Skip to content

[WIP] Python code refactor and code styling #59

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
AlexVCaron wants to merge 9 commits into
base: master
Choose a base branch
from
Open

[WIP] Python code refactor and code styling #59

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
a58913b
QCRAKEN-5 - Trim whitespaces and end-of-line from status when updatin…
Feb 8, 2022
ba64a28
QCRAKEN-5 - Answer code formatting comments from MR. Refactor redunda…
Feb 14, 2022
f2d8143
QCRAKEN-5 - Run black -l 80. Add info to README for code styling and …
Feb 15, 2022
9b0f164
QCRAKEN-5 - Run black -l 100. Minor fixes
Feb 18, 2022
44903a7
QCRAKEN-5 - Extract parallelization code to avoid code repetition. Re…
Feb 21, 2022
4095cc0
QCRAKEN-5 - Fix typos, refactor stats module to avoid repetitions
Feb 28, 2022
784dba5
Transfer refactoring from Imeka. Still need to be tested
Jun 16, 2022
b994d2a
Re-add files deleted by the merge operation
Jun 16, 2022
cbaf8a4
Fix readme
Jun 16, 2022
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
95 changes: 18 additions & 77 deletions dmriqcpy/analysis/stats.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,9 +1,10 @@
# -*- coding: utf-8 -*-
import os

import nibabel as nib
import numpy as np
import os
import pandas as pd

from dmriqcpy.analysis.utils import get_stats_dataframes


def stats_mean_median(column_names, filenames):
Expand All @@ -26,8 +27,6 @@ def stats_mean_median(column_names, filenames):
across subjects.
"""
values = []
import time
sub_filenames = [os.path.basename(curr_subj).split('.')[0] for curr_subj in filenames]

for filename in filenames:
data = nib.load(filename).get_data()
Expand All @@ -40,24 +39,14 @@ def stats_mean_median(column_names, filenames):
mean = np.mean(data[data > 0])
median = np.median(data[data > 0])

values.append(
[mean, median])

stats_per_subjects = pd.DataFrame(values, index=sub_filenames,
columns=column_names)

stats_across_subjects = pd.DataFrame([stats_per_subjects.mean(),
stats_per_subjects.std(),
stats_per_subjects.min(),
stats_per_subjects.max()],
index=['mean', 'std', 'min', 'max'],
columns=column_names)
values.append([mean, median])

return stats_per_subjects, stats_across_subjects
return get_stats_dataframes(filenames, values, column_names)


def stats_mean_in_tissues(column_names, images, wm_images, gm_images,
csf_images):
def stats_mean_in_tissues(
column_names, images, wm_images, gm_images, csf_images
):
"""
Compute mean value in WM, GM and CSF mask.

Expand All @@ -82,7 +71,6 @@ def stats_mean_in_tissues(column_names, images, wm_images, gm_images,
DataFrame containing mean, std, min and max of mean across subjects.
"""
values = []
sub_images = [os.path.basename(curr_subj).split('.')[0] for curr_subj in images]

for i in range(len(images)):
data = nib.load(images[i]).get_data()
Expand All @@ -95,20 +83,9 @@ def stats_mean_in_tissues(column_names, images, wm_images, gm_images,
data_csf = np.mean(data[csf > 0])
data_max = np.max(data[wm > 0])

values.append(
[data_wm, data_gm, data_csf, data_max])
values.append([data_wm, data_gm, data_csf, data_max])

stats_per_subjects = pd.DataFrame(values, index=sub_images,
columns=column_names)

stats_across_subjects = pd.DataFrame([stats_per_subjects.mean(),
stats_per_subjects.std(),
stats_per_subjects.min(),
stats_per_subjects.max()],
index=['mean', 'std', 'min', 'max'],
columns=column_names)

return stats_per_subjects, stats_across_subjects
return get_stats_dataframes(images, values, column_names)


def stats_frf(column_names, filenames):
Expand All @@ -130,22 +107,12 @@ def stats_frf(column_names, filenames):
DataFrame containing mean, std, min and max of mean across subjects.
"""
values = []

for filename in filenames:
frf = np.loadtxt(filename)
values.append([frf[0], frf[1], frf[3]])

sub_filenames = [os.path.basename(curr_subj).split('.')[0] for curr_subj in filenames]
stats_per_subjects = pd.DataFrame(values,index=sub_filenames,
columns=column_names)

stats_across_subjects = pd.DataFrame([stats_per_subjects.mean(),
stats_per_subjects.std(),
stats_per_subjects.min(),
stats_per_subjects.max()],
index=['mean', 'std', 'min', 'max'],
columns=column_names)

return stats_per_subjects, stats_across_subjects
return get_stats_dataframes(filenames, values, column_names)


def stats_tractogram(column_names, tractograms):
Expand All @@ -167,24 +134,12 @@ def stats_tractogram(column_names, tractograms):
DataFrame containing mean, std, min and max of mean across subjects.
"""
values = []
sub_tractograms = [os.path.basename(curr_subj).split('.')[0] for curr_subj in tractograms]

for tractogram_file in tractograms:
tractogram = nib.streamlines.load(tractogram_file, lazy_load=True)
values.append([tractogram.header["nb_streamlines"]])

values.append(
[tractogram.header['nb_streamlines']])

stats_per_subjects = pd.DataFrame(values, index=sub_tractograms,
columns=column_names)

stats_across_subjects = pd.DataFrame([stats_per_subjects.mean(),
stats_per_subjects.std(),
stats_per_subjects.min(),
stats_per_subjects.max()],
index=['mean', 'std', 'min', 'max'],
columns=column_names)

return stats_per_subjects, stats_across_subjects
return get_stats_dataframes(tractograms, values, column_names)


def stats_mask_volume(column_names, images):
Expand All @@ -206,24 +161,10 @@ def stats_mask_volume(column_names, images):
DataFrame containing mean, std, min and max of mean across subjects.
"""
values = []
sub_images = [os.path.basename(curr_subj).split('.')[0] for curr_subj in images]

for image in images:
img = nib.load(image)
data = img.get_data()
voxel_volume = np.prod(img.header['pixdim'][1:4])
volume = np.count_nonzero(data) * voxel_volume

values.append([volume])

stats_per_subjects = pd.DataFrame(values, index=sub_images,
columns=column_names)

stats_across_subjects = pd.DataFrame([stats_per_subjects.mean(),
stats_per_subjects.std(),
stats_per_subjects.min(),
stats_per_subjects.max()],
index=['mean', 'std', 'min', 'max'],
columns=column_names)
voxel_volume = np.prod(img.header["pixdim"][1:4])
values.append([np.count_nonzero(img.get_data()) * voxel_volume])

return stats_per_subjects, stats_across_subjects
return get_stats_dataframes(images, values, column_names)
Loading