 1000 30 2016-09-09 \n4 6 6 PAIDOFF 1000 30 2016-09-09 \n\n due_date age education Gender dayofweek weekend \n0 2016-10-07 45 High School or Below male 3 0 \n1 2016-10-07 33 Bechalor female 3 0 \n2 2016-09-22 27 college male 3 0 \n3 2016-10-08 28 college female 4 1 \n4 2016-10-08 29 college male 4 1 " 355 | }, 356 | "execution_count": 11, 357 | "metadata": {}, 358 | "output_type": "execute_result" 359 | } 360 | ], 361 | "source": "df['weekend'] = df['dayofweek'].apply(lambda x: 1 if (x>3) else 0)\ndf.head()" 362 | }, 363 | { 364 | "cell_type": "markdown", 365 | "metadata": { 366 | "button": false, 367 | "new_sheet": false, 368 | "run_control": { 369 | "read_only": false 370 | } 371 | }, 372 | "source": "## Convert Categorical features to numerical values" 373 | }, 374 | { 375 | "cell_type": "markdown", 376 | "metadata": { 377 | "button": false, 378 | "new_sheet": false, 379 | "run_control": { 380 | "read_only": false 381 | } 382 | }, 383 | "source": "Lets look at gender:" 384 | }, 385 | { 386 | "cell_type": "code", 387 | "execution_count": 12, 388 | "metadata": { 389 | "button": false, 390 | "new_sheet": false, 391 | "run_control": { 392 | "read_only": false 393 | } 394 | }, 395 | "outputs": [ 396 | { 397 | "data": { 398 | "text/plain": "Gender loan_status\nfemale PAIDOFF 0.865385\n COLLECTION 0.134615\nmale PAIDOFF 0.731293\n COLLECTION 0.268707\nName: loan_status, dtype: float64" 399 | }, 400 | "execution_count": 12, 401 | "metadata": {}, 402 | "output_type": "execute_result" 403 | } 404 | ], 405 | "source": "df.groupby(['Gender'])['loan_status'].value_counts(normalize=True)" 406 | }, 407 | { 408 | "cell_type": "markdown", 409 | "metadata": { 410 | "button": false, 411 | "new_sheet": false, 412 | "run_control": { 413 | "read_only": false 414 | } 415 | }, 416 | "source": "86 % of female pay there loans while only 73 % of males pay there loan\n" 417 | }, 418 | { 419 | "cell_type": "markdown", 420 | "metadata": { 421 | "button": false, 422 | "new_sheet": false, 423 | "run_control": { 424 | "read_only": false 425 | } 426 | }, 427 | "source": "Lets convert male to 0 and female to 1:\n" 428 | }, 429 | { 430 | "cell_type": "code", 431 | "execution_count": 13, 432 | "metadata": { 433 | "button": false, 434 | "new_sheet": false, 435 | "run_control": { 436 | "read_only": false 437 | } 438 | }, 439 | "outputs": [ 440 | { 441 | "data": { 442 | "text/html": "
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Unnamed: 0Unnamed: 0.1loan_statusPrincipaltermseffective_datedue_dateageeducationGenderdayofweekweekend
000PAIDOFF1000302016-09-082016-10-0745High School or Below030
122PAIDOFF1000302016-09-082016-10-0733Bechalor130
233PAIDOFF1000152016-09-082016-09-2227college030
344PAIDOFF1000302016-09-092016-10-0828college141
466PAIDOFF1000302016-09-092016-10-0829college041
\n
", 443 | "text/plain": " Unnamed: 0 Unnamed: 0.1 loan_status Principal terms effective_date \\\n0 0 0 PAIDOFF 1000 30 2016-09-08 \n1 2 2 PAIDOFF 1000 30 2016-09-08 \n2 3 3 PAIDOFF 1000 15 2016-09-08 \n3 4 4 PAIDOFF 1000 30 2016-09-09 \n4 6 6 PAIDOFF 1000 30 2016-09-09 \n\n due_date age education Gender dayofweek weekend \n0 2016-10-07 45 High School or Below 0 3 0 \n1 2016-10-07 33 Bechalor 1 3 0 \n2 2016-09-22 27 college 0 3 0 \n3 2016-10-08 28 college 1 4 1 \n4 2016-10-08 29 college 0 4 1 " 444 | }, 445 | "execution_count": 13, 446 | "metadata": {}, 447 | "output_type": "execute_result" 448 | } 449 | ], 450 | "source": "df['Gender'].replace(to_replace=['male','female'], value=[0,1],inplace=True)\ndf.head()" 451 | }, 452 | { 453 | "cell_type": "markdown", 454 | "metadata": { 455 | "button": false, 456 | "new_sheet": false, 457 | "run_control": { 458 | "read_only": false 459 | } 460 | }, 461 | "source": "## One Hot Encoding \n#### How about education?" 462 | }, 463 | { 464 | "cell_type": "code", 465 | "execution_count": 14, 466 | "metadata": { 467 | "button": false, 468 | "new_sheet": false, 469 | "run_control": { 470 | "read_only": false 471 | } 472 | }, 473 | "outputs": [ 474 | { 475 | "data": { 476 | "text/plain": "education loan_status\nBechalor PAIDOFF 0.750000\n COLLECTION 0.250000\nHigh School or Below PAIDOFF 0.741722\n COLLECTION 0.258278\nMaster or Above COLLECTION 0.500000\n PAIDOFF 0.500000\ncollege PAIDOFF 0.765101\n COLLECTION 0.234899\nName: loan_status, dtype: float64" 477 | }, 478 | "execution_count": 14, 479 | "metadata": {}, 480 | "output_type": "execute_result" 481 | } 482 | ], 483 | "source": "df.groupby(['education'])['loan_status'].value_counts(normalize=True)" 484 | }, 485 | { 486 | "cell_type": "markdown", 487 | "metadata": { 488 | "button": false, 489 | "new_sheet": false, 490 | "run_control": { 491 | "read_only": false 492 | } 493 | }, 494 | "source": "#### Feature befor One Hot Encoding" 495 | }, 496 | { 497 | "cell_type": "code", 498 | "execution_count": 15, 499 | "metadata": { 500 | "button": false, 501 | "new_sheet": false, 502 | "run_control": { 503 | "read_only": false 504 | } 505 | }, 506 | "outputs": [ 507 | { 508 | "data": { 509 | "text/html": "
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
PrincipaltermsageGendereducation
0100030450High School or Below
1100030331Bechalor
2100015270college
3100030281college
4100030290college
\n
", 510 | "text/plain": " Principal terms age Gender education\n0 1000 30 45 0 High School or Below\n1 1000 30 33 1 Bechalor\n2 1000 15 27 0 college\n3 1000 30 28 1 college\n4 1000 30 29 0 college" 511 | }, 512 | "execution_count": 15, 513 | "metadata": {}, 514 | "output_type": "execute_result" 515 | } 516 | ], 517 | "source": "df[['Principal','terms','age','Gender','education']].head()" 518 | }, 519 | { 520 | "cell_type": "markdown", 521 | "metadata": { 522 | "button": false, 523 | "new_sheet": false, 524 | "run_control": { 525 | "read_only": false 526 | } 527 | }, 528 | "source": "#### Use one hot encoding technique to conver categorical varables to binary variables and append them to the feature Data Frame " 529 | }, 530 | { 531 | "cell_type": "code", 532 | "execution_count": 16, 533 | "metadata": { 534 | "button": false, 535 | "new_sheet": false, 536 | "run_control": { 537 | "read_only": false 538 | } 539 | }, 540 | "outputs": [ 541 | { 542 | "data": { 543 | "text/html": "
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
PrincipaltermsageGenderweekendBechalorHigh School or Belowcollege
01000304500010
11000303310100
21000152700001
31000302811001
41000302901001
\n
", 544 | "text/plain": " Principal terms age Gender weekend Bechalor High School or Below \\\n0 1000 30 45 0 0 0 1 \n1 1000 30 33 1 0 1 0 \n2 1000 15 27 0 0 0 0 \n3 1000 30 28 1 1 0 0 \n4 1000 30 29 0 1 0 0 \n\n college \n0 0 \n1 0 \n2 1 \n3 1 \n4 1 " 545 | }, 546 | "execution_count": 16, 547 | "metadata": {}, 548 | "output_type": "execute_result" 549 | } 550 | ], 551 | "source": "Feature = df[['Principal','terms','age','Gender','weekend']]\nFeature = pd.concat([Feature,pd.get_dummies(df['education'])], axis=1)\nFeature.drop(['Master or Above'], axis = 1,inplace=True)\nFeature.head()\n" 552 | }, 553 | { 554 | "cell_type": "markdown", 555 | "metadata": { 556 | "button": false, 557 | "new_sheet": false, 558 | "run_control": { 559 | "read_only": false 560 | } 561 | }, 562 | "source": "### Feature selection" 563 | }, 564 | { 565 | "cell_type": "markdown", 566 | "metadata": { 567 | "button": false, 568 | "new_sheet": false, 569 | "run_control": { 570 | "read_only": false 571 | } 572 | }, 573 | "source": "Lets defind feature sets, X:" 574 | }, 575 | { 576 | "cell_type": "code", 577 | "execution_count": 17, 578 | "metadata": { 579 | "button": false, 580 | "new_sheet": false, 581 | "run_control": { 582 | "read_only": false 583 | } 584 | }, 585 | "outputs": [ 586 | { 587 | "data": { 588 | "text/html": "
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
PrincipaltermsageGenderweekendBechalorHigh School or Belowcollege
01000304500010
11000303310100
21000152700001
31000302811001
41000302901001
\n
", 589 | "text/plain": " Principal terms age Gender weekend Bechalor High School or Below \\\n0 1000 30 45 0 0 0 1 \n1 1000 30 33 1 0 1 0 \n2 1000 15 27 0 0 0 0 \n3 1000 30 28 1 1 0 0 \n4 1000 30 29 0 1 0 0 \n\n college \n0 0 \n1 0 \n2 1 \n3 1 \n4 1 " 590 | }, 591 | "execution_count": 17, 592 | "metadata": {}, 593 | "output_type": "execute_result" 594 | } 595 | ], 596 | "source": "X = Feature\nX[0:5]" 597 | }, 598 | { 599 | "cell_type": "markdown", 600 | "metadata": { 601 | "button": false, 602 | "new_sheet": false, 603 | "run_control": { 604 | "read_only": false 605 | } 606 | }, 607 | "source": "What are our lables?" 608 | }, 609 | { 610 | "cell_type": "code", 611 | "execution_count": 18, 612 | "metadata": { 613 | "button": false, 614 | "new_sheet": false, 615 | "run_control": { 616 | "read_only": false 617 | } 618 | }, 619 | "outputs": [ 620 | { 621 | "data": { 622 | "text/plain": "array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0])" 623 | }, 624 | "execution_count": 18, 625 | "metadata": {}, 626 | "output_type": "execute_result" 627 | } 628 | ], 629 | "source": "df['loan_status'].replace(to_replace=['PAIDOFF', 'COLLECTION'], value=[0,1],inplace=True)\ny = df['loan_status'].values\ny[0:10]" 630 | }, 631 | { 632 | "cell_type": "markdown", 633 | "metadata": { 634 | "button": false, 635 | "new_sheet": false, 636 | "run_control": { 637 | "read_only": false 638 | } 639 | }, 640 | "source": "## Normalize Data " 641 | }, 642 | { 643 | "cell_type": "markdown", 644 | "metadata": { 645 | "button": false, 646 | "new_sheet": false, 647 | "run_control": { 648 | "read_only": false 649 | } 650 | }, 651 | "source": "Data Standardization give data zero mean and unit variance (technically should be done after train test split )" 652 | }, 653 | { 654 | "cell_type": "code", 655 | "execution_count": 19, 656 | "metadata": { 657 | "button": false, 658 | "new_sheet": false, 659 | "run_control": { 660 | "read_only": false 661 | } 662 | }, 663 | "outputs": [ 664 | { 665 | "name": "stderr", 666 | "output_type": "stream", 667 | "text": "/opt/conda/envs/Python36/lib/python3.6/site-packages/sklearn/preprocessing/data.py:645: DataConversionWarning: Data with input dtype uint8, int64 were all converted to float64 by StandardScaler.\n return self.partial_fit(X, y)\n/opt/conda/envs/Python36/lib/python3.6/site-packages/ipykernel/__main__.py:1: DataConversionWarning: Data with input dtype uint8, int64 were all converted to float64 by StandardScaler.\n if __name__ == '__main__':\n" 668 | }, 669 | { 670 | "data": { 671 | "text/plain": "array([[ 0.51578458, 0.92071769, 2.33152555, -0.42056004, -1.20577805,\n -0.38170062, 1.13639374, -0.86968108],\n [ 0.51578458, 0.92071769, 0.34170148, 2.37778177, -1.20577805,\n 2.61985426, -0.87997669, -0.86968108],\n [ 0.51578458, -0.95911111, -0.65321055, -0.42056004, -1.20577805,\n -0.38170062, -0.87997669, 1.14984679],\n [ 0.51578458, 0.92071769, -0.48739188, 2.37778177, 0.82934003,\n -0.38170062, -0.87997669, 1.14984679],\n [ 0.51578458, 0.92071769, -0.3215732 , -0.42056004, 0.82934003,\n -0.38170062, -0.87997669, 1.14984679]])" 672 | }, 673 | "execution_count": 19, 674 | "metadata": {}, 675 | "output_type": "execute_result" 676 | } 677 | ], 678 | "source": "X= preprocessing.StandardScaler().fit(X).transform(X)\nX[0:5]" 679 | }, 680 | { 681 | "cell_type": "markdown", 682 | "metadata": { 683 | "button": false, 684 | "new_sheet": false, 685 | "run_control": { 686 | "read_only": false 687 | } 688 | }, 689 | "source": "# Classification " 690 | }, 691 | { 692 | "cell_type": "markdown", 693 | "metadata": { 694 | "button": false, 695 | "new_sheet": false, 696 | "run_control": { 697 | "read_only": false 698 | } 699 | }, 700 | "source": "Now, it is your turn, use the training set to build an accurate model. Then use the test set to report the accuracy of the model\nYou should use the following algorithm:\n- K Nearest Neighbor(KNN)\n- Decision Tree\n- Support Vector Machine\n- Logistic Regression\n\n\n\n__ Notice:__ \n- You can go above and change the pre-processing, feature selection, feature-extraction, and so on, to make a better model.\n- You should use either scikit-learn, Scipy or Numpy libraries for developing the classification algorithms.\n- You should include the code of the algorithm in the following cells." 701 | }, 702 | { 703 | "cell_type": "markdown", 704 | "metadata": {}, 705 | "source": "# K Nearest Neighbor(KNN)\nNotice: You should find the best k to build the model with the best accuracy. \n**warning:** You should not use the __loan_test.csv__ for finding the best k, however, you can split your train_loan.csv into train and test to find the best __k__." 706 | }, 707 | { 708 | "cell_type": "code", 709 | "execution_count": 98, 710 | "metadata": {}, 711 | "outputs": [], 712 | "source": "#Splitting the dataset into test set and train set\nfrom sklearn.model_selection import train_test_split\nX_train,X_test,y_train,y_test = train_test_split(X,y)" 713 | }, 714 | { 715 | "cell_type": "code", 716 | "execution_count": 99, 717 | "metadata": {}, 718 | "outputs": [ 719 | { 720 | "data": { 721 | "text/plain": "KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',\n metric_params=None, n_jobs=None, n_neighbors=3, p=2,\n weights='uniform')" 722 | }, 723 | "execution_count": 99, 724 | "metadata": {}, 725 | "output_type": "execute_result" 726 | } 727 | ], 728 | "source": "#Fitting the KNN with just taking random k=3\nfrom sklearn.neighbors import KNeighborsClassifier\nknn_classifier = KNeighborsClassifier(n_neighbors=3,metric='minkowski')\nknn_classifier.fit(X_train,y_train)" 729 | }, 730 | { 731 | "cell_type": "code", 732 | "execution_count": 100, 733 | "metadata": {}, 734 | "outputs": [], 735 | "source": "#predictions\ny_knn = knn_classifier.predict(X_test)" 736 | }, 737 | { 738 | "cell_type": "code", 739 | "execution_count": 101, 740 | "metadata": {}, 741 | "outputs": [ 742 | { 743 | "name": "stdout", 744 | "output_type": "stream", 745 | "text": "Accuracy Score= 0.8160919540229885\nconfusion_matrix= \n [[62 5]\n [11 9]]\n" 746 | } 747 | ], 748 | "source": "#Visualising the confusion_matrix and accuracy score\nfrom