first commit

task9/public_tests/01_unittest_scalers_input/test.py

@@ -0,0 +1,67 @@
+import numpy as np
+
+from numpy.testing import assert_allclose
+from scalers import StandardScaler, MinMaxScaler
+
+
+def test_scalers_0():
+	with open('scalers.py', 'r') as file:
+		lines = ' '.join(file.readlines())
+		assert 'import numpy' in lines
+		assert 'import typing' in lines
+		assert lines.count('import') == 2
+		assert 'sklearn' not in lines
+
+def test_scalers_1():
+	X_1 = np.random.uniform(-10, 20, (10, 20))
+
+	scaler = StandardScaler()
+	scaler.fit(X_1)
+	X_2 = scaler.transform(X_1)
+
+	assert type(X_2) == np.ndarray
+	assert_allclose(np.mean(X_2, axis=0), np.zeros(20), rtol=1e-05, atol=1e-08)
+	assert_allclose(np.std(X_2, axis=0), np.ones(20), rtol=1e-05, atol=1e-08)
+
+def test_scalers_2():
+	X_1 = np.random.uniform(-10, 20, (10, 20))
+
+	scaler = MinMaxScaler()
+	scaler.fit(X_1)
+	X_2 = scaler.transform(X_1)
+
+	assert type(X_2) == np.ndarray
+	assert_allclose(np.min(X_2, axis=0), np.zeros(20), rtol=1e-05, atol=1e-08)
+	assert_allclose(np.max(X_2, axis=0), np.ones(20), rtol=1e-05, atol=1e-08)
+
+def test_scalers_3():
+	X_1 = np.array([[0, 1, 0], [1, 1, 1], [0.3, 0.25, 0.5], [-0.5, -1, 4]])
+	X_2 = np.array([[0, 1, 0], [1, 1, 1], [0.3, 0.25, 0.5], [-0.5, -1, 4], [0, 0, 0], [2, -1, 0.5]])
+
+	scaler = StandardScaler()
+	scaler.fit(X_1)
+	X_3 = scaler.transform(X_2)
+	answer = np.array([[-0.36822985,  0.84119102, -0.88354126],
+					   [ 1.47291939,  0.84119102, -0.2409658 ],
+					   [ 0.18411492, -0.07647191, -0.56225353],
+					   [-1.28880447, -1.60591014,  1.68676059],
+					   [-0.36822985, -0.38235956, -0.88354126],
+					   [ 3.31406862, -1.60591014, -0.56225353]])
+	assert type(X_3) == np.ndarray
+	assert_allclose(X_3, answer, rtol=1e-05, atol=1e-08)
+
+def test_scalers_4():
+	X_1 = np.array([[0, 1, 0], [1, 1, 1], [0.3, 0.25, 0.5], [-0.5, -1, 4]])
+	X_2 = np.array([[0, 1, 0], [1, 1, 1], [0.3, 0.25, 0.5], [-0.5, -1, 4], [0, 0, 0], [2, -1, 0.5]])
+
+	scaler = MinMaxScaler()
+	scaler.fit(X_1)
+	X_3 = scaler.transform(X_2)
+	answer = np.array([[0.33333333, 1.        , 0.        ],
+					   [1.        , 1.        , 0.25      ],
+					   [0.53333333, 0.625     , 0.125     ],
+					   [0.        , 0.        , 1.        ],
+					   [0.33333333, 0.5       , 0.        ],
+					   [1.66666667, 0.        , 0.125     ]])
+	assert type(X_3) == np.ndarray
+	assert_allclose(X_3, answer, rtol=1e-05, atol=1e-08)

task9/requirements_2025_26_for_colab_small.txt

@@ -0,0 +1,22 @@
+catboost==1.2.8
+gdown==5.2.0
+h5py==3.14.0
+hyperopt==0.2.7
+ipympl==0.9.7
+ipywidgets==7.7.1
+lightgbm==4.6.0
+matplotlib-inline==0.1.7
+matplotlib==3.10.0
+numpy
+pandas==2.2.2
+pep8==1.7.1
+plotly==5.24.1
+pycodestyle==2.14.0
+pytest==8.4.1
+scikit-image==0.25.2
+scikit-learn==1.6.1
+scipy==1.16.1
+seaborn==0.13.2
+tqdm==4.67.1
+umap-learn==0.5.9.post2
+xgboost==3.0.4

task9/run.py

@@ -0,0 +1,69 @@
+#!/usr/bin/env python3
+
+from json import load, dumps
+from glob import glob
+from os import environ
+from os.path import join
+from sys import argv, exit
+
+
+def run_single_test(data_dir, output_dir):
+    from pytest import main
+    exit(main(['-vv', '-p', 'no:cacheprovider', join(data_dir, 'test.py')]))
+
+
+def check_test(data_dir):
+    pass
+
+
+def grade(data_path):
+    results = load(open(join(data_path, 'results.json')))
+    max_mark = 4
+    grade_mapping = [4]
+    total_grade = 0
+    ok_count = 0
+    for result, grade in zip(results, grade_mapping):
+        if result['status'] == 'Ok':
+            total_grade += grade
+            ok_count += 1
+    total_count = len(results)
+    description = '%02d/%02d' % (ok_count, total_count)
+    mark = total_grade / sum(grade_mapping) * max_mark
+    res = {'description': description, 'mark': mark}
+    if environ.get('CHECKER'):
+        print(dumps(res))
+    return res
+
+
+if __name__ == '__main__':
+    if environ.get('CHECKER'):
+        # Script is running in testing system
+        if len(argv) != 4:
+            print('Usage: %s mode data_dir output_dir' % argv[0])
+            exit(0)
+
+        mode = argv[1]
+        data_dir = argv[2]
+        output_dir = argv[3]
+
+        if mode == 'run_single_test':
+            run_single_test(data_dir, output_dir)
+        elif mode == 'check_test':
+            check_test(data_dir)
+        elif mode == 'grade':
+            grade(data_dir)
+    else:
+        # Script is running locally
+        if len(argv) != 3:
+            print(f'Usage: {argv[0]} test/unittest test_name')
+            exit(0)
+
+        mode = argv[1]
+        test_name = argv[2]
+        test_dir = glob(f'public_tests/[0-9][0-9]_{mode}_{test_name}_input')
+        if not test_dir:
+            print('Test not found')
+            exit(0)
+
+        from pytest import main
+        exit(main(['-vv', join(test_dir[0], 'test.py')]))

task9/scalers.py

@@ -0,0 +1,32 @@
+import numpy as np
+import typing
+
+
+class MinMaxScaler:
+    def __init__(self):
+        self.min_vals = None
+        self.max_vals = None
+
+    def fit(self, data: np.ndarray) -> None:
+        self.min_vals = np.min(data, axis=0)
+        self.max_vals = np.max(data, axis=0)
+
+        return
+
+    def transform(self, data: np.ndarray) -> np.ndarray:
+        return (data - self.min_vals) / (self.max_vals - self.min_vals)
+
+
+class StandardScaler:
+    def __init__(self):
+        self.mean_vals = None
+        self.std_vals = None
+
+    def fit(self, data: np.ndarray) -> None:
+        self.mean_vals = np.mean(data, axis=0)
+        self.std_vals = np.std(data, axis=0)
+
+        return
+
+    def transform(self, data: np.ndarray) -> np.ndarray:
+        return (data - self.mean_vals) / self.std_vals