🐝 Upgrade pyright to match VSCode errors (#3148)

* 🐝 update pyright to version 1.1.373

apps/backport/datasync/datasync.py

@@ -38,7 +38,7 @@ def upload_gzip_string(s: str, s3_path: str, private: bool = False) -> None:
         retry=retry_if_exception_type((EndpointConnectionError, SSLError)),
     ):
         with attempt:
-            client.put_object(
+            client.put_object(  # type: ignore[reportAttributeAccessIssue]
                 Bucket=bucket,
                 Body=body_gzip,
                 Key=key,

apps/metadata_migrate/cli.py

@@ -324,22 +324,22 @@ def _create_origin_from_source(ds: Dataset, source: Source, license: Optional[Li
         description += source.description
 
     origin = Origin(
-        title=ds.metadata.title,
-        producer=source.name,
+        title=ds.metadata.title,  # type: ignore[reportArgumentType]
+        producer=source.name,  # type: ignore[reportArgumentType]
         citation_full=source.published_by,
         license=license,
         description=description,
         url_main=source.url,
         url_download=source.source_data_url,
         date_accessed=source.date_accessed,
-        date_published=source.publication_date or source.publication_year,
+        date_published=source.publication_date or source.publication_year,  # type: ignore[reportArgumentType]
     )
 
     if not origin.date_published:
         log.warning(
             f"missing publication_date and publication_year in source, using date_accessed: {origin.date_accessed}"
         )
-        origin.date_published = origin.date_accessed
+        origin.date_published = origin.date_accessed  # type: ignore
     return origin
 
 

apps/metagpt/cli.py

@@ -87,7 +87,7 @@ def main(path_to_file: str, output_dir: str, overwrite: bool, model: str) -> Non
 class MetadataGPTUpdater:
     """Update metadata file using Chat GPT."""
 
-    def __init__(self: Self, path_to_file: str, model: str) -> None:
+    def __init__(self: Self, path_to_file: str, model: str) -> None:  # type: ignore[reportInvalidTypeVarUse]
         """Initialize the metadata updater."""
         # Name of the model
         self.model: str = model

apps/utils/gpt.py

@@ -72,7 +72,7 @@ class GPTResponse(ChatCompletion):
 
     message_content_dix: Optional[Dict[str, Any]] = field(default_factory=dict)
 
-    def __init__(self: Self, chat_completion_instance: ChatCompletion | None = None, **kwargs) -> None:
+    def __init__(self: Self, chat_completion_instance: ChatCompletion | None = None, **kwargs) -> None:  # type: ignore[reportInvalidTypeVarUse]
         """Initialize OpenAI API wrapper."""
         if chat_completion_instance:
             super().__init__(**chat_completion_instance.dict())
@@ -102,7 +102,7 @@ def message_content_as_dict(self: Self) -> Dict[str, Any]:
                 self.message_content_dix = yaml.safe_load(self.message_content)
             else:
                 raise ValueError("`message_content` is empty!")
-        return self.message_content_dix
+        return self.message_content_dix  # type: ignore[reportReturnType]
 
     @property
     def cost(self) -> float | None:
@@ -167,7 +167,7 @@ def to_dict(self: Self) -> Dict[str, Any]:
 class OpenAIWrapper(OpenAI):
     """Wrapper for OpenAI API."""
 
-    def __init__(self: Self, **kwargs) -> None:
+    def __init__(self: Self, **kwargs) -> None:  # type: ignore[reportInvalidTypeVarUse]
         """Initialize OpenAI API wrapper."""
         super().__init__(**kwargs)
 

apps/utils/profile.py

@@ -86,7 +86,7 @@ def cli(step: str, cpu: bool, mem: bool, functions: tuple[str]) -> None:
 
     # Profile the run function
     if mem:
-        memory_usage((mem_profile(lp_wrapper), [dest_dir]))
+        memory_usage((mem_profile(lp_wrapper), [dest_dir]))  # type: ignore[reportArgumentType]
     else:
         lp_wrapper(dest_dir)
 

apps/wizard/app_pages/fasttrack/load.py

@@ -208,7 +208,7 @@ def parse_metadata_from_csv(
         date_published=str(dt.date.today()),  # type: ignore
     )
 
-    return DatasetMeta(**dataset_dict), {k: VariableMeta(**v) for k, v in variables_dict.items()}, origin
+    return DatasetMeta(**dataset_dict), {k: VariableMeta(**v) for k, v in variables_dict.items()}, origin  # type: ignore
 
 
 ###################################
@@ -301,7 +301,7 @@ def _parse_sources(sources_meta_df: pd.DataFrame) -> Optional[Source]:
     # short_name is not used anymore
     source.pop("short_name", None)
 
-    return Source(**source)
+    return Source(**source)  # type: ignore[reportCallIssue]
 
 
 def _parse_origins(origins_meta_df: pd.DataFrame) -> Optional[Origin]:

apps/wizard/app_pages/owidle.py

@@ -298,7 +298,7 @@ def load_data(placeholder: str) -> Tuple[pd.DataFrame, gpd.GeoDataFrame]:
     ].drop_duplicates()
     # df_geo = df_geo.to_crs(3310)
 
-    return tb_indicator, df_geo
+    return tb_indicator, df_geo  # type: ignore[reportReturnType]
 
 
 @st.cache_data
@@ -827,16 +827,16 @@ def plot_chart_gdp_pc(countries_guessed: List[str], years_guessed: List[str], so
             countries_guessed,
             years_guessed=years_guessed,
             solution=solution,
-            column_indicator=GDP_INDICATOR,
-            title=gdp_indicator_titles[GDP_INDICATOR],
+            column_indicator=GDP_INDICATOR,  # type: ignore[reportArgumentType]
+            title=gdp_indicator_titles[GDP_INDICATOR],  # type: ignore[reportArgumentType]
             column_country="location",
         )
     else:
         _plot_chart(
             countries_guessed,
             solution=solution,
-            column_indicator=GDP_INDICATOR,
-            title=gdp_indicator_titles[GDP_INDICATOR],
+            column_indicator=GDP_INDICATOR,  # type: ignore[reportArgumentType]
+            title=gdp_indicator_titles[GDP_INDICATOR],  # type: ignore[reportArgumentType]
             column_country="location",
         )
 

apps/wizard/cli.py

@@ -30,7 +30,7 @@
 @click.command(cls=RichCommand, context_settings=dict(show_default=True))
 @click.argument(
     "phase",
-    type=click.Choice(WIZARD_PHASES.__args__),  # type: ignore
+    type=click.Choice(WIZARD_PHASES),
     default="all",
 )
 @click.option(
@@ -52,7 +52,7 @@
     help="Application port.",
 )
 def cli(
-    phase: Iterable[WIZARD_PHASES],
+    phase: Iterable[str],
     run_checks: bool,
     dummy_data: bool,
     port: int,

apps/wizard/config/__init__.py

@@ -2,7 +2,6 @@
 
 It basically reads the configuration from .wizard.yml and renders the home page and other details.
 """
-from typing import Literal
 
 import yaml
 
@@ -106,7 +105,7 @@ def _check_wizard_config(config: dict):
         _aliases.append(app["alias"])
 ## Add aliases from etl steps and 'all'
 _aliases = tuple(_aliases + list(WIZARD_CONFIG["etl"]["steps"].keys()) + ["all"])
-WIZARD_PHASES = Literal[_aliases]  # type: ignore
+WIZARD_PHASES = _aliases
 
 # Get all pages by alias
 _pages = [ww for w in WIZARD_CONFIG["sections"] for ww in w["apps"]]

apps/wizard/etl_steps/express.py

@@ -90,7 +90,7 @@ class ExpressForm(utils.StepForm):
     namespace_custom: str | None = None
     update_period_date: date
 
-    def __init__(self: Self, **data: str | date | bool | int) -> None:
+    def __init__(self: Self, **data: str | date | bool | int) -> None:  # type: ignore[reportInvalidTypeVarUse]
         """Construct class."""
         data["add_to_dag"] = data["dag_file"] != utils.ADD_DAG_OPTIONS[0]
 

apps/wizard/etl_steps/garden.py

@@ -83,7 +83,7 @@ class GardenForm(utils.StepForm):
     update_period_days: int
     topic_tags: List[str]
 
