def make_dataset(dataset, n_rows, n_cols, n_classes=2):
np.random.seed(137)
if dataset == 'classification1':
X, y = make_classification(n_rows,
n_cols,
n_informative=2,
n_redundant=0,
n_classes=n_classes,
n_clusters_per_class=1)
elif dataset == 'classification2':
X, y = make_classification(n_rows,
n_cols,
n_informative=2,
n_redundant=0,
n_classes=n_classes,
n_clusters_per_class=2)
elif dataset == 'gaussian':
X, y = make_gaussian_quantiles(n_samples=n_rows,
n_features=n_cols,
n_classes=n_classes)
elif dataset == 'blobs':
X, y = make_blobs(n_samples=n_rows,
n_features=n_cols,
centers=n_classes)
X_train, X_test, y_train, y_test = train_test_split(X, y)
# correct case when not all classes made it into the training set
if np.unique(y_train).size < n_classes:
for i in range(n_classes):
y_train[i] = i
return X_train, X_test, y_train, y_test
def get_gaussian_quantiles(n_samples=1000):
x, y = make_gaussian_quantiles(n_samples=n_samples, n_features=2, n_classes=2)
y = np.asarray([[0., 1.] if y_ == 0 else [1., 0,] for y_ in y])
x = x.astype(np.float32)
y = y.astype(np.float32)
return x,y
import matplotlib.pyplot as plt
X, y = make_classification(n_samples=1000,
n_redundant=0,
n_features=2,
n_classes=3,
n_clusters_per_class=1)
plt.scatter(X[:, 0], X[:, 1], marker='o', c=y)
plt.show()
# Gnerate non-linearly seperable classification dataset--------------
from sklearn.datasets.samples_generator import make_gaussian_quantiles
X, y = make_gaussian_quantiles(n_samples=1000,
n_features=2,
n_classes=3,
mean=[10, 5],
cov=2)
plt.scatter(X[:, 0], X[:, 1], marker='o', c=y)
plt.show()
# XOR problem dataset
np.random.seed(0)
n = 100
x1 = np.random.rand(n, 2) * (-1)
x2 = np.random.rand(n, 2)
x2[:, 1] *= (-1)
x3 = np.random.rand(n, 2)
x3[:, 0] *= (-1)
x4 = np.random.rand(n, 2)
x = np.concatenate((x1, x2, x3, x4))
plt.contourf(xx1, xx2, Z, alpha=0.3, cmap=cmap)
plt.xlim(xx1.min(), xx1.max())
plt.ylim(xx2.min(), xx2.max())
for index, cl in enumerate(np.unique(y)):
plt.scatter(x=X[y == cl, 0],
y=X[y == cl, 1],
alpha=0.8,
c=colors[index],
marker=markers[index],
label=cl,
edgecolor='black')
(X, y) = make_blobs(n_samples=1000, n_features=2, centers=2, cluster_std=1.05)
(X, y) = make_gaussian_quantiles(n_samples=1000, n_features=2, n_classes=3)
(X, y) = make_moons(n_samples=1000)
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.3,
stratify=y)
sc = StandardScaler()
sc.fit(X_train)
X_train_std = sc.transform(X_train)
X_test_std = sc.transform(X_test)
svm = SVC(kernel='rbf', C=1.0, gamma=0.5)
svm.fit(X_train_std, y_train)
plot_decision_regions(X_test_std, y_test, svm)