Upload app.py

app.py

@@ -0,0 +1,48 @@
+import re
+import nltk
+import pickle
+import numpy as np
+import pandas as pd
+import streamlit as st 
+from datasets import load_dataset
+from sklearn.metrics.pairwise import cosine_similarity
+
+nltk.download('punkt')
+
+dataset = pd.read_csv("Preprocess_LK_Hadith_dataset.csv")
+
+labels = dataset['Arabic_Grade']
+
+# Helper functions
+def remove_tashkeel(text):
+    tashkeel_pattern = re.compile(r'[\u0617-\u061A\u064B-\u0652]')
+    return re.sub(tashkeel_pattern, '', text)
+
+def preprocess_arabic_text(text):
+    text = remove_tashkeel(text)
+    tokens = nltk.word_tokenize(text)
+    cleaned_tokens = [token for token in tokens if token.isalnum()]
+    lowercase_tokens = [token.lower() for token in cleaned_tokens]
+    return " ".join(lowercase_tokens)
+
+# Function to predict label
+def predict_label(input_text, threshold=0.5):
+    with open("tfidf_vectorizer.pkl", "rb") as f:
+        vectorizer = pickle.load(f)
+    with open("cosine_similarity_model.pkl", "rb") as f:
+        X = pickle.load(f)
+
+    input_text = preprocess_arabic_text(input_text)
+    input_vector = vectorizer.transform([input_text])
+    similarities = cosine_similarity(input_vector, X).flatten()
+
+    max_index = np.argmax(similarities)
+    max_similarity = similarities[max_index]
+
+    if max_similarity >= threshold:
+        return labels.iloc[max_index]
+    else:
+        return "No similar text found in dataset"
+
+x = st.slider('Enter Hadith') 
+st.write(x, 'Hadith Classification', predict_label)