Skip to content

Updates to be able to rerun existing spca on hdf5 feature vector files #24

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
agatabudzillo wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Updates to be able to rerun existing spca on hdf5 feature vector files #24

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
591b5cc
Updated orig_mean_and_std_for_zscore and spca_transform_new_data to u…
agatabudzillo Apr 4, 2024
b70902c
Updated to conform with hdf5 feature vector datasets.
agatabudzillo Apr 4, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions drcme/bin/run_existing_spca_on_new_data.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -98,7 +98,7 @@ def main(orig_transform_file, orig_datasets, new_datasets, params_file,
params_file=params_file)
orig_data_objects.append(data_for_spca)
orig_specimen_ids_list.append(specimen_ids)
orig_data_for_spca = []
orig_data_for_spca = {}
for i, do in enumerate(orig_data_objects):
for k in do:
if k not in orig_data_for_spca:
Expand Down Expand Up @@ -128,7 +128,7 @@ def main(orig_transform_file, orig_datasets, new_datasets, params_file,
params_file=params_file)
new_data_objects.append(data_for_spca)
new_specimen_ids_list.append(specimen_ids)
data_for_spca = []
data_for_spca = {}
for i, do in enumerate(new_data_objects):
for k in do:
if k not in data_for_spca:
Expand Down
34 changes: 14 additions & 20 deletions drcme/spca.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -195,16 +195,13 @@ def orig_mean_and_std_for_zscore(spca_results, orig_data, spca_params,
Standard deviations of sPCs
"""
Z_list = []
for ds in orig_data:
data = ds["data"]
for k in ds["part_keys"]:
_, _, _, indices = spca_params[k]
d = data[:, indices]
above_thresh = spca_results[k]["pev"] >= pev_threshold
Z = d.dot(spca_results[k]["loadings"][:, above_thresh])
if np.any(np.isnan(Z)):
print("NaNs found", k)
Z_list.append(Z)
subset_data = select_data_subset(orig_data, spca_params)
for k, d in subset_data.items():
above_thresh = spca_results[k]["pev"] >= pev_threshold
Z = d.dot(spca_results[k]["loadings"][:, above_thresh])
if np.any(np.isnan(Z)):
print("NaNs found", k)
Z_list.append(Z)

combo_orig = np.hstack(Z_list)
return combo_orig.mean(axis=0), combo_orig.std(axis=0)
Expand Down Expand Up @@ -238,16 +235,13 @@ def spca_transform_new_data(spca_results, new_data, spca_zht_params, orig_mean,
Transformed and z-scored sPC values
"""
Z_list = []
for ds in new_data:
data = ds["data"]
for k in ds["part_keys"]:
_, _, _, indices = spca_zht_params[k]
d = data[:, indices]
above_thresh = spca_results[k]["pev"] >= pev_threshold
Z = d.dot(spca_results[k]["loadings"][:, above_thresh])
if np.any(np.isnan(Z)):
print("NaNs found", k)
Z_list.append(Z)
subset_data = select_data_subset(new_data, spca_zht_params)
for k, d in subset_data.items():
above_thresh = spca_results[k]["pev"] >= pev_threshold
Z = d.dot(spca_results[k]["loadings"][:, above_thresh])
if np.any(np.isnan(Z)):
print("NaNs found", k)
Z_list.append(Z)

combo_new = np.hstack(Z_list)
combo = (combo_new - orig_mean) / orig_std
Expand Down