Skip to content

Fix pseudo-count difference #76

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
godotgildor wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix pseudo-count difference #76

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
54 changes: 21 additions & 33 deletions enrich2/selection.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -530,23 +530,19 @@ def calc_ratios(self, label):
)
shared_counts = shared_counts.values + 0.5
elif self.logr_method == "complete":
counts_df = self.store.select(
"/main/{}/counts".format(label), "columns in ['c_0', c_last]"
)
shared_counts = (
self.store.select(
"/main/{}/counts".format(label), "columns in ['c_0', c_last]"
)
.sum(axis="index")
.values
+ 0.5
counts_df.sum(axis="index").values + 0.5 * len(counts_df)
)
elif self.logr_method == "full":
counts_df = self.store.select(
"/main/{}/counts_unfiltered".format(label),
"columns in ['c_0', c_last]",
)
shared_counts = (
self.store.select(
"/main/{}/counts_unfiltered".format(label),
"columns in ['c_0', c_last]",
)
.sum(axis="index", skipna=True)
.values
+ 0.5
counts_df.sum(axis="index", skipna=True).values + 0.5 * len(counts_df)
)
else:
raise ValueError(
Expand Down Expand Up @@ -612,20 +608,16 @@ def calc_log_ratios(self, label):
)
ratios = ratios - np.log(wt_counts.values + 0.5)
elif self.logr_method == "complete":
counts_df = self.store.select("/main/{}/counts".format(label), "columns=c_n")
ratios = ratios - np.log(
self.store.select("/main/{}/counts".format(label), "columns=c_n")
.sum(axis="index")
.values
+ 0.5
counts_df.sum(axis="index").values + 0.5 * len(counts_df)
)
elif self.logr_method == "full":
counts_df = self.store.select(
"/main/{}/counts_unfiltered".format(label), "columns=c_n"
)
ratios = ratios - np.log(
self.store.select(
"/main/{}/counts_unfiltered".format(label), "columns=c_n"
)
.sum(axis="index", skipna=True)
.values
+ 0.5
counts_df.sum(axis="index", skipna=True).values + 0.5 * len(counts_df)
)
else:
raise ValueError(
Expand Down Expand Up @@ -682,20 +674,16 @@ def calc_weights(self, label):
)
variances = variances + 1.0 / (wt_counts.values + 0.5)
elif self.logr_method == "complete":
counts_df = self.store.select("/main/{}/counts".format(label), "columns=c_n")
variances = variances + 1.0 / (
self.store.select("/main/{}/counts".format(label), "columns=c_n")
.sum(axis="index")
.values
+ 0.5
counts_df.sum(axis="index").values + 0.5 * len(counts_df)
)
elif self.logr_method == "full":
counts_df = self.store.select(
"/main/{}/counts_unfiltered".format(label), "columns=c_n"
)
variances = variances + 1.0 / (
self.store.select(
"/main/{}/counts_unfiltered".format(label), "columns=c_n"
)
.sum(axis="index", skipna=True)
.values
+ 0.5
counts_df.sum(axis="index", skipna=True).values + 0.5 * len(counts_df)
)
else:
raise ValueError(
Expand Down