def cogtest_manipulation(tbldict, roc_cols):
"""Process table containing cognitive testing data
Parameters
----------
tbldict : dict
Dictionary of DataFrames each containing a different type of data
roc_cols : list
List of strings corresponding to column names for which rate of change should be
calculated
Returns
-------
tbldict : dict
The same as input tbldict but now with new item
"""
tbldict['cogtests'] = pd.merge(tbldict['cogtestdates'],tbldict['cogdata'],on=['codeb','NP_Tp'])
del tbldict['cogtestdates']
del tbldict['cogdata']
for col in roc_cols:
tbldict['cogtests'] = cf.rate_of_change(tbldict['cogtests'], 'codeb', 'NP_Tp',
'NP_Date', col, '%s_sl' %col)
#add column for maximum follow-up time per subject
tbldict['cogtests'] = cf.max_per_sub(tbldict['cogtests'], 'codeb', 'NP_YrsRelBL', 'NP_Followup_Time')
return tbldict
def mri_run(datadir, outdir, rois):
"""Main function to collect MRI volume data
Parameters
----------
datadir : string
Full path to root directory of freesurfer processed data. Expect file tree
to be datadir/subcode/stats/aseg.stats
outdir : string
Full path to directory where data will be saved
rois : list of strings
List of freesurfer rois of interest. These volumes of these rois will be
inserted in aseg_change along with their rates of change
Returns
-------
aseg_stats : pandas DataFrame
DataFrame where each row is a scan, and columns are volumes of all
freesurfer processed regions
aseg_change : pandas DataFrame
DataFrame where each row is a scan, and columns are the volumes of interest,
their rates of change, and icv correction
"""
#get aseg_stats data from freesurfer processed data
outfile = '%sFS_aseg_stats.txt' %outdir
subs, asegout, output = extractFSasegstats(datadir, outfile)
aseg_stats = pd.read_csv(outfile, header=0, delim_whitespace=True)
#add columns for SubjID and MRI_TP
aseg_stats['codea'] = [cf.get_id(sub) for sub in subs]
aseg_stats['MRI_Tp'] = [cf.get_tp(sub) for sub in subs]
aseg_stats.drop('Measure:volume', axis=1, inplace=True)
#get dates of MRI scans that were processed with freesurfer
mridates = bacs_pet_mri_date_batch(datadir)
aseg_change = pd.merge(aseg_change, mridates, on=['codea','MRI_Tp'])
rois_icvcorr = dict([(roi, '%s_icvcorr' %roi) for roi in rois])
aseg_change = icvcorr(aseg_change, rois_icvcorr, 'IntraCranialVol')
#calculate rate of change in years
for roi in rois:
aseg_change = cf.rate_of_change(aseg_change, 'codea', 'MRI_Tp',
'MRI_Scandate', roi, '%s_sl' %roi)
cf.save_xls_and_pkl(aseg_stats, 'aseg_stats', outdir)
cf.save_xls_and_pkl(aseg_change, 'aseg_change', outdir)
return aseg_stats, aseg_change
def pibparams_run(path_pib, pibrename, outdir, pibcutoff):
"""Reads data from the spreadsheet, does some calculations, and
returns a Pandas dataframe with PIB data.
Parameters
----------
path_pib : string
String of full path to *.xls
pibrename : dict
Dictionary of name:rename pairs, where the keys are columns in the
PIB spreadsheet and values are what to rename the keys to
outdir : string
Full path where final dataframe will be saved
pibcutoff : float
PIB cutoff value
Returns
-------
pib_df : pandas dataframe
Dataframe containing all PIB data
"""
#read in pib data from old sheet
pib_old = pd.read_excel(path_pib, sheetname='i')
#read in PIB data from longitudinal timepoints
pib_long = pd.read_excel(path_pib, sheetname='j')
#concatenate PIB tables
pib_df = pd.concat([pib_long, pib_old])
pib_df = pib_df[pibrename.keys()]
pib_df.rename(columns=pibrename, inplace=True)
#make binary PIB value
pib_df['PIB_Pos'] = pib_df['PIB_Index'].apply(lambda x: 1 if x >= pibcutoff else 0)
#calculate rate of change of PIB_Index in years
pib_df = cf.rate_of_change(pib_df, 'codea', 'PIB_Tp', 'PIB_Scandate',
'PIB_Index', 'PIB_sl')
#make column for the age at which PIB positivity appears
pib_df.sort(columns=['codea','PIB_Tp'], inplace=True)
#calculate age of PIB positivity
pib_df['PIB_agepos'] = float('nan')
pib_df = pib_df.groupby(by='codea')
pib_df = pib_df.apply(f)
cf.save_xls_and_pkl(pib_df, 'pibparams', outdir)
return pib_df