def setUp(self): self.v = Variables() self.prp = PhrasesRequirementProcessor()
class TestPhrasesRequirementProcessor(TestCase): def setUp(self): self.v = Variables() self.prp = PhrasesRequirementProcessor() def it_generates_new_corpus_from_segmented_reports(self): self.prp.generate_corpus_from_segmented_reports \ |should| equal_to((self.v.cut_of_segmented_reports, self.v.topics)) def it_aggregates_sentences_of_topics_on_segmented_reports(self): self.prp.aggregate_topics_of_segmented_reports(self.v.cut_of_segmented_reports, self.v.topics) \ |should| equal_to(self.v.aggregated_topics) def it_organizes_aggregated_topics_by_dictionary(self): self.prp.organize_aggregated_topics_by_dict(self.v.aggregated_topics, self.v.topics) \ |should| equal_to(self.v.dict_of_sentences_by_topic) def it_tags_unigrams_by_topic(self): self.prp.tag_unigrams_by_topic(self.v.dict_of_sentences_by_topic) \ |should| equal_to(self.v.tagged_unigrams_by_topic) def it_generates_nouns_unigrams_by_topic(self): self.prp.generate_nouns_unigrams_by_topic(self.v.tagged_unigrams_by_topic) \ |should| equal_to(self.v.nouns_unigrams_by_topic) def it_generates_none_unigrams_by_topic(self): self.prp.generate_none_unigrams_by_topic(self.v.tagged_unigrams_by_topic) \ |should| equal_to(self.v.none_unigrams_by_topic) def it_creates_a_dictionary_model_for_test_accuracy_of_tagger_by_topic( self): self.prp.create_a_dict_model_for_test_accuracy(self.v.tagged_unigrams_by_topic) \ |should| equal_to((self.v.dict_model_by_topic, self.v.tagger_accuracy_by_topic)) def it_creates_most_frequent_nouns_unigrams_by_topic(self): self.prp.create_most_frequent_nouns_unigrams_by_topic(self.v.nouns_unigrams_by_topic) \ |should| equal_to(self.v.run_time_most_frequent_nouns_unigrams_by_topic) def it_creates_wordtypes_of_none_unigrams_by_topic(self): self.prp.create_wordtypes_of_none_unigrams_by_topic(self.v.none_unigrams_by_topic) \ |should| equal_to(self.v.run_time_wordtypes_of_none_unigrams_by_topic)
class TestPhrasesRequirementProcessor(TestCase): def setUp(self): self.v = Variables() self.prp = PhrasesRequirementProcessor() def it_generates_new_corpus_from_segmented_reports(self): self.prp.generate_corpus_from_segmented_reports | should | equal_to( (self.v.cut_of_segmented_reports, self.v.topics) ) def it_aggregates_sentences_of_topics_on_segmented_reports(self): self.prp.aggregate_topics_of_segmented_reports( self.v.cut_of_segmented_reports, self.v.topics ) | should | equal_to(self.v.aggregated_topics) def it_organizes_aggregated_topics_by_dictionary(self): self.prp.organize_aggregated_topics_by_dict(self.v.aggregated_topics, self.v.topics) | should | equal_to( self.v.dict_of_sentences_by_topic ) def it_tags_unigrams_by_topic(self): self.prp.tag_unigrams_by_topic(self.v.dict_of_sentences_by_topic) | should | equal_to( self.v.tagged_unigrams_by_topic ) def it_generates_nouns_unigrams_by_topic(self): self.prp.generate_nouns_unigrams_by_topic(self.v.tagged_unigrams_by_topic) | should | equal_to( self.v.nouns_unigrams_by_topic ) def it_generates_none_unigrams_by_topic(self): self.prp.generate_none_unigrams_by_topic(self.v.tagged_unigrams_by_topic) | should | equal_to( self.v.none_unigrams_by_topic ) def it_creates_a_dictionary_model_for_test_accuracy_of_tagger_by_topic(self): self.prp.create_a_dict_model_for_test_accuracy(self.v.tagged_unigrams_by_topic) | should | equal_to( (self.v.dict_model_by_topic, self.v.tagger_accuracy_by_topic) ) def it_creates_most_frequent_nouns_unigrams_by_topic(self): self.prp.create_most_frequent_nouns_unigrams_by_topic(self.v.nouns_unigrams_by_topic) | should | equal_to( self.v.run_time_most_frequent_nouns_unigrams_by_topic ) def it_creates_wordtypes_of_none_unigrams_by_topic(self): self.prp.create_wordtypes_of_none_unigrams_by_topic(self.v.none_unigrams_by_topic) | should | equal_to( self.v.run_time_wordtypes_of_none_unigrams_by_topic )
def detect_unigrams(self): prp = PhrasesRequirementProcessor() cut_of_segmented_reports, \ topics = prp.generate_corpus_from_segmented_reports aggregated_topics = \ prp.aggregate_topics_of_segmented_reports(cut_of_segmented_reports, topics) dict_of_sentences_by_topic = \ prp.organize_aggregated_topics_by_dict(aggregated_topics, topics) tagged_unigrams_by_topic = prp.tag_unigrams_by_topic(dict_of_sentences_by_topic) nouns_unigrams_by_topic = \ prp.generate_nouns_unigrams_by_topic(tagged_unigrams_by_topic) none_unigrams_by_topic = \ prp.generate_none_unigrams_by_topic(tagged_unigrams_by_topic) dict_model_by_topic, \ tagger_accuracy_by_topic = \ prp.create_a_dict_model_for_test_accuracy(tagged_unigrams_by_topic) run_time_most_frequent_nouns_unigrams_by_topic = \ prp.create_most_frequent_nouns_unigrams_by_topic(nouns_unigrams_by_topic) run_time_wordtypes_of_none_unigrams_by_topic = prp.create_wordtypes_of_none_unigrams_by_topic(none_unigrams_by_topic) prp.create_unigram_set_of_nouns_and_nones(run_time_most_frequent_nouns_unigrams_by_topic, run_time_wordtypes_of_none_unigrams_by_topic) prp.show_accuracy_by_topic(tagger_accuracy_by_topic) prp.remove_pyc_and_zombie_files
def detect_unigrams(self): prp = PhrasesRequirementProcessor() cut_of_segmented_reports, \ topics = prp.generate_corpus_from_segmented_reports aggregated_topics = \ prp.aggregate_topics_of_segmented_reports(cut_of_segmented_reports, topics) dict_of_sentences_by_topic = \ prp.organize_aggregated_topics_by_dict(aggregated_topics, topics) tagged_unigrams_by_topic = prp.tag_unigrams_by_topic( dict_of_sentences_by_topic) nouns_unigrams_by_topic = \ prp.generate_nouns_unigrams_by_topic(tagged_unigrams_by_topic) none_unigrams_by_topic = \ prp.generate_none_unigrams_by_topic(tagged_unigrams_by_topic) dict_model_by_topic, \ tagger_accuracy_by_topic = \ prp.create_a_dict_model_for_test_accuracy(tagged_unigrams_by_topic) run_time_most_frequent_nouns_unigrams_by_topic = \ prp.create_most_frequent_nouns_unigrams_by_topic(nouns_unigrams_by_topic) run_time_wordtypes_of_none_unigrams_by_topic = prp.create_wordtypes_of_none_unigrams_by_topic( none_unigrams_by_topic) prp.create_unigram_set_of_nouns_and_nones( run_time_most_frequent_nouns_unigrams_by_topic, run_time_wordtypes_of_none_unigrams_by_topic) prp.show_accuracy_by_topic(tagger_accuracy_by_topic) prp.remove_pyc_and_zombie_files