tsdf 0.5.0__tar.gz → 0.5.2__tar.gz

{tsdf-0.5.0 → tsdf-0.5.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: tsdf
-Version: 0.5.0
+Version: 0.5.2
 Summary: A Python library that provides methods for encoding and decoding TSDF (Time Series Data Format) data, which allows you to easily create, manipulate and serialize TSDF files in your Python code.
 Home-page: https://github.com/biomarkersParkinson/tsdf
 License: Apache-2.0

{tsdf-0.5.0 → tsdf-0.5.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "tsdf"
-version = "0.5.0"
+version = "0.5.2"
 description = "A Python library that provides methods for encoding and decoding TSDF (Time Series Data Format) data, which allows you to easily create, manipulate and serialize TSDF files in your Python code."
 authors = ["Peter Kok <p.kok@esciencecenter.nl>",
             "Pablo Rodríguez <p.rodriguez-sanchez@esciencecenter.nl>",

{tsdf-0.5.0 → tsdf-0.5.2}/src/tsdf/__init__.py

@@ -8,34 +8,34 @@ from .read_tsdf import (
     load_metadata_from_path,
     load_metadatas_from_dir,
     load_metadata_string,
-    load_metadata_legacy_file
+    load_metadata_legacy_file,
 )
 from .write_tsdf import (
     write_metadata,
 )
-    
+
 from .write_binary import (
     write_binary_file,
     write_dataframe_to_binaries,
 )
 from .read_binary import (
-    load_binary_from_metadata,
-    load_binaries_to_dataframe,
+    load_ndarray_from_binary,
+    load_dataframe_from_binaries,
 )
 
 from .tsdfmetadata import TSDFMetadata
 
 __all__ = [
-    'load_metadata_file',
-    'load_metadata_from_path',
-    'load_metadatas_from_dir',
-    'load_metadata_string',
-    'load_metadata_legacy_file',
-    'write_metadata',
-    'write_binary_file',
-    'write_dataframe_to_binaries',
-    'load_binary_from_metadata',
-    'load_binaries_to_dataframe',
-    'TSDFMetadata',
-    'constants'
+    "load_metadata_file",
+    "load_metadata_from_path",
+    "load_metadatas_from_dir",
+    "load_metadata_string",
+    "load_metadata_legacy_file",
+    "write_metadata",
+    "write_binary_file",
+    "write_dataframe_to_binaries",
+    "load_ndarray_from_binary",
+    "load_dataframe_from_binaries",
+    "TSDFMetadata",
+    "constants",
 ]

{tsdf-0.5.0 → tsdf-0.5.2}/src/tsdf/numpy_utils.py

@@ -61,6 +61,7 @@ _map_from_numpy_endianness = {
     "<": "little",
     ">": "big",
     "=": sys.byteorder,
+    "|": "not applicable",
 }
 """ Supported endianness values. """
 
@@ -79,6 +80,7 @@ def endianness_numpy_to_tsdf(data: np.ndarray) -> str:
 _map_to_numpy_endianness = {
     "little": "<",
     "big": ">",
+    "not applicable": "|",
 }
 """ Supported endianness values. """
 

{tsdf-0.5.0 → tsdf-0.5.2}/src/tsdf/parse_metadata.py

@@ -8,9 +8,10 @@ import os
 from typing import Any, Dict, List
 
 from tsdf import constants
-from tsdf import tsdfmetadata 
+from tsdf import tsdfmetadata
 
-def read_data(data: Any, source_path: str) -> Dict[str, 'tsdfmetadata.TSDFMetadata']:
+
+def read_data(data: Any, source_path: str) -> Dict[str, "tsdfmetadata.TSDFMetadata"]:
     """
     Function used to parse the JSON object containing TSDF metadata. It returns a
     list of TSDFMetadata objects, where each object describes formatting of a binary file.
@@ -25,8 +26,10 @@ def read_data(data: Any, source_path: str) -> Dict[str, 'tsdfmetadata.TSDFMetada
 
     # Check if the version is supported
     version = data["metadata_version"]
-    if not version in constants.SUPPORTED_TSDF_VERSIONS:
-        raise tsdfmetadata.TSDFMetadataFieldValueError(f"TSDF file version {version} not supported.")
+    if version not in constants.SUPPORTED_TSDF_VERSIONS:
+        raise tsdfmetadata.TSDFMetadataFieldValueError(
+            f"TSDF file version {version} not supported."
+        )
 
     defined_properties: Dict[str, Any] = {}
     return _read_struct(data, defined_properties.copy(), source_path, version)
@@ -34,7 +37,7 @@ def read_data(data: Any, source_path: str) -> Dict[str, 'tsdfmetadata.TSDFMetada
 
 def _read_struct(
     data: Any, defined_properties: Dict[str, Any], source_path, version: str
-) -> Dict[str, 'tsdfmetadata.TSDFMetadata']:
+) -> Dict[str, "tsdfmetadata.TSDFMetadata"]:
     """
     Recursive method used to parse the TSDF metadata in a hierarchical
     order (from the root towards the leaves).
@@ -48,7 +51,7 @@ def _read_struct(
 
