deps: remove scikit-learn and sqlalchemy as required dependencies #1296
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -19,6 +19,8 @@ | |
|
|
||
| from . import publish_api_coverage | ||
|
|
||
| pytest.importorskip("sklearn") | ||
|
|
||
|
|
||
| @pytest.fixture | ||
| def api_coverage_df(): | ||
|
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -55,8 +55,6 @@ | |
| "pyarrow >=10.0.1", | ||
| "pydata-google-auth >=1.8.2", | ||
| "requests >=2.27.1", | ||
| "sqlglot >=23.6.3", | ||
| "tabulate >=0.9", | ||
| "ipywidgets >=7.7.1", | ||
|
|
@@ -77,8 +75,15 @@ | |
| "tests": [], | ||
| # used for local engine, which is only needed for unit tests at present. | ||
| "polars": ["polars >= 1.7.0"], | ||
| "scikit-learn": ["scikit-learn>=1.2.2"], | ||
| # Packages required for basic development flow. | ||
| "dev": [ | ||
| "pytest", | ||
| "pytest-mock", | ||
| "pre-commit", | ||
| "nox", | ||
| "google-cloud-testutils", | ||
| ], | ||
| } | ||
| extras["all"] = list(sorted(frozenset(itertools.chain.from_iterable(extras.values())))) | ||
|
|
||
|
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -20,7 +20,6 @@ pyarrow==10.0.1 | |
| pydata-google-auth==1.8.2 | ||
| requests==2.27.1 | ||
| scikit-learn==1.2.2 | ||
| sqlglot==23.6.3 | ||
| tabulate==0.9 | ||
| ipywidgets==7.7.1 | ||
|
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -17,7 +17,6 @@ | |
| import numpy as np | ||
| import pandas as pd | ||
| import pytest | ||
|
|
||
| import bigframes | ||
| from bigframes.ml import metrics | ||
|
|
@@ -66,6 +65,7 @@ def test_r2_score_force_finite(session): | |
|
|
||
|
|
||
| def test_r2_score_ok_fit_matches_sklearn(session): | ||
| sklearn_metrics = pytest.importorskip("sklearn.metrics") | ||
| pd_df = pd.DataFrame({"y_true": [1, 2, 3, 4, 5], "y_pred": [2, 3, 4, 3, 6]}) | ||
|
|
||
| df = session.read_pandas(pd_df) | ||
|
|
@@ -113,6 +113,7 @@ def test_accuracy_score_not_normailze(session): | |
|
|
||
|
|
||
| def test_accuracy_score_fit_matches_sklearn(session): | ||
| sklearn_metrics = pytest.importorskip("sklearn.metrics") | ||
| pd_df = pd.DataFrame({"y_true": [1, 2, 3, 4, 5], "y_pred": [2, 3, 4, 3, 6]}) | ||
|
|
||
| df = session.read_pandas(pd_df) | ||
|
|
@@ -203,6 +204,7 @@ def test_roc_curve_binary_classification_prediction_returns_expected(session): | |
|
|
||
|
|
||
| def test_roc_curve_binary_classification_prediction_matches_sklearn(session): | ||
| sklearn_metrics = pytest.importorskip("sklearn.metrics") | ||
| pd_df = pd.DataFrame( | ||
| { | ||
| "y_true": [0, 0, 1, 1, 0, 1, 0, 1, 1, 1], | ||
|
|
@@ -294,6 +296,7 @@ def test_roc_curve_binary_classification_decision_returns_expected(session): | |
|
|
||
|
|
||
| def test_roc_curve_binary_classification_decision_matches_sklearn(session): | ||
| sklearn_metrics = pytest.importorskip("sklearn.metrics") | ||
| # Instead of operating on probabilities, assume a 70% decision threshold | ||
| # has been applied, and operate on the final output | ||
| y_score = [0.1, 0.4, 0.35, 0.8, 0.65, 0.9, 0.5, 0.3, 0.6, 0.45] | ||
|
|
@@ -420,6 +423,7 @@ def test_roc_auc_score_returns_expected(session): | |
|
|
||
|
|
||
| def test_roc_auc_score_returns_matches_sklearn(session): | ||
