Spaces:
Sleeping
Sleeping
File size: 3,657 Bytes
f736779 a4c52ed c7f4293 34c9ab5 a4c52ed 1931174 a4c52ed 1931174 a4c52ed 1931174 a4c52ed 1931174 9d4affc 34c9ab5 9d4affc a4c52ed adbab52 a4c52ed adbab52 a4c52ed 9d4affc 1931174 9d4affc 1931174 |
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 |
#Gerekli kütüphaneleri içe aktar
import nltk
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize
import string
import stylecloud
from PIL import Image
import matplotlib.pyplot as plt
import streamlit as st
import os
import base64
# NLTK kütüphanesinden gerekli bileşenleri indir
nltk.download('stopwords')
nltk.download('punkt')
def preprocess_and_create_stylecloud(file_path, output_name='stylecloud.png',
icon_name='fas fa-laptop', lang='english'):
# Metni dosyadan oku
with open(file_path, 'r', encoding='utf-8') as f:
text = f.read()
# Dil için stopwords listesini yükle
stop_words = set(stopwords.words(lang))
# Noktalama işaretlerini kaldır
translator = str.maketrans('', '', string.punctuation)
text = text.translate(translator)
# Metni tokenlere ayır ve küçük harfe çevir
tokens = word_tokenize(text.lower(), language=lang)
# Stopwords'ü filtrele
filtered_tokens = [word for word in tokens if word not in stop_words]
# Filtrelenmiş tokenleri birleştir
processed_text = ' '.join(filtered_tokens)
# StyleCloud oluştur
stylecloud.gen_stylecloud(text=processed_text,
icon_name=icon_name,
output_name=output_name)
# Oluşturulan StyleCloud'u göster
im = Image.open(output_name)
plt.figure(figsize=(10, 10))
plt.imshow(im)
plt.axis('off') # Eksenleri gizle
plt.show()
def create_stylecloud(text, language, icon):
output_file = "static/stylecloud.png"
stylecloud.gen_stylecloud(text=text, icon_name=icon, output_name=output_file)
# Dosyayı Base64 olarak kodla
with open(output_file, "rb") as file:
data = file.read()
encoded = base64.b64encode(data).decode()
return encoded
st.title("WordCloud Creator")
file = st.file_uploader("Import txt file", type=["txt"])
if file is not None:
text = file.getvalue().decode("utf-8")
language = st.radio("Language", ["tr", "en"])
icon_options = [
("fas fa-car", "Araba"),
("fas fa-star-and-crescent", "Ay Yıldız"),
("fas fa-star", "Yıldız"),
("fas fa-trophy", "Kupa"),
("fas fa-heart", "Kalp"),
("fas fa-wifi", "WiFi"),
("fas fa-laptop", "Dizüstü Bilgisayar"),
("fas fa-coffee", "Kahve"),
("fas fa-radio", "Radyo"),
("fas fa-snowflake", "Kar Tanesi"),
("fas fa-apple-alt", "Elma"),
("fas fa-bell", "Zil"),
("fas fa-bicycle", "Bisiklet"),
("fas fa-bolt", "Yıldırım"),
("fas fa-book", "Kitap"),
("fas fa-bug", "Böcek"),
("fas fa-camera", "Kamera"),
("fas fa-crown", "Taç"),
("fas fa-futbol", "Futbol"),
("fas fa-gift", "Hediye")
]
icon_labels = [label for _, label in icon_options]
icon_selection = st.selectbox("İkon Seçimi", icon_labels, index=1)
icon = [icon for icon, label in icon_options if label == icon_selection][0]
if st.button("Create"):
encoded_image = create_stylecloud(text, language, icon)
st.markdown(
f"""
<a href="data:application/octet-stream;base64,{encoded_image}" download="stylecloud.png">
<button>Download WordCloud</button>
</a>
""",
unsafe_allow_html=True
)
image = Image.open("static/stylecloud.png")
st.image(image, caption='WordCloud', use_column_width=True)
# Ensure the file is deleted after display
if os.path.exists(output_file):
os.remove(output_file) |