     :raises tsdf_metadata.TSDFMetadataFieldError: if the TSDF metadata file is missing a mandatory field.
     """
-    all_streams: Dict[str, 'tsdfmetadata.TSDFMetadata'] = {}
+    all_streams: Dict[str, "tsdfmetadata.TSDFMetadata"] = {}
     remaining_data = {}
     leaf: bool = True
 
@@ -66,16 +69,14 @@ def _read_struct(
     if leaf:
         try:
             bin_file_name = defined_properties["file_name"]
-            path = os.path.split(source_path)
-            file_dir = os.path.join(path[0])
-            meta_file_name = path[1]
-            all_streams[bin_file_name] = tsdfmetadata.TSDFMetadata(
-                defined_properties, file_dir, meta_file_name
-            )
-        except tsdfmetadata.TSDFMetadataFieldError as exc:
-            raise tsdfmetadata.TSDFMetadataFieldError(
-                "A property 'file_name' is missing in the TSDF metadata file."
-            ) from exc
+        except KeyError:
+            raise tsdfmetadata.TSDFMetadataFieldError.missing_field("file_name") 
+        path = os.path.split(source_path)
+        file_dir = os.path.join(path[0])
+        meta_file_name = path[1]
+        all_streams[bin_file_name] = tsdfmetadata.TSDFMetadata(
+            defined_properties, file_dir, meta_file_name
+        )
 
     # 3) If the current element is not a leaf, `remaining_data`` will contain lower
     # levels of the TSDF structure.
@@ -158,18 +159,18 @@ def contains_tsdf_mandatory_fields(dictionary: Dict[str, Any]) -> bool:
     :raises tsdf_metadata.TSDFMetadataFieldValueError: if the TSDF metadata file contains an invalid value.
     """
     version_key = "metadata_version"
-    if not version_key in dictionary.keys():
-        raise tsdfmetadata.TSDFMetadataFieldError(f"TSDF structure is missing key '{version_key}'")
+    if version_key not in dictionary.keys():
+        raise tsdfmetadata.TSDFMetadataFieldError.missing_field(version_key)
 
     version = dictionary[version_key]
     for key in constants.MANDATORY_TSDF_KEYS[version]:
-        if not key in dictionary.keys():
-            raise tsdfmetadata.TSDFMetadataFieldError(f"TSDF structure is missing key '{key}'")
+        if key not in dictionary.keys():
+            raise tsdfmetadata.TSDFMetadataFieldError.missing_field(key)
     units = "units"
     channels = "channels"
     if len(dictionary[units]) != len(dictionary[channels]):
         raise tsdfmetadata.TSDFMetadataFieldValueError(
-            f"TSDF structure requires equal number of {units} and {channels}"
+            f"TSDF metadata structure must specify equal number of {units} and {channels} for each binary file."
         )
 
     for key, value in dictionary.items():
@@ -203,8 +204,8 @@ def _check_tsdf_property_format(key: str, value, version: str) -> None:
 
 
 def get_file_metadata_at_index(
-    metadata: Dict[str, 'tsdfmetadata.TSDFMetadata'], index: int
-) -> 'tsdfmetadata.TSDFMetadata':
+    metadata: Dict[str, "tsdfmetadata.TSDFMetadata"], index: int
+) -> "tsdfmetadata.TSDFMetadata":
     """
     Returns the metadata object at the position defined by the index.
 
@@ -222,7 +223,7 @@ def get_file_metadata_at_index(
     raise IndexError("The index is out of range.")
 
 
-def confirm_dir_of_metadata(metadatas: List['tsdfmetadata.TSDFMetadata']) -> None:
+def confirm_dir_of_metadata(metadatas: List["tsdfmetadata.TSDFMetadata"]) -> None:
     """
     The method is used to confirm whether all the metadata files are expected in the same directory.
 

{tsdf-0.5.0 → tsdf-0.5.2}/src/tsdf/read_binary.py

@@ -8,49 +8,52 @@ import os
 from typing import List, Union
 import numpy as np
 import pandas as pd
-from tsdf import numpy_utils 
+from tsdf import numpy_utils
 from tsdf import tsdfmetadata
 from tsdf.constants import ConcatenationType
 
 
-def load_binaries_to_dataframe(metadatas: '[tsdfmetadata.TSDFMetadata]', concatenation: ConcatenationType = ConcatenationType.none) -> Union[pd.DataFrame, List[pd.DataFrame]]:
+def load_dataframe_from_binaries(
+    metadatas: List["tsdfmetadata.TSDFMetadata"],
+    concatenation: ConcatenationType = ConcatenationType.none,
+) -> Union[pd.DataFrame, List[pd.DataFrame]]:
     """
-    Load binary files associated with TSDF and return a combined pandas DataFrame.
+    Load content of binary files associated with TSDF into a pandas DataFrame. The data frames can be concatenated horizontally (ConcatenationType.columns), vertically (ConcatenationType.rows) or provided as a list of data frames (ConcatenationType.none).
 
