antspymm 1.3.3__py3-none-any.whl → 1.3.5__py3-none-any.whl

antspymm/mm.py

@@ -1061,6 +1061,27 @@ def nrg_format_path( projectID, subjectID, date, modality, imageID, separator='-
     return os.path.join( thedirectory, thefilename )
 
 
+def get_first_item_as_string(df, column_name):
+    """
+    Check if the first item in the specified column of the DataFrame is a string.
+    If it is not a string, attempt to convert it to an integer and then to a string.
+
+    Parameters:
+    df (pd.DataFrame): The DataFrame to operate on.
+    column_name (str): The name of the column to check.
+
+    Returns:
+    str: The first item in the specified column, guaranteed to be returned as a string.
+    """
+    if isinstance(df[column_name].iloc[0], str):
+        return df[column_name].iloc[0]
+    else:
+        try:
+            return str(int(df[column_name].iloc[0]))
+        except ValueError:
+            raise ValueError("The value cannot be converted to an integer.")
+
+
 def study_dataframe_from_matched_dataframe( matched_dataframe, rootdir, outputdir, verbose=False ):
     """
     converts the output of antspymm.match_modalities dataframe (one row) to that needed for a study-driving dataframe for input to mm_csv
@@ -1078,12 +1099,12 @@ def study_dataframe_from_matched_dataframe( matched_dataframe, rootdir, outputdi
     musthavecols = ['projectID', 'subjectID','date','imageID','filename']
     for k in range(len(musthavecols)):
         if not musthavecols[k] in matched_dataframe.keys():
-            raise ValueError('matched_dataframe is missing column ' +musthavecols[k] + ' in study_dataframe_from_qc_dataframe' )
+            raise ValueError('matched_dataframe is missing column ' + musthavecols[k] + ' in study_dataframe_from_qc_dataframe' )
     csvrow=matched_dataframe.dropna(axis=1)
-    pid=str(csvrow['projectID'].iloc[0] )
-    sid=str(csvrow['subjectID'].iloc[0] )
-    dt=str(csvrow['date'].iloc[0])
-    iid=str(csvrow['imageID'].iloc[0])
+    pid=get_first_item_as_string( csvrow, 'projectID'  )
+    sid=get_first_item_as_string( csvrow, 'subjectID'  ) # str(csvrow['subjectID'].iloc[0] )
+    dt=get_first_item_as_string( csvrow, 'date'  )  # str(csvrow['date'].iloc[0])
+    iid=get_first_item_as_string( csvrow, 'imageID'  ) # str(csvrow['imageID'].iloc[0])
     nrgt1fn=os.path.join( rootdir, pid, sid, dt, 'T1w', iid, str(csvrow['filename'].iloc[0]+iext) )
     if not exists( nrgt1fn ):
         raise ValueError("T1 " + nrgt1fn + " does not exist in study_dataframe_from_qc_dataframe")
@@ -1092,32 +1113,32 @@ def study_dataframe_from_matched_dataframe( matched_dataframe, rootdir, outputdi
     rsfList=[]
     nmList=[]
     if 'flairfn' in csvrow.keys():
-        flid=str(int(csvrow['flairid'].iloc[0]))
+        flid=get_first_item_as_string( csvrow, 'flairid' )
         nrgt2fn=os.path.join( rootdir, pid, sid, dt, 'T2Flair', flid, str(csvrow['flairfn'].iloc[0]+iext) )
         if exists( nrgt2fn ):
             flList.append( nrgt2fn )
     if 'dtfn1' in csvrow.keys():
-        dtid=str(int(csvrow['dtid1'].iloc[0]))
+        dtid=get_first_item_as_string( csvrow, 'dtid1' )
         dtfn1=glob.glob(os.path.join( rootdir, pid, sid, dt, 'DTI*', dtid, str(csvrow['dtfn1'].iloc[0]+iext) ))[0]
         if exists( dtfn1 ):
             dtList.append( dtfn1 )
     if 'dtfn2' in csvrow.keys():
-        dtid=str(int(csvrow['dtid2'].iloc[0]))
+        dtid=get_first_item_as_string( csvrow, 'dtid2' )
         dtfn2=glob.glob(os.path.join(rootdir, pid, sid, dt, 'DTI*', dtid, str(csvrow['dtfn2'].iloc[0]+iext) ))[0]
         if exists( dtfn2 ):
             dtList.append( dtfn2 )
     if 'dtfn3' in csvrow.keys():
-        dtid=str(int(csvrow['dtid3'].iloc[0]))
+        dtid=get_first_item_as_string( csvrow, 'dtid3' )
         dtfn3=glob.glob(os.path.join(rootdir, pid, sid, dt, 'DTI*', dtid, str(csvrow['dtfn3'].iloc[0]+iext) ))[0]
         if exists( dtfn3 ):
             dtList.append( dtfn3 )
     if 'rsffn1' in csvrow.keys():
-        rsid=str(int(csvrow['rsfid1'].iloc[0]))
+        rsid=get_first_item_as_string( csvrow, 'rsfid1' )
         rsfn1=glob.glob(os.path.join( rootdir, pid, sid, dt, 'rsfMRI*', rsid, str(csvrow['rsffn1'].iloc[0]+iext) ))[0]
         if exists( rsfn1 ):
             rsfList.append( rsfn1 )
     if 'rsffn2' in csvrow.keys():
-        rsid=str(int(csvrow['rsfid2'].iloc[0]))
+        rsid=get_first_item_as_string( csvrow, 'rsfid2' )
         rsfn2=glob.glob(os.path.join( rootdir, pid, sid, dt, 'rsfMRI*', rsid, str(csvrow['rsffn2'].iloc[0]+iext) ))[0]
         if exists( rsfn2 ):
             rsfList.append( rsfn2 )
@@ -1125,7 +1146,7 @@ def study_dataframe_from_matched_dataframe( matched_dataframe, rootdir, outputdi
         keyname="nmfn"+str(j)
         keynameid="nmid"+str(j)
         if keyname in csvrow.keys() and keynameid in csvrow.keys():
-            nmid=str(int(csvrow[keynameid].iloc[0]))
+            nmid=get_first_item_as_string( csvrow, keynameid )
             nmsearchpath=os.path.join( rootdir, pid, sid, dt, 'NM2DMT', nmid, "*"+nmid+iext)
             nmfn=glob.glob( nmsearchpath )
             nmfn=nmfn[0]
@@ -3430,6 +3451,9 @@ def dipy_dti_recon(
         bvals = bvalsfn.copy()
         bvecs = bvecsfn.copy()
 
