├── CBSE-README.md ├── DEBUGGING.md ├── LICENSE ├── MAINTAINERS.md ├── README.md ├── data-for-testing └── sample_data.json ├── data ├── data_glossary.rtf └── fraud_dataset.csv ├── images ├── add.png ├── add_asset.png ├── add_dply.png ├── add_ml.png ├── architecture.png ├── cf_matrix.png ├── cf_mtrx.png ├── create_exp.png ├── create_prj.png ├── crt-dply.png ├── crt_dply.png ├── def_exp.png ├── def_prj.png ├── deploy_mdl.png ├── deply-space.png ├── dply_ready.png ├── feat_imp.png ├── feature_imp.png ├── feature_transforms.png ├── form.png ├── generate_pipelines.png ├── import_csv.png ├── insert_dataframe.png ├── json.png ├── model_eval.png ├── model_saved.png ├── not_trusted.png ├── overview.png ├── pipeline_3.png ├── prediction_settings.png ├── prmt-space.png ├── sample_split.png ├── sel-dply.png ├── sel_auto_ai.png ├── sel_target.png ├── select_model.png ├── shap.png ├── shap_ft_imp.png └── test_mdl.png └── notebook └── Fraud_Detect.ipynb /CBSE-README.md: -------------------------------------------------------------------------------- 1 | # Build, Train & Deploy model 2 | 3 | In this code pattern, we will demonstrate how to train, build & deploy a predictive model using automated and manual methodology. Students can understand the supervised learning example & play around by following the steps below to complete the model building process which is one of the critical aspects under machine learning. 4 | 5 | When the students have completed this code pattern, they will understand how to : 6 | 7 | * Quickly set up the services on cloud for model building. 8 | * Ingest the data and initiate the Auto AI process. 9 | * Build different models using Auto AI and evaluate the performance. 10 | * Choose the best model and complete the deployment. 11 | * Generate predictions using the deployed model by making ReST calls. 12 | * Compare the process of using Auto AI and building the model manually. 13 | 14 | # Architecture Diagram 15 | 16 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/architecture.png) 17 | 18 | 1. User logs into Watson Studio, creates a project and initiates an instance of Auto AI & Object Storage. 19 | 2. User uploads the data file in the CSV format to the object storage. 20 | 3. User initiates the model building process using Auto AI and create pipelines. 21 | 4. User evaluates different pipelines from Auto AI and selects the best model for deployment. 22 | 5. User generates accurate predictions by making ReST call to the deployed model. 23 | 24 | ## Included components 25 | 26 | * [IBM Watson Studio](https://www.ibm.com/cloud/watson-studio): Analyze data using RStudio, Jupyter, and Python in a configured, collaborative environment that includes IBM value-adds, such as managed Spark. 27 | 28 | * [IBM Auto AI](https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/autoai-overview.html):The AutoAI graphical tool in Watson Studio automatically analyzes your data and generates candidate model pipelines customized for your predictive modeling problem. 29 | 30 | * [IBM Cloud Object Storage](https://console.bluemix.net/catalog/services/cloud-object-storage): An IBM Cloud service that provides an unstructured cloud data store to build and deliver cost effective apps and services with high reliability and fast speed to market. This code pattern uses Cloud Object Storage. 31 | 32 | 33 | ## Featured technologies 34 | 35 | * [Artificial Intelligence](https://developer.ibm.com/technologies/artificial-intelligence/): Any system which can mimic cognitive functions that humans associate with the human mind, such as learning and problem solving. 36 | * [Data Science](https://developer.ibm.com/code/technologies/data-science/): Systems and scientific methods to analyze structured and unstructured data in order to extract knowledge and insights. 37 | * [Analytics](https://developer.ibm.com/code/technologies/analytics/): Analytics delivers the value of data for the enterprise. 38 | * [Python](https://www.python.org/): Python is a programming language that lets you work more quickly and integrate your systems more effectively. 39 | 40 | # Watch the Video 41 | 42 | TBD 43 | 44 | # Steps using AutoAI 45 | 46 | Follow these steps to setup and run this code pattern using `Auto AI`. 47 | 48 | 1. [Create an account with IBM Cloud](#1-create-an-account-with-ibm-cloud) 49 | 1. [Create a new Watson Studio project](#2-create-a-new-watson-studio-project) 50 | 1. [Add Data](#3-add-data) 51 | 1. [Add Asset as Auto AI](#4-add-asset-as-auto-ai) 52 | 1. [Create and define experiment](#5-create-and-define-experiment) 53 | 1. [Import the csv file](#6-import-the-csv-file) 54 | 1. [Run experiment](#7-run-experiment) 55 | 1. [Review the model and select best model](#8-review-the-model-and-select-best-model) 56 | 1. [Deploy to Cloud](#9-deploy-to-cloud) 57 | 1. [Model testing](#10-model-testing) 58 | 59 | 60 | 61 | 62 | ## 1. Create an account with IBM Cloud 63 | 64 | Sign up for IBM [**Cloud**](https://console.bluemix.net/). By clicking on create a free account you will get 30 days trial account. 65 | 66 | ## 2. Create a new Watson Studio project 67 | 68 | Sign up for IBM's [Watson Studio](http://dataplatform.ibm.com/). 69 | 70 | Click on New Project and select per below. 71 | 72 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/create_prj.png) 73 | 74 | Define the project by giving a Name and hit 'Create'. 75 | 76 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/def_prj.png) 77 | 78 | ## 3. Add Data 79 | 80 | [Clone this repo](https://github.com/IBM/predict-fraud-using-auto-ai) 81 | Navigate to [data](https://github.com/IBM/predict-fraud-using-auto-ai/tree/master/data) and save the file on the disk. Review the data glossary from the data folder for more details. `Note: Citation is needed to use this dataset for any other projects.` 82 | 83 | Click on Assets and select Browse and add the csv file from your file system. 84 | 85 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/add_asset.png) 86 | 87 | ## 4. Add Asset as Auto AI 88 | 89 | Click on Add to project and select AutoAI experiment. 90 | 91 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/sel_auto_ai.png) 92 | 93 | `Note: The Lite account for AutoAI comes with 50 capacity units per month and AutoAI consumes 20 capacity units per hour.` 94 | 95 | ## 5. Create and define experiment 96 | 97 | Click on New AutoAI experiment and give a name to the experiment. 98 | 99 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/def_exp.png) 100 | 101 | Click on Associate a Machine Learning service instance to this project and select the Machine Learning service instance and hit reload. If you do not have Machine Learning service instance, then follow the steps on your screen to get one. 102 | 103 | The Create button at the bottom right gets highlighted, go ahead and hit Create. 104 | 105 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/create_exp.png) 106 | 107 | ## 6. Import the csv file 108 | 109 | We need to import the csv file into the experiment. Note that, only csv file format is supported in AutoAI. Click on Browse or Select from project to choose the fraud_dataset.csv file to import. 110 | 111 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/import_csv.png) 112 | 113 | ## 7. Run experiment 114 | 115 | We have to select the target variable, in this case it is Fraud_Risk. Notice that Prediction Type and Optimized Metric get highlighted which tells us that we are working on Binary Classification use case and the evaluation metric is ROC (Receiver Operating Characteristics) & AUC (Area Under The Curve) which is used for classification usecases. 116 | 117 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/sel_target.png) 118 | 119 | We can click on experiment settings to adjust the holdout sample and training sample under source settings. 120 | 121 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/sample_split.png) 122 | 123 | We can click on prediction setting to modify the Prediction type, Positive Class & Optimized metric if required. In this case, we will leave'em as is and hit save and close. 124 | 125 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/prediction_settings.png) 126 | 127 | Click on `Run experiment`. 128 | 129 | ## 8. Review the model and select best model 130 | 131 | The AutoAI experiment has been completed in 97 seconds to generate four pipelines. `The duration of experiment depends completly on the size of the dataset`. AutoAI selects the appropriate machine learning algorithm (in the fifth stage of the process under `Model Selection`) which is best suited for the dataset. 132 | 133 | Each pipeline is run with different parameters, pipeline 3 is run on a sequence of HPO (hyper parameters optimization) & FE (feature engineering) where as pipeline 4 includes HPO (hyper parameters optimization), FE (feature engineering) and a combination of both. All these are done on the fly! Isn't it amazing that we just have to sit and watch while AutoAI takes care of things for us and generates awesome machine learning models!! There's very minimal intervention required to get things going and in no time we have the generated pipelines to choose from. 134 | 135 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/generate_pipelines.png) 136 | 137 | Click on pipeline 3 (which is ranked 1) to see the evaluation metrics on the left side. 138 | 139 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/pipeline_3.png) 140 | 141 | Click on model evaluation to review the performance of the model on the hold out sample and cross validation score. We can observe that our model has done very well by scoring > 95% on Recall, average Precision scores & Area under the curve scores. These scores also mean that our model is able to remember and identify fraudulent transactions with great precision. 142 | 143 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/model_eval.png) 144 | 145 | Click on feature importance to identify the significant features influencing the outcome. Any variable which starts with Newfeature is a variable generated on the fly by the model as part of feature engineering. 146 | 147 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/feature_imp.png) 148 | 149 | Click on feature transforms to understand the transformation of original features to new features. Feature engineering is one of the important factors in the model building process which has a direct impact on the overall accuracy of the model. We can observe that total features are 24 where as the original dataset had 13 variables which means 11 new features have been created by AutoAI which is one of the reasons for high accuracy of the model. 150 | 151 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/feature_transforms.png) 152 | 153 | After all the analysis of model performance, its time to select the model for deployment. We will go ahead and select `pipeline 3 which is Rank 1` and hit on Save as model. `We can select any of the pipelines to be saved which has highest Accuracy or any other evaluation metrics.` 154 | 155 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/select_model.png) 156 | 157 | ## 9. Deploy to Cloud 158 | 159 | The saved model can be found under `Models` under the project in Watson Studio. Click on three dots on the right side below Actions and hit `Deploy.