def test_normalize_one_of_n(self):
# find the Iris data set
irisFile = os.path.dirname(os.path.realpath(__file__))
irisFile = os.path.abspath(irisFile + "../../../datasets/iris.csv")
norm = Normalize()
result = norm.load_csv(irisFile)
self.assertEqual(len(norm.column_map), 5)
self.assertEqual(len(norm.header), 5)
self.assertEqual(norm.header[0], "sepal_length")
self.assertEqual(norm.header[1], "sepal_width")
self.assertEqual(norm.header[2], "petal_length")
self.assertEqual(norm.header[3], "petal_width")
self.assertEqual(norm.header[4], "class")
self.assertTrue("sepal_length" in norm.column_map)
self.assertTrue("sepal_width" in norm.column_map)
self.assertTrue("petal_length" in norm.column_map)
self.assertTrue("petal_width" in norm.column_map)
self.assertTrue("class" in norm.column_map)
self.assertEqual(norm.resolve_column("sepal_length"), 0)
self.assertEqual(norm.resolve_column("sepal_width"), 1)
self.assertEqual(norm.resolve_column("petal_length"), 2)
self.assertEqual(norm.resolve_column("petal_width"), 3)
self.assertEqual(norm.resolve_column("class"), 4)
self.assertRaises(AIFHError, norm.resolve_column, 6)
self.assertRaises(AIFHError, norm.resolve_column, "unknown")
for i in range(0, 4):
norm.make_col_numeric(result, i)
norm.norm_col_range(result, i, -1, 1)
self.assertAlmostEqual(result[0][0], -0.555, 2)
self.assertAlmostEqual(result[0][1], 0.249, 2)
self.assertAlmostEqual(result[0][2], -0.864, 2)
self.assertAlmostEqual(result[0][3], -0.916, 2)
classes = norm.build_class_map(result, 4)
norm.norm_col_one_of_n(result, 4, classes, -1, 1)
self.assertEqual(len(classes), 3)
# Extract the original iris species so we can display during the final validation.
ideal_species = [row[4] for row in iris_work]
# Setup the first four fields to "range normalize" between -1 and 1.
for i in range(0, 4):
norm.make_col_numeric(iris_work, i)
norm.norm_col_range(iris_work, i, 0, 1)
# Discover all of the classes for column #4, the iris species.
classes = norm.build_class_map(iris_work, 4)
inv_classes = {v: k for k, v in classes.items()}
# Normalize iris species using one-of-n.
# We could have used equilateral as well. For an example of equilateral, see the example_nm_iris example.
norm.norm_col_one_of_n(iris_work, 4, classes, 0, 1)
# Prepare training data. Separate into input and ideal.
training = np.array(iris_work)
training_input = training[:, 0:4]
training_ideal = training[:, 4:7]
# Create an RBF network. There are four inputs and two outputs.
# There are also five RBF functions used internally.
# You can experiment with different numbers of internal RBF functions.
# However, the input and output must match the data set.
network = RbfNetwork(4, 4, 3)
network.reset()
def score_funct(x):
# Extract the original iris species so we can display during the final validation.
ideal_species = [row[4] for row in iris_work]
# Setup the first four fields to "range normalize" between -1 and 1.
for i in range(0, 4):
norm.make_col_numeric(iris_work, i)
norm.norm_col_range(iris_work, i, 0, 1)
# Discover all of the classes for column #4, the iris species.
classes = norm.build_class_map(iris_work, 4)
inv_classes = {v: k for k, v in classes.items()}
# Normalize iris species using one-of-n.
# We could have used equilateral as well. For an example of equilateral, see the example_nm_iris example.
norm.norm_col_one_of_n(iris_work, 4, classes, 0, 1)
# Prepare training data. Separate into input and ideal.
training = np.array(iris_work)
training_input = training[:, 0:4]
training_ideal = training[:, 4:7]
# Create an RBF network. There are four inputs and two outputs.
# There are also five RBF functions used internally.
# You can experiment with different numbers of internal RBF functions.
# However, the input and output must match the data set.
network = RbfNetwork(4, 4, 3)
network.reset()
def score_funct(x):
abaloneFile = os.path.abspath(abaloneFile + "../../datasets/abalone.csv")
# Normalize abalone file.
norm = Normalize()
abalone_work = norm.load_csv(abaloneFile)
# Make all columns beyond col #1 numeric.
for i in range(1, 9):
norm.make_col_numeric(abalone_work, i)
# Discover all of the classes for column #1, the gender.
classes = norm.build_class_map(abalone_work, 0)
# Normalize gender one-of-n encoding.
norm.norm_col_one_of_n(abalone_work, 0, classes, 0, 1)
# Separate into input and ideal.
training = np.array(abalone_work)
training_input = training[:, 0:10]
training_ideal = training[:, 10:11]
coeff = multi_linear_regression(training_input, training_ideal)
print("Solution coefficients: " + str(coeff))
# Evaluate.
for i in range(0, len(training_input)):
row = training_input[i]
y = calc_linear_regression(coeff, row)
abaloneFile = os.path.abspath(abaloneFile + "../../datasets/abalone.csv")
# Normalize abalone file.
norm = Normalize()
abalone_work = norm.load_csv(abaloneFile)
# Make all columns beyond col #1 numeric.
for i in range(1, 9):
norm.make_col_numeric(abalone_work, i)
# Discover all of the classes for column #1, the gender.
classes = norm.build_class_map(abalone_work, 0)
# Normalize gender one-of-n encoding.
norm.norm_col_one_of_n(abalone_work, 0, classes, 0, 1)
# Separate into input and ideal.
training = np.array(abalone_work)
training_input = training[:, 0:10]
training_ideal = training[:, 10:11]
coeff = multi_linear_regression(training_input, training_ideal)
print("Solution coefficients: " + str(coeff))
# Evaluate.
for i in range(0, len(training_input)):
row = training_input[i]
y = calc_linear_regression(coeff, row)
