Fix linters

.pre-commit-config.yaml

@@ -0,0 +1,14 @@
+repos:
+- repo: https://github.com/astral-sh/ruff-pre-commit
+  # Ruff version.
+  rev: v0.2.1
+  hooks:
+    # Run the linter.
+    - id: ruff
+      args: [ --fix ]
+    # Run the formatter.
+    - id: ruff-format
+- repo: https://github.com/pre-commit/mirrors-mypy
+  rev: v1.8.0
+  hooks:
+  - id: mypy

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "chronify"
-version = "0.0.0"
+version = "0.0.1"
 description = "Time series store and mapping libray"
 readme = "README.md"
 requires-python = ">=3.10, <3.13"

src/chronify/__init__.py

@@ -1 +0,0 @@
-from time_series_store.models import TableSchema

src/chronify/models.py

@@ -3,7 +3,7 @@
 from pydantic import BaseModel, ConfigDict, Field, field_validator
 from typing_extensions import Annotated
 
-from chronify.time_configs import AnnualTimeRange, TimeBaseModel, TimeConfig
+from chronify.time_configs import TimeConfig
 
 
 def make_model_config(**kwargs) -> ConfigDict:
@@ -16,7 +16,7 @@ def make_model_config(**kwargs) -> ConfigDict:
         use_enum_values=False,
         arbitrary_types_allowed=True,
         populate_by_name=True,
-        **kwargs,
+        **kwargs,  # type: ignore
     )
 
 
@@ -79,7 +79,6 @@ def check_columns(cls, columns: list[str]) -> list[str]:
 # TODO: print example tables here.
 
 
-
 def _check_name(name: str) -> None:
     if not REGEX_NAME_REQUIREMENT.search(name):
         msg = f"A name can only have alphanumeric characters: {name=}"

src/chronify/store.py

@@ -26,8 +26,8 @@ def __init__(self, engine: Optional[Engine] = None, **connect_args) -> None:
         else:
             self._engine = engine
 
-    #def add_time_series(self, data: np.ndarray) -> None:
-        #"""Add a time series array to the store."""
+    # def add_time_series(self, data: np.ndarray) -> None:
+    # """Add a time series array to the store."""
 
     def create_view_from_parquet(self, name: str, path: Path) -> None:
         """Create a view in the database from a Parquet file."""
@@ -67,9 +67,7 @@ def update_table_schema(self) -> None:
     def _check_table_schema(self, schema: TableSchema) -> None:
         table = Table(schema.name, g_metadata)
         expected_columns = set(
-            schema.time_array_id_columns
-            + schema.time_config.time_columns
-            + schema.value_columns
+            schema.time_array_id_columns + schema.time_config.time_columns + schema.value_columns
         )
         existing_columns = {x.name for x in table.columns}
         diff = expected_columns - existing_columns

src/chronify/time.py

@@ -29,7 +29,9 @@ class RepresentativePeriodFormat(StrEnum):
     # number of permutations (seasons, weekend day vs week day, sub-hour time, etc).
 
     ONE_WEEK_PER_MONTH_BY_HOUR = "one_week_per_month_by_hour"
-    ONE_WEEKDAY_DAY_AND_ONE_WEEKEND_DAY_PER_MONTH_BY_HOUR = "one_weekday_day_and_one_weekend_day_per_month_by_hour",
+    ONE_WEEKDAY_DAY_AND_ONE_WEEKEND_DAY_PER_MONTH_BY_HOUR = (
+        "one_weekday_day_and_one_weekend_day_per_month_by_hour",
+    )
 
 
 class LeapDayAdjustmentType(StrEnum):
@@ -63,14 +65,14 @@ class TimeIntervalType(StrEnum):
     # https://github.com/Smart-DS/R2PD/blob/master/R2PD/tshelpers.py#L15
 
     PERIOD_ENDING = "period_ending"
-        #description="A time interval that is period ending is coded by the end time. E.g., 2pm (with"
-        #" freq=1h) represents a period of time between 1-2pm.",
+    # description="A time interval that is period ending is coded by the end time. E.g., 2pm (with"
+    # " freq=1h) represents a period of time between 1-2pm.",
     PERIOD_BEGINNING = "period_beginning"
-        #description="A time interval that is period beginning is coded by the beginning time. E.g.,"
-        #" 2pm (with freq=01:00:00) represents a period of time between 2-3pm. This is the dsgrid"
-        #" default.",
+    # description="A time interval that is period beginning is coded by the beginning time. E.g.,"
+    # " 2pm (with freq=01:00:00) represents a period of time between 2-3pm. This is the dsgrid"
+    # " default.",
     INSTANTANEOUS = "instantaneous"
-        #description="The time record value represents measured, instantaneous time",
+    # description="The time record value represents measured, instantaneous time",
 
