3e2ebf76a530eca5305d1feba6be9c531ee33d71,gensim/corpora/hashdictionary.py,HashDictionary,filter_extremes,#HashDictionary#Any#Any#Any#,172

Before Change


        if keep_n is not None:
            good_ids = sorted(good_ids, key=lambda item: self.dfs.get(item, 0), reverse=True)
            good_ids = good_ids[:keep_n]
        good_ids = set(good_ids)

        self.id2token = dict((tokenid, freq) for tokenid, freq in self.id2token.iteritems() if tokenid in good_ids)
        self.dfs = dict((tokenid, freq) for tokenid, freq in self.dfs.iteritems() if tokenid in good_ids)
        logger.info("kept statistics for %i tokens which were in no less than %i and no more than %i (=%.1f%%) documents" %

After Change


        
        no_above_abs = int(no_above * self.num_docs) // convert fractional threshold to absolute threshold

        self.dfs_debug = dict((word, freq) for word, freq in self.dfs_debug.iteritems() if no_below <= freq <= no_above_abs)
        self.token2id = dict((token, tokenid) for token, tokenid in self.token2id.iteritems() if token in self.dfs_debug)
        self.id2token = dict((tokenid, set(token for token in tokens if token in self.dfs_debug)) for tokenid, tokens in self.id2token.iteritems())
        self.dfs = dict((tokenid, freq) for tokenid, freq in self.dfs.iteritems() if self.id2token.get(tokenid, set()))
Italian Trulli
In pattern: SUPERPATTERN

Frequency: 3

Non-data size: 5

Instances


Project Name: RaRe-Technologies/gensim
Commit Name: 3e2ebf76a530eca5305d1feba6be9c531ee33d71
Time: 2012-08-19
Author: radimrehurek@seznam.cz
File Name: gensim/corpora/hashdictionary.py
Class Name: HashDictionary
Method Name: filter_extremes


Project Name: reinforceio/tensorforce
Commit Name: 632f7df52a90ee775a235142202440d6b798bd6f
Time: 2019-01-23
Author: alexkuhnle@t-online.de
File Name: tensorforce/util.py
Class Name:
Method Name:


Project Name: mathics/Mathics
Commit Name: d3ef32acab314fc2c145d890b0a23e57ac9dd2f8
Time: 2016-09-01
Author: Bernhard.Liebl@gmx.org
File Name: mathics/builtin/colors.py
Class Name:
Method Name: