def test_lasso(self):
# ToDo: add additional tests
# get some test data
X = ht.load_hdf5(
os.path.join(os.getcwd(), "heat/datasets/data/diabetes.h5"),
dataset="x",
device=ht_device,
split=0,
)
y = ht.load_hdf5(
os.path.join(os.getcwd(), "heat/datasets/data/diabetes.h5"),
dataset="y",
device=ht_device,
split=0,
)
# normalize dataset
X = X / ht.sqrt((ht.mean(X ** 2, axis=0)))
m, n = X.shape
# HeAT lasso instance
estimator = ht.regression.lasso.Lasso(max_iter=100, tol=None)
# check whether the results are correct
self.assertEqual(estimator.lam, 0.1)
self.assertTrue(estimator.theta is None)
self.assertTrue(estimator.n_iter is None)
self.assertEqual(estimator.max_iter, 100)
self.assertEqual(estimator.coef_, None)
self.assertEqual(estimator.intercept_, None)
estimator.fit(X, y)
# check whether the results are correct
self.assertEqual(estimator.lam, 0.1)
self.assertIsInstance(estimator.theta, ht.DNDarray)
self.assertEqual(estimator.n_iter, 100)
self.assertEqual(estimator.max_iter, 100)
self.assertEqual(estimator.coef_.shape, (n - 1, 1))
self.assertEqual(estimator.intercept_.shape, (1,))
yest = estimator.predict(X)
# check whether the results are correct
self.assertIsInstance(yest, ht.DNDarray)
self.assertEqual(yest.shape, (m, 1))
with self.assertRaises(ValueError):
estimator.fit(X, ht.zeros((3, 3, 3)))
with self.assertRaises(ValueError):
estimator.fit(ht.zeros((3, 3, 3)), ht.zeros((3, 3)))
def test_fit_one_hot(self,):
x = ht.load_hdf5("heat/datasets/iris.h5", dataset="data")
# keys as label array
keys = []
for i in range(50):
keys.append(0)
for i in range(50, 100):
keys.append(1)
for i in range(100, 150):
keys.append(2)
labels = ht.array(keys, split=0)
# keys as one_hot
keys = []
for i in range(50):
keys.append([1, 0, 0])
for i in range(50, 100):
keys.append([0, 1, 0])
for i in range(100, 150):
keys.append([0, 0, 1])
y = ht.array(keys)
knn = KNeighborsClassifier(n_neighbors=5)
knn.fit(x, y)
result = knn.predict(x)
self.assertTrue(ht.is_estimator(knn))
self.assertTrue(ht.is_classifier(knn))
self.assertIsInstance(result, ht.DNDarray)
self.assertEqual(result.shape, labels.shape)
def test_load_hdf5(self):
# HDF5 support is optional
if not ht.io.supports_hdf5():
return
# default parameters
iris = ht.load_hdf5(self.HDF5_PATH,
self.HDF5_DATASET,
device=ht_device)
self.assertIsInstance(iris, ht.DNDarray)
self.assertEqual(iris.shape, self.IRIS.shape)
self.assertEqual(iris.dtype, ht.float32)
self.assertEqual(iris._DNDarray__array.dtype, torch.float32)
self.assertTrue((self.IRIS == iris._DNDarray__array).all())
# positive split axis
iris = ht.load_hdf5(self.HDF5_PATH,
self.HDF5_DATASET,
split=0,
device=ht_device)
self.assertIsInstance(iris, ht.DNDarray)
self.assertEqual(iris.shape, self.IRIS.shape)
self.assertEqual(iris.dtype, ht.float32)
lshape = iris.lshape
self.assertLessEqual(lshape[0], self.IRIS.shape[0])
self.assertEqual(lshape[1], self.IRIS.shape[1])
# negative split axis
iris = ht.load_hdf5(self.HDF5_PATH, self.HDF5_DATASET, split=-1)
self.assertIsInstance(iris, ht.DNDarray)
self.assertEqual(iris.shape, self.IRIS.shape)
self.assertEqual(iris.dtype, ht.float32)
lshape = iris.lshape
self.assertEqual(lshape[0], self.IRIS.shape[0])
self.assertLessEqual(lshape[1], self.IRIS.shape[1])
# different data type
iris = ht.load_hdf5(self.HDF5_PATH,
self.HDF5_DATASET,
dtype=ht.int8,
device=ht_device)
self.assertIsInstance(iris, ht.DNDarray)
