Python A.print_results方法代码示例

# 需要导入模块: import A [as 别名]
# 或者: from A import print_results [as 别名]
def run(train, test, language, answer):
    results = {}

    total = len(train)
    counter = 1

    s = build_s(train, language)
    #s = {}

    # if language == 'English':
    #     tagger = set_tagger(language)
    # else:
    tagger = None
    #tagger = set_tagger(language)
    stemmer = set_stemmer(language)

    for lexelt in train:
        train_features, y_train = extract_features(train[lexelt], language, tagger, stemmer, s[lexelt])
        test_features, _ = extract_features(test[lexelt], language, tagger, stemmer, s[lexelt])

        X_train, X_test = vectorize(train_features,test_features)
        X_train_new, X_test_new = feature_selection(X_train, X_test,y_train, language)
        results[lexelt] = classify(X_train_new, X_test_new,y_train)

        print str(counter) + ' out of ' + str(total) + ' completed'
        counter += 1

    A.print_results(results, answer)

# 需要导入模块: import A [as 别名]
# 或者: from A import print_results [as 别名]
def run(train, test, language, answer):
    results = {}
    if language == 'English':
        _POS_TAGGER = 'taggers/maxent_treebank_pos_tagger/english.pickle'
        tagger = load(_POS_TAGGER)
    elif language == 'Spanish':
        tagger = ut(cess_esp.tagged_sents())
    elif language == 'Catalan':
        tagger  = ut(cess_cat.tagged_sents())

    for lexelt in train:

        train_features, y_train = extract_features(train[lexelt],language,tagger)
        test_features, _ = extract_features(test[lexelt],language,tagger)

        X_train, X_test = vectorize(train_features,test_features)
        X_train_new, X_test_new = feature_selection(X_train, X_test,y_train)
        results[lexelt] = classify(X_train_new, X_test_new,y_train)
    """
    B1.c
    for lexelt in train:
        features = getBestWords(train[lexelt], 30)
        train_features = countFeature(features, train[lexelt])
        _, y_train = extract_features(train[lexelt], language)
        test_features = countFeature(features, test[lexelt])

        X_train, X_test = vectorize(train_features, test_features)
        results[lexelt] = classify(X_train, X_test, y_train)
    B1.c
    """
    A.print_results(results, answer)

# 需要导入模块: import A [as 别名]
# 或者: from A import print_results [as 别名]
def run(train, test, language, answer):
    results = {}

    for lexelt in train:

        train_features, y_train = extract_features(train[lexelt])
        test_features, _ = extract_features(test[lexelt])

        X_train, X_test = vectorize(train_features,test_features)
        X_train_new, X_test_new = feature_selection(X_train, X_test,y_train)
        results[lexelt] = classify(X_train_new, X_test_new,y_train)

    A.print_results(results, answer)

# 需要导入模块: import A [as 别名]
# 或者: from A import print_results [as 别名]
def run(train, test, language, answer):
    results = {}
    #calc_high_frequency_words(train)
    print 'Calling A'
    s = A.build_s(train)
    for lexelt in train:

        train_features, y_train = extract_features(train[lexelt],language,lexelt,s[lexelt])
        test_features, _ = extract_features(test[lexelt],language,lexelt,s[lexelt])

        X_train, X_test = vectorize(train_features,test_features)
        X_train_new, X_test_new = feature_selection(X_train, X_test,y_train,language)
        results[lexelt] = classify(X_train_new, X_test_new,y_train)
    A.print_results(results, answer)
    print 'ended'

# 需要导入模块: import A [as 别名]
# 或者: from A import print_results [as 别名]
def run(train, test, language, answer):
    results = {}
    l = len(train)
    for i, lexelt in enumerate(train):
        sys.stdout.write('\r{} / {} ({}%)'.format(i, l, int(float(i) / l * 100)))
        sys.stdout.flush()

        train_features, y_train = extract_features(train[lexelt], language)
        test_features, _ = extract_features(test[lexelt], language)

        X_train, X_test = vectorize(train_features,test_features)
        X_train_new, X_test_new = feature_selection(X_train, X_test,y_train)
        results[lexelt] = classify(X_train_new, X_test_new,y_train)

    A.print_results(results, answer)