` 160 | 161 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/deploy_mdl.png) 162 | 163 | In the next step, click on Add Deployment on the right side above `Actions.` 164 | 165 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/add_dply.png) 166 | 167 | Define the deployment by giving a name and hit `Save.` Note that, the model will get deployed as web service as a ReST API. 168 | 169 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/crt_dply.png) 170 | 171 | The deployment will get initialized and the status will show as `ready` when it is complete. 172 | 173 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/dply_ready.png) 174 | 175 | We can click on deployed model to see three tabs, Overview, Implementation and Test. Overview tab will give all details about the deployment like name, type, status et'al. Implementation tab will give scoring endpoint and code snippets to invoke the model. Test tab will give options to test the model. 176 | 177 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/overview.png) 178 | 179 | ## 10. Model testing 180 | 181 | Now that we have created and deployed the model as a web service, how do we test it?? We have to click on `Test` tab which will have two options which are form and json. We can use form if we are to test one record at a time where we can give the values to each attribute manually and hit `Predict` to generate predictions. The output of 0 under `values` indicate that it is a fraudulent transaction. The output can be either 0 or 1 as per the `data glossary` provided in the data folder. 182 | 183 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/form.png) 184 | 185 | For predicting multiple records, we have to update the values in the json file and use the option to input json data & then hit `Predict` to generate real time predictions. 186 | 187 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/json.png) 188 | 189 | A sample json file has been provided for testing purpose. The format for scoring the model has to be same as given in json file. Navigate to [data-for-testing](https://github.com/IBM/predict-fraud-using-auto-ai/tree/master/data-for-testing) and save the file on the disk. Copy and paste the values in the test tab as shown above to generate predictions. 190 | 191 | Go ahead and give it a try on different datasets as per your requirement and realize the ease of creating and deploying models quickly using `AutoAI offering by IBM.` 192 | 193 | # Steps using Jupyter Notebook 194 | 195 | Follow the below steps to use Jupyter Notebook for building the model. This is to compare the manual process of model building with the automated process using AutoAI. 196 | 197 | `Create an account with IBM Cloud and then create a project in Watson Studio. Add the data as an asset. These three steps are given above in detail.` 198 | 199 | 4. [Create the notebook](#4-create-the-notebook) 200 | 5. [Insert the data as dataframe](#5-insert-the-data-as-dataframe) 201 | 6. [Run the notebook](#6-run-the-notebook) 202 | 7. [Review the model performance](#7-review-the-model-performance) 203 | 204 | 205 | ## 4. Create the notebook 206 | 207 | * Open [IBM Watson Studio](https://dataplatform.ibm.com). 208 | * Go to the project and click on Add 209 | * Click on `Create notebook` to create a notebook. 210 | * Select the `From URL` tab. 211 | * Enter a name for the notebook. 212 | * Optionally, enter a description for the notebook. 213 | * Enter this Notebook URL: https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/notebook/Fraud_Detect.ipynb 214 | * Select the runtime (8 vCPU and 32GB RAM) 215 | * Click the `Create` button. 216 | 217 | After the notebook is imported, click on `Not Trusted` and select the option as Yes to trust the source of the notebook. 218 | 219 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/not_trusted.png) 220 | 221 | `This notebook has been created to demonstrate the steps for building the model using Watson Studio platform. For other usecases, the notebook has to be created from scratch.` 222 | 223 | ## 5. Insert the data as dataframe 224 | 225 | Click on 0010 icon at the top right side which will bring up the data assets tab. 226 | 227 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/add.png) 228 | 229 | Click on Insert to code dropdown and select the option Insert Pandas Dataframe. 230 | 231 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/insert_dataframe.png) 232 | 233 | ## 6. Run the notebook 234 | 235 | When a notebook is executed, what is actually happening is that each code cell in 236 | the notebook is executed, in order, from top to bottom. 237 | 238 | Each code cell is selectable and is preceded by a tag in the left margin. The tag 239 | format is `In [x]:`. Depending on the state of the notebook, the `x` can be: 240 | 241 | * A blank, this indicates that the cell has never been executed. 242 | * A number, this number represents the relative order this code step was executed. 243 | * A `*`, this indicates that the cell is currently executing. 244 | 245 | There are several ways to execute the code cells in your notebook: 246 | 247 | * One cell at a time. 248 | * Select the cell, and then press the `Play` button in the toolbar. 249 | * Batch mode, in sequential order. 250 | * From the `Cell` menu bar, there are several options available. For example, you 251 | can `Run All` cells in your notebook, or you can `Run All Below`, that will 252 | start executing from the first cell under the currently selected cell, and then 253 | continue executing all cells that follow. 254 | 255 | ## 7. Review the model performance 256 | 257 | After we run the cells in the notebook which includes data ingestion, data analysis, splitting the data, building the model and generating feature importance, its time to review and analyze the performance. There could be so many other activities like handling missing values, outlier management, feature engineering and hyper parameters optimization which are omitted for demo purpose. 258 | 259 | Check the model accuracy and confusion matrix to identify precision and recall scores. We can observe that model has > 92% accuracy on test data and the Precision/Recall scores are also high. 260 | 261 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/cf_matrix.png) 262 | 263 | Feature importance as per the model is below. The model has highlighted some of the attributes which has high impact on the outcome. Features might or might not be fairly compared to access the impact on outcome. 264 | 265 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/feat_imp.png) 266 | 267 | We have used shapley values which is a very effective model evaluation technique. Shapley values calculate the importance of a feature by comparing what a model predicts with and without the feature. However, since the order in which a model sees features can affect its predictions, this is done in every possible order, so that the features are fairly compared. 268 | 269 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/shap.png) 270 | 271 | We can observe that attributes like Married, Applicant Income & Credit history available are having high impact on the outcome which is to detect fraud as per shapley values. 272 | 273 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/shap_ft_imp.png) 274 | 275 | With this, we have come to the end of this code pattern where we can compare the ease of using AutoAI to build predictive models vs creating a new jupyter notebook to build and evaluate predictive models. `There's considerable reduction of time in building and deploying the models using AutoAI because it handles missing values, outliers, feature engineering & hyper parameters optimization on the fly and selects the best algorithm as per the dataset.` AI Model building process has been reduced from Days to Hours thanks to `AutoAI.` If you are a developer or a data scientist who wants to build the model quickly and deploy it for being production ready, then AutoAI is for you which will help in taking decisions faster and gives a detailed overview of the attribute relationships within the data. 276 | 277 | ## Citation for data : 278 | 279 | `The dataset which is referenced in this code pattern is created and owned by R.K.Sharath Kumar, Data Scientist, IBM India Software Labs.` 280 | 281 | # License 282 | 283 | This code pattern is licensed under the Apache Software License, Version 2. Separate third party code objects invoked within this code pattern are licensed by their respective providers pursuant to their own separate licenses. Contributions are subject to the Developer [Certificate of Origin, Version 1.1 (DCO)](https://developercertificate.org/) and the [Apache Software License, Version 2](http://www.apache.org/licenses/LICENSE-2.0.txt). 284 | 285 | Check the [ASL FAQ link](http://www.apache.org/foundation/license-faq.html#WhatDoesItMEAN) for more details 286 | -------------------------------------------------------------------------------- /DEBUGGING.md: -------------------------------------------------------------------------------- 1 | Troubleshooting 2 | =============== 3 | 4 | Watson Studio 5 | -------------- 6 | 7 | * Make sure you follow the instructions as per the documentation to create the AutoAI service. 8 | * Ingest the dataset as specified. 9 | * Do not stop the AutoAI process abruptly after it has started. 10 | * Create a new experiment if you want to make changes to the settings. 11 | 12 | Jupyter Notebooks 13 | ----------------- 14 | 15 | * Make sure the pip install ran correctly. You might need to restart the kernel and run the cells from the top after the pip install runs the first time. 16 | * Many of the cells rely on variables that are set in earlier cells. Some of these are cleared in later cells. Start over at the top when troubleshooting. 17 | * Many of the cells rely on service credentials from Bluemix that are set in earlier cells. Make sure to add your service credentials correctly. Run the cells from top down and evaluate the outcome. -------------------------------------------------------------------------------- /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 | -------------------------------------------------------------------------------- /MAINTAINERS.md: -------------------------------------------------------------------------------- 1 | ## Maintainers Guide 2 | 3 | This guide is intended for maintainers — anybody with commit access to one or 4 | more Developer Journey repositories. 5 | 6 | ## Methodology: 7 | 8 | A master branch. This branch MUST be releasable at all times. Commits and 9 | merges against this branch MUST contain only bugfixes and/or security fixes. 10 | Maintenance releases are tagged against master. 11 | 12 | A develop branch. This branch contains your proposed changes. 13 | 14 | The remainder of this document details how to merge pull requests to the 15 | repositories. 16 | 17 | ## Merge approval 18 | 19 | The project maintainers use LGTM (Looks Good To Me) in comments on the code 20 | review to indicate acceptance. A change requires LGTMs from two of the members 21 | of the [journey_name-dev-admins](https://github.com/orgs/IBM/teams) 22 | team. If the code is written by a member, the change only requires one more 23 | LGTM. 24 | 25 | ## Reviewing Pull Requests 26 | 27 | We recommend reviewing pull requests directly within GitHub. This allows a 28 | public commentary on changes, providing transparency for all users. When 29 | providing feedback be civil, courteous, and kind. Disagreement is fine, so 30 | long as the discourse is carried out politely. If we see a record of uncivil 31 | or abusive comments, we will revoke your commit privileges and invite you to 32 | leave the project. 