def test_retrieve_nonexistent_file(self):
fake_file = 'nonexistentfile.data'
r = Retriever(fake_file)
with self.assertRaises(errors.RetrieverError):
r.load()
def test_split_target(self, data, target_column, expected_data,
expected_target):
r = Retriever('nonexistentfile.data')
r._data = np.array(data)
actual_data, actual_target = r.split_target(target_column).retrieve()
testing.assert_array_equal(actual_data, np.array(expected_data))
testing.assert_array_equal(expected_target, np.array(expected_target))
def _load_data(self):
r = Retriever('../../datasets/breast-cancer/wdbc.data', delimiter=',')
r.split_column(0) # Remove ids.
# Split target from data and retrieve both.
# Target feature is actually located in the 2nd column, but considering
# we had the ids removed, it's now in the 1st one.
self.data, self.target = r.split_target(0).retrieve()
self.data = self.data.astype(float)
self.feature_names = ['radius', 'texture', 'perimeter']
def _load_data(self):
r = Retriever('../../datasets/diabetes/pima-indians-diabetes.data',
delimiter=',')
self.data, self.target = r.split_target().retrieve()
self.feature_names = [
'Number of times pregnant', 'Plasma glucose concentration',
'Diastolic blood pressure (mm Hg)'
]
self.displayer.colors = [plt.cm.viridis]
def test_retrieve_brainwave(self):
retriever = Retriever('datasets/brainwave/plrx.txt', target_column=-1)
data, target = retriever.load().split_target().retrieve()
# Assert number of samples.
self.assertEqual(182, len(data))
# Assert number of features.
self.assertEqual(12, len(data[1]))
# Assert number of samples in target array.
self.assertEqual(182, len(target))
def test_display_dimensions(self):
data_dir = 'datasets/'
data_set = 'glass/glass.data'
file = os.path.join(data_dir, data_set)
print('Displaying data set {%s} in the Rn' % file)
glass = Retriever(file, delimiter=',')
# Glass has the samples' ids in the first column.
glass.split_column(0)
# Additionally, its last column represents the target feature.
glass.split_target()
data, c = glass.retrieve()
reduced_data = algorithms.Isomap(data, e=20).run()
d = Displayer(title=data_set)
# Scatter all dimensions (3-by-3), using as many graphs as necessary.
for begin in range(0, glass.features_count, 3):
end = min(glass.features_count, begin + 3)
d.load(data[:, begin:end],
color=c,
title='Dimensions: d e [%i, %i]' % (begin + 1, end))
d \
.load('Reduced glass data-set', reduced_data, c) \
.show()
def load_data(self):
self.data, self.target = Retriever(
self.file, delimiter=',').split_target().retrieve()
self.original_data = self.data
self.displayer \
.load(self.data[:, 1:4], self.target) \
.save('datasets/spam') \
.dispose()
print('Data set size: %.2fKB' % (self.data.nbytes / 1024))
print('shape: %s' % str(self.data.shape))
def _run(self):
# the data and marking that the data is delimited by commas.
r = Retriever(self.data_set_file, delimiter=',')
data, glass_type = r.split_target().retrieve()
labels = [
'\nAge', '\nGender', '\nTotal Bilirubin (TB)',
'\nDirect Bilirubin (DB)', '\nAlkaline Phosphotase (Alk.)',
'\nAlamine Aminotransferase (Sgpt)',
'\nAspartate Aminotransferase (Sgot)', '\nTotal Protiens (TP)',
'\nAlbumin (ALB)', '\nRatio Albumin and Globulin Ratio (A/G)'
]
for i in range(0, data.shape[1], 3):
self.displayer.load(data[:, i:i + 3],
glass_type,
axis_labels=labels[i:i + 3])
print('Correlation matrix:')
print(np.corrcoef(data, rowvar=0))
self.displayer.save('displaying_ilpd')
def _load_data(self):
r = Retriever(self.file, delimiter=',')
r.split_column(0) # Remove ids.
self.data, self.target = r.split_target().retrieve()
self.original_data = self.data