owid-datautils 0.6.2__tar.gz → 0.6.3__tar.gz

{owid_datautils-0.6.2 → owid_datautils-0.6.3}/.readthedocs.yaml

@@ -6,7 +6,7 @@ version: 2
 
 # Set the version of Python and other tools you might need
 build:
-  os: ubuntu-20.04
+  os: ubuntu-24.04
   tools: {python: "3.8"}
   jobs:
     pre_create_environment:

{owid_datautils-0.6.2 → owid_datautils-0.6.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: owid-datautils
-Version: 0.6.2
+Version: 0.6.3
 Summary: Data utils library by the Data Team at Our World in Data
 Author-email: Our World in Data <tech@ourworldindata.org>
 License-Expression: MIT
@@ -8,13 +8,21 @@ License-File: LICENSE
 Keywords: data cleaning,data processing,data utils,our world in data
 Requires-Python: <4.0,>=3.10
 Requires-Dist: boto3>=1.38.23
+Requires-Dist: brotli>=1.2.0
 Requires-Dist: click>=8.1.7
 Requires-Dist: colorama>=0.4.4
-Requires-Dist: gdown>=4.5.2
+Requires-Dist: cryptography>=46.0.3
+Requires-Dist: gdown>=5.2.2
 Requires-Dist: gsheets>=0.6.1
-Requires-Dist: pandas>=2.2.3
+Requires-Dist: jinja2>=3.1.6
+Requires-Dist: pandas<3,>=2.2.3
+Requires-Dist: protobuf>=6.33.4
 Requires-Dist: py7zr>=0.22.0
 Requires-Dist: pyarrow>=18.0.0
+Requires-Dist: pyasn1>=0.6.3
 Requires-Dist: pydrive2>=1.15.0
+Requires-Dist: pyopenssl>=26.0.0
+Requires-Dist: requests>=2.32.5
 Requires-Dist: structlog>=21.5.0
-Requires-Dist: urllib3<2
+Requires-Dist: tornado>=6.5.5
+Requires-Dist: urllib3<3

{owid_datautils-0.6.2 → owid_datautils-0.6.3}/owid/datautils/common.py

@@ -1,20 +1,20 @@
 """Common objects shared by other modules."""
 
 import warnings
-from typing import Any, List, Set, Union, cast
+from typing import Any, cast
 
 
 class ExceptionFromDocstring(Exception):
     """Exception that returns its own docstring, if no message is explicitly given."""
 
-    def __init__(self, exception_message: Union[str, None] = None, *args: Any):
+    def __init__(self, exception_message: str | None = None, *args: Any):
         super().__init__(exception_message or self.__doc__, *args)
 
 
 class ExceptionFromDocstringWithKwargs(Exception):
     """Exception that returns its own docstring, if no message is explicitly given."""
 
-    def __init__(self, exception_message: Union[str, None] = None, *args: Any, **kwargs: Any):
+    def __init__(self, exception_message: str | None = None, *args: Any, **kwargs: Any):
         text = cast(str, exception_message or self.__doc__)
         if kwargs:
             additional_text = ", ".join([f"{key}: {value}" for key, value in kwargs.items()])
@@ -23,9 +23,7 @@ class ExceptionFromDocstringWithKwargs(Exception):
         super().__init__(text, *args)
 
 
-def warn_on_list_of_entities(
-    list_of_entities: Union[List[Any], Set[Any]], warning_message: str, show_list: bool
-) -> None:
+def warn_on_list_of_entities(list_of_entities: list[Any] | set[Any], warning_message: str, show_list: bool) -> None:
     """Raise a warning with a custom message, and optionally print a list of affected elements.
 
     Args:
@@ -34,7 +32,8 @@ def warn_on_list_of_entities(
         show_list: True to print a list of affected entities.
 
