Remove hardcoded /home/gg paths so the project is portable

Notebooks now use Path.home() / "cupido" for the repo root (works for
any user inside the JupyterLab container), and the offline-tracking
scripts read the ethoscope source-tree location from the new
ETHOSCOPE_SRC config constant — defaulting to ~/Code/ethoscope_project/...
and overridable via the ETHOSCOPE_SRC environment variable.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

README.md

@@ -53,7 +53,7 @@ is split in two stages so you can sit at the screen and click for an hour, then
 let the tracker grind through overnight.
 
 ```bash
-# extra deps (ethoscope src must be at /home/gg/Code/ethoscope_project/...)
+# extra deps (set ETHOSCOPE_SRC env var if your ethoscope clone isn't at ~/Code/ethoscope_project/...)
 pip install -r requirements-tracking.txt
 
 # 1) build the inventory (xlsx ↔ /mnt/ethoscope_data/videos/)

notebooks/flies_analysis.ipynb

@@ -14,7 +14,7 @@
    "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": "import sys\nfrom pathlib import Path\n\nimport pandas as pd\nimport numpy as np\nimport sqlite3\nimport glob\nimport re\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nfrom scipy.spatial.distance import euclidean\nfrom scipy import stats\n\n# Two locations to know about:\n#   - DATA_DIR  : where the project's bulky data lives (data volume)\n#   - REPO_ROOT : where the code repository lives (this notebook is inside it)\nDATA_DIR  = Path(\"/mnt/data/projects/cupido\")\nREPO_ROOT = Path(\"/home/gg/ownCloud/Work/Projects/coding/cupido/tracking\")\n\n# Pull every other path constant from scripts/config.py so this notebook\n# stays in sync with the rest of the codebase. (Reason: avoids drift when\n# paths change — config.py is the single source of truth.)\nsys.path.insert(0, str(REPO_ROOT / \"scripts\"))\nfrom config import DATA_RAW, DATA_METADATA, DATA_PROCESSED, FIGURES\n\n# Plotting style\nplt.style.use('seaborn-v0_8')\nsns.set_palette(\"husl\")\n"
+   "source": "import sys\nfrom pathlib import Path\n\nimport pandas as pd\nimport numpy as np\nimport sqlite3\nimport glob\nimport re\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nfrom scipy.spatial.distance import euclidean\nfrom scipy import stats\n\n# Two locations to know about:\n#   - DATA_DIR  : where the project's bulky data lives (mounted into the container)\n#   - REPO_ROOT : where the code repository is checked out (your home directory)\n# Path.home() expands to the current user's home, so this works for any\n# user running the container (no hard-coded usernames).\nDATA_DIR  = Path(\"/mnt/data/projects/cupido\")\nREPO_ROOT = Path.home() / \"cupido\"\n\n# Pull every other path constant from scripts/config.py so this notebook\n# stays in sync with the rest of the codebase. (Reason: avoids drift when\n# paths change — config.py is the single source of truth.)\nsys.path.insert(0, str(REPO_ROOT / \"scripts\"))\nfrom config import DATA_RAW, DATA_METADATA, DATA_PROCESSED, FIGURES\n\n# Plotting style\nplt.style.use('seaborn-v0_8')\nsns.set_palette(\"husl\")\n"
   },
   {
    "cell_type": "markdown",

notebooks/flies_analysis_simple.ipynb

@@ -14,7 +14,7 @@
    "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": "import sys\nfrom pathlib import Path\n\nimport pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nfrom scipy.spatial.distance import euclidean\nfrom scipy import stats\n\n# Two locations to know about:\n#   - DATA_DIR  : where the project's bulky data lives (data volume)\n#   - REPO_ROOT : where the code repository lives (this notebook is inside it)\nDATA_DIR  = Path(\"/mnt/data/projects/cupido\")\nREPO_ROOT = Path(\"/home/gg/ownCloud/Work/Projects/coding/cupido/tracking\")\n\n# Pull every other path constant from scripts/config.py so this notebook\n# stays in sync with the rest of the codebase. (Reason: avoids drift when\n# paths change — config.py is the single source of truth.)\nsys.path.insert(0, str(REPO_ROOT / \"scripts\"))\nfrom config import DATA_RAW, DATA_METADATA, DATA_PROCESSED, FIGURES\n\n# Plotting style\nplt.style.use('seaborn-v0_8')\nsns.set_palette(\"husl\")\n\nprint(f\"Data directory: {DATA_DIR}\")\nprint(f\"Repo root:      {REPO_ROOT}\")\nprint(f\"Pandas version: {pd.__version__}\")\nprint(f\"NumPy version:  {np.__version__}\")\n"
