Create app.py

app.py

@@ -0,0 +1,192 @@
+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-oUMTpRuEUBnl9LUbjBGTT3BlbkFJ4mFy0AeXnTVQGVr7V31U'
+
+
+# Load the pipeline
+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 = {
+    0: 'Culture',
+    1: 'Finance',
+    2: 'Medical',
+    3: 'Politics',
+    4: 'Religion',
+    5: 'Sports',
+    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)
+        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
+def summarization_page():
+    st.title("Text Summarization with OpenAI GPT")
+    st.write("Enter text below and click 'Summarize' to generate a summary.")
+    
+    # Text input from user
+    input_text = st.text_area("Text Input", height=200)
+    
+    # Button to trigger summarization
+    if st.button("Summarize"):
+        if input_text:
+            with st.spinner("Generating summary..."):
+                summary = generate_summary(input_text)
+                st.write("### Summary")
+                st.write(summary)
+        else:
+            st.warning("Please enter some text to summarize.")
+
+def generate_questions(user_text):
+    questions = [
+        {
+            "question": "ما هو اسم الكتاب الذي حصل على جائزة عربية على هامش افتتاح معرض بيروت العربي الدولي للكتاب ؟",
+            "options": ["الحضارة الاسلامية", "المصحف وقراءاته", "مؤمنون بلا حدود", "عبد المجيد الشرقي"],
+            "answer": "المصحف وقراءاته"
+        },
+        {
+            "question": "من الذي حصل أشرف على تصنيف كتاب المصحف وقراءاته ؟",
+            "options": ["عبد المجيد الشرقي", "النادي الثقافي العربي", "مؤسسة مؤمنون بلا حدود", "مجموعة من الباحثين"],
+            "answer": "عبد المجيد الشرقي"
+        },
+        {
+            "question": "كم عدد مجلدات كتاب المصحف وقراءاته ؟",
+            "options": ["ثلاثة مجلدات", "أربعة مجلدات", "خمسة مجلدات", "ستة مجلدات"],
+            "answer": "خمسة مجلدات"
+        }
+    ]
+    return questions
+
+def quiz_page():
+    st.title("Simple Quiz")
+
+    user_text = st.text_area("Enter your text here:", height=150)
+    
+    if st.button("Generate Questions"):
+        if user_text:
+            questions = generate_questions(user_text)
+            st.session_state.questions = questions
+            st.session_state.current_question = None
+            st.session_state.score = 0
+            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 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!")
+
+        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")
+
+            if st.button("Submit Answer"):
+                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)}")
+            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"])
+
+if page == "Classification":
+    classification_page()
+elif page == "Summarization":
+    summarization_page()
+else:
+    quiz_page()