? ? ? ?詞云是一種非常漂亮的可視化展示方式,正所謂一圖勝過千言萬語,詞云在之前的項目中我也有過很多的使用,可能對于我來說,一種很好的自我介紹方式就是詞云吧,就像下面這樣的:
? ? ?個人覺還是會比枯燥的文字語言描述性的介紹會更吸引人一點吧。
? ? ? 今天不是說要怎么用詞云來做個人介紹,而是對工作中使用到比較多的詞云計較做了一下總結,主要是包括三個方面:
1、諸如上面的簡單形式矩形詞云
2、基于背景圖片數據來構建詞云數據
3、某些場景下不想使用類似上面的默認的字體顏色,這里可以自定義詞云的字體顏色
? ? ? 接下來對上面三種類型的詞云可視化方法進行demo實現與展示,具體如下:
? ? ? 這里我們使用到的測試數據如下:
The Zen of Python, by Tim Peters
Beautiful is better than ugly.
Explicit is better than implicit.
Simple is better than complex.
Complex is better than complicated.
Flat is better than nested.
Sparse is better than dense.
Readability counts.
Special cases aren't special enough to break the rules.
Although practicality beats purity.
Errors should never pass silently.
Unless explicitly silenced.
In the face of ambiguity, refuse the temptation to guess.
There should be one-- and preferably text one --obvious way to do it.
Although that way may not be obvious at first unless you're Dutch.
Now is better than never.
Although never is often better than *right* now.
If the implementation is hard to explain, it's a bad idea.
If the implementation is easy to explain, it may be a good idea.
Namespaces are one honking great idea -- let's do more of those!
1、簡單形式矩形詞云實現如下:
def simpleWC1(sep=' ',back='black',freDictpath='data_fre.json',savepath='res.png'):
'''
詞云可視化Demo
'''
try:
with open(freDictpath) as f:
data=f.readlines()
data_list=[one.strip().split(sep) for one in data if one]
fre_dict={}
for one_list in data_list:
fre_dict[unicode(one_list[0])]=int(one_list[1])
except:
fre_dict=freDictpath
wc=WordCloud(font_path='font/simhei.ttf',#設置字體 #simhei
background_color=back, #背景顏色
max_words=1300,# 詞云顯示的最大詞數
max_font_size=120, #字體最大值
margin=3, #詞云圖邊距
width=1800, #詞云圖寬度
height=800, #詞云圖高度
random_state=42)
wc.generate_from_frequencies(fre_dict) #從詞頻字典生成詞云
plt.figure()
plt.imshow(wc)
plt.axis("off")
wc.to_file(savepath)
? ? ? 圖像數據結果如下:
?
2、 基于背景圖像數據的詞云可視化具體實現如下:
? ? 先貼一下背景圖像:
? ? ?這也是一個比較經典的圖像數據了,下面來看具體的實現:
def simpleWC2(sep=' ',back='black',backPic='a.png',freDictpath='data_fre.json',savepath='res.png'):
'''
詞云可視化Demo【使用背景圖片】
'''
try:
with open(freDictpath) as f:
data=f.readlines()
data_list=[one.strip().split(sep) for one in data if one]
fre_dict={}
for one_list in data_list:
fre_dict[unicode(one_list[0])]=int(one_list[1])
except:
fre_dict=freDictpath
back_coloring=imread(backPic)
wc=WordCloud(font_path='simhei.ttf',#設置字體 #simhei
background_color=back,max_words=1300,
mask=back_coloring,#設置背景圖片
max_font_size=120, #字體最大值
margin=3,width=1800,height=800,random_state=42,)
wc.generate_from_frequencies(fre_dict) #從詞頻字典生成詞云
wc.to_file(savepath)
? ? ? 結果圖像數據如下:
3、 自定義詞云字體顏色的具體實現如下:
?
#自定義顏色列表
color_list=['#CD853F','#DC143C','#00FF7F','#FF6347','#8B008B','#00FFFF','#0000FF','#8B0000','#FF8C00',
'#1E90FF','#00FF00','#FFD700','#008080','#008B8B','#8A2BE2','#228B22','#FA8072','#808080']
def simpleWC3(sep=' ',back='black',freDictpath='data_fre.json',savepath='res.png'):
'''
詞云可視化Demo【自定義字體的顏色】
'''
#基于自定義顏色表構建colormap對象
colormap=colors.ListedColormap(color_list)
try:
with open(freDictpath) as f:
data=f.readlines()
data_list=[one.strip().split(sep) for one in data if one]
fre_dict={}
for one_list in data_list:
fre_dict[unicode(one_list[0])]=int(one_list[1])
except:
fre_dict=freDictpath
wc=WordCloud(font_path='font/simhei.ttf',#設置字體 #simhei
background_color=back, #背景顏色
max_words=1300, #詞云顯示的最大詞數
max_font_size=120, #字體最大值
colormap=colormap, #自定義構建colormap對象
margin=2,width=1800,height=800,random_state=42,
prefer_horizontal=0.5) #無法水平放置就垂直放置
wc.generate_from_frequencies(fre_dict)
plt.figure()
plt.imshow(wc)
plt.axis("off")
wc.to_file(savepath)
? ? ? 結果圖像數據如下:
? ? ? 上述三種方法就是我在具體工作中使用頻度最高的三種詞云可視化展示方法了,下面貼出來完整的代碼實現,可以直接拿去跑的:
#!usr/bin/env python
#encoding:utf-8
from __future__ import division
'''
__Author__:沂水寒城
功能: 詞云的可視化模塊
'''
import os
import sys
import json
import numpy as np
from PIL import Image
from scipy.misc import imread
from matplotlib import colors
import matplotlib.pyplot as plt
