Skip to main content
 首页 » 编程设计

python之密谋返回空白图形对象

2024年12月31日11oomusou

我有以下代码应该在 matplotlib 中绘制给定文本的词云并将其转换为 plotly:

from wordcloud import WordCloud, STOPWORDS 
import matplotlib.pyplot as plt 
import plotly.graph_objs as go 
from plotly.offline import download_plotlyjs, init_notebook_mode, plot, iplot 
import plotly.tools as tls 
 
# Thanks : https://www.kaggle.com/aashita/word-clouds-of-various-shapes ## 
def plot_wordcloud(text, mask=None, max_words=200, max_font_size=100, figure_size=(24.0,16.0),  
                   title = None, title_size=40, image_color=False): 
    stopwords = set(STOPWORDS) 
    wordcloud = WordCloud(background_color='black', 
                    stopwords = stopwords, 
                    max_words = max_words, 
                    max_font_size = max_font_size,  
                    random_state = 42, 
                    width=800,  
                    height=400, 
                    mask = mask) 
    wordcloud.generate(str(text)) 
 
    fig = plt.figure() 
    plt.imshow(wordcloud) 
    return tls.mpl_to_plotly(fig) 
 
word_list = "Wikipedia was launched on January 15, 2001, by Jimmy Wales and Larry Sanger.[10] Sanger coined its name,[11][12] as a portmanteau of wiki[notes 3] and 'encyclopedia'. Initially an English-language encyclopedia, versions in other languages were quickly developed. With 5,748,461 articles,[notes 4] the English Wikipedia is the largest of the more than 290 Wikipedia encyclopedias. Overall, Wikipedia comprises more than 40 million articles in 301 different languages[14] and by February 2014 it had reached 18 billion page views and nearly 500 million unique visitors per month.[15] In 2005, Nature published a peer review comparing 42 science articles from Encyclopædia Britannica and Wikipedia and found that Wikipedia's level of accuracy approached that of Britannica.[16] Time magazine stated that the open-door policy of allowing anyone to edit had made Wikipedia the biggest and possibly the best encyclopedia in the world and it was testament to the vision of Jimmy Wales.[17] Wikipedia has been criticized for exhibiting systemic bias, for presenting a mixture of 'truths, half truths, and some falsehoods',[18] and for being subject to manipulation and spin in controversial topics.[19] In 2017, Facebook announced that it would help readers detect fake news by suitable links to Wikipedia articles. YouTube announced a similar plan in 2018." 
 
plot_wordcloud(word_list, title="Word Cloud") 

这只会返回一个空白图形,data 中没有任何内容。部分:

Figure({ 
    'data': [], 
    'layout': {'autosize': False, 
               'height': 288, 
               'hovermode': 'closest', 
               'margin': {'b': 61, 'l': 54, 'pad': 0, 'r': 43, 't': 59}, 
               'showlegend': False, 
               'width': 432, 
               'xaxis': {'anchor': 'y', 
                         'domain': [0.0, 1.0], 
                         'mirror': 'ticks', 
                         'nticks': 10, 
                         'range': [-0.5, 799.5], 
                         'showgrid': False, 
                         'showline': True, 
                         'side': 'bottom', 
                         'tickfont': {'size': 10.0}, 
                         'ticks': 'inside', 
                         'type': 'linear', 
                         'zeroline': False}, 
               'yaxis': {'anchor': 'x', 
                         'domain': [0.0, 1.0], 
                         'mirror': 'ticks', 
                         'nticks': 10, 
                         'range': [399.5, -0.5], 
                         'showgrid': False, 
                         'showline': True, 
                         'side': 'left', 
                         'tickfont': {'size': 10.0}, 
                         'ticks': 'inside', 
                         'type': 'linear', 
                         'zeroline': False}} 
}) 

这是为什么?我该如何解决?