+   "source": "import sys\nfrom pathlib import Path\n\nimport pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nfrom scipy.spatial.distance import euclidean\nfrom scipy import stats\n\n# Two locations to know about:\n#   - DATA_DIR  : where the project's bulky data lives (mounted into the container)\n#   - REPO_ROOT : where the code repository is checked out (your home directory)\n# Path.home() expands to the current user's home, so this works for any\n# user running the container (no hard-coded usernames).\nDATA_DIR  = Path(\"/mnt/data/projects/cupido\")\nREPO_ROOT = Path.home() / \"cupido\"\n\n# Pull every other path constant from scripts/config.py so this notebook\n# stays in sync with the rest of the codebase. (Reason: avoids drift when\n# paths change — config.py is the single source of truth.)\nsys.path.insert(0, str(REPO_ROOT / \"scripts\"))\nfrom config import DATA_RAW, DATA_METADATA, DATA_PROCESSED, FIGURES\n\n# Plotting style\nplt.style.use('seaborn-v0_8')\nsns.set_palette(\"husl\")\n\nprint(f\"Data directory: {DATA_DIR}\")\nprint(f\"Repo root:      {REPO_ROOT}\")\nprint(f\"Pandas version: {pd.__version__}\")\nprint(f\"NumPy version:  {np.__version__}\")\n"
   },
   {
    "cell_type": "markdown",

notebooks/getting_started/00_welcome.ipynb

@@ -149,14 +149,14 @@
   {
    "cell_type": "markdown",
    "metadata": {},
-   "source": "## Where everything lives\n\nTake a moment to memorize these locations — you'll come back to them often.\n\n| what | where |\n|---|---|\n| Tracking DBs (SQLite, one per video) | `/mnt/data/projects/cupido/tracked/` |\n| Target JSONs (the user-clicked reference points) | `/mnt/data/projects/cupido/targets/` |\n| The metadata table (xlsx + TSV) | `/mnt/data/projects/cupido/all_video_info_merged.tsv` |\n| Source video files | `/mnt/ethoscope_data/videos/` |\n| Project code (this repo) | `/home/gg/ownCloud/Work/Projects/coding/cupido/tracking/` |\n| Your notebooks | `notebooks/getting_started/` (this folder) |\n\nNotice the pattern: **everything bulky or regenerable lives under\n`/mnt/data/projects/cupido/`**. The repository itself only stores code,\ndocumentation, and small metadata files. We'll refer to that data\ndirectory as `DATA_DIR` from here on.\n\nLet's verify a couple of these from inside Python:\n"
+   "source": "## Where everything lives\n\nTake a moment to memorize these locations — you'll come back to them often.\n\n| what | where |\n|---|---|\n| Tracking DBs (SQLite, one per video) | `/mnt/data/projects/cupido/tracked/` |\n| Target JSONs (the user-clicked reference points) | `/mnt/data/projects/cupido/targets/` |\n| The metadata table (xlsx + TSV) | `/mnt/data/projects/cupido/all_video_info_merged.tsv` |\n| Source video files | `/mnt/ethoscope_data/videos/` |\n| Project code (this repo) | `~/cupido/` (your home directory inside the container) |\n| Your notebooks | `~/cupido/notebooks/getting_started/` (this folder) |\n\nNotice the pattern: **everything bulky or regenerable lives under\n`/mnt/data/projects/cupido/`**. The repository itself, with all the\ncode and notebooks, is checked out into your home directory inside the\nJupyterLab container — that's `~/cupido`, where `~` is shorthand for\nyour home directory (`/home/<your-username>`).\n\nWe'll refer to those two roots as `DATA_DIR` and `REPO_ROOT` from here on.\n\nLet's verify a couple of these from inside Python:\n"
   },
   {
    "cell_type": "code",
    "metadata": {},
    "execution_count": null,
    "outputs": [],
-   "source": "from pathlib import Path\n\n# Single root for all the bulky / regenerable project data.\nDATA_DIR = Path(\"/mnt/data/projects/cupido\")\n\ntracked_dir = DATA_DIR / \"tracked\"\ntargets_dir = DATA_DIR / \"targets\"\nmetadata_tsv = DATA_DIR / \"all_video_info_merged.tsv\"\n\nprint(f\"Tracking DBs available: {len(list(tracked_dir.glob('*_tracking.db')))}\")\nprint(f\"Target JSONs available: {len(list(targets_dir.glob('*.json')))}\")\nprint(f\"Metadata TSV exists:    {metadata_tsv.exists()}\")\n"
+   "source": "from pathlib import Path\n\n# The two roots we keep coming back to.\nDATA_DIR  = Path(\"/mnt/data/projects/cupido\")  # bulky data, mounted into the container\nREPO_ROOT = Path.home() / \"cupido\"             # the code repo in your home dir\n\ntracked_dir  = DATA_DIR / \"tracked\"\ntargets_dir  = DATA_DIR / \"targets\"\nmetadata_tsv = DATA_DIR / \"all_video_info_merged.tsv\"\n\nprint(f\"Repo root:              {REPO_ROOT}  (exists={REPO_ROOT.exists()})\")\nprint(f\"Tracking DBs available: {len(list(tracked_dir.glob('*_tracking.db')))}\")\nprint(f\"Target JSONs available: {len(list(targets_dir.glob('*.json')))}\")\nprint(f\"Metadata TSV exists:    {metadata_tsv.exists()}\")\n"
