def test_non_square_precomputed_distances():
# Precomputed distance matrices must be square matrices.
tsne = TSNE(metric="precomputed")
assert_raises_regexp(ValueError, ".* square distance matrix",
tsne.fit_transform, np.array([[0.0], [1.0]]))
def test_early_exaggeration_too_small():
# Early exaggeration factor must be >= 1.
tsne = TSNE(early_exaggeration=0.99)
assert_raises_regexp(ValueError, "early_exaggeration .*",
tsne.fit_transform, np.array([[0.0], [0.0]]))
def test_too_few_iterations():
# Number of gradient descent iterations must be at least 200.
tsne = TSNE(n_iter=199)
assert_raises_regexp(ValueError, "n_iter .*", tsne.fit_transform,
np.array([[0.0], [0.0]]))
def test_n_components_range():
# barnes_hut method should only be used with n_components <= 3
tsne = TSNE(n_components=4, method="barnes_hut")
assert_raises_regexp(ValueError, "'n_components' should be .*",
tsne.fit_transform, np.array([[0.0], [1.0]]))
import pandas as pd
from scipy.io import loadmat
from sklearn.manifold.t_sne import TSNE
chris_data = loadmat('/home/itskov/Downloads/dataForEyal.mat')
tnse_manifold = TSNE().fit_transform(chris_data['PCs'])
pass
def test_init_ndarray_precomputed():
# Initialize TSNE with ndarray and metric 'precomputed'
# Make sure no FutureWarning is thrown from _fit
tsne = TSNE(init=np.zeros((100, 2)), metric="precomputed")
tsne.fit(np.zeros((100, 100)))
def test_angle_out_of_range_checks():
# check the angle parameter range
for angle in [-1, -1e-6, 1 + 1e-6, 2]:
tsne = TSNE(angle=angle)
assert_raises_regexp(ValueError, "'angle' must be between 0.0 - 1.0",
tsne.fit_transform, np.array([[0.0], [1.0]]))
def test_too_few_iterations():
# Number of gradient descent iterations must be at least 200.
tsne = TSNE(n_iter=199)
with pytest.raises(ValueError, match="n_iter .*"):
tsne.fit_transform(np.array([[0.0], [0.0]]))
def test_non_square_precomputed_distances():
# Precomputed distance matrices must be square matrices.
tsne = TSNE(metric="precomputed")
with pytest.raises(ValueError, match=".* square distance matrix"):
tsne.fit_transform(np.array([[0.0], [1.0]]))
img_path_dict = dict(zip(letters, paths))
images = []
for letter in letters:
img = Image.open(img_path_dict[letter])
img = img.crop((80, 50, 400, 365))
img.thumbnail((16, 16), Image.ANTIALIAS)
images.append(img)
images_dict = dict(zip(letters, images))
X, Y = get_input_data(
'../letter_classification/letter_classification_train.data')
images = []
for letter in Y:
images.append(images_dict[letter])
tsne = TSNE(n_components=2,
init='pca',
verbose=1,
learning_rate=600,
n_iter=5000)
t0 = time.time()
X_tsne = tsne.fit_transform(X)
plot_embedding(
X_tsne, Y, X, images,
"t-SNE embedding of the letters. Time: %.3f seconds" %
(time.time() - t0))
plt.show()
def test_early_exaggeration_too_small():
# Early exaggeration factor must be >= 1.
tsne = TSNE(early_exaggeration=0.99)
with pytest.raises(ValueError, match="early_exaggeration .*"):
tsne.fit_transform(np.array([[0.0], [0.0]]))
#create reduced feature matrix
reader=csv.reader(open("reduced_features.csv","r"),delimiter=",")
X=list(reader)
X=np.array(X)
X=X.astype(np.float)
#create result vector
reader=csv.reader(open("target_output.csv","r"),delimiter=",")
y=list(reader)
y=np.array(y)
y=y.astype(np.int)
y=y.ravel()
X_Train_embedded = TSNE(n_components=2).fit_transform(X)
print X_Train_embedded.shape
model = BernoulliNB().fit(X,y)
y_predicted = model.predict(X)
# replace the above by your data and model
# create meshgrid
resolution = 1024 # 100x100 background pixels
X2d_xmin, X2d_xmax = np.min(X_Train_embedded[:,0]), np.max(X_Train_embedded[:,0])
X2d_ymin, X2d_ymax = np.min(X_Train_embedded[:,1]), np.max(X_Train_embedded[:,1])
xx, yy = np.meshgrid(np.linspace(X2d_xmin, X2d_xmax, resolution), np.linspace(X2d_ymin, X2d_ymax, resolution))
# approximate Voronoi tesselation on resolution x resolution grid using 1-NN
background_model = KNeighborsClassifier(n_neighbors=1).fit(X_Train_embedded, y_predicted)
voronoiBackground = background_model.predict(np.c_[xx.ravel(), yy.ravel()])
voronoiBackground = voronoiBackground.reshape((resolution, resolution))
def test_exact_no_precomputed_sparse():
tsne = TSNE(metric='precomputed', method='exact')
with pytest.raises(TypeError, match='sparse'):
tsne.fit_transform(sp.csr_matrix([[0, 5], [5, 0]]))
def test_bad_precomputed_distances(method, D, retype, message_regex):
tsne = TSNE(metric="precomputed", method=method)
with pytest.raises(ValueError, match=message_regex):
tsne.fit_transform(retype(D))
def test_init_not_available():