from matplotlib.font_manager import FontProperties
from wordcloud import WordCloud,ImageColorGenerator,STOPWORDS
reload(sys)
sys.setdefaultencoding('utf-8')
#自定義顏色列表
color_list=['#CD853F','#DC143C','#00FF7F','#FF6347','#8B008B','#00FFFF','#0000FF','#8B0000','#FF8C00',
'#1E90FF','#00FF00','#FFD700','#008080','#008B8B','#8A2BE2','#228B22','#FA8072','#808080']
def simpleWC1(sep=' ',back='black',freDictpath='data_fre.json',savepath='res.png'):
'''
詞云可視化Demo
'''
try:
with open(freDictpath) as f:
data=f.readlines()
data_list=[one.strip().split(sep) for one in data if one]
fre_dict={}
for one_list in data_list:
fre_dict[unicode(one_list[0])]=int(one_list[1])
except:
fre_dict=freDictpath
wc=WordCloud(font_path='font/simhei.ttf',#設置字體 #simhei
background_color=back, #背景顏色
max_words=1300,# 詞云顯示的最大詞數
max_font_size=120, #字體最大值
margin=3, #詞云圖邊距
width=1800, #詞云圖寬度
height=800, #詞云圖高度
random_state=42)
wc.generate_from_frequencies(fre_dict) #從詞頻字典生成詞云
plt.figure()
plt.imshow(wc)
plt.axis("off")
wc.to_file(savepath)
def simpleWC2(sep=' ',back='black',backPic='a.png',freDictpath='data_fre.json',savepath='res.png'):
'''
詞云可視化Demo【使用背景圖片】
'''
try:
with open(freDictpath) as f:
data=f.readlines()
data_list=[one.strip().split(sep) for one in data if one]
fre_dict={}
for one_list in data_list:
fre_dict[unicode(one_list[0])]=int(one_list[1])
except:
fre_dict=freDictpath
back_coloring=imread(backPic)
wc=WordCloud(font_path='simhei.ttf',#設置字體 #simhei
background_color=back,max_words=1300,
mask=back_coloring,#設置背景圖片
max_font_size=120, #字體最大值
margin=3,width=1800,height=800,random_state=42,)
wc.generate_from_frequencies(fre_dict) #從詞頻字典生成詞云
wc.to_file(savepath)
def simpleWC3(sep=' ',back='black',freDictpath='data_fre.json',savepath='res.png'):
'''
詞云可視化Demo【自定義字體的顏色】
'''
#基于自定義顏色表構建colormap對象
colormap=colors.ListedColormap(color_list)
try:
with open(freDictpath) as f:
data=f.readlines()
data_list=[one.strip().split(sep) for one in data if one]
fre_dict={}
for one_list in data_list:
fre_dict[unicode(one_list[0])]=int(one_list[1])
except:
fre_dict=freDictpath
wc=WordCloud(font_path='font/simhei.ttf',#設置字體 #simhei
background_color=back, #背景顏色
max_words=1300, #詞云顯示的最大詞數
max_font_size=120, #字體最大值
colormap=colormap, #自定義構建colormap對象
margin=2,width=1800,height=800,random_state=42,
prefer_horizontal=0.5) #無法水平放置就垂直放置
wc.generate_from_frequencies(fre_dict)
plt.figure()
plt.imshow(wc)
plt.axis("off")
wc.to_file(savepath)
if __name__ == '__main__':
text="""
The Zen of Python, by Tim Peters
Beautiful is better than ugly.
Explicit is better than implicit.
Simple is better than complex.
Complex is better than complicated.
Flat is better than nested.
Sparse is better than dense.
Readability counts.
Special cases aren't special enough to break the rules.
Although practicality beats purity.
Errors should never pass silently.
Unless explicitly silenced.
In the face of ambiguity, refuse the temptation to guess.
There should be one-- and preferably text one --obvious way to do it.
Although that way may not be obvious at first unless you're Dutch.
Now is better than never.
Although never is often better than *right* now.
If the implementation is hard to explain, it's a bad idea.
If the implementation is easy to explain, it may be a good idea.
Namespaces are one honking great idea -- let's do more of those!
"""
word_list=text.split()
fre_dict={}
for one in word_list:
if one in fre_dict:
fre_dict[one]+=1
else:
fre_dict[one]=1
simpleWC1(sep=' ',back='black',freDictpath=fre_dict,savepath='simpleWC1.png')
simpleWC2(sep=' ',back='black',backPic='backPic/A.png',freDictpath=fre_dict,savepath='simpleWC2.png')
simpleWC3(sep=' ',back='black',freDictpath=fre_dict,savepath='simpleWC3.png')
? ? ? ?記錄一下,歡迎交流學習。
更多文章、技術交流、商務合作、聯系博主
微信掃碼或搜索:z360901061

微信掃一掃加我為好友
QQ號聯系: 360901061
您的支持是博主寫作最大的動力,如果您喜歡我的文章,感覺我的文章對您有幫助,請用微信掃描下面二維碼支持博主2元、5元、10元、20元等您想捐的金額吧,狠狠點擊下面給點支持吧,站長非常感激您!手機微信長按不能支付解決辦法:請將微信支付二維碼保存到相冊,切換到微信,然后點擊微信右上角掃一掃功能,選擇支付二維碼完成支付。
【本文對您有幫助就好】元
