snowpark-connect 0.23.0__py3-none-any.whl → 0.25.0__py3-none-any.whl

snowflake/snowpark_connect/includes/python/pyspark/ml/tests/connect/test_legacy_mode_feature.py

@@ -1,156 +0,0 @@
-# -*- coding: utf-8 -*-
-#
-# Licensed to the Apache Software Foundation (ASF) under one or more
-# contributor license agreements.  See the NOTICE file distributed with
-# this work for additional information regarding copyright ownership.
-# The ASF licenses this file to You under the Apache License, Version 2.0
-# (the "License"); you may not use this file except in compliance with
-# the License.  You may obtain a copy of the License at
-#
-#    http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-#
-
-import os
-import pickle
-import numpy as np
-import tempfile
-import unittest
-
-from pyspark.ml.connect.feature import (
-    MaxAbsScaler,
-    MaxAbsScalerModel,
-    StandardScaler,
-    StandardScalerModel,
-)
-from pyspark.sql import SparkSession
-
-
-class FeatureTestsMixin:
-    def test_max_abs_scaler(self):
-        df1 = self.spark.createDataFrame(
-            [
-                ([2.0, 3.5, 1.5],),
-                ([-3.0, -0.5, -2.5],),
-            ],
-            schema=["features"],
-        )
-
-        scaler = MaxAbsScaler(inputCol="features", outputCol="scaled_features")
-
-        model = scaler.fit(df1)
-        assert model.uid == scaler.uid
-        result = model.transform(df1).toPandas()
-        assert list(result.columns) == ["features", "scaled_features"]
-
-        expected_result = [[2.0 / 3, 1.0, 0.6], [-1.0, -1.0 / 7, -1.0]]
-
-        np.testing.assert_allclose(list(result.scaled_features), expected_result)
-
-        local_df1 = df1.toPandas()
-        local_fit_model = scaler.fit(local_df1)
-        local_transform_result = local_fit_model.transform(local_df1)
-        assert id(local_transform_result) == id(local_df1)
-        assert list(local_transform_result.columns) == ["features", "scaled_features"]
-
-        np.testing.assert_allclose(list(local_transform_result.scaled_features), expected_result)
-
-        with tempfile.TemporaryDirectory() as tmp_dir:
-            estimator_path = os.path.join(tmp_dir, "estimator")
-            scaler.saveToLocal(estimator_path)
-            loaded_scaler = MaxAbsScaler.loadFromLocal(estimator_path)
-            assert loaded_scaler.getInputCol() == "features"
-            assert loaded_scaler.getOutputCol() == "scaled_features"
-
-            model_path = os.path.join(tmp_dir, "model")
-            model.saveToLocal(model_path)
-            loaded_model = MaxAbsScalerModel.loadFromLocal(model_path)
-
-            np.testing.assert_allclose(model.scale_values, loaded_model.scale_values)
-            np.testing.assert_allclose(model.max_abs_values, loaded_model.max_abs_values)
-            assert model.n_samples_seen == loaded_model.n_samples_seen
-
-            # Test loading core model as scikit-learn model
-            with open(os.path.join(model_path, "MaxAbsScalerModel.sklearn.pkl"), "rb") as f:
-                sk_model = pickle.load(f)
-                sk_result = sk_model.transform(np.stack(list(local_df1.features)))
-                np.testing.assert_allclose(sk_result, expected_result)
-
-    def test_standard_scaler(self):
-        df1 = self.spark.createDataFrame(
-            [
-                ([2.0, 3.5, 1.5],),
-                ([-3.0, -0.5, -2.5],),
-                ([1.0, -1.5, 0.5],),
-            ],
-            schema=["features"],
-        )
-
-        scaler = StandardScaler(inputCol="features", outputCol="scaled_features")
-        model = scaler.fit(df1)
-        assert model.uid == scaler.uid
-        result = model.transform(df1).toPandas()
-        assert list(result.columns) == ["features", "scaled_features"]
-
-        expected_result = [
-            [0.7559289460184544, 1.1338934190276817, 0.8006407690254358],
-            [-1.1338934190276817, -0.3779644730092272, -1.1208970766356101],
-            [0.3779644730092272, -0.7559289460184544, 0.32025630761017426],
-        ]
-
-        np.testing.assert_allclose(list(result.scaled_features), expected_result)
-
-        local_df1 = df1.toPandas()
-        local_fit_model = scaler.fit(local_df1)
-        local_transform_result = local_fit_model.transform(local_df1)
