Swap linter to ruff (#33)

openclimatefix · Jan 27, 2023 · 9a25276 · 9a25276
1 parent 0b0a90b
commit 9a25276
Show file tree

Hide file tree

Showing 19 changed files with 137 additions and 193 deletions.
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -15,41 +15,13 @@ repos:
       - id: debug-statements
       - id: detect-private-key
   # python code formatting/linting
-  - repo: https://github.com/PyCQA/pydocstyle
-    rev: 6.1.1
+  - repo: https://github.com/charliermarsh/ruff-pre-commit
+    # Ruff version.
+    rev: "v0.0.236"
     hooks:
-      - id: pydocstyle
-        args: [--convention=google, "--add-ignore=D200,D202,D210,D212,D415"]
+      - id: ruff
         files: sdk/python/pvsite_datamodel
-        exclude: __version__.py
-  - repo: https://github.com/PyCQA/flake8
-    rev: 6.0.0
-    hooks:
-      - id: flake8
-        args:
-          [
-            "--max-line-length",
-            "100",
-            "--extend-ignore=E203",
-            "--per-file-ignores",
-            "__init__.py:F401",
-            "sdk/python/pvsite_datamodel",
-
-          ]
-  - repo: https://github.com/PyCQA/isort
-    rev: 5.11.4
-    hooks:
-      - id: isort
-        args: ["--profile", "black", "--line-length", "100"]
-        files: sdk/python/pvsite_datamodel
-        exclude: __version__.py
-  - repo: https://github.com/psf/black
-    rev: 22.12.0
-    hooks:
-      - id: black
-        args: ["--line-length", "100"]
-        files: sdk/python/pvsite_datamodel
-        exclude: __version__.py
+        args: [--fix, -v]
   # yaml formatting
   - repo: https://github.com/pre-commit/mirrors-prettier
     rev: v3.0.0-alpha.4

diff --git a/gen/pvsite.py b/gen/pvsite.py
@@ -28,7 +28,7 @@ class Sites(Base):
     ml_id = sa.Column(sa.Integer(), autoincrement=True)
 
     __table_args__ = (
-                
+
     UniqueConstraint("client_site_id",client_uuid, name='idx_client')
             )
 

diff --git a/gen/pvsite.sql b/gen/pvsite.sql
@@ -83,7 +83,7 @@ COMMENT ON TABLE "sites" IS 'Each site row specifies a single panel or cluster o
 found on a residential house or commercial building. Their
 data is provided by a client.
 
-*Approximate size: *  
+*Approximate size: *
 4 clients * ~1000 sites each = ~4000 rows';
 
 COMMENT ON COLUMN "sites"."client_uuid" IS 'The internal ID of the client providing the site data';
@@ -109,7 +109,7 @@ COMMENT ON COLUMN "sites"."ml_id" IS 'Auto-incrementing integer ID of the site f
 COMMENT ON TABLE "generation" IS 'Each yield row specifies a generated power output over a
 given time range for a site.
 
-*Approximate size: *  
+*Approximate size: *
 Generation populated every 5 minutes per site * 4000 sites = ~1,125,000 rows per day';
 
 COMMENT ON COLUMN "generation"."site_uuid" IS 'The site for which this geenration yield belongs to';
@@ -119,9 +119,9 @@ COMMENT ON COLUMN "generation"."power_kw" IS 'The actual generated power in kW a
 COMMENT ON COLUMN "generation"."datetime_interval_uuid" IS 'The time interval over which this generated power value applies';
 
 COMMENT ON TABLE "forecasts" IS 'Each forecast row refers to a sequence of predicted solar generation values
-over a set of target times for a site. 
+over a set of target times for a site.
 
-*Approximate size: *  
+*Approximate size: *
 One forecast per site every 5 minutes = ~1,125,000 rows per day';
 
 COMMENT ON COLUMN "forecasts"."site_uuid" IS 'The site for which the forecast sequence was generated';
@@ -130,11 +130,11 @@ COMMENT ON COLUMN "forecasts"."created_utc" IS 'The creation time of the forecas
 
 COMMENT ON COLUMN "forecasts"."forecast_version" IS 'The semantic version of the model used to generate the forecast';
 
-COMMENT ON TABLE "forecast_values" IS 'Each forecast_value row is a prediction for the power output 
+COMMENT ON TABLE "forecast_values" IS 'Each forecast_value row is a prediction for the power output
 of a site over a target datetime interval. Many predictions
 are made for each site at each target interval.
 