+    if bvals.max() < 1.0:
+        raise ValueError("DTI recon error: maximum bvalues are too small.")
+
     b0_idx = segment_timeseries_by_bvalue( bvals )['highermeans']
 
     b0 = ants.slice_image( image, axis=3, idx=b0_idx[0] )
@@ -7954,16 +7978,21 @@ def mm_csv(
                 hier['dataframes'], identifier=None )
         t1wide.to_csv( hierfn + 'mmwide.csv' )
     ################# read the hierarchical data ###############################
+    # over-write the rbp data with a consistent and recent approach ############
+    myx = antspyt1w.inspect_raw_t1( t1, hierfn + 'rbp' , option='both' ) 
+    del myx
     hier = antspyt1w.read_hierarchical( hierfn )
     if exists( hierfn + 'mmwide.csv' ) :
         t1wide = pd.read_csv( hierfn + 'mmwide.csv' )
     elif not testloop:
         t1wide = antspyt1w.merge_hierarchical_csvs_to_wide_format(
                 hier['dataframes'], identifier=None )
-    if t1wide['resnetGrade'].iloc[0] < 0.35:
-        rgrade = str( t1wide['resnetGrade'].iloc[0] )
+    rgrade = str( t1wide['resnetGrade'].iloc[0] )
+    if t1wide['resnetGrade'].iloc[0] < 0.20:
         warnings.warn('T1w quality check indicates failure: ' + rgrade + " will not process." )
         return
+    else:
+        print('T1w quality check indicates success: ' + rgrade + " will process." )
 
