lang2vec.py 文件源码

def get(languages, feature_set_str, header=False, random=False, minimal=False):

    lang_codes = languages.split()
    feature_names, feature_values = get_concatenated_sets(lang_codes, feature_set_str)
    feature_names = np.array([ f.replace(" ","_") for f in feature_names ])
    feats = {}

    if minimal:
        mask = np.all(feature_values == 0.0, axis=0)
        mask |= np.all(feature_values == 1.0, axis=0)
        mask |= np.all(feature_values == -1.0, axis=0)
        unmasked_indices = np.where(np.logical_not(mask))
    else:
        unmasked_indices = np.where(np.ones(feature_values.shape[1]))

    if random:
        feature_values = np.random.random(feature_values.shape) >= 0.5

    if header:
        print("\t".join(['CODE']+list(feature_names[unmasked_indices])))
    feat_names = feature_names[unmasked_indices]

    for i, lang_code in enumerate(lang_codes):
        values = feature_values[i,unmasked_indices].ravel()
        #values = [ '--' if f == -1 else ("%0.4f"%f).rstrip("0").rstrip(".") for f in values ]
        feats[lang_code] = values
        #print("\t".join([lang_code]+values))
    return feats, feat_names

#if __name__ == '__main__':
#    argparser = argparse.ArgumentParser()
#    argparser.add_argument("languages", default='', help="The languages of interest, in ISO 639-3 codes, separated by spaces (e.g., \"deu eng fra swe\")")
#    argparser.add_argument("feature_set", default='', help="The feature set or sets of interest (e.g., \"syntax_knn\" or \"fam\"), joined by concatenation (+) or element-wise union (|).")
#    argparser.add_argument("-f", "--fields", default=False, action="store_true", help="Print feature names as the first row of data.")
#    argparser.add_argument("-r", "--random", default=False, action="store_true", help="Randomize all feature values (e.g., to make a control group).")
#    argparser.add_argument("-m", "--minimal", default=False, action="store_true", help="Suppress columns that are all 0, all 1, or all nulls.")
#    args = argparser.parse_args()
#    get(args.languages, args.feature_set, args.fields, args.random, args.minimal)