#Load Dataset: X_Data, Y_Data#X_Data = Pandas DataFrame#Y_Data = Numpy Array or ListX_data,Y_data=explainx.dataset_heloc() 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) ...
DataFrame(weights, index=target_labels, columns=filters)Visualizing the weights:plt.figure(figsize=(15, 10)) # focus on annotated filters only sns.clustermap(weight_df[[i for i in weight_df.columns if not i.startswith("filter")]], cmap=sns.diverging_palette(145, 10, s=60, as_cmap=...
(in this example it is simply converting predictions to a string)model_predictions=pd.DataFrame(predictions.astype(str),columns=[y_train.name],index=y_train.index)# use Explainer to explain model outputexplainer=Explainer(X=X_train,model_predictions=model_predictions,type="classification")explainer....
classMyData():my_data=pd.read_csv("path/to/csv/file",header=0,index_col=0)data=pd.DataFrame(my_data)def__init__(self):self.data=self.data.iloc[:,:-1]self.target=self.data["name of class"]self.categoric=["colums which are categorical"]self.continues=self.data.columns.difference(se...