# 需要导入模块: import A [as 别名]
# 或者: from A import print_results [as 别名]
def run(train, test, language, answer):
    results = {}

    if language == 'English': language = 'en'
    if language == 'Spanish': language = 'spa'
    if language == 'Catalan': language = 'cat'

    for lexelt in train:
        rel_dict = relevance(train[lexelt])
        train_features, y_train = extract_features(train[lexelt], language, rel_dict=rel_dict)
        test_features, _ = extract_features(test[lexelt], language, rel_dict=rel_dict)

        X_train, X_test = vectorize(train_features,test_features)
        X_train_new, X_test_new = feature_selection(X_train, X_test,y_train)
        results[lexelt] = classify(X_train_new, X_test_new,y_train)

    A.print_results(results, answer)

# 需要导入模块: import A [as 别名]
# 或者: from A import print_results [as 别名]
def run(train, test, language, answer):
    results = {}

    tagger = get_tagger(language)
    stemmer = get_stemmer(language)
    s = build_s(train, stemmer)

    for lexelt in train:

        words_count, senses_count = get_relavence_info(train[lexelt], stemmer)
        train_features, y_train = extract_features(train[lexelt], tagger, words_count, senses_count, stemmer, s[lexelt])
        test_features, _ = extract_features(test[lexelt], tagger, words_count, senses_count, stemmer, s[lexelt])

        X_train, X_test = vectorize(train_features, test_features)
        X_train_new, X_test_new, y_train_new, ids_test = feature_selection(X_train, X_test, y_train)
        results[lexelt] = classify(X_train_new, X_test_new, y_train_new, ids_test)

    A.print_results(results, answer)

# 需要导入模块: import A [as 别名]
# 或者: from A import print_results [as 别名]
def run(train, test, language, answer):
    results = {}
    s = build_s(train, language)

    for lexelt in train:

        feas_set = build_feas_set(train[lexelt], language)
        #feas_set = None
        train_features, y_train = extract_features(train[lexelt], language, feas_set, s[lexelt])
        test_features, _ = extract_features(test[lexelt], language, feas_set, s[lexelt])
    #    print train_features
        X_train, X_test = vectorize(train_features,test_features)
    #    print X_train
    #    X_train_new, X_test_new = feature_selection(X_train, X_test,y_train)
    #    results[lexelt] = classify(X_train_new, X_test_new,y_train)
        results[lexelt] = classify(X_train, X_test,y_train)

    A.print_results(results, answer)

# 需要导入模块: import A [as 别名]
# 或者: from A import print_results [as 别名]
def run(train, test, language, answer):
    print 'running B for language:', language
    results = {}
    if language.lower() in ['english', 'spanish']:
        extract_features.stemmer = nltk.SnowballStemmer(language.lower())

    for lexelt in train:

        train_features, y_train = extract_features(train[lexelt], language=language)
        test_features, _ = extract_features(test[lexelt], language=language)

        X_train, X_test = vectorize(train_features,test_features)
        if language.lower() in ['english', 'spanish']:
            X_train_new, X_test_new = feature_selection(X_train, X_test,y_train)
        else:
            X_train_new = X_train
            X_test_new = X_test
        results[lexelt] = classify(X_train_new, X_test_new,y_train)

    A.print_results(results, answer)

# 需要导入模块: import A [as 别名]
# 或者: from A import print_results [as 别名]
def run(train, test, language, answer):
    results = {}

    # tag_and_save(train, test, language)

    # load cached POS tags
    # print 'loading cached pos tags...'
    # train_name = language + '-train.p'
    # test_name = language + '-test.p'
    # train_pos_tags = pickle.load(open(train_name, 'rb'))
    # test_pos_tags = pickle.load(open(test_name, 'rb'))

    tagger = None
    if POS_WINDOW > 0 or POS_HEAD or FORCE_TAGGER_USE:
        tagger = UniversalTagger.EnglishTagger()
        if language is 'Spanish':
            tagger = UniversalTagger.SpanishTagger()

        if language is 'Catalan':
            tagger = UniversalTagger.CatalanTagger()

    stemmer = None
    if STEM:
        stemmer = PorterStemmer()

    for lexelt in train:
        relevance_key = None
        if USE_RELEVANCY_SCORES:
            relevance_key = top_relevant_words_from_data(train[lexelt])

        train_features, y_train = extract_features(train[lexelt], tagger, stemmer, relevance_key)
        test_features, _ = extract_features(test[lexelt], tagger, stemmer, relevance_key)