     """
-    warnings.warn(warning_message)
     if show_list:
-        print(warning_message)
-        print("\n".join(["* " + str(entity) for entity in list_of_entities]))
+        entity_list = "\n".join(["* " + str(entity) for entity in list_of_entities])
+        warnings.warn(f"{warning_message}\n{entity_list}")
+    else:
+        warnings.warn(warning_message)

{owid_datautils-0.6.2 → owid_datautils-0.6.3}/owid/datautils/dataframes.py

@@ -1,7 +1,8 @@
 """Objects related to pandas dataframes."""
 
 import warnings
-from typing import Any, Callable, Dict, List, Optional, Tuple, Union, cast
+from collections.abc import Callable
+from typing import Any, cast
 
 import numpy as np
 import pandas as pd
@@ -71,7 +72,7 @@ class ObjectsAreNotDataframes(ExceptionFromDocstring):
 def compare(
     df1: pd.DataFrame,
     df2: pd.DataFrame,
-    columns: Optional[List[str]] = None,
+    columns: list[str] | None = None,
     absolute_tolerance: float = 1e-8,
     relative_tolerance: float = 1e-8,
 ) -> pd.DataFrame:
@@ -135,13 +136,13 @@ def compare(
         else:
             # For numeric data, consider them equal within certain absolute and relative tolerances.
             compared_row = np.isclose(
-                df1[col].values,  # type: ignore
-                df2[col].values,  # type: ignore
+                df1[col].values,  # ty: ignore
+                df2[col].values,  # ty: ignore
                 atol=absolute_tolerance,
                 rtol=relative_tolerance,
             )
         # Treat nans as equal.
-        compared_row[pd.isnull(df1[col].values) & pd.isnull(df2[col].values)] = True  # type: ignore
+        compared_row[pd.isnull(df1[col].values) & pd.isnull(df2[col].values)] = True  # ty: ignore
         compared[col] = compared_row
 
     return compared
@@ -153,7 +154,7 @@ def are_equal(
     absolute_tolerance: float = 1e-8,
     relative_tolerance: float = 1e-8,
     verbose: bool = True,
-) -> Tuple[bool, pd.DataFrame]:
+) -> tuple[bool, pd.DataFrame]:
     """Check if two DataFrames are equal with detailed comparison report.
 
     Comprehensive equality check that compares structure, dtypes, and values
@@ -230,12 +231,10 @@ def are_equal(
             equal = False
         for col in common_columns:
             if df1[col].dtype != df2[col].dtype:
-                summary += (
-                    f"  * Column {col} is of type {df1[col].dtype} for df1, but type" f" {df2[col].dtype} for df2."
-                )
+                summary += f"  * Column {col} is of type {df1[col].dtype} for df1, but type {df2[col].dtype} for df2."
                 equal = False
     else:
-        summary += f"\n* Only {len(common_columns)} common columns out of" f" {len(all_columns)} distinct columns."
+        summary += f"\n* Only {len(common_columns)} common columns out of {len(all_columns)} distinct columns."
         equal = False
 
     if not can_be_compared:
@@ -245,7 +244,7 @@ def are_equal(
     else:
         # Check if indexes are equal.
         if (df1.index != df2.index).any():
-            summary += "\n* Dataframes have different indexes (consider resetting indexes of" " input dataframes)."
+            summary += "\n* Dataframes have different indexes (consider resetting indexes of input dataframes)."
             equal = False
 
         # Dataframes can be compared cell by cell (two nans on the same cell are considered equal).
@@ -256,9 +255,9 @@ def are_equal(
             absolute_tolerance=absolute_tolerance,
             relative_tolerance=relative_tolerance,
         )
-        all_values_equal = compared.all().all()  # type: ignore
+        all_values_equal = compared.all().all()  # ty: ignore
         if not all_values_equal:
-            summary += "\n* Values differ by more than the given absolute and relative" " tolerances."
+            summary += "\n* Values differ by more than the given absolute and relative tolerances."
 
         # Dataframes are equal only if all previous checks have passed.
         equal = equal & all_values_equal
@@ -273,7 +272,7 @@ def are_equal(
         # Optionally print the summary of the comparison.
         print(summary)
 
-    return equal, compared
+    return equal, compared  # ty: ignore[invalid-return-type]
 
 
 def _calculate_weighted_mean(
@@ -310,11 +309,11 @@ def _calculate_weighted_mean(
 
 def groupby_agg(
     df: pd.DataFrame,
-    groupby_columns: Union[List[str], str],
-    aggregations: Optional[Dict[str, Any]] = None,
-    num_allowed_nans: Optional[int] = None,
-    frac_allowed_nans: Optional[float] = None,
-    min_num_values: Optional[int] = None,
+    groupby_columns: list[str] | str,
+    aggregations: dict[str, Any] | None = None,
+    num_allowed_nans: int | None = None,
+    frac_allowed_nans: float | None = None,
+    min_num_values: int | None = None,
 ) -> pd.DataFrame:
     """Group DataFrame with intelligent NaN handling during aggregation.
 
