Spaces:
Running
Running
Upload 4 files
Browse files- app.py +48 -0
- requirements.txt +4 -0
- svm_model.pkl +3 -0
- tfidf_vectorizer.pkl +3 -0
app.py
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# app.py
|
| 2 |
+
import streamlit as st
|
| 3 |
+
import pandas as pd
|
| 4 |
+
from sklearn.feature_extraction.text import TfidfVectorizer
|
| 5 |
+
from sklearn.svm import SVC
|
| 6 |
+
import joblib
|
| 7 |
+
|
| 8 |
+
# Load the SVM model and TF-IDF vectorizer
|
| 9 |
+
svm_model = joblib.load('svm_model.pkl')
|
| 10 |
+
tfidf_vectorizer = joblib.load('tfidf_vectorizer.pkl')
|
| 11 |
+
|
| 12 |
+
def preprocess_input(text):
|
| 13 |
+
# Preprocess the input text (e.g., convert to lowercase, remove special characters, etc.)
|
| 14 |
+
# Implement your specific preprocessing steps based on the training data
|
| 15 |
+
processed_text = text.lower()
|
| 16 |
+
# Add more preprocessing steps as needed
|
| 17 |
+
|
| 18 |
+
return processed_text
|
| 19 |
+
|
| 20 |
+
def predict_bullying(text):
|
| 21 |
+
# Preprocess input text
|
| 22 |
+
processed_text = preprocess_input(text)
|
| 23 |
+
|
| 24 |
+
# Convert text to numerical representation using TF-IDF
|
| 25 |
+
text_tfidf = tfidf_vectorizer.transform([processed_text])
|
| 26 |
+
|
| 27 |
+
# Make prediction using the SVM model
|
| 28 |
+
prediction = svm_model.predict(text_tfidf)[0]
|
| 29 |
+
|
| 30 |
+
return prediction
|
| 31 |
+
|
| 32 |
+
# Streamlit UI
|
| 33 |
+
def main():
|
| 34 |
+
st.title("Cyberbullying Detection App (Arabic)")
|
| 35 |
+
user_input = st.text_area("Enter a text for cyberbullying detection:")
|
| 36 |
+
|
| 37 |
+
if st.button("Predict"):
|
| 38 |
+
if user_input:
|
| 39 |
+
prediction = predict_bullying(user_input)
|
| 40 |
+
if prediction == "Bullying":
|
| 41 |
+
st.write(f"<span style='color:red; font-weight:bold'>{prediction}</span>", unsafe_allow_html=True)
|
| 42 |
+
else:
|
| 43 |
+
st.write(f"<span style='color:cyan; font-weight:bold'>{prediction}</span>", unsafe_allow_html=True)
|
| 44 |
+
else:
|
| 45 |
+
st.warning("Please enter text for prediction.")
|
| 46 |
+
|
| 47 |
+
if __name__ == "__main__":
|
| 48 |
+
main()
|
requirements.txt
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
streamlit
|
| 2 |
+
pandas
|
| 3 |
+
scikit-learn
|
| 4 |
+
joblib
|
svm_model.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86cc2e53d9ed03b786c0b0d08162e63cd2a0eddf30c9ef3548837178f326a034
|
| 3 |
+
size 384771
|
tfidf_vectorizer.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86a2ed13d6b9ccca4d42dd85f37ef23980bfb8f6c5090bd471f7d653bf2203df
|
| 3 |
+
size 493534
|