self.assertEqual(iris.shape, self.IRIS.shape)
self.assertEqual(iris.dtype, ht.int8)
self.assertEqual(iris._DNDarray__array.dtype, torch.int8)
def test_load_hdf5_exception(self):
# HDF5 support is optional
if not ht.io.supports_hdf5():
return
# improper argument types
with self.assertRaises(TypeError):
ht.load_hdf5(1, "data")
with self.assertRaises(TypeError):
ht.load_hdf5("iris.h5", 1)
with self.assertRaises(TypeError):
ht.load_hdf5("iris.h5", dataset="data", split=1.0)
# file or dataset does not exist
with self.assertRaises(IOError):
ht.load_hdf5("foo.h5", dataset="data")
with self.assertRaises(IOError):
ht.load_hdf5("iris.h5", dataset="foo")
def test_fit_iris(self):
# get some test data
iris = ht.load_hdf5(
os.path.join(os.getcwd(), 'heat/datasets/data/iris.h5'), 'data')
# fit the clusters
k = 3
kmeans = ht.ml.cluster.KMeans(n_clusters=k)
centroids = kmeans.fit(iris)
# check whether the results are correct
self.assertIsInstance(centroids, ht.tensor)
self.assertEqual(centroids.shape, (1, iris.shape[1], k))
def test_split_zero(self):
X = ht.load_hdf5("heat/datasets/iris.h5", dataset="data", split=0)
# Generate keys for the iris.h5 dataset
keys = []
for i in range(50):
keys.append(0)
for i in range(50, 100):
keys.append(1)
for i in range(100, 150):
keys.append(2)
Y = ht.array(keys, split=0)
knn = KNN(X, Y, 5)
result = knn.predict(X)
self.assertIsInstance(result, ht.DNDarray)
self.assertEqual(result.shape, Y.shape)
def test_split_none(self):
x = ht.load_hdf5("heat/datasets/iris.h5", dataset="data")
# generate keys for the iris.h5 dataset
keys = []
for i in range(50):
keys.append(0)
for i in range(50, 100):
keys.append(1)
for i in range(100, 150):
keys.append(2)
y = ht.array(keys)
knn = KNeighborsClassifier(n_neighbors=5)
knn.fit(x, y)
result = knn.predict(x)
self.assertTrue(ht.is_estimator(knn))
self.assertTrue(ht.is_classifier(knn))
self.assertIsInstance(result, ht.DNDarray)
self.assertEqual(result.shape, y.shape)
def test_split_none(self):
X = ht.load_hdf5("heat/datasets/iris.h5", dataset="data")
# Generate keys for the iris.h5 dataset
keys = []
for i in range(50):
keys.append(0)
for i in range(50, 100):
keys.append(1)
for i in range(100, 150):
keys.append(2)
Y = ht.array(keys)
knn = KNN(X, Y, 5)
result = knn.predict(X)
self.assertTrue(ht.is_estimator(knn))
self.assertTrue(ht.is_classifier(knn))
self.assertIsInstance(result, ht.DNDarray)
self.assertEqual(result.shape, Y.shape)
def test_lasso(self):
# ToDo: add additional tests
# get some test data
X = ht.load_hdf5(os.path.join(os.getcwd(),
"heat/datasets/data/diabetes.h5"),
dataset="x")
y = ht.load_hdf5(os.path.join(os.getcwd(),
"heat/datasets/data/diabetes.h5"),
dataset="y")
# normalize dataset
X = X / ht.sqrt((ht.mean(X**2, axis=0)))
m, n = X.shape
# HeAT lasso instance
estimator = ht.core.regression.lasso.HeatLasso(max_iter=100,
tol=None)
# check whether the results are correct
self.assertEqual(estimator.lam, 0.1)
self.assertTrue(estimator.theta is None)
self.assertTrue(estimator.n_iter is None)
self.assertEqual(estimator.max_iter, 100)
self.assertEqual(estimator.coef_, None)
self.assertEqual(estimator.intercept_, None)
estimator.fit(X, y)
# check whether the results are correct
self.assertEqual(estimator.lam, 0.1)
self.assertIsInstance(estimator.theta, ht.DNDarray)
self.assertEqual(estimator.n_iter, 100)
self.assertEqual(estimator.max_iter, 100)