33 | 34 | During your review, consider the following points: 35 | 36 | ### Does the change have impact? 37 | 38 | While fixing typos is nice as it adds to the overall quality of the project, 39 | merging a typo fix at a time can be a waste of effort. 40 | (Merging many typo fixes because somebody reviewed the entire component, 41 | however, is useful!) Other examples to be wary of: 42 | 43 | Changes in variable names. Ask whether or not the change will make 44 | understanding the code easier, or if it could simply a personal preference 45 | on the part of the author. 46 | 47 | Essentially: feel free to close issues that do not have impact. 48 | 49 | ### Do the changes make sense? 50 | 51 | If you do not understand what the changes are or what they accomplish, 52 | ask the author for clarification. Ask the author to add comments and/or 53 | clarify test case names to make the intentions clear. 54 | 55 | At times, such clarification will reveal that the author may not be using 56 | the code correctly, or is unaware of features that accommodate their needs. 57 | If you feel this is the case, work up a code sample that would address the 58 | issue for them, and feel free to close the issue once they confirm. 59 | 60 | ### Is this a new feature? If so: 61 | 62 | Does the issue contain narrative indicating the need for the feature? If not, 63 | ask them to provide that information. Since the issue will be linked in the 64 | changelog, this will often be a user's first introduction to it. 65 | 66 | Are new unit tests in place that test all new behaviors introduced? If not, do 67 | not merge the feature until they are! 68 | Is documentation in place for the new feature? (See the documentation 69 | guidelines). If not do not merge the feature until it is! 70 | Is the feature necessary for general use cases? Try and keep the scope of any 71 | given component narrow. If a proposed feature does not fit that scope, 72 | recommend to the user that they maintain the feature on their own, and close 73 | the request. You may also recommend that they see if the feature gains traction 74 | amongst other users, and suggest they re-submit when they can show such support. 75 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # WARNING: This repository is no longer maintained 2 | 3 | > This repository will not be updated. The repository will be kept available in read-only mode. 4 | 5 | # Fraud Prediction using Auto AI 6 | 7 | Automation and artificial intelligence (AI) are transforming businesses and will contribute to economic growth via contributions to productivity. They will also help address challenges in areas of healthcare, technology & other areas. At the same time, these technologies will transform the nature of work and the workplace itself. In this code pattern, we will focus on building state of the art systems for churning out predictions which can be used in different scenarios. We will try to predict fraudulent transactions which we know can reduce monetary loss and risk mitigation. The same approach can be used for predicting customer churn, demand and supply forecast and others. Building predictive models require time, effort and good knowledge of algorithms to create effective systems which can predict the outcome accurately. With that being said, IBM has introduced Auto AI which will automate all the tasks involved in building predictive models for different requirements. We will get to see how Auto AI can churn out great models quickly which will save time and effort and aid in faster decision making process. 8 | 9 | When the reader has completed this code pattern, they will understand how to : 10 | 11 | * Quickly set up the services on cloud for model building. 12 | * Ingest the data and initiate the Auto AI process. 13 | * Build different models using Auto AI and evaluate the performance. 14 | * Choose the best model and complete the deployment. 15 | * Generate predictions using the deployed model by making ReST calls. 16 | * Compare the process of using Auto AI and building the model manually. 17 | 18 | # Architecture Diagram 19 | 20 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/architecture.png) 21 | 22 | 1. User logs into Watson Studio, creates a project and initiates an instance of Auto AI & Object Storage. 23 | 2. User uploads the data file in the CSV format to the object storage. 24 | 3. User initiates the model building process using Auto AI and create pipelines. 25 | 4. User evaluates different pipelines from Auto AI and selects the best model for deployment. 26 | 5. User generates accurate predictions by making ReST call to the deployed model. 27 | 28 | ## Included components 29 | 30 | * [IBM Watson Studio](https://www.ibm.com/cloud/watson-studio): Analyze data using RStudio, Jupyter, and Python in a configured, collaborative environment that includes IBM value-adds, such as managed Spark. 31 | 32 | * [IBM Auto AI](https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/autoai-overview.html):The AutoAI graphical tool in Watson Studio automatically analyzes your data and generates candidate model pipelines customized for your predictive modeling problem. 33 | 34 | * [IBM Cloud Object Storage](https://console.bluemix.net/catalog/services/cloud-object-storage): An IBM Cloud service that provides an unstructured cloud data store to build and deliver cost effective apps and services with high reliability and fast speed to market. This code pattern uses Cloud Object Storage. 35 | 36 | 37 | ## Featured technologies 38 | 39 | * [Artificial Intelligence](https://developer.ibm.com/technologies/artificial-intelligence/): Any system which can mimic cognitive functions that humans associate with the human mind, such as learning and problem solving. 40 | * [Data Science](https://developer.ibm.com/code/technologies/data-science/): Systems and scientific methods to analyze structured and unstructured data in order to extract knowledge and insights. 41 | * [Analytics](https://developer.ibm.com/code/technologies/analytics/): Analytics delivers the value of data for the enterprise. 42 | * [Python](https://www.python.org/): Python is a programming language that lets you work more quickly and integrate your systems more effectively. 43 | 44 | # Watch the Video 45 | 46 | TBD 47 | 48 | # Steps using AutoAI 49 | 50 | Follow these steps to setup and run this code pattern using `Auto AI`. 51 | 52 | 1. [Create an account with IBM Cloud](#1-create-an-account-with-ibm-cloud) 53 | 1. [Create a new Watson Studio project](#2-create-a-new-watson-studio-project) 54 | 1. [Add Data](#3-add-data) 55 | 1. [Add Asset as Auto AI](#4-add-asset-as-auto-ai) 56 | 1. [Create and define experiment](#5-create-and-define-experiment) 57 | 1. [Import the csv file](#6-import-the-csv-file) 58 | 1. [Run experiment](#7-run-experiment) 59 | 1. [Analyze results](#8-analyze-results) 60 | 1. [Deploy to Cloud](#9-deploy-to-cloud) 61 | 1. [Model testing](#10-model-testing) 62 | 63 | 64 | 65 | 66 | ## 1. Create an account with IBM Cloud 67 | 68 | Sign up for IBM [**Cloud**](https://console.bluemix.net/). By clicking on create a free account you will get 30 days trial account. 69 | 70 | ## 2. Create a new Watson Studio project 71 | 72 | Sign up for IBM's [Watson Studio](http://dataplatform.ibm.com/). 73 | 74 | Click on New Project and select per below. 75 | 76 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/create_prj.png) 77 | 78 | Define the project by giving a Name and hit 'Create'. 79 | 80 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/def_prj.png) 81 | 82 | ## 3. Add Data 83 | 84 | [Clone this repo](https://github.com/IBM/predict-fraud-using-auto-ai) 85 | Navigate to [data](https://github.com/IBM/predict-fraud-using-auto-ai/tree/master/data) and save the file on the disk. Review the data glossary from the data folder for more details. `Note: Citation is needed to use this dataset for any other projects.` 86 | 87 | Click on Assets and select Browse and add the csv file from your file system. 88 | 89 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/add_asset.png) 90 | 91 | ## 4. Add Asset as Auto AI 92 | 93 | Click on Add to project and select AutoAI experiment. 94 | 95 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/sel_auto_ai.png) 96 | 97 | `Note: The Lite account for AutoAI comes with 50 capacity units per month and AutoAI consumes 20 capacity units per hour.` 98 | 99 | ## 5. Create and define experiment 100 | 101 | Click on New AutoAI experiment and give a name to the experiment. 102 | 103 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/def_exp.png) 104 | 105 | Click on Associate a Machine Learning service instance to this project and select the Machine Learning service instance and hit reload. If you do not have Machine Learning service instance, then follow the steps on your screen to get one. 106 | 107 | The Create button at the bottom right gets highlighted, go ahead and hit Create. 108 | 109 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/create_exp.png) 110 | 111 | ## 6. Import the csv file 112 | 113 | We need to import the csv file into the experiment. Note that, only csv file format is supported in AutoAI. Click on Browse or Select from project to choose the fraud_dataset.csv file to import. 114 | 115 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/import_csv.png) 116 | 117 | ## 7. Run experiment 118 | 119 | We have to select the target variable, in this case it is Fraud_Risk. Notice that Prediction Type and Optimized Metric get highlighted which tells us that we are working on Binary Classification use case and the evaluation metric is ROC (Receiver Operating Characteristics) & AUC (Area Under The Curve) which is used for classification usecases. 120 | 121 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/sel_target.png) 122 | 123 | We can click on experiment settings to adjust the holdout sample and training sample under source settings. 124 | 125 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/sample_split.png) 126 | 127 | We can click on prediction setting to modify the Prediction type, Positive Class & Optimized metric if required. In this case, we will leave'em as is and hit save and close. 128 | 129 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/prediction_settings.png) 130 | 131 | Click on `Run experiment`. 132 | 133 | ## 8. Analyze results 134 | 135 | The AutoAI experiment has been completed in 97 seconds to generate four pipelines. `The duration of experiment depends completly on the size of the dataset`. AutoAI selects the appropriate machine learning algorithm (in the fifth stage of the process under `Model Selection`) which is best suited for the dataset. 