【数据竞赛】“达观杯”文本智能处理挑战赛１

一 读取数据

import pandas as pd
from sklearn.model_selection import train_test_split

# 读取数据
df_train = pd.read_csv('./new_data/train_set.csv',index_col='id')
test_data = pd.read_csv('./new_data/test_set.csv',index_col='id')
train_data = df_train.drop(['class'],axis=1)
train_lable = df_train['class']

数据划分

X_train,X_test,Y_train,Y_test =  train_test_split(train_data, train_lable, test_size=0.3, random_state=2019)