@@ -423,7 +422,7 @@ def groupby_agg(
 
         # Handle regular aggregations first (if any)
         if regular_aggregations:
-            grouped = df.groupby(groupby_columns, **groupby_kwargs).agg(regular_aggregations)  # type: ignore
+            grouped = df.groupby(groupby_columns, **groupby_kwargs).agg(regular_aggregations)  # ty: ignore
         else:
             # Create empty DataFrame with proper groupby index for weighted-only case
             grouped = (
@@ -445,10 +444,10 @@ def groupby_agg(
                 ),
                 include_groups=False,
             )
-            grouped[col] = weighted_results  # type: ignore
+            grouped[col] = weighted_results  # ty: ignore
     else:
         # No weighted aggregations; use standard grouping logic
-        grouped = df.groupby(groupby_columns, **groupby_kwargs).agg(aggregations)  # type: ignore
+        grouped = df.groupby(groupby_columns, **groupby_kwargs).agg(aggregations)  # ty: ignore
 
     # Calculate a few necessary parameters related to the number of nans and valid elements.
     if (num_allowed_nans is not None) or (frac_allowed_nans is not None) or (min_num_values is not None):
@@ -456,16 +455,16 @@ def groupby_agg(
         num_nans_detected = count_missing_in_groups(df, groupby_columns, **groupby_kwargs)
     if (frac_allowed_nans is not None) or (min_num_values is not None):
         # Count number of total elements in each group (counting both nans and non-nan values).
-        num_elements = df.groupby(groupby_columns, **groupby_kwargs).size()  # type: ignore
+        num_elements = df.groupby(groupby_columns, **groupby_kwargs).size()  # ty: ignore
 
     # Apply conditions sequentially.
     if num_allowed_nans is not None:
         # Make nan any aggregation where there were too many missing values.
-        grouped = grouped[num_nans_detected <= num_allowed_nans]  # type: ignore
+        grouped = grouped[num_nans_detected <= num_allowed_nans]  # ty: ignore
 
     if frac_allowed_nans is not None:
         # Make nan any aggregation where there were too many missing values.
-        grouped = grouped[num_nans_detected.divide(num_elements, axis="index") <= frac_allowed_nans]  # type: ignore
+        grouped = grouped[num_nans_detected.divide(num_elements, axis="index") <= frac_allowed_nans]  # ty: ignore
 
     if min_num_values is not None:
         # Make nan any aggregation where there were too few valid (non-nan) values.
@@ -477,13 +476,13 @@ def groupby_agg(
         # Therefore, we impose that either the number of valid values is >= min_num_values, or that there are no nans
         # (and hence all values are valid).
         grouped = grouped[
-            (-num_nans_detected.subtract(num_elements, axis="index") >= min_num_values) | (num_nans_detected == 0)  # type: ignore
+            (-num_nans_detected.subtract(num_elements, axis="index") >= min_num_values) | (num_nans_detected == 0)  # ty: ignore
         ]
 
     return cast(pd.DataFrame, grouped)
 
 
-def count_missing_in_groups(df: pd.DataFrame, groupby_columns: List[str], **kwargs: Any) -> pd.DataFrame:
+def count_missing_in_groups(df: pd.DataFrame, groupby_columns: list[str], **kwargs: Any) -> pd.DataFrame:
     """Count the number of missing values in each group.
 
     This is equivalent but faster than:
@@ -502,7 +501,7 @@ def count_missing_in_groups(df: pd.DataFrame, groupby_columns: List[str], **kwar
     return cast(pd.DataFrame, num_nans_detected)
 
 
-def multi_merge(dfs: List[pd.DataFrame], on: Union[List[str], str], how: str = "inner") -> pd.DataFrame:
+def multi_merge(dfs: list[pd.DataFrame], on: list[str] | str, how: str = "inner") -> pd.DataFrame:
     """Merge multiple DataFrames on common columns.
 
