Unify analysis pipeline around the TSV; move tracked DBs out of cloud sync

- Tracked DBs now live at /mnt/data/projects/cupido/tracked/ (out of
  ownCloud to avoid sync conflicts and bandwidth churn). config.py
  TRACKING_OUTPUT_DIR points there; the docker-compose for ethoscope-lab
  mounts it world-readable for JupyterHub users.
- New scripts/export_video_db_index.py joins all_video_info_merged.xlsx
  with the video inventory and the on-disk DBs, producing a TSV that has
  one row per fly/ROI plus training/testing video and DB paths. Handles
  approximate xlsx times, cross-day training/testing, the 12 AM/PM
  ambiguity, and date typos.
- scripts/load_roi_data.py rewritten as a TSV-driven loader returning a
  single DataFrame with session and metadata columns. calculate_distances
  and the two flies_analysis notebooks migrated to use it; downstream
  trained/naive splits remain available via simple equality filters.
- Metadata vocabulary canonicalized: {naïve, niave, untrained, test} all
  resolve to {trained, naive}. Normalization happens at the TSV-export
  boundary (idempotent); the xlsx and the 2025-07-15 legacy CSV were
  edited in place to remove the worst variants.
- scripts/monitor_tracking.py rate calculation fixed: with N parallel
  workers, completions arrive in bursts; the old formula divided by burst
  width and reported nonsense rates. Now uses a 6 h window denominator.
- scripts/track_videos.py: BGRMovieCamera retries cv2.read on transient
  NFS hiccups and a post-tracking completeness gate (≥ 90 % of expected
  duration via MAX(t) across all 6 ROIs) deletes silent partial DBs.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
Giorgio Gilestro 2026-04-30 15:20:14 +01:00
parent e4da7691d5
commit f60a9d0530
13 changed files with 569 additions and 237 deletions

