从txt文本提取数据制作词云图

大家好，我是天空之城。

以下部分内容来自公众号数据分析与统计学之美，号主很牛叉，需要的赶紧加他。

import numpy as np
import pandas as pd
import jieba
from wordcloud import WordCloud
import matplotlib.pyplot as plt
from imageio import imread

import warnings
warnings.filterwarnings("ignore")

with open(r"非暴力沟通.txt", 'r',encoding="utf-8") as f:
    txt = f.read()

txt = txt.split()
# print(txt[:20])
# display(txt[:5])

# my_words = ['非暴力', '沟通']
# for i in my_words:
#     jieba.add_word(i)

        # 自定义停用词
    # my_stop_words = []
#     # stop_words.extend(my_stop_words)


data_cut = [jieba.lcut(x) for x in txt]

# data_cut =jieba.lcut(txt)
# display(data_cut[:5])
print(data_cut[:20])


all_words = []
for i in data_cut:
    all_words.extend(i)
print(all_words)

word_count = pd.Series(all_words).value_counts()
# print(word_count[:20])


with open("stoplist.txt", encoding="utf-8") as f:
    stop = f.read()

stop = stop.split()
stop = [" ", "道", "说道", "说"] + stop
# print(stop[:5])



s_data_cut = pd.Series(data_cut)
all_words_after = s_data_cut.apply(lambda x:[i for i in x if i not in stop])
# print(all_words_after[:10])

all_words = []
for i in all_words_after:
    all_words.extend(i)

word_count = pd.Series(all_words).value_counts()
print(word_count[:10])

# 1、读取背景图片
background_image = imread("aixin.jpg")

# 2、设置词云参数
wc = WordCloud(font_path="C:/Windows/Fonts/simfang.ttf",
                mask=background_image,
               background_color="white",
               max_words=2000,
               max_font_size=200,
               random_state=42
              )
wc2 = wc.fit_words(word_count)

# 3、绘制词云图
plt.figure(figsize=(16,8))
plt.imshow(wc2)
plt.axis("off")
plt.show()
wc.to_file("ciyun100.png")