def fast_euclid(X):
gamma = 1.0 / X.shape[1]
if X.shape[0] < 1000:
L = rbf_kernel(X, gamma=gamma)
else:
L = Nystroem(gamma=gamma).fit_transform(X)
L = L.dot(L.T)
Ls = np.log(L) * (-1.0 / (gamma))
return Ls
def _dpp_sel(self, X_, y=None):
"""
DPP only relies on X.
We will condition the sampling based on:
* `self.coef_info['cols']`
After sampling it will go ahead and then perform grouped wilcoxon selection.
"""
X = np.array(X_)
print(X.shape)
cols_to_index = [
idx for idx, x in enumerate(X_.columns)
if x in self.coef_info['cols']
]
unseen_cols_to_index = [
idx for idx, x in enumerate(X_.columns)
if x not in self.coef_info['cols']
]
if X.shape[0] < 1000 or X.shape[1] < 100:
feat_dist = rbf_kernel(X.T)
else:
feat_dist = Nystroem().fit_transform(X.T)
feat_dist = feat_dist.dot(feat_dist.T)
#self._dpp_estimate_k(feat_dist)
#k = self.dpp_k['pca'] #- len(self.coef_info['cols'])
k = None
feat_index = []
#while len(feat_index) == 0:
if len(self.coef_info['cols']) == 0:
feat_index = sample_dpp(decompose_kernel(feat_dist), k=k)
else:
feat_index = sample_conditional_dpp(feat_dist, cols_to_index, k=k)
feat_index = [x for x in feat_index if x is not None]
# select features using entropy measure
# how can we order features from most to least relevant first?
# we chould do it using f test? Or otherwise - presume DPP selects best one first
s_b, s_w = class_separability(X, y)
col_sel = evaluate_feats(s_b, s_w)
#sel_cols = list(self.coef_info['cols']) + list(col_sel)
"""
feat_entropy = []
excl_entropy = []
X_sel = X[:, feat_index]
for idx, feat in enumerate(X_sel.T):
if len(feat_entropy) == 0:
feat_entropy.append(idx)
continue
if entropy(X_sel[:, feat_entropy]) > entropy(X_sel[:, feat_entropy+[idx]]):
feat_entropy.append(idx)
else:
excl_entropy.append(idx)
"""
# iterate over feat_index to determine
# information on wilcoxon test
# as the feat index are already "ordered" as that is how DPP would
# perform the sampling - we will do the single pass in the same
# way it was approached in the OGFS
# feat index will have all previous sampled columns as well...
if not self.unseen_only and len(feat_index) > 0:
feat_check = []
excl_check = []
X_sel = X[:, feat_index]
for idx, feat in enumerate(X_sel.T):
if len(feat_check) == 0:
feat_check.append(idx)
continue
wilcoxon_pval = wilcoxon_group(X_sel[:, feat_check], feat)
#print("\tWilcoxon: {}".format(wilcoxon_pval))
if wilcoxon_pval < self.intragroup_alpha:
feat_check.append(idx)
else:
excl_check.append(idx)
feat_check_ = (feat_check + col_sel)
index_to_col = [
col for idx, col in enumerate(X_.columns) if idx in feat_check_
]
elif self.unseen_only:
# if we are considering unseen only, we will simply let the regulariser
# act on it, sim. to grafting.
index_to_col = [
col for idx, col in enumerate(X_.columns) if idx in feat_index
]
else:
# only use supervised criteria
feat_check_ = (feat_check + col_sel)
index_to_col = [
col for idx, col in enumerate(X_.columns) if idx in feat_index
]
self.unseen_only = False # perhaps add more conditions around unseen - i.e. once unseen condition kicks in, it remains active?
self.coef_info['cols'] = list(
set(self.coef_info['cols'] + index_to_col))
col_rem = X_.columns.difference(self.coef_info['cols'])
# update column exclusion...
self.coef_info['excluded_cols'] = [
x for x in self.coef_info['excluded_cols']
if x not in self.coef_info['cols']
]
self.add_column_exclusion(col_rem)