     if srmodel_T1 is not False :
         hierfntest = hierfnSR + 'mtl.csv'
@@ -9523,6 +9552,7 @@ def blind_image_assessment(
         image_reference = ants.image_clone( image )
     ntimepoints = 1
     bvalueMax=None
+    bvecnorm=None
     if image_reference.dimension == 4:
         ntimepoints = image_reference.shape[3]
         if "DTI" in image_filename:
@@ -9535,6 +9565,8 @@ def blind_image_assessment(
             if exists( bval_name ) and exists( bvec_name ):
                 bvals, bvecs = read_bvals_bvecs( bval_name , bvec_name  )
                 bvalueMax = bvals.max()
+                bvecnorm = np.linalg.norm(bvecs,axis=1).reshape( bvecs.shape[0],1 )
+                bvecnorm = bvecnorm.max()
         else:
             image_b0 = ants.get_average_of_timeseries( image_reference ).iMath("Normalize")
     else:
@@ -9700,11 +9732,11 @@ def blind_image_assessment(
             noizlevel, snrref, cnrref, psnrref, ssimref, mymi, asym_err, myevr, msk_vol, 
             spc[0], spc[1], spc[2],org[0], org[1], org[2], 
             image.shape[0], image.shape[1], image.shape[2], ntimepoints, 
-            jjj, modality, mriseries, mrimfg, mrimodel, MagneticFieldStrength, mriSAR, PixelBandwidth, BandwidthPerPixelPhaseEncode, bvalueMax ]], 
+            jjj, modality, mriseries, mrimfg, mrimodel, MagneticFieldStrength, mriSAR, PixelBandwidth, BandwidthPerPixelPhaseEncode, bvalueMax, bvecnorm ]], 
             columns=[
                 'filename', 
                 'dimensionality',
-                'noise', 'snr', 'cnr', 'psnr', 'ssim', 'mi', 'reflection_err', 'EVR', 'msk_vol', 'spc0','spc1','spc2','org0','org1','org2','dimx','dimy','dimz','dimt','slice','modality', 'mriseries', 'mrimfg', 'mrimodel', 'mriMagneticFieldStrength', 'mriSAR', 'mriPixelBandwidth', 'mriPixelBandwidthPE', 'dti_bvalueMax' ])
+                'noise', 'snr', 'cnr', 'psnr', 'ssim', 'mi', 'reflection_err', 'EVR', 'msk_vol', 'spc0','spc1','spc2','org0','org1','org2','dimx','dimy','dimz','dimt','slice','modality', 'mriseries', 'mrimfg', 'mrimodel', 'mriMagneticFieldStrength', 'mriSAR', 'mriPixelBandwidth', 'mriPixelBandwidthPE', 'dti_bvalueMax', 'dti_bvecnorm' ])
         outdf = pd.concat( [outdf, df ], axis=0, ignore_index=False )
         if verbose:
             print( outdf )
@@ -10467,6 +10499,7 @@ def brainmap_figure(statistical_df, data_dictionary_path, output_prefix, brain_i
                 print(str(k) +  " " + anattoshow[k]  )
             mysub = zz[zz['anat'].str.contains(anattoshow[k])]
             anatsear=re.sub("dti.fa","",anattoshow[k])
+            anatsear=re.sub("cbf.","",anatsear)
             anatsear=re.sub("t1.volasym","",anatsear)
             anatsear=re.sub("t1.thkasym","",anatsear)
             anatsear=re.sub("t1.areaasym","",anatsear)
@@ -10482,6 +10515,8 @@ def brainmap_figure(statistical_df, data_dictionary_path, output_prefix, brain_i
             anatsear=re.sub("dti.mean.fa.","",anatsear)
             anatsear=re.sub("lravg","",anatsear)
             atlassearch = mydict['tidynames'].str.contains(anatsear)
+            if verbose:
+                print( " anatsear " + anatsear + " atlassearch " )
             if atlassearch.sum() > 0:
                 whichatlas = mydict[atlassearch]['Atlas'].iloc[0]
                 oglabelname = mydict[atlassearch]['Label'].iloc[0]
@@ -10490,13 +10525,13 @@ def brainmap_figure(statistical_df, data_dictionary_path, output_prefix, brain_i
                 oglabelname='unknown'
                 whichatlas=None
             if verbose:
-                print("oglabelname " + oglabelname )
+                print("oglabelname " + oglabelname + " whichatlas " + str(whichatlas) )
             vals2viz = mysub[col2viz].agg(['min', 'max'])
             vals2viz = vals2viz[abs(vals2viz).idxmax()]
             myext = None
-            if 'dktcortex' in anattoshow[k]:
+            if 'dktcortex' in anattoshow[k] or whichatlas == 'desikan-killiany-tourville' or 'dtkregions' in anattoshow[k]:
                 myext = 'dkt_cortex'
-            elif 'cit168' in anattoshow[k]:
+            elif 'cit168' in anattoshow[k] or whichatlas == 'CIT168':
                 myext = 'cit168lab'
             elif 'mtl' in anattoshow[k]:
                 myext = 'mtl'
@@ -10601,9 +10636,17 @@ def brainmap_figure(statistical_df, data_dictionary_path, output_prefix, brain_i
                 print("oglabelname " + oglabelname )
 
