Spaces:
Sleeping
Sleeping
Update src/streamlit_app.py
Browse files- src/streamlit_app.py +7 -5
src/streamlit_app.py
CHANGED
|
@@ -9,11 +9,13 @@ from tensorflow.keras.preprocessing.sequence import pad_sequences
|
|
| 9 |
from tensorflow.keras.models import load_model
|
| 10 |
import nltk
|
| 11 |
|
| 12 |
-
|
|
|
|
|
|
|
| 13 |
|
| 14 |
-
# Download the stopwords
|
| 15 |
-
nltk.download('stopwords', download_dir=
|
| 16 |
-
nltk.download('punkt', download_dir=
|
| 17 |
|
| 18 |
# Load the trained model
|
| 19 |
model = load_model('src/model.keras')
|
|
@@ -49,7 +51,7 @@ def text_preprocessing(text):
|
|
| 49 |
tokens = word_tokenize(text)
|
| 50 |
|
| 51 |
# Stopwords removal
|
| 52 |
-
|
| 53 |
|
| 54 |
# Combining Tokens
|
| 55 |
text = ' '.join(tokens)
|
|
|
|
| 9 |
from tensorflow.keras.models import load_model
|
| 10 |
import nltk
|
| 11 |
|
| 12 |
+
# Use /tmp for NLTK data (writable in Hugging Face Spaces)
|
| 13 |
+
nltk_data_dir = "/tmp/nltk_data"
|
| 14 |
+
nltk.data.path.append(nltk_data_dir)
|
| 15 |
|
| 16 |
+
# Download the stopwords and punkt resources
|
| 17 |
+
nltk.download('stopwords', download_dir=nltk_data_dir)
|
| 18 |
+
nltk.download('punkt', download_dir=nltk_data_dir)
|
| 19 |
|
| 20 |
# Load the trained model
|
| 21 |
model = load_model('src/model.keras')
|
|
|
|
| 51 |
tokens = word_tokenize(text)
|
| 52 |
|
| 53 |
# Stopwords removal
|
| 54 |
+
tokens = [word for word in tokens if word not in stpwds_id]
|
| 55 |
|
| 56 |
# Combining Tokens
|
| 57 |
text = ' '.join(tokens)
|