def prep_ablation()

in scripts/interpret.py [0:0]

• 27 lines of code
• 1 McCabe index (conditional complexity)

def prep_ablation(df):
    """Prepare data for making predictions."""
    
    # convert df to list of dicts
    data = df.to_json(orient="records")
    data = json.loads(data)
    
    # load model assets from training job
    model_assets = train.get_train_assets()
    #print('extracting features')
    numerical_features, categorical_features, textual_features = preprocess.extract_features(
        data,
        model_assets['numerical_feature_names'],
        model_assets['categorical_feature_names'],
        model_assets['textual_feature_names']
    )

    # extract labels
    _, _, _, label_name = preprocess.get_feature_names(df)
    labels = preprocess.extract_labels(
        data,
        label_name
    )

    # preprocess the data
    #print('transforming numerical_features')
    numerical_features = model_assets['numerical_transformer'].transform(numerical_features)
    #print('transforming categorical_features')
    categorical_features = model_assets['categorical_transformer'].transform(categorical_features)
    #print('transforming textual_features')
    textual_features = model_assets['textual_transformer'].transform(textual_features)

    #print('concatenating features')
    categorical_features = categorical_features.toarray()
    textual_features = np.array(textual_features)
    textual_features = textual_features.reshape(textual_features.shape[0], -1)
    features = np.concatenate([
        numerical_features,
        categorical_features,
        textual_features
    ], axis=1)

    return features, labels