自然语言处理 Task 2 数据读取与数据分析

Task2 数据读取与数据分析

import pandas as pd  #引入pandas库
import matplotlib.pyplot as plt  #引入matplotlib
train_df = pd.read_csv(r'D:\NLP\train_set.csv', sep='\t', nrows=200000)
#导入数据集
train_df.head(5)  #前五个数据

train_df['text_len'] = train_df['text'].apply(lambda x: len(x.split(' ')))
print(train_df['text_len'].describe())
#分析数据基本情况

_ = plt.hist(train_df['text_len'], bins=200)
plt.xlabel('Text char count')
plt.title("Histogram of char count")
#分析句长分布图

train_df['label'].value_counts().plot(kind='bar')
plt.title('News class count')
plt.xlabel("category")
#分析类别分布图

from collections import Counter
all_lines = ' '.join(list(train_df['text']))
word_count = Counter(all_lines.split(" "))
word_count = sorted(word_count.items(), key=lambda d:d[1], reverse = True)

print(len(word_count))
# 6869

print(word_count[0])
# ('3750', 7482224)

print(word_count[-1])
# ('3133', 1)
#字符分布统计

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(" "))
word_count = sorted(word_count.items(), key=lambda d:int(d[1]), reverse = True)

print(word_count[0])
# ('3750', 197997)

print(word_count[1])
# ('900', 197653)

print(word_count[2])
# ('648', 191975)
#反推标点符号

作业1：

train_df['punctuation'] = train_df['text'].apply(lambda x:sum([x.count('3750'),x.count('900'),x.count('648')]))
train_df['punctuation'].mean()

作业2：

key = ['科技', '股票', '体育', '娱乐', '时政', '社会', '教育', '财经', '家居', '游戏', '房产', '时尚', '彩票','星座']
for i in range(0,14):
    temp = train_df.loc[train_df['label'] == i,]
    all_lines = ' '.join(list(temp['text']))
    word_count = Counter(all_lines.split(" "))
    word_count = sorted(word_count.items(), key=lambda d:d[1], reverse = True)
    print('%s类新闻中出现次数最多的字符为%s,出现次数为%d'%(key[i],word_count[0][0],word_count[0][1]))