             if myext == 'cerebellum':
-                atlasDescript['Description'] = atlasDescript['Description'].str.replace("l_", "")
-                atlasDescript['Description'] = atlasDescript['Description'].str.replace("r_", "")
-                whichindex = atlasDescript.index[atlasDescript['Description'] == oglabelname].values[0]
+                if not atlasDescript.empty and 'Description' in atlasDescript.columns:
+                    atlasDescript['Description'] = atlasDescript['Description'].str.replace("l_", "")
+                    atlasDescript['Description'] = atlasDescript['Description'].str.replace("r_", "")
+                    oglabelname=re.sub("ravg","",oglabelname)
+                    oglabelname=re.sub("lavg","",oglabelname)
+                    whichindex = atlasDescript.index[atlasDescript['Description'] == oglabelname].values[0]
+                else:
+                    if atlasDescript.empty:
+                        print("The DataFrame 'atlasDescript' is empty.")
+                    if 'Description' not in atlasDescript.columns:
+                        print("The column 'Description' does not exist in 'atlasDescript'.")
             else:
                 whichindex = atlasDescript.index[atlasDescript['Description'].str.contains(oglabelname)]
 
@@ -10645,10 +10688,10 @@ def brainmap_figure(statistical_df, data_dictionary_path, output_prefix, brain_i
             if fixed_overlay_range is not None:
                 addemC[0:3,0:3,0:3]=fixed_overlay_range[0]
                 addemC[4:7,4:7,4:7]=fixed_overlay_range[1]
-                addemC[ addemC < fixed_overlay_range[0] ] = fixed_overlay_range[0]
-                addemC[ addemC > fixed_overlay_range[1] ] = fixed_overlay_range[1]
+                addemC[ addemC <= fixed_overlay_range[0] ] = 0 # fixed_overlay_range[0]
+                addemC[ addemC >= fixed_overlay_range[1] ] = fixed_overlay_range[1]
             ants.plot(edgeimgC, addemC, axis=axx, nslices=nslices, ncol=ncol,       
-                overlay_cmap=overlay_cmap, resample=False,
+                overlay_cmap=overlay_cmap, resample=False, overlay_alpha=1.0,
                 filename=figfn, cbar=axx==axes[0], crop=True, black_bg=black_bg )
         if verbose:
             print(f"{col2viz} done")
@@ -10861,6 +10904,7 @@ def aggregate_antspymm_results_sdf(
     splitsep='-',
     idsep='-',
     wild_card_modality_id=False,
+    second_split=False,
     verbose=False ):
     """
     Aggregate ANTsPyMM results from the specified study data frame and store the aggregated results in a new data frame.  This assumes data is organized on disk 
@@ -10879,6 +10923,7 @@ def aggregate_antspymm_results_sdf(
     - idsep (str): the separator used to partition subjectid date and imageid 
         for example, if idsep is - then we have subjectid-date-imageid
     - wild_card_modality_id (bool): keep if False for safer execution
+    - second_split (bool): this is a hack that will split the imageID by . and keep the first part of the split; may be needed when the input filenames contain .
     - verbose : boolean
 
