miguelgfierro
commented
10 months ago Weird error. The input is 100k, but the regex parser inputs 10k
tests/functional/examples/test_notebooks_gpu.py F [100%]
================================================================================= FAILURES ==================================================================================
______________________________________________________ test_ncf_deep_dive_functional[100k-10-512-expected_values0-42] _______________________________________________________
notebooks = {'als_deep_dive': '/home/u/MS/recommenders/examples/02_model_collaborative_filtering/als_deep_dive.ipynb', 'als_pyspar...aseline_deep_dive.ipynb', 'benchmark_movielens': '/home/u/MS/recommenders/examples/06_benchmarks/movielens.ipynb', ...}
output_notebook = 'output.ipynb', kernel_name = 'python3', size = '100k', epochs = 10, batch_size = 512
expected_values = {'map': 0.0435856, 'map2': 0.0510391, 'ndcg': 0.37586, 'ndcg2': 0.202186, ...}, seed = 42
@pytest.mark.gpu
@pytest.mark.notebooks
@pytest.mark.parametrize(
"size, epochs, batch_size, expected_values, seed",
[
(
"100k",
10,
512,
{
"map": 0.0435856,
"ndcg": 0.37586,
"precision": 0.169353,
"recall": 0.0923963,
"map2": 0.0510391,
"ndcg2": 0.202186,
"precision2": 0.179533,
"recall2": 0.106434,
},
42,
)
],
)
def test_ncf_deep_dive_functional(
notebooks,
output_notebook,
kernel_name,
size,
epochs,
batch_size,
expected_values,
seed,
):
notebook_path = notebooks["ncf_deep_dive"]
> execute_notebook(
notebook_path,
output_notebook,
kernel_name=kernel_name,
parameters=dict(
TOP_K=10,
MOVIELENS_DATA_SIZE=size,
EPOCHS=epochs,
BATCH_SIZE=batch_size,
SEED=seed,
),
)
tests/functional/examples/test_notebooks_gpu.py:91:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
recommenders/utils/notebook_utils.py:99: in execute_notebook
executed_notebook, _ = execute_preprocessor.preprocess(
../../anaconda/envs/recommenders/lib/python3.9/site-packages/nbconvert/preprocessors/execute.py:100: in preprocess
self.preprocess_cell(cell, resources, index)
../../anaconda/envs/recommenders/lib/python3.9/site-packages/nbconvert/preprocessors/execute.py:121: in preprocess_cell
cell = self.execute_cell(cell, index, store_history=True)
../../anaconda/envs/recommenders/lib/python3.9/site-packages/jupyter_core/utils/__init__.py:166: in wrapped
return loop.run_until_complete(inner)
../../anaconda/envs/recommenders/lib/python3.9/asyncio/base_events.py:647: in run_until_complete
return future.result()
../../anaconda/envs/recommenders/lib/python3.9/site-packages/nbclient/client.py:1058: in async_execute_cell
await self._check_raise_for_error(cell, cell_index, exec_reply)
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
self = <nbconvert.preprocessors.execute.ExecutePreprocessor object at 0x7fc7855dc6d0>
cell = {'cell_type': 'code', 'execution_count': 3, 'metadata': {'execution': {'iopub.status.busy': '2023-10-31T16:26:54.66711...oad_pandas_df(\n size=MOVIELENS_DATA_SIZE,\n header=["userID", "itemID", "rating", "timestamp"]\n)\n\ndf.head()'}
cell_index = 9
exec_reply = {'buffers': [], 'content': {'ename': 'ValueError', 'engine_info': {'engine_id': -1, 'engine_uuid': 'e1defabf-6d1f-40f2...e, 'engine': 'e1defabf-6d1f-40f2-a86b-3533e758ecca', 'started': '2023-10-31T16:26:54.667305Z', 'status': 'error'}, ...}
async def _check_raise_for_error(
self, cell: NotebookNode, cell_index: int, exec_reply: t.Optional[t.Dict]
) -> None:
if exec_reply is None:
return None
exec_reply_content = exec_reply['content']
if exec_reply_content['status'] != 'error':
