ckean 1

KAGGLE_NOTEBOOK.md

@@ -1,191 +0,0 @@
-# 🎵 Spotify Genre Classifier - Kaggle Notebook
-
-## Cell 1: Install Dependencies
-```python
-!pip install -q transformers datasets accelerate evaluate scikit-learn python-dotenv tqdm
-```
-
-## Cell 2: Import and Setup Secrets
-```python
-from kaggle_secrets import UserSecretsClient
-import os
-
-# Get secrets from Kaggle
-user_secrets = UserSecretsClient()
-os.environ['HF_TOKEN'] = user_secrets.get_secret("HF_TOKEN")
-os.environ['HF_USERNAME'] = user_secrets.get_secret("HF_USERNAME")
-
-print(f"✓ Logged in as: {os.environ['HF_USERNAME']}")
-```
-
-## Cell 3: Check GPU
-```python
-import torch
-
-if torch.cuda.is_available():
-    print(f"✓ GPU Available: {torch.cuda.get_device_name(0)}")
-    print(f"  GPU Count: {torch.cuda.device_count()}")
-else:
-    print("⚠ No GPU - using CPU (slower)")
-```
-
-## Cell 4: Load Dataset
-```python
-from datasets import load_dataset
-
-print("📊 Loading dataset...")
-dataset = load_dataset("maharshipandya/spotify-tracks-dataset")
-print(f"✓ Loaded {len(dataset['train'])} tracks")
-```
-
-## Cell 5: Load Model
-```python
-from transformers import AutoTokenizer, AutoModelForSequenceClassification
-
-model_name = "gpt2"
-print(f"🤖 Loading model: {model_name}")
-
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-if tokenizer.pad_token is None:
-    tokenizer.pad_token = tokenizer.eos_token
-
-# Get unique genres
-genres = sorted(set(dataset['train']['track_genre']))
-num_labels = len(genres)
-label2id = {g: i for i, g in enumerate(genres)}
-id2label = {i: g for i, g in enumerate(genres)}
-
-model = AutoModelForSequenceClassification.from_pretrained(
-    model_name, 
-    num_labels=num_labels,
-    id2label=id2label,
-    label2id=label2id
-)
-
-print(f"✓ Model loaded: {num_labels} genres")
-```
-
-## Cell 6: Preprocess Data
-```python
-def tokenize(ex):
-    texts = [str(t) if t else "" for t in ex['track_name']]
-    tokenized = tokenizer(texts, padding='max_length', truncation=True, max_length=128)
-    tokenized['labels'] = [label2id[l] for l in ex['track_genre']]
-    return tokenized
-
-print("🔧 Preprocessing...")
-tokenized_dataset = dataset.map(tokenize, batched=True, remove_columns=dataset['train'].column_names)
-
-# Create validation split
-splits = tokenized_dataset['train'].train_test_split(test_size=0.1)
-tokenized_dataset = {
-    'train': splits['train'],
-    'validation': splits['test']
-}
-
-print(f"✓ Train: {len(tokenized_dataset['train'])}, Val: {len(tokenized_dataset['validation'])}")
-```
-
-## Cell 7: Training
-```python
-from transformers import TrainingArguments, Trainer
-import numpy as np
-import evaluate
-
-# Metrics
-def compute_metrics(eval_pred):
-    predictions = np.argmax(eval_pred.predictions, axis=1)
-    accuracy = evaluate.load("accuracy")
-    f1 = evaluate.load("f1")
-    return {
-        'accuracy': accuracy.compute(predictions=predictions, references=eval_pred.label_ids)['accuracy'],
-        'f1_macro': f1.compute(predictions=predictions, references=eval_pred.label_ids, average='macro')['f1']
-    }
-
-# Training args
-training_args = TrainingArguments(
-    output_dir="./model",
-    num_train_epochs=3,
-    per_device_train_batch_size=16,
-    per_device_eval_batch_size=32,
-    learning_rate=5e-5,
-    fp16=True,  # Use mixed precision on GPU
-    eval_strategy="epoch",
-    save_strategy="epoch",
-    load_best_model_at_end=True,
-    logging_steps=50,
-    report_to="none"
-)
-
-# Trainer
-trainer = Trainer(
-    model=model,
-    args=training_args,
-    train_dataset=tokenized_dataset['train'],
-    eval_dataset=tokenized_dataset['validation'],
-    processing_class=tokenizer,
-    compute_metrics=compute_metrics
-)
-
-print("🚀 Starting training...")
-trainer.train()
-print("✓ Training complete!")
-```
-
-## Cell 8: Evaluate
-```python
-print("📈 Evaluating...")
-metrics = trainer.evaluate()
-print(f"Final Accuracy: {metrics['eval_accuracy']:.4f}")
-print(f"Final F1: {metrics['eval_f1_macro']:.4f}")
-```
-
-## Cell 9: Save Model
-```python
-model.save_pretrained("./final_model")
-tokenizer.save_pretrained("./final_model")
-print("💾 Model saved to ./final_model")
-```
-
-## Cell 10: Test Predictions
-```python
-import torch
-
-test_tracks = [
-    "Bohemian Rhapsody",
-    "Shape of You",
-    "Old Town Road",
-    "Blinding Lights",
-    "Bad Guy"
-]
-
-model.eval()
-print("\n🎵 Predictions:")
-for track in test_tracks:
-    inputs = tokenizer(track, return_tensors='pt', truncation=True, max_length=128)
-    if torch.cuda.is_available():
-        inputs = {k: v.cuda() for k, v in inputs.items()}
-    
-    with torch.no_grad():
-        outputs = model(**inputs)
-        pred_id = torch.argmax(outputs.logits, dim=-1).item()
-        conf = torch.softmax(outputs.logits, dim=-1)[0, pred_id].item()
-    
-    print(f"  '{track}' → {id2label[pred_id]} ({conf:.2%})")
-```
-
-## Cell 11: Push to Hub (Optional)
-```python
-from huggingface_hub import login
-
-hf_token = os.environ['HF_TOKEN']
-username = os.environ['HF_USERNAME']
-
-login(token=hf_token)
-
-repo_name = "spotify-genre-classifier"
-model.push_to_hub(f"{username}/{repo_name}")
-tokenizer.push_to_hub(f"{username}/{repo_name}")
-
-print(f"✅ Model pushed to: https://huggingface.co/{username}/{repo_name}")
-```