sklearn.metrics import confusion_matrix,accuracy_score\naccuracy_knn = accuracy_score(y_knn,y_test)\nconfusion_knn = confusion_matrix(y_knn,y_test)\nprint('Accuracy Score= ',accuracy_knn)\nprint('confusion_matrix= \\n',confusion_knn)" 749 | }, 750 | { 751 | "cell_type": "code", 752 | "execution_count": 102, 753 | "metadata": {}, 754 | "outputs": [ 755 | { 756 | "name": "stdout", 757 | "output_type": "stream", 758 | "text": "Accuracy for k=1 => 0.7471264367816092\nAccuracy for k=2 => 0.8275862068965517\nAccuracy for k=3 => 0.8160919540229885\nAccuracy for k=4 => 0.8620689655172413\nAccuracy for k=5 => 0.8505747126436781\nAccuracy for k=6 => 0.8620689655172413\nAccuracy for k=7 => 0.8735632183908046\nAccuracy for k=8 => 0.8275862068965517\nAccuracy for k=9 => 0.8275862068965517\nAccuracy for k=10 => 0.8160919540229885\nAccuracy for k=11 => 0.8045977011494253\nAccuracy for k=12 => 0.8045977011494253\nAccuracy for k=13 => 0.7931034482758621\nAccuracy for k=14 => 0.8045977011494253\nAccuracy for k=15 => 0.7931034482758621\nAccuracy for k=16 => 0.8045977011494253\nAccuracy for k=17 => 0.7701149425287356\nAccuracy for k=18 => 0.8160919540229885\nAccuracy for k=19 => 0.8045977011494253\n" 759 | } 760 | ], 761 | "source": "#Searching for best k for the KNN\nfrom sklearn.metrics import accuracy_score\nfor k in range (1,20):\n knn_classifier = KNeighborsClassifier(n_neighbors=k,metric='minkowski')\n knn_classifier.fit(X_train,y_train)\n y_knn = knn_classifier.predict(X_test)\n acc_score = accuracy_score(y_knn,y_test)\n print('Accuracy for k={0} => {1}'.format(k,acc_score))" 762 | }, 763 | { 764 | "cell_type": "code", 765 | "execution_count": 103, 766 | "metadata": {}, 767 | "outputs": [ 768 | { 769 | "name": "stdout", 770 | "output_type": "stream", 771 | "text": "Accuracy Score= 0.8735632183908046\nconfusion_matrix= \n [[69 7]\n [ 4 7]]\n" 772 | } 773 | ], 774 | "source": "#from the above result we get the best k as k = 7\n#Now applying k=7 in the KNN classification and fitting\nk = 7\nknn_classifier = KNeighborsClassifier(n_neighbors=k,metric='minkowski')\nknn_classifier.fit(X_train,y_train)\n\n#predictions\ny_knn = knn_classifier.predict(X_test)\n\n#Visualising the confusion_matrix and accuracy score\nfrom sklearn.metrics import confusion_matrix,accuracy_score\naccuracy_knn = accuracy_score(y_knn,y_test)\nconfusion_knn = confusion_matrix(y_knn,y_test)\nprint('Accuracy Score= ',accuracy_knn)\nprint('confusion_matrix= \\n',confusion_knn)" 775 | }, 776 | { 777 | "cell_type": "markdown", 778 | "metadata": {}, 779 | "source": "# Decision Tree" 780 | }, 781 | { 782 | "cell_type": "code", 783 | "execution_count": 104, 784 | "metadata": {}, 785 | "outputs": [ 786 | { 787 | "data": { 788 | "text/plain": "DecisionTreeClassifier(class_weight=None, criterion='entropy', max_depth=None,\n max_features=None, max_leaf_nodes=None,\n min_impurity_decrease=0.0, min_impurity_split=None,\n min_samples_leaf=1, min_samples_split=2,\n min_weight_fraction_leaf=0.0, presort=False, random_state=0,\n splitter='best')" 789 | }, 790 | "execution_count": 104, 791 | "metadata": {}, 792 | "output_type": "execute_result" 793 | } 794 | ], 795 | "source": "#Fitting the Dataset into Decision Tree\nfrom sklearn.tree import DecisionTreeClassifier\nclassifier_dt = DecisionTreeClassifier(criterion='entropy',random_state=0)\nclassifier_dt.fit(X_train,y_train)" 796 | }, 797 | { 798 | "cell_type": "code", 799 | "execution_count": 105, 800 | "metadata": {}, 801 | "outputs": [], 802 | "source": "#Predictions\ny_dt = classifier_dt.predict(X_test)" 803 | }, 804 | { 805 | "cell_type": "code", 806 | "execution_count": 106, 807 | "metadata": {}, 808 | "outputs": [ 809 | { 810 | "name": "stdout", 811 | "output_type": "stream", 812 | "text": "Accuracy Score= 0.7586206896551724\nconfusion_matrix= \n [[60 8]\n [13 6]]\n" 813 | } 814 | ], 815 | "source": "#Accuracy Score and Confusion matrix visualization\naccuracy_dt = accuracy_score(y_dt,y_test)\nconfusion_dt = confusion_matrix(y_dt,y_test)\nprint('Accuracy Score= ',accuracy_dt)\nprint('confusion_matrix= \\n',confusion_dt)" 816 | }, 817 | { 818 | "cell_type": "markdown", 819 | "metadata": {}, 820 | "source": "# Support Vector Machine" 821 | }, 822 | { 823 | "cell_type": "code", 824 | "execution_count": 107, 825 | "metadata": {}, 826 | "outputs": [ 827 | { 828 | "name": "stderr", 829 | "output_type": "stream", 830 | "text": "/opt/conda/envs/Python36/lib/python3.6/site-packages/sklearn/svm/base.py:196: FutureWarning: The default value of gamma will change from 'auto' to 'scale' in version 0.22 to account better for unscaled features. Set gamma explicitly to 'auto' or 'scale' to avoid this warning.\n \"avoid this warning.