def similarity_function()

in mozetl/taar/taar_similarity.py [0:0]

• 10 lines of code
• 13 McCabe index (conditional complexity)

def similarity_function(x, y):
    """Similarity function for comparing user features.

    This actually really should be implemented in taar.similarity_recommender
    and then imported here for consistency.
    """

    def safe_get(field, row, default_value):
        # Safely get a value from the Row. If the value is None, get the
        # default value.
        return row[field] if row[field] is not None else default_value

    # Extract the values for the categorical and continuous features for both
    # the x and y samples. Use an empty string as the default value for missing
    # categorical fields and 0 for the continuous ones.
    x_categorical_features = [safe_get(k, x, "") for k in CATEGORICAL_FEATURES]
    x_continuous_features = [safe_get(k, x, 0) for k in CONTINUOUS_FEATURES]
    y_categorical_features = [safe_get(k, y, "") for k in CATEGORICAL_FEATURES]
    y_continuous_features = [safe_get(k, y, 0) for k in CONTINUOUS_FEATURES]

    # Here a larger distance indicates a poorer match between categorical variables.
    j_d = distance.hamming(x_categorical_features, y_categorical_features)
    j_c = distance.canberra(x_continuous_features, y_continuous_features)

    # Take the product of similarities to attain a univariate similarity score.
    # Add a minimal constant to prevent zero values from categorical features.
    # Note: since both the distance function return a Numpy type, we need to
    # call the |item| function to get the underlying Python type. If we don't
    # do that this job will fail when performing KDE due to SPARK-20803 on
    # Spark 2.2.0.
    return abs((j_c + 0.001) * j_d).item()