Update app.py

app.py

@@ -2,127 +2,74 @@ import streamlit as st
 import random
 import openai
 import joblib
-import re
-from nltk.corpus import stopwords
-from nltk.tokenize import word_tokenize
-import nltk
-
-nltk.download('stopwords')
-nltk.download('punkt')
-
-StopWords = set(stopwords.words('arabic'))
-# Set your OpenAI API key here
-openai.api_key = 'sk-proj-iWuQUklfwcatAyNbwpmhT3BlbkFJhfrEnp9SFu1sdwSPcxsX'
-
 
 # Load the pipeline
 pipeLine = joblib.load('model_pipeline.joblib')
+# Load the model pipeline
+model_pipeline = joblib.load('model_pipeline.joblib')
 
-# Text Preprocessor Class
-class TextPreprocessor:
-    def __init__(self):
-        self.StopWords = set(stopwords.words('arabic'))
-        self.ArabicDiacritics = re.compile(r"""
-                                 ّ    | # Tashdid
-                                 َ    | # Fatha
-                                 ً    | # Tanwin Fath
-                                 ُ    | # Damma
-                                 ٌ    | # Tanwin Damm
-                                 ِ    | # Kasra
-                                 ٍ    | # Tanwin Kasr
-                                 ْ    | # Sukun
-                                 ـ     # Tatwil/Kashida
-                             """, re.VERBOSE)
-        self.RegrexPattern = re.compile(
-            r"[\U0001F600-\U0001F64F" +  # emoticons {😀 , 😆}
-            r"\U0001F300-\U0001F5FF" +  # symbols & pictographs {🌍 , 🌞}
-            r"\U0001F680-\U0001F6FF" +  # transport & map symbols {🚌 , 🚕 }
-            r"\U0001F1E0-\U0001F1FF]",   # flags (iOS) { 🇺🇸 , 🇨🇦 }
-            re.UNICODE
-        )
-
-    def preprocess_text(self, text):
-        # Remove special characters {& $ @} and punctuation {. , ? !}
-        text = re.sub(r'[^\w\s]', '', text)
-
-        # Remove emoji characters
-        text = re.sub(self.RegrexPattern, '', text)
-
-        # Remove Arabic diacritics
-        text = re.sub(self.ArabicDiacritics, '', text)
-        tokens = word_tokenize(text)
-        tokens = [word for word in tokens if word not in self.StopWords]
-        return ' '.join(tokens)
-
-preprocessor = TextPreprocessor()
-
+# Category mapping
 category_mapping = {
-    0: 'Culture',
+    0: 'ثقافة',
     1: 'Finance',
     2: 'Medical',
-    3: 'Politics',
+    3: 'سياسة',
     4: 'Religion',
-    5: 'Sports',
+    5: 'رياضي',
     6: 'Tech'
 }
-
-def classify_article(article_text, pipeline):
-    # Preprocess the texts
-    preprocessed_text = preprocessor.preprocess_text(article_text)
-    predicted_category = pipeline.predict([preprocessed_text])[0]
-    return category_mapping.get(predicted_category, "Unknown")
-
 def classification_page():
-    st.title("Text Classification")
-    st.write("Enter text below to classify it into categories like Culture, Finance, Medical, Politics, Religion, Sports, and Tech.")
-
-    # Text input from user
-    input_text = st.text_area("Text Input", height=200)
-
-    # Button to trigger classification
-    if st.button("Classify"):
-        if input_text:
-            with st.spinner("Classifying..."):
-                category = classify_article(input_text, pipeLine)
-                st.write("### Predicted Category")
-                st.write(category)
+    st.title("صفحة التصنيف")
+    
+    article = st.text_area("ادخل المقال هنا", height=150)
+    
+    if st.button("صنّف"):
+        if article.strip():
+            # Use the model pipeline to predict the category
+            numeric_prediction = model_pipeline.predict([article])[0]
+            category_prediction = category_mapping.get(numeric_prediction, "Unknown")
+            st.write(f"**{category_prediction}** الصنف المتوقع : ")
         else:
-            st.warning("Please enter some text to classify.")
-
-# Function to generate summary using OpenAI
-def generate_summary(text):
-    response = openai.ChatCompletion.create(
-        model="gpt-3.5-turbo",  # Default model
-        messages=[
-            {"role": "system", "content": "You are a helpful assistant that summarizes text."},
-            {"role": "user", "content": text}
-        ],
-        temperature=0.7,  # Default temperature
-        max_tokens=150,  # Default max tokens
-        top_p=1.0,
-        frequency_penalty=0.0,
-        presence_penalty=0.0
-    )
-    return response.choices[0].message['content'].strip()
-
-# Function for the summarization page
+            st.error("Please enter an article to classify.")
+
 def summarization_page():
-    st.title("Text Summarization")
-    st.write("Enter text below and click 'Summarize' to generate a summary.")
+    st.title("صفحة التلخيص")
     
