Python Bunch.sentence方法代码示例

本文整理汇总了Python中sklearn.datasets.base.Bunch.sentence方法的典型用法代码示例。如果您正苦于以下问题：Python Bunch.sentence方法的具体用法？Python Bunch.sentence怎么用？Python Bunch.sentence使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类sklearn.datasets.base.Bunch的用法示例。

在下文中一共展示了Bunch.sentence方法的3个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。

示例1: main

# 需要导入模块: from sklearn.datasets.base import Bunch [as 别名]
# 或者: from sklearn.datasets.base.Bunch import sentence [as 别名]
def main():
    print args
    print

    accuracies = defaultdict(lambda: [])

    ora_accu = defaultdict(lambda: [])

    oracle_accuracies =[]
    ora_cm = defaultdict(lambda: [])
    lbl_dit = defaultdict(lambda: [])

    aucs = defaultdict(lambda: [])

    x_axis = defaultdict(lambda: [])

    vct = TfidfVectorizer(encoding='ISO-8859-1', min_df=5, max_df=1.0, binary=False, ngram_range=(1, 1),
                          token_pattern='\\b\\w+\\b', tokenizer=StemTokenizer())

    print("Start loading ...")
    # data fields: data, bow, file_names, target_names, target

    ########## NEWS GROUPS ###############
    # easy to hard. see "Less is More" paper: http://axon.cs.byu.edu/~martinez/classes/678/Presentations/Clawson.pdf
    categories = [['alt.atheism', 'talk.religion.misc'],
                  ['comp.graphics', 'comp.windows.x'],
                  ['comp.os.ms-windows.misc', 'comp.sys.ibm.pc.hardware'],
                  ['rec.sport.baseball', 'sci.crypt']]

    min_size = 10

    args.fixk = None

    data, vct = load_from_file(args.train, [categories[3]], args.fixk, min_size, vct, raw=True)

    print("Data %s" % args.train)
    print("Data size %s" % len(data.train.data))

    parameters = experiment_utils.parse_parameters_mat(args.cost_model)

    print "Cost Parameters %s" % parameters

    cost_model = experiment_utils.set_cost_model(args.cost_function, parameters=parameters)
    print "\nCost Model: %s" % cost_model.__class__.__name__

    ### SENTENCE TRANSFORMATION
    if args.train == "twitter":
        sent_detector = TwitterSentenceTokenizer()
    else:
        sent_detector = nltk.data.load('tokenizers/punkt/english.pickle')

    ## delete <br> to "." to recognize as end of sentence
    data.train.data = experiment_utils.clean_html(data.train.data)
    data.test.data = experiment_utils.clean_html(data.test.data)

    print("Train:{}, Test:{}, {}".format(len(data.train.data), len(data.test.data), data.test.target.shape[0]))
    ## Get the features of the sentence dataset

    ## create splits of data: pool, test, oracle, sentences
    expert_data = Bunch()
    if not args.fulloracle:
        train_test_data = Bunch()

        expert_data.sentence, train_test_data.pool = split_data(data.train)
        expert_data.oracle, train_test_data.test = split_data(data.test)

        data.train.data = train_test_data.pool.train.data
        data.train.target = train_test_data.pool.train.target

        data.test.data = train_test_data.test.train.data
        data.test.target = train_test_data.test.train.target

    ## convert document to matrix
    data.train.bow = vct.fit_transform(data.train.data)
    data.test.bow = vct.transform(data.test.data)

    #### EXPERT CLASSIFIER: ORACLE
    print("Training Oracle expert")
    exp_clf = experiment_utils.set_classifier(args.classifier, parameter=args.expert_penalty)

    if not args.fulloracle:
        print "Training expert documents:%s" % len(expert_data.oracle.train.data)
        labels, sent_train = experiment_utils.split_data_sentences(expert_data.oracle.train, sent_detector, vct, limit=args.limit)

        expert_data.oracle.train.data = sent_train
        expert_data.oracle.train.target = np.array(labels)
        expert_data.oracle.train.bow = vct.transform(expert_data.oracle.train.data)

        exp_clf.fit(expert_data.oracle.train.bow, expert_data.oracle.train.target)
    else:
        # expert_data.data = np.concatenate((data.train.data, data.test.data))
        # expert_data.target = np.concatenate((data.train.target, data.test.target))
        expert_data.data =data.train.data
        expert_data.target = data.train.target
        expert_data.target_names = data.train.target_names
        labels, sent_train = experiment_utils.split_data_sentences(expert_data, sent_detector, vct, limit=args.limit)
        expert_data.bow = vct.transform(sent_train)
        expert_data.target = labels
        expert_data.data = sent_train
        exp_clf.fit(expert_data.bow, expert_data.target)
#.........这里部分代码省略.........