return None
cell_allows_errors = (not self.force_raise_errors) and (
self.allow_errors
or exec_reply_content.get('ename') in self.allow_error_names
or "raises-exception" in cell.metadata.get("tags", [])
)
await run_hook(
self.on_cell_error, cell=cell, cell_index=cell_index, execute_reply=exec_reply
)
if not cell_allows_errors:
> raise CellExecutionError.from_cell_and_msg(cell, exec_reply_content)
E nbclient.exceptions.CellExecutionError: An error occurred while executing the following cell:
E ------------------
E df = movielens.load_pandas_df(
E size=MOVIELENS_DATA_SIZE,
E header=["userID", "itemID", "rating", "timestamp"]
E )
E
E df.head()
E ------------------
E
E
E ---------------------------------------------------------------------------
E ValueError Traceback (most recent call last)
E Cell In[3], line 1
E ----> 1 df = movielens.load_pandas_df(
E 2 size=MOVIELENS_DATA_SIZE,
E 3 header=["userID", "itemID", "rating", "timestamp"]
E 4 )
E 6 df.head()
E
E File ~/MS/recommenders/recommenders/datasets/movielens.py:201, in load_pandas_df(size, header, local_cache_path, title_col, genres_col, year_col)
E 199 size = size.lower()
E 200 if size not in DATA_FORMAT and size not in MOCK_DATA_FORMAT:
E --> 201 raise ValueError(f"Size: {size}. " + ERROR_MOVIE_LENS_SIZE)
E 203 if header is None:
E 204 header = DEFAULT_HEADER
E
E ValueError: Size: 10k. Invalid data size. Should be one of {100k, 1m, 10m, or 20m, or mock100}
../../anaconda/envs/recommenders/lib/python3.9/site-packages/nbclient/client.py:914: CellExecutionError
============================================================================= warnings summary ==============================================================================
../../anaconda/envs/recommenders/lib/python3.9/site-packages/jupyter_client/connect.py:20
/home/u/anaconda/envs/recommenders/lib/python3.9/site-packages/jupyter_client/connect.py:20: DeprecationWarning: Jupyter is migrating its paths to use standard platformdirs
given by the platformdirs library. To remove this warning and
see the appropriate new directories, set the environment variable
`JUPYTER_PLATFORM_DIRS=1` and then run `jupyter --paths`.
The use of platformdirs will be the default in `jupyter_core` v6
from jupyter_core.paths import jupyter_data_dir, jupyter_runtime_dir, secure_write
-- Docs: https://docs.pytest.org/en/stable/how-to/capture-warnings.html
========================================================================== short test summary info ==========================================================================
FAILED tests/functional/examples/test_notebooks_gpu.py::test_ncf_deep_dive_functional[100k-10-512-expected_values0-42] - nbclient.exceptions.CellExecutionError: An error occurred while executing the following cell:
======================================================================= 1 failed, 1 warning in 5.23s ========================================================================Similar error but with a different notebook:
@pytest.mark.notebooks
@pytest.mark.experimental
def test_rlrmc_quickstart_runs(notebooks, output_notebook, kernel_name):
notebook_path = notebooks["rlrmc_quickstart"]
> execute_notebook(
notebook_path,
output_notebook,
kernel_name=kernel_name,
parameters=dict(rank_parameter=2, MOVIELENS_DATA_SIZE="mock100"),
)
tests/unit/examples/test_notebooks_python.py:88:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
recommenders/utils/notebook_utils.py:99: in execute_notebook
executed_notebook, _ = execute_preprocessor.preprocess(
