work on kgcnn.io.file

Author: PatReis

kgcnn/data/base.py

@@ -20,7 +20,7 @@ class MemoryGraphList(list):
     r"""Class to store a list of graph dictionaries in memory.
 
     Inherits from a python list. The graph properties are defined by tensor-like (numpy) arrays
-    for indices, attributes, labels, symbol etc. in :obj:`GraphDict`, which are the items of the list.
+    for indices, attributes, labels, symbol etc. in :obj:`GraphDict` , which are the items of the list.
     Access to items via `[]` indexing operator.
 
     A python list of a single named property can be obtained from each :obj:`GraphDict` in :obj:`MemoryGraphList` via
@@ -68,7 +68,7 @@ def validate(self):
                 self[i] = GraphDict(x)
 
     def assign_property(self, key: str, value: list):
-        """Assign a list of numpy arrays of a property to :obj:`GraphDict` s in this list.
+        """Assign a list of numpy arrays of a property to the respective :obj:`GraphDict` s in this list.
 
         Args:
             key (str): Name of the property.
@@ -81,7 +81,7 @@ def assign_property(self, key: str, value: list):
             # We could also here remove the key from all graphs.
             return self
         if not isinstance(value, list):
-            raise TypeError("Expected type 'list' to assign graph properties.")
+            raise TypeError("Expected type `list` to assign graph properties.")
         if len(self) == 0:
             self.empty(len(value))
         if len(self) != len(value):
@@ -123,7 +123,7 @@ def __getitem__(self, item) -> Union[GraphDict, List]:
 
     def __setitem__(self, key, value):
         if not isinstance(value, GraphDict):
-            raise TypeError("Require a GraphDict as list item.")
+            raise TypeError("Require a `GraphDict` as list item.")
         super(MemoryGraphList, self).__setitem__(key, value)
 
     def __repr__(self):

kgcnn/io/file.py

@@ -1,9 +1,11 @@
+import os.path
+
 import numpy as np
 import h5py
 from typing import List, Union
 
 
-class RaggedArrayNumpyFile:
+class RaggedTensorNumpyFile:
 
     def __init__(self, file_path: str, compressed: bool = False):
         self.file_path = file_path
@@ -30,7 +32,7 @@ def __getitem__(self, item):
         raise NotImplementedError("Not implemented for file reference load.")
 
 
-class RaggedArrayHDFile:
+class RaggedTensorHDFile:
 
     def __init__(self, file_path: str, compressed: bool = None):
         self.file_path = file_path
@@ -100,4 +102,13 @@ def append_multiple(self, items: list):
                 file["row_splits"].shape[0] + new_len, axis=0
             )
             file["row_splits"][-new_len:] = split_last + new_splits
-            file["values"][split_last:+split_last+new_splits[-1]] = new_values
+            file["values"][split_last:+split_last+new_splits[-1]] = new_values
+
+    def __len__(self):
+        with h5py.File(self.file_path, "r") as file:
+            num_row_splits = file["row_splits"].shape[0]
+        # length is num_row_splits - 1
+        return num_row_splits-1
+
+    def exists(self):
+        return os.path.exists(self.file_path)