136 | 137 | Each pipeline is run with different parameters, pipeline 3 is run on a sequence of HPO (hyper parameters optimization) & FE (feature engineering) where as pipeline 4 includes HPO (hyper parameters optimization), FE (feature engineering) and a combination of both. All these are done on the fly! Isn't it amazing that we just have to sit and watch while AutoAI takes care of things for us and generates awesome machine learning models!! There's very minimal intervention required to get things going and in no time we have the generated pipelines to choose from. 138 | 139 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/generate_pipelines.png) 140 | 141 | Click on pipeline 3 (which is ranked 1) to see the evaluation metrics on the left side. 142 | 143 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/pipeline_3.png) 144 | 145 | Click on model evaluation to review the performance of the model on the hold out sample and cross validation score. We can observe that our model has done very well by scoring > 95% on Recall, average Precision scores & Area under the curve scores. These scores also mean that our model is able to remember and identify fraudulent transactions with great precision. 146 | 147 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/model_eval.png) 148 | 149 | Click on feature importance to identify the significant features influencing the outcome. Any variable which starts with Newfeature is a variable generated on the fly by the model as part of feature engineering. 150 | 151 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/feature_imp.png) 152 | 153 | Click on feature transforms to understand the transformation of original features to new features. Feature engineering is one of the important factors in the model building process which has a direct impact on the overall accuracy of the model. We can observe that total features are 24 where as the original dataset had 13 variables which means 11 new features have been created by AutoAI which is one of the reasons for high accuracy of the model. 154 | 155 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/feature_transforms.png) 156 | 157 | After all the analysis of model performance, its time to select the model for deployment. We will go ahead and select `pipeline 3 which is Rank 1` and hit on Save as model. `We can select any of the pipelines to be saved which has highest Accuracy or any other evaluation metrics.` 158 | 159 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/select_model.png) 160 | 161 | ## 9. Deploy to Cloud 162 | 163 | The saved model can be found under `Models` under the project in Watson Studio. Click on three dots on the right side below Actions and hit `Promote.` 164 | Click the Promote to deployment space. Choose an existing deployment space or create a new one. Click Add Deployment. 165 | 166 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/deploy_mdl.png) 167 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/deply-space.png) 168 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/crt-dply.png) 169 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/prmt-space.png) 170 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/sel-dply.png) 171 | 172 | In the page that opens, fill in the fields: Specify a name for the deployment. Select “Web service” as the Deployment type. Click Save. 173 | 174 | Define the deployment by giving a name and hit `Save.` Note that, the model will get deployed as web service as a ReST API. 175 | 176 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/crt_dply.png) 177 | 178 | After you save the deployment, click on the deployment name from the left navigation pane to view the deployment details page. The deployment will get initialized and the status will show as `ready` when it is complete. 179 | 180 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/dply_ready.png) 181 | 182 | We can click on deployed model to see three tabs, Overview, Implementation and Test. Overview tab will give all details about the deployment like name, type, status et'al. Implementation tab will give scoring endpoint and code snippets to invoke the model. Test tab will give options to test the model. 183 | 184 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/overview.png) 185 | 186 | ## 10. Model testing 187 | 188 | Now that we have created and deployed the model as a web service, how do we test it?? We have to click on `Test` tab which will have two options which are form and json. We can use form if we are to test one record at a time where we can give the values to each attribute manually and hit `Predict` to generate predictions. The output of 0 under `values` indicate that it is a fraudulent transaction. The output can be either 0 or 1 as per the `data glossary` provided in the data folder. 189 | 190 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/form.png) 191 | 192 | For predicting multiple records, we have to update the values in the json file and use the option to input json data & then hit `Predict` to generate real time predictions. 193 | 194 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/json.png) 195 | 196 | A sample json file has been provided for testing purpose. The format for scoring the model has to be same as given in json file. Navigate to [data-for-testing](https://github.com/IBM/predict-fraud-using-auto-ai/tree/master/data-for-testing) and save the file on the disk. Copy and paste the values in the test tab as shown above to generate predictions. 197 | 198 | Go ahead and give it a try on different datasets as per your requirement and realize the ease of creating and deploying models quickly using `AutoAI offering by IBM.` 199 | 200 | # Steps using Jupyter Notebook 201 | 202 | Follow the below steps to use Jupyter Notebook for building the model. This is to compare the manual process of model building with the automated process using AutoAI. 203 | 204 | `Create an account with IBM Cloud and then create a project in Watson Studio. Add the data as an asset. These three steps are given above in detail.` 205 | 206 | 4. [Create the notebook](#4-create-the-notebook) 207 | 5. [Insert the data as dataframe](#5-insert-the-data-as-dataframe) 208 | 6. [Run the notebook](#6-run-the-notebook) 209 | 7. [Analyze the results](#7-analyze-the-results) 210 | 211 | 212 | ## 4. Create the notebook 213 | 214 | * Open [IBM Watson Studio](https://dataplatform.ibm.com). 215 | * Go to the project and click on Add 216 | * Click on `Create notebook` to create a notebook. 217 | * Select the `From URL` tab. 218 | * Enter a name for the notebook. 219 | * Optionally, enter a description for the notebook. 220 | * Enter this Notebook URL: https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/notebook/Fraud_Detect.ipynb 221 | * Select the runtime (8 vCPU and 32GB RAM) 222 | * Click the `Create` button. 223 | 224 | After the notebook is imported, click on `Not Trusted` and select the option as Yes to trust the source of the notebook. 225 | 226 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/not_trusted.png) 227 | 228 | `This notebook has been created to demonstrate the steps for building the model using Watson Studio platform. For other usecases, the notebook has to be created from scratch.` 229 | 230 | ## 5. Insert the data as dataframe 231 | 232 | Click on 0010 icon at the top right side which will bring up the data assets tab. 233 | 234 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/add.png) 235 | 236 | Click on Insert to code dropdown and select the option Insert Pandas Dataframe. 237 | 238 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/insert_dataframe.png) 239 | 240 | ## 6. Run the notebook 241 | 242 | When a notebook is executed, what is actually happening is that each code cell in 243 | the notebook is executed, in order, from top to bottom. 244 | 245 | Each code cell is selectable and is preceded by a tag in the left margin. The tag 246 | format is `In [x]:`. Depending on the state of the notebook, the `x` can be: 247 | 248 | * A blank, this indicates that the cell has never been executed. 249 | * A number, this number represents the relative order this code step was executed. 250 | * A `*`, this indicates that the cell is currently executing. 251 | 252 | There are several ways to execute the code cells in your notebook: 253 | 254 | * One cell at a time. 255 | * Select the cell, and then press the `Play` button in the toolbar. 256 | * Batch mode, in sequential order. 257 | * From the `Cell` menu bar, there are several options available. For example, you 258 | can `Run All` cells in your notebook, or you can `Run All Below`, that will 259 | start executing from the first cell under the currently selected cell, and then 260 | continue executing all cells that follow. 261 | 262 | ## 7. Analyze the results 263 | 264 | After we run the cells in the notebook which includes data ingestion, data analysis, splitting the data, building the model and generating feature importance, its time to review and analyze the performance. There could be so many other activities like handling missing values, outlier management, feature engineering and hyper parameters optimization which are omitted for demo purpose. 265 | 266 | Check the model accuracy and confusion matrix to identify precision and recall scores. We can observe that model has > 92% accuracy on test data and the Precision/Recall scores are also high. 267 | 268 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/cf_matrix.png) 269 | 270 | Feature importance as per the model is below. The model has highlighted some of the attributes which has high impact on the outcome. Features might or might not be fairly compared to access the impact on outcome. 271 | 272 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/feat_imp.png) 273 | 274 | We have used shapley values which is a very effective model evaluation technique. Shapley values calculate the importance of a feature by comparing what a model predicts with and without the feature. However, since the order in which a model sees features can affect its predictions, this is done in every possible order, so that the features are fairly compared. 275 | 276 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/shap.png) 277 | 278 | We can observe that attributes like Married, Applicant Income & Credit history available are having high impact on the outcome which is to detect fraud as per shapley values. 279 | 280 | ![](https://github.com/IBM/predict-fraud-using-auto-ai/blob/master/images/shap_ft_imp.png) 281 | 282 | With this, we have come to the end of this code pattern where we can compare the ease of using AutoAI to build predictive models vs creating a new jupyter notebook to build and evaluate predictive models. `There's considerable reduction of time in building and deploying the models using AutoAI because it handles missing values, outliers, feature engineering & hyper parameters optimization on the fly and selects the best algorithm as per the dataset.` AI Model building process has been reduced from Days to Hours thanks to `AutoAI.` If you are a developer or a data scientist who wants to build the model quickly and deploy it for being production ready, then AutoAI is for you which will help in taking decisions faster and gives a detailed overview of the attribute relationships within the data. 283 | 284 | ## More to come : 285 | 286 | The integration of Auto AI and Watson Open Scale is currently in progress and will be updated at a later date. 287 | 288 | ## Related Links : 289 | 290 | [Fraud Prediction using skewed data](https://github.com/IBM/xgboost-smote-detect-fraud) 291 | 292 | # Troubleshooting 293 | 294 | [See DEBUGGING.md.](DEBUGGING.md) 295 | 296 | ## Citation for data : 297 | 298 | `The dataset which is referenced in this code pattern is created and owned by R.K.Sharath Kumar, Data Scientist, IBM India Software Labs.