目录
4.1、CountVectors+RidgeClassifier
4.3、MultinomialNB +CountVectors
1、读取数据
import pandas as pd
import seaborn as sns
# nrows=100 设置读取100行数据
train_df = pd.read_csv('新建文件夹/天池—新闻文本分类/train_set.csv', sep='\t')
print(train_df.head())
label text 0 2 2967 6758 339 2021 1854 3731 4109 3792 4149 15... 1 11 4464 486 6352 5619 2465 4802 1452 3137 5778 54... 2 3 7346 4068 5074 3747 5681 6093 1777 2226 7354 6... 3 2 7159 948 4866 2109 5520 2490 211 3956 5520 549... 4 3 3646 3055 3055 2490 4659 6065 3370 5814 2465 5...
查看句子长度
#句子长度分析
train_df['text_len'] = train_df['text'].apply(lambda x: len(x.split(' ')))
print(train_df['text_len'].describe())
#平均长度907.207110
count 200000.000000 mean 907.207110 std 996.029036 min 2.000000 25% 374.000000 50% 676.000000 75% 1131.000000 max 57921.000000 Name: text_len, dtype: float64
2、可视化
2.1、新闻的字数分布
由图可知，字数 10000以上的新闻文本是极少数，小于5000
import matplotlib.pyplot as plt
_ = plt.hist(train_df['text_len'], bins=200)
plt.xlabel('Text char count')
plt.title("Histogram of char count")
plt.show()
2.2、新闻文本类别统计
train_df['label'].value_counts().plot(kind = 'bar')
plt.title('News class count')
plt.xlabel('category')
plt.show()数据集中标签的对应的关系如下：{‘科技’: 0, ‘股票’: 1, ‘体育’: 2, ‘娱乐’: 3, ‘时政’: 4, ‘社会’: 5, ‘教育’: 6, ‘财经’: 7, ‘家居’: 8, ‘游戏’: 9, ‘房产’: 10, ‘时尚’: 11, ‘彩票’: 12, ‘星座’: 13}
- 由图知，科技，股票，体育类别的新闻占比最多
3、数据分析
3.1、统计每个字符出现的次数
- Counter（）是collections里面的一个类，作用是计算出字符串或者列表等中不同元素出现的个数，返回值可以理解为一个字典： {"字符"：”字符出现次数“}
#统计每个字符出现的次数
from collections import Counter
#先将所有字符用空格连接起来
all_lines = ' '.join(list(train_df['text']))
#统计按空格切割的字符数目
#Counter 返回字典，key为元素，值为元素个数。
word_count = Counter(all_lines.split(' '))
#按降序排列字符出现的次数 #排的是次数
word_count = sorted(word_count.items(),key = lambda d : d[1],reverse = True)
#打印字符的数量
print('len(word_count) : ',len(word_count))
#打印第一个字符出现的次数
print('word_count[0]:',word_count[0])
#打印最后一个字符出现的次数
print('word_count[-1]:',word_count[-1])
'''
len(word_count) : 6869
word_count[0]: ('3750', 7482224)
word_count[-1]: ('3133', 1)'''
#训练集中总共包括6869个字，其中编号3750的字出现的次数最多，编号3133的字出现的次数最少。3.2、统计不同字符在句子中出现的次数
- list(set())：对原列表去重并按从小到大排序
- 将text中的字符用空格切割并打乱成无序列表，用空格连接无序列表
- 重复出现多次的很有可能是标点符号，字符3750，字符900和字符648在20w新闻的覆盖率接近99%，很有可能是标点符号。
#统计不同字符在句子中出现的次数
train_df['text_unique'] = train_df['text'].apply(lambda x : ' '.join(list(set(x.split(' ')))))
all_lines = ' '.join(list(train_df['text_unique']))
word_count = Counter(all_lines.split(' '))
#按降序排列字符出现的次数 #排的是次数
word_count = sorted(word_count.items(),key = lambda d :int(d[1]),reverse = True)
#打印出现次数前三的字符
print('word_count[0]:',word_count[0])
print('word_count[1]:',word_count[1])
print('word_count[2]:',word_count[2])
'''word_count[0]: ('3750', 197997)
word_count[1]: ('900', 197653)
word_count[2]: ('648', 191975)'''
4、文本特征提取
4.1、CountVectors+RidgeClassifier
from sklearn.feature_extraction.text import CountVectorizer
vectorizer = CountVectorizer(max_features = 3000,ngram_range=(1,3))
train_text = vectorizer.fit_transform(train_df['text'])
#CountVectors+RidgeClassifier