如果我想绘制 matplotlib 图,它工作正常 - return fig返回词云的静态图形。

我试图直接在 plotly 中绘制 wordcloud,但是使用 go.Scatter您需要明确提供 x 和 y 值 - 它不能从 wordcloud 中获取它们隐含地喜欢 plt.imshow能。所以,我得到一个“对象不可迭代”的错误:

def plot_wordcloud(text, mask=None, max_words=200, max_font_size=100, figure_size=(24.0,16.0),  
                   title = None, title_size=40, image_color=False): 
    stopwords = set(STOPWORDS) 
    wordcloud = WordCloud(background_color='black', 
                    stopwords = stopwords, 
                    max_words = max_words, 
                    max_font_size = max_font_size,  
                    random_state = 42, 
                    width=800,  
                    height=400, 
                    mask = mask) 
    wordcloud.generate(str(text)) 
 
 
    data = go.Scatter(dict(wordcloud.generate(str(text))), 
                 mode='text', 
                 text=words, 
                 marker={'opacity': 0.3}, 
                 textfont={'size': weights, 
                           'color': colors}) 
    layout = go.Layout({'xaxis': {'showgrid': False, 'showticklabels': False, 'zeroline': False}, 
                        'yaxis': {'showgrid': False, 'showticklabels': False, 'zeroline': False}}) 
    fig = go.Figure(data=[data], layout=layout) 
    return fig 
 
 
word_list = "Wikipedia was launched on January 15, 2001, by Jimmy Wales and Larry Sanger.[10] Sanger coined its name,[11][12] as a portmanteau of wiki[notes 3] and 'encyclopedia'. Initially an English-language encyclopedia, versions in other languages were quickly developed. With 5,748,461 articles,[notes 4] the English Wikipedia is the largest of the more than 290 Wikipedia encyclopedias. Overall, Wikipedia comprises more than 40 million articles in 301 different languages[14] and by February 2014 it had reached 18 billion page views and nearly 500 million unique visitors per month.[15] In 2005, Nature published a peer review comparing 42 science articles from Encyclopædia Britannica and Wikipedia and found that Wikipedia's level of accuracy approached that of Britannica.[16] Time magazine stated that the open-door policy of allowing anyone to edit had made Wikipedia the biggest and possibly the best encyclopedia in the world and it was testament to the vision of Jimmy Wales.[17] Wikipedia has been criticized for exhibiting systemic bias, for presenting a mixture of 'truths, half truths, and some falsehoods',[18] and for being subject to manipulation and spin in controversial topics.[19] In 2017, Facebook announced that it would help readers detect fake news by suitable links to Wikipedia articles. YouTube announced a similar plan in 2018." 
 
plot_wordcloud(word_list, title="Word Cloud") 
 
--------------------------------------------------------------------------- 
 
TypeError                                 Traceback (most recent call last) 
<ipython-input-50-0567281b72b3> in <module>() 
 
---> 48 plot_wordcloud(word_list, title="Word Cloud") 
 
<ipython-input-50-0567281b72b3> in plot_wordcloud(text, mask, max_words, max_font_size, figure_size, title, title_size, image_color) 
     18  
     19  
---> 20     data = go.Scatter(dict(wordcloud.generate(str(text))), 
     21                  mode='text', 
     22                  text=words, 
 
TypeError: 'WordCloud' object is not iterable 

如果我return wordcloud ,它显示:<wordcloud.wordcloud.WordCloud at 0x1c8faeda748> .如果有人知道如何解压 wordcloud对象,以便我可以将其中的 x 和 y 参数输入到 go.Figure 中,那也很棒(事实上更好)。


只是为了表明解压 wordcloud object 会工作,我可以通过在 go.Scatter 中为 x 和 y 值放置随机数来使用 plotly 本地绘制 wordcloud像这样:

import random 
import plotly.graph_objs as go 
 
def plot_wordcloud(text, mask=None, max_words=200, max_font_size=100, figure_size=(24.0,16.0),  
                   title = None, title_size=40, image_color=False): 
    stopwords = set(STOPWORDS) 
    wordcloud = WordCloud(background_color='black', 
                    stopwords = stopwords, 
                    max_words = max_words, 
                    max_font_size = max_font_size,  
                    random_state = 42, 
                    width=800,  
                    height=400, 
                    mask = mask) 
    wordcloud.generate(str(text)) 
 
 
    data = go.Scatter(x=[random.random() for i in range(3000)], 
                 y=[random.random() for i in range(3000)], 
                 mode='text', 
                 text=str(word_list).split(), 
                 marker={'opacity': 0.3}, 
                 textfont={'size': weights, 
                           'color': colors}) 
    layout = go.Layout({'xaxis': {'showgrid': False, 'showticklabels': False, 'zeroline': False}, 
                        'yaxis': {'showgrid': False, 'showticklabels': False, 'zeroline': False}}) 
    fig = go.Figure(data=[data], layout=layout) 
    return fig 

