jieba分词-tfidf文本表征-SVM分类

jieba分词-tfidf文本表征-SVM分类

• 数据预处理

---

import pandas as pd
import jieba
import numpy as np
from sklearn import feature_extraction
from sklearn.feature_extraction.text import TfidfTransformer
from sklearn.feature_extraction.text import CountVectorizer
from sklearn import svm
from sklearn.metrics import precision_recall_fscore_support
from sklearn.svm import SVC

def read_data(url):
    data = pd.read_csv(url,encoding='utf-8')
    data.fillna("null",inplace=True)      #使用inplace参数会改掉本身 
    return data

数据清洗

def clean_text(text):
    text = str(text)
    text = text.replace('\n', '')
    text = text.replace('<br />', ' ')
    text = text<