北航学长的NLP赛事教程！

#安装相关依赖库 如果是windows系统，cmd命令框中输入pip安装，参考上述环境配置
#!pip install sklearn
#!pip install pandas
#---------------------------------------------------
#导入库
import pandas as pd
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.linear_model import SGDClassifier
from sklearn.model_selection import cross_val_score

#----------------数据探索----------------
#数据预处理
#加载训练集
train_df = pd.read_csv('./基于论文摘要的文本分类与查询性问答公开数据/train.csv', sep=',')
#加载测试集
test_df = pd.read_csv('./基于论文摘要的文本分类与查询性问答公开数据/test.csv', sep=',')

#EDA数据探索性分析
train_df.head()

test_df.head()

#----------------特征工程----------------
#将Topic(Label)编码
train_df['Topic(Label)'], lbl = pd.factorize(train_df['Topic(Label)'])

#将论文的标题与摘要组合为 text 特征
train_df['Title'] = train_df['Title'].apply(lambda x: x.strip())
train_df['Abstract'] = train_df['Abstract'].fillna('').apply(lambda x: x.strip())
train_df['text'] = train_df['Title'] + ' ' + train_df['Abstract']
train_df['text'] = train_df['text'].str.lower()

test_df['Title'] = test_df['Title'].apply(lambda x: x.strip())
test_df['Abstract'] = test_df['Abstract'].fillna('').apply(lambda x: x.strip())
test_df['text'] = test_df['Title'] + ' ' + test_df['Abstract']
test_df['text'] = test_df['text'].str.lower()

#使用tfidf算法做文本特征提取
tfidf = TfidfVectorizer(max_features=2500)

#----------------模型训练----------------

train_tfidf = tfidf.fit_transform(train_df['text'])
clf = SGDClassifier()
cross_val_score(clf, train_tfidf, train_df['Topic(Label)'], cv=5)

test_tfidf = tfidf.transform(test_df['text'])
clf = SGDClassifier()
clf.fit(train_tfidf, train_df['Topic(Label)'])
test_df['Topic(Label)'] = clf.predict(test_tfidf)

#----------------结果输出----------------
test_df['Topic(Label)'] = test_df['Topic(Label)'].apply(lambda x: lbl[x])
test_df[['Topic(Label)']].to_csv('submit.csv', index=None)