From d1b8e8c95d8c75ec0a0a6f3463b3959b7df8792c Mon Sep 17 00:00:00 2001
From: p2fx74kt6 <2671606322@qq.com>
Date: Wed, 18 Sep 2024 20:54:26 +0800
Subject: [PATCH] =?UTF-8?q?=E8=AF=8D=E4=BA=91=E5=9B=BE=E4=B9=8B=E4=BB=A3?=
 =?UTF-8?q?=E7=A0=81?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 WordCloud.py | 40 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 40 insertions(+)
 create mode 100644 WordCloud.py

diff --git a/WordCloud.py b/WordCloud.py
new file mode 100644
index 0000000..d037451
--- /dev/null
+++ b/WordCloud.py
@@ -0,0 +1,40 @@
+import matplotlib.pyplot as plt
+import wordcloud
+import jieba
+import pyecharts
+import pandas as pd
+import numpy as np
+from PIL import Image
+import nltk
+from nltk import FreqDist
+
+font_path = r"C:\Users\26716\AppData\Local\Microsoft\Windows\Fonts\HanYiDieYuTiJian-1.ttf"
+
+with open("danmu.txt", 'r', encoding='utf-8') as f:
+    danmu_text = f.read()
+
+stopword = pd.read_csv("stopwords.txt", names=["w"], sep="\t", encoding="utf-8")
+
+jieba.add_word("发来贺电")
+words = jieba.cut(danmu_text)
+
+filtered_words = [w for w in words if w not in stopword['w'].tolist() and len(w) > 1]
+
+top_words = FreqDist(filtered_words)
+
+background = np.array(Image.open("D:\CODING\软工\奥运五环.png").convert("RGB"))
+
+cloudobj =wordcloud.WordCloud(font_path = font_path,
+                              scale = 4,
+                              width = 1920,
+                              height= 1080,
+                              max_words= 100,
+                              background_color= "white",
+                              max_font_size= 200,
+                              min_font_size= 10,
+                              mask = background
+                              ).fit_words(top_words)
+
+plt.imshow(cloudobj)
+plt.axis("off")
+plt.show()