# 'init' must be 'pca', 'random', or numpy array.
tsne = TSNE(init="not available")
m = "'init' must be 'pca', 'random', or a numpy array"
assert_raises_regexp(ValueError, m, tsne.fit_transform,
np.array([[0.0], [1.0]]))
def test_init_not_available():
# 'init' must be 'pca', 'random', or numpy array.
tsne = TSNE(init="not available")
m = "'init' must be 'pca', 'random', or a numpy array"
with pytest.raises(ValueError, match=m):
tsne.fit_transform(np.array([[0.0], [1.0]]))
def test_init_ndarray():
# Initialize TSNE with ndarray and test fit
tsne = TSNE(init=np.zeros((100, 2)))
X_embedded = tsne.fit_transform(np.ones((100, 5)))
assert_array_equal(np.zeros((100, 2)), X_embedded)
def test_method_not_available():
# 'nethod' must be 'barnes_hut' or 'exact'
tsne = TSNE(method='not available')
with pytest.raises(ValueError, match="'method' must be 'barnes_hut' or "):
tsne.fit_transform(np.array([[0.0], [1.0]]))
def test_method_not_available():
# 'nethod' must be 'barnes_hut' or 'exact'
tsne = TSNE(method='not available')
assert_raises_regexp(ValueError, "'method' must be 'barnes_hut' or ",
tsne.fit_transform, np.array([[0.0], [1.0]]))
def test_n_components_range():
# barnes_hut method should only be used with n_components <= 3
tsne = TSNE(n_components=4, method="barnes_hut")
with pytest.raises(ValueError, match="'n_components' should be .*"):
tsne.fit_transform(np.array([[0.0], [1.0]]))
def test_pca_initialization_not_compatible_with_precomputed_kernel():
# Precomputed distance matrices must be square matrices.
tsne = TSNE(metric="precomputed", init="pca")
assert_raises_regexp(ValueError, "The parameter init=\"pca\" cannot be "
"used with metric=\"precomputed\".",
tsne.fit_transform, np.array([[0.0], [1.0]]))
def test_distance_not_available():
"""'metric' must be valid."""
tsne = TSNE(metric="not available")
assert_raises_regexp(ValueError, "Unknown metric not available.*",
tsne.fit_transform, np.array([[0.0], [1.0]]))
def test_chebyshev_metric():
# t-SNE should allow metrics that cannot be squared (issue #3526).
random_state = check_random_state(0)
tsne = TSNE(metric="chebyshev")
X = random_state.randn(5, 2)
tsne.fit_transform(X)
name = image.split('/')[-1]
if name in valid_names:
img = open_image(image)
pred = learn.predict(img)
embedding = pred[-1].detach().numpy()
x.append(embedding)
y.append(n_class)
n_class += 1
x, y = np.asarray(x), np.asarray(y)
print(x.shape, y.shape)
print(np.unique(y))
x_tsne = TSNE(n_components=2).fit_transform(x)
print(x_tsne.shape)
color = ['darkcyan', 'g', 'y', 'magenta', 'lightgreen', 'mediumslateblue', 'yellow', 'brown', 'k', 'b']
labels = [str(i) for i in range(10)]
times = [0 for i in range(10)]
for i in range(len(x_tsne)):
if times[y[i]] == 0:
plt.scatter(x_tsne[i, 0], x_tsne[i, 1], color=color[y[i]], label=labels[y[i]])
times[y[i]] += 1
else:
plt.scatter(x_tsne[i, 0], x_tsne[i, 1], color=color[y[i]])
plt.legend()
plt.title('TSNE validation')
plt.savefig('tsne_val.png')
