Delete app.py

app.py

@@ -1,100 +0,0 @@
-
-import gradio as gr
-from PyPDF2 import PdfReader
-from sklearn.feature_extraction.text import TfidfVectorizer
-from sklearn.metrics.pairwise import cosine_similarity
-from sentence_transformers import SentenceTransformer, util
-import matplotlib.pyplot as plt
-import pandas as pd
-import io
-
-# Load sentence transformer model
-model = SentenceTransformer('all-MiniLM-L6-v2')
-
-def extract_text_from_pdf(pdf_file):
-    try:
-        reader = PdfReader(io.BytesIO(pdf_file))
-        full_text = ""
-        for page in reader.pages:
-            text = page.extract_text()
-            if text:
-                full_text += text
-        return full_text.strip()
-    except Exception as e:
-        return ""
-
-def tfidf_similarity(text1, text2):
-    vectorizer = TfidfVectorizer()
-    tfidf = vectorizer.fit_transform([text1, text2])
-    return cosine_similarity(tfidf[0:1], tfidf[1:2])[0][0]
-
-def transformer_similarity(text1, text2):
-    emb1 = model.encode(text1, convert_to_tensor=True)
-    emb2 = model.encode(text2, convert_to_tensor=True)
-    return util.pytorch_cos_sim(emb1, emb2).item()
-
-def compare_all(old_pdf, new_pdf, lo_file):
-    try:
-        los = lo_file.decode("utf-8", errors="ignore").splitlines()
-        los = [lo.strip() for lo in los if lo.strip()]
-    except:
-        return "❌ Could not read learning outcomes file.", None, None, None, None, None
-
-    old_text = extract_text_from_pdf(old_pdf)
-    new_text = extract_text_from_pdf(new_pdf)
-
-    if not old_text or not new_text:
-        return "❌ Could not extract text from one or both PDFs.", None, None, None, None, None
-
-    tfidf_sim = tfidf_similarity(old_text, new_text)
-    transformer_sim = transformer_similarity(old_text, new_text)
-    content_diff = abs(len(new_text) - len(old_text)) / max(len(old_text), 1) * 100
-
-    tfidf_summary = f"🔍 **TF-IDF Similarity:** {round(tfidf_sim * 100, 2)}%"
-    trans_summary = f"🤖 **Transformer Similarity:** {round(transformer_sim * 100, 2)}%"
-    length_change = f"📄 **Text Length Difference:** {round(content_diff, 2)}%"
-
-    insights = f"{tfidf_summary}\n{trans_summary}\n{length_change}\n"
-
-    # LO-wise comparison
-    lo_scores = []
-    for lo in los:
-        lo_score = transformer_similarity(lo, new_text)
-        lo_scores.append(lo_score)
-
-    labels = [f"LO{i+1}" for i in range(len(los))]
-    df = pd.DataFrame({
-        "Learning Outcome": labels,
-        "Match Score (0-1)": [round(s, 2) for s in lo_scores]
-    })
-
-    # Chart
-    fig, ax = plt.subplots(figsize=(8, 4))
-    ax.bar(labels, lo_scores, color="skyblue")
-    ax.set_ylim(0, 1)
-    ax.set_ylabel("Semantic Match")
-    ax.set_title("LO-wise Transformer Similarity")
-    plt.xticks(rotation=45)
-
-    return insights, df, fig, new_text, tfidf_sim, transformer_sim
-
-iface = gr.Interface(
-    fn=compare_all,
-    inputs=[
-        gr.File(label="Old Handout PDF", type="binary"),
-        gr.File(label="New Handout PDF", type="binary"),
-        gr.File(label="Learning Outcomes (TXT)", type="binary"),
-    ],
-    outputs=[
-        gr.Textbox(label="📘 Summary of Analysis"),
-        gr.Dataframe(label="📊 LO-wise Semantic Comparison"),
-        gr.Plot(label="📈 LO Match Chart"),
-        gr.Textbox(label="📖 New Handout Preview (Full Text)", lines=10, max_lines=20),
-        gr.Number(label="TF-IDF Similarity Score"),
-        gr.Number(label="Transformer Similarity Score"),
-    ],
-    title="📘 Course Handout Comparison Tool",
-    description="Compare old and new handouts, analyze semantic change, LO alignment, and visualize Bloom's mapping."
-)
-
-iface.launch()