klib.tests.test_describe - Code Metrics - Inspection of "add test cases for corr_mat and for missing_vals" - akanz1/klib - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Push — master ( 5df733...c3852e )

by Andreas

created 2020-04-08 08:50 UTC

klib.tests.test_describe A

↳ Parent: Project

Complexity

Total Complexity

Size/Duplication

Total Lines	98
Duplicated Lines	24.49 %

Importance

Changes

Metric	Value
eloc	70
dl	24
loc	98
rs	10
c	0
b	0
f	0
wmc	9

9 Methods

Rating	Name	Duplication	Size	Complexity
A	Test__missing_vals.setUpClass()	0	17	1
A	Test_corr_mat.test_output_type()	0	4	1
A	Test__missing_vals.test_mv_cols()	0	6	1
A	Test__missing_vals.test_mv_cols_ratio()	12	12	1
A	Test_corr_mat.test_output_shape()	0	4	1
A	Test__missing_vals.test_mv_total()	0	5	1
A	Test__missing_vals.test_mv_rows()	0	6	1
A	Test_corr_mat.setUpClass()	0	9	1
A	Test__missing_vals.test_mv_rows_ratio()	12	12	1

How to fix Duplicated Code

import numpy as np
import pandas as pd
import unittest
from klib.describe import _missing_vals, corr_mat

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


class Test__missing_vals(unittest.TestCase):

    @classmethod
    def setUpClass(cls):
        cls.data_mv_df = pd.DataFrame([[1, np.nan, 3, 4],
                                       [None, 4, 5, None],
                                       ['a', 'b', pd.NA, 'd'],
                                       [True, False, 7, pd.NaT]],
                                      columns=['Col1', 'Col2', 'Col3', 'Col4'])

        cls.data_mv_array = np.array([[1, np.nan, 3, 4],
                                      [None, 4, 5, None],
                                      ['a', 'b', pd.NA, 'd'],
                                      [True, False, 7, pd.NaT]])

        cls.data_mv_list = [[1, np.nan, 3, 4],
                            [None, 4, 5, None],
                            ['a', 'b', pd.NA, 'd'],
                            [True, False, 7, pd.NaT]]

    def test_mv_total(self):
        # Test total missing values
        self.assertAlmostEqual(_missing_vals(self.data_mv_df)['mv_total'], 5)
        self.assertAlmostEqual(_missing_vals(self.data_mv_array)['mv_total'], 5)
        self.assertAlmostEqual(_missing_vals(self.data_mv_list)['mv_total'], 5)

    def test_mv_rows(self):
        # Test missing values for each row
        self.assertAlmostEqual(_missing_vals(self.data_mv_df)['mv_rows'][0], 1)
        self.assertAlmostEqual(_missing_vals(self.data_mv_df)['mv_rows'][1], 2)
        self.assertAlmostEqual(_missing_vals(self.data_mv_df)['mv_rows'][2], 1)
        self.assertAlmostEqual(_missing_vals(self.data_mv_df)['mv_rows'][3], 1)

    def test_mv_cols(self):
        # Test missing values for each column
        self.assertAlmostEqual(_missing_vals(self.data_mv_df)['mv_cols'][0], 1)
        self.assertAlmostEqual(_missing_vals(self.data_mv_df)['mv_cols'][1], 1)
        self.assertAlmostEqual(_missing_vals(self.data_mv_df)['mv_cols'][2], 1)
        self.assertAlmostEqual(_missing_vals(self.data_mv_df)['mv_cols'][3], 2)

    def test_mv_rows_ratio(self):

        # Test missing values ratio for each row
        self.assertAlmostEqual(_missing_vals(self.data_mv_df)['mv_rows_ratio'][0], 0.25)
        self.assertAlmostEqual(_missing_vals(self.data_mv_df)['mv_rows_ratio'][1], 0.5)
        self.assertAlmostEqual(_missing_vals(self.data_mv_df)['mv_rows_ratio'][2], 0.25)
        self.assertAlmostEqual(_missing_vals(self.data_mv_df)['mv_rows_ratio'][3], 0.25)

        # Test if missing value ratio is between 0 and 1
        self.assertTrue(0 <= _missing_vals(self.data_mv_df)['mv_rows_ratio'][0] <= 1)
        self.assertTrue(0 <= _missing_vals(self.data_mv_df)['mv_rows_ratio'][1] <= 1)
        self.assertTrue(0 <= _missing_vals(self.data_mv_df)['mv_rows_ratio'][2] <= 1)
        self.assertTrue(0 <= _missing_vals(self.data_mv_df)['mv_rows_ratio'][3] <= 1)

    def test_mv_cols_ratio(self):

