Repository files navigation

xplainable

Real-time explainable machine learning for business optimisation

Xplainable makes tabular machine learning transparent, fair, and actionable.

In machine learning, there has long been a trade-off between accuracy andexplainability. This drawback has led to the creation of explainable MLlibraries such asShap andLime which make estimations of model decision processes. These can be incredibly time-expensive and often present steeplearning curves making them challenging to implement effectively in productionenvironments.

To solve this problem, we createdxplainable.xplainable presents asuite of novel machine learning algorithms specifically designed to match theperformance of popular black box models likeXGBoost andLightGBM whileproviding complete transparency, all in real-time.

You can interface with xplainable either through a typical Pythonic API, orusing a notebook-embedded GUI in your Jupyter Notebook.

Xplainable has each of the fundamental tabular models used in data scienceteams. They are fast, accurate, and easy to use.

You can install the core features ofxplainable with:

pip install xplainable

to use thexplainable gui in a jupyter notebook, install with:

pip install xplainable[gui]

• Visit ourGeneral Documentation to learn how to get the best out of xplainable
• Vist ourAPI Documentation for additional support with using our API

Basic Example

importxplainableasxpfromxplainable.core.modelsimportXClassifierimportpandasaspdfromsklearn.model_selectionimporttrain_test_split# Load datadata=xp.load_dataset('titanic')X,y=data.drop(columns=['Survived']),data['Survived']X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.25,random_state=42)# Train a modelmodel=XClassifier()model.fit(X_train,y_train)# Explain the modelmodel.explain()

Xplainable helps to streamline development processes by making model tuningand deployment simpler than you can imagine.

We built a comprehensive suite of preprocessing transformers for rapid andreproducible data preprocessing.

fromxplainable.preprocessing.pipelineimportXPipelinefromxplainable.preprocessingimporttransformersasxtfpipeline=XPipeline()# Add stages for specific featurespipeline.add_stages([    {"feature":"age","transformer":xtf.Clip(lower=18,upper=99)},    {"feature":"balance","transformer":xtf.LogTransform()}])# add stages on multiple featurespipeline.add_stages([    {"transformer":xtf.FillMissing({'job':'mode','age':'mean'})},    {"transformer":xtf.DropCols(columns=['duration','campaign'])}])# Fit and transform the datatrain_transformed=pipeline.fit_transform(train)# Apply transformations on new datatest_transformed=pipeline.transform(test)

pp=xp.Preprocessor()pp.preprocess(train)

Xplainable models can be developed, optimised, and re-optimised using PythonicAPIs or the embedded GUI.

importxplainableasxpfromxplainable.core.modelsimportXClassifierfromxplainable.core.optimisation.bayesianimportXParamOptimiserfromsklearn.model_selectionimporttrain_test_splitimportpandasaspd# Load your datadata=xp.load_dataset('titanic')# note: the data requires preprocessing, so results may be poorX,y=data.drop('Survived',axis=1),data['Survived']X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.2)# Optimise paramsopt=XParamOptimiser(metric='roc-auc')params=opt.optimise(X_train,y_train)# Train your modelmodel=XClassifier(**params)model.fit(X_train,y_train)# Predict on the test sety_pred=model.predict(X_test)# Explain the modelmodel.explain()

model=xp.classifier(train)

Fine tune your models by refitting model parameters on the fly, even onindividual features.

new_params= {"features": ['Age'],"max_depth":6,"min_info_gain":0.01,"min_leaf_size":0.03,"weight":0.05,"power_degree":1,"sigmoid_exponent":1,"x":X_train,"y":y_train}model.update_feature_params(**new_params)

Models are explainable and real-time, right out of the box, without having to fitsurrogate models such asShap orLime.

model.explain()

We leverage the explainability of our models to provide real-timerecommendations on how to optimise predicted outcomes at a local and globallevel.

Xplainable brings transparency to API deployments, and it's easy. By the timeyour finger leaves the mouse, your model is on a secure server and ready to go.

We promote fair and ethical use of technology for all machine learning tasks.To help encourage this, we're working on additional bias detection and fairnesstesting classes to ensure that everything you deploy is safe, fair, andcompliant.

This Python package is free and open-source. To add more value to data teamswithin organisations, we also created Xplainable Cloud that brings your modelsto a collaborative environment.

importxplainableasxpimportosxp.initialise(api_key=os.environ['XP_API_KEY'])

We'd love to welcome contributors to xplainable to keep driving forward moretransparent and actionable machine learning. We're working on our contributordocs at the moment, but if you're interested in contributing, please send us amessage atcontact@xplainable.io.