QUICKSTART.md

@@ -1,16 +0,0 @@
-# Quick Start
-
-```bash
-cd ~/code/hf-training
-pip install -r requirements.txt
-cp .env.example .env
-nano .env  # Add: HF_TOKEN=hf_xxxxx
-./run.sh spotify
-```
-
-## Commands
-
-```bash
-./run.sh spotify        # BERT
-./run.sh gpt2_spotify   # GPT-2
-```

deploy_space.sh

@@ -1,108 +0,0 @@
-#!/bin/bash
-#
-# Create and deploy Hugging Face Space
-# Usage: ./deploy_space.sh [space_name]
-#
-
-set -e
-
-SPACE_NAME="${1:-spotify-genre-classifier}"
-
-echo "=========================================="
-echo "  Hugging Face Space Deployment"
-echo "=========================================="
-echo ""
-
-# Check HF token
-if [ ! -f ".env" ]; then
-    echo "❌ .env not found"
-    exit 1
-fi
-
-source .env
-if [ -z "$HF_TOKEN" ]; then
-    echo "❌ HF_TOKEN not set in .env"
-    exit 1
-fi
-
-echo "✓ HF_TOKEN found"
-echo ""
-
-# Username
-USERNAME="maxxcarl"
-
-echo "✓ Username: $USERNAME"
-echo ""
-
-SPACE_ID="$USERNAME/$SPACE_NAME"
-
-echo "Creating Space: $SPACE_ID"
-echo ""
-
-# Create space if not exists
-hf repo create "$SPACE_ID" --type space --space_sdk gradio --exists-ok || true
-
-# Copy files to temp space folder
-TEMP_DIR="/tmp/hf-space-$SPACE_NAME"
-rm -rf "$TEMP_DIR"
-mkdir -p "$TEMP_DIR"
-
-# Copy all necessary files
-cp app.py "$TEMP_DIR/"
-cp requirements_sp.txt "$TEMP_DIR/requirements.txt"
-
-# Copy trained model if exists
-if [ -d "outputs/final_model" ]; then
-    echo "Copying trained model..."
-    cp -r outputs/final_model "$TEMP_DIR/model/"
-fi
-
-# Create README for space
-cat > "$TEMP_DIR/README.md" << 'EOF'
----
-title: Spotify Genre Classifier
-emoji: 🎵
-colorFrom: blue
-colorTo: purple
-sdk: gradio
-sdk_version: 4.44.0
-app_file: app.py
-pinned: false
-license: mit
----
-
-# 🎵 Spotify Genre Classifier
-
-This model predicts the genre of a song based on its track name.
-
-## Features
-- Fine-tuned GPT-2 model
-- 114 different genres
-- Real-time predictions
-
-## How to Use
-1. Enter a track name
-2. Click "Predict Genre"
-3. See the predicted genre and confidence
-
-## Training Your Own
-Check out the training pipeline: https://github.com/huggingface/transformers
-EOF
-
-# Upload to space
-echo ""
-echo "Uploading files to Space..."
-cd "$TEMP_DIR"
-hf upload "$SPACE_ID" "." "." --repo-type space
-cd - > /dev/null
-
-echo ""
-echo "=========================================="
-echo "✅ Space deployed successfully!"
-echo "=========================================="
-echo ""
