def test_get_rf_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)
scores, forest = fs.get_rf_feature_scores(
x, y, mode=RuleInductionType.CLASSIFICATION, random_state=10)
self.assertEqual(len(scores), len(x.columns) - 3)
self.assertTrue(isinstance(forest, RandomForestClassifier))
self.assertRaises(ValueError,
fs.get_rf_feature_scores,
x,
y,
mode='illegal argument')
y = outcomes['deceased population region 1'][:, -1]
scores, forest = fs.get_rf_feature_scores(
x, y, mode=RuleInductionType.REGRESSION, random_state=10)
self.assertEqual(len(scores), len(x.columns) - 3)
self.assertTrue(isinstance(forest, RandomForestRegressor))
def test_get_rf_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)
scores, forest = fs.get_rf_feature_scores(x,y, mode=CLASSIFICATION,
random_state=10)
self.assertEqual(len(scores), len(x.dtype.fields))
self.assertTrue(isinstance(forest, RandomForestClassifier))
self.assertRaises(ValueError, fs.get_rf_feature_scores, x,y,
mode='illegal argument')
y = outcomes['deceased population region 1'][:,-1]
scores, forest = fs.get_rf_feature_scores(x,y, mode=REGRESSION,
random_state=10)
self.assertEqual(len(scores), len(x.dtype.fields))
self.assertTrue(isinstance(forest, RandomForestRegressor))