达观杯DAY1

from sklearn.model_selection import train_test_split

#读取训练集和测试集数据
train_df = pd.read_csv('data/train_set.csv')
train_df.head()
#读取测试集数据
test_df = pd.read_csv('data/test_set.csv')
test_df.head()

#训练特征集
train_df_train_data = train_df[['id','article','word_seg']]
#训练标签
train_df_train_target = train_df['class']
 
x_train,x_test,y_train,y_test = train_test_split(train_df_train_data,train_df_train_target,test_size = 0.3,random_state = 2019)