Update app.py

app.py

@@ -1,23 +1,105 @@
-from gradio_client import Client
+import streamlit as st
+from keras.models import load_model
+import numpy as np
+import tensorflow as tf
+import nltk
+import re
+from nltk.corpus import stopwords
+from nltk.tokenize import TweetTokenizer
+from nltk.tokenize import word_tokenize
+from tensorflow.keras.preprocessing.text import Tokenizer
+from tensorflow.keras.preprocessing.sequence import pad_sequences
 
-client = Client("https://ayoubchlin-ayoubchlin-bart-mnli-cnn-news.hf.space/")
+import subprocess
 
-result = client.predict(
-				"Prior to the introduction of scopes, Dropbox API apps would select only their level of content access (described below). Business API apps would select from one of four permission types to determine the API calls they have access to:",	# str representing input in 'Input' Textbox component
-				'politics,news,sports,tech,science',	# str representing input in 'Possible class names (comma-separated)' Textbox component
-				False,	# bool representing input in 'Allow multiple true classes' Checkbox component
-				api_name="/predict"
-)
+# Command to execute
+command = "git clone https://huggingface.co/lydiadida/lstmhatespeachdetection"
 
-import json
+# Execute the command
+try:
+    subprocess.run(command, shell=True, check=True)
+    print("Git clone command executed successfully.")
+except subprocess.CalledProcessError as e:
+    print(f"Error executing git clone command: {e}")
 
+# Load the LSTM model
+model_path = "model.h5"  # Set your model path here
+lstm_model = load_lstm_model(model_path)
 
 
-# Open the file in read mode
-with open(result, 'r') as file:
-    # Read the contents of the file
-    json_data = json.load(file)
+def clean_text(text):
+    # Remove stopwords
+    stop_words = set(stopwords.words('english'))
+    words = nltk.word_tokenize(text)
+    filtered_words = [word for word in words if word not in stop_words]
+    
+    # Remove Twitter usernames
+    text = re.sub(r'@\w+', '', ' '.join(filtered_words))
+    
+    # Remove URLs
+    text = re.sub(r'http\S+', '', text)
+    
+    # Tokenize using TweetTokenizer
+    tokenizer = TweetTokenizer(preserve_case=True)
+    text = tokenizer.tokenize(text)
+    
+    # Remove hashtag symbols
+    text = [word.replace('#', '') for word in text]
+    
+    # Remove short words
+    text = ' '.join([word.lower() for word in text if len(word) > 2])
+    
+    # Remove digits
+    text = re.sub(r'\d+', '', text)
+    
+    # Remove non-alphanumeric characters
+    text = re.sub(r'[^a-zA-Z\s]', '', text)
+    
+    return text
 
-# Do further processing with the JSON data
-# For example, print the content of the JSON file
-print(json_data["label"])
+
+def preprocess_text(text):
+    # Clean the text
+    cleaned_text = clean_text(text)
+    
+    # Tokenize and pad sequences
+    token = Tokenizer()
+    token.fit_on_texts([cleaned_text])
+    text_sequences = token.texts_to_sequences([cleaned_text])
+    padded_sequences = pad_sequences(text_sequences, maxlen=100)
+    
+    return padded_sequences
+
+# Function to load the saved LSTM model
+@st.cache(allow_output_mutation=True)
+def load_lstm_model(model_path):
+    return load_model(model_path)
+
+# Function to predict hate speech
+def predict_hate_speech(text):
+    # Preprocess the text
+    padded_sequences = preprocess_text(text)
+    prediction = lstm_model.predict(padded_sequences)
+    return prediction
+
+# Main function to run the Streamlit app
+def main():
+    # Set up Streamlit UI
+    st.title("Hate Speech Detection")
+    st.write("Enter text below to detect hate speech:")
+    input_text = st.text_area("Input Text", "")
+
+    if st.button("Detect Hate Speech"):
+        if input_text:
+            # Predict hate speech
+            prediction = predict_hate_speech(input_text, lstm_model)
+            if prediction > 0.5:
+                st.error("Hate Speech Detected")
+            else:
+                st.success("No Hate Speech Detected")
+        else:
+            st.warning("Please enter some text")
+
+# Run the app
+if __name__ == "__main__":
+    main()