ssb-konjunk 0.1.22__tar.gz → 1.0.1__tar.gz

{ssb_konjunk-0.1.22 → ssb_konjunk-1.0.1}/PKG-INFO

@@ -1,10 +1,10 @@
 Metadata-Version: 2.3
 Name: ssb-konjunk
-Version: 0.1.22
-Summary: SSB Konjunk
+Version: 1.0.1
+Summary: SSB Konjunk 422
 License: MIT
-Author: Edvard Garmannslund
-Author-email: ged@ssb.no
+Author: Johanne Saxegaard
+Author-email: jox@ssb.no
 Requires-Python: >=3.10,<4.0
 Classifier: Development Status :: 1 - Planning
 Classifier: License :: OSI Approved :: MIT License
@@ -44,7 +44,6 @@ Description-Content-Type: text/markdown
 [pypi status]: https://pypi.org/project/ssb-konjunk/
 [documentation]: https://statisticsnorway.github.io/ssb-konjunk
 [tests]: https://github.com/statisticsnorway/ssb-konjunk/actions?workflow=Tests
-
 [sonarcov]: https://sonarcloud.io/summary/overall?id=statisticsnorway_ssb-konjunk
 [sonarquality]: https://sonarcloud.io/summary/overall?id=statisticsnorway_ssb-konjunk
 [pre-commit]: https://github.com/pre-commit/pre-commit

{ssb_konjunk-0.1.22 → ssb_konjunk-1.0.1}/README.md

@@ -18,7 +18,6 @@
 [pypi status]: https://pypi.org/project/ssb-konjunk/
 [documentation]: https://statisticsnorway.github.io/ssb-konjunk
 [tests]: https://github.com/statisticsnorway/ssb-konjunk/actions?workflow=Tests
-
 [sonarcov]: https://sonarcloud.io/summary/overall?id=statisticsnorway_ssb-konjunk
 [sonarquality]: https://sonarcloud.io/summary/overall?id=statisticsnorway_ssb-konjunk
 [pre-commit]: https://github.com/pre-commit/pre-commit

{ssb_konjunk-0.1.22 → ssb_konjunk-1.0.1}/pyproject.toml

@@ -1,8 +1,8 @@
 [tool.poetry]
 name = "ssb-konjunk"
-version = "0.1.22"
-description = "SSB Konjunk"
-authors = ["Edvard Garmannslund <ged@ssb.no>"]
+version = "1.0.1"
+description = "SSB Konjunk 422"
+authors = ["Johanne Saxegaard <jox@ssb.no>"]
 license = "MIT"
 readme = "README.md"
 homepage = "https://github.com/statisticsnorway/ssb-konjunk"
@@ -60,6 +60,9 @@ relative_files = true
 show_missing = true
 fail_under = 50
 
+[tool.deptry.per_rule_ignores]
+DEP001 = ["nox", "nox_poetry"]  # packages available by default
+
 [tool.mypy]
 strict = true
 warn_unreachable = true
@@ -96,7 +99,7 @@ select = [
     "RUF",  # the ruff developer's own rules
 ]
 ignore = [
-    "ANN202", # Don't requiere return type annotation for private functions.
+    "ANN202", # Don't require return type annotation for private functions.
     "ANN401", # Allow type annotation with type Any.
     "D100",   # Supress undocumented-public-module. Only doc of public api required.
     "FBT001", # Allow boolean positional arguments in a function.

{ssb_konjunk-0.1.22 → ssb_konjunk-1.0.1}/src/ssb_konjunk/saving.py

@@ -5,6 +5,7 @@ Follows the the standardization for versioning and names.
 
 import glob
 import re
+import warnings
 
 import dapla
 import pandas as pd
@@ -350,6 +351,7 @@ 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 = ";",
@@ -371,6 +373,7 @@ 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'.
+        columns: Columns to read from the file. If None (default), all columns are read.
         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.
@@ -411,15 +414,27 @@ def read_ssb_file(
         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)
+                df = pd.read_csv(f, sep=seperator, encoding=encoding, usecols=columns)
                 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, filesystem=fs)
     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