from Analysis.retrieval import Retriever
from Network import FileManager
from experiments import load_experiments
from scipy.signal import savgol_filter
dset = 'Valid'
metrics = ['l2']
n_groups = 5
runs, run_net_types, run_metrics, run_epochs, run_names, _, _ = load_experiments(
'Siam')
for run, net_type, r, epochs in zip(runs, run_net_types, range(len(runs)),
run_epochs):
Embed = FileManager.Embed(net_type)
embed_source = [
Embed(run + 'c{}'.format(c), dset) for c in range(n_groups)
]
Ret = Retriever(title='{}'.format(run), dset=dset)
plt.figure('PCA: {}{}-{}'.format(net_type, run, dset))
for source in embed_source[1:]:
embd, epoch_mask = Ret.load_embedding(source, multi_epcch=True)
for i, e in enumerate([10, 20, 30, 50]):
try:
plt_ = plt.subplot(2, 2, i + 1)
Ret.pca(epoch=e, plt_=plt_)
except:
print('epoch {} failed'.format(e))
break
plt.show()
def eval_embed_space(run,
net_type,
metric,
rating_metric,
epochs,
dset,
rating_norm='none',
cross_validation=False,
n_groups=5):
# init
Embed = FileManager.Embed(net_type)
embed_source = [
Embed(run + 'c{}'.format(c), dset) for c in range(n_groups)
]
idx_hubness, idx_symmetry, idx_concentration, idx_contrast, idx_kummar, idx_featCorr, idx_sampCorr \
= [[] for i in range(n_groups)], [[] for i in range(n_groups)], [[] for i in range(n_groups)], \
[[] for i in range(n_groups)], [[] for i in range(n_groups)], [[] for i in range(n_groups)], \
[[] for i in range(n_groups)]
valid_epochs = [[] for i in range(n_groups)]
# calculate
Ret = Retriever(title='{}'.format(run), dset=dset)
for i, source in enumerate(embed_source):
embd, epoch_mask = Ret.load_embedding(source, multi_epcch=True)
for e in epochs:
try:
epoch_idx = np.argwhere(e == epoch_mask)[0][0]
Ret.fit(metric=metric, epoch=e)
indices, distances = Ret.ret_nbrs()
# hubness
idx_hubness[i].append(calc_hubness(indices))
# symmetry
idx_symmetry[i].append(calc_symmetry(indices))
# kumar index
tau, l_e = kumar(distances, res=0.01)
idx_kummar[i].append(tau)
# concentration & contrast
idx_concentration[i].append(concentration(distances))
idx_contrast[i].append(relative_contrast_imp(distances))
valid_epochs[i].append(e)
# correlation
idx_featCorr[i].append(features_correlation(embd[epoch_idx]))
idx_sampCorr[i].append(samples_correlation(embd[epoch_idx]))
except:
print("Epoch {} - no calculated embedding".format(e))
valid_epochs[i] = np.array(valid_epochs[i])
idx_hubness[i] = np.array(list(zip(*idx_hubness[i])))
idx_symmetry[i] = np.array(list(zip(*idx_symmetry[i])))
idx_concentration[i] = np.array(list(zip(*idx_concentration[i])))
idx_contrast[i] = np.array(list(zip(*idx_contrast[i])))
idx_kummar[i] = np.array([idx_kummar[i]])
idx_featCorr[i] = np.array([idx_featCorr[i]])
idx_sampCorr[i] = np.array([idx_sampCorr[i]])
combined_epochs = [
i for i, c in enumerate(np.bincount(np.concatenate(valid_epochs)))
if c > 3
]
idx_hubness = mean_cross_validated_index(idx_hubness, valid_epochs,
combined_epochs)
idx_symmetry = mean_cross_validated_index(idx_symmetry, valid_epochs,
combined_epochs)
idx_concentration = np.zeros_like(
idx_hubness
) #mean_cross_validated_index(idx_concentration, valid_epochs, combined_epochs)
idx_contrast = np.zeros_like(
idx_hubness
) # mean_cross_validated_index(idx_contrast, valid_epochs, combined_epochs)
idx_kummar = np.zeros_like(
idx_hubness
) # mean_cross_validated_index(idx_kummar, valid_epochs, combined_epochs)
idx_featCorr = np.zeros_like(
idx_hubness
) # mean_cross_validated_index(idx_featCorr, valid_epochs, combined_epochs)
idx_sampCorr = np.zeros_like(
idx_hubness
) # mean_cross_validated_index(idx_sampCorr, valid_epochs, combined_epochs)
return combined_epochs, idx_hubness, idx_symmetry, idx_concentration, idx_contrast, idx_kummar, idx_featCorr, idx_sampCorr
range(len(runs)), run_epochs,
run_names):
print("Evaluating run {}{}".format(net_type, run))
# initialize figures
plt.figure("Distances - {}".format(name))
p = [None] * 9
for i in range(9):
p[i] = plt.subplot(3, 3, i + 1)
# init
Embed = FileManager.Embed(net_type)
embed_source = [
Embed(run + 'c{}'.format(c), dset) for c in range(n_groups)
]
idx_hubness, idx_symmetry, idx_concentration, idx_contrast, idx_kummar, valid_epochs = [], [], [], [], [], []
# calculate
Ret = Retriever(title='{}'.format(run), dset=dset)
embd, epoch_mask = Ret.load_embedding(embed_source, multi_epcch=True)
for e in [60]: # epochs:
# full
Ret.fit(metric=metric, epoch=e)
_, distances = Ret.ret_nbrs()
plot_row(0, distances)
# benign
Ret.fit(metric=metric, epoch=e, label=0)
_, distances = Ret.ret_nbrs()
plot_row(3, distances, label=0)
# malignant
Ret.fit(metric=metric, epoch=e, label=1)
_, distances = Ret.ret_nbrs()
post = "All"
else:
assert False
print("{} Set Analysis".format(post))
print('=' * 15)
if DataSubSet == -1:
data = load_nodule_dataset(size=160,
sample='Normal',
res=0.5,
configuration=0)
data = data[0] + data[1] + data[2]
else:
data = load_nodule_dataset(size=160)[DataSubSet]
Ret = Retriever(title='Rating', dset=post)
Ret.load_rating(data)
idx_hubness = np.zeros(len(metrics))
idx_hubness_std_p = np.zeros(len(metrics))
idx_hubness_std_m = np.zeros(len(metrics))
idx_symmetry = np.zeros(len(metrics))
idx_symmetry_std = np.zeros(len(metrics))
idx_concentration = np.zeros(len(metrics))
idx_concentration_std = np.zeros(len(metrics))
idx_contrast = np.zeros(len(metrics))
idx_contrast_std = np.zeros(len(metrics))
idx_kummar = np.zeros(len(metrics))
#rating = []
#for entry in data: