def get_local_remote_dir(self, dir_data, _dir='None'):
location = dir_data[0]
dir_abspath = dir_data[1]
print(f'{LogLVL.lvl2}folder {dir_abspath}')
print(f'{LogLVL.lvl3}is located on: {location}')
if location == 'local':
if not os.path.exists(dir_abspath):
dir_abspath = get_userdefined_paths(f'{_dir} folder',
dir_abspath,
'',
create=False)
makedir_ifnot_exist(dir_abspath)
if _dir != 'None':
from setup.get_credentials_home import _get_credentials_home
if _dir in self.all_vars.projects[self.project]:
self.all_vars.projects[
self.project][_dir][1] = dir_abspath
abs_path_projects = os.path.join(
_get_credentials_home(), 'projects.json')
save_json(self.all_vars.projects, abs_path_projects)
else:
print(
' folder to change is not located in the projects.json variables'
)
else:
print(
' Folder to change is not defined, cannot create a new one.'
)
return True, dir_abspath, 'local'
else:
return False, dir_abspath, location
def chk_stats(self):
"""
check if variables are defined in json
:param config_file: path to configuration json file
:return: new version, populated with missing values
"""
default_stats = self.load_file('stats', default=True)
update_stats = False
for key in [i for i in default_stats.keys() if 'EXPLANATION' not in i]:
if key not in self.stats_vars:
print('adding missing key {} to stats'.format(key))
self.stats_vars[key] = default_stats[key]
update_stats = True
for subkey in default_stats[key]:
if subkey not in self.stats_vars[key]:
print('adding missing subkey {} to stats group: {}'.format(
subkey, key))
self.stats_vars[key][subkey] = default_stats[key][subkey]
self.stats_vars['EXPLANATION'][subkey] = default_stats[
'EXPLANATION'][subkey]
update_stats = True
if isinstance(subkey, list):
if not isinstance(self.stats_vars[key][subkey], list):
print(' types are different {}'.format(subkey))
if update_stats:
save_json(self.stats_vars,
path.join(self.credentials_home, 'stats.json'))
def chk_location_vars(self):
default_local = self.load_file('local', default=True)
update = False
for location in self.location_vars:
for Key in default_local:
if Key not in self.location_vars[location]:
print('adding missing key {} to location: {}'.format(
Key, location))
self.location_vars[location][Key] = default_local[Key]
update = True
for subkey in default_local[Key]:
if subkey not in self.location_vars[location][Key]:
print(
'adding missing subkey {} to location: {}, key: {}'
.format(subkey, location, Key))
self.location_vars[location][Key][
subkey] = default_local[Key][subkey]
update = True
if location == 'local':
self.chk_paths(self.location_vars[location])
if update:
self.location_vars[location]['EXPLANATION'] = default_local[
'EXPLANATION']
print('must update location: {}'.format(location))
save_json(self.location_vars[location],
path.join(self.credentials_home, location + '.json'))
def chk_project_vars(self):
"""
check if variables are defined in json
:param config_file: path to configuration json file
:return: new version, populated with missing values
"""
update = False
if self.params:
update = self.set_stats()
default_project = self.load_file('projects', default=True)
for subkey in default_project[DEFAULT.default_project]:
if subkey not in self.projects[self.project]:
print('adding missing subkey {} to project: {}'.format(
subkey, self.project))
self.projects[self.project][subkey] = default_project[
