changed absolute paths to relative paths

Former-commit-id: e1e5d0d

imgtools/io/dataset.py

@@ -1,5 +1,6 @@
 from genericpath import exists
 import os
+import pathlib
 from typing import List, Sequence, Optional, Callable, Iterable, Dict,Tuple
 from tqdm import tqdm
 
@@ -44,6 +45,11 @@ def load_from_nrrd(
         if not os.path.exists(path_metadata):
             raise ValueError("The specified path has no file name {}".format(path_metadata))
         df_metadata = pd.read_csv(path_metadata,index_col=0)
+
+        for col in df_metadata.columns:
+            if col.startswith("folder"):
+                df_metadata[col] = df_metadata[col].apply(lambda x: pathlib.Path(os.path.split(os.path.dirname(path))[0], x).as_posix()) #input folder joined with the rel path
+
         output_streams = [("_").join(cols.split("_")[1:]) for cols in df_metadata.columns if cols.split("_")[0] == "folder"]
         imp_metadata = [cols for cols in df_metadata.columns if cols.split("_")[0] in ("metadata")]
         #Ignores multiple connection to single modality

imgtools/io/loaders.py

@@ -80,16 +80,13 @@ def read_dicom_pet(path,series=None):
 def read_dicom_auto(path, series=None):
     if path is None:
         return None
-    dcms = glob.glob(os.path.join(path, "*.dcm"))
+    dcms = glob.glob(pathlib.Path(path, "*.dcm").as_posix())
     meta = dcmread(dcms[0])
     modality = meta.Modality
     if modality == 'CT' or modality == 'MR':
         return read_dicom_series(path,series)
     elif modality == 'PT':
         return read_dicom_pet(path,series)
-    # elif len(dcms) == 1:
-    #     meta = dcmread(dcms[0])
-    #     modality = meta.Modality
     elif modality == 'RTSTRUCT':
         return read_dicom_rtstruct(dcms[0])
     elif modality == 'RTDOSE':
@@ -141,7 +138,6 @@ def __init__(self,
 
         self.colnames = colnames
         self.seriesnames = seriesnames
-
         if isinstance(csv_path_or_dataframe, str):
             if id_column is not None and id_column not in colnames:
                 colnames.append(id_column)
@@ -168,6 +164,9 @@ def __getitem__(self, subject_id):
         if self.expand_paths:
             # paths = {col: glob.glob(path)[0] for col, path in paths.items()}
             paths = {col: glob.glob(path)[0] if pd.notna(path) else None for col, path in paths.items()}
+        for col, path in paths.items():
+            print(path)
+
         outputs = {col: self.readers[i](path,series["series_"+("_").join(col.split("_")[1:])]) for i, (col, path) in enumerate(paths.items())}
         return self.output_tuple(**outputs)
 

imgtools/modules/datagraph.py

@@ -4,6 +4,7 @@
 import numpy as np
 import pandas as pd
 from tqdm import tqdm
+import pathlib
 
 
 class DataGraph:
@@ -276,6 +277,11 @@ def parser(self, query_string: str) -> pd.DataFrame:
         final_df["index_chng"] = final_df.index.astype(str) + "_" + final_df["patient_ID"]
         final_df.set_index("index_chng", inplace=True)
         final_df.rename_axis(None, inplace=True)
+
+        #change relative paths to absolute paths
+        for col in final_df.columns:
+            if col.startswith("folder"):
+                final_df[col] = final_df[col].apply(lambda x: pathlib.Path(os.path.split(os.path.dirname(self.edge_path))[0], x).as_posix()) #input folder joined with the rel path
         return final_df
 
     def graph_query(self, 

imgtools/ops/ops.py

@@ -1,4 +1,5 @@
 from typing import List, TypeVar, Sequence, Union, Tuple, Optional, Any
+from cv2 import DFT_COMPLEX_INPUT
 
 import numpy as np
 import SimpleITK as sitk
@@ -98,6 +99,7 @@ def __init__(self,
         graph = DataGraph(path_crawl=path_crawl, edge_path=edge_path, visualize=visualize)
         print(f"Forming the graph based on the given modalities: {self.modalities}")
         self.df_combined = graph.parser(self.modalities)
+        print(self.df_combined.head())
         self.output_streams = [("_").join(cols.split("_")[1:]) for cols in self.df_combined.columns if cols.split("_")[0] == "folder"]
         self.column_names = [cols for cols in self.df_combined.columns if cols.split("_")[0] == "folder"]
         self.series_names = [cols for cols in self.df_combined.columns if cols.split("_")[0] == "series"]
@@ -110,7 +112,7 @@ def __init__(self,
                                 colnames=self.column_names,
                                 seriesnames=self.series_names,
                                 id_column=None,
-                                expand_paths=True,
+                                expand_paths=False,
                                 readers=self.readers) 
         super().__init__(loader)
 
@@ -297,9 +299,7 @@ def __init__(self,
         self.create_dirs = create_dirs
         self.compress = compress
 
-        writer_class = BaseSubjectWriter
-
-        writer = writer_class(self.root_directory,
+        writer = BaseSubjectWriter(self.root_directory,
                               self.filename_format,
                               self.create_dirs,
                               self.compress)

imgtools/utils/crawl.py

@@ -1,5 +1,5 @@
 from argparse import ArgumentParser
-import os
+import os, pathlib
 import glob
 import json
 
@@ -64,6 +64,9 @@ def crawl_one(folder):
                 if study not in database[patient]:
                     database[patient][study] = {'description': study_description}
                 if series not in database[patient][study]:
+                    parent, child = os.path.split(folder)
+                    print(folder, path)
+                    rel_path = pathlib.Path(os.path.split(parent)[1], os.path.relpath(path, parent)).as_posix()
                     database[patient][study][series] = {'instances': [],
                                                         'instance_uid': instance,
                                                         'modality': meta.Modality,
@@ -72,7 +75,7 @@ def crawl_one(folder):
                                                         'reference_rs': reference_rs,
                                                         'reference_pl': reference_pl,
                                                         'reference_frame': reference_frame,
-                                                        'folder': path}
+                                                        'folder': rel_path}
                 database[patient][study][series]['instances'].append(instance)
             except:
                 pass
@@ -102,6 +105,7 @@ def to_df(database_dict):
 
 def crawl(top, 
           n_jobs: int = -1):
+    #top is the input directory in the argument parser from autotest.py
     database_list = []
     folders = glob.glob(os.path.join(top, "*"))