Create app.py

app.py

@@ -0,0 +1,236 @@
+import gradio as gr
+import sqlite3
+import fitz # PyMuPDF
+import re
+import matplotlib.pyplot as plt
+import pandas as pd
+import numpy as np
+import requests
+import os
+from collections import Counter
+from datetime import datetime
+
+# ==============================
+# DATABASE SETUP
+# ==============================
+
+conn = sqlite3.connect("exam_trends.db", check_same_thread=False)
+cursor = conn.cursor()
+
+cursor.execute("""
+CREATE TABLE IF NOT EXISTS past_questions (
+    id INTEGER PRIMARY KEY AUTOINCREMENT,
+    year INTEGER,
+    question TEXT,
+    topic TEXT
+)
+""")
+
+cursor.execute("""
+CREATE TABLE IF NOT EXISTS current_questions (
+    id INTEGER PRIMARY KEY AUTOINCREMENT,
+    question TEXT,
+    topic TEXT
+)
+""")
+
+conn.commit()
+
+
+# ==============================
+# PDF TEXT EXTRACTION
+# ==============================
+
+def extract_text_from_pdf(file):
+    text = ""
+    pdf = fitz.open(stream=file.read(), filetype="pdf")
+    for page in pdf:
+        text += page.get_text()
+    return text
+
+
+# ==============================
+# SIMPLE QUESTION SEGMENTATION
+# ==============================
+
+def extract_questions(text):
+    questions = re.split(r'\n\d+\.|\nQ\d+', text)
+    return [q.strip() for q in questions if len(q.strip()) > 20]
+
+
+# ==============================
+# SIMPLE TOPIC CLASSIFIER
+# (Basic keyword approach)
+# ==============================
+
+def classify_topic(question):
+    question = question.lower()
+
+    if "integral" in question or "derivative" in question:
+        return "Calculus"
+    elif "triangle" in question or "angle" in question:
+        return "Geometry"
+    elif "probability" in question:
+        return "Probability"
+    elif "matrix" in question:
+        return "Linear Algebra"
+    else:
+        return "Algebra"
+
+
+# ==============================
+# STORE PAST PAPERS
+# ==============================
+
+def upload_past_papers(files):
+    for file in files:
+        text = extract_text_from_pdf(file)
+        questions = extract_questions(text)
+
+        year = datetime.now().year # Simplified
+
+        for q in questions:
+            topic = classify_topic(q)
+            cursor.execute(
+                "INSERT INTO past_questions (year, question, topic) VALUES (?, ?, ?)",
+                (year, q, topic),
+            )
+
+    conn.commit()
+    return "Past papers uploaded and processed successfully."
+
+
+# ==============================
+# STORE CURRENT PAPER
+# ==============================
+
+def upload_current_paper(file):
+    text = extract_text_from_pdf(file)
+    questions = extract_questions(text)
+
+    for q in questions:
+        topic = classify_topic(q)
+        cursor.execute(
+            "INSERT INTO current_questions (question, topic) VALUES (?, ?)",
+            (q, topic),
+        )
+
+    conn.commit()
+    return "Current paper uploaded successfully."
+
+
+# ==============================
+# TREND ANALYSIS ENGINE
+# ==============================
+
+def analyze_trends():
+    cursor.execute("SELECT topic FROM past_questions")
+    past_topics = [row[0] for row in cursor.fetchall()]
+
+    cursor.execute("SELECT topic FROM current_questions")
+    current_topics = [row[0] for row in cursor.fetchall()]
+
+    past_count = Counter(past_topics)
+    current_count = Counter(current_topics)
+
+    results = []
+
+    for topic, freq in past_count.items():
+        frequency_weight = freq
+        recency_weight = freq * 0.2
+        gap_weight = 1 if topic not in current_count else 0
+
+        prediction_score = (
+            frequency_weight * 0.5
+            + recency_weight * 0.3
+            + gap_weight * 0.2
+        )
+
+        results.append((topic, prediction_score))
+
+    results.sort(key=lambda x: x[1], reverse=True)
+
+    df = pd.DataFrame(results, columns=["Topic", "Prediction Score"])
+    return df
+
+
+# ==============================
+# HEATMAP VISUALIZATION
+# ==============================
+
+def generate_heatmap():
+    cursor.execute("SELECT topic FROM past_questions")
+    topics = [row[0] for row in cursor.fetchall()]
+    count = Counter(topics)
+
+    df = pd.DataFrame.from_dict(count, orient='index', columns=['Frequency'])
+    df = df.sort_values(by='Frequency', ascending=False)
+
+    plt.figure()
+    plt.imshow(np.array(df['Frequency']).reshape(-1,1))
+    plt.yticks(range(len(df.index)), df.index)
+    plt.xticks([])
+    plt.title("Topic Heatmap")
+    plt.colorbar()
+    plt.tight_layout()
+
+    return plt
+
+
+# ==============================
+# AI QUESTION GENERATOR (Simple)
+# ==============================
+
+def generate_predicted_questions():
+    df = analyze_trends()
+    top_topics = df["Topic"].head(3).tolist()
+
+    output = "Predicted High Probability Questions:\n\n"
+
+    for topic in top_topics:
+        output += f"• Create an exam-level question from {topic}\n"
+
+    return output
+
+
+# ==============================
+# GRADIO UI
+# ==============================
+
+with gr.Blocks() as demo:
+    gr.Markdown("# 🎓 AI Predictive Exam Intelligence System")
+
+    with gr.Tab("📂 Upload Past 5 Years Papers"):
+        past_files = gr.File(file_count="multiple")
+        past_button = gr.Button("Upload & Analyze")
+        past_output = gr.Textbox()
+
+        past_button.click(upload_past_papers, inputs=past_files, outputs=past_output)
+
+    with gr.Tab("📄 Upload Current Year Paper"):
+        current_file = gr.File()
+        current_button = gr.Button("Upload Current Paper")
+        current_output = gr.Textbox()
+
+        current_button.click(upload_current_paper, inputs=current_file, outputs=current_output)
+
+    with gr.Tab("📊 Trend Analysis"):
+        analyze_button = gr.Button("Run Trend Analysis")
+        trend_output = gr.Dataframe()
+
+        analyze_button.click(analyze_trends, outputs=trend_output)
+
+    with gr.Tab("🔥 Topic Heatmap"):
+        heatmap_button = gr.Button("Generate Heatmap")
+        heatmap_output = gr.Plot()
+
+        heatmap_button.click(generate_heatmap, outputs=heatmap_output)
+
+    with gr.Tab("🔮 Predicted Questions"):
+        predict_button = gr.Button("Generate Predictions")
+        predict_output = gr.Textbox()
+
+        predict_button.click(generate_predicted_questions, outputs=predict_output)
+
+
+demo.launch()