| sklearn_metrics = pytest.importorskip("sklearn.metrics") | ||
| pd_df = pd.DataFrame( | ||
| { | ||
| "y_true": [0, 0, 1, 1, 0, 1, 0, 1, 1, 1], | ||
|
|
@@ -525,6 +529,7 @@ def test_confusion_matrix_column_index(session): | |
|
|
||
|
|
||
| def test_confusion_matrix_matches_sklearn(session): | ||
| sklearn_metrics = pytest.importorskip("sklearn.metrics") | ||
| pd_df = pd.DataFrame( | ||
| { | ||
| "y_true": [2, 3, 3, 3, 4, 1], | ||
|
|
@@ -543,6 +548,7 @@ def test_confusion_matrix_matches_sklearn(session): | |
|
|
||
|
|
||
| def test_confusion_matrix_str_matches_sklearn(session): | ||
| sklearn_metrics = pytest.importorskip("sklearn.metrics") | ||
| pd_df = pd.DataFrame( | ||
| { | ||
| "y_true": ["cat", "ant", "cat", "cat", "ant", "bird"], | ||
|
|
@@ -603,6 +609,7 @@ def test_recall_score(session): | |
|
|
||
|
|
||
| def test_recall_score_matches_sklearn(session): | ||
| sklearn_metrics = pytest.importorskip("sklearn.metrics") | ||
| pd_df = pd.DataFrame( | ||
| { | ||
| "y_true": [2, 0, 2, 2, 0, 1], | ||
|
|
@@ -620,6 +627,7 @@ def test_recall_score_matches_sklearn(session): | |
|
|
||
|
|
||
| def test_recall_score_str_matches_sklearn(session): | ||
| sklearn_metrics = pytest.importorskip("sklearn.metrics") | ||
| pd_df = pd.DataFrame( | ||
| { | ||
| "y_true": ["cat", "ant", "cat", "cat", "ant", "bird"], | ||
|
|
@@ -673,6 +681,7 @@ def test_precision_score(session): | |
|
|
||
|
|
||
| def test_precision_score_matches_sklearn(session): | ||
| sklearn_metrics = pytest.importorskip("sklearn.metrics") | ||
| pd_df = pd.DataFrame( | ||
| { | ||
| "y_true": [2, 0, 2, 2, 0, 1], | ||
|
|
@@ -695,6 +704,7 @@ def test_precision_score_matches_sklearn(session): | |
|
|
||
|
|
||
| def test_precision_score_str_matches_sklearn(session): | ||
| sklearn_metrics = pytest.importorskip("sklearn.metrics") | ||
| pd_df = pd.DataFrame( | ||
| { | ||
| "y_true": ["cat", "ant", "cat", "cat", "ant", "bird"], | ||
|
|
@@ -752,6 +762,7 @@ def test_f1_score(session): | |
|
|
||
|
|
||
| def test_f1_score_matches_sklearn(session): | ||
| sklearn_metrics = pytest.importorskip("sklearn.metrics") | ||
| pd_df = pd.DataFrame( | ||
| { | ||
| "y_true": [2, 0, 2, 2, 0, 1], | ||
|
|
@@ -769,6 +780,7 @@ def test_f1_score_matches_sklearn(session): | |
|
|
||
|
|
||
| def test_f1_score_str_matches_sklearn(session): | ||
| sklearn_metrics = pytest.importorskip("sklearn.metrics") | ||
| pd_df = pd.DataFrame( | ||
| { | ||
| "y_true": ["cat", "ant", "cat", "cat", "ant", "bird"], | ||
|
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -641,6 +641,8 @@ def test_series_replace_dict(scalars_dfs, replacement_dict): | |
| ), | ||
| ) | ||
| def test_series_interpolate(method): | ||
| pytest.importorskip("scipy") | ||
|
|
||
| values = [None, 1, 2, None, None, 16, None] | ||
| index = [-3.2, 11.4, 3.56, 4, 4.32, 5.55, 76.8] | ||
| pd_series = pd.Series(values, index) | ||
|
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -13,8 +13,6 @@ | |
| # limitations under the License. | ||
|
|
||
| import pytest | ||
|
|
||
| import bigframes.ml.decomposition | ||
| import bigframes.ml.linear_model | ||
|
|
@@ -35,8 +33,9 @@ def test_base_estimator_repr(): | |
| assert pca_estimator.__repr__() == "PCA(n_components=7)" | ||