` 299 | 300 | # License 301 | 302 | This code pattern is licensed under the Apache Software License, Version 2. Separate third party code objects invoked within this code pattern are licensed by their respective providers pursuant to their own separate licenses. Contributions are subject to the Developer [Certificate of Origin, Version 1.1 (DCO)](https://developercertificate.org/) and the [Apache Software License, Version 2](http://www.apache.org/licenses/LICENSE-2.0.txt). 303 | 304 | Check the [ASL FAQ link](http://www.apache.org/foundation/license-faq.html#WhatDoesItMEAN) for more details 305 | -------------------------------------------------------------------------------- /data-for-testing/sample_data.json: -------------------------------------------------------------------------------- 1 | {"input_data": [{"fields": ["Gender", "Married", "Dependents", "Education", "Self_Employed", "ApplicantIncome", "CoapplicantIncome", "LoanAmount", "Loan_Term", "Credit_History_Available", "Housing", "Locality"], "values": [[1,0,0,0,0,3748,1668,110,360,1,0,2]]}]} -------------------------------------------------------------------------------- /data/data_glossary.rtf: -------------------------------------------------------------------------------- 1 | {\rtf1\ansi\ansicpg1252\cocoartf1561\cocoasubrtf400 2 | {\fonttbl\f0\fnil\fcharset0 HelveticaNeue;} 3 | {\colortbl;\red255\green255\blue255;\red53\green53\blue53;} 4 | {\*\expandedcolortbl;;\cssrgb\c27059\c27059\c27059;} 5 | \paperw11900\paperh16840\margl1440\margr1440\vieww10800\viewh8400\viewkind0 6 | \deftab560 7 | \pard\pardeftab560\slleading20\partightenfactor0 8 | 9 | \f0\fs24 \cf2 Gender \ 10 | 1 = Male\ 11 | 0 = Female\ 12 | \ 13 | Married\ 14 | 1 = Yes\ 15 | 0 = No\ 16 | \ 17 | Education\ 18 | 1 = Masters\ 19 | 0 = Graduate\ 20 | \ 21 | Self Employed\ 22 | 1 = No\ 23 | 0 = Yes\ 24 | \ 25 | Credit History Available\ 26 | 1 = Yes\ 27 | 0 = No\ 28 | \ 29 | Housing\ 30 | 1 = Own House\ 31 | 0 = Rented\ 32 | \ 33 | Locality\ 34 | 1 = Urban\ 35 | 2 = Semi urban\ 36 | 3 = Rural\ 37 | \ 38 | Fraud Risk\ 39 | 1 = No risk\ 40 | 0 = Risk\ 41 | } -------------------------------------------------------------------------------- /data/fraud_dataset.csv: -------------------------------------------------------------------------------- 1 | Gender,Married,Dependents,Education,Self_Employed,ApplicantIncome,CoapplicantIncome,LoanAmount,Loan_Term,Credit_History_Available,Housing,Locality,Fraud_Risk 2 | 1,0,0,1,0,5849,0,146,360,1,1,1,0 3 | 1,1,1,1,1,4583,1508,128,360,1,1,3,1 4 | 1,1,0,1,1,3000,0,66,360,1,1,1,1 5 | 1,1,0,0,1,2583,2358,120,360,1,1,1,1 6 | 1,0,0,1,0,6000,0,141,360,1,1,1,0 7 | 1,1,2,1,1,5417,4196,267,360,1,0,1,1 8 | 1,1,0,0,1,2333,1516,95,360,1,1,1,1 9 | 1,1,3,1,1,3036,2504,158,360,0,1,2,1 10 | 1,1,2,1,1,4006,1526,168,360,1,1,1,1 11 | 1,1,1,1,1,12841,10968,349,360,1,0,2,1 12 | 1,1,2,1,1,3200,700,70,360,1,0,1,1 13 | 1,1,2,1,1,2500,1840,109,360,1,0,1,1 14 | 1,1,2,1,1,3073,8106,200,360,1,0,1,1 15 | 1,0,0,1,0,1853,2840,114,360,1,1,3,1 16 | 1,1,2,1,1,1299,1086,17,120,1,1,1,1 17 | 1,0,0,1,0,4950,0,125,360,1,1,1,0 18 | 1,0,1,0,0,3596,0,100,240,1,1,1,0 19 | 0,0,0,1,0,3510,0,76,360,0,1,1,1 20 | 1,1,0,0,1,4887,0,133,360,1,1,3,1 21 | 1,1,0,1,1,2600,3500,115,12,1,1,1,1 22 | 1,1,0,0,1,7660,0,104,360,0,1,1,1 23 | 1,1,1,1,1,5955,5625,315,360,1,0,1,1 24 | 1,1,0,0,1,2600,1911,116,360,0,1,2,1 25 | 0,1,2,0,1,3365,1917,112,360,0,0,3,1 26 | 1,1,1,1,1,3717,2925,151,360,1,0,2,1 27 | 1,1,0,1,1,9560,0,191,360,1,1,2,1 28 | 1,1,0,1,1,2799,2253,122,360,1,0,2,1 29 | 1,1,2,0,1,4226,1040,110,360,1,0,1,1 30 | 1,0,0,0,0,1442,0,35,360,1,1,1,1 31 | 0,0,2,1,1,3750,2083,120,360,1,1,2,0 32 | 1,1,1,1,1,4166,3369,201,360,1,1,1,1 33 | 1,0,0,1,0,3167,0,74,360,1,1,1,1 34 | 1,0,1,1,1,4692,0,106,360,1,0,3,1 35 | 1,1,0,1,1,3500,1667,114,360,1,1,2,1 36 | 1,0,3,1,0,12500,3000,320,360,1,1,3,1 37 | 1,1,0,1,1,2275,2067,146,360,1,0,1,1 38 | 1,1,0,1,1,1828,1330,100,12,0,1,1,1 39 | 0,1,0,1,1,3667,1459,144,360,1,1,2,1 40 | 1,0,0,1,0,4166,7210,184,360,1,1,1,0 41 | 1,0,0,0,0,3748,1668,110,360,1,0,2,0 42 | 1,0,0,1,0,3600,0,80,360,1,1,1,1 43 | 1,0,0,1,0,1800,1213,47,360,1,1,1,0 44 | 1,1,0,1,1,2400,0,75,360,1,0,1,1 45 | 1,1,0,1,1,3941,2336,134,360,1,0,2,1 46 | 1,1,0,0,1,4695,0,96,12,1,1,1,1 47 | 0,0,0,1,0,3410,0,88,12,1,0,1,0 48 | 1,1,1,1,1,5649,0,44,360,1,0,1,1 49 | 1,1,0,1,1,5821,0,144,360,1,1,1,1 50 | 0,1,0,1,1,2645,3440,120,360,0,1,1,1 51 | 0,0,0,1,0,4000,2275,144,360,1,1,2,0 52 | 0,1,0,0,1,1928,1644,100,360,1,0,2,1 53 | 0,0,0,1,0,3086,0,120,360,1,0,2,0 54 | 0,0,0,1,0,4230,0,112,360,1,1,2,1 55 | 1,1,2,1,1,4616,0,134,360,1,0,1,1 56 | 0,1,1,1,1,11500,0,286,360,0,0,1,1 57 | 1,1,2,1,1,2708,1167,97,360,1,1,2,1 58 | 1,1,0,1,1,2132,1591,96,360,1,1,2,1 59 | 1,1,0,1,1,3366,2200,135,360,1,1,3,1 60 | 1,1,1,1,1,8080,2250,180,360,1,1,1,1 61 | 1,1,2,0,1,3357,2859,144,360,1,1,1,1 62 | 1,1,0,1,1,2500,3796,120,360,1,0,1,1 63 | 1,1,3,1,1,3029,0,99,360,1,1,1,1 64 | 1,1,0,0,1,2609,3449,165,180,0,1,3,1 65 | 1,1,1,1,1,4945,0,146,360,0,0,3,1 66 | 0,0,0,1,0,4166,0,116,360,0,1,2,1 67 | 1,1,0,1,1,5726,4595,258,360,1,1,2,1 68 | 1,0,0,0,0,3200,2254,126,180,0,1,1,1 69 | 1,1,1,1,1,10750,0,312,360,1,1,1,1 70 | 1,1,3,0,1,7100,0,125,60,1,1,1,1 71 | 0,0,0,1,0,4300,0,136,360,0,1,2,1 72 | 1,1,0,1,1,3208,3066,172,360,1,1,1,1 73 | 1,1,2,0,1,1875,1875,97,360,1,1,2,1 74 | 1,0,0,1,0,3500,0,81,300,1,1,2,0 75 | 1,1,3,0,1,4755,0,95,12,0,0,2,1 76 | 1,1,3,1,1,5266,1774,187,360,1,1,2,1 77 | 1,0,0,1,0,3750,0,113,480,1,1,1,1 78 | 1,0,0,1,0,3750,4750,176,360,1,1,1,1 79 | 1,1,1,1,1,1000,3022,110,360,1,1,1,1 80 | 1,1,3,1,1,3167,4000,180,300,0,0,2,1 81 | 1,1,3,0,1,3333,2166,130,360,1,0,2,1 82 | 0,0,0,1,0,3846,0,111,360,1,1,2,0 83 | 1,1,1,1,1,2395,0,146,360,1,1,2,1 84 | 0,1,2,1,1,1378,1881,167,360,1,1,1,1 85 | 1,1,0,1,1,6000,2250,265,360,1,0,2,1 86 | 1,1,1,1,1,3988,0,50,240,1,0,1,1 87 | 1,0,0,1,0,2366,2531,136,360,1,1,2,0 88 | 1,1,2,0,1,3333,2000,99,360,1,1,2,1 89 | 1,1,0,1,1,2500,2118,104,360,1,0,2,1 90 | 1,0,0,1,0,8566,0,210,360,1,1,1,0 91 | 1,1,0,1,1,5695,4167,175,360,1,1,2,1 92 | 1,1,0,1,1,2958,2900,131,360,1,1,2,1 93 | 1,1,2,1,1,6250,5654,188,180,1,1,2,1 94 | 1,1,2,0,1,3273,1820,81,360,1,1,1,1 95 | 1,0,0,1,0,4133,0,122,360,1,1,2,0 96 | 1,0,0,0,0,3620,0,25,120,1,1,2,0 97 | 1,0,0,1,1,6782,0,146,360,1,1,1,1 98 | 0,1,0,1,1,2484,2302,137,360,1,1,2,1 99 | 1,1,0,1,1,1977,997,50,360,1,0,2,1 100 | 1,1,0,0,1,4188,0,115,180,1,1,2,1 101 | 1,1,0,1,1,1759,3541,131,360,1,1,2,1 102 | 1,1,2,0,1,4288,3263,133,180,1,0,1,1 103 | 1,0,0,1,0,4843,3806,151,360,1,1,2,0 104 | 1,1,1,1,1,13650,0,146,360,1,0,1,1 105 | 1,1,0,1,1,4652,3583,146,360,1,1,2,1 106 | 1,0,1,1,0,3816,754,160,360,1,0,1,0 107 | 1,1,1,1,1,3052,1030,100,360,1,0,1,1 108 | 1,1,2,1,1,11417,1126,225,360,1,0,1,1 109 | 1,0,0,0,1,7333,0,120,360,1,1,3,1 110 | 1,1,2,1,1,3800,3600,216,360,0,0,1,1 111 | 1,1,3,0,1,2071,754,94,480,1,1,2,1 112 | 1,0,0,1,0,5316,0,136,360,1,1,1,0 113 | 0,1,0,1,1,2929,2333,139,360,1,1,2,1 114 | 1,1,0,0,1,3572,4114,152,12,0,1,3,1 115 | 0,0,1,1,1,7451,0,146,360,1,1,2,0 116 | 1,0,0,1,1,5050,0,118,360,1,0,2,0 117 | 1,1,1,1,1,14583,0,185,180,1,0,3,1 118 | 0,1,0,1,1,3167,2283,154,360,1,1,2,1 119 | 1,1,1,1,1,2214,1398,85,360,1,0,1,1 120 | 1,1,0,1,1,5568,2142,175,360,1,0,3,1 121 | 0,0,0,1,0,10408,0,259,360,1,0,1,0 122 | 1,1,1,1,1,5667,2667,180,360,1,1,3,1 123 | 0,0,0,1,0,4166,0,44,360,1,1,2,0 124 | 0,0,0,1,0,2137,8980,137,360,0,0,2,0 125 | 1,1,2,1,1,2957,0,81,360,1,0,2,1 126 | 1,1,0,0,1,4300,2014,194,360,1,1,3,1 127 | 0,0,0,1,0,3692,0,93,360,1,1,3,0 128 | 0,1,3,1,1,23803,0,370,360,1,1,3,1 129 | 1,0,0,1,0,3865,1640,146,360,1,1,3,0 130 | 1,1,1,1,1,10513,3850,160,180,0,1,1,1 131 | 1,1,0,1,1,6080,2569,182,360,1,1,3,1 132 | 1,0,0,1,1,20166,0,650,480,1,0,1,0 133 | 1,0,0,1,0,2014,1929,74,360,1,0,1,0 134 | 1,0,0,1,0,2718,0,70,360,1,1,2,0 135 | 1,1,0,1,1,3459,0,25,120,1,0,2,1 136 | 1,0,0,1,0,4895,0,102,360,1,1,2,0 137 | 1,1,3,1,1,4000,7750,290,360,1,1,2,1 138 | 0,1,0,1,1,4583,0,84,360,1,1,3,1 139 | 1,1,2,1,1,3316,3500,88,360,1,1,1,1 140 | 1,0,0,1,0,14999,0,242,360,0,0,2,1 141 | 1,1,2,0,1,4200,1430,129,360,1,1,3,1 142 | 1,1,2,1,1,5042,2083,185,360,1,0,3,1 143 | 1,0,0,1,0,5417,0,168,360,1,0,1,0 144 | 1,0,0,1,1,6950,0,175,180,1,1,2,0 145 | 1,1,0,1,1,2698,2034,122,360,1,0,2,1 146 | 1,1,2,1,1,11757,0,187,180,1,1,1,1 147 | 0,1,0,1,1,2330,4486,100,360,1,0,2,1 148 | 0,1,2,1,1,14866,0,70,360,1,0,1,1 149 | 1,1,1,1,1,1538,1425,30,360,1,0,1,1 150 | 0,0,0,1,0,10000,1666,225,360,1,1,3,1 151 | 1,1,0,1,1,4860,830,125,360,1,1,2,1 152 | 1,0,0,1,0,6277,0,118,360,0,1,3,1 153 | 1,1,0,1,1,2577,3750,152,360,1,1,3,1 154 | 1,0,0,1,0,9166,0,244,360,1,1,1,1 155 | 1,1,2,0,1,2281,0,113,360,1,0,3,1 156 | 1,0,0,1,0,3254,0,50,360,1,1,1,0 157 | 1,1,3,1,1,39999,0,600,180,0,0,2,1 158 | 1,1,1,1,1,6000,0,160,360,1,1,3,1 159 | 1,1,1,1,1,9538,0,187,360,1,1,1,1 160 | 1,0,0,1,1,2980,2083,120,360,1,1,3,0 161 | 1,1,0,1,1,4583,5625,255,360,1,0,2,1 162 | 1,1,0,0,1,1863,1041,98,360,1,0,2,1 163 | 1,1,0,1,1,7933,0,275,360,1,1,1,1 164 | 1,1,1,1,1,3089,1280,121,360,0,0,2,1 165 | 1,1,2,1,1,4167,1447,158,360,1,1,3,1 166 | 1,1,0,1,1,9323,0,75,180,1,0,1,1 167 | 1,1,0,1,1,3707,3166,182,12,1,0,3,1 168 | 0,1,0,1,1,4583,0,112,360,1,1,3,1 169 | 1,1,0,1,1,2439,3333,129,360,1,0,3,1 170 | 1,0,0,1,0,2237,0,63,480,0,1,2,1 171 | 1,1,2,1,1,8000,0,200,360,1,1,2,1 172 | 1,1,0,0,1,1820,1769,95,360,1,0,3,1 173 | 0,1,3,1,1,51763,0,700,300,1,0,1,1 174 | 1,1,3,0,1,3522,0,81,180,1,1,3,1 175 | 1,1,0,1,1,5708,5625,187,360,1,0,2,1 176 | 1,1,0,0,1,4344,736,87,360,1,1,2,1 177 | 1,1,0,1,1,3497,1964,116,360,1,1,3,1 178 | 1,1,2,1,1,2045,1619,101,360,1,1,3,1 179 | 1,1,3,1,1,5516,11300,495,360,0,1,2,1 180 | 1,1,1,1,1,3750,0,116,360,1,1,2,1 181 | 1,0,0,0,0,2333,1451,102,480,0,1,1,1 182 | 1,1,1,1,1,6400,7250,180,360,0,1,1,1 183 | 1,0,0,1,0,1916,5063,67,360,1,1,3,1 184 | 1,1,0,1,1,4600,0,73,180,1,1,2,1 185 | 1,1,1,1,1,33846,0,260,360,1,0,2,1 186 | 0,1,0,1,1,3625,0,108,360,1,1,2,1 187 | 1,1,0,1,1,39147,4750,120,360,1,0,2,1 188 | 1,1,1,1,1,2178,0,66,300,0,1,3,1 189 | 1,1,0,1,1,2383,2138,58,360,1,1,3,1 190 | 0,1,0,1,1,674,5296,168,360,1,1,3,1 191 | 1,1,0,1,1,9328,0,188,180,1,1,3,1 192 | 1,0,0,0,0,4885,0,48,360,1,1,3,0 193 | 1,0,0,1,0,12000,0,164,360,1,0,2,1 194 | 1,1,0,0,1,6033,0,160,360,1,1,1,1 195 | 1,0,0,1,0,3858,0,76,360,1,1,2,0 196 | 1,0,0,1,0,4191,0,120,360,1,1,3,0 197 | 1,1,1,1,1,3125,2583,170,360,1,0,2,1 198 | 1,0,0,1,0,8333,3750,187,360,1,1,3,0 199 | 0,0,0,0,0,1907,2365,120,12,1,1,1,0 200 | 0,1,0,1,1,3416,2816,113,360,1,1,2,1 201 | 1,0,0,1,1,11000,0,83,360,1,1,1,1 202 | 1,1,1,0,1,2600,2500,90,360,1,1,2,1 203 | 1,0,2,1,0,4923,0,166,360,0,1,2,0 204 | 1,1,3,0,1,3992,0,146,180,1,1,1,1 205 | 1,1,1,0,1,3500,1083,135,360,1,1,1,1 206 | 1,1,2,0,1,3917,0,124,360,1,0,2,1 207 | 0,0,0,0,0,4408,0,120,360,1,0,2,0 208 | 0,0,0,1,0,3244,0,80,360,1,0,1,0 209 | 1,0,0,0,0,3975,2531,55,360,1,1,3,0 210 | 1,0,0,1,0,2479,0,59,360,1,1,1,0 211 | 1,0,0,1,0,3418,0,127,360,1,1,2,1 212 | 0,0,0,1,0,10000,0,214,360,1,1,2,1 213 | 1,1,3,1,1,3430,1250,128,360,0,1,2,1 214 | 1,1,1,1,1,7787,0,240,360,1,1,1,1 215 | 1,1,3,0,1,5703,0,130,360,1,1,3,1 216 | 1,1,0,1,1,3173,3021,137,360,1,1,1,1 217 | 1,1,3,0,1,3850,983,100,360,1,1,2,1 218 | 1,1,0,1,1,150,1800,135,360,1,1,3,1 219 | 1,1,0,1,1,3727,1775,131,360,1,0,2,1 220 | 1,1,2,1,1,5000,0,72,360,0,0,2,1 221 | 