     Convenience function for merging more than two DataFrames sequentially.
@@ -535,14 +534,14 @@ def multi_merge(dfs: List[pd.DataFrame], on: Union[List[str], str], how: str = "
     """
     merged = dfs[0].copy()
     for df in dfs[1:]:
-        merged = pd.merge(merged, df, how=how, on=on)  # type: ignore
+        merged = pd.merge(merged, df, how=how, on=on)  # ty: ignore
 
     return merged
 
 
 def map_series(
     series: pd.Series,
-    mapping: Dict[Any, Any],
+    mapping: dict[Any, Any],
     make_unmapped_values_nan: bool = False,
     warn_on_missing_mappings: bool = False,
     warn_on_unused_mappings: bool = False,
@@ -644,7 +643,7 @@ def map_series(
         missing = series_mapped.isnull() & (~series.isin(values_mapped_to_nan))
         if missing.any():
             # Replace those nans by their original values.
-            series_mapped.loc[missing] = series[missing]  # type: ignore[reportCallIssue]
+            series_mapped.loc[missing] = series[missing]  # ty: ignore[call-non-callable]
 
     if warn_on_missing_mappings:
         unmapped = set(series) - set(mapping)
@@ -667,7 +666,7 @@ def map_series(
     return series_mapped
 
 
-def rename_categories(series: pd.Series, mapping: Dict[Any, Any]) -> pd.Series:
+def rename_categories(series: pd.Series, mapping: dict[Any, Any]) -> pd.Series:
     """Alternative to pd.Series.cat.rename_categories which supports non-unique categories.
 
     We do that by replacing non-unique categories first and then mapping with unique categories.
@@ -679,7 +678,7 @@ def rename_categories(series: pd.Series, mapping: Dict[Any, Any]) -> pd.Series:
 
     series = series.copy()
 
-    new_mapping: Dict[Any, Any] = {}
+    new_mapping: dict[Any, Any] = {}
     for map_from, map_to in mapping.items():
         # Map nulls right away
         if pd.isnull(map_to):
@@ -699,7 +698,7 @@ def rename_categories(series: pd.Series, mapping: Dict[Any, Any]) -> pd.Series:
     )
 
 
-def concatenate(objs: List[pd.DataFrame], **kwargs: Any) -> pd.DataFrame:
+def concatenate(objs: list[pd.DataFrame], **kwargs: Any) -> pd.DataFrame:
     """Concatenate while preserving categorical columns.
 
     Original source code from https://stackoverflow.com/a/57809778/1275818.
@@ -719,7 +718,7 @@ def concatenate(objs: List[pd.DataFrame], **kwargs: Any) -> pd.DataFrame:
         return pd.concat(objs, **kwargs)
 
 
-def apply_on_categoricals(cat_series: List[pd.Series], func: Callable[..., str]) -> pd.Series:
+def apply_on_categoricals(cat_series: list[pd.Series], func: Callable[..., str]) -> pd.Series:
     """Apply a function across multiple categorical Series efficiently.
 
     High-performance operation that applies a function to categorical Series
@@ -770,13 +769,13 @@ def apply_on_categoricals(cat_series: List[pd.Series], func: Callable[..., str])
         # use existing category
         codes.append(seen[cat_codes])
 
-    return cast(pd.Series, pd.Categorical.from_codes(codes, categories=categories))
+    return cast(pd.Series, pd.Categorical.from_codes(codes, categories=pd.Index(categories)))
 
 
 def combine_two_overlapping_dataframes(
     df1: pd.DataFrame,
     df2: pd.DataFrame,
-    index_columns: Optional[List[str]] = None,
+    index_columns: list[str] | None = None,
     keep_column_order: bool = False,
 ) -> pd.DataFrame:
     """Combine two DataFrames with overlapping columns, prioritizing the first.
@@ -835,7 +834,7 @@ def combine_two_overlapping_dataframes(
     if index_columns is not None:
         # Ensure dataframes have a dummy index.
         if not ((df1.index.names == [None]) and (df2.index.names == [None])):
-            warnings.warn("If index_columns is given, dataframes should have a dummy index. Use" " reset_index().")
+            warnings.warn("If index_columns is given, dataframes should have a dummy index. Use reset_index().")
         # Set index columns.
         df1 = df1.set_index(index_columns)
         df2 = df2.set_index(index_columns)

{owid_datautils-0.6.2 → owid_datautils-0.6.3}/owid/datautils/decorators.py

@@ -2,12 +2,13 @@
 
 import functools
 import tempfile
-from typing import Any, Callable, Optional
+from collections.abc import Callable
+from typing import Any
 
 from owid.datautils.web import download_file_from_url
 
 
-def enable_file_download(path_arg_name: Optional[str] = None) -> Callable[[Any], Any]:
+def enable_file_download(path_arg_name: str | None = None) -> Callable[[Any], Any]:
     """Decorator that allows functions expecting local file paths to accept URLs and S3 paths.
 
