def reduce_data(self, mode=1, plot=True):
print "Reducing data..."
K = 500
X = self.D[:, :self.state_dim]
# Normalize
# x_max_X = np.max(X, axis=0)
# x_min_X = np.min(X, axis=0)
# for i in range(self.state_action_dim):
# X[:,i] = (X[:,i]-x_min_X[i])/(x_max_X[i]-x_min_X[i])
kdt = KDTree(X, leaf_size=20, metric='euclidean')
df = DiffusionMap(sigma=1, embedding_dim=2, k=K)
Xreduced = []
for i in range(X.shape[0]):
if not (i % 100):
print i, X.shape[0]
idx = kdt.query(X[i, :].reshape(1, -1), k=K, return_distance=False)
X_nn = X[idx, :].reshape(K, self.state_dim)
V, _ = df.fit_transform(X_nn, density_normalize=False)
Xreduced.append(V[0, :])
Xreduced = np.array(Xreduced)
if plot:
plt.scatter(Xreduced[:, 0], Xreduced[:, 1])
plt.show()
return Xreduced
def test_DiffusionMap_fit_transform_eigenvalue_ordering(mixtureNormals):
"must return the largest first"
X = mixtureNormals
embDim = 2
df = DiffusionMap(sigma=1, embedding_dim=embDim)
X_embed, lam = df.fit_transform(X)
assert (lam[0] > lam[1])
def test_DiffusionMap_fit_transform_eigenvalue_ordering(mixtureNormals):
"must return the largest first"
X = mixtureNormals
embDim = 2
df = DiffusionMap(sigma=1, embedding_dim=embDim)
X_embed, lam = df.fit_transform(X)
assert lam[0] > lam[1]
def test_DiffusionMap_fit_transform_output_dimensions(mixtureNormals):
X = mixtureNormals
embDim = 2
df = DiffusionMap(sigma=1, embedding_dim=embDim)
X_embed, lam = df.fit_transform(X)
assert X_embed.shape == (X.shape[0], embDim), "returns wrong dimensionally"
assert lam.shape[0] == X_embed.shape[1], "must return as many eigenvalues as embedded dimensions"
def test_DiffusionMap_fit_transform_output_dimensions(mixtureNormals):
X = mixtureNormals
embDim = 2
df = DiffusionMap(sigma=1, embedding_dim=embDim)
X_embed, lam = df.fit_transform(X)
assert X_embed.shape == (X.shape[0], embDim), "returns wrong dimensionally"
assert lam.shape[0] == X_embed.shape[
1], "must return as many eigenvalues as embedded dimensions"