        X_train, X_test = vectorize(train_features,test_features)
        X_train_new, X_test_new = feature_selection(X_train, X_test,y_train)
        results[lexelt] = classify(X_train_new, X_test_new,y_train)

    A.print_results(results, answer)

# 需要导入模块: import A [as 别名]
# 或者: from A import print_results [as 别名]
def run(train, test, language, answer):
    global global_language
    global stop_words
    global punctuation_unicode
    global unigram_tagger
    global bigram_tagger
    global trigram_tagger
    global stemmer
    global window_size


    global_language = language

    if global_language == "english":
        window_size = 3
    elif global_language == "spanish":
        window_size = 2
    else:
        window_size = 3

    global_language = language.lower()
    
    if global_language == "english" or global_language == "spanish":
        stop_words = [word.lower() for word in stopwords.words(global_language)]
    else:
       stop_words =  [u'\ufeffa', u'abans', u'algun', u'alguna', u'algunes', u'alguns', u'altre', u'amb', u'ambd\xf3s', u'anar', u'ans', u'aquell', u'aquelles', u'aquells', u'aqu\xed', u'bastant', u'b\xe9', u'cada', u'com', u'consegueixo', u'conseguim', u'conseguir', u'consigueix', u'consigueixen', u'consigueixes', u'dalt', u'de', u'des de', u'dins', u'el', u'elles', u'ells', u'els', u'en', u'ens', u'entre', u'era', u'erem', u'eren', u'eres', u'es', u'\xe9s', u'\xe9ssent', u'est\xe0', u'estan', u'estat', u'estava', u'estem', u'esteu', u'estic', u'ets', u'fa', u'faig', u'fan', u'fas', u'fem', u'fer', u'feu', u'fi', u'haver', u'i', u'incl\xf2s', u'jo', u'la', u'les', u'llarg', u'llavors', u'mentre', u'meu', u'mode', u'molt', u'molts', u'nosaltres', u'o', u'on', u'per', u'per', u'per que', u'per\xf2', u'perqu\xe8', u'podem', u'poden', u'poder', u'podeu', u'potser', u'primer', u'puc', u'quan', u'quant', u'qui', u'sabem', u'saben', u'saber', u'sabeu', u'sap', u'saps', u'sense', u'ser', u'seu', u'seus', u'si', u'soc', u'solament', u'sols', u'som', u'sota', u'tamb\xe9', u'te', u'tene', u'tenim', u'tenir', u'teniu', u'teu', u'tinc', u'tot', u'\xfaltim', u'un', u'un', u'una', u'unes', u'uns', u'\xfas', u'va', u'vaig', u'van', u'vosaltres', u'']


    if global_language == "catalan":
        stemmer = SnowballStemmer("spanish")
    else:
        stemmer = SnowballStemmer(global_language)    
    
    #train the taggers here and keep the reference global

    if global_language == "english":

        _POS_TAGGER = 'taggers/maxent_treebank_pos_tagger/english.pickle'
        trigram_tagger = load(_POS_TAGGER)


    elif global_language == "spanish":
        train_sents = nltk.corpus.cess_esp.tagged_sents()
        unigram_tagger = nltk.UnigramTagger(train_sents)
        bigram_tagger = nltk.BigramTagger(train_sents, backoff = unigram_tagger)
        trigram_tagger = nltk.TrigramTagger(train_sents, backoff = bigram_tagger)

    else:
        train_sents = nltk.corpus.cess_cat.tagged_sents()
        unigram_tagger = nltk.UnigramTagger(train_sents)
        bigram_tagger = nltk.BigramTagger(train_sents, backoff = unigram_tagger)
        trigram_tagger = nltk.TrigramTagger(train_sents, backoff = bigram_tagger)

    #we have the taggers ready now. use them to extract the features!

    punctuation = list(string.punctuation)   
    punctuation_unicode = [unicode(punc) for punc in punctuation]
    punctuation_unicode.append(unicode("''")) 
    results = {}

    for lexelt in train:
        #print lexelt
        train_features, y_train = extract_features(train[lexelt])
        test_features, _ = extract_features(test[lexelt])

        X_train, X_test = vectorize(train_features,test_features)
        X_train_new, X_test_new = feature_selection(X_train, X_test,y_train)
        results[lexelt] = classify(X_train_new, X_test_new,y_train)

    A.print_results(results, answer)