原文網址：
https://segmentfault.com/a/1190000021947908

import pandas as pd import jieba import re #邏輯回歸建模需要的庫 from sklearn.model_selection import train_test_split from sklearn.feature_extraction.text import CountVectorizer from sklearn.linear_model import LogisticRegression import numpy as np from pandas import DataFramedf1 = [{"name":"整兒錢小姐","short":"少年的你值得一看"}] df2 = [{"rating":[('50','力薦')]}] data = pd.merge(df1,df2,how = 'outer') print(data.shape)#劃分等級 def rating(e):if '50' in e:return 5if '40' in e:return 4if '30' in e:return 3if '20' in e:return 2if '10' in e:return 1data['new_rating'] = data['rating'].map(rating) print(data.head())#剔除中性的評價 new_data = data[data['new_rating'] != 3] new_data['sentiment'] = new_data['new_rating'].apply(lambda x : +1 if x>3 else -1)print(new_data['sentiment'].value_counts())#分詞 def cut_word(text):text = jieba.cut(str(text), cut_all = False)return " ".join(text) new_data['new_short'] = new_data['short'].apply(cut_word)#刪除數字 def remove_num(new_short):return re.sub(r'\d+','',new_short)#刪除字母 def remove_word(new_short):return re.sub(r'[a-z]+','',new_short)new_data['new_short'] = new_data['new_short'].apply(remove_num) new_data['new_short'] = new_data['new_short'].apply(remove_word)#邏輯回歸分析與建模 #第一步需要對分析好的數據進行數據劃分，分為訓練集和測試集 train_data, test_data = train_test_split(new_data, train_size = 0.8,random_stat=0)#文本提取 transfer = CountVectorizer() train_word = transfer.fit_transform(train_data['new_short']) test_word = transfer.transform(test_data['new_short'])#稀疏矩陣 print('new_data:\n', train_word.toarray())#特征值 print('feature_name:\n',transfer.get_feature_names())#第二步對分詞后的文本進行特征提取，可以生成一個對應的稀疏矩陣，并且得到稀疏矩陣對應的特征值 #第三步利用邏輯回歸建模，即讓訓練集中的特征值和目標值進行擬合，從而生成一個模型 x_train, x_test,y_train,y_test = train_test_split(new_data['new_short'],new_data['sentiment'],train_size = 0.8, random_state = 0) x_train = train_word x_test = test_word model = LogisticRegression() model.fit(x_train,y_train) y_predict = model.predict(x_test) print('布爾比對：\n',y_predict==y_test) score = model.score(x_test,y_test) print('模型準確率：\n',score)example = test_data[50:55] example[['short','new_rating','sentiment']]possibility = model.predict_proba(test_word)[:,1] test_data.loc[:,'possibility'] = possibility print(test_data.head())

總結

以上是生活随笔為你收集整理的《少年的你》短评情感分析——机器学习之逻辑回归的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。