From bdddd95e3c0d62e5b0ea0283feb0d2900da76b8e Mon Sep 17 00:00:00 2001 From: Angela Lin Date: Mon, 30 Nov 2020 16:09:36 -0500 Subject: [PATCH 1/4] remove copy_dataframe --- core-requirements.txt | 2 +- evalml/utils/gen_utils.py | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/core-requirements.txt b/core-requirements.txt index 96cd557dff..369a7d18a5 100644 --- a/core-requirements.txt +++ b/core-requirements.txt @@ -10,6 +10,6 @@ psutil>=5.6.3 requirements-parser>=0.2.0 shap>=0.35.0 texttable>=1.6.2 -woodwork>=0.0.5 +woodwork>=0.0.6 featuretools>=0.20.0 nlp-primitives>=1.1.0 diff --git a/evalml/utils/gen_utils.py b/evalml/utils/gen_utils.py index d04b1c07c1..ffd9bc6e32 100644 --- a/evalml/utils/gen_utils.py +++ b/evalml/utils/gen_utils.py @@ -302,7 +302,7 @@ def _convert_to_woodwork_structure(data): # Convert pandas data structures to Woodwork data structures if isinstance(ww_data, pd.Series): return ww.DataColumn(ww_data) - return ww.DataTable(ww_data, copy_dataframe=True) + return ww.DataTable(ww_data) def _convert_woodwork_types_wrapper(pd_data): From fc36f18760a5c36788ada4f2711389ddfa15a04d Mon Sep 17 00:00:00 2001 From: Angela Lin Date: Mon, 30 Nov 2020 16:25:37 -0500 Subject: [PATCH 2/4] cleanup --- docs/source/release_notes.rst | 1 + evalml/utils/gen_utils.py | 2 ++ 2 files changed, 3 insertions(+) diff --git a/docs/source/release_notes.rst b/docs/source/release_notes.rst index ddfd95158b..9feda2ee7f 100644 --- a/docs/source/release_notes.rst +++ b/docs/source/release_notes.rst @@ -5,6 +5,7 @@ Release Notes * Enhancements * Fixes * Updated ``Woodwork`` to >=0.0.5 in ``core-requirements.txt`` :pr:`1473` + * Removed ``copy_dataframe`` parameter for ``Woodwork``, updated ``Woodwork`` to >=0.0.6 in ``core-requirements.txt`` :pr:`1478` * Changes * Changed ``make clean`` to delete coverage reports as a convenience for developers :pr:`1464` * Documentation Changes diff --git a/evalml/utils/gen_utils.py b/evalml/utils/gen_utils.py index ffd9bc6e32..b29771ddcc 100644 --- a/evalml/utils/gen_utils.py +++ b/evalml/utils/gen_utils.py @@ -300,8 +300,10 @@ def _convert_to_woodwork_structure(data): ww_data = pd.DataFrame(ww_data) # Convert pandas data structures to Woodwork data structures + ww_data = ww.data.copy() if isinstance(ww_data, pd.Series): return ww.DataColumn(ww_data) + return ww.DataTable(ww_data) From 5cbd6586620c0f5325c2fb27ec361e7bc584348d Mon Sep 17 00:00:00 2001 From: Angela Lin Date: Mon, 30 Nov 2020 16:40:34 -0500 Subject: [PATCH 3/4] fix typo --- evalml/utils/gen_utils.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/evalml/utils/gen_utils.py b/evalml/utils/gen_utils.py index b29771ddcc..bf16e0d788 100644 --- a/evalml/utils/gen_utils.py +++ b/evalml/utils/gen_utils.py @@ -300,7 +300,7 @@ def _convert_to_woodwork_structure(data): ww_data = pd.DataFrame(ww_data) # Convert pandas data structures to Woodwork data structures - ww_data = ww.data.copy() + ww_data = ww_data.copy() if isinstance(ww_data, pd.Series): return ww.DataColumn(ww_data) From 038cf3867a19390faee840ddcb8aa60a195392ce Mon Sep 17 00:00:00 2001 From: Angela Lin Date: Mon, 30 Nov 2020 16:55:23 -0500 Subject: [PATCH 4/4] fix test --- evalml/tests/automl_tests/test_automl.py | 6 +++--- evalml/utils/gen_utils.py | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/evalml/tests/automl_tests/test_automl.py b/evalml/tests/automl_tests/test_automl.py index 2894b7316d..2ee6fa9d68 100644 --- a/evalml/tests/automl_tests/test_automl.py +++ b/evalml/tests/automl_tests/test_automl.py @@ -1767,7 +1767,7 @@ def test_automl_woodwork_user_types_preserved(mock_binary_fit, mock_binary_score X['num col'] = pd.Series(new_col) X['text col'] = pd.Series([f"{num}" for num in range(len(new_col))]) X = ww.DataTable(X, semantic_tags={'cat col': 'category', 'num col': 'numeric'}, - logical_types={'cat col': 'Categorical', 'num col': 'WholeNumber', 'text col': 'NaturalLanguage'}) + logical_types={'cat col': 'Categorical', 'num col': 'Integer', 'text col': 'NaturalLanguage'}) automl = AutoMLSearch(problem_type=problem_type, max_batches=5) automl.search(X, y) for arg in mock_fit.call_args[0]: @@ -1776,7 +1776,7 @@ def test_automl_woodwork_user_types_preserved(mock_binary_fit, mock_binary_score assert arg.semantic_tags['cat col'] == {'category'} assert arg.logical_types['cat col'] == ww.logical_types.Categorical assert arg.semantic_tags['num col'] == {'numeric'} - assert arg.logical_types['num col'] == ww.logical_types.WholeNumber + assert arg.logical_types['num col'] == ww.logical_types.Integer assert arg.semantic_tags['text col'] == set() assert arg.logical_types['text col'] == ww.logical_types.NaturalLanguage for arg in mock_score.call_args[0]: @@ -1785,7 +1785,7 @@ def test_automl_woodwork_user_types_preserved(mock_binary_fit, mock_binary_score assert arg.semantic_tags['cat col'] == {'category'} assert arg.logical_types['cat col'] == ww.logical_types.Categorical assert arg.semantic_tags['num col'] == {'numeric'} - assert arg.logical_types['num col'] == ww.logical_types.WholeNumber + assert arg.logical_types['num col'] == ww.logical_types.Integer assert arg.semantic_tags['text col'] == set() assert arg.logical_types['text col'] == ww.logical_types.NaturalLanguage diff --git a/evalml/utils/gen_utils.py b/evalml/utils/gen_utils.py index bf16e0d788..8a2b432d2c 100644 --- a/evalml/utils/gen_utils.py +++ b/evalml/utils/gen_utils.py @@ -303,7 +303,7 @@ def _convert_to_woodwork_structure(data): ww_data = ww_data.copy() if isinstance(ww_data, pd.Series): return ww.DataColumn(ww_data) - + return ww.DataTable(ww_data)