大作業之中文文字分類(終稿)
阿新 • • 發佈:2018-12-22
import os import numpy as np import sys from datetime import datetime import gc path = 'H:\大三上大作業\python大作業\date' import jieba with open(r'H:\大三上大作業\python大作業\stopsCN.txt', encoding='utf-8') as f: stopwords = f.read().split('\n') #print(stopwords.shape)#檢視停用的字元數量 # for w in stopwords:#檢視stopwords檔案資料 # print(w) #文字預處理 def processing(tokens): tokens = "".join([char for char in tokens if char.isalpha()])# 去掉非字母漢字的字元 tokens = [token for token in jieba.cut(tokens, cut_all=True) if len(token) >= 2]#分詞 tokens = " ".join([token for token in tokens if token not in stopwords])# 去掉停用詞 return tokens tokenList = [] targetList = [] for root, dirs, files in os.walk(path): # print(root)#地址 # print(dirs)#子目錄 # print(files)#詳細檔名 for f in files: filePath = os.path.join(root, f)#地址拼接 with open(filePath, encoding='utf-8') as f: content = f.read() target = filePath.split('\\')[-2] targetList.append(target) tokenList.append(processing(content)) #建模 from sklearn.feature_extraction.text import TfidfVectorizer from sklearn.model_selection import train_test_split from sklearn.naive_bayes import GaussianNB, MultinomialNB from sklearn.model_selection import cross_val_score from sklearn.metrics import classification_report x_train, x_test, y_train, y_test = train_test_split(tokenList, targetList, test_size=0.3, stratify=targetList) vectorizer = TfidfVectorizer() X_train = vectorizer.fit_transform(x_train) X_test = vectorizer.transform(x_test) from sklearn.naive_bayes import MultinomialNB mnb = MultinomialNB() module = mnb.fit(X_train, y_train) y_predict = module.predict(X_test) scores = cross_val_score(mnb, X_test, y_test, cv=5) print("驗證結果:%.3f" % scores.mean()) print("分類結果:\n", classification_report(y_predict, y_test)) import collections # 測試集和預測集的各類新聞數量 testCount = collections.Counter(y_test) predCount = collections.Counter(y_predict) print('實際:', testCount, '\n', '預測', predCount) # 建立標籤列表,實際結果與預測結果 nameList = list(testCount.keys()) testList = list(testCount.values()) predictList = list(predCount.values()) x = list(range(len(nameList))) print("類別:", nameList, '\n', "實際:", testList, '\n', "預測:", predictList) # 畫圖 import matplotlib.pyplot as plt from pylab import mpl mpl.rcParams['font.sans-serif'] = ['FangSong'] # 指定字型 plt.figure(figsize=(7,5)) total_width, n = 0.6, 2 width = total_width / n plt.bar(x, testList, width=width,label='實際',fc = 'black') for i in range(len(x)): x[i] = x[i] + width plt.bar(x, predictList,width=width,label='預測',tick_label = nameList,fc='r') plt.grid() plt.title('實際和預測對比圖',fontsize=17) plt.xlabel('新聞類別',fontsize=17) plt.ylabel('頻數',fontsize=17) plt.legend(fontsize =17) plt.tick_params(labelsize=15) plt.show()