“达观杯”文本智能处理挑战赛练手编码

最新推荐文章于 2019-06-24 23:10:20 发布

六号铺子

最新推荐文章于 2019-06-24 23:10:20 发布

阅读量1k

点赞数 2

本文链接：https://blog.csdn.net/sinat_39356629/article/details/81264774

版权

代码：

print ("开始......")

import pandas as pd
from sklearn.linear_model import LogisticRegression
from sklearn.feature_extraction.text import CountVectorizer

df_train = pd.read_csv('E:/yh/v0.0/train_set.csv')
df_test = pd.read_csv('E:/yh/v0.0/test_set.csv')
df_train.drop(columns=['article','id'],inplace=True)
df_test.drop(columns=['article'],inplace=True)

vectorizer = CountVectorizer(ngram_range=(1, 2), min_df=3,max_df=0.9, max_features=100000)
vectorizer.fit(df_train['word_seg'])
x_train = vectorizer.transform(df_train['word_seg'])
x_test = vectorizer.transform(df_test['word_seg'])
y_train = df_train['class']-1

lg = LogisticRegression(C=4, dual=True)
lg.fit(x_train, y_train)

y_test = lg.predict(x_test)

df_test['class'] = y_test.tolist()
df_test['class'] = df_test['class'] + 1
df_result = df_test.loc[:, ['id', 'class']]
df_result.to_csv('E:/yh/v0.0/result.csv', index=False)

print("完成...........")