Merge branch 'iblrigv8dev' into photometry

iblrig/online_plots.py

@@ -11,6 +11,7 @@
 from pandas.api.types import CategoricalDtype
 
 import one.alf.io
+import one.alf.path
 from iblrig.choiceworld import get_subject_training_info
 from iblrig.misc import online_std
 from iblrig.raw_data_loaders import load_task_jsonable
@@ -50,7 +51,7 @@ class DataModel:
     time_elapsed = 0.0
 
     def __init__(self, settings_file: Path | None):
-        self.session_path = one.alf.files.get_session_path(settings_file) or ''
+        self.session_path = one.alf.path.get_session_path(settings_file) or ''
         self.last_trials = pd.DataFrame(
             columns=['correct', 'signed_contrast', 'stim_on', 'play_tone', 'reward_time', 'error_time', 'response_time'],
             index=np.arange(NTRIALS_PLOT),

iblrig/raw_data_loaders.py

@@ -1,11 +1,14 @@
 import json
 import logging
+import re
 from pathlib import Path
 from typing import Any
 
 import pandas as pd
+from pandas.core.dtypes.concat import union_categoricals
 
 log = logging.getLogger(__name__)
+RE_PATTERN_EVENT = re.compile(r'^(\D+\d)_?(.+)$')
 
 
 def load_task_jsonable(jsonable_file: str | Path, offset: int | None = None) -> tuple[pd.DataFrame, list[Any]]:
@@ -37,3 +40,80 @@ def load_task_jsonable(jsonable_file: str | Path, offset: int | None = None) ->
 
     trials_table = pd.DataFrame(trials_table)
     return trials_table, bpod_data
+
+
+def bpod_session_events_to_dataframe(bpod_data: list[dict[str, Any]], trials: int | list[int] | slice | None = None):
+    """
+    Convert Bpod session data into a single Pandas DataFrame.
+
+    Parameters
+    ----------
+    bpod_data : list of dict
+        A list of dictionaries as returned by load_task_jsonable, where each dictionary contains data for a single trial.
+    trials : int, list of int, slice, or None, optional
+        Specifies which trials to include in the DataFrame. All trials are included by default.
+
+    Returns
+    -------
+    pd.DataFrame
+        A Pandas DataFrame containing combined event data from the specified trials, with columns for time, event, channel,
+        and value.
+    """
+    # define trial index
+    if trials is None:
+        trials = range(len(bpod_data))
+    elif isinstance(trials, int):
+        return _bpod_trial_events_to_dataframe(bpod_data[trials], trials)
+    elif isinstance(trials, slice):
+        trials = range(len(bpod_data))[trials]
+
+    # loop over requested trials
+    dataframes = []
+    for trial in trials:
+        dataframes.append(_bpod_trial_events_to_dataframe(bpod_data[trial], trial))
+
+    # combine trials into a single dataframe
+    categories_event = union_categoricals([df['Event'] for df in dataframes])
+    categories_channel = union_categoricals([df['Channel'] for df in dataframes])
+    for df in dataframes:
+        df['Event'] = df['Event'].cat.set_categories(categories_event.categories)
+        df['Channel'] = df['Channel'].cat.set_categories(categories_channel.categories)
+    return pd.concat(dataframes, ignore_index=True)
+
+
+def _bpod_trial_events_to_dataframe(bpod_trial_data: dict[str, Any], trial: int) -> pd.DataFrame:
+    """
+    Convert a single Bpod trial's data into a Pandas DataFrame.
+
+    Parameters
+    ----------
+    bpod_trial_data : dict
+        A dictionary containing data for a single trial, including timestamps and events.
+    trial : int
+        An integer representing the trial index.
+
+    Returns
+    -------
+    pd.DataFrame
+        A Pandas DataFrame containing the event data for the specified trial, with columns for time, event, channel, and value.
+    """
+    trial_start = bpod_trial_data['Trial start timestamp']
+    trial_end = bpod_trial_data['Trial end timestamp']
+
+    # convert bpod trial data to list of tuples, containing timestamps and event-names
+    event_list = [(time, event) for event, times in bpod_trial_data['Events timestamps'].items() for time in times]
+    event_list = [(0, 'TrialStart')] + sorted(event_list) + [(trial_end - trial_start, 'TrialEnd')]
+
+    # create dataframe
+    df = pd.DataFrame(data=event_list, columns=['Time', 'Event'])
+    df['Time'] = pd.to_timedelta(df['Time'] + trial_start, unit='seconds')
+    df['Event'] = df['Event'].astype('category')
+    df.insert(1, 'Trial', pd.to_numeric(pd.Series(trial, index=df.index), downcast='unsigned'))
+
+    # deduce channels and values from event names
+    df[['Channel', 'Value']] = df['Event'].str.extract(RE_PATTERN_EVENT, expand=True)
+    df['Channel'] = df['Channel'].astype('category')
+    df['Value'] = df['Value'].replace({'Low': 0, 'High': 1, 'Out': 0, 'In': 1})
+    df['Value'] = pd.to_numeric(df['Value'], errors='coerce', downcast='unsigned', dtype_backend='numpy_nullable')
+
+    return df