它只是不正确的词云(显然,正确定义了单词的位置和大小),它应该看起来像这样(用 matplotlib.pyplot 绘制的静态词云):

请您参考如下方法:

由于 wordcloud 生成图像,而 plotly 的转换函数当前无法处理图像,因此您需要以某种方式从 wordcloud.wordcloud.WordCloud 的位置、大小和方向重新生成 wordcloud 对象。

这些信息存储在 .layout_ 属性中

wc = Wordcloud(...) 
wc.generate(text) 
print(wc.layout_) 

打印形式为

的元组列表
[(word, freq), fontsize, position, orientation, color] 

例如在这种情况下

[(('Wikipedia', 1.0), 100, (8, 7), None, 'rgb(56, 89, 140)'),  
 (('articles', 0.4444444444444444), 72, (269, 310), None, 'rgb(58, 186, 118)'), ...] 

所以原则上这允许将词云重新生成为文本。但是必须注意小细节。 IE。字体和字体大小需要相同。

这是一个纯 matplotlib 示例,它使用 matplotlib.text.Text 对象再现了词云。

import numpy as np 
from wordcloud import WordCloud, STOPWORDS  
from wordcloud.wordcloud import FONT_PATH 
import matplotlib.pyplot as plt 
from matplotlib.font_manager import FontProperties 
 
word_list = "Wikipedia was launched on January 15, 2001, by Jimmy Wales and Larry Sanger.[10] Sanger coined its name,[11][12] as a portmanteau of wiki[notes 3] and 'encyclopedia'. Initially an English-language encyclopedia, versions in other languages were quickly developed. With 5,748,461 articles,[notes 4] the English Wikipedia is the largest of the more than 290 Wikipedia encyclopedias. Overall, Wikipedia comprises more than 40 million articles in 301 different languages[14] and by February 2014 it had reached 18 billion page views and nearly 500 million unique visitors per month.[15] In 2005, Nature published a peer review comparing 42 science articles from Encyclopædia Britannica and Wikipedia and found that Wikipedia's level of accuracy approached that of Britannica.[16] Time magazine stated that the open-door policy of allowing anyone to edit had made Wikipedia the biggest and possibly the best encyclopedia in the world and it was testament to the vision of Jimmy Wales.[17] Wikipedia has been criticized for exhibiting systemic bias, for presenting a mixture of 'truths, half truths, and some falsehoods',[18] and for being subject to manipulation and spin in controversial topics.[19] In 2017, Facebook announced that it would help readers detect fake news by suitable links to Wikipedia articles. YouTube announced a similar plan in 2018." 
 
def get_wordcloud(width, height): 
    wc = WordCloud(background_color='black', 
                    stopwords = set(STOPWORDS), 
                    max_words = 200, 
                    max_font_size = 100,  
                    random_state = 42, 
                    width=int(width),  
                    height=int(height), 
                    mask = None) 
    wc.generate(word_list) 
    return wc 
 
 
fig, (ax, ax2) = plt.subplots(nrows=2, sharex=True, sharey=True) 
 
fp=FontProperties(fname=FONT_PATH) 
bbox = ax.get_position().transformed(fig.transFigure) 
wc = get_wordcloud(bbox.width, bbox.height) 
 
ax.imshow(wc) 
 
ax2.set_facecolor("black") 
for (word, freq), fontsize, position, orientation, color in wc.layout_: 
    color = np.array(color[4:-1].split(", ")).astype(float)/255. 
    x,y = position 
    rot = {None : 0, 2: 90}[orientation] 
    fp.set_size(fontsize*72./fig.dpi) 
    ax2.text(y,x, word, va="top", ha="left", color=color, rotation=rot,  
             fontproperties=fp) 
 
print(wc.layout_) 
plt.show() 

上图是通过imshow显示的词云图,下图是重新生成的词云图。

现在你可能想在 plotly 而不是 matplotlib 中做同样的事情,但我对 plotly 不够熟练,无法在这里直接给出解决方案。