Merge pull request #75 from Islast/dev

Remove names_308_style from BrainNetworksInPython
merging ✨

BrainNetworksInPython/datasets/NSPN_WhitakerVertes_PNAS2016/500.names.txt

@@ -1,44 +1,3 @@
-Left-Cerebral-White-Matter
-Left-Lateral-Ventricle
-Left-Inf-Lat-Vent
-Left-Cerebellum-White-Matter
-Left-Cerebellum-Cortex
-Left-Thalamus-Proper
-Left-Caudate
-Left-Putamen
-Left-Pallidum
-3rd-Ventricle
-4th-Ventricle
-Brain-Stem
-Left-Hippocampus
-Left-Amygdala
-CSF
-Left-Accumbens-area
-Left-VentralDC
-Left-vessel
-Left-choroid-plexus
-Right-Cerebral-White-Matter
-Right-Lateral-Ventricle
-Right-Inf-Lat-Vent
-Right-Cerebellum-White-Matter
-Right-Cerebellum-Cortex
-Right-Thalamus-Proper
-Right-Caudate
-Right-Putamen
-Right-Pallidum
-Right-Hippocampus
-Right-Amygdala
-Right-Accumbens-area
-Right-VentralDC
-Right-vessel
-Right-choroid-plexus
-WM-hypointensities
-Optic-Chiasm
-CC_Posterior
-CC_Mid_Posterior
-CC_Central
-CC_Mid_Anterior
-CC_Anterior
 lh_bankssts_part1
 lh_bankssts_part2
 lh_caudalanteriorcingulate_part1

BrainNetworksInPython/datasets/NSPN_WhitakerVertes_PNAS2016/__init__.py

@@ -19,15 +19,13 @@
 names_file = filepath + "/500.names.txt"
 regionalmeasures_file = filepath + "/PARC_500aparc_thickness_behavmerge.csv"
 covars_file = None
-names_308_style = True
 
 
 def _data():
     return (centroids_file,
             regionalmeasures_file,
             names_file,
-            covars_file,
-            names_308_style)
+            covars_file)
 
 
 def _centroids():
@@ -46,15 +44,10 @@ def _covars():
     return covars_file
 
 
-def _is_names_308_style():
-    return names_308_style
-
-
 def import_data():
     return read_in_data(
         regionalmeasures_file,
         names_file,
         covars_file=covars_file,
         centroids_file=centroids_file,
-        names_308_style=names_308_style,
         data_as_df=True)

BrainNetworksInPython/make_graphs.py

@@ -18,7 +18,7 @@ def anatomical_graph_attributes():
     return ['parcellation', 'centroids']
 
 
-def assign_node_names(G, parcellation, names_308_style=False):
+def assign_node_names(G, parcellation):
     """
     Returns the network G with node attributes "name" assigned
     according to the list parcellation.
@@ -36,10 +36,6 @@ def assign_node_names(G, parcellation, names_308_style=False):
     # Assign anatomical names to the nodes
     for i, node in enumerate(G.nodes()):
         G.node[i]['name'] = parcellation[i]
-        if names_308_style:
-            G.node[i]['name_34'] = parcellation[i].split('_')[1]
-            G.node[i]['name_68'] = parcellation[i].rsplit('_', 1)[0]
-            G.node[i]['hemi'] = parcellation[i].split('_', 1)[0]
     #
     G.graph['parcellation'] = True
     return G

BrainNetworksInPython/scripts/useful_functions.py

@@ -10,7 +10,6 @@ def read_in_data(
         names_file,
         covars_file=None,
         centroids_file=None,
-        names_308_style=False,
         data_as_df=True):
     '''
     Read in the data from the three input files:
@@ -23,16 +22,10 @@ def read_in_data(
             brain regions. Should be aligned with names_file such that the ith
             line of centroids_file is the coordinates of the brain region named
             in the ith line of names_file.
-        * names_308_style : If the names are in 308 style then drop the first
-            41 entries from the names file.
     '''
     # Load names
     with open(names_file) as f:
         names = [line.strip() for line in f]
-    # If you have your names in names_308_style you need to strip the
-    # first 41 items
-    if names_308_style:
-        names = names[41:]
 
     # Load covariates
     if covars_file is not None:
@@ -43,24 +36,14 @@ def read_in_data(
 
     if centroids_file is not None:
         centroids = np.loadtxt(centroids_file)
-        # If you have your names in names_308_style you need to strip the
-        # first 41 items
-        if names_308_style:
-            names = names[41:]
-            centroids = centroids[41:, :]
 
     # Load data
     if data_as_df:
         df = pd.read_csv(data)
-        # You may also have to strip the words "thickness" from the
-        # end of the names in the data frame
-        if names_308_style:
-            df.columns = [col.rsplit('_thickness', 1)[0] for col in df.columns]
     else:
         df = np.loadtxt(data)
 