+
+    # Set your OpenAI API key
+    openai.api_key = 'sk-proj-iWuQUklfwcatAyNbwpmhT3BlbkFJhfrEnp9SFu1sdwSPcxsX'
+    # Streamlit app
+
     # Text input from user
-    input_text = st.text_area("Text Input", height=200)
-    
+    input_text = st.text_area("ادخل المقال هنا", height=200)
+
+    # Function to generate summary using OpenAI
+    def generate_summary(text):
+        response = openai.ChatCompletion.create(
+            model="gpt-3.5-turbo",  # Default model
+            messages=[
+                {"role": "system", "content": "You are a helpful assistant that summarizes text."},
+                {"role": "user", "content": text}
+            ],
+            temperature=0.7,  # Default temperature
+            max_tokens=150,  # Default max tokens
+            top_p=1.0,
+            frequency_penalty=0.0,
+            presence_penalty=0.0
+        )
+        return response.choices[0].message['content'].strip()
+
     # Button to trigger summarization
-    if st.button("Summarize"):
+    if st.button("لخّص"):
         if input_text:
-            with st.spinner("Generating summary..."):
+            with st.spinner("إنشاء التلخيص"):
                 summary = generate_summary(input_text)
-                st.write("### Summary")
+                st.write("### الملخص ")
                 st.write(summary)
         else:
             st.warning("Please enter some text to summarize.")
 
+
 def generate_questions(user_text):
     questions = [
         {
@@ -144,11 +91,11 @@ def generate_questions(user_text):
     return questions
 
 def quiz_page():
-    st.title("Simple Quiz")
+    st.title("صفحة الاختبار")
 
-    user_text = st.text_area("Enter your text here:", height=150)
+    user_text = st.text_area("ادخل المقال هنا", height=150)
     
-    if st.button("Generate Questions"):
+    if st.button("أنشئ الأسئلة"):
         if user_text:
             questions = generate_questions(user_text)
             st.session_state.questions = questions
@@ -157,36 +104,36 @@ def quiz_page():
             st.session_state.asked_questions = []
 
     if 'questions' in st.session_state and len(st.session_state.questions) > 0:
-        if st.button("Ask a Question"):
+        if st.button("اسأل"):
             if len(st.session_state.asked_questions) < len(st.session_state.questions):
                 available_questions = [q for q in st.session_state.questions if q not in st.session_state.asked_questions]
                 st.session_state.current_question = random.choice(available_questions)
                 st.session_state.asked_questions.append(st.session_state.current_question)
             else:
-                st.write("All questions have been asked!")
+                st.write("تم عرض جميع الأسئلة")
 
         if st.session_state.current_question:
             question = st.session_state.current_question
-            st.write(f"Question: {question['question']}")
-            user_answer = st.radio("Choose your answer:", question['options'], key="answer")
+            st.write(f"السؤال: {question['question']}")
+            user_answer = st.radio("اختر الإجابة", question['options'], key="answer")
 
-            if st.button("Submit Answer"):
+            if st.button("سلّم الإجابة"):
                 if user_answer == question['answer']:
                     st.session_state.score += 1
                 st.session_state.current_question = None
 
-        if st.button("Finish Quiz"):
-            st.write(f"Your final score is {st.session_state.score} out of {len(st.session_state.asked_questions)}")
+        if st.button("إنهاء الاختبار"):
+            st.write(f"نتيجة الاختبار {st.session_state.score} من {len(st.session_state.asked_questions)}")
             st.session_state.score = 0
             st.session_state.asked_questions = []
             st.session_state.questions = []
 
 # Add navigation
-page = st.sidebar.selectbox("Choose a page", ["Classification", "Summarization", "Quiz"])
+page = st.sidebar.selectbox("اختر صفحة", ["التصنيف", "التلخيص", "الاختبار"])
 
-if page == "Classification":
+if page == "التصنيف":
     classification_page()
-elif page == "Summarization":
+elif page == "التلخيص":
     summarization_page()
 else:
-    quiz_page()
+    quiz_page()