Python word_cloud 样例 标签云系列（三）

wd = {}

fp=codecs.open("rsa.txt", "r",‘utf-8‘);

alllines=fp.readlines();

fp.close();

for eachline in alllines:
    line = eachline.split(‘        ‘)
    #print eachline,
    wd[line[0]] = int(line[1])
print wd

# -*- coding: utf-8 -*-
import codecs
fp=codecs.open("rs300.txt", "r",‘utf-8‘);

wd = []
alllines=fp.readlines();

fp.close();

for eachline in alllines:
    line = eachline.split(‘\\‘)
    line[1]=int(line[1])
    wd.append(line)
    #print eachline,

print wd

#-*- coding: utf-8 -*-
"""
Minimal Example
===============
Generating a square wordcloud from the US constitution using default arguments.
"""

from os import path
from wordcloud import WordCloud

d = path.dirname(__file__)

# Read the whole text.
 此处原为处理英文文本，我们修改为传入中文数组
#text = open(path.join(d, ‘constitution.txt‘)).read()
frequencies = [(u‘知乎‘,5),(u‘小段同学‘,4),(u‘曲小花‘,3),(u‘中文分词‘,2),(u‘样例‘,1)]

# Generate a word cloud image 此处原为 text 方法，我们改用 frequencies 
#wordcloud = WordCloud().generate(text)
wordcloud = WordCloud().fit_words(frequencies)

# Display the generated image:
# the matplotlib way:
import matplotlib.pyplot as plt
plt.imshow(wordcloud)
plt.axis("off")

# take relative word frequencies into account, lower max_font_size
#wordcloud = WordCloud(max_font_size=40, relative_scaling=.5).generate(text)
wordcloud = WordCloud(max_font_size=40, relative_scaling=.5).fit_words(frequencies)
plt.figure()
plt.imshow(wordcloud)
plt.axis("off")
plt.show()

# The pil way (if you don‘t have matplotlib)
#image = wordcloud.to_image()
#image.show()

# -*- coding: utf-8 -*-
""""
Masked wordcloud
================
Using a mask you can generate wordclouds in arbitrary shapes.
"""

from os import path
from PIL import Image
import numpy as np
import matplotlib.pyplot as plt

from wordcloud import WordCloud, STOPWORDS

d = path.dirname(__file__)

# Read the whole text.
text = open(path.join(d, ‘alice.txt‘)).read()

# read the mask image
# taken from
# http://www.stencilry.org/stencils/movies/alice%20in%20wonderland/255fk.jpg
alice_mask = np.array(Image.open(path.join(d, "huge.jpg")))

wc = WordCloud(background_color="white", max_words=2000, mask=alice_mask,
               stopwords=STOPWORDS.add("said"))
# generate word cloud
wc.generate(text)

# store to file
wc.to_file(path.join(d, "alice.png"))

# show
plt.imshow(wc)
plt.axis("off")
plt.figure()
plt.imshow(alice_mask, cmap=plt.cm.gray)
plt.axis("off")
plt.show()

"""
Using custom colors
====================
Using the recolor method and custom coloring functions.
"""

import numpy as np
from PIL import Image
from os import path
import matplotlib.pyplot as plt
import random

from wordcloud import WordCloud, STOPWORDS


def grey_color_func(word, font_size, position, orientation, random_state=None, **kwargs):
    return "hsl(0, 0%%, %d%%)" % random.randint(60, 100)

d = path.dirname(__file__)

# read the mask image
# taken from
# http://www.stencilry.org/stencils/movies/star%20wars/storm-trooper.gif
mask = np.array(Image.open(path.join(d, "huge.jpg")))

# movie script of "a new hope"
# http://www.imsdb.com/scripts/Star-Wars-A-New-Hope.html
# May the lawyers deem this fair use.
text = open("a_new_hope.txt").read()

# preprocessing the text a little bit
text = text.replace("HAN", "Han")
text = text.replace("LUKE‘S", "Luke")

# adding movie script specific stopwords
stopwords = STOPWORDS.copy()
stopwords.add("int")
stopwords.add("ext")

wc = WordCloud(max_words=1000, mask=mask, stopwords=stopwords, margin=10,
               random_state=1).generate(text)
# store default colored image
default_colors = wc.to_array()
plt.title("Custom colors")
plt.imshow(wc.recolor(color_func=grey_color_func, random_state=3))
wc.to_file("a_new_hope.png")
plt.axis("off")
plt.figure()
plt.title("Default colors")
plt.imshow(default_colors)
plt.axis("off")
plt.show()

#!/usr/bin/env python2
"""
Image-colored wordcloud
========================
You can color a word-cloud by using an image-based coloring strategy implemented in
ImageColorGenerator. It uses the average color of the region occupied by the word
in a source image. You can combine this with masking - pure-white will be interpreted
as ‘don‘t occupy‘ by the WordCloud object when passed as mask.
If you want white as a legal color, you can just pass a different image to "mask",
but make sure the image shapes line up.
"""

from os import path
from PIL import Image
import numpy as np
import matplotlib.pyplot as plt

from wordcloud import WordCloud, STOPWORDS, ImageColorGenerator

d = path.dirname(__file__)

# Read the whole text.
text = open(path.join(d, ‘alice.txt‘)).read()

# read the mask / color image
# taken from http://jirkavinse.deviantart.com/art/quot-Real-Life-quot-Alice-282261010
alice_coloring = np.array(Image.open(path.join(d, "xhr.jpg")))

wc = WordCloud(background_color="white", max_words=2000, mask=alice_coloring,
               stopwords=STOPWORDS.add("said"),
               max_font_size=40, random_state=42)
# generate word cloud
wc.generate(text)

# create coloring from image
image_colors = ImageColorGenerator(alice_coloring)

# show
plt.imshow(wc)
plt.axis("off")
plt.figure()
# recolor wordcloud and show
# we could also give color_func=image_colors directly in the constructor
plt.imshow(wc.recolor(color_func=image_colors))
plt.axis("off")
plt.figure()
plt.imshow(alice_coloring, cmap=plt.cm.gray)
plt.axis("off")
plt.show()