-    return df, names, covars_list, centroids, names_308_style
-
+    return df, names, covars_list, centroids
 
 def write_out_measures(df, output_dir, name, first_columns=[]):
     '''

BrainNetworksInPython/wrappers/corrmat_from_regionalmeasures.py

@@ -72,18 +72,6 @@ def setup_argparser():
             ('  Default: None')),
         default=None)
 
-    parser.add_argument(
-        '--names_308_style',
-        action='store_true',
-        help=textwrap.dedent(
-            ('Include this flag if your names are in the NSPN 308\n') +
-            ('parcellation style (which means you have 41 subcortical \
-regions)\n') +
-            ('that are still in the names files and that\n') +
-            ('the names are in <hemi>_<DK-region>_<part> format.\n') +
-            ('  Default: False')),
-        default=False)
-
     parser.add_argument(
         '--method',
         type=str,
@@ -102,7 +90,6 @@ def corrmat_from_regionalmeasures(regional_measures_file,
                                   names_file,
                                   output_name,
                                   covars_file=None,
-                                  names_308_style=False,
                                   method='pearson'):
     '''
     Read in regional measures, names and covariates files to compute
@@ -123,8 +110,7 @@ def corrmat_from_regionalmeasures(regional_measures_file,
     df, names, covars_list, *a = read_in_data(
         regional_measures_file,
         names_file,
-        covars_file=covars_file,
-        names_308_style=names_308_style)
+        covars_file=covars_file)
 
     M = mcm.corrmat_from_regionalmeasures(
         df, names, covars=covars_list, method=method)
@@ -144,7 +130,6 @@ def corrmat_from_regionalmeasures(regional_measures_file,
         arg.names_file,
         arg.output_name,
         covars_file=arg.covars_file,
-        names_308_style=arg.names_308_style,
         method=arg.method)
 
 # ============================================================================

BrainNetworksInPython/wrappers/network_analysis_from_corrmat.py

@@ -86,17 +86,6 @@ def setup_argparser():
 with real network.\n') + ('  Default: 1000')),
         default=1000)
 
-    parser.add_argument(
-        '--names_308_style',
-        action='store_true',
-        help=textwrap.dedent(
-            ('Include this flag if your names are in the NSPN 308\n')
-            + ('parcellation style (which means you have 41 subcortical \
-regions)\n')
-            + ('that are still in the names and centroids files and that\n')
-            + ('the names are in <hemi>_<DK-region>_<part> format.\n')
-            + ('  Default: False')),
-        default=False)
 
     arguments = parser.parse_args()
 
@@ -108,8 +97,7 @@ def network_analysis_from_corrmat(corr_mat_file,
                                   centroids_file,
                                   output_dir,
                                   cost=10,
-                                  n_rand=1000,
-                                  names_308_style=False):
+                                  n_rand=1000):
     '''
     This is the big function!
     It reads in the correlation matrix, thresholds it at the given cost
@@ -122,7 +110,6 @@ def network_analysis_from_corrmat(corr_mat_file,
                                 corr_mat_file,
                                 names_file,
                                 centroids_file=centroids_file,
-                                names_308_style=names_308_style,
                                 data_as_df=False)
 
     corrmat = os.path.basename(corr_mat_file).strip('.txt')
@@ -131,8 +118,7 @@ def network_analysis_from_corrmat(corr_mat_file,
     B = bnip.BrainNetwork(
         network=M,
         parcellation=names,
-        centroids=centroids,
-        names_308_style=names_308_style)
+        centroids=centroids)
     # Threshold graph
     G = B.threshold(cost)
     # Calculate the modules
@@ -181,8 +167,7 @@ def network_analysis_from_corrmat(corr_mat_file,
                                 arg.centroids_file,
                                 arg.output_dir,
                                 cost=arg.cost,
-                                n_rand=arg.n_rand,
-                                names_308_style=arg.names_308_style)
+                                n_rand=arg.n_rand)
 
