Repository files navigation

Use explainX to understand overall model behavior, explain the "why" behind model predictions, remove biases and create convincing explanations for your business stakeholders.

Essential for:

1. Explaining model predictions
2. Debugging models
3. Detecting biases in data
4. Gaining trust of business users
5. Successfully deploying AI solution

1. Why did my model make a mistake?
2. Is my model biased? If yes, where?
3. How can I understand and trust the model's decisions?
4. Does my model satisfy legal & regulatory requirements?

Dashboard Demo:http://3.128.188.55:8080/

Python 3.5+ | Linux, Mac, Windows

pip install explainx

To download on Windows, please installMicrosoft C++ Build Tools first and then install the explainX package viapip

If you are using a notebook instance on the cloud (AWS SageMaker, Colab, Azure), please follow our step-by-step guide to install & run explainX cloud.

After successfully installing explainX, open up your Python IDE of Jupyter Notebook and simply follow the code below to use it:

1. Import required module.

fromexplainximport*fromsklearn.ensembleimportRandomForestClassifierfromsklearn.model_selectionimporttrain_test_split

2. Load and split your dataset into x_data and y_data

#Load Dataset: X_Data, Y_Data#X_Data = Pandas DataFrame#Y_Data = Numpy Array or ListX_data,Y_data=explainx.dataset_heloc()

3. Split dataset into training & testing.

X_train,X_test,Y_train,Y_test=train_test_split(X_data,Y_data,test_size=0.3,random_state=0)

4. Train your model.

# Train a RandomForest Modelmodel=RandomForestClassifier()model.fit(X_train,Y_train)

After you're done training the model, you can either access the complete explainability dashboard or access individual techniques.

To access the entire dashboard with all the explainability techniques under one roof, follow the code down below. It is great for sharing your work with your peers and managers in an interactive and easy to understand way.

5.1. Pass your model and dataset into the explainX function:

explainx.ai(X_test,Y_test,model,model_name="randomforest")

5.2. Click on the dashboard link to start exploring model behavior:

Apprunningonhttps://127.0.0.1:8080

In this latest release, we have also given the option to use explainability techniques individually. This will allow the user to choose technique that fits their personal AI use case.

6.1. Pass your model, X_Data and Y_Data into the explainx_modules function.

explainx_modules.ai(model,X_test,Y_test)

As an upgrade, we have eliminated the need to pass in the model name as explainX is smart enough to identify the model type and problem type i.e. classification or regression, by itself.

You can access multiple modules:

Module 1: Dataframe with Predictions

explainx_modules.dataframe_graphing()

Module 2: Model Metrics

explainx_modules.metrics()

Module 3: Global Level SHAP Values

explainx_modules.shap_df()

Module 4: What-If Scenario Analysis (Local Level Explanations)

explainx_modules.what_if_analysis()

Module 5: Partial Dependence Plot & Summary Plot

explainx_modules.feature_interactions()

Module 6: Model Performance Comparison (Cohort Analysis)

explainx_modules.cohort_analysis()

To access the modules within your jupyter notebook as IFrames, just pass themode='inline' argument.

If you are running explainX on the cloud e.g., AWS Sagemaker?https://0.0.0.0:8080 will not work.

After installation is complete, just open yourterminal and run the following command.

lt -h "https://serverless.social" -p [port number]

lt -h "https://serverless.social" -p 8080

Please click on the image below to load the tutorial:

(Note: Please manually set it to 720p or greater to have the text appear clearly)

Pull requests are welcome. In order to make changes to explainx, the ideal approach is to fork the repository then clone the fork locally.

For major changes, please open an issue first to discuss what you would like to change.Please make sure to update tests as appropriate.

Please help us byreporting any issues you may have while using explainX.

MIT