特徵工程(二)TfidfVectorizer
阿新 • • 發佈:2018-12-11
''' 將原始資料的word特徵數字化為tfidf特徵,並將結果儲存到本地 article特徵可做類似處理 ''' import pandas as pd from sklearn.feature_extraction.text import TfidfVectorizer import pickle import time t_start = time.time() """===================================================================================================================== 1 資料預處理 """ df_train = pd.read_csv('train_set.csv') df_test = pd.read_csv('test_set.csv') df_train.drop(columns='article', inplace=True) #article word_seg df_test.drop(columns='article', inplace=True) df_all = pd.concat(objs=[df_train, df_test], axis=0, sort=True) y_train = (df_train['class'] - 1).values # 演算法的分類預測結果是從0開始的,所以訓練集的分類標籤也要從0開始 """===================================================================================================================== 2 特徵工程 """ vectorizer = TfidfVectorizer(ngram_range=(1, 2), min_df=3, max_df=0.9, sublinear_tf=True) vectorizer.fit(df_all['word_seg']) x_train = vectorizer.transform(df_train['word_seg']) x_test = vectorizer.transform(df_test['word_seg']) """===================================================================================================================== 3 儲存至本地 """ data = (x_train, y_train, x_test) with open('tfidf_word.pkl', 'wb') as f: pickle.dump(data, f) t_end = time.time() print("共耗時:{}min".format((t_end-t_start)/60))