-        assert id(local_transform_result) == id(local_df1)
-        assert list(local_transform_result.columns) == ["features", "scaled_features"]
-
-        np.testing.assert_allclose(list(local_transform_result.scaled_features), expected_result)
-
-        with tempfile.TemporaryDirectory() as tmp_dir:
-            estimator_path = os.path.join(tmp_dir, "estimator")
-            scaler.saveToLocal(estimator_path)
-            loaded_scaler = StandardScaler.loadFromLocal(estimator_path)
-            assert loaded_scaler.getInputCol() == "features"
-            assert loaded_scaler.getOutputCol() == "scaled_features"
-
-            model_path = os.path.join(tmp_dir, "model")
-            model.saveToLocal(model_path)
-            loaded_model = StandardScalerModel.loadFromLocal(model_path)
-
-            np.testing.assert_allclose(model.std_values, loaded_model.std_values)
-            np.testing.assert_allclose(model.mean_values, loaded_model.mean_values)
-            np.testing.assert_allclose(model.scale_values, loaded_model.scale_values)
-            assert model.n_samples_seen == loaded_model.n_samples_seen
-
-            # Test loading core model as scikit-learn model
-            with open(os.path.join(model_path, "StandardScalerModel.sklearn.pkl"), "rb") as f:
-                sk_model = pickle.load(f)
-                sk_result = sk_model.transform(np.stack(list(local_df1.features)))
-                np.testing.assert_allclose(sk_result, expected_result)
-
-
-class FeatureTests(FeatureTestsMixin, unittest.TestCase):
-    def setUp(self) -> None:
-        self.spark = SparkSession.builder.master("local[2]").getOrCreate()
-
-    def tearDown(self) -> None:
-        self.spark.stop()
-
-
-if __name__ == "__main__":
-    from pyspark.ml.tests.connect.test_legacy_mode_feature import *  # noqa: F401,F403
-
-    try:
-        import xmlrunner  # type: ignore[import]
-
-        testRunner = xmlrunner.XMLTestRunner(output="target/test-reports", verbosity=2)
-    except ImportError:
-        testRunner = None
-    unittest.main(testRunner=testRunner, verbosity=2)

snowflake/snowpark_connect/includes/python/pyspark/ml/tests/connect/test_legacy_mode_pipeline.py

@@ -1,184 +0,0 @@
-# -*- coding: utf-8 -*-
-#
-# Licensed to the Apache Software Foundation (ASF) under one or more
-# contributor license agreements.  See the NOTICE file distributed with
-# this work for additional information regarding copyright ownership.
-# The ASF licenses this file to You under the Apache License, Version 2.0
-# (the "License"); you may not use this file except in compliance with
-# the License.  You may obtain a copy of the License at
-#
-#    http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-#
-import os
-import tempfile
-import unittest
-import numpy as np
-from pyspark.ml.connect.feature import StandardScaler
-from pyspark.ml.connect.classification import LogisticRegression as LORV2
-from pyspark.ml.connect.pipeline import Pipeline
-from pyspark.sql import SparkSession
-
-
-have_torch = True
-try:
-    import torch  # noqa: F401
-except ImportError:
-    have_torch = False
-
-
-class PipelineTestsMixin:
-    @staticmethod
-    def _check_result(result_dataframe, expected_predictions, expected_probabilities=None):
-        np.testing.assert_array_equal(list(result_dataframe.prediction), expected_predictions)
-        if "probability" in result_dataframe.columns:
-            np.testing.assert_allclose(
-                list(result_dataframe.probability),
-                expected_probabilities,
-                rtol=1e-1,
-            )
-
-    def test_pipeline(self):
-        train_dataset = self.spark.createDataFrame(
-            [
-                (1.0, [0.0, 5.0]),
-                (0.0, [1.0, 2.0]),
-                (1.0, [2.0, 1.0]),
-                (0.0, [3.0, 3.0]),
-            ]
-            * 100,
-            ["label", "features"],
-        )
-        eval_dataset = self.spark.createDataFrame(
-            [
-                ([0.0, 2.0],),
-                ([3.5, 3.0],),
-            ],
-            ["features"],
-        )
-        scaler = StandardScaler(inputCol="features", outputCol="scaled_features")
-        lorv2 = LORV2(
-            maxIter=200, numTrainWorkers=2, learningRate=0.001, featuresCol="scaled_features"
-        )
-