DEFAULT.default_project][subkey]
self.projects['EXPLANATION'][subkey] = default_project[
'EXPLANATION'][subkey]
update = True
if isinstance(subkey, list):
if not isinstance(self.projects[self.project][subkey], list):
print('types are different {}'.format(subkey))
if update:
save_json(self.projects,
path.join(self.credentials_home, 'projects.json'))
for project in DEFAULT.project_ids:
if project not in self.projects:
self.projects[project] = default_project[
DEFAULT.default_project]
def make_f_subjects_2b_processed(self, location, unprocessed_d):
NIMB_tmp_loc = self.locations[location]['NIMB_PATHS']['NIMB_tmp']
f_abspath = os.path.join(NIMB_tmp_loc, DEFAULT.f_subjects2proc)
print(f'{LogLVL.lvl2}creating file: {f_abspath}')
# print(unprocessed_d)
for _id_bids in unprocessed_d:
unprocessed_d[_id_bids] = self.adjust_paths_2data(
NIMB_tmp_loc, unprocessed_d[_id_bids])
print(unprocessed_d[_id_bids])
save_json(unprocessed_d, f_abspath)
def set_project(self, location):
if path.exists(path.join(self.credentials_home, 'projects.json')):
projects = load_json(
path.join(self.credentials_home, 'projects.json'))
projects['LOCATION'].append(location)
save_json(projects,
path.join(self.credentials_home, 'projects.json'))
# self.save_json('projects.json', projects, self.credentials_home)
new_loc = load_json(
path.join(self.credentials_home, 'remote1.json'))
new_loc['USER']['user'] = self.username
save_json(new_loc,
path.join(self.credentials_home, location + '.json'))
def chk_spaces(self):
if self.spaces_in_paths:
f_paths_spaces = os.path.join(self.NIMB_tmp,
'paths_with_spaces.json')
save_json(self.spaces_in_paths, f_paths_spaces)
len_spaces = len(self.spaces_in_paths)
log.info(
f' ATTENTION: ERR: paths of {len_spaces} subjects have spaces \
and will not be processed by FreeSurfer')
log.info(
f' ATTENTION: paths with spaces can be found here: {f_paths_spaces}'
)
log.info(
' ATTENTION: nimb can change spaces to underscores when adding the parameter: -fix-spaces; \
example: python nimb.py -process classify -project Project -fix-spaces'
)
def update_config(self):
"""....."""
self.add_criterion = False
self.config = load_json(self.config_file)
criterion1 = 'SeriesDescription'
sidecar_crit1 = self.sidecar_content[criterion1]
list_criteria = list()
for des in self.config['descriptions']:
if des['dataType'] == self.data_Type and \
des["modalityLabel"] == self.modalityLabel:
list_criteria.append(des)
if len(list_criteria) > 0:
print(
f'{" " *12}> there is at least one configuration with dataType: {self.data_Type}'
)
for des in list_criteria[::-1]:
if criterion1 in des['criteria']:
if des['criteria'][criterion1] == sidecar_crit1:
print(
f'{" " *12} sidecar is present in the config file. Add another sidecar criterion in the dcm2bids_helper.py script'
)
self.add_criterion = True
sys.exit(0)
else:
list_criteria.remove(des)
if len(list_criteria) > 0:
print(
f'{" " *12}> cannot find a correct sidecar location. Please add more parameters.'
)
if len(list_criteria) == 0:
print(f'{" " *12}> updating config with value: {sidecar_crit1}')
new_des = {
'dataType': self.data_Type,
'modalityLabel': self.modalityLabel,
'criteria': {
criterion1: sidecar_crit1
}
}
self.config['descriptions'].append(new_des)
self.update = True
if self.update:
self.run_stt = 0
save_json(self.config, self.config_file, print_space=12)
else:
print(f'{" " *12}criterion {criterion1} present in config file')
def check_nan(self, df, err_file_abspath):
d_err = dict()
cols_with_nans = list()
for col in df.columns:
if df[col].isnull().values.any():
ls = df[col].isnull().tolist()
for val in ls:
if val:
ix = df.index[ls.index(val)]
if ix not in d_err:
d_err[ix] = list()
if col not in d_err[ix]:
d_err[ix].append(col)
if col not in cols_with_nans:
cols_with_nans.append(col)
save_json(d_err, err_file_abspath)
return d_err, cols_with_nans
def run(self):
self.dir_2classify = self.get_dirs2classify()
for self._dir in self.dir_2classify:
self.archived = False
dir_abspath = os.path.join(self.MAIN_DIR, self._dir)
self.main = self.get_dict_4classification(dir_abspath)
paths_2mris = self._get_MR_paths(dir_abspath)
if paths_2mris:
if self.archived:
bids_ids = self.get_bids_ids(paths_2mris)
for bids_id in bids_ids:
# self.main[bids_id] = dict()
paths_2classify = self.get_content_per_bids_id(
paths_2mris, bids_id)
BIDS_classifed = self.classify_2bids(paths_2classify)
self.main[bids_id] = BIDS_classifed
self.main[bids_id]['archived'] = str(dir_abspath)
else:
# self.main[self._dir] = dict()
paths_2classify = paths_2mris
BIDS_classifed = self.classify_2bids(paths_2classify)
self.main[self._dir] = BIDS_classifed
self.main[self._dir]['archived'] = ''
log.info(" saving classification file")
save_json(self.main, self.f_nimb_classified)
else:
log.info(
f' there are no file or folders in the provided path to read: {dir_abspath}'
)
log.info(
f"classification of new subjects is complete, file located at: {self.f_nimb_classified}"
)
if self.multiple_T1 == 1:
from classification.get_mr_params import verify_MRIs_for_similarity
self.main = verify_MRIs_for_similarity(self.main, self.NIMB_tmp,
self.flair_t2_add)
else:
self.main = self.keep_only1_T1()
self.chk_spaces()
if os.path.exists(self.f_nimb_classified):
return True, self.main
else:
return False, self.main
def save_df_Emmanuelle(df,
groups,
stats_dic,
cols2color_sig,
path2save,
make_with_colors,
extensions=('xlsx', 'csv', 'json')):
if 'xlsx' in extensions:
import openpyxl
import string
df.to_excel('stats_new.xlsx')
########## MERGE MEAN/STD SUB-INDEXES ################
file = openpyxl.load_workbook('stats_new.xlsx')
sheet = file['Sheet1']
alpha = string.ascii_uppercase
for ltr in range(len(alpha))[1:(2 * len(groups)) + 1:2]:
cell1, cell2 = alpha[ltr] + str(2), alpha[ltr + 1] + str(2)
sheet.merge_cells(str(cell1 + ':' + cell2))
file.save('stats_new.xlsx')
if 'json' in extensions:
utilities.save_json(stats_dic, os.path.join(path2save, 'stats.json'))
if 'csv' in extensions:
tab = Table()
tab.save_df(df,
os.path.join(path2save, 'stats_new.csv'),
sheet_name='stats')
if make_with_colors:
save_2xlsx_with_colors_Emmanuelle(df,
'stats_new.xlsx',
path2save,
'stats_wcolors.xlsx',
cols2color_sig=cols2color_sig)
def __init__(self,
all_vars,
PATHglm,
sig_fdr_thresh = 3.0):
'''
sig_fdr_thresh at 3.0 corresponds to p = 0.001;
for p=0.05 use value 1.3,
but it should be used ONLY for visualisation.
'''
vars_fs = all_vars.location_vars['local']["FREESURFER"]
self.FREESURFER_HOME = vars_fs["FREESURFER_HOME"]
self.SUBJECTS_DIR = vars_fs["SUBJECTS_DIR"]
self.measurements = vars_fs["GLM_measurements"]
self.thresholds = vars_fs["GLM_thresholds"]
self.mc_cache_thresh = vars_fs["GLM_MCz_cache"]
param = fs_definitions.FSGLMParams(PATHglm)
