Delete app.py

app.py

@@ -1,272 +0,0 @@
-"""
-AUTOMATION 2 — Hugging Face Spaces App
-=======================================
-AI-Enhanced interface for Amazon & Spotify analysis
-Deploy this on Hugging Face Spaces (SDK: Gradio)
-
-Instructions:
-1. Go to huggingface.co/spaces → Create new Space
-2. Select Gradio as SDK
-3. Upload this file as app.py
-4. Upload amazon_synthetic.csv and spotify_synthetic.csv
-5. Add requirements.txt with: pandas, scikit-learn, matplotlib, vaderSentiment
-"""
-
-import gradio as gr
-import pandas as pd
-import numpy as np
-import matplotlib
-matplotlib.use('Agg')
-import matplotlib.pyplot as plt
-import io
-import tempfile
-import os
-import warnings
-warnings.filterwarnings('ignore')
-
-from sklearn.ensemble import RandomForestRegressor, RandomForestClassifier
-from sklearn.model_selection import train_test_split
-from vaderSentiment.vaderSentiment import SentimentIntensityAnalyzer
-
-# ── TRAIN MODELS ON STARTUP ─────────────────────────────────
-
-print("Loading data and training models...")
-
-# Amazon model
-try:
-    df_amz = pd.read_csv('amazon_synthetic.csv')
-    features_amz = ['actual_price','discounted_price','discount_pct','rating','sentiment_score']
-    df_amz['log_sales'] = np.log1p(df_amz['rating_count'])
-    X_amz = df_amz[features_amz].dropna()
-    y_amz = df_amz.loc[X_amz.index, 'log_sales']
-    rf_amz = RandomForestRegressor(n_estimators=100, random_state=42)
-    rf_amz.fit(X_amz, y_amz)
-    AMZ_LOADED = True
-    print("✓ Amazon model ready")
-except Exception as e:
-    AMZ_LOADED = False
-    print(f"Amazon model failed: {e}")
-
-# Spotify model
-try:
-    df_spot = pd.read_csv('spotify_synthetic.csv')
-    features_spot = ['danceability','energy','loudness','speechiness','acousticness',
-                     'instrumentalness','valence','tempo','explicit']
-    df_spot['explicit'] = df_spot['explicit'].astype(int)
-    X_spot = df_spot[features_spot].dropna()
-    y_spot = df_spot.loc[X_spot.index, 'popularity']
-    rf_spot = RandomForestRegressor(n_estimators=100, random_state=42)
-    rf_spot.fit(X_spot, y_spot)
-    SPOT_LOADED = True
-    print("✓ Spotify model ready")
-except Exception as e:
-    SPOT_LOADED = False
-    print(f"Spotify model failed: {e}")
-
-analyzer = SentimentIntensityAnalyzer()
-
-# ── AMAZON TAB ───────────────────────────────────────────────
-
-def analyze_amazon(category, actual_price, discount_pct, rating, review_text):
-    discounted_price = actual_price * (1 - discount_pct / 100)
-    sentiment_score = analyzer.polarity_scores(review_text)['compound'] if review_text else 0.0
-    sentiment_label = 'Positive' if sentiment_score >= 0.05 else ('Negative' if sentiment_score <= -0.05 else 'Neutral')
-
-    if AMZ_LOADED:
-        X = np.array([[actual_price, discounted_price, discount_pct, rating, sentiment_score]])
-        log_sales_pred = rf_amz.predict(X)[0]
-        sales_pred = int(np.expm1(log_sales_pred))
-    else:
-        sales_pred = int(rating * 1000 * (1 + sentiment_score))
-
-    # Score 0-100
-    score = min(100, int(
-        25 * (rating / 5) +
-        25 * ((sentiment_score + 1) / 2) +
-        25 * min(sales_pred / 50000, 1) +
-        25 * min(discount_pct / 70, 1)
-    ))
-    tier = 'Top Performer' if score >= 75 else 'Average' if score >= 45 else 'Underperformer'
-
-    # Plot
-    fig, axes = plt.subplots(1, 2, figsize=(10, 4))
-    fig.suptitle('Amazon Product Analysis', fontsize=13, fontweight='bold')
-
-    metrics = ['Rating\n(/5)', 'Sentiment\n(scaled)', 'Discount\n(%/100)', 'Score\n(/100)']
-    values  = [rating/5, (sentiment_score+1)/2, discount_pct/100, score/100]
-    colors  = ['#2E86AB','#A23B72','#F18F01','#44BBA4']
-    bars = axes[0].bar(metrics, values, color=colors, edgecolor='white')
-    axes[0].set_ylim(0, 1.1)
-    axes[0].set_title('Performance Breakdown', fontweight='bold')
-    for bar, val in zip(bars, values):
-        axes[0].text(bar.get_x()+bar.get_width()/2, bar.get_height()+0.02,
-                     f'{val:.2f}', ha='center', fontsize=10)
-
-    axes[1].pie([score, 100-score], labels=[f'Score: {score}', ''],
-                colors=['#2E86AB','#eee'], startangle=90,
-                wedgeprops={'edgecolor':'white'})
-    axes[1].set_title(f'Overall: {tier}', fontweight='bold')
-
-    plt.tight_layout()
-    tmp = tempfile.NamedTemporaryFile(delete=False, suffix='.png')
-    plt.savefig(tmp.name, format='png', dpi=120, bbox_inches='tight')
-    plt.close()
-
-    report = f"""
-📦 AMAZON PRODUCT ANALYSIS REPORT
-{'='*40}
-Category:         {category}
-Actual Price:     ₹{actual_price:.2f}
-Discounted Price: ₹{discounted_price:.2f}
-Discount:         {discount_pct}%
-Rating:           {rating}/5
-{'─'*40}
-SENTIMENT
-  Score:  {sentiment_score:.3f}
-  Label:  {sentiment_label}
-{'─'*40}
-PREDICTED SALES VOLUME
-  Est. Review Count: ~{sales_pred:,}
-{'─'*40}
-PERFORMANCE SCORE
-  Score: {score}/100
-  Tier:  {tier}
-{'─'*40}
-RECOMMENDATIONS
-{'  ✓ Maintain pricing — good balance' if discount_pct < 50 else '  ⚠ High discount may hurt margins'}
-{'  ✓ Leverage positive reviews in ads' if sentiment_label == 'Positive' else '  ⚠ Address negative customer feedback'}
-{'  ✓ Strong rating — invest in visibility' if rating >= 4 else '  ⚠ Focus on quality improvement'}
-"""
-    return report.strip(), tmp.name
-
-# ── SPOTIFY TAB ──────────────────────────────────────────────
-
-def analyze_spotify(genre, danceability, energy, loudness, tempo, valence,
-                    acousticness, speechiness, instrumentalness, explicit):
-    exp = 1 if explicit else 0
-
-    if SPOT_LOADED:
-        X = np.array([[danceability, energy, loudness, speechiness, acousticness,
-                       instrumentalness, valence, tempo, exp]])
-        pop_pred = float(np.clip(rf_spot.predict(X)[0], 0, 100))
-    else:
-        pop_pred = float(np.clip(20 + 30*danceability + 15*energy + 0.5*(loudness+20), 0, 100))
-
-    is_hit = pop_pred >= 60
-    tier = 'Hit 🔥' if pop_pred >= 70 else 'Popular' if pop_pred >= 50 else 'Mid-tier' if pop_pred >= 30 else 'Niche'
-
-    # Radar-style bar chart
-    fig, axes = plt.subplots(1, 2, figsize=(12, 4))
-    fig.suptitle('Spotify Track Analysis', fontsize=13, fontweight='bold')
-
-    feats  = ['Dance', 'Energy', 'Valence', 'Acoustic', 'Speech']
-    values = [danceability, energy, valence, acousticness, speechiness]
-    axes[0].bar(feats, values, color='#2E86AB', edgecolor='white')
-    axes[0].set_ylim(0, 1.1)
-    axes[0].set_title('Audio Feature Profile', fontweight='bold')
-    for i, (f, v) in enumerate(zip(feats, values)):
-        axes[0].text(i, v+0.02, f'{v:.2f}', ha='center', fontsize=9)
-
-    pop_normalized = pop_pred / 100
-    axes[1].pie([pop_normalized, 1-pop_normalized],
-                labels=[f'{pop_pred:.0f}/100', ''],
-                colors=['#A23B72','#eee'], startangle=90,
-                wedgeprops={'edgecolor':'white'})
-    axes[1].set_title(f'Predicted Popularity: {tier}', fontweight='bold')
-
-    plt.tight_layout()
-    tmp2 = tempfile.NamedTemporaryFile(delete=False, suffix='.png')
-    plt.savefig(tmp2.name, format='png', dpi=120, bbox_inches='tight')
-    plt.close()
-
-    report = f"""
-🎵 SPOTIFY TRACK ANALYSIS REPORT
-{'='*40}
-Genre:            {genre}
-Tempo:            {tempo:.1f} BPM
-Explicit:         {'Yes' if explicit else 'No'}
-{'─'*40}
-AUDIO FEATURES
-  Danceability:   {danceability:.3f}
-  Energy:         {energy:.3f}
-  Loudness:       {loudness:.1f} dB
-  Valence:        {valence:.3f}
-  Acousticness:   {acousticness:.3f}
-  Speechiness:    {speechiness:.3f}
-{'─'*40}
-PREDICTED PERFORMANCE
-  Popularity Score: {pop_pred:.1f}/100
-  Commercial Tier:  {tier}
-  Hit Potential:    {'Yes 🔥' if is_hit else 'Not quite yet'}
-{'─'*40}
-RECOMMENDATIONS
-{'  ✓ Strong commercial profile — pitch to playlists' if pop_pred >= 60 else '  → Consider boosting danceability'}