-        pipeline = Pipeline(stages=[scaler, lorv2])
-        model = pipeline.fit(train_dataset)
-        assert model.uid == pipeline.uid
-
-        expected_predictions = [1, 0]
-        expected_probabilities = [
-            [0.117658, 0.882342],
-            [0.878738, 0.121262],
-        ]
-
-        result = model.transform(eval_dataset).toPandas()
-        self._check_result(result, expected_predictions, expected_probabilities)
-        local_transform_result = model.transform(eval_dataset.toPandas())
-        self._check_result(local_transform_result, expected_predictions, expected_probabilities)
-
-        pipeline2 = Pipeline(stages=[pipeline])
-        model2 = pipeline2.fit(train_dataset)
-        result2 = model2.transform(eval_dataset).toPandas()
-        self._check_result(result2, expected_predictions, expected_probabilities)
-        local_transform_result2 = model2.transform(eval_dataset.toPandas())
-        self._check_result(local_transform_result2, expected_predictions, expected_probabilities)
-
-        with tempfile.TemporaryDirectory() as tmp_dir:
-            pipeline_local_path = os.path.join(tmp_dir, "pipeline")
-            pipeline.saveToLocal(pipeline_local_path)
-            loaded_pipeline = Pipeline.loadFromLocal(pipeline_local_path)
-
-            assert pipeline.uid == loaded_pipeline.uid
-            assert loaded_pipeline.getStages()[1].getMaxIter() == 200
-
-            pipeline_model_local_path = os.path.join(tmp_dir, "pipeline_model")
-            model.saveToLocal(pipeline_model_local_path)
-            loaded_model = Pipeline.loadFromLocal(pipeline_model_local_path)
-
-            assert model.uid == loaded_model.uid
-            assert loaded_model.stages[1].getMaxIter() == 200
-
-            loaded_model_transform_result = loaded_model.transform(eval_dataset).toPandas()
-            self._check_result(
-                loaded_model_transform_result, expected_predictions, expected_probabilities
-            )
-
-            pipeline2_local_path = os.path.join(tmp_dir, "pipeline2")
-            pipeline2.saveToLocal(pipeline2_local_path)
-            loaded_pipeline2 = Pipeline.loadFromLocal(pipeline2_local_path)
-
-            assert pipeline2.uid == loaded_pipeline2.uid
-            assert loaded_pipeline2.getStages()[0].getStages()[1].getMaxIter() == 200
-
-            pipeline2_model_local_path = os.path.join(tmp_dir, "pipeline2_model")
-            model2.saveToLocal(pipeline2_model_local_path)
-            loaded_model2 = Pipeline.loadFromLocal(pipeline2_model_local_path)
-
-            assert model2.uid == loaded_model2.uid
-            assert loaded_model2.stages[0].stages[1].getMaxIter() == 200
-
-            loaded_model2_transform_result = loaded_model2.transform(eval_dataset).toPandas()
-            self._check_result(
-                loaded_model2_transform_result, expected_predictions, expected_probabilities
-            )
-
-    @staticmethod
-    def test_pipeline_copy():
-        scaler = StandardScaler(inputCol="features", outputCol="scaled_features")
-        lorv2 = LORV2(
-            maxIter=200, numTrainWorkers=2, learningRate=0.001, featuresCol="scaled_features"
-        )
-
-        pipeline = Pipeline(stages=[scaler, lorv2])
-
-        copied_pipeline = pipeline.copy(
-            {scaler.inputCol: "f1", lorv2.maxIter: 10, lorv2.numTrainWorkers: 1}
-        )
-
-        stages = copied_pipeline.getStages()
-
-        assert stages[0].getInputCol() == "f1"
-        assert stages[1].getOrDefault(stages[1].maxIter) == 10
-        assert stages[1].getOrDefault(stages[1].numTrainWorkers) == 1
-        assert stages[1].getOrDefault(stages[1].featuresCol) == "scaled_features"
-
-        pipeline2 = Pipeline(stages=[pipeline])
-        copied_pipeline2 = pipeline2.copy(
-            {scaler.inputCol: "f2", lorv2.maxIter: 20, lorv2.numTrainWorkers: 20}
-        )
-
-        stages = copied_pipeline2.getStages()[0].getStages()
-
-        assert stages[0].getInputCol() == "f2"
-        assert stages[1].getOrDefault(stages[1].maxIter) == 20
-        assert stages[1].getOrDefault(stages[1].numTrainWorkers) == 20
-        assert stages[1].getOrDefault(stages[1].featuresCol) == "scaled_features"
-
-        # test original stage instance params are not modified after pipeline copying.