\", FutureWarning)\n" 831 | }, 832 | { 833 | "data": { 834 | "text/plain": "SVC(C=1.0, cache_size=200, class_weight=None, coef0=0.0,\n decision_function_shape='ovr', degree=3, gamma='auto_deprecated',\n kernel='rbf', max_iter=-1, probability=False, random_state=0,\n shrinking=True, tol=0.001, verbose=False)" 835 | }, 836 | "execution_count": 107, 837 | "metadata": {}, 838 | "output_type": "execute_result" 839 | } 840 | ], 841 | "source": "#Fitting the SVM\nfrom sklearn.svm import SVC\nclassifier_svm = SVC(kernel='rbf',random_state=0)\nclassifier_svm.fit(X_train,y_train)" 842 | }, 843 | { 844 | "cell_type": "code", 845 | "execution_count": 108, 846 | "metadata": {}, 847 | "outputs": [], 848 | "source": "#Predictions\ny_svm = classifier_svm.predict(X_test)" 849 | }, 850 | { 851 | "cell_type": "code", 852 | "execution_count": 109, 853 | "metadata": {}, 854 | "outputs": [ 855 | { 856 | "name": "stdout", 857 | "output_type": "stream", 858 | "text": "Accuracy Score= 0.8275862068965517\nconfusion_matrix= \n [[68 10]\n [ 5 4]]\n" 859 | } 860 | ], 861 | "source": "#Accuracy Score and Confusion Matrix Check\naccuracy_svm = accuracy_score(y_svm,y_test)\nconfusion_svm = confusion_matrix(y_svm,y_test)\nprint('Accuracy Score= ',accuracy_svm)\nprint('confusion_matrix= \\n',confusion_svm)" 862 | }, 863 | { 864 | "cell_type": "markdown", 865 | "metadata": {}, 866 | "source": "# Logistic Regression" 867 | }, 868 | { 869 | "cell_type": "code", 870 | "execution_count": 110, 871 | "metadata": {}, 872 | "outputs": [ 873 | { 874 | "name": "stderr", 875 | "output_type": "stream", 876 | "text": "/opt/conda/envs/Python36/lib/python3.6/site-packages/sklearn/linear_model/logistic.py:433: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.\n FutureWarning)\n" 877 | }, 878 | { 879 | "data": { 880 | "text/plain": "LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,\n intercept_scaling=1, max_iter=100, multi_class='warn',\n n_jobs=None, penalty='l2', random_state=0, solver='warn',\n tol=0.0001, verbose=0, warm_start=False)" 881 | }, 882 | "execution_count": 110, 883 | "metadata": {}, 884 | "output_type": "execute_result" 885 | } 886 | ], 887 | "source": "#Fitting the Logistic Regression\nfrom sklearn.linear_model import LogisticRegression\nclassifier_lr = LogisticRegression(random_state=0)\nclassifier_lr.fit(X_train,y_train)" 888 | }, 889 | { 890 | "cell_type": "code", 891 | "execution_count": 111, 892 | "metadata": {}, 893 | "outputs": [], 894 | "source": "#Predictions\ny_lr = classifier_lr.predict(X_test)" 895 | }, 896 | { 897 | "cell_type": "code", 898 | "execution_count": 112, 899 | "metadata": {}, 900 | "outputs": [ 901 | { 902 | "name": "stdout", 903 | "output_type": "stream", 904 | "text": "Accuracy Score= 0.7931034482758621\nconfusion_matrix= \n [[68 13]\n [ 5 1]]\n" 905 | } 906 | ], 907 | "source": "#Accuracy score and confusion matrix visualization\naccuracy_lr = accuracy_score(y_lr,y_test)\nconfusion_lr = confusion_matrix(y_lr,y_test)\nprint('Accuracy Score= ',accuracy_lr)\nprint('confusion_matrix= \\n',confusion_lr)" 908 | }, 909 | { 910 | "cell_type": "markdown", 911 | "metadata": {}, 912 | "source": "# Model Evaluation using Test set" 913 | }, 914 | { 915 | "cell_type": "code", 916 | "execution_count": 113, 917 | "metadata": {}, 918 | "outputs": [], 919 | "source": "#importing libraries\nfrom sklearn.metrics import jaccard_similarity_score\nfrom sklearn.metrics import f1_score\nfrom sklearn.metrics import log_loss" 920 | }, 921 | { 922 | "cell_type": "markdown", 923 | "metadata": {}, 924 | "source": "First, download and load the test set:" 925 | }, 926 | { 927 | "cell_type": "code", 928 | "execution_count": 114, 929 | "metadata": {}, 930 | "outputs": [ 931 | { 932 | "name": "stdout", 933 | "output_type": "stream", 934 | "text": "--2020-01-06 09:14:18-- https://s3-api.us-geo.objectstorage.softlayer.net/cf-courses-data/CognitiveClass/ML0101ENv3/labs/loan_test.csv\nResolving s3-api.us-geo.objectstorage.softlayer.net (s3-api.us-geo.objectstorage.softlayer.net)... 67.228.254.196\nConnecting to s3-api.us-geo.objectstorage.softlayer.net (s3-api.us-geo.objectstorage.softlayer.net)|67.228.254.196|:443... connected.\nHTTP request sent, awaiting response... 200 OK\nLength: 3642 (3.6K) [text/csv]\nSaving to: \u2018loan_test.csv\u2019\n\n100%[======================================>] 3,642 --.-K/s in 0s \n\n2020-01-06 09:14:18 (211 MB/s) - \u2018loan_test.csv\u2019 saved [3642/3642]\n\n" 935 | } 936 | ], 937 | "source": "!wget -O loan_test.csv https://s3-api.us-geo.objectstorage.softlayer.net/cf-courses-data/CognitiveClass/ML0101ENv3/labs/loan_test.csv" 938 | }, 939 | { 940 | "cell_type": "markdown", 941 | "metadata": { 942 | "button": false, 943 | "new_sheet": false, 944 | "run_control": { 945 | "read_only": false 946 | } 947 | }, 948 | "source": "### Load Test set for evaluation " 949 | }, 950 | { 951 | "cell_type": "code", 952 | "execution_count": 115, 953 | "metadata": { 954 | "button": false, 955 | "new_sheet": false, 956 | "run_control": { 957 | "read_only": false 958 | } 959 | }, 960 | "outputs": [ 961 | { 962 | "data": { 963 | "text/html": "