        # Test missing values ratio for each row
        self.assertAlmostEqual(_missing_vals(self.data_mv_df)['mv_cols_ratio'][0], 0.25)
        self.assertAlmostEqual(_missing_vals(self.data_mv_df)['mv_cols_ratio'][1], 0.25)
        self.assertAlmostEqual(_missing_vals(self.data_mv_df)['mv_cols_ratio'][2], 0.25)
        self.assertAlmostEqual(_missing_vals(self.data_mv_df)['mv_cols_ratio'][3], 0.5)

        # Test if missing value ratio is between 0 and 1
        self.assertTrue(0 <= _missing_vals(self.data_mv_df)['mv_cols_ratio'][0] <= 1)
        self.assertTrue(0 <= _missing_vals(self.data_mv_df)['mv_cols_ratio'][1] <= 1)
        self.assertTrue(0 <= _missing_vals(self.data_mv_df)['mv_cols_ratio'][2] <= 1)
        self.assertTrue(0 <= _missing_vals(self.data_mv_df)['mv_cols_ratio'][3] <= 1)


class Test_corr_mat(unittest.TestCase):

    @classmethod
    def setUpClass(cls):
        cls.data_corr = pd.DataFrame([[1, 0, 3j, 4],
                                      [3, 4, 5, 6],
                                      ['a', 'b', pd.NA, 'd'],
                                      [5, False, np.nan, pd.NaT]],
                                     columns=['Col1', 'Col2', 'Col3', 'Col4'])

        cls.data_corr_list = [1, 2, -3, 4j, 5, 0]

    def test_output_type(self):
        # Test conversion from pd.io.formats.style.Styler to pd.core.frame.DataFrame
        self.assertTrue(type(corr_mat(self.data_corr)), type(pd.DataFrame))
        self.assertTrue(type(corr_mat(self.data_corr_list)), type(pd.DataFrame))

    def test_output_shape(self):
        # Test for output of equal dimensions
        self.assertEqual(corr_mat(self.data_corr).data.shape[0], corr_mat(self.data_corr).data.shape[1])
        self.assertEqual(corr_mat(self.data_corr_list).data.shape[0], corr_mat(self.data_corr_list).data.shape[1])


