Move calculate_episode_data_index

lerobot/common/datasets/utils.py

@@ -18,7 +18,7 @@ import warnings
 from itertools import accumulate
 from pathlib import Path
 from pprint import pformat
-from typing import Any, Dict
+from typing import Any
 
 import datasets
 import jsonlines
@@ -368,61 +368,6 @@ def get_delta_indices(delta_timestamps: dict[str, list[float]], fps: int) -> dic
     return delta_indices
 
 
-# TODO(aliberts): remove
-def calculate_episode_data_index(hf_dataset: datasets.Dataset) -> Dict[str, torch.Tensor]:
-    """
-    Calculate episode data index for the provided HuggingFace Dataset. Relies on episode_index column of hf_dataset.
-
-    Parameters:
-    - hf_dataset (datasets.Dataset): A HuggingFace dataset containing the episode index.
-
-    Returns:
-    - episode_data_index: A dictionary containing the data index for each episode. The dictionary has two keys:
-        - "from": A tensor containing the starting index of each episode.
-        - "to": A tensor containing the ending index of each episode.
-    """
-    episode_data_index = {"from": [], "to": []}
-
-    current_episode = None
-    """
-    The episode_index is a list of integers, each representing the episode index of the corresponding example.
-    For instance, the following is a valid episode_index:
-      [0, 0, 0, 1, 1, 1, 1, 2, 2, 2, 2, 2]
-
-    Below, we iterate through the episode_index and populate the episode_data_index dictionary with the starting and
-    ending index of each episode. For the episode_index above, the episode_data_index dictionary will look like this:
-        {
-            "from": [0, 3, 7],
-            "to": [3, 7, 12]
-        }
-    """
-    if len(hf_dataset) == 0:
-        episode_data_index = {
-            "from": torch.tensor([]),
-            "to": torch.tensor([]),
-        }
-        return episode_data_index
-    for idx, episode_idx in enumerate(hf_dataset["episode_index"]):
-        if episode_idx != current_episode:
-            # We encountered a new episode, so we append its starting location to the "from" list
-            episode_data_index["from"].append(idx)
-            # If this is not the first episode, we append the ending location of the previous episode to the "to" list
-            if current_episode is not None:
-                episode_data_index["to"].append(idx)
-            # Let's keep track of the current episode index
-            current_episode = episode_idx
-        else:
-            # We are still in the same episode, so there is nothing for us to do here
-            pass
-    # We have reached the end of the dataset, so we append the ending location of the last episode to the "to" list
-    episode_data_index["to"].append(idx + 1)
-
-    for k in ["from", "to"]:
-        episode_data_index[k] = torch.tensor(episode_data_index[k])
-
-    return episode_data_index
-
-
 def cycle(iterable):
     """The equivalent of itertools.cycle, but safe for Pytorch dataloaders.