self.assertEqual(estimator.coef_.shape, (n - 1, 1))
self.assertEqual(estimator.intercept_.shape, (1, ))
yest = estimator.predict(X)
# check whether the results are correct
self.assertIsInstance(yest, ht.DNDarray)
self.assertEqual(yest.shape, (m, ))
X = ht.load_hdf5(os.path.join(os.getcwd(),
"heat/datasets/data/diabetes.h5"),
dataset="x")
y = ht.load_hdf5(os.path.join(os.getcwd(),
"heat/datasets/data/diabetes.h5"),
dataset="y")
# Now the same stuff again in PyTorch
X = torch.tensor(X._DNDarray__array)
y = torch.tensor(y._DNDarray__array)
# normalize dataset
X = X / torch.sqrt((torch.mean(X**2, 0)))
m, n = X.shape
estimator = ht.core.regression.lasso.PytorchLasso(max_iter=100,
tol=None)
# check whether the results are correct
self.assertEqual(estimator.lam, 0.1)
self.assertTrue(estimator.theta is None)
self.assertTrue(estimator.n_iter is None)
self.assertEqual(estimator.max_iter, 100)
self.assertEqual(estimator.coef_, None)
self.assertEqual(estimator.intercept_, None)
estimator.fit(X, y)
# check whether the results are correct
self.assertEqual(estimator.lam, 0.1)
self.assertIsInstance(estimator.theta, torch.Tensor)
self.assertEqual(estimator.n_iter, 100)
self.assertEqual(estimator.max_iter, 100)
self.assertEqual(estimator.coef_.shape, (n - 1, 1))
self.assertEqual(estimator.intercept_.shape, (1, ))
yest = estimator.predict(X)
# check whether the results are correct
self.assertIsInstance(yest, torch.Tensor)
self.assertEqual(yest.shape, (m, ))
X = ht.load_hdf5(os.path.join(os.getcwd(),
"heat/datasets/data/diabetes.h5"),
dataset="x")
y = ht.load_hdf5(os.path.join(os.getcwd(),
"heat/datasets/data/diabetes.h5"),
dataset="y")
# Now the same stuff again in PyTorch
X = X._DNDarray__array.numpy()
y = y._DNDarray__array.numpy()
# normalize dataset
X = X / np.sqrt((np.mean(X**2, axis=0, keepdims=True)))
m, n = X.shape
estimator = ht.core.regression.lasso.NumpyLasso(max_iter=100,
tol=None)
# check whether the results are correct
self.assertEqual(estimator.lam, 0.1)
self.assertTrue(estimator.theta is None)
self.assertTrue(estimator.n_iter is None)
self.assertEqual(estimator.max_iter, 100)
self.assertEqual(estimator.coef_, None)
self.assertEqual(estimator.intercept_, None)
estimator.fit(X, y)
# check whether the results are correct
self.assertEqual(estimator.lam, 0.1)
self.assertIsInstance(estimator.theta, np.ndarray)
self.assertEqual(estimator.n_iter, 100)
self.assertEqual(estimator.max_iter, 100)
self.assertEqual(estimator.coef_.shape, (n - 1, 1))
self.assertEqual(estimator.intercept_.shape, (1, ))
yest = estimator.predict(X)
# check whether the results are correct
self.assertIsInstance(yest, np.ndarray)
self.assertEqual(yest.shape, (m, ))
import sys
import os
import random
# Fix python path if run from terminal
curdir = os.path.dirname(os.path.abspath(__file__))
sys.path.insert(0, os.path.abspath(os.path.join(curdir, "../../")))
import heat as ht
from heat.classification.knn import KNN
# Load dataset from hdf5 file
X = ht.load_hdf5("../../heat/datasets/data/iris.h5", dataset="data", split=0)
# Generate keys for the iris.h5 dataset
keys = []
for i in range(50):
keys.append(0)
for i in range(50, 100):
keys.append(1)
for i in range(100, 150):
keys.append(2)
Y = ht.array(keys, split=0)
def calculate_accuracy(new_y, verification_y):
"""
Calculates the accuracy of classification/clustering-algorithms.
