similarity_recommender.py 文件源码

def compute_clients_dist(self, client_data):
        client_categorical_feats = [client_data.get(specified_key) for specified_key in CATEGORICAL_FEATURES]
        client_continuous_feats = [client_data.get(specified_key) for specified_key in CONTINUOUS_FEATURES]

        # Compute the distances between the user and the cached continuous
        # and categorical features.
        cont_features = distance.cdist(self.continuous_features,
                                       np.array([client_continuous_feats]),
                                       'canberra')
        # The lambda trick is needed to prevent |cdist| from force-casting the
        # string features to double.
        cat_features = distance.cdist(self.categorical_features,
                                      np.array([client_categorical_feats]),
                                      lambda x, y: distance.hamming(x, y))

        # Take the product of similarities to attain a univariate similarity score.
        # Addition of 0.001 to the continuous features avoids a zero value from the
        # categorical variables, allowing categorical features precedence.
        return (cont_features + 0.001) * cat_features