kesci---2019大数据挑战赛预选赛---情感分析

一、预选赛题------文本情感分类模型

本预选赛要求选手建立文本情感分类模型，选手用训练好的模型对测试集中的文本情感进行预测，判断其情感为「Negative」或者「Positive」。所提交的结果按照指定的评价指标使用在线评测数据进行评测，达到或超过规定的分数线即通过预选赛。

二、比赛数据

训练集数据：(6328个样本）

测试集数据（2712个样本）

评价方法：AUC

三、分析

1、加载模块

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import re
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
from sklearn.metrics import f1_score
from sklearn.feature_extraction.text import TfidfTransformer,TfidfVectorizer

2、数据读取

train_data = pd.read_csv('./data/train.csv',engine = 'python')
test_data = pd.read_csv('./data/20190520_test.csv')

3、数据预处理

test_data.info()  ###可以看到有5个缺失值。

   ###缺失值处理

train_data = train_data.dropna (axis=0,subset = ['label'])

###标签数据处理，label转成（0,1）

train_data['label'] = train_data['label'].replace(to_replace=['Positive', 'Negative'], value=[0, 1])

###评论数据处理

    1、去除一些【标点符号、数字、特殊符号、等】
    2、分词，去除句子的空格前缀(strip)，单词最小化（lower)
    3、去除一些【短词】和【停用词】，大多数太短的词起不到什么作用，比如‘pdx’，‘his’，‘all’。
    4、提取词干，将不同但同义的词转化成相同的词，如loves，loving，lovable变成love

###评论数据处理
def filter_fun(line):
    #表示将data中的除了大小写字母之外的符号换成空格,去除一些标点符号、特征符号、数字等
    line = re.sub(r'[^a-zA-Z]',' ',line)
    ##单词小写化
    line = line.lower()
    return line

train_data['review'] = train_data['review'].apply(filter_fun)
test_data['review'] = test_data['review'].apply(filter_fun)
##把空格前缀去除
train_data['review'] = train_data['review'].str.strip()
test_data['review'] = test_data['review'].str.strip()

##删除短单词
train_data['review'] = train_data['review'].apply(lambda x:' '.join([w for w in x.split() if len(w) > 3]))
test_data['review'] = test_data['review'].apply(lambda x:' '.join([w for w in x.split() if len(w) > 3]))

##分词
train_data['review'] = train_data['review'].str.split()
test_data['review'] = test_data['review'].str.split()

##提取词干，即基于规则从单词中去除后缀的过程。例如，play，player，played，plays，playing都是play的变种。
from nltk.stem.porter import *
stemmer =PorterStemmer()
train_data['review'] = train_data['review'].apply(lambda x: [stemmer.stem(i) for i in x])
test_data['review'] = test_data['review'].apply(lambda x: [stemmer.stem(i) for i in x])

train_data['review'] = train_data['review'].apply(lambda x:" ".join(x))
test_data['review'] = test_data['review'].apply(lambda x:" ".join(x))

########################以下部分可以不处理##################

3、数据分析

在这次比赛中数据分析没起什么作用，因为评论做了脱敏处理。

####################################
    1、数据集中最常见的单词有哪些？【可采用词云】
    2、数据集上表述积极和消极的常见词汇有哪些？【可采用词云】
    3、评论一般有多少主题标签？
    4、我的数据集跟哪些趋势相关？
    5、哪些趋势跟情绪相关？他们和情绪是吻合的吗？
　　 6、词长与频次的关系【画柱状图，此次代码中平均词长为15】

#使用 词云 来了解评论中最常用的词汇
all_words = ' '.join([text for text in combi['review']])
from wordcloud import WordCloud
wordcloud = WordCloud(width=800, height=500, random_state=21, max_font_size=110).generate(all_words)
plt.figure(figsize=(10, 7))
plt.imshow(wordcloud, interpolation="bilinear")
plt.axis('off')
plt.show()

# 积极数据
positive_words =' '.join([text for text in combi['review'][combi['label'] == 0]])
wordcloud = WordCloud(width=800, height=500, random_state=21, max_font_size=110).generate(positive_words)
plt.figure(figsize=(10, 7))
plt.imshow(wordcloud, interpolation="bilinear")
plt.axis('off')
plt.show()

# 消极数据
negative_words = ' '.join([text for text in combi['review'][combi['label'] == 1]])
wordcloud = WordCloud(width=800, height=500,random_state=21, max_font_size=110).generate(negative_words)
plt.figure(figsize=(10, 7))
plt.imshow(wordcloud, interpolation="bilinear")
plt.axis('off')
plt.show()

def hashtag_extract(x):
    hashtags = []    # Loop over the words in the tweet
    for i in x:
        ht = re.findall(r"#(\w+)", i)
        hashtags.append(ht)
    return hashtags

# extracting hashtags from non racist/sexist tweets
HT_positive = hashtag_extract(combi['review'][combi['label'] == 0])
# extracting hashtags from racist/sexist tweets
HT_negative = hashtag_extract(combi['review'][combi['label'] == 1])
# unnesting list
HT_positive = sum(HT_positive,[])
HT_negative = sum(HT_negative,[])

# 画积极标签
a = nltk.FreqDist(HT_positive)
d = pd.DataFrame({'Hashtag': list(a.keys()),'Count': list(a.values())})
# selecting top 10 most frequent hashtags
d = d.nlargest(columns="Count", n = 10)
#前十
plt.figure(figsize=(16,5))
ax = sns.barplot(data=d, x= "Hashtag", y = "Count")
ax.set(ylabel = 'Count')
plt.show()

