pyarrow fix

[svittoz]

Description

pyarrow patch in last release fails when it is run by spark executor.

This PR fix this issue by specifying the python path the executor must look for in spark config.

This PR works combined with EDS-Toolbox PR 80.

Checklist

• If this PR is a bug fix, the bug is documented in the test suite.
• Changes were documented in the changelog (pending section).
• If necessary, changes were made to the documentation (eg new pipeline).

[Thomzoy]

Let's go !

[github-actions]

Coverage Report

Name	Stmts	Miss	∆ Miss	Cover
TOTAL	2278	153	0	93%

Files without new missing coverage

Name	Stmts	Miss	∆ Miss	Cover
eds_scikit/utils/test_utils.py Was already missing at line 50 def date(s): - return dt.strptime(s, "%Y-%m-%d") Was already missing at lines 88-90 args = tuple(args) - elif type(index_or_key) == str: - kwargs[index_or_key] = inputs Was already missing at lines 114-116 else: - normalized_sum_sq_diff = sum_sq_diff / np.sqrt(sum_sq_diff) - assert normalized_sum_sq_diff < 0.001	54	5	0	91%
eds_scikit/utils/flowchart/flowchart.py Was already missing at line 152 def __str__(self) -> str: - return self.__repr__()	131	1	0	99%
eds_scikit/utils/custom_implem/custom_implem.py Was already missing at line 54 """ - return cut( x,	22	1	0	95%
eds_scikit/utils/checks.py Was already missing at line 127 if return_index_or_key: - return kwargs[argname], argname return kwargs[argname] Was already missing at line 149 else: - to_display_per_concept = [f"- {concept}" for concept in required_concepts] str_to_display = "\n".join(to_display_per_concept) Was already missing at lines 172-189 - if all(isinstance(table, tuple) for table in required_tables): ... - super().__init__(message)	71	10	0	86%
eds_scikit/utils/bunch.py Was already missing at line 32 def __setattr__(self, key, value): - self[key] = value Was already missing at line 35 def __dir__(self): - return self.keys() Was already missing at lines 38-41 def __getattr__(self, key): - try: - return self[key] - except KeyError: raise AttributeError(key)	11	5	0	55%
eds_scikit/resources/utils.py Was already missing at line 19 if len(splited) == 1: - return None return splited[-1]	6	1	0	83%
eds_scikit/resources/reg.py Was already missing at lines 50-78 # Looking for a match excluding version string - candidates = [ ... - func = r.get(candidates[0]) return func	16	4	0	75%
eds_scikit/period/tagging_functions.py Was already missing at lines 60-63 # TODO: is this necessary ? - logger.warning("No matching were found between the 2 DataFrames") - - return framework.DataFrame( columns=["person_id", "t_start", "t_end", "concept", "value"] Was already missing at lines 119-123 return (B_start >= A_start) & (B_end <= A_end) - elif algo == interval_algos.from_before_to: - return B_end <= A_start - elif algo == interval_algos.to_before_from: - return A_end <= B_start else:	36	6	0	83%
eds_scikit/period/stays.py Was already missing at line 409 if open_stay_end_datetime is None: - open_stay_end_datetime = datetime.now() vo["visit_end_datetime_calc"] = open_stay_end_datetime	86	1	0	99%
eds_scikit/io/i2b2_mapping.py Was already missing at lines 38-211 - i2b2_table_name = i2b2_tables[db_source][table] ... - return df Was already missing at lines 230-234 - def f(x): - return mapping.get(x, default) - - return F.udf(f)	79	69	0	13%
eds_scikit/io/base.py Was already missing at line 13 def __str__(self): - return self.__repr__()	9	1	0	89%
eds_scikit/event/from_code.py Was already missing at lines 108-111 else: - event.loc[:, "t_start"] = event.loc[:, columns["code_start_datetime"]] ... - event = event.drop( columns=[columns["code_start_datetime"], columns["code_end_datetime"]]	42	3	0	93%
eds_scikit/event/diabetes.py Was already missing at lines 88-102 """ - diabetes = conditions_from_icd10( ... - - return diabetes	10	4	0	60%
eds_scikit/event/consultations.py Was already missing at line 68 if type(algo) == str: - algo = [algo]	61	1	0	98%
eds_scikit/emergency/emergency_care_site.py Was already missing at line 54 if algo == "from_regex_on_parent_UF": - return from_regex_on_parent_UF(care_site) elif algo == "from_regex_on_care_site_description": Was already missing at line 166 """ - return attributes.get_parent_attributes( care_site,	31	2	0	94%
eds_scikit/datasets/synthetic/biology.py Was already missing at lines 37-44 def reset_to_pandas(self): - if self.module == "koalas": ... - self.module = "pandas"	132	7	0	95%
eds_scikit/datasets/__init__.py Was already missing at line 38 def __dir__(): - return known_datasets + [func.__name__ for func in __all__] Was already missing at lines 52-56 def add_dataset(table: pd.DataFrame, name: str): - dataset_path = os.path.abspath( - os.path.join(os.path.dirname(__file__), name + ".csv") - ) - table.to_csv(dataset_path, index=False) Was already missing at line 67 """ - return [func.__name__ for func in __all__]	26	4	0	85%
eds_scikit/biology/viz/plot.py Was already missing at line 72 else: - logger.error( "The folder {} has not been found", Was already missing at lines 718-720 else: - terminologies_hist = alt.Chart().mark_text() - terminologies_time_series = ( alt.Chart(measurement)	130	3	0	98%
eds_scikit/biology/viz/aggregate.py Was already missing at line 83 if stats_only: - return {"measurement_stats": measurement_stats} Was already missing at line 208 if overall_only: - return measurement_stats_overall	97	2	0	98%
eds_scikit/biology/utils/config.py Was already missing at lines 30-66 """ - my_custom_config = pd.DataFrame() ... - register_configs() Was already missing at lines 73-75 for config in glob.glob(os.path.join(CONFIGS_PATH, "*.csv")): - config_name = Path(config).stem - registry.data.register( f"get_biology_config.{config_name}", Was already missing at lines 89-94 """ - registered = list(registry.data.get_all().keys()) - configs = [ - r.split(".")[-1] for r in registered if r.startswith("get_biology_config") - ] - return configs	35	22	0	37%
eds_scikit/biology/cleaning/cohort.py Was already missing at line 28 if isinstance(studied_pop, DataFrame.__args__): - filtered_measures = measurement.merge( studied_pop,	9	1	0	89%

59 files skipped due to complete coverage.

Coverage success: total of 93% is above 93% 🎉