   },
   {
    "cell_type": "markdown",

notebooks/getting_started/03_compare_trained_vs_naive.ipynb

@@ -48,7 +48,7 @@
    "metadata": {},
    "execution_count": null,
    "outputs": [],
-   "source": "import sys\nfrom pathlib import Path\n\nimport numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\nfrom scipy import stats\n\n# Two locations to know about:\n#   - DATA_DIR  : where the project's data files live (read-only data volume)\n#   - REPO_ROOT : where the code repository lives (this notebook is inside it)\n# We build both as Path objects, then derive everything else from them.\nDATA_DIR  = Path(\"/mnt/data/projects/cupido\")\nREPO_ROOT = Path(\"/home/gg/ownCloud/Work/Projects/coding/cupido/tracking\")\n\n# Tell Python where to find the project's helper modules (in scripts/).\nsys.path.insert(0, str(REPO_ROOT / \"scripts\"))\n\nfrom load_roi_data import load_roi_data\n"
+   "source": "import sys\nfrom pathlib import Path\n\nimport numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\nfrom scipy import stats\n\n# Two locations to know about:\n#   - DATA_DIR  : where the project's data files live (mounted into the container)\n#   - REPO_ROOT : where the code repository is checked out (your home directory)\n# Path.home() expands to the current user's home directory, so this\n# works for any user running the container — no hard-coded usernames.\nDATA_DIR  = Path(\"/mnt/data/projects/cupido\")\nREPO_ROOT = Path.home() / \"cupido\"\n\n# Tell Python where to find the project's helper modules (in scripts/).\nsys.path.insert(0, str(REPO_ROOT / \"scripts\"))\n\nfrom load_roi_data import load_roi_data\n"
   },
   {
    "cell_type": "markdown",

scripts/auto_detect_targets.py

@@ -24,10 +24,10 @@ import cv2
 import numpy as np
 import pandas as pd
 
-# ethoscope source tree
-sys.path.insert(0, "/home/gg/Code/ethoscope_project/ethoscope/src/ethoscope")
+from config import ETHOSCOPE_SRC, INVENTORY_CSV, TARGETS_DIR
 
-from config import INVENTORY_CSV, TARGETS_DIR  # noqa: E402
+# ethoscope source tree
+sys.path.insert(0, str(ETHOSCOPE_SRC))
 
 from ethoscope.roi_builders.target_roi_builder import TargetGridROIBuilder  # noqa: E402
 

scripts/config.py

@@ -1,5 +1,6 @@
 """Shared path constants for the Cupido tracking project."""
 
+import os
 from pathlib import Path
 
 # Where this code repository lives (the directory containing scripts/, notebooks/, ...).
@@ -13,9 +14,9 @@ LOGS_DIR = PROJECT_ROOT / "data" / "logs"
 # Where the source videos live (read-only NFS mount).
 VIDEOS_ROOT = Path("/mnt/ethoscope_data/videos")
 
-# Where the project's bulky data lives — outside the ownCloud-synced repo so
-# it doesn't churn the cloud sync. This single root holds everything that's
-# big or regenerable: tracking DBs, target-point JSONs, and the metadata
+# Where the project's bulky data lives — outside the cloud-synced repo so
+# it doesn't churn the sync. This single root holds everything that's big
+# or regenerable: tracking DBs, target-point JSONs, and the metadata
 # spreadsheet (xlsx + TSV).
 DATA_VOLUME = Path("/mnt/data/projects/cupido")
 TARGETS_DIR = DATA_VOLUME / "targets"
@@ -25,3 +26,13 @@ VIDEO_INFO_TSV = DATA_VOLUME / "all_video_info_merged.tsv"
 
 # A small CSV listing every video file we know about (built locally).
 INVENTORY_CSV = DATA_METADATA / "video_inventory.csv"
+
+# Where the ethoscope source tree is checked out (used by track_videos.py
+# and auto_detect_targets.py — host-side scripts that import ethoscope
+# from a local clone rather than from pip). Default assumes the standard
+# layout `~/Code/ethoscope_project/ethoscope/src/ethoscope`; override with
+# the ETHOSCOPE_SRC environment variable if your clone lives elsewhere.
+ETHOSCOPE_SRC = Path(os.environ.get(
+    "ETHOSCOPE_SRC",
+    str(Path.home() / "Code" / "ethoscope_project" / "ethoscope" / "src" / "ethoscope"),
+))

scripts/track_videos.py

@@ -27,11 +27,11 @@ from pathlib import Path
 
 import numpy as np
 
+from config import ETHOSCOPE_SRC, TARGETS_DIR, TRACKING_OUTPUT_DIR
+
 # Import ethoscope from the local source tree (no pip install).
-ETHOSCOPE_SRC = Path("/home/gg/Code/ethoscope_project/ethoscope/src/ethoscope")
 sys.path.insert(0, str(ETHOSCOPE_SRC))
 
-from config import TARGETS_DIR, TRACKING_OUTPUT_DIR  # noqa: E402
 from tracking_geometry import HD_FG_DATA, compute_roi_polygons  # noqa: E402