|
|
||
|
|
||
| def test_base_estimator_repr_matches_sklearn(): | ||
| sklearn_decomposition = pytest.importorskip("sklearn.decomposition") | ||
| sklearn_linear_model = pytest.importorskip("sklearn.linear_model") | ||
| estimator = bigframes.ml.linear_model.LinearRegression() | ||
| sklearn_estimator = sklearn_linear_model.LinearRegression() | ||
| assert estimator.__repr__() == sklearn_estimator.__repr__() | ||
|
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -15,8 +15,6 @@ | |
|
|
||
| from google.cloud import bigquery | ||
| import pytest | ||
|
|
||
| from bigframes.ml import compose, preprocessing | ||
| from bigframes.ml.compose import ColumnTransformer, SQLScalarColumnTransformer | ||
|
|
@@ -119,6 +117,8 @@ def test_columntransformer_repr(): | |
|
|
||
|
|
||
| def test_columntransformer_repr_matches_sklearn(): | ||
| sklearn_compose = pytest.importorskip("sklearn.compose") | ||
| sklearn_preprocessing = pytest.importorskip("sklearn.preprocessing") | ||
| bf_column_transformer = compose.ColumnTransformer( | ||
| [ | ||
| ( | ||
|
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -13,10 +13,6 @@ | |
| # limitations under the License. | ||
|
|
||
| import pytest | ||
|
|
||
| from bigframes.ml import compose, forecasting, linear_model, pipeline, preprocessing | ||
|
|
||
|
|
@@ -57,8 +53,11 @@ def test_pipeline_repr(): | |
| ) | ||
|
|
||
|
|
||
| def test_pipeline_repr_matches_sklearn(): | ||
| sklearn_compose = pytest.importorskip("sklearn.compose") | ||
| sklearn_linear_model = pytest.importorskip("sklearn.linear_model") | ||
| sklearn_pipeline = pytest.importorskip("sklearn.pipeline") | ||
| sklearn_preprocessing = pytest.importorskip("sklearn.preprocessing") | ||
| bf_pl = pipeline.Pipeline( | ||
| [ | ||
| ( | ||
|
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -16,6 +16,8 @@ | |
| # Michal Karbownik <michakarbownik@gmail.com> | ||
| # License: BSD 3 clause | ||
|
|
||
| import numpy as np | ||
|
|
||
| from bigframes import constants | ||
|
|
||
|
|
||
|
|
@@ -60,7 +62,23 @@ def auc(x, y) -> float: | |
| Returns: | ||
| float: Area Under the Curve. | ||
| """ | ||
| if len(x) < 2: | ||
| raise ValueError( | ||
| f"At least 2 points are needed to compute area under curve, but x.shape = {len(x)}" | ||
| ) | ||
|
|
||
| if x.is_monotonic_decreasing: | ||
| d = -1 | ||
| elif x.is_monotonic_increasing: | ||
| d = 1 | ||
| else: | ||
| raise ValueError(f"x is neither increasing nor decreasing : {x}.") | ||
|
|
||
| if hasattr(np, "trapezoid"): | ||
| # new in numpy 2.0 | ||
| return d * np.trapezoid(y, x) | ||
| # np.trapz has been deprecated in 2.0 | ||
| return d * np.trapz(y, x) # type: ignore | ||
|
|
||
|
|
||
| def roc_auc_score(y_true, y_score) -> float: | ||
|
|
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I'm very concerned if we need to install
scikit-learnjust to build the docs. Please remove.There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Not sure if it's possible to remove this as we are calling publish_api_coverage.py, and one of the things it do is go through sklearn APIs and generate a coverage report.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Good point. Thanks for clarifying.