0,1,2,1,1,4283,2383,127,360,1,1,2,1 222 | 1,1,0,1,1,2221,0,60,360,0,1,1,1 223 | 1,1,2,1,1,4009,1717,116,360,1,1,2,1 224 | 1,0,0,1,0,2971,2791,144,360,1,0,2,0 225 | 1,1,0,1,1,7578,1010,175,12,1,1,2,1 226 | 1,1,0,1,1,6250,0,128,360,1,1,2,1 227 | 1,1,0,1,1,3250,0,170,360,1,1,3,1 228 | 1,1,1,0,1,4735,0,138,360,1,0,1,1 229 | 1,1,2,1,1,6250,1695,210,360,1,1,2,1 230 | 1,0,1,1,0,4758,0,158,480,1,1,2,0 231 | 1,0,0,1,1,6400,0,200,360,1,0,3,0 232 | 1,1,1,1,1,2491,2054,104,360,1,1,2,1 233 | 1,1,0,1,1,3716,0,42,180,1,1,3,1 234 | 1,0,0,0,0,3189,2598,120,12,1,1,3,0 235 | 0,0,0,1,0,8333,0,280,360,1,0,2,0 236 | 1,1,1,1,1,3155,1779,140,360,1,0,2,1 237 | 1,1,1,1,1,5500,1260,170,360,1,1,3,1 238 | 1,1,0,1,1,5746,0,255,360,1,0,1,1 239 | 0,0,0,1,1,3463,0,122,360,1,1,1,0 240 | 0,0,1,1,0,3812,0,112,360,1,1,3,0 241 | 1,1,1,1,1,3315,0,96,360,1,0,2,1 242 | 1,1,2,1,1,5819,5000,120,360,1,0,3,1 243 | 1,1,1,0,1,2510,1983,140,180,1,0,1,1 244 | 1,0,0,1,0,2965,5701,155,60,1,0,1,0 245 | 1,1,2,1,1,6250,1300,108,360,1,1,3,1 246 | 1,1,0,0,1,3406,4417,123,360,1,0,2,1 247 | 1,0,0,1,1,6050,4333,120,180,1,0,1,1 248 | 1,1,2,1,1,9703,0,112,360,1,1,1,1 249 | 1,1,1,0,1,6608,0,137,180,1,0,1,1 250 | 1,1,1,1,1,2882,1843,123,480,1,1,2,1 251 | 1,1,0,1,1,1809,1868,90,360,1,1,1,1 252 | 1,1,0,0,1,1668,3890,201,360,0,0,2,1 253 | 0,0,2,1,0,3427,0,138,360,1,1,1,1 254 | 1,0,0,0,1,2583,2167,104,360,1,0,3,0 255 | 1,1,1,0,1,2661,7101,279,180,1,1,2,1 256 | 1,0,0,1,1,16250,0,192,360,0,0,1,1 257 | 0,0,3,1,0,3083,0,255,360,1,1,3,0 258 | 1,0,0,0,0,6045,0,115,360,0,1,3,1 259 | 1,1,3,1,1,5250,0,94,360,1,1,1,1 260 | 1,1,0,1,1,14683,2100,304,360,1,1,3,1 261 | 1,1,3,0,1,4931,0,128,360,1,1,2,1 262 | 1,1,1,1,1,6083,4250,330,360,1,1,1,1 263 | 1,0,0,1,0,2060,2209,134,360,1,1,2,0 264 | 0,0,1,1,0,3481,0,155,36,1,1,2,1 265 | 0,0,0,1,0,7200,0,120,360,1,1,3,0 266 | 1,0,0,1,1,5166,0,128,360,1,1,2,0 267 | 1,0,0,1,0,4095,3447,151,360,1,1,3,0 268 | 1,1,2,1,1,4708,1387,150,360,1,1,2,1 269 | 1,1,3,1,1,4333,1811,160,360,0,1,1,1 270 | 0,0,0,1,1,3418,0,135,360,1,0,3,1 271 | 0,0,1,1,0,2876,1560,90,360,1,1,1,0 272 | 0,0,0,1,0,3237,0,30,360,1,0,1,0 273 | 1,1,0,1,1,11146,0,136,360,1,1,1,1 274 | 1,0,0,1,0,2833,1857,126,360,1,1,3,0 275 | 1,1,0,1,1,2620,2223,150,360,1,0,2,1 276 | 1,1,2,1,1,3900,0,90,360,1,1,2,1 277 | 1,1,1,1,1,2750,1842,115,360,1,1,2,1 278 | 1,1,0,1,1,3993,3274,207,360,1,0,2,1 279 | 1,1,0,1,1,3103,1300,80,360,1,1,1,1 280 | 1,1,0,1,1,14583,0,436,360,1,1,2,1 281 | 0,1,0,0,1,4100,0,124,360,1,0,3,1 282 | 1,0,1,0,1,4053,2426,158,360,0,0,1,1 283 | 1,1,0,1,1,3927,800,112,360,1,1,2,1 284 | 1,1,2,1,1,2301,986,78,180,1,0,1,1 285 | 0,0,0,1,0,1811,1666,54,360,1,0,1,0 286 | 1,1,0,1,1,20667,0,146,360,1,0,3,1 287 | 1,0,0,1,0,3158,3053,89,360,1,1,3,0 288 | 0,0,0,1,1,2600,1717,99,300,1,0,2,1 289 | 1,1,0,1,1,3704,2000,120,360,1,1,3,1 290 | 0,0,0,1,0,4124,0,115,360,1,0,2,0 291 | 1,0,0,1,0,9508,0,187,360,1,0,3,0 292 | 1,1,0,1,1,3075,2416,139,360,1,1,3,1 293 | 1,1,2,1,1,4400,0,127,360,0,1,2,1 294 | 1,1,2,1,1,3153,1560,134,360,1,1,1,1 295 | 0,0,1,1,0,5417,0,143,480,0,1,1,1 296 | 1,1,0,1,1,2383,3334,172,360,1,1,2,1 297 | 1,1,3,1,1,4416,1250,110,360,1,1,1,1 298 | 1,1,1,1,1,6875,0,200,360,1,1,2,1 299 | 0,1,1,1,1,4666,0,135,360,1,1,1,1 300 | 0,0,0,1,0,5000,2541,151,480,1,1,3,1 301 | 1,1,1,1,1,2014,2925,113,360,1,1,1,1 302 | 1,1,0,0,1,1800,2934,93,360,0,0,1,1 303 | 1,1,1,0,1,2875,1750,105,360,1,1,2,1 304 | 0,0,0,1,0,5000,0,132,360,1,1,3,0 305 | 1,1,1,1,1,1625,1803,96,360,1,1,1,1 306 | 1,0,0,1,0,4000,2500,140,360,1,1,3,0 307 | 1,0,0,0,0,2000,0,146,360,1,1,1,1 308 | 0,0,0,1,0,3762,1666,135,360,1,1,3,0 309 | 0,0,0,1,0,2400,1863,104,360,0,1,1,1 310 | 1,0,0,1,0,20233,0,480,360,1,0,3,1 311 | 1,1,2,0,1,7667,0,185,360,1,1,3,1 312 | 0,0,0,1,0,2917,0,84,360,1,1,2,0 313 | 1,0,0,0,0,2927,2405,111,360,1,1,2,0 314 | 0,0,0,1,0,2507,0,56,360,1,1,3,0 315 | 1,1,2,1,1,5746,0,144,84,1,0,3,1 316 | 0,1,0,1,1,2473,1843,159,360,1,1,3,1 317 | 1,1,1,0,1,3399,1640,111,180,1,1,1,1 318 | 1,1,2,1,1,3717,0,120,360,1,1,2,1 319 | 1,1,0,1,1,2058,2134,88,360,1,0,1,1 320 | 0,0,1,1,0,3541,0,112,360,1,0,2,0 321 | 1,1,1,1,1,10000,0,155,360,1,0,3,1 322 | 1,1,0,1,1,2400,2167,115,360,1,0,2,1 323 | 1,1,3,1,1,4342,189,124,360,1,1,2,1 324 | 1,1,2,0,1,3601,1590,146,360,1,0,3,1 325 | 0,0,0,1,0,3166,2985,132,360,1,1,3,0 326 | 1,1,3,1,1,15000,0,300,360,1,0,3,1 327 | 1,1,1,1,1,8666,4983,376,360,0,1,3,1 328 | 1,0,0,1,0,4917,0,130,360,0,1,3,0 329 | 1,1,0,1,1,5818,2160,184,360,1,0,2,1 330 | 0,1,0,1,1,4333,2451,110,360,1,0,1,1 331 | 0,0,0,1,0,2500,0,67,360,1,0,1,0 332 | 1,0,1,1,0,4384,1793,117,360,1,0,1,0 333 | 1,0,0,1,0,2935,0,98,360,1,1,2,0 334 | 1,0,1,1,0,2833,0,71,360,1,1,1,0 335 | 1,1,0,1,1,63337,0,490,180,1,1,1,1 336 | 0,1,1,1,1,9833,1833,182,180,1,0,1,1 337 | 1,1,1,1,1,5503,4490,70,12,1,1,2,1 338 | 1,1,1,1,1,5250,688,160,360,1,0,3,1 339 | 1,1,2,1,1,2500,4600,176,360,1,1,3,1 340 | 0,0,3,0,0,1830,0,146,360,0,1,1,1 341 | 0,0,0,1,0,4160,0,71,360,1,0,2,0 342 | 1,1,3,0,1,2647,1587,173,360,1,1,3,1 343 | 0,0,0,1,0,2378,0,46,360,1,1,3,1 344 | 1,1,1,0,1,4554,1229,158,360,1,0,1,1 345 | 1,1,3,0,1,3173,0,74,360,1,1,2,1 346 | 1,1,2,1,1,2583,2330,125,360,1,1,3,1 347 | 1,1,0,1,1,2499,2458,160,360,1,1,2,1 348 | 1,1,1,0,1,3523,3230,152,360,0,0,3,1 349 | 1,1,2,0,1,3083,2168,126,360,1,0,1,1 350 | 1,1,0,1,1,6333,4583,259,360,1,0,2,1 351 | 1,1,0,1,1,2625,6250,187,360,1,1,3,1 352 | 1,1,0,1,1,9083,0,228,360,1,0,2,1 353 | 1,0,0,1,0,8750,4167,308,360,1,1,3,1 354 | 1,1,3,1,1,2666,2083,95,360,1,1,3,1 355 | 0,1,0,1,1,5500,0,105,360,0,0,3,1 356 | 0,1,0,1,1,2423,505,130,360,1,1,2,1 357 | 0,0,1,1,0,3813,0,116,180,1,0,1,0 358 | 1,1,2,1,1,8333,3167,165,360,1,1,3,1 359 | 1,1,1,1,1,3875,0,67,360,1,1,1,1 360 | 1,1,0,0,1,3000,1666,100,480,0,1,1,1 361 | 1,1,3,1,1,5167,3167,200,360,1,1,2,1 362 | 0,0,1,1,0,4723,0,81,360,1,0,2,1 363 | 1,1,2,1,1,5000,3667,236,360,1,0,2,1 364 | 1,1,0,1,1,4750,2333,130,360,1,1,1,1 365 | 1,1,0,1,1,3013,3033,95,300,1,1,1,1 366 | 1,0,0,1,1,6822,0,141,360,1,0,3,0 367 | 1,0,0,0,0,6216,0,133,360,1,1,3,1 368 | 1,0,0,1,0,2500,0,96,480,1,1,2,1 369 | 1,0,0,1,0,5124,0,124,12,0,0,3,1 370 | 1,1,1,1,1,6325,0,175,360,1,1,2,1 371 | 1,1,0,1,1,19730,5266,570,360,1,1,3,1 372 | 0,0,0,1,1,15759,0,55,360,1,1,2,0 373 | 1,1,2,1,1,5185,0,155,360,1,1,2,1 374 | 1,1,2,1,1,9323,7873,380,300,1,1,3,1 375 | 1,0,1,1,0,3062,1987,111,180,0,1,1,1 376 | 0,0,0,1,1,2764,1459,110,360,1,1,1,0 377 | 1,1,0,1,1,4817,923,120,180,1,0,1,1 378 | 1,1,3,1,1,8750,4996,130,360,1,1,3,1 379 | 1,1,0,1,1,4310,0,130,360,1,1,2,1 380 | 1,0,0,1,0,3069,0,71,480,1,1,1,1 381 | 1,1,2,1,1,5391,0,130,360,1,0,1,1 382 | 1,1,0,1,1,3333,2500,128,360,1,1,2,1 383 | 1,0,0,1,0,5941,4232,296,360,1,1,2,0 384 | 0,0,0,1,0,6000,0,156,360,1,1,1,0 385 | 1,0,0,1,1,7167,0,128,360,1,1,1,0 386 | 1,1,2,1,1,4566,0,100,360,1,1,1,1 387 | 1,0,1,1,1,3667,0,113,180,1,1,1,0 388 | 1,0,0,0,0,2346,1600,132,360,1,1,2,0 389 | 1,1,0,0,1,3010,3136,146,360,0,1,1,1 390 | 1,1,0,1,1,2333,2417,136,360,1,0,1,1 391 | 1,1,0,1,1,5488,0,125,360,1,0,3,1 392 | 1,0,3,1,0,9167,0,185,360,1,0,3,0 393 | 1,1,3,1,1,9504,0,275,360,1,1,3,1 394 | 1,1,0,1,1,2583,2115,120,360,1,1,1,1 395 | 1,1,2,0,1,1993,1625,113,180,1,1,2,1 396 | 1,1,2,1,1,3100,1400,113,360,1,1,1,1 397 | 1,1,2,1,1,3276,484,135,360,1,0,2,1 398 | 0,0,0,1,0,3180,0,71,360,0,0,1,1 399 | 1,1,0,1,1,3033,1459,95,360,1,1,1,1 400 | 1,0,0,0,0,3902,1666,109,360,1,1,3,0 401 | 0,0,0,1,0,1500,1800,103,360,0,1,2,1 402 | 1,1,2,0,1,2889,0,45,180,0,1,1,1 403 | 1,0,0,0,0,2755,0,65,300,1,0,3,1 404 | 1,0,0,1,0,2500,20000,103,360,1,1,2,0 405 | 0,0,0,0,0,1963,0,53,360,1,1,2,0 406 | 0,0,0,1,1,7441,0,194,360,1,0,3,1 407 | 0,0,0,1,0,4547,0,115,360,1,1,2,0 408 | 1,1,0,0,1,2167,2400,115,360,1,1,1,1 409 | 0,0,0,0,0,2213,0,66,360,1,1,3,0 410 | 1,1,1,1,1,8300,0,152,300,0,1,2,1 411 | 1,1,3,1,1,81000,0,360,360,0,1,3,1 412 | 0,0,1,0,1,3867,0,62,360,1,1,2,1 413 | 1,1,0,1,1,6256,0,160,360,1,1,1,1 414 | 1,1,0,0,1,6096,0,218,360,0,1,3,1 415 | 1,1,0,0,1,2253,2033,110,360,1,1,3,1 416 | 0,1,0,0,1,2149,3237,178,360,0,0,2,1 417 | 0,0,0,1,0,2995,0,60,360,1,1,1,0 418 | 0,0,1,1,0,2600,0,160,360,1,0,1,1 419 | 1,1,2,1,1,1600,20000,239,360,1,1,1,1 420 | 1,1,0,1,1,1025,2773,112,360,1,0,3,1 421 | 1,1,0,1,1,3246,1417,138,360,1,1,2,1 422 | 1,1,0,1,1,5829,0,138,360,1,0,3,1 423 | 0,0,0,0,0,2720,0,80,12,0,1,1,1 424 | 1,1,0,1,1,1820,1719,100,360,1,0,1,1 425 | 1,1,1,1,1,7250,1667,110,12,0,0,1,1 426 | 1,1,0,1,1,14880,0,96,360,1,1,2,1 427 | 1,1,0,1,1,2666,4300,121,360,1,1,3,1 428 | 0,0,1,0,0,4606,0,81,360,1,1,3,1 429 | 1,1,2,1,1,5935,0,133,360,1,0,2,1 430 | 1,1,0,1,1,2920,16,87,360,1,1,3,1 431 | 1,0,0,0,0,2717,0,60,180,1,1,1,0 432 | 0,0,1,1,1,8624,0,150,360,1,1,2,0 433 | 1,0,0,1,0,6500,0,105,360,0,0,3,1 434 | 1,0,0,1,1,12876,0,405,360,1,1,2,0 435 | 1,1,0,1,1,2425,2340,143,360,1,1,2,1 436 | 1,0,0,1,0,3750,0,100,360,1,0,1,0 437 | 0,0,1,1,0,10047,0,146,240,1,0,2,0 438 | 1,0,0,1,0,1926,1851,50,360,1,0,2,0 439 | 1,1,0,1,1,2213,1125,146,360,1,1,1,1 440 | 1,0,0,1,1,10416,0,187,360,0,0,1,1 441 | 0,1,0,0,1,7142,0,138,360,1,0,3,1 442 | 1,0,0,1,0,3660,5064,187,360,1,1,2,0 443 | 1,1,0,1,1,7901,1833,180,360,1,0,3,1 444 | 1,0,3,0,0,4707,1993,148,360,1,0,2,0 445 | 1,0,1,1,0,37719,0,152,360,1,1,2,0 446 | 1,1,0,1,1,7333,8333,175,300,1,0,3,1 447 | 1,1,1,1,1,3466,1210,130,360,1,1,3,1 448 | 1,1,2,0,1,4652,0,110,360,1,0,3,1 449 | 1,1,0,1,1,3539,1376,55,360,1,0,3,1 450 | 1,1,2,1,1,3340,1710,150,360,0,1,3,1 451 | 1,0,1,0,1,2769,1542,190,360,1,1,2,1 452 | 1,1,2,0,1,2309,1255,125,360,0,1,3,1 453 | 1,1,2,0,1,1958,1456,60,300,1,0,1,1 454 | 1,1,0,1,1,3948,1733,149,360,0,1,3,1 455 | 1,1,0,1,1,2483,2466,90,180,0,1,3,1 456 | 1,0,0,1,1,7085,0,84,360,1,0,2,0 457 | 1,1,2,1,1,3859,0,96,360,1,1,2,1 458 | 1,1,0,1,1,4301,0,118,360,1,0,1,1 459 | 1,1,0,1,1,3708,2569,173,360,1,1,1,1 460 | 1,0,2,1,0,4354,0,136,360,1,0,3,0 461 | 1,1,0,1,1,8334,0,160,360,1,1,2,1 462 | 0,1,0,1,1,2083,4083,160,360,1,1,2,1 463 | 1,1,3,1,1,7740,0,128,180,1,1,1,1 464 | 1,1,0,1,1,3015,2188,153,360,1,0,3,1 465 | 0,0,1,0,1,5191,0,132,360,1,1,2,0 466 | 1,0,0,1,0,4166,0,98,360,0,0,2,1 467 | 1,0,0,1,0,6000,0,140,360,1,1,3,0 468 | 1,1,3,0,1,2947,1664,70,180,0,1,1,1 469 | 0,1,0,1,1,16692,0,110,360,1,0,2,1 470 | 0,1,2,0,1,210,2917,98,360,1,0,2,1 471 | 1,1,0,1,1,4333,2451,110,360,1,0,1,1 472 | 1,1,1,1,1,3450,2079,162,360,1,0,2,1 473 | 1,1,1,0,1,2653,1500,113,180,0,0,3,1 474 | 1,1,3,1,1,4691,0,100,360,1,1,2,1 475 | 0,0,0,1,1,2500,0,93,360,1,0,1,0 476 | 1,0,2,1,0,5532,4648,162,360,1,1,3,0 477 | 1,1,2,1,1,16525,1014,150,360,1,1,3,1 478 | 1,1,2,1,1,6700,1750,230,300,1,1,2,1 479 | 0,1,2,1,1,2873,1872,132,360,0,1,2,1 480 | 1,1,1,1,1,16667,2250,86,360,1,0,2,1 481 | 1,1,2,1,1,2947,1603,146,360,1,1,1,1 482 | 0,0,0,0,0,4350,0,154,360,1,0,3,0 483 | 1,1,3,0,1,3095,0,113,360,1,0,3,1 484 | 1,1,0,1,1,2083,3150,128,360,1,0,2,1 485 | 1,1,0,1,1,10833,0,234,360,1,1,2,1 486 | 1,1,2,1,1,8333,0,246,360,1,1,2,1 487 | 1,1,1,0,1,1958,2436,131,360,1,0,3,1 488 | 1,0,2,1,0,3547,0,80,360,0,1,3,1 489 | 1,1,1,1,1,18333,0,500,360,1,1,1,1 490 | 1,1,2,1,1,4583,2083,160,360,1,0,2,1 491 | 1,0,0,1,0,2435,0,75,360,1,0,1,1 492 | 1,0,0,0,0,2699,2785,96,360,1,0,2,0 493 | 1,1,1,0,1,5333,1131,186,360,1,0,1,1 494 | 1,0,0,0,0,3691,0,110,360,1,1,3,0 495 | 0,0,0,0,1,17263,0,225,360,1,1,2,0 496 | 1,1,0,1,1,3597,2157,119,360,0,0,3,1 497 | 0,1,1,1,1,3326,913,105,84,1,1,2,1 498 | 1,1,0,0,1,2600,1700,107,360,1,0,3,1 499 | 1,1,0,1,1,4625,2857,111,12,1,1,1,1 500 | 1,1,1,1,1,2895,0,95,360,1,1,2,1 501 | 1,0,0,1,0,6283,4416,209,360,0,1,3,1 502 | 0,0,0,1,0,645,3683,113,480,1,1,3,0 503 | 0,0,0,1,0,3159,0,100,360,1,1,2,0 504 | 1,1,2,1,1,4865,5624,208,360,1,1,2,1 505 | 1,1,1,0,1,4050,5302,138,360,1,0,3,1 506 | 1,1,0,0,1,3814,1483,124,300,1,0,2,1 507 | 1,1,2,1,1,3510,4416,243,360,1,1,3,1 508 | 1,1,0,1,1,20833,6667,480,360,1,0,1,1 509 | 0,0,0,1,0,3583,0,96,360,1,1,1,1 510 | 1,1,0,1,1,2479,3013,188,360,1,0,1,1 511 | 0,0,1,1,0,13262,0,40,360,1,1,1,0 512 | 1,0,0,0,0,3598,1287,100,360,1,0,3,1 513 | 1,1,1,1,1,6065,2004,250,360,1,1,2,1 514 | 1,1,2,1,1,3283,2035,148,360,1,1,1,1 515 | 1,1,0,1,1,2130,6666,70,180,1,1,2,1 516 | 1,0,0,1,0,5815,3666,311,360,1,0,3,1 517 | 1,1,3,1,1,3466,3428,150,360,1,1,3,1 518 | 0,1,2,1,1,2031,1632,113,480,1,1,2,1 519 | 1,1,1,0,1,3074,1800,123,360,0,1,2,1 520 | 1,0,0,1,0,4683,1915,185,360,1,1,2,1 521 | 0,0,0,0,0,3400,0,95,360,1,1,3,1 522 | 1,1,2,0,1,2192,1742,45,360,1,0,2,1 523 | 1,0,0,1,0,2500,0,55,360,1,1,2,0 524 | 1,1,3,1,1,5677,1424,100,360,1,0,3,1 525 | 1,1,2,1,1,7948,7166,480,360,1,1,3,1 526 | 1,0,0,1,0,4680,2087,146,360,1,1,2,1 527 | 1,1,2,1,1,17500,0,400,360,1,1,3,1 528 | 1,1,0,1,1,3775,0,110,360,1,1,2,1 529 | 1,1,1,0,1,5285,1430,161,360,0,1,2,1 530 | 1,0,1,0,0,2679,1302,94,360,1,0,2,0 531 | 1,0,0,0,0,6783,0,130,360,1,1,2,0 532 | 1,1,0,1,1,1025,5500,216,360,1,0,3,1 533 | 1,1,3,1,1,4281,0,100,360,1,0,1,1 534 | 1,0,2,1,0,3588,0,110,360,0,1,3,1 535 | 1,0,1,1,0,11250,0,196,360,1,1,2,1 536 | 0,0,0,0,1,18165,0,125,360,1,1,1,0 537 | 1,0,0,0,1,2550,2042,126,360,1,1,3,0 538 | 1,1,0,1,1,6133,3906,324,360,1,0,1,1 539 | 1,0,2,1,0,3617,0,107,360,1,0,2,0 540 | 1,1,0,0,1,2917,536,66,360,1,0,3,1 541 | 1,1,3,1,1,6417,0,157,180,1,1,3,1 542 | 0,1,1,1,1,4608,2845,140,180,1,0,2,1 543 | 0,0,0,1,0,2138,0,99,360,0,0,2,1 544 | 0,0,1,1,1,3652,0,95,360,1,1,2,0 545 | 1,1,1,0,1,2239,2524,128,360,1,1,1,1 546 | 0,1,0,0,1,3017,663,102,360,1,0,2,1 547 | 1,1,0,1,1,2768,1950,155,360,1,0,3,1 548 | 1,0,0,0,0,3358,0,80,36,1,0,2,1 549 | 1,0,0,1,0,2526,1783,145,360,1,0,3,0 550 | 0,0,0,1,0,5000,0,103,360,0,0,2,1 551 | 1,1,0,1,1,2785,2016,110,360,1,1,3,1 552 | 1,1,2,1,1,6633,0,146,360,0,1,3,1 553 | 1,1,1,0,1,2492,2375,146,360,1,1,3,1 554 | 1,1,1,1,1,3333,3250,158,360,1,1,1,1 555 | 1,1,0,0,1,2454,2333,181,360,0,1,1,1 556 | 1,1,0,1,1,3593,4266,132,180,0,1,3,1 557 | 1,1,1,1,1,5468,1032,26,360,1,1,2,1 558 | 0,0,0,1,0,2667,1625,84,360,1,0,1,0 559 | 1,1,3,1,1,10139,0,260,360,1,1,2,1 560 | 1,1,0,1,1,3887,2669,162,360,1,0,2,1 561 | 0,1,0,1,1,4180,2306,182,360,1,0,2,1 562 | 1,1,2,0,1,3675,242,108,360,1,1,2,1 563 | 0,1,1,1,1,19484,0,600,360,1,1,2,1 564 | 1,1,0,1,1,5923,2054,211,360,1,1,3,1 565 | 1,0,0,0,1,5800,0,132,360,1,1,2,0 566 | 1,1,2,1,1,8799,0,258,360,0,0,1,1 567 | 1,1,0,0,1,4467,0,120,360,1,1,3,1 568 | 1,0,0,1,0,3333,0,70,360,1,1,1,0 569 | 1,1,3,1,1,3400,2500,123,360,0,0,3,1 570 | 0,0,0,1,0,2378,0,9,360,1,1,1,1 571 | 1,1,0,1,1,3166,2064,104,360,0,0,1,1 572 | 1,1,1,1,1,3417,1750,186,360,1,0,1,1 573 | 1,1,1,1,1,5116,1451,165,360,0,1,1,1 574 | 1,1,2,1,1,16666,0,275,360,1,0,1,1 575 | 1,1,2,0,1,6125,1625,187,480,1,0,2,1 576 | 1,1,3,1,1,6406,0,150,360,1,0,2,1 577 | 1,1,2,1,1,3159,461,108,84,1,1,1,1 578 | 0,1,0,1,1,3087,2210,136,360,0,1,2,1 579 | 1,0,0,1,0,3229,2739,110,360,1,1,1,0 580 | 1,1,1,1,1,1782,2232,107,360,1,0,3,1 581 | 1,0,0,1,1,3182,2917,161,360,1,0,1,0 582 | 1,1,2,1,1,6540,0,205,360,1,1,2,1 583 | 1,0,0,1,0,1836,33837,90,360,1,1,1,1 584 | 0,1,0,1,1,3166,0,36,360,1,1,2,1 585 | 1,1,1,1,1,1880,0,61,360,1,1,3,1 586 | 1,1,1,1,1,2787,1917,146,360,0,1,3,1 587 | 1,1,1,1,1,4283,3000,172,84,1,1,3,1 588 | 1,1,0,1,1,2297,1522,104,360,1,1,1,1 589 | 0,0,0,0,0,2165,0,70,360,1,1,2,0 590 | 0,0,0,1,0,4750,0,94,360,1,1,2,0 591 | 1,1,2,1,1,2726,0,106,360,0,0,2,1 592 | 1,1,0,1,1,3000,3416,56,180,1,1,2,1 593 | 1,1,2,1,1,6000,0,205,240,1,0,2,1 594 | 0,0,3,1,1,9357,0,292,360,1,0,2,0 595 | 1,1,0,1,1,3859,3300,142,180,1,0,3,1 596 | 1,1,0,1,1,16120,0,260,360,1,0,1,1 597 | 1,0,0,0,0,3833,0,110,360,1,0,3,0 598 | 1,1,2,0,1,6383,1000,187,360,1,0,3,1 599 | 1,0,1,1,0,2987,0,88,360,0,1,2,1 600 | 1,1,0,1,1,9963,0,180,360,1,1,3,1 601 | 1,1,2,1,1,5780,0,192,360,1,0,1,1 602 | 0,0,3,1,1,416,41667,350,180,1,0,1,1 603 | 1,1,0,0,1,2894,2792,155,360,1,1,3,1 604 | 1,1,3,1,1,5703,0,128,360,1,0,1,1 605 | 1,0,0,1,0,3676,4301,172,360,1,1,3,0 606 | 0,1,1,1,1,12000,0,496,360,1,1,2,1 607 | 1,1,0,0,1,2400,3800,146,180,1,1,1,1 608 | 1,1,1,1,1,3400,2500,173,360,1,0,2,1 609 | 1,1,2,0,1,3987,1411,157,360,1,1,3,1 610 | 1,1,0,1,1,3232,1950,108,360,1,0,3,1 611 | 0,0,0,1,0,2900,0,71,360,1,0,3,0 612 | 1,1,3,1,1,4106,0,40,180,1,1,3,1 613 | 1,1,1,1,1,8072,240,253,360,1,0,1,1 614 | 1,1,2,1,1,7583,0,187,360,1,0,1,1 615 | 0,0,0,1,1,4583,0,133,360,0,1,2,1 616 | 0,0,1,1,1,7364,0,131,360,1,1,2,0 617 | 1,0,1,0,0,3615,0,104,224,1,1,1,0 618 | 0,0,2,1,0,3084,0,205,360,1,1,3,0 619 | 1,0,0,1,0,4987,0,122,360,1,1,1,0 620 | 0,0,0,1,0,8418,0,254,360,1,0,2,0 621 | 0,0,1,1,0,3884,2186,133,360,1,1,2,0 622 | 1,0,0,0,1,2561,2004,122,360,1,1,3,0 623 | 1,0,0,1,0,2829,6241,152,109,1,0,1,0 624 | 0,0,1,1,0,4485,0,122,360,1,1,2,0 625 | 0,0,0,1,0,3215,0,87,360,1,0,1,0 626 | 0,0,0,1,0,4998,0,132,360,1,1,3,0 627 | 1,0,0,1,0,3185,11174,153,360,1,1,2,0 628 | 1,0,0,1,0,5587,4095,249,360,1,1,2,0 629 | 1,0,0,1,0,4917,0,131,360,0,1,3,0 630 | 0,0,0,1,0,5154,0,134,360,1,1,2,0 631 | 0,0,0,1,0,4788,0,102,360,1,1,2,0 632 | 1,0,0,0,0,3889,1657,122,360,1,1,3,0 633 | 0,0,0,1,0,4774,0,86,360,1,1,2,0 634 | 1,0,0,1,0,2621,1806,139,360,1,0,3,0 635 | 0,0,1,1,0,3757,1827,129,360,1,1,3,0 636 | 0,0,0,1,0,10564,0,268,360,1,0,1,0 637 | 0,0,0,1,1,15363,0,103,360,1,1,2,0 638 | 1,0,0,1,0,2929,0,93,360,1,1,2,0 639 | 1,0,0,1,0,8015,3852,184,360,1,1,3,0 640 | 1,0,0,1,0,1936,1878,56,360,1,0,2,0 641 | 1,0,0,1,1,6838,0,145,338,1,0,3,0 642 | 1,0,1,1,0,3282,16040,118,360,1,1,2,0 643 | 1,0,0,0,0,2164,1622,105,360,1,1,2,0 644 | 1,0,0,0,0,3748,1744,112,360,1,0,2,0 645 | 1,0,0,1,0,3391,0,93,360,1,1,1,0 646 | 1,0,0,1,0,2843,2788,121,360,1,0,2,0 647 | 0,0,0,0,0,2282,0,63,360,1,1,3,0 648 | 1,0,0,1,0,3511,0,83,306,1,1,2,0 649 | 1,0,0,1,0,3674,4379,174,360,1,1,3,0 650 | 1,0,0,1,0,2932,0,95,360,1,1,2,0 651 | 1,0,0,1,0,2957,0,84,360,1,1,2,0 652 | 1,0,0,1,0,4245,0,132,360,1,1,3,0 653 | 1,0,0,0,0,2779,2652,101,360,1,0,2,0 654 | 0,0,1,1,1,3663,0,99,360,1,1,2,0 655 | 1,0,0,0,0,2954,2425,112,324,1,1,2,0 656 | 0,0,1,1,1,8785,0,150,346,1,1,2,0 657 | 1,0,0,0,0,3894,1660,117,360,1,1,3,0 658 | 0,0,0,1,0,2582,0,57,296,1,1,2,0 659 | 1,0,0,1,0,3224,2760,112,360,1,1,1,0 660 | 0,0,2,1,1,3790,2114,124,360,1,1,2,0 661 | 0,0,0,1,0,3245,0,77,360,1,0,1,0 662 | 1,0,1,1,0,2993,0,160,360,1,1,2,0 663 | 1,0,0,1,0,2936,0,98,360,1,1,2,0 664 | 1,0,0,0,0,6787,0,131,360,1,1,2,0 665 | 0,0,0,1,0,3163,3008,118,360,1,1,3,0 666 | 1,0,0,1,0,4950,0,125,360,1,1,1,0 667 | 1,0,0,0,0,3154,2629,124,68,1,1,3,0 668 | 0,0,0,1,0,2908,0,77,360,1,0,3,0 669 | 0,0,0,1,0,3022,2923,121,360,1,1,3,0 670 | 1,0,0,1,0,3497,2656,120,360,1,1,2,0 671 | 1,0,1,1,0,3820,585,149,360,1,0,1,0 672 | 1,0,0,1,0,3160,3033,101,360,1,1,3,0 673 | 1,0,0,0,0,4016,1696,111,360,1,1,3,0 674 | 0,0,0,1,0,5951,0,153,360,1,1,1,0 675 | 1,0,0,0,0,2240,1664,111,360,1,1,2,0 676 | 1,0,1,1,0,4161,1749,115,360,1,0,1,0 677 | 1,0,2,1,0,4362,0,134,360,1,0,3,0 678 | 1,0,1,1,1,3651,0,83,159,1,1,1,0 679 | 1,0,0,1,0,2510,2641,119,360,1,1,2,0 680 | 1,0,0,1,0,2941,0,94,360,1,1,2,0 681 | 1,0,0,1,0,5905,0,144,360,1,1,1,0 682 | 1,0,0,1,0,2975,0,104,360,1,1,2,0 683 | 1,0,0,0,0,3691,0,106,360,1,1,3,0 684 | 0,0,0,1,0,5001,0,132,360,1,1,3,0 685 | 0,0,0,1,0,2964,0,69,360,1,1,1,0 686 | 0,0,1,1,0,3812,0,112,341,1,1,3,0 687 | 1,0,1,1,0,4353,0,143,360,1,0,3,0 688 | 1,0,0,1,1,7057,0,103,323,1,0,2,0 689 | 1,0,1,1,0,4937,0,145,360,1,1,1,0 690 | 1,0,0,0,0,2781,2304,108,360,1,1,2,0 691 | 0,0,2,1,0,3084,0,189,360,1,1,3,0 692 | 1,0,0,1,0,2429,17848,110,360,1,1,2,0 693 | 0,0,0,0,0,2144,0,62,360,1,1,3,0 694 | 0,0,0,1,1,3473,0,110,343,1,1,1,0 695 | 0,0,1,1,0,2873,1558,90,360,1,1,1,0 696 | 0,0,1,1,1,3839,2231,127,360,1,1,2,0 697 | 0,0,1,1,0,3085,0,144,360,1,0,2,0 698 | 0,0,0,1,0,3999,2290,139,360,1,1,2,0 699 | 0,0,0,1,0,4127,0,115,360,1,0,2,0 700 | 1,0,0,1,0,2699,0,70,360,1,1,2,0 701 | 1,0,0,1,1,11829,0,309,316,1,1,2,0 702 | 0,0,0,1,0,3413,0,87,14,1,0,1,0 703 | 0,0,1,0,1,5207,0,135,360,1,1,2,0 704 | 1,0,0,1,0,4993,0,122,360,1,1,1,0 705 | 1,0,0,0,0,3696,0,110,360,1,1,3,0 706 | 1,0,0,1,1,20805,0,632,476,1,0,1,0 707 | 0,0,2,1,1,3752,2022,122,360,1,1,2,0 708 | 0,0,1,1,0,3670,0,97,360,1,1,3,0 709 | 1,0,0,1,0,3130,2759,123,360,1,1,1,0 710 | 0,0,0,0,0,2000,0,55,360,1,1,2,0 711 | 0,0,0,1,0,3850,0,100,360,1,1,2,0 712 | 1,0,0,1,1,18996,0,547,460,1,0,1,0 713 | 1,0,0,0,0,3796,0,106,360,1,0,2,0 714 | 1,0,0,1,0,2480,0,59,360,1,1,1,0 715 | 0,0,0,1,0,2891,0,80,360,1,1,2,0 716 | 1,0,0,0,0,3752,0,110,360,1,1,3,0 717 | 0,0,0,1,1,2741,1490,113,360,1,1,1,0 718 | 0,0,0,1,0,5064,0,130,360,1,1,3,0 719 | 0,0,0,1,1,2500,0,93,360,1,0,1,0 720 | 0,0,1,1,1,8748,0,155,360,1,1,2,0 721 | 0,0,0,1,0,4754,0,125,418,1,1,2,0 722 | 1,0,0,0,0,3594,0,33,107,1,1,2,0 723 | 0,0,0,1,0,2663,8521,149,360,0,0,2,0 724 | 1,0,1,1,0,4227,1747,126,360,1,0,2,0 725 | 1,0,1,1,0,4919,0,141,360,0,1,3,0 726 | 1,0,0,0,0,3803,1667,110,360,1,0,2,0 727 | 0,0,1,1,0,3927,2219,137,360,1,1,2,0 728 | 0,0,3,1,1,9489,0,264,337,1,0,2,0 729 | 1,0,0,1,1,6926,0,169,214,1,1,2,0 730 | 0,0,1,1,0,13794,0,65,360,1,1,1,0 731 | 1,0,0,1,1,5073,0,120,360,1,0,2,0 732 | 0,0,0,1,0,2949,0,65,360,1,1,2,0 733 | 0,0,0,1,0,2504,0,74,360,1,1,2,0 734 | 1,0,0,1,0,2776,1894,126,360,1,1,3,0 735 | 0,0,0,0,0,2125,0,61,360,1,1,3,0 736 | 0,0,0,1,0,3266,0,42,360,1,0,1,0 737 | 1,0,0,1,0,5505,0,164,360,1,0,1,0 738 | 0,0,2,1,1,3775,2132,113,360,1,1,2,0 739 | 0,0,2,1,0,9814,0,195,281,1,0,2,0 740 | 0,0,0,1,0,4150,0,90,360,1,0,2,0 741 | 1,0,1,1,0,2843,0,74,360,1,1,1,0 742 | 0,0,0,0,0,4374,0,140,360,1,0,3,0 743 | 1,0,0,1,0,4954,0,125,360,1,1,1,0 744 | 1,0,1,1,0,4668,4486,167,360,1,1,3,0 745 | 0,0,0,0,0,2073,0,62,360,1,1,2,0 746 | 0,0,0,0,1,16006,0,277,360,1,1,2,0 747 | 1,0,0,1,0,3213,2681,114,218,1,1,2,0 748 | 1,0,0,0,0,2714,2789,98,360,1,0,2,0 749 | 1,0,0,1,0,5320,0,137,360,1,1,1,0 750 | 0,0,0,1,0,2544,0,57,328,1,1,3,0 751 | 1,0,0,1,1,6868,0,153,295,1,0,3,0 752 | 1,0,1,1,0,4757,0,150,465,1,1,2,0 753 | 1,0,0,0,0,3186,2750,140,178,1,1,2,0 754 | 1,0,0,1,0,2867,1909,125,360,1,1,3,0 755 | 1,0,0,1,0,6000,0,140,360,1,1,3,0 756 | 0,0,0,1,0,1807,1495,51,360,1,0,1,0 757 | 1,0,1,1,0,35632,0,142,360,1,1,2,0 758 | 1,0,0,1,0,5437,0,166,360,1,0,1,0 759 | 1,0,0,1,1,3185,2768,142,197,1,0,2,0 760 | 1,0,0,1,0,4439,3612,151,360,1,1,3,0 761 | 1,0,0,1,0,1742,2949,128,404,1,1,2,0 762 | 1,0,0,1,0,2925,0,91,360,1,1,2,0 763 | 0,0,0,0,0,4407,0,121,360,1,0,2,0 764 | 0,0,1,1,0,15197,0,129,360,1,1,1,0 765 | 1,0,0,1,0,3214,2796,126,360,1,1,1,0 766 | 0,0,0,1,0,2553,8617,147,360,0,0,2,0 767 | 1,0,2,1,0,3611,0,105,328,1,0,2,0 768 | 0,0,1,0,0,4352,0,146,360,1,0,3,0 769 | 1,0,0,1,0,3940,2519,138,360,1,1,3,0 770 | 0,0,0,1,0,4999,0,132,360,1,1,3,0 771 | 1,0,0,1,0,5431,0,167,360,1,0,1,0 772 | 1,0,0,1,0,2000,1916,70,360,1,0,1,0 773 | 0,0,0,1,0,2971,0,67,360,1,1,1,0 774 | 0,0,0,0,0,2322,0,63,360,1,1,2,0 775 | 1,0,1,1,0,4757,0,147,459,1,1,2,0 776 | 1,0,0,1,0,4216,0,125,360,1,1,3,0 777 | 1,0,0,1,0,2539,0,62,360,1,1,1,0 778 | 0,0,0,1,0,4042,1723,127,360,1,1,2,0 779 | 0,0,0,1,0,2505,0,59,360,1,1,2,0 780 | 0,0,1,1,1,7366,0,137,360,1,1,2,0 781 | 0,0,0,1,0,2628,1669,101,360,1,0,2,0 782 | 1,0,0,0,1,2549,2030,127,360,1,1,3,0 783 | 1,0,0,1,0,3766,0,103,360,1,0,2,0 784 | 0,0,0,1,1,2503,0,77,360,1,0,2,0 785 | 0,0,0,1,0,2278,13259,124,360,0,0,2,0 786 | 0,0,0,1,1,16390,0,126,360,1,1,2,0 