1		import numpy as np
2		import pandas as pd
3		import unittest
4		from klib.describe import _missing_vals, corr_mat
5
6		if __name__ == '__main__':
7		unittest.main()
8
9
10		class Test__missing_vals(unittest.TestCase):
11
12		@classmethod
13		def setUpClass(cls):
14		cls.data_mv_df = pd.DataFrame([[1, np.nan, 3, 4],
15		[None, 4, 5, None],
16		['a', 'b', pd.NA, 'd'],
17		[True, False, 7, pd.NaT]],
18		columns=['Col1', 'Col2', 'Col3', 'Col4'])
19
20		cls.data_mv_array = np.array([[1, np.nan, 3, 4],
21		[None, 4, 5, None],
22		['a', 'b', pd.NA, 'd'],
23		[True, False, 7, pd.NaT]])
24
25		cls.data_mv_list = [[1, np.nan, 3, 4],
26		[None, 4, 5, None],
27		['a', 'b', pd.NA, 'd'],
28		[True, False, 7, pd.NaT]]
29
30		def test_mv_total(self):
31		# Test total missing values
32		self.assertAlmostEqual(_missing_vals(self.data_mv_df)['mv_total'], 5)
33		self.assertAlmostEqual(_missing_vals(self.data_mv_array)['mv_total'], 5)
34		self.assertAlmostEqual(_missing_vals(self.data_mv_list)['mv_total'], 5)
35
36		def test_mv_rows(self):
37		# Test missing values for each row
38		self.assertAlmostEqual(_missing_vals(self.data_mv_df)['mv_rows'][0], 1)
39		self.assertAlmostEqual(_missing_vals(self.data_mv_df)['mv_rows'][1], 2)
40		self.assertAlmostEqual(_missing_vals(self.data_mv_df)['mv_rows'][2], 1)
41		self.assertAlmostEqual(_missing_vals(self.data_mv_df)['mv_rows'][3], 1)
42
43		def test_mv_cols(self):
44		# Test missing values for each column
45		self.assertAlmostEqual(_missing_vals(self.data_mv_df)['mv_cols'][0], 1)
46		self.assertAlmostEqual(_missing_vals(self.data_mv_df)['mv_cols'][1], 1)
47		self.assertAlmostEqual(_missing_vals(self.data_mv_df)['mv_cols'][2], 1)
48		self.assertAlmostEqual(_missing_vals(self.data_mv_df)['mv_cols'][3], 2)
49
50	View Code Duplication	def test_mv_rows_ratio(self):
		0 ignored issues – show Duplication introduced 2020-04-08 08:52 UTC by Report Bug Copy Issue Report This code seems to be duplicated in your project. Loading history...
51		# Test missing values ratio for each row
52		self.assertAlmostEqual(_missing_vals(self.data_mv_df)['mv_rows_ratio'][0], 0.25)
53		self.assertAlmostEqual(_missing_vals(self.data_mv_df)['mv_rows_ratio'][1], 0.5)
54		self.assertAlmostEqual(_missing_vals(self.data_mv_df)['mv_rows_ratio'][2], 0.25)
55		self.assertAlmostEqual(_missing_vals(self.data_mv_df)['mv_rows_ratio'][3], 0.25)
56
57		# Test if missing value ratio is between 0 and 1
58		self.assertTrue(0 <= _missing_vals(self.data_mv_df)['mv_rows_ratio'][0] <= 1)
59		self.assertTrue(0 <= _missing_vals(self.data_mv_df)['mv_rows_ratio'][1] <= 1)
60		self.assertTrue(0 <= _missing_vals(self.data_mv_df)['mv_rows_ratio'][2] <= 1)
61		self.assertTrue(0 <= _missing_vals(self.data_mv_df)['mv_rows_ratio'][3] <= 1)
62
63	View Code Duplication	def test_mv_cols_ratio(self):
		0 ignored issues – show Duplication introduced 2020-04-08 08:52 UTC by Report Bug Copy Issue Report This code seems to be duplicated in your project. Loading history...
64		# Test missing values ratio for each row
65		self.assertAlmostEqual(_missing_vals(self.data_mv_df)['mv_cols_ratio'][0], 0.25)
66		self.assertAlmostEqual(_missing_vals(self.data_mv_df)['mv_cols_ratio'][1], 0.25)
67		self.assertAlmostEqual(_missing_vals(self.data_mv_df)['mv_cols_ratio'][2], 0.25)
68		self.assertAlmostEqual(_missing_vals(self.data_mv_df)['mv_cols_ratio'][3], 0.5)
69
70		# Test if missing value ratio is between 0 and 1
71		self.assertTrue(0 <= _missing_vals(self.data_mv_df)['mv_cols_ratio'][0] <= 1)
72		self.assertTrue(0 <= _missing_vals(self.data_mv_df)['mv_cols_ratio'][1] <= 1)
73		self.assertTrue(0 <= _missing_vals(self.data_mv_df)['mv_cols_ratio'][2] <= 1)
74		self.assertTrue(0 <= _missing_vals(self.data_mv_df)['mv_cols_ratio'][3] <= 1)
75
76
77		class Test_corr_mat(unittest.TestCase):
78
79		@classmethod
80		def setUpClass(cls):
81		cls.data_corr = pd.DataFrame([[1, 0, 3j, 4],
82		[3, 4, 5, 6],
83		['a', 'b', pd.NA, 'd'],
84		[5, False, np.nan, pd.NaT]],
85		columns=['Col1', 'Col2', 'Col3', 'Col4'])
86
87		cls.data_corr_list = [1, 2, -3, 4j, 5, 0]
88
89		def test_output_type(self):
90		# Test conversion from pd.io.formats.style.Styler to pd.core.frame.DataFrame
91		self.assertTrue(type(corr_mat(self.data_corr)), type(pd.DataFrame))
92		self.assertTrue(type(corr_mat(self.data_corr_list)), type(pd.DataFrame))
93
94		def test_output_shape(self):
95		# Test for output of equal dimensions
96		self.assertEqual(corr_mat(self.data_corr).data.shape[0], corr_mat(self.data_corr).data.shape[1])
97		self.assertEqual(corr_mat(self.data_corr_list).data.shape[0], corr_mat(self.data_corr_list).data.shape[1])
98

akanz1 / klib

GitHub Access Token became invalid

Push — master ( 5df733...c3852e )

klib.tests.test_describe A

Complexity

Size/Duplication

Importance

9 Methods

How to fix Duplicated Code

Duplicated Code

Duplication Side-by-Side

Filter issues like