Skip to content
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

ENH: Fix GP estimation error analysis script #30

Draft
wants to merge 4 commits into
base: main
Choose a base branch
from
Draft

ENH: Fix GP estimation error analysis script #30

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
97d9edf
ENH: Fix return value type annotation in GP error analysis script func
jhlegarreta Dec 22, 2024
5c3e7d3
ENH: Use a boolean to tell whether to serialize the pandas df index
jhlegarreta Dec 22, 2024
d9dafbe
BUG: Provide missing position arg to local cross validation function
jhlegarreta Dec 22, 2024
6e8311f
ENH: Add type annotation for variable in GP estimation error analysis
jhlegarreta Dec 22, 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
13 changes: 8 additions & 5 deletions scripts/dwi_gp_estimation_error_analysis.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,6 +31,7 @@
import argparse
from collections import defaultdict
from pathlib import Path
from typing import DefaultDict, List

import numpy as np
import pandas as pd
Expand All @@ -49,7 +50,7 @@ def cross_validate(
cv: int,
n_repeats: int,
gpr: DiffusionGPR,
) -> dict[int, list[tuple[np.ndarray, np.ndarray, np.ndarray, np.ndarray]]]:
) -> np.ndarray:
"""
Perform the experiment by estimating the dMRI signal using a Gaussian process model.

Expand All @@ -68,7 +69,7 @@ def cross_validate(

Returns
-------
:obj:`dict`
:obj:`~numpy.ndarray`
Data for the predicted signal and its error.

"""
Expand Down Expand Up @@ -202,12 +203,14 @@ def main() -> None:
# max_iter=2e5,
)

n_repeats = 10

if args.kfold:
# Use Scikit-learn cross validation
scores = defaultdict(list, {})
scores: DefaultDict[str, List[float | str]] = defaultdict(list)
for n in args.kfold:
for i in range(args.repeats):
cv_scores = -1.0 * cross_validate(X, y.T, n, gpr)
cv_scores = -1.0 * cross_validate(X, y.T, n, n_repeats, gpr)
scores["rmse"] += cv_scores.tolist()
scores["repeat"] += [i] * len(cv_scores)
scores["n_folds"] += [n] * len(cv_scores)
Expand All @@ -217,7 +220,7 @@ def main() -> None:
print(f"Finished {n}-fold cross-validation")

scores_df = pd.DataFrame(scores)
scores_df.to_csv(args.output_scores, sep="\t", index=None, na_rep="n/a")
scores_df.to_csv(args.output_scores, sep="\t", index=False, na_rep="n/a")

grouped = scores_df.groupby(["n_folds"])
print(grouped[["rmse"]].mean())
Expand Down
Loading