youtube-sentiment 0.3.0

tldr：对于传统模型，引导是最简单、最有效的方法

# Develop sentiment analysis classifier using traditional ML models# Pipeline modeling using the following guide: # https://ryan-cranfill.github.io/sentiment-pipeline-sklearn-1/# Data processing and cleaning guide:# https://towardsdatascience.com/another-twitter-sentiment-analysis-bb5b01ebad90# Importsimportnumpyasnpimporttimeimportpandasaspdimportmatplotlib.pyplotaspltimportrefrombs4importBeautifulSoupimportnltkfromsklearn.feature_extraction.textimportTfidfVectorizerfromsklearn.linear_modelimportLogisticRegressionfromsklearn.metricsimportaccuracy_score,log_loss,confusion_matrix,auc,roc_curvefromsklearn.model_selectionimportGridSearchCVfromsklearn.pipelineimportFeatureUnion,Pipelinefromsklearn.externalsimportjoblibfromsklearn.model_selectionimporttrain_test_split

# Dataset of 1.6m Twitter tweetscolumns=['sentiment','id','date','query_string','user','text']train=pd.read_csv('stanford_twitter_train.csv',encoding='latin-1',header=None,names=columns)test=pd.read_csv('stanford_twitter_test.csv',encoding='latin-1',header=None,names=columns)

## Local helpers# AUC visualizationdefshow_roc(model,test,test_labels):# Predictprobs=model.predict_proba(test)preds=probs[:,1]fpr,tpr,threshold=roc_curve(test_labels,preds)roc_auc=auc(fpr,tpr)# Chartplt.title('Receiver Operating Characteristic')plt.plot(fpr,tpr,'b',label='AUC = %0.2f'%roc_auc)plt.legend(loc='lower right')plt.plot([0,1],[0,1],'r--')plt.xlim([0,1])plt.ylim([0,1])plt.ylabel('True Positive Rate')plt.xlabel('False Positive Rate')plt.show()# Tweet cleansertok=nltk.tokenize.WordPunctTokenizer()pat1=r'@[A-Za-z0-9_]+'pat2=r'https?://[^ ]+'combined_pat=r'|'.join((pat1,pat2))www_pat=r'www.[^ ]+'negations_dic={"isn't":"is not","aren't":"are not","wasn't":"was not","weren't":"were not","haven't":"have not","hasn't":"has not","hadn't":"had not","won't":"will not","wouldn't":"would not","don't":"do not","doesn't":"does not","didn't":"did not","can't":"can not","couldn't":"could not","shouldn't":"should not","mightn't":"might not","mustn't":"must not"}neg_pattern=re.compile(r'\b('+'|'.join(negations_dic.keys())+r')\b')defclean_tweet(text):soup=BeautifulSoup(text,'lxml')souped=soup.get_text()try:bom_removed=souped.decode("utf-8-sig").replace(u"\ufffd","?")except:bom_removed=soupedstripped=re.sub(combined_pat,'',bom_removed)stripped=re.sub(www_pat,'',stripped)lower_case=stripped.lower()neg_handled=neg_pattern.sub(lambdax:negations_dic[x.group()],lower_case)letters_only=re.sub("[^a-zA-Z]"," ",neg_handled)# During the letters_only process two lines above, it has created unnecessay white spaces,# I will tokenize and join together to remove unneccessary white spaceswords=[xforxintok.tokenize(letters_only)iflen(x)>1]return(" ".join(words)).strip()

# Data cleaningcleaned_tweets=[]fortweetintrain['text']:cleaned_tweets.append(clean_tweet(tweet))cleaned_df=pd.DataFrame(cleaned_tweets,columns=['text'])cleaned_df['target']=train.sentimentcleaned_df.target[cleaned_df.target==4]=1# rename 4 to 1 as positive labelcleaned_df=cleaned_df[cleaned_df.target!=2]# remove neutral labelscleaned_df=cleaned_df.dropna()# drop null recordscleaned_df.to_csv('stanford_clean_twitter_train.csv',encoding='utf-8')

# Starting point from importcsv='stanford_clean_twitter_train.csv'df=pd.read_csv(csv,index_col=0)

# Random shuffle and ensure no null recordsdf=df.sample(frac=1).reset_index(drop=True)df=df.dropna()# drop null records

X,y=df.text[0:200000],df.target[0:200000]# Max data size 200k for memory purposesX_train,X_test,y_train,y_test=train_test_split(X,y,random_state=42,test_size=0.10)