-    def __init__(self: Self, **data: str | bool) -> None:
+    def __init__(self: Self, **data: str | bool) -> None:  # type: ignore[reportInvalidTypeVarUse]
         """Construct class."""
         data["add_to_dag"] = data["dag_file"] != utils.ADD_DAG_OPTIONS[0]
 

apps/wizard/etl_steps/grapher.py

@@ -59,7 +59,7 @@ class GrapherForm(utils.StepForm):
     dag_file: str
     is_private: bool
 
-    def __init__(self: Self, **data: str | bool) -> None:
+    def __init__(self: Self, **data: str | bool) -> None:  # type: ignore[reportInvalidTypeVarUse]
         """Construct class."""
         data["add_to_dag"] = data["dag_file"] != utils.ADD_DAG_OPTIONS[0]
 

apps/wizard/etl_steps/meadow.py

@@ -65,7 +65,7 @@ class MeadowForm(utils.StepForm):
     generate_notebook: bool
     is_private: bool
 
-    def __init__(self: Self, **data: str | bool) -> None:
+    def __init__(self: Self, **data: str | bool) -> None:  # type: ignore[reportInvalidTypeVarUse]
         """Construct class."""
         data["add_to_dag"] = data["dag_file"] != utils.ADD_DAG_OPTIONS[0]
 

apps/wizard/etl_steps/snapshot.py

@@ -101,7 +101,7 @@ class SnapshotForm(utils.StepForm):
     license_url: str
     license_name: str
 
-    def __init__(self: Self, **data: str | int) -> None:
+    def __init__(self: Self, **data: str | int) -> None:  # type: ignore[reportInvalidTypeVarUse]
         """Construct form."""
         # Change name for certain fields (and remove old ones)
         data["license_url"] = data["origin.license.url"]
@@ -177,7 +177,7 @@ def validate(self: "SnapshotForm") -> None:
             self.errors["origin.attribution_custom"] = "Please introduce the name of the custom attribute!"
 
     @property
-    def metadata(self: Self) -> Dict[str, Any]:
+    def metadata(self: Self) -> Dict[str, Any]:  # type: ignore[reportIncompatibleMethodOverride]
         """Define metadata for easy YAML-export."""
         license_field = {
             "name": self.license_name,

apps/wizard/home.py

@@ -77,7 +77,7 @@ def create_card(
             # text=f"Press {i + 1}",
             # text=["This is a test card", "This is a subtext"],
             styles=styles,
-            on_click=lambda: None,
+            on_click=lambda: None,  # type: ignore[reportArgumentType]
         )
         if go_to_page:
             st.switch_page(entrypoint)

apps/wizard/utils/__init__.py

@@ -161,7 +161,7 @@ def remove_from_dag(step: str, dag_path: Path = DAG_WIZARD_PATH) -> None:
 class classproperty(property):
     """Decorator."""
 
-    def __get__(self, owner_self: Self, owner_cls: Self):
+    def __get__(self, owner_self: Self, owner_cls: Self):  # type: ignore[reportIncompatibleMethodOverride]
         return self.fget(owner_cls)  # type: ignore
 
 

apps/wizard/utils/step_form.py

@@ -18,7 +18,7 @@ class StepForm(BaseModel):
     errors: Dict[str, Any] = {}
     step_name: str
 
-    def __init__(self: Self, **kwargs: str | int) -> None:
+    def __init__(self: Self, **kwargs: str | int) -> None:  # type: ignore[reportInvalidTypeVarUse]
         """Construct parent class."""
         super().__init__(**kwargs)
         self.validate()
@@ -36,7 +36,7 @@ def from_state(cls: Type[Self]) -> Self:
         # st.write(data)
         return cls(**data)
 
-    def validate(self: Self) -> None:
+    def validate(self: Self) -> None:  # type: ignore[reportIncompatibleMethodOverride]
         """Validate form fields."""
         raise NotImplementedError("Needs to be implemented in the child class!")
 

