Merge branch 'nico-dev-2' of https://github.com/hertie-data-science-lab/tutorial-new-tutorial-group-1 into giorgio-dev

Author: giocopp

.DS_Store

@@ -153,4 +153,9 @@ dmypy.json
 cython_debug/
 data/
 
-.DS_Store
+.DS_Store
+
+# Exclude not needed notebooks files
+notebooks/exploration.ipynb
+notebooks/class_template.ipynb
+notebooks/few_shot_approaches_setup.ipynb

.gitignore

@@ -59,7 +59,7 @@ repos:
         #Automatic linting fixes
         types_or: [ python, pyi, jupyter ]
         args: [ --fix ]
-        stages: [manual]
+        #stages: [manual]
       - id: ruff-format
         types_or: [ python, pyi, jupyter ]
-        stages: [manual]
+        #stages: [manual]

.pre-commit-config.yaml

@@ -0,0 +1,59 @@
+import numpy as np
+from PIL import Image
+from pathlib import Path
+
+def extract_pv_masks(
+    src_dir: Path,
+    dst_dir: Path,
+    pv_class: int = 0,
+    background_value: int = 255
+):
+    """
+    Extract masks that contain PV modules (class 0) and save a cleaned PV-only mask.
+
+    Parameters
+    ----------
+    src_dir : Path
+        Directory containing original RID superstructure masks.
+    dst_dir : Path
+        Output directory for pv-only masks.
+    pv_class : int, optional
+        Class index representing PV modules (default: 0).
+    background_value : int, optional
+        Value used for non-PV pixels in the output mask (default: 255 for easy visualization).
+    """
+    dst_dir.mkdir(parents=True, exist_ok=True)
+
+    mask_files = list(src_dir.glob("*.png"))
+
+    print(f"Found {len(mask_files)} masks to inspect...")
+    count_saved = 0
+
+    for mask_path in mask_files:
+        mask = np.array(Image.open(mask_path))
+
+        # Check whether PV class exists
+        if pv_class not in np.unique(mask):
+            continue  # skip masks without PV
+
+        # Create PV-only mask
+        pv_mask = np.where(mask == pv_class, pv_class, background_value).astype(np.uint8)
+
+        # Save to new directory
+        out_path = dst_dir / mask_path.name
+        Image.fromarray(pv_mask).save(out_path)
+        count_saved += 1
+
+    print(f"Saved {count_saved} PV-only masks to: {dst_dir}")
+
+if __name__ == "__main__":
+    BASE_DIR = Path(__file__).resolve().parent
+    SRC_MASK_DIR = BASE_DIR / "masks_superstructures_reviewed"
+    DST_PV_MASK_DIR = BASE_DIR / "masks_pv_modules_only"
+
+    extract_pv_masks(
+        src_dir=SRC_MASK_DIR,
+        dst_dir=DST_PV_MASK_DIR,
+        pv_class=0,
+        background_value=255,   # white background for visualization
+    )

data/.DS_Store

@@ -0,0 +1,85 @@
+#!/usr/bin/env python3
+"""
+Minimal setup script for the RID dataset.
+
+Place this script in your `data/` directory and run:
+
+    python setup_rid_data_minimal.py
+
+It will:
+- rsync ONLY:
+    - images_roof_centered_geotiff
+    - masks_superstructures_reviewed
+  from the TUM server
+- download them directly into THIS folder (data/)
+- skip downloading if the folder already exists and is non-empty
+"""
+
+import subprocess
+from pathlib import Path
+
+SERVER = "rsync://m1655470@dataserv.ub.tum.de/m1655470"
+BASE_DIR = Path(__file__).resolve().parent     # data/
+DATA_DIR = BASE_DIR
+
+FOLDERS = [
+    "images_roof_centered_geotiff",
+    "masks_superstructures_reviewed",
+]
+
+
+def folder_has_data(path: Path) -> bool:
+    """Return True if folder exists and contains at least one file."""
+    return path.exists() and any(path.iterdir())
+
+
+def rsync_folder(remote_name: str):
+    """Rsync a single folder from the server into DATA_DIR."""
+    dst = DATA_DIR / remote_name
+
+    # Skip if already present and non-empty
+    if folder_has_data(dst):
+        print(f"✔ Skipping '{remote_name}' — folder already exists and is not empty.")
+        return
+
+    # Ensure directory exists
+    dst.mkdir(parents=True, exist_ok=True)
+
+    src = f"{SERVER}/{remote_name}/"
+    cmd = [
+        "rsync",
+        "-av",
+        "--progress",
+        src,
+        str(dst) + "/",     # ensure trailing slash
+    ]
+
+    print(f">>> Downloading '{remote_name}' from server...")
+    print("    ", " ".join(cmd))
+    print(">>> You may be asked for the password (m1655470).")
+
+    try:
+        subprocess.run(cmd, check=True)
+    except FileNotFoundError:
+        raise SystemExit("ERROR: rsync not found. Please install rsync and try again.")
+    except subprocess.CalledProcessError as e:
+        raise SystemExit(f"ERROR: rsync for {remote_name} failed with exit code {e.returncode}.")
+
+
+def main():
+    print("=== Minimal RID dataset setup (only 2 folders, with existence check) ===")
+    print(f"Data directory: {DATA_DIR}")
+    print()
+
+    for folder in FOLDERS:
+        rsync_folder(folder)
+        print()
+
+    print("=== Done! ===")
+    print("Folders now present:")
+    for folder in FOLDERS:
+        print(" •", DATA_DIR / folder)
+
+
+if __name__ == "__main__":
+    main()

data/generate_pv_masks.py

@@ -1440,7 +1440,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.14"
+   "version": "3.10.19"
   }
  },
  "nbformat": 4,