787 | 1,0,0,1,0,3211,2817,105,360,1,1,1,0 788 | 1,0,0,1,0,3183,2941,96,360,1,1,2,0 789 | 1,0,0,1,0,3994,3654,156,360,1,1,3,0 790 | 1,0,0,1,0,2482,0,59,360,1,1,1,0 791 | 1,0,1,1,0,4777,0,159,466,1,1,2,0 792 | 0,0,0,1,0,2904,0,70,360,1,0,3,0 793 | 0,0,0,1,0,4757,0,95,360,1,1,2,0 794 | 0,0,0,1,0,4988,0,132,360,1,1,3,0 795 | 0,0,1,1,0,3818,0,111,360,1,1,3,0 796 | 0,0,0,0,1,17024,0,92,360,1,1,1,0 797 | 0,0,0,0,0,2189,0,65,360,1,1,3,0 798 | 1,0,1,1,0,4836,0,144,421,1,1,2,0 799 | 0,0,1,1,0,9910,0,275,360,1,0,1,0 800 | 1,0,0,1,0,3740,0,102,360,1,0,1,0 801 | 1,0,0,0,0,2485,1611,111,360,1,1,2,0 802 | 1,0,0,0,0,2891,2838,122,360,1,0,2,0 803 | 1,0,0,1,0,2737,1976,118,360,1,1,3,0 804 | 1,0,0,1,0,2307,1808,110,360,1,0,3,0 805 | 1,0,0,1,0,2934,0,97,360,1,1,2,0 806 | 1,0,0,1,0,2922,0,88,360,1,1,2,0 807 | 0,0,2,1,1,9750,0,280,360,1,0,2,0 808 | 1,0,0,1,0,2692,1949,126,360,1,1,3,0 809 | 0,0,1,1,0,3557,0,110,360,1,0,2,0 810 | 1,0,1,1,1,3651,0,83,160,1,1,1,0 811 | 0,0,0,1,0,10237,0,264,360,1,0,1,0 812 | 1,0,0,1,0,5860,0,146,360,1,1,1,0 813 | 0,0,0,1,0,3276,0,76,360,1,0,1,0 814 | 1,0,0,0,0,3986,2511,57,360,1,1,3,0 815 | 0,0,0,1,0,3692,0,100,360,1,1,3,0 816 | 1,0,0,1,0,2704,0,69,360,1,1,2,0 817 | 0,0,0,1,0,4026,1720,127,360,1,1,2,0 818 | 0,0,1,1,0,3821,0,114,250,1,0,2,0 819 | 1,0,0,1,0,5929,0,138,360,1,1,1,0 820 | 0,0,0,1,0,3747,0,102,360,1,1,3,0 821 | 0,0,2,1,0,3084,0,194,360,1,1,3,0 822 | 0,0,0,1,0,2989,0,61,360,1,1,1,0 823 | 1,0,0,0,0,3825,0,111,360,1,0,3,0 824 | 0,0,1,1,0,2872,1556,91,360,1,1,1,0 825 | 0,0,1,1,1,8596,0,162,360,1,1,2,0 826 | 1,0,1,1,1,3664,0,109,215,1,1,1,0 827 | 1,0,2,1,0,4921,0,162,360,0,1,2,0 828 | 1,0,0,1,0,3847,0,78,360,1,1,2,0 -------------------------------------------------------------------------------- /images/add.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IBM/predict-fraud-using-auto-ai/84ddd32eeaf3e615e42fd04968e8451bfa0bc451/images/add.png -------------------------------------------------------------------------------- /images/add_asset.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IBM/predict-fraud-using-auto-ai/84ddd32eeaf3e615e42fd04968e8451bfa0bc451/images/add_asset.png -------------------------------------------------------------------------------- /images/add_dply.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IBM/predict-fraud-using-auto-ai/84ddd32eeaf3e615e42fd04968e8451bfa0bc451/images/add_dply.png -------------------------------------------------------------------------------- /images/add_ml.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IBM/predict-fraud-using-auto-ai/84ddd32eeaf3e615e42fd04968e8451bfa0bc451/images/add_ml.png -------------------------------------------------------------------------------- /images/architecture.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IBM/predict-fraud-using-auto-ai/84ddd32eeaf3e615e42fd04968e8451bfa0bc451/images/architecture.png -------------------------------------------------------------------------------- /images/cf_matrix.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IBM/predict-fraud-using-auto-ai/84ddd32eeaf3e615e42fd04968e8451bfa0bc451/images/cf_matrix.png -------------------------------------------------------------------------------- /images/cf_mtrx.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IBM/predict-fraud-using-auto-ai/84ddd32eeaf3e615e42fd04968e8451bfa0bc451/images/cf_mtrx.png -------------------------------------------------------------------------------- /images/create_exp.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IBM/predict-fraud-using-auto-ai/84ddd32eeaf3e615e42fd04968e8451bfa0bc451/images/create_exp.png -------------------------------------------------------------------------------- /images/create_prj.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IBM/predict-fraud-using-auto-ai/84ddd32eeaf3e615e42fd04968e8451bfa0bc451/images/create_prj.png -------------------------------------------------------------------------------- /images/crt-dply.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IBM/predict-fraud-using-auto-ai/84ddd32eeaf3e615e42fd04968e8451bfa0bc451/images/crt-dply.png -------------------------------------------------------------------------------- /images/crt_dply.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IBM/predict-fraud-using-auto-ai/84ddd32eeaf3e615e42fd04968e8451bfa0bc451/images/crt_dply.png -------------------------------------------------------------------------------- /images/def_exp.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IBM/predict-fraud-using-auto-ai/84ddd32eeaf3e615e42fd04968e8451bfa0bc451/images/def_exp.png -------------------------------------------------------------------------------- /images/def_prj.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IBM/predict-fraud-using-auto-ai/84ddd32eeaf3e615e42fd04968e8451bfa0bc451/images/def_prj.png -------------------------------------------------------------------------------- /images/deploy_mdl.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IBM/predict-fraud-using-auto-ai/84ddd32eeaf3e615e42fd04968e8451bfa0bc451/images/deploy_mdl.png -------------------------------------------------------------------------------- /images/deply-space.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IBM/predict-fraud-using-auto-ai/84ddd32eeaf3e615e42fd04968e8451bfa0bc451/images/deply-space.png -------------------------------------------------------------------------------- /images/dply_ready.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IBM/predict-fraud-using-auto-ai/84ddd32eeaf3e615e42fd04968e8451bfa0bc451/images/dply_ready.png -------------------------------------------------------------------------------- /images/feat_imp.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IBM/predict-fraud-using-auto-ai/84ddd32eeaf3e615e42fd04968e8451bfa0bc451/images/feat_imp.png -------------------------------------------------------------------------------- /images/feature_imp.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IBM/predict-fraud-using-auto-ai/84ddd32eeaf3e615e42fd04968e8451bfa0bc451/images/feature_imp.png -------------------------------------------------------------------------------- /images/feature_transforms.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IBM/predict-fraud-using-auto-ai/84ddd32eeaf3e615e42fd04968e8451bfa0bc451/images/feature_transforms.png -------------------------------------------------------------------------------- /images/form.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IBM/predict-fraud-using-auto-ai/84ddd32eeaf3e615e42fd04968e8451bfa0bc451/images/form.png -------------------------------------------------------------------------------- /images/generate_pipelines.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IBM/predict-fraud-using-auto-ai/84ddd32eeaf3e615e42fd04968e8451bfa0bc451/images/generate_pipelines.png -------------------------------------------------------------------------------- /images/import_csv.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IBM/predict-fraud-using-auto-ai/84ddd32eeaf3e615e42fd04968e8451bfa0bc451/images/import_csv.png -------------------------------------------------------------------------------- /images/insert_dataframe.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IBM/predict-fraud-using-auto-ai/84ddd32eeaf3e615e42fd04968e8451bfa0bc451/images/insert_dataframe.png -------------------------------------------------------------------------------- /images/json.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IBM/predict-fraud-using-auto-ai/84ddd32eeaf3e615e42fd04968e8451bfa0bc451/images/json.png -------------------------------------------------------------------------------- /images/model_eval.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IBM/predict-fraud-using-auto-ai/84ddd32eeaf3e615e42fd04968e8451bfa0bc451/images/model_eval.png -------------------------------------------------------------------------------- /images/model_saved.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IBM/predict-fraud-using-auto-ai/84ddd32eeaf3e615e42fd04968e8451bfa0bc451/images/model_saved.png -------------------------------------------------------------------------------- /images/not_trusted.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IBM/predict-fraud-using-auto-ai/84ddd32eeaf3e615e42fd04968e8451bfa0bc451/images/not_trusted.png -------------------------------------------------------------------------------- /images/overview.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IBM/predict-fraud-using-auto-ai/84ddd32eeaf3e615e42fd04968e8451bfa0bc451/images/overview.png -------------------------------------------------------------------------------- /images/pipeline_3.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IBM/predict-fraud-using-auto-ai/84ddd32eeaf3e615e42fd04968e8451bfa0bc451/images/pipeline_3.png -------------------------------------------------------------------------------- /images/prediction_settings.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IBM/predict-fraud-using-auto-ai/84ddd32eeaf3e615e42fd04968e8451bfa0bc451/images/prediction_settings.png -------------------------------------------------------------------------------- /images/prmt-space.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IBM/predict-fraud-using-auto-ai/84ddd32eeaf3e615e42fd04968e8451bfa0bc451/images/prmt-space.png -------------------------------------------------------------------------------- /images/sample_split.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IBM/predict-fraud-using-auto-ai/84ddd32eeaf3e615e42fd04968e8451bfa0bc451/images/sample_split.png -------------------------------------------------------------------------------- /images/sel-dply.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IBM/predict-fraud-using-auto-ai/84ddd32eeaf3e615e42fd04968e8451bfa0bc451/images/sel-dply.png -------------------------------------------------------------------------------- /images/sel_auto_ai.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IBM/predict-fraud-using-auto-ai/84ddd32eeaf3e615e42fd04968e8451bfa0bc451/images/sel_auto_ai.png -------------------------------------------------------------------------------- /images/sel_target.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IBM/predict-fraud-using-auto-ai/84ddd32eeaf3e615e42fd04968e8451bfa0bc451/images/sel_target.png -------------------------------------------------------------------------------- /images/select_model.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IBM/predict-fraud-using-auto-ai/84ddd32eeaf3e615e42fd04968e8451bfa0bc451/images/select_model.png -------------------------------------------------------------------------------- /images/shap.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IBM/predict-fraud-using-auto-ai/84ddd32eeaf3e615e42fd04968e8451bfa0bc451/images/shap.png -------------------------------------------------------------------------------- /images/shap_ft_imp.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IBM/predict-fraud-using-auto-ai/84ddd32eeaf3e615e42fd04968e8451bfa0bc451/images/shap_ft_imp.png -------------------------------------------------------------------------------- /images/test_mdl.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/IBM/predict-fraud-using-auto-ai/84ddd32eeaf3e615e42fd04968e8451bfa0bc451/images/test_mdl.png --------------------------------------------------------------------------------