self.PATHglm = PATHglm
self.sig_fdr_thresh = sig_fdr_thresh
self.PATHglm_glm = param.PATHglm_glm
self.PATH_img = param.PATH_img
self.PATHglm_results = param.PATHglm_results
self.sig_fdr_json = param.sig_fdr_json
self.sig_mc_json = param.sig_mc_json
self.err_mris_preproc_file = param.err_mris_preproc_file
self.mcz_sim_direction = param.mcz_sim_direction
self.hemispheres = fs_definitions.hemi
self.GLM_sim_fwhm4csd = param.GLM_sim_fwhm4csd
self.GLM_MCz_meas_codes = param.GLM_MCz_meas_codes
self.cluster_stats = param.cluster_stats
self.cluster_stats_2csv = param.cluster_stats_2csv
self.sig_contrasts = param.sig_contrasts
RUN = True
# get files_glm.
try:
files_glm = load_json(param.files_for_glm)
print(f' successfully uploaded file: {param.files_for_glm}')
except ImportError as e:
print(e)
print(f' file {param.files_for_glm} is missing')
RUN = False
# get file with subjects per group
try:
subjects_per_group = load_json(param.subjects_per_group)
print(f' successfully uploaded file: {param.subjects_per_group}')
except Exception as e:
print(e)
print(f' file {param.subjects_per_group} is missing')
RUN = False
# checking that all subjects are present
print(' subjects are located in: {}'.format(self.SUBJECTS_DIR))
for group in subjects_per_group:
for subject in subjects_per_group[group]:
if subject not in os.listdir(self.SUBJECTS_DIR):
print(f' subject is missing from FreeSurfer Subjects folder: {subject}')
RUN = False
break
for subdir in (self.PATHglm_glm, self.PATHglm_results, self.PATH_img):
if not os.path.isdir(subdir): os.makedirs(subdir)
if not os.path.isfile(self.sig_contrasts):
open(self.sig_contrasts,'w').close()
if RUN:
self.err_preproc = list()
self.sig_fdr_data = dict()
self.sig_mc_data = dict()
self.run_loop(files_glm)
if self.err_preproc:
save_json(self.err_preproc, self.err_mris_preproc_file)
if self.sig_fdr_data:
save_json(self.sig_fdr_data, self.sig_fdr_json)
if self.sig_mc_data:
save_json(self.sig_mc_data, self.sig_mc_json)
if os.path.exists(self.cluster_stats):
ClusterFile2CSV(self.cluster_stats,
self.cluster_stats_2csv)
print('\n\nGLM DONE')
else:
sys.exit('some ERRORS were found. Cannot perform FreeSurfer GLM')
def setup_default_local_nimb(self):
shutil.copy(
os.path.join(os.path.dirname(os.path.abspath(__file__)),
'local.json'),
os.path.join(self.credentials_home, 'remote1.json'))
local_vars = self.load_file('local', default=True)
local_vars['USER']['user'] = _get_username()
'''setting NIMB paths'''
NIMB_PATHS = local_vars['NIMB_PATHS']
NIMB_HOME = os.path.abspath(
os.path.join(os.path.dirname(__file__), '..'))
print('NIMB_HOME is: ', NIMB_HOME)
NIMB_PATHS['NIMB_HOME'] = NIMB_HOME
new_NIMB_tmp = get_userdefined_paths(
'NIMB temporary folder nimb_tmp',
os.path.join(NIMB_HOME.replace('/nimb/nimb', ''), 'nimb_tmp'),
'nimb_tmp')
if not path.exists(new_NIMB_tmp):
makedirs(new_NIMB_tmp)
NIMB_PATHS['NIMB_tmp'] = new_NIMB_tmp
NIMB_PATHS['NIMB_NEW_SUBJECTS'] = os.path.join(new_NIMB_tmp,
'nimb_new_subjects')
'''setting FREESURFER paths'''
new_freesurfer_path = get_userdefined_paths(
'FreeSurfer folder',
os.path.join(NIMB_HOME.replace('/nimb/nimb', ''), 'freesurfer'),
'freesurfer')
new_conda_path = new_freesurfer_path.replace("freesurfer", "conda3")
NIMB_PATHS['conda_home'] = new_conda_path
NIMB_PATHS['miniconda_python_run'] = os.path.join(
new_conda_path, 'bin',
'python3.7').replace(os.path.expanduser("~"), "~")
local_vars['NIMB_PATHS'] = NIMB_PATHS
FS_PATHS = local_vars['FREESURFER']
FS_PATHS['FREESURFER_HOME'] = new_freesurfer_path
FS_PATHS['FS_SUBJECTS_DIR'] = os.path.join(new_freesurfer_path,
'subjects')
FS_PATHS[
'export_FreeSurfer_cmd'] = "export FREESURFER_HOME=" + new_freesurfer_path
if not os.path.exists(new_freesurfer_path):
FreeSurfer_install = get_yes_no(
f'do you want to install FreeSurfer at the provided location {new_freesurfer_path}? (y/n)'