etl/compare.py

@@ -10,6 +10,7 @@
 import rich
 from dotenv import dotenv_values
 from owid import catalog
+from owid.catalog import CHANNEL
 from owid.repack import repack_frame
 from rich import print
 from rich_click.rich_command import RichCommand
@@ -116,7 +117,7 @@ def diff_print(
 @click.pass_context
 def etl_catalog(
     ctx: click.core.Context,
-    channel: str,
+    channel: CHANNEL,
     namespace: str,
     dataset: str,
     table: str,
@@ -140,7 +141,11 @@ def etl_catalog(
     """
     try:
         remote_df = catalog.find_latest(
-            table=table, namespace=namespace, dataset=dataset, channels=[channel], version=version
+            table=table,
+            namespace=namespace,
+            dataset=dataset,
+            channels=[channel],
+            version=version,  # type: ignore[reportArgumentType]
         )
     except Exception as e:
         if debug:
@@ -157,7 +162,7 @@ def etl_catalog(
                 namespace=namespace,
                 dataset=dataset,
                 channel=cast(catalog.CHANNEL, channel),
-                version=version,
+                version=version,  # type: ignore[reportArgumentType]
             )
         except ValueError as e:
             # try again after reindexing
@@ -168,7 +173,7 @@ def etl_catalog(
                     namespace=namespace,
                     dataset=dataset,
                     channel=cast(catalog.CHANNEL, channel),
-                    version=version,
+                    version=version,  # type: ignore[reportArgumentType]
                 )
             else:
                 raise e

etl/data_helpers/geo.py

@@ -5,7 +5,7 @@
 import warnings
 from datetime import datetime
 from pathlib import Path
-from typing import Any, Dict, List, Literal, Optional, Set, TypeVar, Union, cast
+from typing import Any, Dict, Hashable, List, Literal, Optional, Set, TypeVar, Union, cast
 
 import numpy as np
 import owid.catalog.processing as pr
@@ -848,7 +848,8 @@ def add_gdp_to_table(
 def create_table_of_regions_and_subregions(ds_regions: Dataset, subregion_type: str = "members") -> Table:
     # Subregion type can be "members" or "successors" (or in principle also "related").
     # Get the main table from the regions dataset.
-    tb_regions = ds_regions["regions"][["name", subregion_type]]
+    tb_regions = ds_regions["regions"]
+    tb_regions = tb_regions.loc[:, ["name", subregion_type]]
 
     # Get a mapping from code to region name.
     mapping = tb_regions["name"].to_dict()
@@ -1002,7 +1003,7 @@ def list_members_of_region(
 def detect_overlapping_regions(
     df: TableOrDataFrame,
     index_columns: List[str],
-    regions_and_members: Dict[str, List[str]],
+    regions_and_members: Dict[Hashable, List[str]],
     country_col: str = "country",
     year_col: str = "year",
     ignore_overlaps_of_zeros: bool = True,