View file

@ -1,117 +1,99 @@
import pandas as pd
"""Compute per-frame inter-fly distances for every (date, machine, ROI, session).
Reads tracking data via :func:`load_roi_data.load_roi_data` (which is driven
by ``all_video_info_merged.tsv``) and produces one distances DataFrame
spanning every fly/session in the batch. Group membership (``trained`` /
``untrained``) is preserved from the ``male`` column.
"""
import numpy as np
import pandas as pd
from scipy.spatial.distance import euclidean
from config import DATA_PROCESSED
from load_roi_data import load_roi_data
def calculate_fly_distances(trained_file=None, untrained_file=None):
"""Calculate distances between flies at each time point.
def calculate_fly_distances(data: pd.DataFrame | None = None) -> pd.DataFrame:
"""Compute inter-fly distances over time for every fly/session.
For each time point:
- If two flies are detected: calculate Cartesian distance between them
- If one fly is detected: set distance to 0 if area > average area, otherwise NaN
For each time point inside one (date, machine, ROI, session) trajectory:
- 2+ flies detected: Euclidean distance between the first two by id
- 1 fly detected: distance = 0 if its bbox area exceeds the global
mean (likely a single blob containing both flies), else NaN
Args:
trained_file (Path): Path to trained ROI data CSV.
untrained_file (Path): Path to untrained ROI data CSV.
data: optional pre-loaded DataFrame from :func:`load_roi_data`. If
None, the full batch is loaded.
Returns:
tuple: (trained_distances, untrained_distances) DataFrames.
DataFrame with one row per (track, time) pair, including ``distance``,
``n_flies``, ``area_fly1``, ``area_fly2``, plus the metadata columns
propagated from the source row (``date``, ``machine_name``, ``ROI``,
``session``, ``male``, ``species``, ``memory``, ``age``).
"""
if trained_file is None:
trained_file = DATA_PROCESSED / 'trained_roi_data.csv'
if untrained_file is None:
untrained_file = DATA_PROCESSED / 'untrained_roi_data.csv'
if data is None:
data = load_roi_data()
if data.empty:
return pd.DataFrame()
trained_df = pd.read_csv(trained_file)
untrained_df = pd.read_csv(untrained_file)
trained_df['area'] = trained_df['w'] * trained_df['h']
untrained_df['area'] = untrained_df['w'] * untrained_df['h']
avg_area = np.mean([trained_df['area'].mean(), untrained_df['area'].mean()])
data = data.copy()
data["area"] = data["w"] * data["h"]
avg_area = data["area"].mean()
print(f"Average area across all data: {avg_area:.2f}")
trained_distances = process_distance_data(trained_df, avg_area)
untrained_distances = process_distance_data(untrained_df, avg_area)
# Carry these onto every output row (constant within a track).
keep_meta = ["date", "machine_name", "ROI", "session", "male",
"species", "memory", "age"]
return trained_distances, untrained_distances
def process_distance_data(df, avg_area):
"""Process a DataFrame to calculate distances between flies at each time point.
Args:
df (pd.DataFrame): Input tracking data.
avg_area (float): Average area threshold for single-fly detection.
Returns:
pd.DataFrame: Distance data with columns for machine, ROI, time, distance.
"""
results = []
for (machine_name, roi), group in df.groupby(['machine_name', 'ROI']):
for t, time_group in group.groupby('t'):
time_group = time_group.sort_values('id').reset_index(drop=True)
rows: list[dict] = []
track_keys = ["date", "machine_name", "ROI", "session"]
for track, track_df in data.groupby(track_keys, sort=False):
meta_row = {k: v for k, v in zip(track_keys, track)}
# Carry the rest of the metadata from any sample (constant per track).
sample = track_df.iloc[0]
for col in keep_meta:
if col not in meta_row:
meta_row[col] = sample[col]
for t, time_group in track_df.groupby("t", sort=False):
time_group = time_group.sort_values("id").reset_index(drop=True)
row = dict(meta_row)
row["t"] = t
if len(time_group) >= 2:
fly1 = time_group.iloc[0]
fly2 = time_group.iloc[1]
distance = euclidean([fly1['x'], fly1['y']], [fly2['x'], fly2['y']])
f1, f2 = time_group.iloc[0], time_group.iloc[1]
row["distance"] = euclidean([f1["x"], f1["y"]], [f2["x"], f2["y"]])
row["n_flies"] = len(time_group)
row["area_fly1"] = f1["area"]
row["area_fly2"] = f2["area"]
else:
f = time_group.iloc[0]
row["distance"] = 0.0 if f["area"] > avg_area else np.nan
row["n_flies"] = 1
row["area_fly1"] = f["area"]
row["area_fly2"] = np.nan
rows.append(row)
results.append({
'machine_name': machine_name,
'ROI': roi,
't': t,
'distance': distance,
'n_flies': len(time_group),
'area_fly1': fly1['area'],
'area_fly2': fly2['area']
})
elif len(time_group) == 1:
fly = time_group.iloc[0]
area = fly['area']
if area > avg_area:
distance = 0.0
else:
distance = np.nan
results.append({
'machine_name': machine_name,
'ROI': roi,
't': t,
'distance': distance,
'n_flies': 1,
'area_fly1': area,
'area_fly2': np.nan
})
return pd.DataFrame(results)
return pd.DataFrame(rows)
def main():
"""Run distance calculations and save results."""
trained_distances, untrained_distances = calculate_fly_distances()
def main() -> None:
distances = calculate_fly_distances()
print(f"Trained data distance summary:")
print(f" Shape: {trained_distances.shape}")
print(f" Distance stats:")
print(f" Count: {trained_distances['distance'].count()}")
print(f" Mean: {trained_distances['distance'].mean():.2f}")
print(f" Std: {trained_distances['distance'].std():.2f}")
print("\nDistance summary:")
print(f" Shape: {distances.shape}")
if not distances.empty:
print(f" Distance count: {distances['distance'].count()}")
print(f" Distance mean: {distances['distance'].mean():.2f}")
print(f" Distance std: {distances['distance'].std():.2f}")
male = distances["male"]
print(f" Trained tracks: {(male == 'trained').sum()}")
print(f" Naive tracks: {(male == 'naive').sum()}")
print(f"\nUntrained data distance summary:")
print(f" Shape: {untrained_distances.shape}")
print(f" Distance stats:")
print(f" Count: {untrained_distances['distance'].count()}")
print(f" Mean: {untrained_distances['distance'].mean():.2f}")
print(f" Std: {untrained_distances['distance'].std():.2f}")
trained_distances.to_csv(DATA_PROCESSED / 'trained_distances.csv', index=False)
untrained_distances.to_csv(DATA_PROCESSED / 'untrained_distances.csv', index=False)
print("\nDistance data saved")
DATA_PROCESSED.mkdir(parents=True, exist_ok=True)
out = DATA_PROCESSED / "distances.csv"
distances.to_csv(out, index=False)
print(f"\nSaved {out}")
if __name__ == "__main__":