Maria@18: # -*- coding: utf-8 -*-
Maria@18: """
Maria@18: Created on Fri Sep  1 19:11:52 2017
Maria@18: 
Maria@18: @author: mariapanteli
Maria@18: """
Maria@18: 
Maria@18: import pytest
Maria@18: 
Maria@18: import numpy as np
Maria@18: 
Maria@18: import scripts.outliers as outliers
Maria@18: 
Maria@18: 
Maria@18: def test_country_outlier_df():
Maria@18:     counts = {'a':2, 'b':3}
Maria@18:     labels = np.array(['a', 'a', 'a', 'a', 'b', 'b', 'b'])
Maria@18:     df = outliers.country_outlier_df(counts, labels, normalize=True)
Maria@18:     assert np.array_equal(df['Outliers'].get_values(), np.array([0.5, 1.0]))
Maria@18: 
Maria@18: 
Maria@18: def test_normalize_outlier_counts():
Maria@18:     outlier_counts = {'a':2, 'b':3}
Maria@18:     country_counts = {'a':4, 'b':3}
Maria@18:     outlier_counts = outliers.normalize_outlier_counts(outlier_counts, country_counts)
Maria@18:     outlier_counts_true = {'a':.5, 'b':1.}
Maria@18:     assert np.array_equal(outlier_counts, outlier_counts_true)
Maria@18: 
Maria@18: 
Maria@18: def test_get_outliers_df():
m@20:     np.random.seed(1)
m@20:     X = np.random.randn(100, 3)
m@20:     # create outliers by shifting the entries of the last 5 samples
m@20:     X[-5:, :] = X[-5:, :] + 10
m@20:     Y = np.concatenate([np.repeat('a', 95), np.repeat('b', 5)])
m@20:     df, threshold, MD = outliers.get_outliers_df(X, Y)
m@20:     # expect that items from country 'b' are detected as outliers
m@20:     assert np.array_equal(df['Outliers'].get_values(), np.array([0., 1.0]))
m@20: