資源簡(jiǎn)介
Al_challenger細(xì)粒度情感分析數(shù)據(jù)集,包含ai_challenger_sentiment_analysis_testa_20180816、ai_challenger_sentiment_analysis_trainingset_20180816、ai_challenger_sentiment_analysis_validationset_20180816

代碼片段和文件信息
import?numpy?as?np
import?pickle
def?get_data(file_path):
????data?=?[]
????with?open(file_path)?as?f:
????????for?line?in?f:
????????????data.append(line.strip())
????return?data
train_content_ori?=?get_data(
????‘../data/ai_challenger_sentiment_analysis_trainingset_20180816/sentiment_analysis_trainingset_cut_word_rst.txt‘)
val_content_ori?=?get_data(
????‘../data/ai_challenger_sentiment_analysis_validationset_20180816/sentiment_analysis_validationset_cut_word_rst.txt‘)
test_content_ori?=?get_data(
????‘../data/ai_challenger_sentiment_analysis_testa_20180816/sentiment_analysis_testa_cut_word_rst.txt‘)
print(len(train_content_ori)?len(val_content_ori)?len(test_content_ori))
from?sklearn.feature_extraction.text?import?TfidfVectorizer
vectorizer?=?TfidfVectorizer()
vectorizer.fit(train_content_ori)
train_content?=?vectorizer.transform(train_content_ori)
val_content?=?vectorizer.transform(val_content_ori)
test_content?=?vectorizer.transform(test_content_ori)
from?sklearn.decomposition?import?TruncatedSVD
svd?=?TruncatedSVD(n_components=20?*?4?n_iter=7?random_state=2018)
svd.fit(train_content)
train_svd?=?svd.transform(train_content)
val_svd?=?svd.transform(val_content)
test_svd?=?svd.transform(test_content)
prefix?=?‘svd_tfidf_withP_80‘
np.save(‘../data/%s_train‘?%?prefix?train_svd)
np.save(‘../data/%s_val‘?%?prefix?val_svd)
np.save(‘../data/%s_test‘?%?prefix?test_svd)
pickle.dump(svd?open(‘../data/%s.pk‘?%?prefix?‘wb‘))
?屬性????????????大小?????日期????時(shí)間???名稱(chēng)
-----------?---------??----------?-----??----
?????目錄???????????0??2018-11-16?09:29??Al_challenger_2018_sentiment_analysis-master\
?????文件????????1056??2018-11-16?09:29??Al_challenger_2018_sentiment_analysis-master\.gitignore
?????目錄???????????0??2018-11-16?09:29??Al_challenger_2018_sentiment_analysis-master\.idea\
?????文件?????????459??2018-11-16?09:29??Al_challenger_2018_sentiment_analysis-master\.idea\Al_challenger_2018_sentiment_analysis.iml
?????文件?????????599??2018-11-16?09:29??Al_challenger_2018_sentiment_analysis-master\.idea\misc.xm
?????文件?????????326??2018-11-16?09:29??Al_challenger_2018_sentiment_analysis-master\.idea\modules.xm
?????文件???????31566??2018-11-16?09:29??Al_challenger_2018_sentiment_analysis-master\.idea\workspace.xm
?????文件????????3788??2018-11-16?09:29??Al_challenger_2018_sentiment_analysis-master\README.md
?????目錄???????????0??2018-11-16?09:29??Al_challenger_2018_sentiment_analysis-master\code\
?????文件???????19447??2018-11-16?09:29??Al_challenger_2018_sentiment_analysis-master\code\GCAE_word_char.py
?????文件???????25901??2018-11-16?09:29??Al_challenger_2018_sentiment_analysis-master\code\SynAtt_expand_model.py
?????文件????????1463??2018-11-16?09:29??Al_challenger_2018_sentiment_analysis-master\code\feature.py
?????目錄???????????0??2018-11-16?09:29??Al_challenger_2018_sentiment_analysis-master\code\models\
?????文件???????????1??2018-11-16?09:29??Al_challenger_2018_sentiment_analysis-master\code\models\tmp.txt
?????目錄???????????0??2018-11-16?09:29??Al_challenger_2018_sentiment_analysis-master\code\tf_graph\
?????文件???????????1??2018-11-16?09:29??Al_challenger_2018_sentiment_analysis-master\code\tf_graph\tmp.txt
?????文件???????14737??2018-11-16?09:29??Al_challenger_2018_sentiment_analysis-master\code\train.py
?????文件???????10890??2018-11-16?09:29??Al_challenger_2018_sentiment_analysis-master\code\utils.py
?????文件????????3730??2018-11-16?09:29??Al_challenger_2018_sentiment_analysis-master\code\word2vec.py
?????目錄???????????0??2018-11-16?09:29??Al_challenger_2018_sentiment_analysis-master\data\
?????文件????????2077??2018-11-16?09:29??Al_challenger_2018_sentiment_analysis-master\data\哈工大停用標(biāo)點(diǎn)表.txt
?????文件????????5275??2018-11-16?09:29??Al_challenger_2018_sentiment_analysis-master\data\哈工大停用詞表擴(kuò)展.txt
?????目錄???????????0??2018-11-16?09:29??Al_challenger_2018_sentiment_analysis-master\readme_resource\
?????文件???????14338??2018-11-16?09:29??Al_challenger_2018_sentiment_analysis-master\readme_resource\GCAE.jpg
?????文件???????34821??2018-11-16?09:29??Al_challenger_2018_sentiment_analysis-master\readme_resource\SynAtt.jpg
?????文件?????????266??2018-11-16?09:29??Al_challenger_2018_sentiment_analysis-master\run.sh
評(píng)論
共有 條評(píng)論