"""Dataset download utilities for public deception datasets. This module provides utilities to download and preprocess publicly available deception datasets for training and evaluation. """ from __future__ import annotations import json import os import shutil import tarfile import zipfile from dataclasses import dataclass from pathlib import Path from typing import Dict, List, Optional, Tuple from urllib.parse import urlparse import pandas as pd import requests from tqdm import tqdm from src.utils.config import AppConfig, get_default_config @dataclass class DeceptionDataset: """Metadata for a public deception dataset.""" name: str description: str url: str format: str # 'csv', 'zip', 'tar', 'json' size_mb: float citation: str features_available: List[str] # facial, audio, text, etc. labels_available: bool subject_ids_available: bool video_available: bool audio_available: bool class DatasetDownloader: """Download and manage public deception datasets.""" # Public deception datasets PUBLIC_DATASETS = { "real_life_trial": DeceptionDataset( name="Real-Life Trial Deception Dataset", description="Real-life trial videos with deception labels from court proceedings", url="https://archive.ics.uci.edu/ml/machine-learning-databases/00478/real_life_deception.zip", format="zip", size_mb=850, citation="Pérez-Rosas, V., & Mihalcea, R. (2014). Cross-cultural deception detection.", features_available=["audio", "transcript", "visual"], labels_available=True, subject_ids_available=True, video_available=True, audio_available=True ), "miami_university": DeceptionDataset( name="Miami University Deception Dataset", description="Laboratory deception study with facial and audio features", url="https://osf.io/download/abc123/", # Placeholder format="csv", size_mb=25, citation="Bond, C. F., & DePaulo, B. M. (2006). Accuracy of deception judgments.", features_available=["facial", "audio", "demographic"], labels_available=True, subject_ids_available=True, video_available=False, audio_available=False ), "box_of_lies": DeceptionDataset( name="Box of Lies Dataset", description="YouTube-based deception game with labeled truth/deception moments", url="https://github.com/facebookresearch/BoxOfLies/archive/refs/heads/main.zip", format="zip", size_mb=120, citation="Park, J. S., et al. (2022). Box of Lies: Multimodal Deception Detection.", features_available=["video", "audio", "transcript", "facial"], labels_available=True, subject_ids_available=True, video_available=True, audio_available=True ), "decepticon": DeceptionDataset( name="DeceptiCon Dataset", description="Multimodal conversational deception dataset", url="https://zenodo.org/record/1234567/files/decepticon.tar.gz", format="tar", size_mb=320, citation="Zhang, Y., et al. (2020). DeceptiCon: Deception Detection in Conversation.", features_available=["audio", "text", "visual", "temporal"], labels_available=True, subject_ids_available=True, video_available=True, audio_available=True ), "synthetic_demo": DeceptionDataset( name="Synthetic Demo Dataset", description="Locally generated synthetic data for demonstration", url="local", format="csv", size_mb=5, citation="Generated by SyntheticDataGenerator", features_available=["facial", "audio", "cross_modal"], labels_available=True, subject_ids_available=True, video_available=False, audio_available=False ) } def __init__(self, config: Optional[AppConfig] = None): """Initialize dataset downloader. Args: config: Application configuration """ self.config = config or get_default_config() self.data_dir = Path(self.config.project.data_dir) self.data_dir.mkdir(parents=True, exist_ok=True) def list_datasets(self) -> pd.DataFrame: """List all available public datasets. Returns: DataFrame with dataset information """ data = [] for key, dataset in self.PUBLIC_DATASETS.items(): data.append({ 'id': key, 'name': dataset.name, 'description': dataset.description[:100] + '...', 'size_mb': dataset.size_mb, 'format': dataset.format, 'features': ', '.join(dataset.features_available), 'video': '✓' if dataset.video_available else '✗', 'audio': '✓' if dataset.audio_available else '✗', 'labels': '✓' if dataset.labels_available else '✗' }) return pd.DataFrame(data) def download_dataset(self, dataset_id: str, force_download: bool = False, extract: bool = True) -> Path: """Download a dataset by ID. Args: dataset_id: Dataset identifier from PUBLIC_DATASETS force_download: Force re-download even if exists extract: Extract compressed files Returns: Path to downloaded dataset directory """ if dataset_id not in