     :param metadatas: list of TSDFMetadata objects.
-:param concatenation: concatenation rule, i.e., determines whether the data frames (content of binary files) should be concatenated horizontally (ConcatenationType.columns), vertically (ConcatenationType.rows) or not concatenated (ConcatenationType.none), but provided as a list of data frames.
+    :param concatenation: concatenation rule, i.e., determines whether the data frames (content of binary files) should be concatenated horizontally (ConcatenationType.columns), vertically (ConcatenationType.rows) or provided as a list of data frames (ConcatenationType.none).
 
     :return: pandas DataFrame containing the combined data.
     """
     # Load the data
-    dataFrames = []
+    data_frames = []
     for metadata in metadatas:
-        data = load_binary_from_metadata(metadata)
+        data = load_ndarray_from_binary(metadata)
         df = pd.DataFrame(data, columns=metadata.channels)
-        dataFrames.append(df)
+        data_frames.append(df)
 
     # Merge the data
     if concatenation == ConcatenationType.rows:
-        return pd.concat(dataFrames)
+        return pd.concat(data_frames)
     elif concatenation == ConcatenationType.columns:
-        return pd.concat(dataFrames, axis=1)
+        return pd.concat(data_frames, axis=1)
     elif concatenation == ConcatenationType.none:
-        return dataFrames
+        return data_frames
 
 
-def load_binary_from_metadata(
-    metadata: 'tsdfmetadata.TSDFMetadata', start_row: int = 0, end_row: int = -1
+def load_ndarray_from_binary(
+    metadata: "tsdfmetadata.TSDFMetadata", start_row: int = 0, end_row: int = -1
 ) -> np.ndarray:
     """
     Use metadata properties to load and return numpy array from a binary file (located the same directory where the metadata is saved).
-    
+
     :param metadata: TSDFMetadata object.
     :param start_row: (optional) first row to load.
     :param end_row: (optional) last row to load. If -1, load all rows.
 
     :return: numpy array containing the data."""
     metadata_dir = metadata.file_dir_path
-    
+
     bin_path = os.path.join(metadata_dir, metadata.file_name)
     return _load_binary_file(
         bin_path,
@@ -75,7 +78,7 @@ def _load_binary_file(
     end_row: int = -1,
 ) -> np.ndarray:
     """
-    Use provided parameters to load and return a numpy array from a binary file
+    Use provided parameters to load and return a numpy array from a binary file.
 
     :param bin_file_path: path to the binary file.
     :param data_type: data type of the binary file.

{tsdf-0.5.0 → tsdf-0.5.2}/src/tsdf/tsdfmetadata.py

@@ -1,11 +1,14 @@
 import copy
 from typing import Any, Dict, List
-from numpy import ndarray
-from tsdf import parse_metadata, read_binary
+
+from tsdf import parse_metadata
 
 class TSDFMetadataFieldError(Exception):
     "Raised when the TSDFMetadata is missing an obligatory field."
-    pass
+    @classmethod
+    def missing_field(cls, field_name: str):
+        message = f"Value for the obligatory TSDF field '{field_name}' is missing in the provided TSDF metadata file."
+        return cls(message)
 
 
 class TSDFMetadataFieldValueError(Exception):

{tsdf-0.5.0 → tsdf-0.5.2}/src/tsdf/validator.py

@@ -4,6 +4,7 @@ import traceback
 import json
 from tsdf import read_tsdf, read_binary
 
+
 def validate_tsdf_format(file_path):
     try:
         # Read the meta data (this will check for compulsory fields and such)
@@ -15,27 +16,31 @@ def validate_tsdf_format(file_path):
 
         # Loop through all the files in the metadata
         for file_name, file_metadata in metadata.items():
-
             # print the file_metadata as json
             # print(json.dumps(file_metadata.get_plain_tsdf_dict_copy(), indent=4))
 
             # Load the binary data
-            binary_data = read_binary.load_binary_from_metadata(file_metadata)
+            binary_data = read_binary.load_ndarray_from_binary(file_metadata)
 
             # Success message
-            print(f"Successfully loaded binary file {file_name}, resulting shape: {binary_data.shape}")
+            print(
+                f"Successfully loaded binary file {file_name}, resulting shape: {binary_data.shape}"
+            )
 
         return True
 
     except Exception as e:
         print(f"Error while validating: {e}")
-        #traceback.print_exc()
+        # traceback.print_exc()
         return False
 
+
 def main():
     # Parse the arguments
-    parser = argparse.ArgumentParser(description='Validate a file content against the TSDF format.')
-    parser.add_argument('file_path', help='Path to the file to validate')
+    parser = argparse.ArgumentParser(
+        description="Validate a file content against the TSDF format."
+    )
+    parser.add_argument("file_path", help="Path to the file to validate")
     args = parser.parse_args()
 
     # Perform validation
@@ -44,5 +49,6 @@ def main():
     # Exit with error code 1 if the validation failed
     exit(0 if is_valid else 1)
 
-if __name__ == '__main__':
+
+if __name__ == "__main__":
     main()