 # =============================================================================
 # Wooo! All done :)

tests/write_fixtures.py

@@ -1,42 +1,41 @@
 #--------------------------- Write fixtures ---------------------------
-# To regression test our wrappers we need examples. This script 
+# To regression test our wrappers we need examples. This script
 # generates files. We save these files once, and regression_test.py
 # re-generates these files to tests them for identicality with the
-# presaved examples (fixtures). If they are found not to be identical 
-# it throws up an error. 
+# presaved examples (fixtures). If they are found not to be identical
+# it throws up an error.
 #
-# The point of this is to check that throughout the changes we make to 
+# The point of this is to check that throughout the changes we make to
 # BrainNetworksInPython the functionality of this script stays the same
 #
-# Currently the functionality of write_fixtures is to generate corrmat 
-# and network_analysis data via the functions 
+# Currently the functionality of write_fixtures is to generate corrmat
+# and network_analysis data via the functions
 # corrmat_from_regionalmeasures and network_analysis_from_corrmat.
 #----------------------------------------------------------------------
 import os
 import sys
 import networkx as nx
-             
+
 def recreate_correlation_matrix_fixture(folder):
     ##### generate a correlation matrix in the given folder using #####
-    ##### the Whitaker_Vertes dataset                             ##### 
+    ##### the Whitaker_Vertes dataset                             #####
     import BrainNetworksInPython.datasets.NSPN_WhitakerVertes_PNAS2016.data as data
-    centroids, regionalmeasures, names, covars, names_308_style = data._get_data()
+    centroids, regionalmeasures, names, covars= data._get_data()
     from BrainNetworksInPython.wrappers.corrmat_from_regionalmeasures import corrmat_from_regionalmeasures
     corrmat_path = os.getcwd()+folder+'/corrmat_file.txt'
     corrmat_from_regionalmeasures(
         regionalmeasures,
-        names, 
-        corrmat_path,
-        names_308_style=names_308_style)
-
+        names,
+        corrmat_path)
+
 def recreate_network_analysis_fixture(folder, corrmat_path):
     ##### generate network analysis in the given folder using the #####
     ##### data in example_data and the correlation matrix given   #####
-    ##### by corrmat_path                                         #####  
+    ##### by corrmat_path                                         #####
     import BrainNetworksInPython.datasets.NSPN_WhitakerVertes_PNAS2016.data as data
-    centroids, regionalmeasures, names, covars, names_308_style = data._get_data()
-    # It is necessary to specify a random seed because 
-    # network_analysis_from_corrmat generates random graphs to 
+    centroids, regionalmeasures, names, covars= data._get_data()
+    # It is necessary to specify a random seed because
+    # network_analysis_from_corrmat generates random graphs to
     # calculate global measures
     import random
     random.seed(2984)
@@ -46,48 +45,48 @@ def recreate_network_analysis_fixture(folder, corrmat_path):
                               centroids,
                               os.getcwd()+folder+'/network-analysis',
                               cost=10,
-                              n_rand=10, # this is not a reasonable 
+                              n_rand=10 # this is not a reasonable
                               # value for n, we generate only 10 random
                               # graphs to save time
-                              names_308_style=names_308_style)
-    
-def write_fixtures(folder='/temporary_test_fixtures'): 
+                              )
+
+def write_fixtures(folder='/temporary_test_fixtures'):
     ## Run functions corrmat_from_regionalmeasures and               ##
     ## network_analysis_from_corrmat to save corrmat in given folder ##
     ##---------------------------------------------------------------##
     # if the folder does not exist, create it
     if not os.path.isdir(os.getcwd()+folder):
         os.makedirs(os.getcwd()+folder)
     # generate and save the correlation matrix
-    print("generating new correlation matrix") 
+    print("generating new correlation matrix")
     recreate_correlation_matrix_fixture(folder)
     # generate and save the network analysis
-    print("generating new network analysis") 
+    print("generating new network analysis")
     corrmat_path = 'temporary_test_fixtures/corrmat_file.txt'
     recreate_network_analysis_fixture(folder, corrmat_path)
-    
+
 def delete_fixtures(folder):
         import shutil
         print('\ndeleting temporary files')
         shutil.rmtree(os.getcwd()+folder)
-    
+
 def hash_folder(folder='temporary_test_fixtures'):
     hashes = {}
     for path, directories, files in os.walk(folder):
         for file in sorted(files):
             hashes[os.path.join(path, file)] = hash_file(os.path.join(path, file))
         for dir in sorted(directories):
             hashes.update(hash_folder(os.path.join(path, dir)))
-        break 
+        break
     return hashes
-    
+
 
 def hash_file(filename):
     import hashlib
     m = hashlib.sha256()
     with open(filename, 'rb') as f:
         while True:
-            b = f.read(2**10) 
+            b = f.read(2**10)
             if not b: break
             m.update(b)
     return m.hexdigest()
@@ -103,16 +102,16 @@ def generate_fixture_hashes(folder='temporary_test_fixtures'):
     return hash_dict
 
 def current_fixture_name():
-    # returns the fixture name appropriate the current versions 
+    # returns the fixture name appropriate the current versions
     # of python and networkx
     return "tests/.fixture_hash"+str(sys.version_info[:2])+'networkx_version'+str(nx.__version__)
-    
+
 def pickle_hash(hash_dict):
     import pickle
     # when we save we record the python and networkx versions
     with open(current_fixture_name(), 'wb') as f:
         pickle.dump(hash_dict, f)
-    
+
 def unpickle_hash():
     import pickle
     # import fixture relevant to the current python, networkx versions
@@ -125,4 +124,3 @@ def unpickle_hash():
     if input("Are you sure you want to update Brain Networks In Python's test fixtures? (y/n)") == 'y':
         hash_dict = generate_fixture_hashes()
         pickle_hash(hash_dict)
-