)
FS_PATHS['FreeSurfer_install'] = FreeSurfer_install
if FreeSurfer_install == 1:
freesurfer_license = get_FS_license()
FS_PATHS['freesurfer_license'] = freesurfer_license
else:
FS_PATHS['FreeSurfer_install'] = 1
local_vars['FREESURFER'] = FS_PATHS
'''setting PROCESSING paths'''
environ = get_yes_no(
"Will this account use slurm or tmux for processing ? (y/n; y=slurm/ n=tmux)"
)
if environ == 1:
local_vars['PROCESSING']['processing_env'] = 'slurm'
supervisor = input(
"For some slurm environments a supervisor account is required. Please type supervisor account name or leave blank:"
)
if supervisor:
print('supervisor account name is: {}'.format(supervisor))
local_vars['USER']['supervisor_account'] = str(supervisor)
local_vars['PROCESSING']['supervisor_account'] = str(
supervisor)
local_vars['PROCESSING']['text4_scheduler'][1] = local_vars[
'PROCESSING']['text4_scheduler'][1].replace(
'def-supervisor', supervisor)
else:
print('supervisor account not provided')
local_vars['USER']['supervisor_account'] = ''
local_vars['PROCESSING']['supervisor_account'] = ''
local_vars['PROCESSING']['text4_scheduler'].remove(
local_vars['PROCESSING']['text4_scheduler'][1])
else:
print('environment for processing is: {}'.format(environ))
local_vars['PROCESSING']['processing_env'] = 'tmux'
save_json(local_vars, os.path.join(self.credentials_home,
'local.json'))
self.get_all_locations_vars()
def chk_if_subjects_ready(self):
fs_proc_ids = self.get_ids_processed()
miss_bids_ids = [
i for i in self.bids_ids if i not in fs_proc_ids.keys()
]
if miss_bids_ids:
print(
f' {len(miss_bids_ids)} IDs are missing from file: {self.f_ids_processed}'
)
print(f' first 5 IDs are: {self.f_ids_processed[:5]}')
for bids_id in miss_bids_ids:
self.add_to_miss(bids_id, 'id_missing')
if len(miss_bids_ids) < len(fs_proc_ids.keys()):
for bids_id in [
i for i in self.bids_ids if i not in miss_bids_ids
]:
fs_proc_id = fs_proc_ids[bids_id].replace(
self.archive_type, '')
if os.path.exists(os.path.join(self.FS_SUBJECTS_DIR, bids_id)):
self.ids_4fs_glm[bids_id] = bids_id
self.chk_glm_files(bids_id)
elif os.path.exists(
os.path.join(self.FS_SUBJECTS_DIR, fs_proc_id)):
self.ids_4fs_glm[bids_id] = fs_proc_id
self.chk_glm_files(fs_proc_id)
else:
print(f'id {bids_id} or freesurfer id {fs_proc_id} \
are missing from the {self.FS_SUBJECTS_DIR} folder')
self.add_to_miss(bids_id, 'id_missing')
if self.miss.keys():
print(" missing files and ids: ", self.miss)
save_json(self.miss, self.ids_exclude_glm, print_space=8)
subjs_missing = len(self.miss.keys())
subjs_present = len(self.ids_4fs_glm.keys())
print(f' Number of participants ready for FreeSurfer GLM:')
print(f' in the folder: {self.FS_SUBJECTS_DIR}')
print(f' {subjs_present} present')
print(f' {subjs_missing} missing')
not_ready = [
i for i in self.miss if "id_missing" not in self.miss[i]
]
maybe_archived = [i for i in self.miss if i not in not_ready]
if maybe_archived:
print(" MAYBE archived: ", maybe_archived)
q = " EXCEPTION! Some IDs are missing, but they could be archived.\n\
Do you want to do glm analysis with current subjects (y) or try to check the archive (n) ? (y/n)\n\
(note: if you answer NO, you will be asked to unarchive the \n\
processed folders of IDs if they are present in FREESURFER_PROCESSED)"
if get_yes_no(q) == 1:
self.create_fs_glm_df()
return True, list()
else:
return False, maybe_archived
if not_ready:
print(
" MISSING FILES: these participant CANNOT be included in the GLM analysis: ",
not_ready)
q = " EXCEPTION! Some IDs have missing files and they MUST be excluded from analysis.\n\
Do you want to continue without excluded IDs ? (y/n)"
if get_yes_no(q) == 1:
self.create_fs_glm_df()
return True, list()
else:
return False, not_ready
else:
self.create_fs_glm_df()
return True, list()
else:
print(' no ids found')
return False, list()
def run_anova(self, p_thresh, intercept_thresh, path2save):
ls_err = list()
for param_y in self.params_y:
x = np.array(self.df[param_y])
df_result = self.tab.get_clean_df()
df_result_list = df_result.copy()
df_result[param_y] = ''
df_result_list[param_y] = ''
ix = 1
ixx = 1
# print(f' analysing {len(self.ls_cols4anova)} features for parameter: {param_y}')
for col in self.ls_cols4anova:
y = np.array(self.df[col])
data_tmp = pd.DataFrame({'x': x, col: y})
model = ols(col + " ~ x", data=data_tmp).fit()
if model.pvalues.Intercept < p_thresh and model.pvalues.x < intercept_thresh:
measurement, structure, ls_err = self.fs_struc_meas.get(
col, ls_err)
if param_y not in self.sig_cols:
self.sig_cols[param_y] = dict()
self.sig_cols[param_y][col] = {
'rsquared': model.rsquared,
'rsquared-adjusted': model.rsquared_adj,
'F-statistic': model.fvalue,
'AIC': model.aic,
'BIC': model.bic,
'pvalue_slope': model.pvalues.x,
'pvalue_intercept': model.pvalues.Intercept,
'tvalue_slope': model.tvalues.x,
'tvalue_intercept': model.tvalues.Intercept,
'meas': measurement,
'struct': structure
}
df_result_list = self.populate_df(
df_result_list, ixx, {
param_y: structure,
'measure': measurement,
'pvalue': '%.4f' % model.pvalues.x
})
if structure not in df_result[param_y].tolist():
df_result = self.populate_df(
df_result, ix, {
param_y: structure,
measurement: '%.4f' % model.pvalues.x
})
ix += 1
else:
df_result = self.populate_df(
df_result,
df_result[param_y].tolist().index(structure),
{measurement: '%.4f' % model.pvalues.x})
ixx += 1
self.tab.save_df_tocsv(
df_result_list,
path.join(path2save, f'anova_per_significance_{param_y}.csv'))
self.tab.save_df_tocsv(
df_result,
path.join(path2save, f'anova_per_structure_{param_y}.csv'))
save_json(self.sig_cols,
path.join(path2save, f'anova_significant_features.json'))
if self.print_not_FS:
print('NOT freesurfer structures: ', ls_err)
def mkstatisticsf(df_4stats,
groups,
group_col,
path2save,
make_with_colors=True):
'''Creates discriptive statistical file for publication,
based on provided pandas.DataFrame
Works only on 2 groups
Args: df_4stats: pandas.DataFrame
group: list/ tuple of groups as str/int
group_col: str() column name in df_4stats that has the group names from group
path_2save: abspath to save the descrptive files
make_with_colors: will create an additional .xlsx file with
colored significant results,
provided xlwt is installed
Return:
json file with results
.csv file with results
.xlsx file with results with red colored significant ones
'''
tab = Table()
ls_tests = ('mean', 'std', 'kurtosis', 'skewness', 'TTest', 'Welch',
'ANOVA', 'Bartlett', 'MannWhitneyu', 'Kruskal')
groups_df = dict()
for group in groups:
groups_df[group] = tab.get_df_per_parameter(df_4stats, group_col,
group)
stats_dic = dict()
vals2chk = df_4stats.columns.tolist()
if group_col in vals2chk:
vals2chk.remove(group_col)
cols2color_sig = list()
groups = list(groups_df.keys())
group1 = groups_df[groups[0]]
group2 = groups_df[groups[1]]
for test in ls_tests:
for val in vals2chk:
results, params = get_stats(test, group1[val], group2[val])
if test in ('mean', 'std', 'kurtosis', 'skewness'):
key1 = f'{groups[0]}, {params[0]}'
key2 = f'{groups[1]}, {params[0]}'
else:
key1 = f'{test}, {params[0]}'
key2 = f'{test}, {params[1]}'
cols2color_sig.append(key2)
for key in (key1, key2):
if key not in stats_dic:
stats_dic[key] = dict()
stats_dic[key1][val] = f'{results[0]}'
stats_dic[key2][val] = f'{results[1]}'
df = tab.create_df_from_dict(stats_dic)
tab.save_df(df,
os.path.join(path2save, 'stats_general.csv'),
sheet_name='stats')
utilities.save_json(stats_dic, os.path.join(path2save,
'stats_general.json'))
if make_with_colors:
save_2xlsx_with_colors(df,
path2save=path2save,
cols2color_sig=cols2color_sig)