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Unnamed: 0Unnamed: 0.1loan_statusPrincipaltermseffective_datedue_dateageeducationGender
011PAIDOFF1000309/8/201610/7/201650Bechalorfemale
155PAIDOFF30079/9/20169/15/201635Master or Abovemale
22121PAIDOFF1000309/10/201610/9/201643High School or Belowfemale
32424PAIDOFF1000309/10/201610/9/201626collegemale
43535PAIDOFF800159/11/20169/25/201629Bechalormale
\n
", 964 | "text/plain": " Unnamed: 0 Unnamed: 0.1 loan_status Principal terms effective_date \\\n0 1 1 PAIDOFF 1000 30 9/8/2016 \n1 5 5 PAIDOFF 300 7 9/9/2016 \n2 21 21 PAIDOFF 1000 30 9/10/2016 \n3 24 24 PAIDOFF 1000 30 9/10/2016 \n4 35 35 PAIDOFF 800 15 9/11/2016 \n\n due_date age education Gender \n0 10/7/2016 50 Bechalor female \n1 9/15/2016 35 Master or Above male \n2 10/9/2016 43 High School or Below female \n3 10/9/2016 26 college male \n4 9/25/2016 29 Bechalor male " 965 | }, 966 | "execution_count": 115, 967 | "metadata": {}, 968 | "output_type": "execute_result" 969 | } 970 | ], 971 | "source": "import pandas as pd\ntest_df = pd.read_csv('loan_test.csv')\ntest_df.head()" 972 | }, 973 | { 974 | "cell_type": "code", 975 | "execution_count": 116, 976 | "metadata": {}, 977 | "outputs": [ 978 | { 979 | "data": { 980 | "text/html": "
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Unnamed: 0Unnamed: 0.1loan_statusPrincipaltermseffective_datedue_dateageeducationGender
011PAIDOFF1000302016-09-082016-10-0750Bechalorfemale
155PAIDOFF30072016-09-092016-09-1535Master or Abovemale
22121PAIDOFF1000302016-09-102016-10-0943High School or Belowfemale
32424PAIDOFF1000302016-09-102016-10-0926collegemale
43535PAIDOFF800152016-09-112016-09-2529Bechalormale
\n
", 981 | "text/plain": " Unnamed: 0 Unnamed: 0.1 loan_status Principal terms effective_date \\\n0 1 1 PAIDOFF 1000 30 2016-09-08 \n1 5 5 PAIDOFF 300 7 2016-09-09 \n2 21 21 PAIDOFF 1000 30 2016-09-10 \n3 24 24 PAIDOFF 1000 30 2016-09-10 \n4 35 35 PAIDOFF 800 15 2016-09-11 \n\n due_date age education Gender \n0 2016-10-07 50 Bechalor female \n1 2016-09-15 35 Master or Above male \n2 2016-10-09 43 High School or Below female \n3 2016-10-09 26 college male \n4 2016-09-25 29 Bechalor male " 982 | }, 983 | "execution_count": 116, 984 | "metadata": {}, 985 | "output_type": "execute_result" 986 | } 987 | ], 988 | "source": "#Date and time conversion\ntest_df['due_date'] = pd.to_datetime(test_df['due_date'])\ntest_df['effective_date'] = pd.to_datetime(test_df['effective_date'])\ntest_df.head()" 989 | }, 990 | { 991 | "cell_type": "code", 992 | "execution_count": 117, 993 | "metadata": {}, 994 | "outputs": [ 995 | { 996 | "data": { 997 | "text/plain": "education loan_status\nBechalor PAIDOFF 1.000000\nHigh School or Below PAIDOFF 0.523810\n COLLECTION 0.476190\nMaster or Above PAIDOFF 1.000000\ncollege PAIDOFF 0.826087\n COLLECTION 0.173913\nName: loan_status, dtype: float64" 998 | }, 999 | "execution_count": 117, 1000 | "metadata": {}, 1001 | "output_type": "execute_result" 1002 | } 1003 | ], 1004 | "source": "test_df.groupby(['education'])['loan_status'].value_counts(normalize=True)" 1005 | }, 1006 | { 1007 | "cell_type": "code", 1008 | "execution_count": 118, 1009 | "metadata": {}, 1010 | "outputs": [ 1011 | { 1012 | "data": { 1013 | "text/plain": "Gender loan_status\nfemale PAIDOFF 0.727273\n COLLECTION 0.272727\nmale PAIDOFF 0.744186\n COLLECTION 0.255814\nName: loan_status, dtype: float64" 1014 | }, 1015 | "execution_count": 118, 1016 | "metadata": {}, 1017 | "output_type": "execute_result" 1018 | } 1019 | ], 1020 | "source": "#Categorical Feature to numetrical values\ntest_df.groupby(['Gender'])['loan_status'].value_counts(normalize=True)" 1021 | }, 1022 | { 1023 | "cell_type": "code", 1024 | "execution_count": 119, 1025 | "metadata": {}, 1026 | "outputs": [ 1027 | { 1028 | "data": { 1029 | "text/html": "
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Unnamed: 0Unnamed: 0.1loan_statusPrincipaltermseffective_datedue_dateageeducationGender
011PAIDOFF1000302016-09-082016-10-0750Bechalor1
155PAIDOFF30072016-09-092016-09-1535Master or Above0
22121PAIDOFF1000302016-09-102016-10-0943High School or Below1
32424PAIDOFF1000302016-09-102016-10-0926college0
43535PAIDOFF800152016-09-112016-09-2529Bechalor0
\n
