features.py 文件源码

def create_crosstabs(model):
    r"""Create cross-tabulations for categorical variables.

    Parameters
    ----------
    model : alphapy.Model
        The model object containing the data.

    Returns
    -------
    model : alphapy.Model
        The model object with the updated feature map.

    """

    logger.info("Creating Cross-Tabulations")

    # Extract model data
    X = model.X_train
    y = model.y_train

    # Extract model parameters

    factors = model.specs['factors']
    target_value = model.specs['target_value']

    # Iterate through columns, dispatching and transforming each feature.

    crosstabs = {}
    for fname in X:
        if fname in factors:
            logger.info("Creating crosstabs for feature %s", fname)
            ct = pd.crosstab(X[fname], y).apply(lambda r : r / r.sum(), axis=1)
            crosstabs[fname] = ct

    # Save crosstabs to the feature map

    model.feature_map['crosstabs'] = crosstabs
    return model


#
# Function get_factors
#