def per_sample_subsets(X, nsubsets, ncell_per_subset, k_init=False):
nmark = X.shape[1]
shape = (nsubsets, nmark, ncell_per_subset)
Xres = np.zeros(shape)
if not k_init:
for i in range(nsubsets):
X_i = random_subsample(X, ncell_per_subset)
Xres[i] = X_i.T
else:
for i in range(nsubsets):
X_i = random_subsample(X, 2000)
X_i = kmeans_subsample(X_i, ncell_per_subset, random_state=i)
Xres[i] = X_i.T
return Xres
def per_sample_subsets(X, nsubsets, ncell_per_subset, k_init=False): nmark = X.shape[1] shape = (nsubsets, nmark, ncell_per_subset) Xres = np.zeros(shape) if not k_init: for i in range(nsubsets): X_i = random_subsample(X, ncell_per_subset) Xres[i] = X_i.T else: for i in range(nsubsets): X_i = random_subsample(X, 2000) X_i = kmeans_subsample(X_i, ncell_per_subset, random_state=i) Xres[i] = X_i.T return Xres
def per_sample_biased_subsets(X, x_ctrl, nsubsets, ncell_final, to_keep, ratio_biased):
nmark = X.shape[1]
Xres = np.empty((nsubsets, nmark, ncell_final))
nc_biased = int(ratio_biased * ncell_final)
nc_unbiased = ncell_final - nc_biased
for i in range(nsubsets):
print i
x_unbiased = random_subsample(X, nc_unbiased)
if (i % 100) == 0:
x_outlier, outlierness = outlier_subsample(X, x_ctrl, to_keep)
x_biased = weighted_subsample(x_outlier, outlierness, nc_biased)
Xres[i] = np.vstack([x_biased, x_unbiased]).T
return Xres
def per_sample_biased_subsets(X, x_ctrl, nsubsets, ncell_final,
to_keep, ratio_biased):
nmark = X.shape[1]
Xres = np.empty((nsubsets, nmark, ncell_final))
nc_biased = int(ratio_biased * ncell_final)
nc_unbiased = ncell_final - nc_biased
for i in range(nsubsets):
x_unbiased = random_subsample(X, nc_unbiased)
if (i % 100) == 0:
x_outlier, outlierness = outlier_subsample(X, x_ctrl, to_keep)
x_biased = weighted_subsample(x_outlier, outlierness, nc_biased)
Xres[i] = np.vstack([x_biased, x_unbiased]).T
return Xres
