ssb-konjunk 1.0.0__tar.gz → 2.0.0__tar.gz

{ssb_konjunk-1.0.0 → ssb_konjunk-2.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: ssb-konjunk
-Version: 1.0.0
+Version: 2.0.0
 Summary: SSB Konjunk 422
 License: MIT
 Author: Johanne Saxegaard
@@ -14,7 +14,6 @@ Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
 Requires-Dist: click (>=8.0.1)
-Requires-Dist: dapla-toolbelt (>=3.0.0)
 Requires-Dist: pandas (>=2.2.0)
 Requires-Dist: pandas-stubs (>=2.2.2.240807)
 Requires-Dist: pendulum (>=3.0.0)

{ssb_konjunk-1.0.0 → ssb_konjunk-2.0.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "ssb-konjunk"
-version = "1.0.0"
+version = "2.0.0"
 description = "SSB Konjunk 422"
 authors = ["Johanne Saxegaard <jox@ssb.no>"]
 license = "MIT"
@@ -18,7 +18,6 @@ python = ">=3.10, <4.0"
 click = ">=8.0.1"
 pandas = ">=2.2.0"
 pendulum = ">=3.0.0"
-dapla-toolbelt = ">=3.0.0"
 pandas-stubs = ">=2.2.2.240807"
 
 [tool.poetry.group.dev.dependencies]
@@ -35,7 +34,6 @@ pytest = ">=6.2.5"
 sphinx = ">=6.2.1"
 sphinx-autobuild = ">=2021.3.14"
 sphinx-autodoc-typehints = ">=1.24.0"
-sphinx-click = ">=3.0.2"
 typeguard = ">=2.13.3"
 xdoctest = { extras = ["colors"], version = ">=0.15.10" }
 myst-parser = { version = ">=0.16.1" }

{ssb_konjunk-1.0.0 → ssb_konjunk-2.0.0}/src/ssb_konjunk/fame.py

@@ -6,11 +6,9 @@ https://sphinxcontrib-napoleon.readthedocs.io/en/latest/example_google.html
 """
 
 # Importing external packages
-import pandas as pd
-from dapla import FileClient
+from __future__ import annotations
 
-# Getting filesystem
-fs = FileClient.get_gcs_file_system()
+import pandas as pd
 
 
 def change_date_format_fame(series: pd.Series[str]) -> pd.Series[str]:
@@ -34,7 +32,7 @@ def write_out_fame_format_txt(
     names: pd.Series[str],
     dates: pd.Series[str],
     values: pd.Series[float],
-    gcp_path: str,
+    path: str,
 ) -> None:
     """Function to write out txt file in fame format.
 
@@ -42,9 +40,9 @@ def write_out_fame_format_txt(
         names: Pandas series containing name or type for value.
         dates: Pandas series containing date for values.
         values: Pandas series containing values.
-        gcp_path: String to google cloud.
+        path: String to output file.
     """
-    with fs.open(gcp_path, "w") as f:
+    with open(path, "w") as f:
         # Write data rows
         for name, date, value in zip(names, dates, values, strict=False):
             # Apply format specification

{ssb_konjunk-1.0.0 → ssb_konjunk-2.0.0}/src/ssb_konjunk/saving.py

@@ -5,8 +5,8 @@ Follows the the standardization for versioning and names.
 
 import glob
 import re
+import warnings
 
-import dapla
 import pandas as pd
 
 from ssb_konjunk import timestamp
@@ -39,7 +39,6 @@ def _structure_ssb_filepath(
     undermappe: str | None = None,
     version_number: int | None = None,
     filetype: str = "parquet",
-    fs: dapla.gcs.GCSFileSystem | None = None,
 ) -> str:
     """Structure the name of the file to SSB-format and the path.
 
@@ -53,7 +52,6 @@ def _structure_ssb_filepath(
         undermappe: Optional string for if you want folders betwen 'datatilstand' and file.
         version_number: Optional int for reading specific file.
         filetype: String with default 'parquet', specifies file type.
-        fs: the filesystem, pass with gsc Filesystem if Dapla. Default: None.
 