etl/data_helpers/misc.py

@@ -165,7 +165,7 @@ def add_origins_to_mortality_database(tb_who: Table) -> Table:
                 producer="World Health Organisation",
                 url_main="https://platform.who.int/mortality/themes/theme-details/MDB/all-causes",
                 date_accessed="2023-08-01",
-                date_published="2023-08-01",
+                date_published="2023-08-01",  # type: ignore
                 citation_full="Mortality Database, World Health Organization. Licence: CC BY-NC-SA 3.0 IGO.",
                 description="The WHO mortality database is a collection death registration data including cause-of-death information from member states. Where they are collected, death registration data are the best source of information on key health indicators, such as life expectancy, and death registration data with cause-of-death information are the best source of information on mortality by cause, such as maternal mortality and suicide mortality. WHO requests from all countries annual data by age, sex, and complete ICD code (e.g., 4-digit code if the 10th revision of ICD was used). Countries have reported deaths by cause of death, year, sex, and age for inclusion in the WHO Mortality Database since 1950. Data are included only for countries reporting data properly coded according to the International Classification of Diseases (ICD). Today the database is maintained by the WHO Division of Data, Analytics and Delivery for Impact (DDI) and contains data from over 120 countries and areas. Data reported by member states and selected areas are displayed in this portal’s interactive visualizations if the data are reported to the WHO mortality database in the requested format and at least 65% of deaths were recorded in each country and year.",
                 license=License(name="CC BY 4.0"),
@@ -197,7 +197,7 @@ def add_origins_to_global_burden_of_disease(tb_gbd: Table) -> Table:
                 producer="Institute of Health Metrics and Evaluation",
                 url_main="https://vizhub.healthdata.org/gbd-results/",
                 date_accessed="2021-12-01",
-                date_published="2020-10-17",
+                date_published="2020-10-17",  # type: ignore
                 citation_full="Global Burden of Disease Collaborative Network. Global Burden of Disease Study 2019 (GBD 2019). Seattle, United States: Institute for Health Metrics and Evaluation (IHME), 2020.",
                 description="The Global Burden of Disease (GBD) provides a comprehensive picture of mortality and disability across countries, time, age, and sex. It quantifies health loss from hundreds of diseases, injuries, and risk factors, so that health systems can be improved and disparities eliminated. GBD research incorporates both the prevalence of a given disease or risk factor and the relative harm it causes. With these tools, decision-makers can compare different health issues and their effects.",
                 license=License(

etl/datadiff.py

@@ -225,7 +225,7 @@ def _diff_tables(self, ds_a: Dataset, ds_b: Dataset, table_name: str):
                         changed.append("changed [u]metadata[/u]")
                     if new_index.any():
                         changed.append("new [u]data[/u]")
-                    if (~eq_data[~new_index]).any():
+                    if (~eq_data[~new_index]).any():  # type: ignore[reportCallIssue]
                         changed.append("changed [u]data[/u]")
 
                     if changed:

etl/git_helpers.py

@@ -49,9 +49,9 @@ def ensure_cloned(self, shallow: bool = True) -> None:
         if not dest_dir.is_dir():
             dest_dir.parent.mkdir(parents=True, exist_ok=True)
             if shallow:
-                sh.git("clone", "--depth=1", self.github_url, dest_dir.as_posix(), _fg=True)
+                sh.git("clone", "--depth=1", self.github_url, dest_dir.as_posix(), _fg=True)  # type: ignore[reportCallIssue]
             else:
-                sh.git("clone", self.github_url, dest_dir.as_posix(), _fg=True)
+                sh.git("clone", self.github_url, dest_dir.as_posix(), _fg=True)  # type: ignore[reportCallIssue]
         else:
             self.update_and_reset()
 
@@ -86,7 +86,7 @@ def _git(self, *args: str, **kwargs: Any) -> str:
         "Execute a git command in the context of this repo."
         return cast(
             str,
-            sh.git("--no-pager", *args, _cwd=self.cache_dir.as_posix(), **kwargs).stdout.decode("utf8").strip(),
+            sh.git("--no-pager", *args, _cwd=self.cache_dir.as_posix(), **kwargs).stdout.decode("utf8").strip(),  # type: ignore[reportCallIssue]
         )
 
     def is_up_to_date(self) -> bool:

etl/grapher_helpers.py

@@ -392,11 +392,11 @@ def country_to_entity_id(
         assert by == "name", "create_entities works only with `by='name'`"
         ix = entity_id.isnull()
         # cast to float to fix issues with categories
-        entity_id[ix] = (
-            country[ix].map(_get_and_create_entities_in_db(set(country[ix].unique()), engine=engine)).astype(float)
+        entity_id[ix] = (  # type: ignore[reportCallIssue]
+            country[ix].map(_get_and_create_entities_in_db(set(country[ix].unique()), engine=engine)).astype(float)  # type: ignore[reportCallIssue]
         )
 
-    assert not entity_id.isnull().any(), f"Some countries have not been mapped: {set(country[entity_id.isnull()])}"
+    assert not entity_id.isnull().any(), f"Some countries have not been mapped: {set(country[entity_id.isnull()])}"  # type: ignore[reportCallIssue]
 
     return cast(pd.Series, entity_id.astype(int))