-echo "🌐 View your Space:"
-echo "   https://huggingface.co/spaces/$SPACE_ID"
-echo ""
-echo "📝 Note: First build may take 2-3 minutes"
-echo ""

kaggle_auto.ipynb

@@ -1,82 +0,0 @@
-# 🎵 Spotify Genre Classifier - Automatic Training
-# 
-# Kaggle Notebook: Just run this single cell!
-# 
-# Setup:
-# 1. Add secrets in Kaggle: HF_TOKEN and HF_USERNAME
-# 2. Run this cell
-# 3. Wait for training to complete (~15-20 min on GPU)
-# 4. Model will be saved and optionally pushed to HF Hub
-
-print("=" * 60)
-print("  Spotify Genre Classifier - Automatic Training")
-print("=" * 60)
-
-# Step 1: Get secrets
-from kaggle_secrets import UserSecretsClient
-import os
-
-user_secrets = UserSecretsClient()
-os.environ['HF_TOKEN'] = user_secrets.get_secret("HF_TOKEN")
-os.environ['HF_USERNAME'] = user_secrets.get_secret("HF_USERNAME")
-
-print(f"\n✓ Logged in as: {os.environ['HF_USERNAME']}")
-
-# Step 2: Install dependencies
-print("\n📦 Installing dependencies...")
-!pip install -q transformers datasets accelerate evaluate scikit-learn python-dotenv tqdm
-
-# Step 3: Clone repo
-print("\n📥 Cloning training repo...")
-!git clone https://huggingface.co/maxxcarl/spotify-training
-%cd spotify-training
-
-# Step 4: Check GPU
-print("\n🔍 Checking GPU...")
-import torch
-if torch.cuda.is_available():
-    print(f"✓ GPU: {torch.cuda.get_device_name(0)}")
-else:
-    print("⚠ No GPU - using CPU")
-
-# Step 5: Run training
-print("\n" + "=" * 60)
-print("  Starting Training")
-print("=" * 60)
-
-!chmod +x run.sh
-!./run.sh gpt2_spotify
-
-# Step 6: Test model
-print("\n" + "=" * 60)
-print("  Testing Model")
-print("=" * 60)
-
-!./run.sh test
-
-# Step 7: Push to Hub (optional)
-print("\n" + "=" * 60)
-print("  Push to Hugging Face Hub?")
-print("=" * 60)
-
-from huggingface_hub import login
-
-hf_token = os.environ['HF_TOKEN']
-username = os.environ['HF_USERNAME']
-
-login(token=hf_token)
-
-repo_name = "spotify-genre-classifier"
-print(f"\nPushing to: {username}/{repo_name}")
-
-from transformers import AutoTokenizer, AutoModelForSequenceClassification
-
-model = AutoModelForSequenceClassification.from_pretrained("./outputs/final_model")
-tokenizer = AutoTokenizer.from_pretrained("./outputs/final_model")
-
-model.push_to_hub(f"{username}/{repo_name}")
-tokenizer.push_to_hub(f"{username}/{repo_name}")
-
-print(f"\n✅ Complete!")
-print(f"📊 Model: https://huggingface.co/{username}/{repo_name}")
-print(f"🌐 Space: https://huggingface.co/spaces/{username}/pool")

