/usr/local/lib/python3.8/dist-packages/torch/distributed/launch.py:180: FutureWarning: The module torch.distributed.launch is deprecated
and will be removed in future. Use torchrun.
Note that --use_env is set by default in torchrun.
If your script expects `--local_rank` argument to be set, please
change it to read from `os.environ['LOCAL_RANK']` instead. See 
https://pytorch.org/docs/stable/distributed.html#launch-utility for 
further instructions

  warnings.warn(
WARNING:torch.distributed.run:
*****************************************
Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. 
*****************************************
/usr/local/lib/python3.8/dist-packages/merlin/dtypes/mappings/tf.py:52: UserWarning: Tensorflow dtype mappings did not load successfully due to an error: No module named 'tensorflow'
  warn(f"Tensorflow dtype mappings did not load successfully due to an error: {exc.msg}")
/usr/local/lib/python3.8/dist-packages/merlin/dtypes/mappings/tf.py:52: UserWarning: Tensorflow dtype mappings did not load successfully due to an error: No module named 'tensorflow'
  warn(f"Tensorflow dtype mappings did not load successfully due to an error: {exc.msg}")
Traceback (most recent call last):
  File "pyt_trainer.py", line 41, in <module>
    input_module = tr.TabularSequenceFeatures.from_schema(
  File "/usr/local/lib/python3.8/dist-packages/transformers4rec/torch/features/sequence.py", line 193, in from_schema
    output: TabularSequenceFeatures = super().from_schema(  # type: ignore
  File "/usr/local/lib/python3.8/dist-packages/transformers4rec/torch/features/tabular.py", line 176, in from_schema
    output = cls(
  File "/usr/local/lib/python3.8/dist-packages/transformers4rec/torch/features/sequence.py", line 127, in __init__
    super().__init__(
  File "/usr/local/lib/python3.8/dist-packages/transformers4rec/torch/features/tabular.py", line 84, in __init__
    assert to_merge != {}, "Please provide at least one input layer"
AssertionError: Please provide at least one input layer
Traceback (most recent call last):
  File "pyt_trainer.py", line 41, in <module>
    input_module = tr.TabularSequenceFeatures.from_schema(
  File "/usr/local/lib/python3.8/dist-packages/transformers4rec/torch/features/sequence.py", line 193, in from_schema
    output: TabularSequenceFeatures = super().from_schema(  # type: ignore
  File "/usr/local/lib/python3.8/dist-packages/transformers4rec/torch/features/tabular.py", line 176, in from_schema
    output = cls(
  File "/usr/local/lib/python3.8/dist-packages/transformers4rec/torch/features/sequence.py", line 127, in __init__
    super().__init__(
  File "/usr/local/lib/python3.8/dist-packages/transformers4rec/torch/features/tabular.py", line 84, in __init__
    assert to_merge != {}, "Please provide at least one input layer"
AssertionError: Please provide at least one input layer
ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: 1) local_rank: 0 (pid: 23905) of binary: /usr/bin/python
Traceback (most recent call last):
  File "/usr/lib/python3.8/runpy.py", line 194, in _run_module_as_main
    return _run_code(code, main_globals, None,
  File "/usr/lib/python3.8/runpy.py", line 87, in _run_code
    exec(code, run_globals)
  File "/usr/local/lib/python3.8/dist-packages/torch/distributed/launch.py", line 195, in <module>
    main()
  File "/usr/local/lib/python3.8/dist-packages/torch/distributed/launch.py", line 191, in main
    launch(args)
  File "/usr/local/lib/python3.8/dist-packages/torch/distributed/launch.py", line 176, in launch
    run(args)
  File "/usr/local/lib/python3.8/dist-packages/torch/distributed/run.py", line 753, in run
    elastic_launch(
  File "/usr/local/lib/python3.8/dist-packages/torch/distributed/launcher/api.py", line 132, in __call__
    return launch_agent(self._config, self._entrypoint, list(args))
  File "/usr/local/lib/python3.8/dist-packages/torch/distributed/launcher/api.py", line 246, in launch_agent
    raise ChildFailedError(
torch.distributed.elastic.multiprocessing.errors.ChildFailedError: 
============================================================
pyt_trainer.py FAILED
------------------------------------------------------------
Failures:
[1]:
  time      : 2023-03-16_19:30:24
  host      : 1902e905751e
  rank      : 1 (local_rank: 1)
  exitcode  : 1 (pid: 23906)
  error_file: <N/A>
  traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
------------------------------------------------------------
Root Cause (first observed failure):
[0]:
  time      : 2023-03-16_19:30:24
  host      : 1902e905751e
  rank      : 0 (local_rank: 0)
  exitcode  : 1 (pid: 23905)
  error_file: <N/A>
  traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html

import calendar
import datetime

import numpy as np
import pandas as pd


def generate_synthetic_data(
    start_date: datetime.date, end_date: datetime.date, rows_per_day: int = 1000
) -> pd.DataFrame:
    assert end_date > start_date, "end_date must be later than start_date"

    number_of_days = (end_date - start_date).days
    total_number_of_rows = number_of_days * rows_per_day

    # Generate a long-tail distribution of item interactions. This simulates that some items are
    # more popular than others.
    long_tailed_item_distribution = np.clip(
        np.random.lognormal(3.0, 1.0, total_number_of_rows).astype(np.int64), 1, 50000
    )

    # generate random item interaction features
    df = pd.DataFrame(
        {
            "session_id": np.random.randint(70000, 80000, total_number_of_rows),
            "item_id": long_tailed_item_distribution,
        },
    )

    # generate category mapping for each item-id
    df["category"] = pd.cut(df["item_id"], bins=334, labels=np.arange(1, 335)).astype(
        np.int64
    )

    max_session_length = 60 * 60  # 1 hour

    def add_timestamp_to_session(session: pd.DataFrame):
        random_start_date_and_time = calendar.timegm(
            (
                start_date
                # Add day offset from start_date
                + datetime.timedelta(days=np.random.randint(0, number_of_days))
                # Add time offset within the random day
                + datetime.timedelta(seconds=np.random.randint(0, 86_400))
            ).timetuple()
        )
        session["timestamp"] = random_start_date_and_time + np.clip(
            np.random.lognormal(3.0, 1.0, len(session)).astype(np.int64),
            0,
            max_session_length,
        )
        return session

    df = df.groupby("session_id").apply(add_timestamp_to_session).reset_index()

    return df

interactions_df = generate_synthetic_data(datetime.date(2014, 4, 1), datetime.date(2014, 6, 30))
interactions_df = cudf.from_pandas(interactions_df)