     This decorator automatically downloads remote files to temporary storage before calling
@@ -55,11 +56,11 @@ def enable_file_download(path_arg_name: Optional[str] = None) -> Callable[[Any],
             # Get path to file
             _used_args = False
             if args:
-                args = list(args)  # type: ignore
+                args = list(args)  # ty: ignore
                 path = args[0]
                 _used_args = True
             else:
-                path = kwargs.get(path_arg_name)  # type: ignore
+                path = kwargs.get(path_arg_name)  # ty: ignore
                 if path is None:
                     raise ValueError(f"Filename was not found in args or kwargs ({path_arg_name}!")
             # Check if download is needed and download
@@ -73,7 +74,7 @@ def enable_file_download(path_arg_name: Optional[str] = None) -> Callable[[Any],
                     elif path.startswith(prefixes["s3"]):
                         try:
                             # Import here to avoid circular dependency
-                            from owid.catalog import s3_utils  # type: ignore
+                            from owid.catalog import s3_utils  # ty: ignore
                         except ImportError as e:
                             raise ImportError("owid-catalog is required for S3 downloads. ") from e
 
@@ -81,9 +82,9 @@ def enable_file_download(path_arg_name: Optional[str] = None) -> Callable[[Any],
 
                     # Modify args/kwargs
                     if _used_args:
-                        args[0] = temp_file.name  # type: ignore
+                        args[0] = temp_file.name  # ty: ignore
                     else:
-                        kwargs[path_arg_name] = temp_file.name  # type: ignore
+                        kwargs[path_arg_name] = temp_file.name  # ty: ignore
                     # Call function
                     return func(*args, **kwargs)
             else:  # Run function on local file

{owid_datautils-0.6.2 → owid_datautils-0.6.3}/owid/datautils/format/numbers.py

@@ -1,18 +1,18 @@
 """Numeric formatting."""
 
 import re
-from typing import Any, Dict, Set, Union
+from typing import Any
 
 
 class IntegerNumber:
     """Wrapper around integer numbers."""
 
-    def __init__(self, number: Union[str, int]) -> None:
+    def __init__(self, number: str | int) -> None:
         self.number_raw = number
         self.number = self.init_clean(number)
 
     @classmethod
-    def init_clean(cls, number: Union[int, str]) -> str:
+    def init_clean(cls, number: int | str) -> str:
         """First number cleaning steps.
 
         Args:
@@ -103,7 +103,7 @@ class IntegerNumberWithWords:
     Use with caution!
     """
 
-    numeric_words: Dict[str, Dict[str, Any]] = {
+    numeric_words: dict[str, dict[str, Any]] = {
         "million": {
             "words": [
                 "million",
@@ -175,22 +175,22 @@ class IntegerNumberWithWords:
         return r"\s?".join(regex)
 
     @classmethod
-    def numeric_words_list(cls) -> Set[str]:
+    def numeric_words_list(cls) -> set[str]:
         """Return list of all numeric words (flattened)."""
         words = set(word for value in cls.numeric_words.values() for word in value["words"] if word != "")
-        return words  # type: ignore
+        return words  # ty: ignore
 
-    def _match_numeric_words(self) -> Dict[str, Union[str, int]]:
+    def _match_numeric_words(self) -> dict[str, str | int]:
         """Match number with words."""
         match = re.search(self.regex_number_verbose(), self.number)
         if match:
             numbers = match.groupdict(default=0)
-            return numbers  # type: ignore
+            return numbers  # ty: ignore
         else:
             raise ValueError("Number may not contain numeric words. Please review!")
 
     @classmethod
-    def _build_IntegerNumber(cls, numbers: Dict[str, Union[str, int]]) -> int:
+    def _build_IntegerNumber(cls, numbers: dict[str, str | int]) -> int:
         """Build number from dictionary."""
         value = 0
         for k, v in numbers.items():
@@ -223,7 +223,7 @@ class IntegerNumberWithWords:
         raise ValueError(f"Given number {self.number_raw} is not valid!")
 
 
-def num_to_str(num_as_str: Union[int, str]) -> str:
+def num_to_str(num_as_str: int | str) -> str:
     """Convert number to string.
 