-        assert scaler.getInputCol() == "features"
-        assert lorv2.getOrDefault(lorv2.maxIter) == 200
-
-
-class PipelineTests(PipelineTestsMixin, unittest.TestCase):
-    def setUp(self) -> None:
-        self.spark = SparkSession.builder.master("local[2]").getOrCreate()
-
-    def tearDown(self) -> None:
-        self.spark.stop()
-
-
-if __name__ == "__main__":
-    from pyspark.ml.tests.connect.test_legacy_mode_pipeline import *  # noqa: F401,F403
-
-    try:
-        import xmlrunner  # type: ignore[import]
-
-        testRunner = xmlrunner.XMLTestRunner(output="target/test-reports", verbosity=2)
-    except ImportError:
-        testRunner = None
-    unittest.main(testRunner=testRunner, verbosity=2)

snowflake/snowpark_connect/includes/python/pyspark/ml/tests/connect/test_legacy_mode_summarizer.py

@@ -1,78 +0,0 @@
-# -*- coding: utf-8 -*-
-#
-# Licensed to the Apache Software Foundation (ASF) under one or more
-# contributor license agreements.  See the NOTICE file distributed with
-# this work for additional information regarding copyright ownership.
-# The ASF licenses this file to You under the Apache License, Version 2.0
-# (the "License"); you may not use this file except in compliance with
-# the License.  You may obtain a copy of the License at
-#
-#    http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-#
-
-import unittest
-import numpy as np
-
-from pyspark.ml.connect.summarizer import summarize_dataframe
-from pyspark.sql import SparkSession
-
-
-class SummarizerTestsMixin:
-    def test_summarize_dataframe(self):
-        df1 = self.spark.createDataFrame(
-            [
-                ([2.0, -1.5],),
-                ([-3.0, 0.5],),
-                ([1.0, 3.5],),
-            ],
-            schema=["features"],
-        )
-
-        df1_local = df1.toPandas()
-
-        result = summarize_dataframe(df1, "features", ["min", "max", "sum", "mean", "std"])
-        result_local = summarize_dataframe(
-            df1_local, "features", ["min", "max", "sum", "mean", "std"]
-        )
-        expected_result = {
-            "min": [-3.0, -1.5],
-            "max": [2.0, 3.5],
-            "sum": [0.0, 2.5],
-            "mean": [0.0, 0.83333333],
-            "std": [2.64575131, 2.51661148],
-        }
-
-        def assert_dict_allclose(dict1, dict2):
-            assert set(dict1.keys()) == set(dict2.keys())
-
-            for key in dict1:
-                np.testing.assert_allclose(dict1[key], dict2[key])
-
-        assert_dict_allclose(result, expected_result)
-        assert_dict_allclose(result_local, expected_result)
-
-
-class SummarizerTests(SummarizerTestsMixin, unittest.TestCase):
-    def setUp(self) -> None:
-        self.spark = SparkSession.builder.master("local[2]").getOrCreate()
-
-    def tearDown(self) -> None:
-        self.spark.stop()
-
-
-if __name__ == "__main__":
-    from pyspark.ml.tests.connect.test_legacy_mode_summarizer import *  # noqa: F401,F403
-
-    try:
-        import xmlrunner  # type: ignore[import]
-
-        testRunner = xmlrunner.XMLTestRunner(output="target/test-reports", verbosity=2)
-    except ImportError:
-        testRunner = None
-    unittest.main(testRunner=testRunner, verbosity=2)