Note this only works with integer/discrete classes. For algorithms that give approximations an error function is
required.
import torch
import sys
sys.path.append("../../")
import heat as ht
from matplotlib import pyplot as plt
from sklearn import datasets
import heat.ml.regression.lasso as lasso
import plotfkt
# read scikit diabetes data set
diabetes = datasets.load_diabetes()
# load diabetes dataset from hdf5 file
X = ht.load_hdf5("../../heat/datasets/data/diabetes.h5", dataset="x", split=0)
y = ht.load_hdf5("../../heat/datasets/data/diabetes.h5", dataset="y", split=0)
# normalize dataset #DoTO this goes into the lasso fit routine soon as issue #106 is solved
X = X / ht.sqrt((ht.mean(X**2, axis=0)))
# HeAT lasso instance
estimator = lasso.HeatLasso(max_iter=100)
# List lasso model parameters
theta_list = list()
# Range of lambda values
lamda = np.logspace(0, 4, 10) / 10
# compute the lasso path
from matplotlib import pyplot as plt
from sklearn import datasets
import heat.regression.lasso as lasso
import plotfkt
import pkg_resources
# read scikit diabetes data set
diabetes = datasets.load_diabetes()
# load diabetes dataset from hdf5 file
diabetes_path = pkg_resources.resource_filename(
pkg_resources.Requirement.parse("heat"), "heat/datasets/diabetes.h5")
X = ht.load_hdf5(diabetes_path, dataset="x", split=0)
y = ht.load_hdf5(diabetes_path, dataset="y", split=0)
# normalize dataset #DoTO this goes into the lasso fit routine soon as issue #106 is solved
X = X / ht.sqrt((ht.mean(X**2, axis=0)))
# HeAT lasso instance
estimator = lasso.Lasso(max_iter=100)
# List lasso model parameters
theta_list = list()
# Range of lambda values
lamda = np.logspace(0, 4, 10) / 10
# compute the lasso path
import sys
import os
import random
import heat as ht
from heat.classification.kneighborsclassifier import KNeighborsClassifier
import pkg_resources
# Load dataset from hdf5 file
iris_path = pkg_resources.resource_filename(
pkg_resources.Requirement.parse("heat"), "heat/datasets/iris.h5")
X = ht.load_hdf5(iris_path, dataset="data", split=0)
# Generate keys for the iris.h5 dataset
keys = []
for i in range(50):
keys.append(0)
for i in range(50, 100):
keys.append(1)
for i in range(100, 150):
keys.append(2)
Y = ht.array(keys, split=0)
def calculate_accuracy(new_y, verification_y):
"""
Calculates the accuracy of classification/clustering-algorithms.
Note this only works with integer/discrete classes. For algorithms that give approximations an error function is
required.
