Python StemmedCountVectorizer Examples

Example #1

File: pipelineconfig_combinations.py Project: RolandColored/emo-predict

 def text_tfidf_stemmed_bow_1000(lang):
     return make_pipeline(TextExtractor(column='text'),
                          StemmedCountVectorizer(lang, strip_accents='ascii', stop_words=PipelineConfig._stop_words(lang)),
                          TfidfTransformer(),
                          TruncatedSVD(n_components=1000))

Example #2

File: pipelineconfig_combinations.py Project: RolandColored/emo-predict

 def text_bigram_stemmed_bow_1000(lang):
     return make_pipeline(TextExtractor(column='text'),
                          StemmedCountVectorizer(lang, strip_accents='ascii', min_df=0.001, max_df=0.8,
                                                 ngram_range=(2, 2), stop_words=PipelineConfig._stop_words(lang)),
                          TruncatedSVD(n_components=1000))