def test_get_univariate_feature_scores(self):
x, outcomes = utilities.load_flu_data()
def classify(data):
#get the output for deceased population
result = data['deceased population region 1']
#make an empty array of length equal to number of cases
classes = np.zeros(result.shape[0])
#if deceased population is higher then 1.000.000 people, classify as 1
classes[result[:, -1] > 1000000] = 1
return classes
y = classify(outcomes)
# f classify
scores = fs.get_univariate_feature_scores(x,
y,
score_func=F_CLASSIFICATION)
self.assertEqual(len(scores), len(x.columns) - 3)
# chi2
scores = fs.get_univariate_feature_scores(x, y, score_func=CHI2)
self.assertEqual(len(scores), len(x.columns) - 3)
# f regression
y = outcomes['deceased population region 1'][:, -1]
scores = fs.get_univariate_feature_scores(x,
y,
score_func=F_REGRESSION)
self.assertEqual(len(scores), len(x.columns) - 3)
def test_get_univariate_feature_scores(self):
x, outcomes = test_utilities.load_flu_data()
def classify(data):
#get the output for deceased population
result = data['deceased population region 1']
#make an empty array of length equal to number of cases
classes = np.zeros(result.shape[0])
#if deceased population is higher then 1.000.000 people, classify as 1
classes[result[:, -1] > 1000000] = 1
return classes
y = classify(outcomes)
# f classify
scores = fs.get_univariate_feature_scores(x,y,
score_func=F_CLASSIFICATION)
self.assertEqual(len(scores), len(x.dtype.fields))
# chi2
scores = fs.get_univariate_feature_scores(x,y, score_func=CHI2)
self.assertEqual(len(scores), len(x.dtype.fields))
# f regression
y= outcomes['deceased population region 1'][:,-1]
scores = fs.get_univariate_feature_scores(x,y, score_func=F_REGRESSION)
self.assertEqual(len(scores), len(x.dtype.fields))