Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -1,3 +1,4 @@
|
|
|
|
1 |
import nltk
|
2 |
from nltk.corpus import stopwords
|
3 |
from nltk.tokenize import word_tokenize
|
@@ -6,25 +7,27 @@ import stylecloud
|
|
6 |
from PIL import Image
|
7 |
import matplotlib.pyplot as plt
|
8 |
import streamlit as st
|
9 |
-
import tempfile
|
10 |
import os
|
11 |
-
os.environ['NLTK_DATA'] = '/path/to/nltk_data'
|
12 |
-
from nltk.corpus import stopwords
|
13 |
|
14 |
# NLTK kütüphanesinden gerekli bileşenleri indir
|
15 |
nltk.download('stopwords')
|
16 |
nltk.download('punkt')
|
17 |
|
18 |
-
def preprocess_and_create_stylecloud(
|
|
|
|
|
|
|
|
|
|
|
19 |
# Dil için stopwords listesini yükle
|
20 |
-
stop_words = set(stopwords.words(
|
21 |
|
22 |
# Noktalama işaretlerini kaldır
|
23 |
translator = str.maketrans('', '', string.punctuation)
|
24 |
text = text.translate(translator)
|
25 |
|
26 |
# Metni tokenlere ayır ve küçük harfe çevir
|
27 |
-
tokens = word_tokenize(text.lower(), language=
|
28 |
|
29 |
# Stopwords'ü filtrele
|
30 |
filtered_tokens = [word for word in tokens if word not in stop_words]
|
@@ -33,11 +36,24 @@ def preprocess_and_create_stylecloud(text, language, icon):
|
|
33 |
processed_text = ' '.join(filtered_tokens)
|
34 |
|
35 |
# StyleCloud oluştur
|
36 |
-
|
37 |
-
|
38 |
-
|
39 |
-
|
40 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
41 |
|
42 |
st.title("WordCloud Creator")
|
43 |
|
@@ -76,12 +92,11 @@ if file is not None:
|
|
76 |
icon = [icon for icon, label in icon_options if label == icon_selection][0]
|
77 |
|
78 |
if st.button("Create"):
|
79 |
-
|
80 |
-
|
81 |
-
|
82 |
-
|
83 |
-
|
84 |
-
|
85 |
-
|
86 |
-
)
|
87 |
-
st.image(output_file, caption='WordCloud', use_column_width=True)
|
|
|
1 |
+
Gerekli kütüphaneleri içe aktar
|
2 |
import nltk
|
3 |
from nltk.corpus import stopwords
|
4 |
from nltk.tokenize import word_tokenize
|
|
|
7 |
from PIL import Image
|
8 |
import matplotlib.pyplot as plt
|
9 |
import streamlit as st
|
|
|
10 |
import os
|
|
|
|
|
11 |
|
12 |
# NLTK kütüphanesinden gerekli bileşenleri indir
|
13 |
nltk.download('stopwords')
|
14 |
nltk.download('punkt')
|
15 |
|
16 |
+
def preprocess_and_create_stylecloud(file_path, output_name='stylecloud.png',
|
17 |
+
icon_name='fas fa-laptop', lang='english'):
|
18 |
+
# Metni dosyadan oku
|
19 |
+
with open(file_path, 'r', encoding='utf-8') as f:
|
20 |
+
text = f.read()
|
21 |
+
|
22 |
# Dil için stopwords listesini yükle
|
23 |
+
stop_words = set(stopwords.words(lang))
|
24 |
|
25 |
# Noktalama işaretlerini kaldır
|
26 |
translator = str.maketrans('', '', string.punctuation)
|
27 |
text = text.translate(translator)
|
28 |
|
29 |
# Metni tokenlere ayır ve küçük harfe çevir
|
30 |
+
tokens = word_tokenize(text.lower(), language=lang)
|
31 |
|
32 |
# Stopwords'ü filtrele
|
33 |
filtered_tokens = [word for word in tokens if word not in stop_words]
|
|
|
36 |
processed_text = ' '.join(filtered_tokens)
|
37 |
|
38 |
# StyleCloud oluştur
|
39 |
+
stylecloud.gen_stylecloud(text=processed_text,
|
40 |
+
icon_name=icon_name,
|
41 |
+
output_name=output_name)
|
42 |
+
# Oluşturulan StyleCloud'u göster
|
43 |
+
im = Image.open(output_name)
|
44 |
+
plt.figure(figsize=(10, 10))
|
45 |
+
plt.imshow(im)
|
46 |
+
plt.axis('off') # Eksenleri gizle
|
47 |
+
plt.show()
|
48 |
+
|
49 |
+
def create_stylecloud(text, language, icon):
|
50 |
+
output_file = "stylecloud.png"
|
51 |
+
|
52 |
+
stylecloud.gen_stylecloud(text=text,
|
53 |
+
icon_name=icon,
|
54 |
+
output_name=output_file)
|
55 |
+
|
56 |
+
return output_file
|
57 |
|
58 |
st.title("WordCloud Creator")
|
59 |
|
|
|
92 |
icon = [icon for icon, label in icon_options if label == icon_selection][0]
|
93 |
|
94 |
if st.button("Create"):
|
95 |
+
output_file = create_stylecloud(text, language, icon)
|
96 |
+
st.markdown(f"### [Download WordCloud](./{output_file})")
|
97 |
+
|
98 |
+
image = Image.open(output_file)
|
99 |
+
st.image(image, caption='WordCloud', use_column_width=True)
|
100 |
+
# Ensure the file is deleted after display
|
101 |
+
if os.path.exists(output_file):
|
102 |
+
os.remove(output_file)
|
|