     Args:
@@ -251,7 +251,7 @@ def remove_multiple_whitespaces(text: str) -> str:
     return re.sub(r"\s+", " ", text)
 
 
-def format_number(number: Union[int, str]) -> int:
+def format_number(number: int | str) -> int:
     """Format number string to integer.
 
     Only supports integer conversion. Handles various formats including

{owid_datautils-0.6.2 → owid_datautils-0.6.3}/owid/datautils/google/api.py

@@ -1,6 +1,6 @@
 """Google API class."""
 
-from typing import Any, Optional
+from typing import Any
 
 import gdown
 from pydrive2.auth import GoogleAuth
@@ -20,7 +20,7 @@ from owid.datautils.google.sheets import GSheetsApi
 class GoogleApi:
     """API for Google Drive."""
 
-    def __init__(self, clients_secrets_file: Optional[str] = None) -> None:
+    def __init__(self, clients_secrets_file: str | None = None) -> None:
         """Initialise Google API.
 
         To obtain `client_secrets_file`, follow the instructions from:
@@ -74,8 +74,8 @@ class GoogleApi:
     def download_file(
         cls,
         output: str,
-        url: Optional[str] = None,
-        file_id: Optional[str] = None,
+        url: str | None = None,
+        file_id: str | None = None,
         quiet: bool = True,
         **kwargs: Any,
     ) -> None:
@@ -93,7 +93,7 @@ class GoogleApi:
             ValueError: If neither `url` nor `id` are provided.
         """
         if url:
-            gdown.download(url=url, output=output, fuzzy=True, quiet=quiet, **kwargs)
+            gdown.download(url=url, output=output, quiet=quiet, **kwargs)
         elif file_id:
             gdown.download(id=file_id, output=output, quiet=quiet, **kwargs)
         else:
@@ -119,4 +119,4 @@ class GoogleApi:
         request = f"'{parent_id}' in parents and trashed=false"
         # Get list of files
         files = self.drive.ListFile({"q": request}).GetList()
-        return files  # type: ignore[reportReturnType]
+        return files  # ty: ignore[invalid-return-type]

{owid_datautils-0.6.2 → owid_datautils-0.6.3}/owid/datautils/google/config.py

@@ -3,7 +3,6 @@
 import os
 from pathlib import Path
 from shutil import copyfile
-from typing import Union
 
 import yaml
 from pydrive2.auth import GoogleAuth
@@ -15,7 +14,7 @@ SETTINGS_PATH = os.path.join(CONFIG_DIR, "google_settings.yaml")
 CREDENTIALS_PATH = os.path.join(CONFIG_DIR, "google_credentials.json")
 
 
-def google_config_init(client_secrets_file: Union[str, Path], encoding: str = "utf8") -> GoogleAuth:
+def google_config_init(client_secrets_file: str | Path, encoding: str = "utf8") -> GoogleAuth:
     """Initialise Google configuration files.
 
     Uses `clients_secrets` to generate all the required Google configuration files: `SETTINGS_PATH`, `CREDENTIALS_PATH`.
@@ -45,7 +44,7 @@ def google_config_init(client_secrets_file: Union[str, Path], encoding: str = "u
     """
     # Check client_secrets
     if not os.path.isfile(client_secrets_file):
-        raise ValueError(f"Credentials not found at {client_secrets_file}. Please provide a valid" " path!")
+        raise ValueError(f"Credentials not found at {client_secrets_file}. Please provide a valid path!")
     # Check or create config directory
     if not os.path.isdir(CONFIG_DIR):
         os.makedirs(CONFIG_DIR, exist_ok=True)
@@ -87,12 +86,10 @@ def _check_google_config() -> None:
                         - owid.datautils.google.config.CREDENTIALS_PATH
     """
     if not os.path.isdir(CONFIG_DIR):
-        raise FileNotFoundError(
-            f"{CONFIG_DIR} folder is not created. Please check you have run" " `google_config_init`!"
-        )
+        raise FileNotFoundError(f"{CONFIG_DIR} folder is not created. Please check you have run `google_config_init`!")
     for f in [CLIENT_SECRETS_PATH, CREDENTIALS_PATH, SETTINGS_PATH]:
         if not os.path.isfile(f):
-            raise FileNotFoundError(f"{f} file was not found. Please check you have run" " `google_config_init`!")
+            raise FileNotFoundError(f"{f} file was not found. Please check you have run `google_config_init`!")
 
 
 def is_google_config_init() -> bool:

{owid_datautils-0.6.2 → owid_datautils-0.6.3}/owid/datautils/google/sheets.py

@@ -1,7 +1,7 @@
 """Google Sheet utils."""
 
 import os
-from typing import Any, Optional, Union
+from typing import Any
 
 import pandas as pd
 from gsheets import Sheets
@@ -35,7 +35,7 @@ class GSheetsApi:
         if not os.path.isdir(credentials_folder):
             os.makedirs(credentials_folder, exist_ok=True)
 
-    def get(self, spreadsheet_id: str, worksheet_id: Optional[int] = None) -> Union[SpreadSheet, WorkSheet]:
+    def get(self, spreadsheet_id: str, worksheet_id: int | None = None) -> SpreadSheet | WorkSheet:
         """Get a spreadsheet or worksheet from a Google sheet.
 
         If only `spreadsheet_id` is provided, this will return the entire spreadsheet. Otherwise,
@@ -50,14 +50,14 @@ class GSheetsApi:
         """
         ssheet = self.sheets.get(spreadsheet_id)
         if worksheet_id:
-            return ssheet.get(worksheet_id)  # type: ignore[reportReturnType]
-        return ssheet  # type: ignore[reportReturnType]
+            return ssheet.get(worksheet_id)  # ty: ignore[invalid-return-type]
+        return ssheet  # ty: ignore[invalid-return-type]
 
     def download_worksheet(
         self,
         spreadsheet_id: str,
         worksheet_id: int,
-        output_path: Optional[str] = None,
+        output_path: str | None = None,
         encoding: str = "utf-8",
         **kwargs: Any,
     ) -> None:
@@ -74,7 +74,11 @@ class GSheetsApi:
         """
         sheet = self.get(spreadsheet_id, worksheet_id)
         if output_path:
-            sheet.to_csv(output_path, encoding=encoding, **kwargs)  # type: ignore[reportCallIssue]
+            sheet.to_csv(
+                output_path,
+                encoding=encoding,
+                **kwargs,  # ty: ignore[call-non-callable]
+            )
         else:
             make_filename = "%(title)s.csv"
             sheet.to_csv(make_filename=make_filename, encoding=encoding, **kwargs)
@@ -109,5 +113,5 @@ class GSheetsApi:
             Dataframe with the data from the worksheet.
         """
         ws = self.get(spreadsheet_id, worksheet_id)
-        df: pd.DataFrame = ws.to_frame()  # type: ignore[reportAttributeAccessIssue]
+        df: pd.DataFrame = ws.to_frame()  # ty: ignore[unresolved-attribute]
         return df

{owid_datautils-0.6.2 → owid_datautils-0.6.3}/owid/datautils/io/archive.py

@@ -3,7 +3,7 @@
 import tarfile
 import zipfile
 from pathlib import Path
-from typing import Union, cast
+from typing import cast
 
 from py7zr import SevenZipFile
 
@@ -12,8 +12,8 @@ from owid.datautils.decorators import enable_file_download
 
 @enable_file_download(path_arg_name="input_file")
 def decompress_file(
-    input_file: Union[str, Path],
-    output_folder: Union[str, Path],
+    input_file: str | Path,
+    output_folder: str | Path,
     overwrite: bool = False,
 ) -> None:
     """Extract a zip or tar file.
@@ -41,8 +41,8 @@ def decompress_file(
 
 
 def _decompress_zip_file(
-    input_file: Union[str, Path],
-    output_folder: Union[str, Path],
+    input_file: str | Path,
+    output_folder: str | Path,
     overwrite: bool = False,
 ) -> None:
     """Unpack zip file."""
@@ -61,8 +61,8 @@ def _decompress_zip_file(
 
 
 def _decompress_tar_file(
-    input_file: Union[str, Path],
-    output_folder: Union[str, Path],
+    input_file: str | Path,
+    output_folder: str | Path,
     overwrite: bool = False,
 ) -> None:
     """Unpack tar file."""
@@ -72,7 +72,7 @@ def _decompress_tar_file(
         # Path to new file to be created.
         new_file = Path(output_folder) / Path(tar_file.getnames()[0])
         if new_file.exists() and not overwrite:
-            raise FileExistsError("Output already exists. Either change output_folder or use" " overwrite=True.")
+            raise FileExistsError("Output already exists. Either change output_folder or use overwrite=True.")
 
         # Unzip the file and save it in the local output folder.
         # Note that, if output_folder path does not exist, the following command will create it.