     Returns:
         str: the full path to the file.
@@ -61,11 +59,7 @@ def _structure_ssb_filepath(
     Raises:
         ValueError: Raise if version number is not None or int.
     """
-    # Handle that path starts with / in prodsonen.
-    if fs is None:
-        bucket = _remove_edge_slashes(bucket, only_last=True)
-    else:
-        bucket = _remove_edge_slashes(bucket)
+    bucket = _remove_edge_slashes(bucket)
     kortnavn = _remove_edge_slashes(kortnavn)
     datatilstand = _remove_edge_slashes(datatilstand)
     file_name = _remove_edge_slashes(file_name)
@@ -95,17 +89,12 @@ def _structure_ssb_filepath(
     return file_path
 
 
-def _get_files(
-    folder_path: str, filetype: str, fs: dapla.gcs.GCSFileSystem | None
-) -> list[str]:
+def _get_files(folder_path: str, filetype: str) -> list[str]:
     """Function to list files in a folder based on base name and timestamp."""
     filenames = []
 
     match_string = f"{folder_path}*"
-    if fs:
-        filenames = fs.glob(match_string)
-    else:
-        filenames = glob.glob(match_string)
+    filenames = glob.glob(match_string)
 
     # Only include files with the relevant file extension
     filenames = [i for i in filenames if i.endswith(filetype)]
@@ -237,28 +226,16 @@ def _save_df(
     df: pd.DataFrame,
     file_path: str,
     filetype: str,
-    fs: dapla.gcs.GCSFileSystem | None,
     seperator: str,
     encoding: str,
 ) -> None:
     """Do the actual saving, either as csv or parquet."""
     # Save as parquet
     if filetype == "parquet":
-
-        if fs:
-            with fs.open(file_path, "wb") as f:
-                df.to_parquet(f, index=False)
-                f.close()
-        else:
-            df.to_parquet(file_path, index=False)
+        df.to_parquet(file_path, index=False)
     # Save as csv
     elif filetype == "csv":
-        if fs:
-            with fs.open(file_path, "wb") as f:
-                df.to_csv(f, sep=seperator, index=False, encoding=encoding)
-                f.close()
-        else:
-            df.to_csv(file_path, sep=seperator, index=False, encoding=encoding)
+        df.to_csv(file_path, sep=seperator, index=False, encoding=encoding)
     # Save as jsonl
     elif filetype == "jsonl":
         df.to_json(file_path, orient="records", lines=True)
@@ -285,7 +262,6 @@ def write_ssb_file(
     undermappe: str | None = None,
     stable_version: bool = True,
     filetype: str = "parquet",
-    fs: dapla.gcs.GCSFileSystem | None = None,
     seperator: str = ";",
     encoding: str = "latin1",
 ) -> None:
@@ -302,7 +278,6 @@ def write_ssb_file(
         undermappe: Optional folder under 'datatilstand'.
         stable_version: Bool for whether you should have checks in place in case of overwrite.
         filetype: the filetype to save as. Default: 'parquet'.
-        fs: the filesystem, pass with gsc Filesystem if Dapla. Default: None.
         seperator: the seperator to use it filetype is csv. Default: ';'.
         encoding: Encoding for file, base is latin1.
 
@@ -326,10 +301,9 @@ def write_ssb_file(
         datatilstand=datatilstand,
         file_name=file_name,
         undermappe=undermappe,
-        fs=fs,
     )
     # Get list with the filenames, if several, ordered by the highest version number at last.
-    files = _get_files(file_path, filetype, fs=fs)
+    files = _get_files(file_path, filetype)
     # Find version number/decide whether to overwrite or make new version.
     version_number = _find_version_number(files, stable_version)
 
@@ -338,7 +312,7 @@ def write_ssb_file(
             file_path = file_path[:-1]
         file_path = f"{file_path}_v{version_number}.{filetype}"
 
