1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
|
import operator
from os import path
from PIL import Image
import numpy as np
import matplotlib.pyplot as plt
from wordcloud import WordCloud,STOPWORDS,ImageColorGenerator
import jieba
def get_poems(name_txt):
with open(name_txt, encoding='utf-8') as f:
poems_text=f.read()
poems = poems_text.split('\n')
poems = list(filter(None,poems))
return f.name , poems
def mk_single(single_txt):
singled = []
for i in single_txt:
single_poem = i.split(' ')
singled.append(single_poem[3])
singled = ''.join(singled)
return singled
def rm_symbol(words_txt):
unsymbol = []
for i in words_txt:
if i.isalpha():
unsymbol.append(i)
return unsymbol
def mk_dict(dic_data):
mked_dic={}
qc_data=list(set(dic_data))
for i in qc_data:
mked_dic.setdefault(i,dic_data.count(i))
mked_dic = sorted(mked_dic.items(), key = operator.itemgetter(1))
mked_dic.reverse()
mked_dic=dict(mked_dic)
return mked_dic
def tj_core(origin_data):
poems_ab=get_poems(origin_data)
poems_author=str(poems_ab[0])
poems_author=poems_author.split('.',1)
poems=poems_ab[1]
poems_sg=mk_single(poems)
poems_wd=rm_symbol(poems_sg)
poems_dic=mk_dict(poems_wd)
return poems_author[0], poems ,poems_dic
def tj_HFWD(tj_author,tj_poems,tj_dic,pl_min):
num_total=len(tj_poems)
tj_LS=[]
for i in tj_dic:
if tj_dic[i]/num_total >= pl_min:
tj_LS.append(i)
return set(tj_LS)
def tj_frequence(tj_author,tj_poems,tj_dic,pl_min):
num_total=len(tj_poems)
print('---------BEGIN---------')
print(tj_author,'----汉字词频','(>=',pl_min,')')
for i in tj_dic:
if tj_dic[i]/num_total >= pl_min:
print(i, ' '*2, '{:.8f}'.format(tj_dic[i]/num_total))
print('----------END----------')
def pome_cloud(in_poem,in_mask,d,wd_num,wds_max,wdf_siz):
poems_ab=get_poems(in_poem)
poems_author=str(poems_ab[0])
poems_author=poems_author.split('.',1)
poems=poems_ab[1]
poems_sg=mk_single(poems)
if wd_num == 1:
poems_sg=' '.join(list(poems_sg))
elif wd_num == 2:
poems_sg=' '.join(jieba.cut(poems_sg))
mask_png = np.array(Image.open(path.join(d,in_mask)))
wa = WordCloud(background_color="white",
font_path='/usr/share/fonts/windows10/simsun.ttc',
max_words=wds_max,
mask=mask_png,
max_font_size=wdf_siz,
min_word_length=wd_num).generate(poems_sg)
print(poems_author[0],'----词云',wd_num)
plt.imshow(wa,interpolation="bilinear")
plt.axis("off")
plt.show()
min_f=0.1
LB=tj_core('李白.txt')
DF=tj_core('杜甫.txt')
LB_frequent=tj_HFWD(LB[0],LB[1],LB[2],min_f)
DF_frequent=tj_HFWD(DF[0],DF[1],DF[2],min_f)
tj_frequence(LB[0],LB[1],LB[2],min_f)
print('\n')
tj_frequence(DF[0],DF[1],DF[2],min_f)
print('\n')
m = 1
print('两位诗人都爱用的字有{}个，这些字为：'.format(len(LB_frequent & DF_frequent)))
for i in LB_frequent & DF_frequent:
print(i, end = ' ')
if m % 10 == 0:
print()
m += 1
print('\n')
n = 1
print('李白爱用但杜甫不爱用的字有{}个，这些字为：'.format(len(LB_frequent - DF_frequent)))
for i in LB_frequent - DF_frequent:
print(i, end = ' ')
if n % 10 == 0:
print()
n += 1
print('\n')
k = 1
print('杜甫爱用但李白不爱用的字有{}个，这些字为：'.format(len(DF_frequent - LB_frequent)))
for i in DF_frequent - LB_frequent:
print(i, end = ' ')
if k % 10 == 0:
print()
k += 1
print('\n')
poem_path = '/home/feng'
poem_mask="libai.png"
mask_png = np.array(Image.open(path.join(poem_path,poem_mask)))
plt.imshow(mask_png,interpolation="bilinear")
plt.axis("off")
plt.show()
pome_cloud('李白.txt',poem_mask,poem_path,1,100,40)
pome_cloud('李白.txt',poem_mask,poem_path,2,100,40)
pome_cloud('杜甫.txt',poem_mask,poem_path,1,100,40)
pome_cloud('杜甫.txt',poem_mask,poem_path,2,100,40)
|