     Note:
@@ -10950,22 +10995,34 @@ def aggregate_antspymm_results_sdf(
         myfn = os.path.basename( df['filename'].iloc[x] )
         temp = myfn.split( splitsep )
         # Generalized search paths
-        sid0 = str( temp[0] )
+        sid0 = str( temp[1] )
         sid = str( df[subject_col].iloc[x] )
         if sid0 != sid:
-            warnings.warn("OUTER: the id derived from the filename " + sid + " does not match the id stored in the data frame " + sid )
+            warnings.warn("OUTER: the id derived from the filename " + sid0 + " does not match the id stored in the data frame " + sid )
             warnings.warn( "filename is : " +  myfn )
             warnings.warn( "sid is : " + sid )
             warnings.warn( "x is : " + str(x) )
         myproj = str(df[project_col].iloc[x])
         mydate = str(df[date_col].iloc[x])
         myid = str(df[image_col].iloc[x])
+        if second_split:
+            myid = myid.split(".")[0]
         path_template = base_path + "/" + myproj +  "/" + sid + "/" + mydate + '/' + hiervariable + '/' + str(myid) + "/"
         hierfn = sorted(glob( path_template + "*" + hiervariable + "*wide.csv" ) )
+        if len( hierfn ) == 0:
+            print( hierfn )
+            print( path_template )
+            print( myproj )
+            print( sid )
+            print( mydate ) 
+            print( myid )
         if len( hierfn ) > 0:
             keep[x]=True
 
-    df=df[keep]
+    # df=df[keep]
+    if df.shape[0] == 0:
+        warnings.warn("input data frame shape is filtered down to zero")
+        return df
 
     if not df.index.is_unique:
         warnings.warn("data frame does not have unique indices.  we therefore reset the index to allow the function to continue on." )
@@ -10998,7 +11055,8 @@ def aggregate_antspymm_results_sdf(
         myproj = str(df[project_col].iloc[x])
         mydate = str(df[date_col].iloc[x])
         myid = str(df[image_col].iloc[x])
-        myt1id = myid
+        if second_split:
+            myid = myid.split(".")[0]
         if verbose:
             print( myfn )
             print( temp )
@@ -11058,7 +11116,6 @@ def aggregate_antspymm_results_sdf(
                     nlarge = len(t1wfn)
                     t1wfn = find_most_recent_file( t1wfn )
                     warnings.warn("there are " + str( nlarge ) + " number of wide fns with search path " + modsearch + " we take the most recent of these " + t1wfn[0] )
-#                    raise ValueError("there are " + str( len( t1wfn ) ) + " number of wide fns with search path " + modsearch )
                 if len( t1wfn ) == 1:
                     if verbose:
                         print(t1wfn)
@@ -11076,9 +11133,11 @@ def aggregate_antspymm_results_sdf(
             hdf.index = subdf.index.copy()
             subdf = pd.concat( [subdf,hdf], axis=1, ignore_index=False)
             dfout = pd.concat( [dfout,subdf], axis=0, ignore_index=False )
-    badnames = get_names_from_data_frame( ['Unnamed'], dfout )
-    dfout=dfout.drop(badnames, axis=1)
-    return( dfout )
+
+    if dfout.shape[0] > 0:
+        badnames = get_names_from_data_frame( ['Unnamed'], dfout )
+        dfout=dfout.drop(badnames, axis=1)
+    return dfout
 
 def enantiomorphic_filling_without_mask( image, axis=0, intensity='low' ):
     """
@@ -11197,8 +11256,11 @@ def mm_match_by_qc_scoring(df_a, df_b, match_column, criteria, prefix='matched_'
         2. A DataFrame containing rows from df_b that were not matched to df_a.
     """
     from scipy.stats import zscore
-    df_a = df_a.loc[:, ~df_a.columns.str.startswith('Unnamed:')]
-    df_b = df_b.loc[:, ~df_b.columns.str.startswith('Unnamed:')].copy()
+    df_a = df_a.loc[:, ~df_a.columns.str.startswith('Unnamed:')].copy()
+    if df_b is not None:
+        df_b = df_b.loc[:, ~df_b.columns.str.startswith('Unnamed:')].copy()
+    else:
+        return df_a, pd.DataFrame()
     