# 画消极标签
b = nltk.FreqDist(HT_negative)
e = pd.DataFrame({'Hashtag': list(b.keys()),'Count': list(b.values())})
# selecting top 10 most frequent
hashtagse = e.nlargest(columns="Count", n = 10)
plt.figure(figsize=(16,5))
ax = sns.barplot(data=e, x= "Hashtag", y = "Count")
ax.set(ylabel = 'Count')
plt.show()

##数据分析
def split_word(s):
    return len(s.split())
train_data['word_length'] = train_data['review'].apply(split_word)
sum_len , nums ,maxnum , minnum = sum(train_data['word_length']) , len(train_data['word_length']) , max(train_data['word_length']) ,min(train_data['word_length'])
print("all words number: {0} , mean word length : {1} ,max word length: {2} and min: {3} ".format(sum_len , sum_len // nums , maxnum,minnum))

##评论词长---频次
plt.xlabel('length')
plt.ylabel('frequency')
plt.hist(train_data['word_length'],bins = 150)
plt.axis([0,100,0,800])
plt.show()

#######################################################3

4、模型

　　训练模型----两部分（文本特征提取、文本分类）

    1、文本特征提取：词袋模型、TF_IDF、word_embbeding
    2、文本分类：逻辑回归、SVM、贝叶斯、LSTM、textCNN等

    【在这次预选赛中，效果最好的是 TF_IDF + 贝叶斯 ----0.86】
    【试了 词袋模型 + LR 和 TF_IDF + LR（这两种效果最差）、词袋模型 + 贝叶斯 （效果一般）----0.84、TF_IDF + 贝叶斯（效果最好）】

（1）文本特征提取：

　　①词袋模型

#构建词袋模型
from sklearn.feature_extraction.text import CountVectorizer
bow_vectorizer = CountVectorizer(max_df=0.30, max_features=8200, stop_words='english')
X_train = bow_vectorizer.fit_transform(train_data['review'])
X_test = bow_vectorizer.fit_transform(test_data['review'])
print(test_data.describe())
print(X_train.toarray())

　　②TF-IDF模型

#####TF-IDF模型
ngram = 2
vectorizer = TfidfVectorizer(sublinear_tf=True,ngram_range=(1, ngram), max_df=0.5)

X_all = train_data['review'].values.tolist() + test_data['review'].values.tolist() # Combine both to fit the TFIDF vectorization.
lentrain = len(train_data)

vectorizer.fit(X_all)
X_all = vectorizer.transform(X_all)

X_train = X_all[:lentrain] # Separate back into training and test sets.
X_test = X_all[lentrain:]

（2）文本分类模型

　　①逻辑回归

# 逻辑回归构建模型 

#切分训练集和测试集
# xtrain_bow, xvalid_bow, ytrain, yvalid = train_test_split(X_train, train_data['label'], random_state=42, test_size=0.3)
X_train_part,X_test_part,y_train_part,y_test_part = train_test_split(X_train,train_data['label'],test_size = 0.2)
# 使用词袋模型特征集合构建模型

lreg = LogisticRegression()
lreg.fit(X_train_part, y_train_part)
prediction = lreg.predict_proba(X_test_part)
# predicting on the validation set
prediction_int = prediction[:,1] >= 0.3
prediction_int = prediction_int.astype(np.int)
print("回归f",f1_score(y_test_part, prediction_int)) # calculating f1 score
fpr, tpr, thresholds = roc_curve(y_test_part, prediction_int)
print('回归auc',auc(fpr, tpr))

test_pred = lreg.predict_proba(X_test)

print("这里P:",test_pred)

保存测试结果

print(test_pred.size)
test_pred_int = test_pred[:,1]    #提取我们需要预测的test的label列
print(test_pred_int.size)    #看看进过模型预测后的长度是否有变化
print(pd.DataFrame(test_data,columns=["ID"]).size)     #看看原始test的数据列有多少  

test_data['Pred'] = test_pred_int
submission = test_data[['ID','Pred']]
submission.to_csv('./result.csv', index=False) # writing data to a CSV file

　　②贝叶斯模型

from sklearn.model_selection import  train_test_split,KFold
#from sklearn.linear_model import LogisticRegression
from sklearn.naive_bayes import GaussianNB,BernoulliNB,MultinomialNB
from sklearn.metrics import roc_auc_score,auc,roc_curve
#from sklearn.svm import SVC
#import xgboost as xgb

X_train_part,X_test_part,y_train_part,y_test_part = train_test_split(X_train,train_data['label'],test_size = 0.2)

clf = MultinomialNB()
clf.fit(X_train_part,y_train_part)

y_pred = clf.predict_proba(X_train_part)
fpr, tpr, thresholds = roc_curve(y_train_part, y_pred[:,1])
auc(fpr, tpr)  ###0.9992496306904572

y_pred = clf.predict_proba(X_test_part)
fpr, tpr, thresholds = roc_curve(y_test_part, y_pred[:,1])
auc(fpr, tpr) ###0.8613719824212871

clf = MultinomialNB() clf.fit(X_train,train_data['label']) y_pred_text = clf.predict_proba(X_test) ##保存测试结果 submit = pd.DataFrame() submit['ID'] = test['ID'] submit['Pred'] = y_pred_text[:,1] submit.to_csv('submit_bayes_2.csv',index=False)

参考：https://blog.csdn.net/Strawberry_595/article/details/90205761