[BUG] Loading of some internal datasets fails

[egoriyaa]

🐛 Bug Report

Can't load following internal datasets:

traffic_2008_10T
traffic_2008_hourly

Expected behavior

Datasets are loading correctly

How To Reproduce

Code

from etna.datasets import load_dataset

load_dataset("traffic_2008_hourly", rebuild_dataset=True)

Environment

No response

Additional context

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
Cell In[85], line 3
      1 from etna.datasets import load_dataset
----> 3 load_dataset("traffic_2008_hourly", rebuild_dataset=True)

File ~/etna/etna/datasets/internal_datasets.py:159, in load_dataset(name, download_path, rebuild_dataset, parts)
    156 freq = dataset_params["freq"]
    158 if not _check_dataset_local(dataset_path) or rebuild_dataset:
--> 159     get_dataset_function(dataset_dir)
    160 ts_out = []
    161 for part in parts_:

File ~/etna/etna/datasets/internal_datasets.py:363, in get_traffic_2008_dataset(dataset_dir, dataset_freq)
    360 dates_df = dates_df.drop(["dt"], axis=1)
    362 df = pd.DataFrame(targets, columns=stations)
--> 363 df["timestamp"] = dates_df_cropped["timestamp"].values
    364 df = df.merge(dates_df, on=["timestamp"], how="right").fillna(0)
    365 df = df.melt("timestamp", var_name="segment", value_name="target")

File ~/Library/Caches/pypoetry/virtualenvs/etna-yJQui467-py3.8/lib/python3.8/site-packages/pandas/core/frame.py:3980, in DataFrame.__setitem__(self, key, value)
   3977     self._setitem_array([key], value)
   3978 else:
   3979     # set column
-> 3980     self._set_item(key, value)

File ~/Library/Caches/pypoetry/virtualenvs/etna-yJQui467-py3.8/lib/python3.8/site-packages/pandas/core/frame.py:4174, in DataFrame._set_item(self, key, value)
   4164 def _set_item(self, key, value) -> None:
   4165     """
   4166     Add series to DataFrame in specified column.
   4167 
   (...)
   4172     ensure homogeneity.
   4173     """
-> 4174     value = self._sanitize_column(value)
   4176     if (
   4177         key in self.columns
   4178         and value.ndim == 1
   4179         and not is_extension_array_dtype(value)
   4180     ):
   4181         # broadcast across multiple columns if necessary
   4182         if not self.columns.is_unique or isinstance(self.columns, MultiIndex):

File ~/Library/Caches/pypoetry/virtualenvs/etna-yJQui467-py3.8/lib/python3.8/site-packages/pandas/core/frame.py:4915, in DataFrame._sanitize_column(self, value)
   4912     return _reindex_for_setitem(Series(value), self.index)
   4914 if is_list_like(value):
-> 4915     com.require_length_match(value, self.index)
   4916 return sanitize_array(value, self.index, copy=True, allow_2d=True)

File ~/Library/Caches/pypoetry/virtualenvs/etna-yJQui467-py3.8/lib/python3.8/site-packages/pandas/core/common.py:571, in require_length_match(data, index)
    567 """
    568 Check the length of data matches the length of the index.
    569 """
    570 if len(data) != len(index):
--> 571     raise ValueError(
    572         "Length of values "
    573         f"({len(data)}) "
    574         "does not match length of index "
    575         f"({len(index)})"
    576     )

ValueError: Length of values (63648) does not match length of index (63360)

Checklist

• [X] Bug appears at the latest library version