import csv, jieba, re
from itertools import islice
import pandas as pd
import imageio
import matplotlib.pyplot as plt
from wordcloud import WordCloud, ImageColorGenerator
def csv_to_txt():
chat_csv = open("my_chat.csv","r",encoding="utf-8")
my_chat = csv.reader(chat_csv)
fp = open("chat.txt", "w+", encoding="utf-8")
for line in islice(my_chat, 1, None):
if re.search("[\u4e00-\u9fa5]", line[8]) and len(line[8]) < 50:
fp.write(line[8] + "\n")
fp.close()
def cut_words():
fp = open("chat.txt", "r", encoding="utf-8")
content = fp.read()
fp.close()
jieba.load_userdict("custom_dict.txt")
words = jieba.cut(content)
word_L = []
with open("stopwords.txt", 'r', encoding="utf-8") as ss:
stopwords = ss.read()
for word in words:
if word not in stopwords and word != '\n' and len(word) > 1:
word_L.append(word)
return word_L
def word_cloud(words):
count_word_df = pd.DataFrame({"word":words}).groupby(["word"]).size()
count_word_dt = count_word_df.to_dict()
mk = imageio.imread('my_pic.jpg')
mk_color = ImageColorGenerator(mk)
wx_wc = WordCloud(
background_color="white",
mode="RGB",
mask=mk,
font_path="青鸟华光简胖头鱼.TTF",
scale=3,
)
wx_wc = wx_wc.generate_from_frequencies(count_word_dt)
wx_wc.to_file("wordcloud.png")
plt.axis("off")
plt.imshow(wx_wc.recolor(color_func=mk_color))
plt.savefig('pltwordcloud.png', dpi=400)
def run():
csv_to_txt()
words = cut_words()
word_cloud(words)
if __name__ == '__main__':
run()
[复制链接]
发表于 2020-4-12 15:48
|
发表于 2020-4-14 14:19