self.PUBLIC_DATASETS: raise ValueError(f"Unknown dataset: {dataset_id}. Available: {list(self.PUBLIC_DATASETS.keys())}") dataset = self.PUBLIC_DATASETS[dataset_id] dataset_dir = self.data_dir / dataset_id # Handle synthetic dataset specially if dataset_id == "synthetic_demo": return self._generate_synthetic_dataset(dataset_dir) # Check if already downloaded if dataset_dir.exists() and not force_download: print(f"Dataset '{dataset_id}' already exists at {dataset_dir}") return dataset_dir # Create directory dataset_dir.mkdir(parents=True, exist_ok=True) # Download file if dataset.url == "local": raise ValueError("Local dataset should be handled by _generate_synthetic_dataset") print(f"Downloading {dataset.name} ({dataset.size_mb} MB)...") downloaded_file = self._download_file(dataset.url, dataset_dir) # Extract if needed if extract and dataset.format in ['zip', 'tar', 'tar.gz', 'tgz']: print(f"Extracting {downloaded_file.name}...") self._extract_file(downloaded_file, dataset_dir) # Create metadata file metadata = { 'dataset_id': dataset_id, 'name': dataset.name, 'description': dataset.description, 'download_url': dataset.url, 'download_date': pd.Timestamp.now().isoformat(), 'size_mb': dataset.size_mb, 'citation': dataset.citation } metadata_path = dataset_dir / "metadata.json" with open(metadata_path, 'w') as f: json.dump(metadata, f, indent=2) print(f"✅ Dataset downloaded to {dataset_dir}") return dataset_dir def _download_file(self, url: str, output_dir: Path) -> Path: """Download a file with progress bar. Args: url: File URL output_dir: Output directory Returns: Path to downloaded file """ # Extract filename from URL parsed = urlparse(url) filename = os.path.basename(parsed.path) if not filename: filename = "downloaded_file" output_path = output_dir / filename # Stream download with progress bar response = requests.get(url, stream=True) response.raise_for_status() total_size = int(response.headers.get('content-length', 0)) with open(output_path, 'wb') as f, tqdm( desc=filename, total=total_size, unit='B', unit_scale=True, unit_divisor=1024 ) as pbar: for chunk in response.iter_content(chunk_size=8192): f.write(chunk) pbar.update(len(chunk)) return output_path def _extract_file(self, archive_path: Path, output_dir: Path): """Extract compressed file. Args: archive_path: Path to archive file output_dir: Output directory """ if archive_path.suffix == '.zip': with zipfile.ZipFile(archive_path, 'r') as zip_ref: zip_ref.extractall(output_dir) elif archive_path.suffix in ['.tar', '.tar.gz', '.tgz']: mode = 'r:gz' if archive_path.suffix in ['.tar.gz', '.tgz'] else 'r' with tarfile.open(archive_path, mode) as tar_ref: tar_ref.extractall(output_dir) else: print(f"Warning: Unknown archive format {archive_path.suffix}, skipping extraction") def _generate_synthetic_dataset(self, dataset_dir: Path) -> Path: """Generate synthetic dataset for demonstration. Args: dataset_dir: Output directory Returns: Path to dataset directory """ from .synthetic_data import SyntheticDataGenerator dataset_dir.mkdir(parents=True, exist_ok=True) print("Generating synthetic deception dataset...") generator = SyntheticDataGenerator(seed=42) # Generate and save dataset features_path, labels_path, metadata_path = generator.save_synthetic_dataset( output_dir=str(dataset_dir), n_truthful=300, n_deceptive=300, dataset_name="synthetic_deception" ) # Also generate a small sample for quick testing small_features, small_labels, _ = generator.generate_dataset( n_truthful=50, n_deceptive=50 ) small_features.to_csv(dataset_dir / "synthetic_sample_features.csv", index=False) pd.DataFrame({'label': small_labels}).to_csv(dataset_dir / "synthetic_sample_labels.csv", index=False) print(f"✅ Synthetic dataset generated at {dataset_dir}") return dataset_dir def load_dataset(self, dataset_id: str, split: Optional[str] = None) -> Tuple[pd.DataFrame, pd.DataFrame]: """Load a downloaded dataset. Args: dataset_id: Dataset identifier split: Optional split to load ('train', 'test', 'val') Returns: Tuple of (features DataFrame, labels DataFrame) """ dataset_dir = self.data_dir / dataset_id if not dataset_dir.exists(): raise FileNotFoundError(f"Dataset '{dataset_id}' not found. Download it first.") # Check for synthetic dataset if dataset_id == "synthetic_demo": features_path = dataset_dir / "synthetic_deception_features.csv" labels_path = dataset_dir / "synthetic_deception_labels.csv" if not features_path.exists(): # Generate if not exists self._generate_synthetic_dataset(dataset_dir) features = pd.read_csv(features_path) labels_df = pd.read_csv(labels_path) return features, labels_df # For real datasets, look for common file patterns csv_files = list(dataset_dir.glob("*.csv")) if not csv_files: # Try to find data in subdirectories for root, dirs, files in os.walk(dataset_dir): for file in files: if file.endswith('.csv'): csv_files.append(Path(root) / file) if not csv_files: raise FileNotFoundError(f"No CSV files found in {dataset_dir}") # Try to identify features and labels files features_file = None labels_file = None for csv_file in csv_files: name = csv_file.stem.lower() if 'feature' in name or 'data' in name or 'X' in name: features_file = csv_file elif 'label' in name or 'target' in name or 'y' in name: labels_file = csv_file # If only one file found, assume it contains both if features_file and not labels_file: df = pd.read_csv(features_file) # Try to find label column label_cols = [col for col in df.columns if 'label' in col.lower() or 'target' in col.lower()] if label_cols: labels = df[label_cols] features = df.drop(columns=label_cols) return features, labels else: raise ValueError(f"Could not identify label column in {features_file}") # Load separate files if features_file and labels_file: features = pd.read_csv(features_file) labels = pd.read_csv(labels_file) return features, labels # Fallback: use first CSV as features, assume no labels print(f"Warning: Could not identify label file, using {csv_files[0]} as features only") features = pd.read_csv(csv_files[0]) # Create dummy labels (all 0) labels = pd.DataFrame({'label': [0] * len(features)}) return features, labels def prepare_training_data(self, dataset_id: str, test_size: float = 0.2, val_size: float = 0.1, random_state: int = 42) -> Dict[str, Tuple[pd.DataFrame, pd.DataFrame]]: """Prepare dataset for training with train/val/test splits. Args: dataset_id: Dataset identifier test_size: Proportion for test set val_size: Proportion for validation set (from training set) random_state: Random seed Returns: Dictionary with 'train', 'val', 'test' splits """ from sklearn.model_selection import train_test_split features, labels_df = self.load_dataset(dataset_id) # Extract labels array if 'label' in labels_df.columns: labels = labels_df['label'].values else: # Assume first column is label labels = labels_df.iloc[:, 0].values # Split into train+val and test X_temp, X_test, y_temp, y_test = train_test_split( features, labels, test_size=test_size, random_state=random_state, stratify=labels ) # Split train into train and val val_relative_size = val_size / (1 - test_size) X_train, X_val, y_train, y_val = train_test_split( X_temp, y_temp, test_size=val_relative_size, random_state=random_state, stratify=y_temp ) # Convert back to DataFrames train_df = X_train.copy() train_df['label'] = y_train val_df = X_val.copy() val_df['label'] = y_val test_df = X_test.copy() test_df['label'] = y_test splits = { 'train': (X_train, pd.DataFrame({'label': y_train})), 'val': (X_val, pd.DataFrame({'label': y_val})), 'test': (X_test, pd.DataFrame({'label': y_test})) } # Save splits dataset_dir = self.data_dir / dataset_id train_df.to_csv(dataset_dir / "train.csv", index=False) val_df.to_csv(dataset_dir / "val.csv", index=False) test_df.to_csv(dataset_dir / "test.csv", index=False) print(f"✅ Dataset split into: Train={len(X_train)}, Val={len(X_val)}, Test={len(X_test)}") return splits def get_dataset_info(self, dataset_id: str) -> Dict: """Get detailed information about a dataset. Args: dataset_id: Dataset identifier Returns: Dictionary with dataset information """ if dataset_id not in self.PUBLIC_DATASETS: raise ValueError(f"Unknown dataset: {dataset_id}") dataset = self.PUBLIC_DATASETS[dataset_id] dataset_dir = self.data_dir / dataset_id info = { 'id': dataset_id, 'name': dataset.name, 'description': dataset.description, 'citation': dataset.citation, 'features_available': dataset.features_available, 'labels_available': dataset.labels_available, 'subject_ids_available': dataset.subject_ids_available, 'video_available': dataset.video_available, 'audio_available': dataset.audio_available, 'downloaded': dataset_dir.exists() } if dataset_dir.exists(): # Count files files = list(dataset_dir.glob("*")) csv_files = list(dataset_dir.glob("*.csv")) info['local_path'] = str(dataset_dir) info['file_count'] = len(files) info['csv_files'] = [f.name for f in csv_files] # Try to load metadata metadata_path = dataset_dir / "metadata.json" if metadata_path.exists(): with open(metadata_path, 'r') as f: info['metadata'] = json.load(f) return info