sibi-dst 0.3.31__tar.gz → 0.3.32__tar.gz

{sibi_dst-0.3.31 → sibi_dst-0.3.32}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sibi-dst
-Version: 0.3.31
+Version: 0.3.32
 Summary: Data Science Toolkit
 Author: Luis Valverde
 Author-email: lvalverdeb@gmail.com
@@ -20,6 +20,7 @@ Requires-Dist: django (>=5.1.4,<6.0.0)
 Requires-Dist: djangorestframework (>=3.15.2,<4.0.0)
 Requires-Dist: folium (>=0.19.4,<0.20.0)
 Requires-Dist: geopandas (>=1.0.1,<2.0.0)
+Requires-Dist: gunicorn (>=23.0.0,<24.0.0)
 Requires-Dist: httpx (>=0.27.2,<0.28.0)
 Requires-Dist: ipython (>=8.29.0,<9.0.0)
 Requires-Dist: jinja2 (>=3.1.4,<4.0.0)
@@ -42,6 +43,7 @@ Requires-Dist: sqlalchemy (>=2.0.36,<3.0.0)
 Requires-Dist: tornado (>=6.4.1,<7.0.0)
 Requires-Dist: tqdm (>=4.67.0,<5.0.0)
 Requires-Dist: uvicorn (>=0.34.0,<0.35.0)
+Requires-Dist: uvicorn-worker (>=0.3.0,<0.4.0)
 Description-Content-Type: text/markdown
 
 # sibi-dst

{sibi_dst-0.3.31 → sibi_dst-0.3.32}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "sibi-dst"
-version = "0.3.31"
+version = "0.3.32"
 description = "Data Science Toolkit"
 authors = ["Luis Valverde <lvalverdeb@gmail.com>"]
 readme = "README.md"
@@ -41,6 +41,8 @@ nltk = "^3.9.1"
 folium = "^0.19.4"
 geopandas = "^1.0.1"
 osmnx = "^2.0.1"
+gunicorn = "^23.0.0"
+uvicorn-worker = "^0.3.0"
 
 
 [build-system]

{sibi_dst-0.3.31 → sibi_dst-0.3.32}/sibi_dst/df_helper/_parquet_artifact.py

@@ -61,6 +61,11 @@ class ParquetArtifact(DfHelper):
         dw = DataWrapper(self.data_wrapper_class, **params)
         dw.process()
 
+    def __exit__(self, exc_type, exc_value, traceback):
+        # Ensure resources are cleaned up
+        if self.fs:
+            self.fs.close()
+
     def update_parquet(self, period: str = 'today', **kwargs) -> None:
         """Update the Parquet file with data from a specific period."""
         kwargs.update(self.parse_parquet_period(period=period))

{sibi_dst-0.3.31 → sibi_dst-0.3.32}/sibi_dst/df_helper/_parquet_reader.py

@@ -31,7 +31,10 @@ class ParquetReader(DfHelper):
         # Filesystem setup
         self.filesystem_type = filesystem_type
         self.filesystem_options = filesystem_options or {}
-        self.fs = fsspec.filesystem(self.filesystem_type, **self.filesystem_options)
+        self.fs = self.config.setdefault('fs', None)
+        if self.fs is None:
+            self.fs = fsspec.filesystem(self.filesystem_type, **self.filesystem_options)
+        self.config.setdefault('fs', self.fs)
 
         if not self.directory_exists():
             raise ValueError(f"{self.parquet_storage_path} does not exist")
@@ -48,3 +51,8 @@ class ParquetReader(DfHelper):
             return info['type'] == 'directory'
         except FileNotFoundError:
             return False
+
+    def __exit__(self, exc_type, exc_value, traceback):
+        # Ensure resources are cleaned up
+        if self.fs:
+            self.fs.close()

{sibi_dst-0.3.31 → sibi_dst-0.3.32}/sibi_dst/utils/parquet_saver.py

@@ -38,6 +38,7 @@ class ParquetSaver:
         schema = self._define_schema()
         self._convert_dtypes(schema)
         self._save_dataframe_to_parquet(full_path, schema)
+        self.fs.close()
 
     def _define_schema(self) -> pa.Schema:
         """Define a PyArrow schema dynamically based on df_result column types."""

{sibi_dst-0.3.31 → sibi_dst-0.3.32}/sibi_dst/utils/storage_manager.py

@@ -90,4 +90,7 @@ class StorageManager:
         """
         print("Rebuilding depot structure...")
         self.rebuild_depot_paths(depots, clear_existing=clear_existing)
-        print("Rebuild complete.")
+        print("Rebuild complete.")
+
+    def get_fs_instance(self):
+        return fsspec.filesystem(self.fs_type, **self.fs_options)