/azureml-envs/azureml_8854b0bdccc7bb7425b7c3f2145bc96f/lib/python3.9/site-packages/nbconvert/preprocessors/execute.py:102: in preprocess
self.preprocess_cell(cell, resources, index)
/azureml-envs/azureml_8854b0bdccc7bb7425b7c3f2145bc96f/lib/python3.9/site-packages/nbconvert/preprocessors/execute.py:123: in preprocess_cell
cell = self.execute_cell(cell, index, store_history=True)
/azureml-envs/azureml_8854b0bdccc7bb7425b7c3f2145bc96f/lib/python3.9/site-packages/jupyter_core/utils/__init__.py:173: in wrapped
return loop.run_until_complete(inner)
/azureml-envs/azureml_8854b0bdccc7bb7425b7c3f2145bc96f/lib/python3.9/asyncio/base_events.py:647: in run_until_complete
return future.result()
/azureml-envs/azureml_8854b0bdccc7bb7425b7c3f2145bc96f/lib/python3.9/site-packages/nbclient/client.py:1058: in async_execute_cell
await self._check_raise_for_error(cell, cell_index, exec_reply)
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
self = <nbconvert.preprocessors.execute.ExecutePreprocessor object at 0x14e3f8053940>
cell = ***'cell_type': 'code', 'execution_count': 4, 'metadata': ***'execution': ***'iopub.status.busy': '2023-10-31T16:49:29.42054...= movielens.load_pandas_df(\n size=MOVIELENS_DATA_SIZE,\n header=["userID", "itemID", "rating", "timestamp"]\n)'***
cell_index = 7
exec_reply = ***'buffers': [], 'content': ***'ename': 'ValueError', 'engine_info': ***'engine_id': -1, 'engine_uuid': '79883de8-cb38-47df...e, 'engine': '79883de8-cb38-47df-a3b2-e63115050117', 'started': '2023-10-31T16:49:29.420956Z', 'status': 'error'***, ...***
async def _check_raise_for_error(
self, cell: NotebookNode, cell_index: int, exec_reply: t.Optional[t.Dict]
) -> None:
if exec_reply is None:
return None
exec_reply_content = exec_reply['content']
if exec_reply_content['status'] != 'error':
return None
cell_allows_errors = (not self.force_raise_errors) and (
self.allow_errors
or exec_reply_content.get('ename') in self.allow_error_names
or "raises-exception" in cell.metadata.get("tags", [])
)
await run_hook(
self.on_cell_error, cell=cell, cell_index=cell_index, execute_reply=exec_reply
)
if not cell_allows_errors:
> raise CellExecutionError.from_cell_and_msg(cell, exec_reply_content)
E nbclient.exceptions.CellExecutionError: An error occurred while executing the following cell:
E ------------------
E
E df = movielens.load_pandas_df(
E size=MOVIELENS_DATA_SIZE,
E header=["userID", "itemID", "rating", "timestamp"]
E )
E ------------------
E
E
E ---------------------------------------------------------------------------
E ValueError Traceback (most recent call last)
E Cell In[4], line 1
E ----> 1 df = movielens.load_pandas_df(
E 2 size=MOVIELENS_DATA_SIZE,
E 3 header=["userID","itemID","rating","timestamp"]
E 4 )
E
E File /mnt/azureml/cr/j/f1d53f64bdb5410196f4cc9b6e069605/exe/wd/recommenders/datasets/movielens.py:201, in load_pandas_df(size, header, local_cache_path, title_col, genres_col, year_col)
E 199 size = size.lower()
E 200 if size not in DATA_FORMAT and size not in MOCK_DATA_FORMAT:
E --> 201 raise ValueError(f"Size: ***size***. " + ERROR_MOVIE_LENS_SIZE)
E 203 if header is None:
E 204 header = DEFAULT_HEADER
E
E ValueError: Size: 2m. Invalid data size. Should be one of ***100k, 1m, 10m, or 20m, or mock100***
loomlike
SimonYansenZhao
Description
This PR removes papermill and scrapbook and adds the same functionality
Related Issues
Fixes https://github.com/recommenders-team/recommenders/issues/2012
References
Checklist:
staging branchand not tomain branch.