def test_summary3(self):
d1 = [random.random() * 100 for _ in range(20)]
d2 = d1.copy()
d2[0] = None
table1 = pd.DataFrame({'d1': d1, 'd2': d2})
input_cols = ['d1', 'd2']
outtable1 = statistic_summary(
table1,
input_cols=input_cols,
statistics=['avg', 'percentile', 'trimmed_mean'],
percentile_amounts=[0.5, None],
trimmed_mean_amounts=[0.1, None, 0.2])['out_table']
print(outtable1)
def test_summary2(self):
d1 = [
2.0, 3.0, 5.0, 7.0, 11.0, 13.0, 17.0, 19.0, 23.0, 29.0, 31.0, 37.0,
43.0, 47.0
]
d2 = [
2.5, 3.0, 5.0, 7.0, None, 13.0, 17.0, 19.0, 23.0, 29.0, 31.0, 37.0,
43.0, 46.5
]
d3 = [
2.0, 3.0, 5.0, 7.0, None, 13.0, 17.0, 19.0, 23.0, 29.0, 31.0, 37.0,
43.0, 47.0
]
t1 = pd.DataFrame({'d1': d1, 'd2': d2, 'd3': d3})
print(t1)
input_cols = ['d2', 'd3']
pa_list = [0.25, 0.25]
ta_list = [0.20, 0.20]
out1 = statistic_summary(t1, input_cols, ['max', 'min'])
print(out1['out_table'])
def test(self):
stats = [
'max', 'min', 'range', 'sum', 'avg', 'variance', 'stddev',
'skewness', 'kurtosis', 'nrow', 'num_of_value', 'null_count',
'median', 'q1', 'q3', 'iqr', 'percentile', 'trimmed_mean'
]
pa_list = [0.25, 0.25]
ta_list = [0.20, 0.20]
out = statistic_summary(self.testdata,
input_cols=['d1', 'd2'],
statistics=stats,
percentile_amounts=pa_list,
trimmed_mean_amounts=ta_list,
group_by=['d3'])
np.testing.assert_array_almost_equal(
list(out['out_table'].values[0][2:]), [
43.0, 2.0, 41.0, 132.0, 18.857142857142858, 214.80952380952385,
14.65638167521315, 0.456945126469852, -0.9637153614645078, 7,
7, 0, 17.0, 8.0, 27.0, 19.0, 2.045, 17.4
], 10)
np.testing.assert_array_almost_equal(
list(out['out_table'].values[1][2:]), [
43.0, 2.5, 40.5, 121.5, 20.25, 239.775, 15.484669838262617,
np.nan, np.nan, 7, 6, 1, 20.0, np.nan, np.nan, np.nan, np.nan,
23.8
], 10)
np.testing.assert_array_almost_equal(
list(out['out_table'].values[2][2:]), [
47.0, 3.0, 44.0, 155.0, 22.142857142857142, 262.4761904761905,
16.201116951500303, 0.325040658885993, -1.2313300865139738, 7,
7, 0, 19.0, 10.0, 33.0, 23.0, 3.06, 21.0
], 10)
np.testing.assert_array_almost_equal(
list(out['out_table'].values[3][2:]), [
46.5, 3.0, 43.5, 154.5, 22.071428571428573, 258.36904761904765,
16.073862249597873, 0.307849200412774, -1.2556904973476417, 7,
7, 0, 19.0, 10.0, 33.0, 23.0, 3.06, 21.0
], 10)