import pandas as pd
import random
import jieba
import jieba.analyse
import re
from sklearn.model_selection import train_test_split
from numpy import *
#导入正例负例数据
def load_datas(bid):
Pfilename = 'result'+str(bid)+'positive.csv'
df_P = pd.DataFrame(pd.read_csv(Pfilename, encoding='utf-8'))
Nfilename = 'result'+str(bid)+'negative.csv'
df_N = pd.DataFrame(pd.read_csv(Nfilename, encoding='utf-8'))
#为正例打标签1
df_P = df_P[['name']]
df_P['label'] = 1
#为负例打标签0
df_N = df_N[['name']]
df_N['label'] = 0
#将正例和负例合并成一个大表
df_P_part = df_P
df_N_part = df_N
pd_merge = pd.concat([df_P_part,df_N_part])
return pd_merge
def randSplit(dataSet,n):
dataSet = {
"name": pd.Series(dataSet["name"].values),
"label": pd.Series(dataSet["label"].values)}
datas = pd.DataFrame(dataSet)
data_rdm = datas.sample(n)
朴素贝叶斯(手撕代码Python3)
最新推荐文章于 2023-06-15 11:07:27 发布
本文详细介绍了朴素贝叶斯分类器的工作原理,并提供了使用Python3从头实现的示例代码,帮助读者深入理解这一重要的机器学习算法。
摘要由CSDN通过智能技术生成