     # Normalize df_b based on criteria
     for col, crit in criteria.items():
@@ -11378,15 +11440,16 @@ def mm_match_by_qc_scoring_all( qc_dataframe, fix_LRRL=True, verbose=True ):
 
     prefixes = ['NM1_', 'NM2_', 'NM3_', 'NM4_', 'NM5_', 'NM6_']  
     undfmod = nmdf  # Initialize 'undfmod' with 'nmdf' for the first iteration
-    if verbose:
-        print('start NM')
-        print( undfmod.shape )
-    for prefix in prefixes:
-        if undfmod.shape[0] > 50:
-            mmdf, undfmod = mm_match_by_qc_scoring(mmdf, undfmod, 'subjectIDdate', criteria, prefix=prefix, exclude_columns=xcl)
-            if verbose:
-                print( prefix )
-                print( undfmod.shape )
+    if undfmod is not None:
+        if verbose:
+            print('start NM')
+            print( undfmod.shape )
+        for prefix in prefixes:
+            if undfmod.shape[0] > 50:
+                mmdf, undfmod = mm_match_by_qc_scoring(mmdf, undfmod, 'subjectIDdate', criteria, prefix=prefix, exclude_columns=xcl)
+                if verbose:
+                    print( prefix )
+                    print( undfmod.shape )
 
     criteria = {'ol_loop': 'min', 'noise': 'min', 'snr': 'max', 'EVR': 'max', 'dimt':'max'}
     # higher bvalues lead to more noise ...

{antspymm-1.3.3.dist-info → antspymm-1.3.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: antspymm
-Version: 1.3.3
+Version: 1.3.5
 Summary: multi-channel/time-series medical image processing with antspyx
 Home-page: https://github.com/stnava/ANTsPyMM
 Author: Avants, Gosselin, Tustison, Reardon

antspymm-1.3.5.dist-info/RECORD

@@ -0,0 +1,7 @@
+antspymm/__init__.py,sha256=1fHqufHndrkJwz473av8qOf5-1xm5r-aKHuMAETGIiE,4462
+antspymm/mm.py,sha256=7UVUV4vASSwsASTT2aObJX4dg7mU28K4H85106BTuXM,479710
+antspymm-1.3.5.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+antspymm-1.3.5.dist-info/METADATA,sha256=sJaL9YV5hUbe04k_j8YG0DhiNyyJc9CMBo-AdWDH6-M,14590
+antspymm-1.3.5.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+antspymm-1.3.5.dist-info/top_level.txt,sha256=iyD1sRhCKzfwKRJLq5ZUeV9xsv1cGQl8Ejp6QwXM1Zg,9
+antspymm-1.3.5.dist-info/RECORD,,

antspymm-1.3.3.dist-info/RECORD

@@ -1,7 +0,0 @@
-antspymm/__init__.py,sha256=1fHqufHndrkJwz473av8qOf5-1xm5r-aKHuMAETGIiE,4462
-antspymm/mm.py,sha256=R7W1v2ejIjIc5FZaAVLfyX9De8R5A_W2U-AyHZenxUg,476733
-antspymm-1.3.3.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-antspymm-1.3.3.dist-info/METADATA,sha256=PJy3nUwSUKIXi62KNJ73RlPBUwL16kX0ZP32gHq3IAg,14590
-antspymm-1.3.3.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-antspymm-1.3.3.dist-info/top_level.txt,sha256=iyD1sRhCKzfwKRJLq5ZUeV9xsv1cGQl8Ejp6QwXM1Zg,9
-antspymm-1.3.3.dist-info/RECORD,,