from wordcloud import WordCloud, STOPWORDS
import matplotlib.pyplot as plt
import numpy as np
import jieba.posseg as pseg
from collections import Counter
import PIL.Image as Image
from matplotlib import colors

# 閱讀文本（這里yourfile.txt，根據(jù)文本所在具體位置進行設置）
text = open("yourfile.txt", encoding="utf-8").read()  
words = pseg.cut(text)

# 按指定長度和詞性提取詞
report_words = []
for word, flag in words:
    if (len(word) >= 2) and ('n' in flag): #這里設置統(tǒng)計的字數(shù)
        report_words.append(word)
# 設置停用詞
stopwords = set(STOPWORDS)
stopwords.update(["的", "感謝", "我代表", "以上", "報告", "表示誠摯感謝","戰(zhàn)略"])
# 去除停用詞
report_words = [word for word in report_words if word not in stopwords]
# 統(tǒng)計高頻詞匯
result = Counter(report_words).most_common(200) #詞的個數(shù)
# 建立詞匯字典
content = dict(result)
#輸出詞頻統(tǒng)計結果
for i in range(50):
    word,flag=result[i]
    print("{0:<10}{1:>5}".format(word,flag))
 

#設置png掩膜（yourfile.png根據(jù)實際路徑進行替換）
background = Image.open("yourfile.png")
mask = np.array(background)

# 如果當前位深是32的話，可以不用寫轉(zhuǎn)RGBA模式的這一句，但是寫上也沒啥問題
# 從RGB（24位）模式轉(zhuǎn)成RGBA（32位）模式
img = Image.open("yourfile.png").convert('RGBA')
W, L = img.size
white_pixel = (0, 0, 0, 0)  # 白色
for h in range(W):
    for i in range(L):
        if img.getpixel((h, i)) == white_pixel:
            img.putpixel((h, i), (255, 255, 255, 0))  # 設置透明
img.save("yourfile_new.png")  # 自己設置保存地址

# 設置字體樣式路徑
font_path = r"C:\Windows\Fonts\STLITI.TTF"
# 設置字體大小
max_font_size =200
min_font_size =10
# 建立顏色數(shù)組，可更改顏色
color_list = ['#FF274B']
# 調(diào)用顏色數(shù)組
colormap = colors.ListedColormap(color_list)

# 生成詞云
wordcloud = WordCloud(scale=4,                         #輸出清晰度
                      font_path=font_path,             #輸出路徑
                      colormap=colormap,               #字體顏色
                      width=1600,                      #輸出圖片寬度
                      height=900,                      #輸出圖片高度
                      background_color='white',        #圖片背景顏色
                      stopwords=stopwords,             #停用詞
                      mask=mask,                       #掩膜
                      max_font_size=max_font_size,     #最大字體大小
                      min_font_size=min_font_size)     #最小字體大小
wordcloud.generate_from_frequencies(content)
# 使用 matplotlib 顯示詞云
plt.imshow(wordcloud, interpolation='bilinear')
plt.axis('off')
plt.show()
# 保存詞云圖
wordcloud.to_file("wordcloud.png")

from wordcloud import WordCloud, STOPWORDS
import matplotlib.pyplot as plt
import numpy as np
import jieba.posseg as pseg
from collections import Counter
import PIL.Image as Image
from matplotlib import colors
# 閱讀文本（這里yourfile.txt，根據(jù)文本所在具體位置進行設置）
text = open("yourfile.txt", encoding="utf-8").read()
words = pseg.cut(text)
# 按指定長度和詞性提取詞
report_words = []
for word, flag in words:
    if (len(word) >= 2) and ('n' in flag): #這里設置統(tǒng)計的字數(shù)
        report_words.append(word)
# 統(tǒng)計高頻詞匯
result = Counter(report_words).most_common(200) #詞的個數(shù)
# 建立詞匯字典
content = dict(result)
#輸出詞頻統(tǒng)計結果
for i in range(50):
    word,flag=result[i]
    print("{0:<10}{1:>5}".format(word,flag))
# 設置停用詞
stopwords = set(STOPWORDS)
stopwords.update(["的", "感謝", "我代表", "以上", "報告", "表示誠摯感謝","戰(zhàn)略"])
#設置png掩膜（yourfile.png根據(jù)實際路徑進行替換）
background = Image.open("yourfile.png").convert('RGB')
mask = np.array(background)
'''
# 如果當前位深是32的話，可以不用寫轉(zhuǎn)RGBA模式的這一句，但是寫上也沒啥問題
# 從RGB（24位）模式轉(zhuǎn)成RGBA（32位）模式
img = Image.open("yourfile.png").convert('RGBA')
W, L = img.size
white_pixel = (0, 0, 0, 0)  # 白色
for h in range(W):
    for i in range(L):
        if img.getpixel((h, i)) == white_pixel:
            img.putpixel((h, i), (255, 255, 255, 0))  # 設置透明
img.save("yourfile_new.png")  # 自己設置保存地址
'''
# 設置字體樣式路徑
font_path = r"C:\Windows\Fonts\STLITI.TTF"
# 設置字體大小
max_font_size =200
min_font_size =10
# 建立顏色數(shù)組，可更改顏色
color_list = ['#FF274B']
# 調(diào)用顏色數(shù)組
colormap = colors.ListedColormap(color_list)
# 生成詞云
wordcloud = WordCloud(scale=4,                         #輸出清晰度
                      font_path=font_path,             #輸出路徑
                      colormap=colormap,               #字體顏色
                      width=1600,                      #輸出圖片寬度
                      height=900,                      #輸出圖片高度
                      background_color='white',        #圖片背景顏色
                      stopwords=stopwords,             #停用詞
                      mask=mask,                       #掩膜
                      max_font_size=max_font_size,     #最大字體大小
                      min_font_size=min_font_size)     #最小字體大小
wordcloud.generate_from_frequencies(content)
# 使用 matplotlib 顯示詞云
plt.imshow(wordcloud, interpolation='bilinear')
plt.axis('off')
plt.show()
# 保存詞云圖
wordcloud.to_file("wordcloud.png")