kaggle_single_cell.py

@@ -1,57 +0,0 @@
-# Kaggle Auto-Training Notebook
-# Copy this entire file into a single Kaggle notebook cell
-
-print("=" * 60)
-print("  Spotify Genre Classifier - Automatic Training")
-print("=" * 60)
-
-# Get secrets
-from kaggle_secrets import UserSecretsClient
-import os
-
-user_secrets = UserSecretsClient()
-os.environ['HF_TOKEN'] = user_secrets.get_secret("HF_TOKEN")
-os.environ['HF_USERNAME'] = user_secrets.get_secret("HF_USERNAME")
-
-print(f"\n✓ Logged in as: {os.environ['HF_USERNAME']}")
-
-# Install
-print("\n📦 Installing...")
-!pip install -q transformers datasets accelerate evaluate scikit-learn python-dotenv tqdm
-
-# Clone
-print("\n📥 Cloning...")
-!git clone https://huggingface.co/maxxcarl/spotify-training
-%cd spotify-training
-
-# Check GPU
-print("\n🔍 GPU:")
-import torch
-if torch.cuda.is_available():
-    print(f"✓ {torch.cuda.get_device_name(0)}")
-else:
-    print("⚠ CPU only")
-
-# Train
-print("\n🚀 Training...")
-!chmod +x run.sh
-!./run.sh gpt2_spotify
-
-# Test
-print("\n📈 Testing...")
-!./run.sh test
-
-# Push to Hub
-print("\n💾 Pushing to Hub...")
-from huggingface_hub import login
-login(token=os.environ['HF_TOKEN'])
-
-from transformers import AutoTokenizer, AutoModelForSequenceClassification
-model = AutoModelForSequenceClassification.from_pretrained("./outputs/final_model")
-tokenizer = AutoTokenizer.from_pretrained("./outputs/final_model")
-
-username = os.environ['HF_USERNAME']
-model.push_to_hub(f"{username}/spotify-genre-classifier")
-tokenizer.push_to_hub(f"{username}/spotify-genre-classifier")
-
-print(f"\n✅ Done! https://huggingface.co/{username}/spotify-genre-classifier")

requirements.txt

@@ -1,23 +0,0 @@
-# Core Hugging Face & PyTorch
-transformers>=4.35.0
-datasets>=2.14.0
-torch>=2.0.0
-accelerate>=0.24.0
-
-# Training & Evaluation
-scikit-learn>=1.3.0
-evaluate>=0.4.1
-seqeval>=1.2.2
-
-# Configuration & Environment
-python-dotenv>=1.0.0
-hydra-core>=1.3.0
-omegaconf>=2.3.0
-
-# Progress & Logging
-tqdm>=4.66.0
-wandb>=0.15.0
-
-# Utilities
-pandas>=2.0.0
-numpy>=1.24.0

requirements_sp.txt

@@ -1,3 +0,0 @@
-transformers>=4.35.0
-torch>=2.0.0
-gradio>=4.0.0