import pandas as pd
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.linear_model import RidgeClassifier
from sklearn.metrics import f1_score
from sklearn.model_selection import train_test_split
df = pd.read_csv('新建文件夹/天池—新闻文本分类/train_set.csv', sep='\t',nrows = 15000)
##统计每个字出现的次数，并赋值为0/1 用词袋表示text（特征集）
##max_features=3000，文档中出现频率最多的前3000个词
#ngram_range（1,3）（单个字，两个字，三个字 都会统计
vectorizer = CountVectorizer(max_features = 3000,ngram_range=(1,3))
train_text = vectorizer.fit_transform(train_df['text'])
X_train,X_val,y_train,y_val = train_test_split(train_text,df.label,test_size = 0.3)
#岭回归拟合训练集（包含text 和 label）
clf = RidgeClassifier()
clf.fit(X_train,y_train)
val_pred = clf.predict(X_val)
f1_score_cv = f1_score(y_val,val_pred,average = 'macro')
print(f1_score_cv)4.2、TF-IDF + RidgeClassifier
#TF-IDF + RidgeClassifier
import pandas as pd
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.linear_model import RidgeClassifier
from sklearn.metrics import f1_score
df = pd.read_csv('新建文件夹/天池—新闻文本分类/train_set.csv', sep='\t',nrows = 15000)
train_test = TfidfVectorizer(ngram_range=(1,3),max_features = 3000).fit_transform(df.text)
X_train,X_val,y_train,y_val = train_test_split(train_text,df.label,test_size = 0.3)
clf = RidgeClassifier()
clf.fit(X_train,y_train)
val_pred = clf.predict(X_val)
f1_score_tfidf = f1_score(y_val,val_pred,average = 'macro')
print(f1_score_tfidf)4.3、MultinomialNB +CountVectors
from sklearn.naive_bayes import MultinomialNB
df = pd.read_csv('新建文件夹/天池—新闻文本分类/train_set.csv', sep='\t',nrows = 15000)
##统计每个字出现的次数，并赋值为0/1 用词袋表示text（特征集）
##max_features=3000文档中出现频率最多的前3000个词
#ngram_range（1,3）（单个字，两个字，三个字 都会统计
vectorizer = CountVectorizer(max_features = 3000,ngram_range=(1,3))
train_text = vectorizer.fit_transform(train_df['text'])
X_train,X_val,y_train,y_val = train_test_split(train_text,df.label,test_size = 0.3)
clf = MultinomialNB()
clf.fit(X_train,y_train)
val_pre_CountVec_NBC = clf.predict(X_val)
score_f1_CountVec_NBC = f1_score(y_val,val_pre_CountVec_NBC,average='macro')
print('CountVec + MultinomialNB : %.4f' %score_f1_CountVec_NBC )4.4、MultinomialNB +TF-IDF
df = pd.read_csv('新建文件夹/天池—新闻文本分类/train_set.csv', sep='\t',nrows = 15000)
train_test = TfidfVectorizer(ngram_range=(1,3),max_features = 3000).fit_transform(df.text)
X_train,X_val,y_train,y_val = train_test_split(train_text,df.label,test_size = 0.3)
clf = MultinomialNB()
clf.fit(X_train,y_train)
val_pre_tfidf_NBC = clf.predict(X_val)
score_f1_tfidf_NBC = f1_score(y_val,val_pre_tfidf_NBC,average='macro')
print('TF-IDF + MultinomialNB : %.4f' %score_f1_tfidf_NBC )4.5、 绘图
import matplotlib.pyplot as plt
import numpy as np
%matplotlib inline
scores = [f1_score_cv , f1_score_tfidf , score_f1_CountVec_NBC , score_f1_tfidf_NBC]
x_ticks = np.arange(4)
x_ticks_label = ['CountVec_RidgeClassifier','tfidf_RidgeClassifier','CountVec_NBC','tfidf_NBC']
plt.plot(x_ticks,scores)
plt.xticks(x_ticks, x_ticks_label, fontsize=8) #指定字体
plt.ylabel('F1_score')
plt.show()