def test_sort_top_terms(): a = analyzer.Analyzer() words = {'came': 1, 'saw': 1, 'conquered': 1, 'I': 3} result1 = a.sort_top_terms(words, 1) # result2 = a.sort_top_terms(words, 2) assert result1 == [('I', 3)]
def test_remove_no_stop_words(): a = analyzer.Analyzer() input_words = ['a', 'fantastic', 'test'] stopwords = ['foo'] result = a.remove_stop_words(input_words, stopwords) assert result == input_words
def test_remove_punctuation(): a = analyzer.Analyzer() text = 'I; really! should. stop:: putting??? so&*, many punctuation marks In my Sentences!!!&!$)' result = a.remove_punctuation(text) assert result == [ 'I', 'really', 'should', 'stop', 'putting', 'so', 'many', 'punctuation', 'marks', 'In', 'my', 'Sentences' ]
def test_compute_term_frequency(): a = analyzer.Analyzer() words = ['a', 'man', 'a', 'plan', 'a', 'canal', 'Panama'] result = a.compute_term_frequency(words) assert result['a'] == 3 assert result['man'] == 1 assert result['plan'] == 1 assert result['canal'] == 1 assert result['Panama'] == 1
def test_stem(): a = analyzer.Analyzer() words = ['jumping', 'jumps', 'jumped', 'jump'] result = a.stem(words) assert result == ['jump', 'jump', 'jump', 'jump']
from analyzer import analyzer a = analyzer.Analyzer() a.clear_screen() a.greeting() input_words = [] stopwords = [] while input_words == []: input_words = a.get_input_words() while stopwords == []: stopwords = a.get_stopwords() filtered_words = a.remove_stop_words(input_words, stopwords) root_words = a.stem(filtered_words) frequency = a.compute_term_frequency(root_words) common_terms = a.sort_top_terms(frequency, 20) a.print_top_terms(common_terms)