 
 class MeasurementType(StrEnum):
@@ -80,9 +82,9 @@ class MeasurementType(StrEnum):
     MIN = "min"
     MAX = "max"
     MEASURED = "measured"
-        #description="Data values represent the measured value at that reported time",
+    # description="Data values represent the measured value at that reported time",
     TOTAL = "total"
-        #description="Data values represent the sum of values in a time range",
+    # description="Data values represent the sum of values in a time range",
 
 
 class TimeZone(StrEnum):
@@ -162,7 +164,9 @@ def get_standard_time(tz: TimeZone) -> TimeZone:
         case TimeZone.ARIZONA:
             return TimeZone.ARIZONA
         case _:
-            raise NotImplementedError(f"BUG: case not covered: {tz}")
+            msg = f"BUG: case not covered: {tz}"
+            raise NotImplementedError(msg)
+
 
 def get_prevailing_time(tz: TimeZone) -> TimeZone:
     """get equivalent prevailing time"""
@@ -184,7 +188,9 @@ def get_prevailing_time(tz: TimeZone) -> TimeZone:
         case TimeZone.ARIZONA:
             return TimeZone.ARIZONA
         case _:
-            raise NotImplementedError(f"BUG: case not covered: {tz}")
+            msg = f"BUG: case not covered: {tz}"
+            raise NotImplementedError(msg)
+
 
 _STANDARD_TIME_ZONES = {
     TimeZone.UTC,
@@ -205,6 +211,7 @@ def get_prevailing_time(tz: TimeZone) -> TimeZone:
     TimeZone.ARIZONA,
 }
 
+
 def is_standard(tz: TimeZone) -> bool:
     return tz in _STANDARD_TIME_ZONES
 

src/chronify/time_configs.py

@@ -57,9 +57,7 @@ class LocalTimeAsStrings(BaseModel):
     They are aligned for each geography when adjusted for time zone but staggered
     in an absolute time scale."""
 
-    format_type: Literal[DatetimeFormat.LOCAL_AS_STRINGS] = (
-        DatetimeFormat.LOCAL_AS_STRINGS
-    )
+    format_type: Literal[DatetimeFormat.LOCAL_AS_STRINGS] = DatetimeFormat.LOCAL_AS_STRINGS
 
     data_str_format: Annotated[
         str,
@@ -70,23 +68,21 @@ class LocalTimeAsStrings(BaseModel):
         ),
     ]
 
-    @field_validator("data_str_format")
-    @classmethod
-    def check_data_str_format(cls, data_str_format):
-        raise NotImplementedError(
-            "DatetimeFormat.LOCAL_AS_STRINGS is not fully implemented."
-        )
-        dsf = data_str_format
-        if (
-            "x" not in dsf
-            and "X" not in dsf
-            and "Z" not in dsf
-            and "z" not in dsf
-            and "V" not in dsf
-            and "O" not in dsf
-        ):
-            raise ValueError("data_str_format must provide time zone or zone offset.")
-        return data_str_format
+    # @field_validator("data_str_format")
+    # @classmethod
+    # def check_data_str_format(cls, data_str_format):
+    #    raise NotImplementedError("DatetimeFormat.LOCAL_AS_STRINGS is not fully implemented.")
+    #    dsf = data_str_format
+    #    if (
+    #        "x" not in dsf
+    #        and "X" not in dsf
+    #        and "Z" not in dsf
+    #        and "z" not in dsf
+    #        and "V" not in dsf
+    #        and "O" not in dsf
+    #    ):
+    #        raise ValueError("data_str_format must provide time zone or zone offset.")
+    #    return data_str_format
 
 
 class DaylightSavingAdjustment(BaseModel):
@@ -199,9 +195,7 @@ def iter_timestamps(self) -> Generator[datetime, None, None]:
         tz_info = self.start.tzinfo
         for i in range(self.length):
             cur = self.start.astimezone(ZoneInfo("UTC")) + i * self.frequency
-            cur = adjust_timestamp_by_dst_offset(
-                cur.astimezone(tz_info), self.frequency
-            )
+            cur = adjust_timestamp_by_dst_offset(cur.astimezone(tz_info), self.frequency)
             month = cur.month
             day = cur.day
             if not (
@@ -238,7 +232,6 @@ def iter_timestamps(self) -> Generator[int, None, None]:
 
 
 class IndexTimeRange(TimeBaseModel):
-
     time_type: Literal[TimeType.INDEX] = TimeType.INDEX
     start: int
     frequency: timedelta
@@ -248,39 +241,39 @@ class IndexTimeRange(TimeBaseModel):
     measurement_type: MeasurementType
 
     # TODO DT: totally wrong
-    def iter_timestamps(self) -> Generator[datetime, None, None]:
-        cur = self.start.to_pydatetime().astimezone(ZoneInfo("UTC"))
-        cur_idx = self.start_index
-        end = (
-            self.end.to_pydatetime().astimezone(ZoneInfo("UTC")) + self.frequency
-        )  # to make end time inclusive
-
-        while cur < end:
-            cur_tz = cur.astimezone(self.tzinfo)
-            cur_tz = adjust_timestamp_by_dst_offset(cur_tz, self.frequency)
-            month = cur_tz.month
-            day = cur_tz.day
-            if not (
-                self.time_based_data_adjustment.leap_day_adjustment
-                == LeapDayAdjustmentType.DROP_FEB29
-                and month == 2
-                and day == 29
-            ):
-                if not (
-                    self.time_based_data_adjustment.leap_day_adjustment
-                    == LeapDayAdjustmentType.DROP_DEC31
-                    and month == 12
-                    and day == 31
-                ):
-                    if not (
-                        self.time_based_data_adjustment.leap_day_adjustment
-                        == LeapDayAdjustmentType.DROP_JAN1
-                        and month == 1
-                        and day == 1
-                    ):
-                        yield cur_idx
-            cur += self.frequency
-            cur_idx += 1
+    # def iter_timestamps(self) -> Generator[datetime, None, None]:
+    #    cur = self.start.to_pydatetime().astimezone(ZoneInfo("UTC"))
+    #    cur_idx = self.start_index
+    #    end = (
+    #        self.end.to_pydatetime().astimezone(ZoneInfo("UTC")) + self.frequency
+    #    )  # to make end time inclusive
+
+    #    while cur < end:
+    #        cur_tz = cur.astimezone(self.tzinfo)
+    #        cur_tz = adjust_timestamp_by_dst_offset(cur_tz, self.frequency)
+    #        month = cur_tz.month
+    #        day = cur_tz.day
+    #        if not (
+    #            self.time_based_data_adjustment.leap_day_adjustment
+    #            == LeapDayAdjustmentType.DROP_FEB29
+    #            and month == 2
+    #            and day == 29
+    #        ):
+    #            if not (
+    #                self.time_based_data_adjustment.leap_day_adjustment
+    #                == LeapDayAdjustmentType.DROP_DEC31
+    #                and month == 12
+    #                and day == 31
+    #            ):
+    #                if not (
+    #                    self.time_based_data_adjustment.leap_day_adjustment
+    #                    == LeapDayAdjustmentType.DROP_JAN1
+    #                    and month == 1
+    #                    and day == 1
+    #                ):
+    #                    yield cur_idx
+    #        cur += self.frequency
+    #        cur_idx += 1
 
 
 class RepresentativePeriodTimeRange(TimeBaseModel):
@@ -293,19 +286,15 @@ class RepresentativePeriodTimeRange(TimeBaseModel):
 
 
 TimeConfig = Annotated[
-    Union[
-        AnnualTimeRange, DatetimeRange, IndexTimeRange, RepresentativePeriodTimeRange
-    ],
+    Union[AnnualTimeRange, DatetimeRange, IndexTimeRange, RepresentativePeriodTimeRange],
     Field(
         description="Defines the times in a time series table.",
         discriminator="time_type",
     ),
 ]
 
 
-def adjust_timestamp_by_dst_offset(
-    timestamp: datetime, frequency: timedelta
-) -> datetime:
+def adjust_timestamp_by_dst_offset(timestamp: datetime, frequency: timedelta) -> datetime:
     """Reduce the timestamps within the daylight saving range by 1 hour.
     Used to ensure that a time series at daily (or lower) frequency returns each day at the
     same timestamp in prevailing time, an expected behavior in most standard libraries.

src/chronify/time_series_checker.py

@@ -1,7 +1,7 @@
 from sqlalchemy import Connection, Engine, text
 
-from chronify import TableSchema
 from chronify.exceptions import InvalidTable
+from chronify.models import TableSchema
 
 
 class TimeSeriesChecker:
@@ -62,5 +62,7 @@ def _run_timestamp_checks_on_tmp_table(schema: TableSchema, conn: Connection, ta
         result3 = conn.execute(text(query3)).all()
         actual_count = result3[0][0]
         if actual_count != schema.time_config.length:
-            msg = "Time arrays must have length={schema.time_config.length}. Actual = {actual_count}"
+            msg = (
+                "Time arrays must have length={schema.time_config.length}. Actual = {actual_count}"
+            )
             raise InvalidTable(msg)

src/chronify/time_series_mapper.py

@@ -1,3 +1,6 @@
+from chronify.time_configs import TimeConfig
+
+
 class TimeSeriesMapper:
     """Maps time series data from one configuration to another."""
 
@@ -9,4 +12,3 @@ def map_time_series(
         to_table: str,
     ) -> None:
         pass
-