-        _save_df(df, file_path, filetype, fs, seperator, encoding)
+        _save_df(df, file_path, filetype, seperator, encoding)
 
 
 def read_ssb_file(
@@ -350,8 +324,8 @@ def read_ssb_file(
     datatilstand: str = "",
     undermappe: str | None = None,
     filetype: str = "parquet",
+    columns: list[str] | None = None,
     version_number: int | None = None,
-    fs: dapla.gcs.GCSFileSystem | None = None,
     seperator: str = ";",
     encoding: str = "latin1",
 ) -> pd.DataFrame | None:
@@ -371,7 +345,7 @@ def read_ssb_file(
         undermappe: Optional folder under 'datatilstand'.
         version_number: possibility to get another version, than the newest (i.e. highest version number). Default: np.nan.
         filetype: the filetype to save as. Default: 'parquet'.
-        fs: the filesystem, pass with gsc Filesystem if Dapla. Default: None.
+        columns: Columns to read from the file. If None (default), all columns are read.
         seperator: the seperator to use it filetype is csv. Default: ';'.
         encoding: Encoding for file, base is latin1.
 
@@ -392,12 +366,11 @@ def read_ssb_file(
         undermappe=undermappe,
         version_number=version_number,
         filetype=filetype,
-        fs=fs,
     )
 
     if not version_number:
         # If version number not specified then list out versions.
-        files = _get_files(file_path, filetype, fs=fs)
+        files = _get_files(file_path, filetype)
         # If list is empty, no matching files of any version were found.
         if not files:
             raise FileNotFoundError(
@@ -408,18 +381,22 @@ def read_ssb_file(
 
     # Different functions used for reading depending on the filetype.
     if filetype == "csv":
-        if fs:
-            # Samme som tidligere kan brukes til å lese alle filformater.
-            with fs.open(file_path, "r") as f:
-                df = pd.read_csv(f, sep=seperator, encoding=encoding)
-                f.close()
-        else:
-            df = pd.read_csv(file_path, sep=seperator, encoding=encoding)
+        df = pd.read_csv(file_path, sep=seperator, encoding=encoding, usecols=columns)
     elif filetype == "parquet":
-        df = pd.read_parquet(file_path, filesystem=fs)
+        df = pd.read_parquet(file_path, columns=columns)
     elif filetype == "jsonl":
-        df = pd.read_json(file_path, lines=True)
+        if columns is not None:
+            warnings.warn(
+                f"Columns argumentet blir ignorert for {filetype} filer, hele filen vil bli lastet inn.",
+                stacklevel=2,
+            )
+        df = pd.read_json(file_path, lines=False)
     elif filetype == "json":
+        if columns is not None:
+            warnings.warn(
+                f"Columns argumentet blir ignorert for {filetype} filer, hele filen vil bli lastet inn.",
+                stacklevel=2,
+            )
         df = pd.read_json(file_path, lines=False)
     # Returns pandas df.
     return df

{ssb_konjunk-1.0.0 → ssb_konjunk-2.0.0}/src/ssb_konjunk/xml_handling.py

@@ -2,27 +2,19 @@
 
 import xml.etree.ElementTree as ET
 
-import dapla
 
-
-def read_xml(xml_file: str, fs: dapla.gcs.GCSFileSystem | None = None) -> ET.Element:
+def read_xml(xml_file: str) -> ET.Element:
     """Funtion to get xml root from disk.
 
     Args:
         xml_file: Strin value for xml filepath.
-        fs: filesystem
 
     Returns:
         ET.Element: Root of xml file.
     """
-    if fs:
-        with fs.open(xml_file, mode="r") as file:
-            single_xml = file.read()
-            file.close()
-    else:
-        with open(xml_file) as file:
-            single_xml = file.read()
-            file.close()
+    with open(xml_file) as file:
+        single_xml = file.read()
+        file.close()
 
     return ET.fromstring(single_xml)