Python关于对文本进行词频分析、词云图制作、情感分析的分享

 自行测试，欢迎交流，使用前安转所需内容。

一、  下面是一次利用python编程对文本分析的测试

1.词频图生成代码

import pandas as pd
from collections import Counter
from textblob import TextBlob
from wordcloud import WordCloud
import matplotlib.pyplot as plt
import jieba

import matplotlib.pyplot as plt

plt.rcParams['font.sans-serif'] = ['SimHei']  # 设置中文字体为SimHei
plt.rcParams['axes.unicode_minus'] = False  # 解决负号'-'显示为方块的问题


# 读取Excel文件
data = pd.read_csv(r'你的文件路径')

import re

# 去除中文标点符号
data['你需要提取的一列内容标题'] = data['你需要提取的一列内容标题'].apply(lambda x: re.sub(r'[^\w\s]','', x))

# 创建停用词列表（txt文件是自行在网上搜索“最全中文停用词表”保存到同一目录，文章----最下面）
stopwords = set(line.strip() for line in open('ting.txt', encoding='UTF-8'))

# 分词并去除停用词
words = []
for comment in data['你需要提取的一列内容标题']:
    words.extend([word for word in jieba.lcut(comment) if word not in stopwords and len(word) > 1])

words = [word for word in words if len(word) > 1]

# 统计词频
word_counts = Counter(words)

# 假设stopwords是一个包含停用词的集合
stopwords = {'的', '了', '在', '是', '我'}
words_cleaned = [word for word in words if word not in stopwords and len(word) > 1]
word_counts_cleaned = Counter(words_cleaned)

import jieba.posseg as pseg

words_classified = pseg.lcut(''.join(data['你需要提取的一列内容标题']))

import matplotlib.pyplot as plt
import seaborn as sns

# 选择要展示的词频数0
top_words = word_counts_cleaned.most_common(50)

# 数据准备
words, counts = zip(*top_words)

# 假设top_words是一个包含(词, 频率)元组的列表
top_words = word_counts.most_common(30)
words, counts = zip(*top_words)
# 使用关键字参数x和y来绘制条形图
sns.barplot(x=list(counts), y=list(words))
plt.show()
import matplotlib.pyplot as plt

 2.词云图代码

import pandas as pd
from collections import Counter
from textblob import TextBlob
from wordcloud import WordCloud
import matplotlib.pyplot as plt
import jieba

# 读取Excel文件
data = pd.read_csv(r'读取文件名')

import re

# 去除中文标点符号
data['你需要提取的一列内容标题'] = data['你需要提取的一列内容标题'].apply(lambda x: re.sub(r'[^\w\s]','', x))

# 创建停用词列表（txt文件是自行在网上搜索“最全中文停用词表”保存到同一目录，文章----最下面）
stopwords = set(line.strip() for line in open('ting.txt', encoding='UTF-8'))

# 分词并去除停用词
words = []
for comment in data['你需要提取的一列内容标题']:
    words.extend([word for word in jieba.lcut(comment) if word not in stopwords and len(word) > 1])

words = [word for word in words if len(word) > 1]

# 使用Counter统计词频
word_counts = Counter(words)

# 生成词云图
wordcloud = WordCloud(font_path='simhei.ttf', width=800, height=400).generate_from_frequencies(word_counts)

# 显示词云图
plt.figure(figsize=(10, 5))
plt.imshow(wordcloud, interpolation='bilinear')
plt.axis('off')
plt.show()

3.情感分析代码 

import pandas as pd
from collections import Counter
from textblob import TextBlob
from wordcloud import WordCloud
import matplotlib.pyplot as plt
import jieba

import matplotlib.pyplot as plt

plt.rcParams['font.sans-serif'] = ['SimHei']  # 设置中文字体为SimHei
plt.rcParams['axes.unicode_minus'] = False  # 解决负号'-'显示为方块的问题


# 读取Excel文件
data = pd.read_csv(r'读取文件名')

import re

# 去除中文标点符号
data['你需要提取的一列内容标题'] = data['你需要提取的一列内容标题'].apply(lambda x: re.sub(r'[^\w\s]','', x))

# 创建停用词列表（txt文件是自行在网上搜索“最全中文停用词表”保存到同一目录，文章----最下面）
stopwords = set(line.strip() for line in open('ting.txt', encoding='UTF-8'))

# 分词并去除停用词
words = []
for comment in data['你需要提取的一列内容标题']:
    words.extend([word for word in jieba.lcut(comment) if word not in stopwords and len(word) > 1])

words = [word for word in words if len(word) > 1]

# 统计词频
word_counts = Counter(words)

# 假设stopwords是一个包含停用词的集合
stopwords = {'的', '了', '在', '是', '我'}
words_cleaned = [word for word in words if word not in stopwords and len(word) > 1]
word_counts_cleaned = Counter(words_cleaned)

import jieba.posseg as pseg

words_classified = pseg.lcut(''.join(data['你需要提取的一列内容标题']))

import matplotlib.pyplot as plt
import seaborn as sns

import jieba.posseg as pseg

words_classified = pseg.lcut(''.join(data['你需要提取的一列内容标题']))

from collections import Counter

import matplotlib.pyplot as plt
import seaborn as sns
from textblob import TextBlob
import pandas as pd

# 假设data['你需要提取的一列内容标题']包含了清洗后的评论数据
# 进行情感分析
data['情感极性'] = data['你需要提取的一列内容标题'].apply(lambda x: TextBlob(x).sentiment.polarity)

# 将情感极性分为积极、中性和消极三类
data['情感分类'] = pd.cut(data['情感极性'], bins=[-0.02,-0.01, 0.01, 1], labels=['消极', '中性', '积极'])


# 绘制情感分类的计数条形图
plt.figure(figsize=(8, 6))
sns.countplot(x='情感分类', data=data, order=['积极', '中性', '消极'])
plt.title('评论情感分类')
plt.xlabel('情感类型')
plt.ylabel('评论数量')
plt.show()

4.中文停用词 

最全中文停用词最全中文停用词表（可直接复制）_停用词库-CSDN博客

———————————————————— FXCZ————————————————————