开发者ID:mramire8，项目名称:active，代码行数:103，代码来源:sent_unc.py

示例2: main

# 需要导入模块: from sklearn.datasets.base import Bunch [as 别名]
# 或者: from sklearn.datasets.base.Bunch import sentence [as 别名]
def main():


    vct = TfidfVectorizer(encoding='ISO-8859-1', min_df=1, max_df=1.0, binary=False, ngram_range=(1, 1),
                          token_pattern='\\b\\w+\\b')  #, tokenizer=StemTokenizer())

    vct_analizer = vct.build_tokenizer()

    print("Start loading ...")
    # data fields: data, bow, file_names, target_names, target

    ########## NEWS GROUPS ###############
    # easy to hard. see "Less is More" paper: http://axon.cs.byu.edu/~martinez/classes/678/Presentations/Clawson.pdf
    categories = [['alt.atheism', 'talk.religion.misc'],
                  ['comp.graphics', 'comp.windows.x'],
                  ['comp.os.ms-windows.misc', 'comp.sys.ibm.pc.hardware'],
                  ['rec.sport.baseball', 'sci.crypt']]

    min_size = 10  # max(10, args.fixk)

    args.fixk = None

    data, vct = load_from_file(args.train, [categories[3]], args.fixk, min_size, vct, raw=True)

    print("Data %s" % args.train)
    print("Data size %s" % len(data.train.data))


    ### SENTENCE TRANSFORMATION
    sent_detector = nltk.data.load('tokenizers/punkt/english.pickle')

    ## delete <br> to "." to recognize as end of sentence
    data.train.data = experiment_utils.clean_html(data.train.data)
    data.test.data = experiment_utils.clean_html(data.test.data)

    print("Train:{}, Test:{}, {}".format(len(data.train.data), len(data.test.data), data.test.target.shape[0]))
    ## Get the features of the sentence dataset

    ## create splits of data: pool, test, oracle, sentences
    expert_data = Bunch()
    train_test_data = Bunch()

    expert_data.sentence, train_test_data.pool = split_data(data.train)
    expert_data.oracle, train_test_data.test = split_data(data.test)

    data.train.data = train_test_data.pool.train.data
    data.train.target = train_test_data.pool.train.target

    data.test.data = train_test_data.test.train.data
    data.test.target = train_test_data.test.train.target

    ## convert document to matrix
    data.train.bow = vct.fit_transform(data.train.data)
    data.test.bow = vct.transform(data.test.data)

    #### EXPERT CLASSIFIER: ORACLE
    print("Training Oracle expert")

    labels, sent_train = split_data_sentences(expert_data.oracle.train, sent_detector)

    expert_data.oracle.train.data = sent_train
    expert_data.oracle.train.target = np.array(labels)
    expert_data.oracle.train.bow = vct.transform(expert_data.oracle.train.data)

    exp_clf = linear_model.LogisticRegression(penalty='l1', C=args.expert_penalty)
    exp_clf.fit(expert_data.oracle.train.bow, expert_data.oracle.train.target)


    #### EXPERT CLASSIFIER: SENTENCES
    print("Training sentence expert")
    labels, sent_train = split_data_sentences(expert_data.sentence.train, sent_detector)

    expert_data.sentence.train.data = sent_train
    expert_data.sentence.train.target = np.array(labels)
    expert_data.sentence.train.bow = vct.transform(expert_data.sentence.train.data)

    sent_clf = linear_model.LogisticRegression(penalty='l1', C=args.expert_penalty)
    sent_clf.fit(expert_data.sentence.train.bow, expert_data.sentence.train.target)

    #### TESTING THE CLASSIFERS

    test_target, test_data = split_data_sentences(data.test,sent_detector)
    test_data_bow = vct.transform(test_data)

