import os

# Directories
DATA_DIR = "data"
IMAGE_DIR = os.path.join(DATA_DIR, "core_images")
MODEL_DIR = "models"
OUTPUT_DIR = "output"

# Create directories if they don't exist
os.makedirs(IMAGE_DIR, exist_ok=True)
os.makedirs(MODEL_DIR, exist_ok=True)
os.makedirs(OUTPUT_DIR, exist_ok=True)

# Model parameters - adaptive to data size
NUM_CLUSTERS = 3  # Reduced default
IMAGE_SIZE = (224, 224)
BATCH_SIZE = 32

# Candidate labels for classification
CANDIDATE_LABELS = [
    "gold-bearing rock",
    "iron-rich rock",
    "lithium-rich rock",
    "copper-bearing rock",
    "waste rock",
    "quartz-rich rock",
    "sulfide-rich rock"
]

# Public geology repositories
DATASET_SOURCES = [
    {
        "name": "Geoscience Australia",
        "url": "https://geology.csiro.au/datasets/drill-core-images",
        "description": "Australian geological survey drill core images"
    },
    {
        "name": "USGS Mineral Resources",
        "url": "https://mrdata.usgs.gov/geology/state/map-viewer.php",
        "description": "US Geological Survey mineral resources data"
    },
    {
        "name": "BGS OpenGeoscience",
        "url": "https://www.bgs.ac.uk/discovering-geology/rock-library/",
        "description": "British Geological Survey rock sample images"
    }
]