-{'  ✓ High energy suits live events & promo' if energy >= 0.7 else '  → Lower energy may limit mainstream appeal'}
-{'  ✓ Positive mood boosts streaming' if valence >= 0.5 else '  → Consider a more upbeat arrangement'}
-"""
-    return report.strip(), tmp2.name
-
-# ── GRADIO INTERFACE ─────────────────────────────────────────
-
-with gr.Blocks(title="AI Music & E-Commerce Analyzer", theme=gr.themes.Soft()) as demo:
-
-    gr.Markdown("""
-    # 🤖 AI Performance Analyzer
-    ### Amazon Products × Spotify Tracks
-    *Predicting commercial success using Machine Learning & Sentiment Analysis*
-    """)
-
-    with gr.Tabs():
-
-        # ── AMAZON TAB
-        with gr.TabItem("🛒 Amazon Product"):
-            gr.Markdown("### Analyze an Amazon product's performance potential")
-            with gr.Row():
-                with gr.Column():
-                    amz_category = gr.Dropdown(
-                        ['Electronics','Clothing','HomeKitchen','Books','Sports','Beauty','Toys'],
-                        label="Category", value="Electronics")
-                    amz_actual   = gr.Slider(50, 50000, value=999, label="Actual Price (₹)")
-                    amz_discount = gr.Slider(0, 80, value=30, label="Discount %")
-                    amz_rating   = gr.Slider(1.0, 5.0, value=4.2, step=0.1, label="Rating (/5)")
-                    amz_review   = gr.Textbox(label="Sample Review Text",
-                                              value="Great product, works perfectly and fast delivery!",
-                                              lines=2)
-                    amz_btn = gr.Button("Analyze Product", variant="primary")
-                with gr.Column():
-                    amz_output = gr.Textbox(label="Analysis Report", lines=20)
-                    amz_plot   = gr.Image(label="Performance Chart", type="filepath")
-
-            amz_btn.click(analyze_amazon,
-                          inputs=[amz_category, amz_actual, amz_discount, amz_rating, amz_review],
-                          outputs=[amz_output, amz_plot])
-
-        # ── SPOTIFY TAB
-        with gr.TabItem("🎵 Spotify Track"):
-            gr.Markdown("### Predict a track's commercial success on Spotify")
-            with gr.Row():
-                with gr.Column():
-                    sp_genre  = gr.Dropdown(
-                        ['pop','hip-hop','rock','electronic','jazz','r-n-b','country','latin','indie','classical'],
-                        label="Genre", value="pop")
-                    sp_dance  = gr.Slider(0.0, 1.0, value=0.7, step=0.01, label="Danceability")
-                    sp_energy = gr.Slider(0.0, 1.0, value=0.8, step=0.01, label="Energy")
-                    sp_loud   = gr.Slider(-40, 0, value=-7, step=0.5, label="Loudness (dB)")
-                    sp_tempo  = gr.Slider(60, 200, value=120, step=1, label="Tempo (BPM)")
-                    sp_val    = gr.Slider(0.0, 1.0, value=0.6, step=0.01, label="Valence (positivity)")
-                    sp_acou   = gr.Slider(0.0, 1.0, value=0.1, step=0.01, label="Acousticness")
-                    sp_speech = gr.Slider(0.0, 1.0, value=0.05, step=0.01, label="Speechiness")
-                    sp_instr  = gr.Slider(0.0, 1.0, value=0.0, step=0.01, label="Instrumentalness")
-                    sp_exp    = gr.Checkbox(label="Explicit content", value=False)
-                    sp_btn    = gr.Button("Analyze Track", variant="primary")
-                with gr.Column():
-                    sp_output = gr.Textbox(label="Analysis Report", lines=20)
-                    sp_plot   = gr.Image(label="Track Performance Chart", type="filepath")
-
-            sp_btn.click(analyze_spotify,
-                         inputs=[sp_genre, sp_dance, sp_energy, sp_loud, sp_tempo,
-                                 sp_val, sp_acou, sp_speech, sp_instr, sp_exp],
-                         outputs=[sp_output, sp_plot])
-
-if __name__ == "__main__":
-    demo.launch(share=True)