top_features.py

def get_top_features_cluster(tf_idf_array, prediction, n_feats):
    labels = np.unique(prediction)
    dfs = []
    for label in labels:
        id_temp = np.where(prediction==label) # indices for each cluster
        x_means = np.mean(tf_idf_array[id_temp], axis = 0) # returns average score across cluster
        sorted_means = np.argsort(x_means)[::-1][:n_feats] # indices with top 20 scores
        features = tf_idf_vectorizor.get_feature_names()
        best_features = [(features[i], x_means[i]) for i in sorted_means]
        df = pd.DataFrame(best_features, columns = ['features', 'score'])
        dfs.append(df)
    return dfs
dfs = get_top_features_cluster(tf_idf_array, prediction, 15)