src/main/python/tests/auto_tests/test_randomForest.py

# -------------------------------------------------------------
#
# 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.
#
# -------------------------------------------------------------

# Autogenerated By   : src/main/python/generator/generator.py
import unittest, contextlib, io
class TestRANDOMFOREST(unittest.TestCase):
    def test_randomForest(self):
        # Example test case provided in python the code block
        buf = io.StringIO()
        with contextlib.redirect_stdout(buf):
            import numpy as np
            from systemds.context import SystemDSContext
            from systemds.operator.algorithm import randomForest, randomForestPredict

            # tiny toy dataset
            X = np.array([[1],
                          [2],
                          [10],
                          [11]], dtype=np.int64)
            y = np.array([[1],
                          [1],
                          [2],
                          [2]], dtype=np.int64)

            with SystemDSContext() as sds:
                X_sds = sds.from_numpy(X)
                y_sds = sds.from_numpy(y)

                ctypes = sds.from_numpy(np.array([[1, 2]], dtype=np.int64))

                # train a 4-tree forest (no sampling)
                M = randomForest(
                        X_sds, y_sds, ctypes,
                        num_trees    = 4,
                        sample_frac  = 1.0,
                        feature_frac = 1.0,
                        max_depth    = 3,
                        min_leaf     = 1,
                        min_split    = 2,
                        seed         = 42
                     )

                preds = randomForestPredict(X_sds, ctypes, M).compute()
                print(preds)

            expected="""[[1.]
 [1.]
 [2.]
 [2.]]"""
        self.assertEqual(buf.getvalue().strip(), expected)

if __name__ == '__main__':
    unittest.main()