Add parquet protocol

.github/workflows/python-test.yml

@@ -59,4 +59,4 @@ jobs:
           pytest
 
       - name: Upload coverage reports to Codecov
-        uses: codecov/codecov-action@v3
+        uses: codecov/codecov-action@v3

.gitignore

@@ -130,3 +130,6 @@ dmypy.json
 
 # Pyre type checker
 .pyre/
+
+# PyCharm
+.idea/

.pre-commit-config.yaml

@@ -50,17 +50,6 @@ repos:
   rev: 6.0.0
   hooks:
   - id: flake8
+    args: ["--ignore=E501"]
   ## You can add flake8 plugins via `additional_dependencies`:
   #  additional_dependencies: [flake8-bugbear]
-- repo: local
-  hooks:
-    - id: pylint
-      name: pylint
-      entry: pylint
-      language: system
-      types: [python]
-      args:
-        [
-          "-rn", # Only display messages
-          "-sn", # Don't display the score
-        ]

bw_processing/__init__.py

@@ -15,6 +15,7 @@
     "generic_zipfile_filesystem",
     "INDICES_DTYPE",
     "load_datapackage",
+    "MatrixSerializeFormat",
     "md5",
     "merge_datapackages_with_mask",
     "reindex",
@@ -29,7 +30,12 @@
 
 
 from .array_creation import create_array, create_structured_array
-from .constants import DEFAULT_LICENSES, INDICES_DTYPE, UNCERTAINTY_DTYPE
+from .constants import (
+    DEFAULT_LICENSES,
+    INDICES_DTYPE,
+    UNCERTAINTY_DTYPE,
+    MatrixSerializeFormat,
+)
 from .datapackage import (
     Datapackage,
     DatapackageBase,

bw_processing/constants.py

@@ -1,4 +1,5 @@
 import re
+from enum import Enum
 
 import numpy as np
 
@@ -30,3 +31,19 @@
         "title": "Open Data Commons Public Domain Dedication and License v1.0",
     }
 ]
+
+
+class MatrixSerializeFormat(str, Enum):
+    """
+    Enum with the serializing formats for the vectors and matrices.
+    """
+
+    NUMPY = "numpy"  # numpy .npy format
+    PARQUET = "parquet"  # Apache .parquet format
+
+
+# FILE EXTENSIONS
+NUMPY_SERIALIZE_FORMAT_EXTENSION = ".npy"
+NUMPY_SERIALIZE_FORMAT_NAME = "npy"
+PARQUET_SERIALIZE_FORMAT_EXTENSION = ".parquet"
+PARQUET_SERIALIZE_FORMAT_NAME = "pqt"