", 1030 | "text/plain": " Unnamed: 0 Unnamed: 0.1 loan_status Principal terms effective_date \\\n0 1 1 PAIDOFF 1000 30 2016-09-08 \n1 5 5 PAIDOFF 300 7 2016-09-09 \n2 21 21 PAIDOFF 1000 30 2016-09-10 \n3 24 24 PAIDOFF 1000 30 2016-09-10 \n4 35 35 PAIDOFF 800 15 2016-09-11 \n\n due_date age education Gender \n0 2016-10-07 50 Bechalor 1 \n1 2016-09-15 35 Master or Above 0 \n2 2016-10-09 43 High School or Below 1 \n3 2016-10-09 26 college 0 \n4 2016-09-25 29 Bechalor 0 " 1031 | }, 1032 | "execution_count": 119, 1033 | "metadata": {}, 1034 | "output_type": "execute_result" 1035 | } 1036 | ], 1037 | "source": "#Gender Encoding\ntest_df['Gender'].replace(to_replace=['male','female'], value=[0,1],inplace=True)\ntest_df.head()" 1038 | }, 1039 | { 1040 | "cell_type": "code", 1041 | "execution_count": 120, 1042 | "metadata": {}, 1043 | "outputs": [ 1044 | { 1045 | "data": { 1046 | "text/html": "
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
PrincipaltermsageGendereducationweekend
0100030501Bechalor0
13007350Master or Above1
2100030431High School or Below1
3100030260college1
480015290Bechalor1
\n
", 1047 | "text/plain": " Principal terms age Gender education weekend\n0 1000 30 50 1 Bechalor 0\n1 300 7 35 0 Master or Above 1\n2 1000 30 43 1 High School or Below 1\n3 1000 30 26 0 college 1\n4 800 15 29 0 Bechalor 1" 1048 | }, 1049 | "execution_count": 120, 1050 | "metadata": {}, 1051 | "output_type": "execute_result" 1052 | } 1053 | ], 1054 | "source": "#Features\ntest_df['dayofweek'] = test_df['effective_date'].dt.dayofweek\ntest_df['weekend'] = test_df['dayofweek'].apply(lambda x: 1 if (x>3) else 0)\ntest_df[['Principal','terms','age','Gender','education','weekend']].head()" 1055 | }, 1056 | { 1057 | "cell_type": "code", 1058 | "execution_count": 121, 1059 | "metadata": {}, 1060 | "outputs": [ 1061 | { 1062 | "data": { 1063 | "text/html": "
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
PrincipaltermsageGenderweekendBechalorHigh School or Belowcollege
01000305010100
130073501000
21000304311010
31000302601001
4800152901100
\n
", 1064 | "text/plain": " Principal terms age Gender weekend Bechalor High School or Below \\\n0 1000 30 50 1 0 1 0 \n1 300 7 35 0 1 0 0 \n2 1000 30 43 1 1 0 1 \n3 1000 30 26 0 1 0 0 \n4 800 15 29 0 1 1 0 \n\n college \n0 0 \n1 0 \n2 0 \n3 1 \n4 0 " 1065 | }, 1066 | "execution_count": 121, 1067 | "metadata": {}, 1068 | "output_type": "execute_result" 1069 | } 1070 | ], 1071 | "source": "#After one hot encoding\nFeature = test_df[['Principal','terms','age','Gender','weekend']]\nFeature = pd.concat([Feature,pd.get_dummies(test_df['education'])], axis=1)\nFeature.drop(['Master or Above'], axis = 1,inplace=True)\nFeature.head()" 1072 | }, 1073 | { 1074 | "cell_type": "code", 1075 | "execution_count": 122, 1076 | "metadata": {}, 1077 | "outputs": [], 1078 | "source": "X_test2 = Feature" 1079 | }, 1080 | { 1081 | "cell_type": "code", 1082 | "execution_count": 123, 1083 | "metadata": {}, 1084 | "outputs": [ 1085 | { 1086 | "name": "stderr", 1087 | "output_type": "stream", 1088 | "text": "/opt/conda/envs/Python36/lib/python3.6/site-packages/sklearn/preprocessing/data.py:645: DataConversionWarning: Data with input dtype uint8, int64 were all converted to float64 by StandardScaler.\n return self.partial_fit(X, y)\n/opt/conda/envs/Python36/lib/python3.6/site-packages/ipykernel/__main__.py:1: DataConversionWarning: Data with input dtype uint8, int64 were all converted to float64 by StandardScaler.\n if __name__ == '__main__':\n" 1089 | } 1090 | ], 1091 | "source": "X_test2 = preprocessing.StandardScaler().fit(X_test2).transform(X_test2)" 1092 | }, 1093 | { 1094 | "cell_type": "code", 1095 | "execution_count": 124, 1096 | "metadata": {}, 1097 | "outputs": [ 1098 | { 1099 | "data": { 1100 | "text/plain": "array([[ 0.49362588, 0.92844966, 3.05981865, 1.97714211, -1.30384048,\n 2.39791576, -0.79772404, -0.86135677],\n [-3.56269116, -1.70427745, 0.53336288, -0.50578054, 0.76696499,\n -0.41702883, -0.79772404, -0.86135677],\n [ 0.49362588, 0.92844966, 1.88080596, 1.97714211, 0.76696499,\n -0.41702883, 1.25356634, -0.86135677],\n [ 0.49362588, 0.92844966, -0.98251057, -0.50578054, 0.76696499,\n -0.41702883, -0.79772404, 1.16095912],\n [-0.66532184, -0.78854628, -0.47721942, -0.50578054, 0.76696499,\n 2.39791576, -0.79772404, -0.86135677]])" 1101 | }, 1102 | "execution_count": 124, 1103 | "metadata": {}, 1104 | "output_type": "execute_result" 1105 | } 1106 | ], 1107 | "source": "X_test2[0:5,:]" 1108 | }, 1109 | { 1110 | "cell_type": "code", 1111 | "execution_count": 125, 1112 | "metadata": {}, 1113 | "outputs": [ 1114 | { 1115 | "data": { 1116 | "text/plain": "array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1,\n 1, 1, 