# Dataset shapes post-splitprint(np.shape(X_train))print(np.shape(X_test))print(np.unique(y_train))

(180000,)
(20000,)
[0 1]

# NLTK Twitter tokenizer best used for short comment-type text setsimportnltktokenizer=nltk.casual.TweetTokenizer(preserve_case=False)

# Hyperparameter tuning (Simple model)#cvect = CountVectorizer(tokenizer=tokenizer.tokenize)tfidf=TfidfVectorizer()clf=LogisticRegression()pipeline=Pipeline([('tfidf',tfidf),('clf',clf)])parameters={'tfidf__ngram_range':[(1,1),(1,2),(1,3)],# ngram range of tokenizer'tfidf__norm':['l1','l2',None],# term vector normalization'tfidf__max_df':[0.25,0.5,1.0],# maximum document frequency for the CountVectorizer'clf__C':np.logspace(-2,0,3)# C value for the LogisticRegression}grid=GridSearchCV(pipeline,parameters,cv=3,verbose=1)print("Performing grid search...")print("pipeline:",[nameforname,_inpipeline.steps])t0=time.time()grid.fit(X_train,y_train)print("done in %0.3fs"%(time.time()-t0))print()print("Best score: %0.3f"%grid.best_score_)print("Best parameters set:")best_parameters=grid.best_estimator_.get_params()forparam_nameinsorted(parameters.keys()):print("\t%s: %r"%(param_name,best_parameters[param_name]))

Performing grid search...
pipeline: ['tfidf', 'clf']
Fitting 3 folds for each of 81 candidates, totalling 243 fits


[Parallel(n_jobs=1)]: Done 243 out of 243 | elapsed: 52.7min finished


done in 3186.295s

Best score: 0.803
Best parameters set:
	clf__C: 0.01
	tfidf__max_df: 0.25
	tfidf__ngram_range: (1, 3)
	tfidf__norm: None

# Dump model from grid search cvjoblib.dump(grid.best_estimator_,'lr_sentiment_cv.pkl',compress=1)

['lr_sentiment_cv.pkl']

# Starting point 2: Post-model load comparisonlra=joblib.load('./Models/Stanford_Twitter_Models/lr_sentiment_cv.pkl')lrb=joblib.load('./Models/Twitter_Simple_Models/lr_sentiment_basic.pkl')

# Model performance indicators for basic modely_pred_basic=lrb.predict(X_test)print(confusion_matrix(y_test,y_pred_basic))show_roc(lrb,X_test,y_test)# AUC

[[7562 2347]
 [2181 7910]]

# Model performance indicators for hypertuned modely_pred_hyper=lra.predict(X_test)print(confusion_matrix(y_test,y_pred_hyper))show_roc(lra,X_test,y_test)# AUC

[[7861 2048]
 [1863 8228]]

print(lrb.predict(["terrible idea why was this even made"]))print(lrb.predict(["that was the best movie ever"]))

[0]
[1]

标签：

• test
• import
• df
• 视频
• youtube
• not
• train
• 情绪
• sentiment
• cleaned

欢迎加入QQ群-->： 979659372

推荐PyPI第三方库

• xbrl_parser

  没有项目描述

• django-msgpack-serializer

  为django序列化msgpack。

• swimlane-python-logger

  泳道集成的记录器包装类

• inspire-matcher

  在Inspire中查找与给定记录或参考最相似的记录。

• sftpman

  一个命令行应用程序，帮助您装载sftp文件系统。

• DustyShock

  两次液体粉尘气体冲击。

• django-dbindexer

  Django的表达型NoSQL

• FauxIdent

  一个简单的、伪造的ident守护进程

• fakeable

  在单元测试期间，可以用“假”对象无缝替换“真”对象

• openerp-l10n-cr

  哥斯达黎加-会计

• openerp-auth-openid

  公开认证

• tranchitella.recipe.fs

  创建文件和目录的构建方法

• odoo10-addon-web-ckeditor4

  提供一个小部件，用于使用ckeditor 4.x编辑html字段

• sfs

  声场合成工具箱

• gitplots

  来自git日志的绘图