    #pred_sent = sent_clf.predict(test_data_bow)
    pred_ora = exp_clf.predict(test_data_bow)
    y_probas = sent_clf.predict_proba(test_data_bow)
    pred_sent = sent_clf.classes_[np.argmax(y_probas, axis=1)]
    ## just based on one class probability
    # order = np.argsort(y_probas[:,0])
    order = np.argsort(y_probas.max(axis=1))
    print "ORACLE\tSENTENCE\tMAX-SENT"
    # for i in order[:500]:
    #     print pred_ora[i],pred_sent[i], y_probas[i,0], test_data[i]
    for i in order[-500:]:
        print pred_ora[i],pred_sent[i], y_probas[i,0], test_data[i]
    print "Accuracy of Sentences Classifier", metrics.accuracy_score(test_target, pred_sent)
    print "Class distribution: %s" % pred_sent.sum()
    print "Size of data: %s" % pred_sent.shape[0]
    sizes = [50, 100, 500, 1000, 2000, 3000, 4000, 20000]
#.........这里部分代码省略.........

开发者ID:mramire8，项目名称:active，代码行数:103，代码来源:test_sent.py

示例3: get_data

# 需要导入模块: from sklearn.datasets.base import Bunch [as 别名]
# 或者: from sklearn.datasets.base.Bunch import sentence [as 别名]
def get_data(clf, train, cats, fixk, min_size, vct, raw, limit=2):
    import copy
    min_size = 10

    args.fixk = None

    data, vct2 = load_from_file(train, cats, fixk, min_size, vct, raw=raw)

    print("Data %s" % args.train)
    print("Data size %s" % len(data.train.data))


    ### SENTENCE TRANSFORMATION
    sent_detector = nltk.data.load('tokenizers/punkt/english.pickle')

    ## delete <br> to "." to recognize as end of sentence
    data.train.data = clean_html(data.train.data)
    data.test.data = clean_html(data.test.data)

    print("Train:{}, Test:{}, {}".format(len(data.train.data), len(data.test.data), data.test.target.shape[0]))
    ## Get the features of the sentence dataset

    ## create splits of data: pool, test, oracle, sentences
    expert_data = Bunch()
    train_test_data = Bunch()

    expert_data.sentence, train_test_data.pool = split_data(data.train)
    expert_data.oracle, train_test_data.test = split_data(data.test)

    data.train.data = train_test_data.pool.train.data
    data.train.target = train_test_data.pool.train.target

    data.test.data = train_test_data.test.train.data
    data.test.target = train_test_data.test.train.target

    ## convert document to matrix
    data.train.bow = vct.fit_transform(data.train.data)
    data.test.bow = vct.transform(data.test.data)

    #### EXPERT CLASSIFIER: ORACLE
    print("Training Oracle expert")

    labels, sent_train = split_data_sentences(expert_data.oracle.train, sent_detector, vct, limit=limit)
    print len(sent_train)
    expert_data.oracle.train.data = sent_train
    expert_data.oracle.train.target = np.array(labels)
    expert_data.oracle.train.bow = vct.transform(expert_data.oracle.train.data)
    print expert_data.oracle.train.bow.shape
    # exp_clf = linear_model.LogisticRegression(penalty='l1', C=args.expert_penalty)
    exp_clf = copy.copy(clf)
    exp_clf.fit(expert_data.oracle.train.bow, expert_data.oracle.train.target)

    #### EXPERT CLASSIFIER: SENTENCES
    print("Training sentence expert")
    labels, sent_train = split_data_sentences(expert_data.sentence.train, sent_detector, vct, limit=limit)

    expert_data.sentence.train.data = sent_train
    expert_data.sentence.train.target = np.array(labels)
    expert_data.sentence.train.bow = vct.transform(expert_data.sentence.train.data)

    sent_clf = None
    # if args.cheating:
    sent_clf = copy.copy(clf)
    # sent_clf = linear_model.LogisticRegression(penalty='l1', C=args.expert_penalty)
    sent_clf.fit(expert_data.sentence.train.bow, expert_data.sentence.train.target)

    return exp_clf, data, vct, sent_clf, expert_data

开发者ID:mramire8，项目名称:active，代码行数:69，代码来源:score_distribution.py

注：本文中的sklearn.datasets.base.Bunch.sentence方法示例由纯净天空整理自Github/MSDocs等开源代码及文档管理平台，相关代码片段筛选自各路编程大神贡献的开源项目，源码版权归原作者所有，传播和使用请参考对应项目的License；未经允许，请勿转载。