1, 1, 1, 1, 1, 1, 1, 1])" 1117 | }, 1118 | "execution_count": 125, 1119 | "metadata": {}, 1120 | "output_type": "execute_result" 1121 | } 1122 | ], 1123 | "source": "test_df['loan_status'].replace(to_replace=['PAIDOFF', 'COLLECTION'], value=[0,1],inplace=True)\ny_test2 = test_df['loan_status'].values\ny_test2" 1124 | }, 1125 | { 1126 | "cell_type": "code", 1127 | "execution_count": 126, 1128 | "metadata": {}, 1129 | "outputs": [], 1130 | "source": "#All predictions\ny_knn2 = knn_classifier.predict(X_test2) \ny_dt2 = classifier_dt.predict(X_test2) \ny_svm2 = classifier_svm.predict(X_test2) \ny_lr2 = classifier_lr.predict(X_test2) \n\n#probability of the logistic regression predictions\nlr_prob = classifier_lr.predict_proba(X_test2) " 1131 | }, 1132 | { 1133 | "cell_type": "code", 1134 | "execution_count": 127, 1135 | "metadata": {}, 1136 | "outputs": [ 1137 | { 1138 | "name": "stdout", 1139 | "output_type": "stream", 1140 | "text": "KNN J-Index= 0.7222222222222222\nDT J-Index= 0.7037037037037037\nSVM J-Index= 0.7962962962962963\nLR J-Index= 0.7592592592592593\n" 1141 | } 1142 | ], 1143 | "source": "#JCCARD Index for all of them\nfrom sklearn.metrics import jaccard_similarity_score\nj_index_knn = jaccard_similarity_score(y_test2,y_knn2)\nj_index_dt = jaccard_similarity_score(y_true=y_test2,y_pred=y_dt2)\nj_index_svm = jaccard_similarity_score(y_true=y_test2,y_pred=y_svm2)\nj_index_lr = jaccard_similarity_score(y_true=y_test2,y_pred=y_lr2)\nprint('KNN J-Index= ',j_index_knn)\nprint('DT J-Index= ',j_index_dt)\nprint('SVM J-Index= ',j_index_svm)\nprint('LR J-Index= ',j_index_lr)" 1144 | }, 1145 | { 1146 | "cell_type": "code", 1147 | "execution_count": 128, 1148 | "metadata": {}, 1149 | "outputs": [ 1150 | { 1151 | "name": "stdout", 1152 | "output_type": "stream", 1153 | "text": "KNN f1-Score= 0.7105756358768406\nDT f1-Score= 0.7037037037037038\nSVM f1-Score= 0.7801458747750308\nLR f1-Score= 0.6717642373556352\n" 1154 | } 1155 | ], 1156 | "source": "#F1_Score for all of them\nfrom sklearn.metrics import f1_score\nscore_knn = f1_score(y_test2,y_knn2, average='weighted')\nscore_dt = f1_score(y_test2,y_dt2, average='weighted')\nscore_svm = f1_score(y_test2,y_svm2, average='weighted')\nscore_lr = f1_score(y_test2,y_lr2, average='weighted')\nprint('KNN f1-Score= ',score_knn)\nprint('DT f1-Score= ',score_dt)\nprint('SVM f1-Score= ',score_svm)\nprint('LR f1-Score= ',score_lr)" 1157 | }, 1158 | { 1159 | "cell_type": "code", 1160 | "execution_count": 129, 1161 | "metadata": {}, 1162 | "outputs": [ 1163 | { 1164 | "name": "stdout", 1165 | "output_type": "stream", 1166 | "text": "LR f1-Score= 0.47296409967926384\n" 1167 | } 1168 | ], 1169 | "source": "#Log loss of the Logistic Regression predictions\nfrom sklearn.metrics import log_loss\nlog_lr = log_loss(y_test2,lr_prob)\nprint('LR f1-Score= ',log_lr)" 1170 | }, 1171 | { 1172 | "cell_type": "markdown", 1173 | "metadata": {}, 1174 | "source": "
\n\n# Report \nThe accuracy of the built model using different evaluation metrics are as given in the following table:-\n\n| Algorithm | Jaccard | F1-score | LogLoss |\n|--------------------|---------|----------|---------|\n| KNN | 0.72 | 0.71 | NA |\n| Decision Tree | 0.70 | 0.70 | NA |\n| SVM | 0.79 | 0.78 | NA |\n| LogisticRegression | 0.75 | 0.67 | 0.47 |" 1175 | }, 1176 | { 1177 | "cell_type": "markdown", 1178 | "metadata": { 1179 | "button": false, 1180 | "new_sheet": false, 1181 | "run_control": { 1182 | "read_only": false 1183 | } 1184 | }, 1185 | "source": "
\n

Conclusion:

\n\nAs we can see the accuracy rate for the predictions are almost in the range of 70% to 80% and for different classification algorithms used, and the highest accuation rate is in case of SVM algorithm so we can use this algorithm for getting more accurate prediction of the loan repayment status of Loan Holder.\n\n

Thanks!

\n\n

Author: SHASHI RAJ

\n

You can contact me on LinkedIn

\n\n
" 1186 | }, 1187 | { 1188 | "cell_type": "code", 1189 | "execution_count": null, 1190 | "metadata": {}, 1191 | "outputs": [], 1192 | "source": "" 1193 | } 1194 | ], 1195 | "metadata": { 1196 | "kernelspec": { 1197 | "display_name": "Python 3.6", 1198 | "language": "python", 1199 | "name": "python3" 1200 | }, 1201 | "language_info": { 1202 | "codemirror_mode": { 1203 | "name": "ipython", 1204 | "version": 3 1205 | }, 1206 | "file_extension": ".py", 1207 | "mimetype": "text/x-python", 1208 | "name": "python", 1209 | "nbconvert_exporter": "python", 1210 | "pygments_lexer": "ipython3", 1211 | "version": "3.6.8" 1212 | } 1213 | }, 1214 | "nbformat": 4, 1215 | "nbformat_minor": 2 1216 | } --------------------------------------------------------------------------------