-*Approximate size: *  
+*Approximate size: *
 One forecast value every 5 minutes per site per forecast.
 Each forecast"s prediction sequence covers 24 hours of target
 intervals = ~324,000,000 rows per day';
@@ -145,12 +145,12 @@ COMMENT ON COLUMN "forecast_values"."forecast_generation_kw" IS 'The predicted p
 
 COMMENT ON COLUMN "forecast_values"."forecast_uuid" IS 'The forecast sequence this forcast value belongs to';
 
-COMMENT ON TABLE "latest_forecast_values" IS 'Each forecast_value row is a prediction for the power output 
-of a site over a target datetime interval. Only the most recent 
+COMMENT ON TABLE "latest_forecast_values" IS 'Each forecast_value row is a prediction for the power output
+of a site over a target datetime interval. Only the most recent
 prediction for each target time interval is stored in this table
 per site.
 
-*Approximate size: *  
+*Approximate size: *
 One forecast value every 5 minutes per site per forecast
 sequence = ~1,125,000 rows per day';
 
@@ -166,18 +166,18 @@ COMMENT ON COLUMN "latest_forecast_values"."forecast_version" IS 'The semantic v
 
 COMMENT ON TABLE "clients" IS 'Each client row defines a provider of site data
 
-*Approximate size: *  
+*Approximate size: *
 One row per client = ~4 rows';
 
 COMMENT ON TABLE "datetime_intervals" IS 'Each datetime_interval row defines a timespan between a start and end time
 
-*Approximate size: *  
+*Approximate size: *
 One interval every 5 minutes per day = ~288 rows per day';
 
 COMMENT ON TABLE "status" IS 'Each status row defines a message reporting on the status of the
 services within the nowcasting domain
 
-*Approximate size: *  
+*Approximate size: *
 ~1 row per day';
 
 ALTER TABLE "sites" ADD FOREIGN KEY ("client_uuid") REFERENCES "clients" ("client_uuid");

diff --git a/pvsite.dbml b/pvsite.dbml
@@ -1,6 +1,6 @@
 Project pvsite {
   database_type: 'PostgreSQL'
-  
+
   Note: '''
     Datamodel for PV site-level data. To be surfaced via
     the to-be built nowcasting site-level API and frontend.
@@ -23,17 +23,17 @@ Table sites {
   created_utc timestamp [not null]
   updated_utc timestamp [not null]
   ml_id serial [note: 'Auto-incrementing integer ID of the site for use in ML training']
-  
+
   Indexes {
     (client_uuid, client_site_id) [unique, name: 'idx_client']
   }
-  
+
   Note: '''
     Each site row specifies a single panel or cluster of panels
     found on a residential house or commercial building. Their
     data is provided by a client.
-    
-    *Approximate size: *  
+
+    *Approximate size: *
     4 clients * ~1000 sites each = ~4000 rows
   '''
 }
@@ -44,12 +44,12 @@ Table generation {
   power_kw real [not null, note: 'The actual generated power in kW at this site for this datetime interval']
   datetime_interval_uuid uuid [not null, note: 'The time interval over which this generated power value applies']
   created_utc timestamp [not null]
-  
+
   Note: '''
   Each yield row specifies a generated power output over a
   given time range for a site.
-  
-  *Approximate size: *  
+
+  *Approximate size: *
   Generation populated every 5 minutes per site * 4000 sites = ~1,125,000 rows per day
   '''
 }
@@ -59,12 +59,12 @@ Table forecasts {
   site_uuid uuid [not null, note: 'The site for which the forecast sequence was generated']
   created_utc timestamp [not null, note: 'The creation time of the forecast sequence']
   forecast_version varchar(32) [not null, note: 'The semantic version of the model used to generate the forecast']
-  
+
   Note: '''
     Each forecast row refers to a sequence of predicted solar generation values
-    over a set of target times for a site. 
-    
-    *Approximate size: *  
+    over a set of target times for a site.
+
+    *Approximate size: *
     One forecast per site every 5 minutes = ~1,125,000 rows per day
   '''
 }
@@ -75,13 +75,13 @@ Table forecast_values {
   forecast_generation_kw real [not null, note: 'The predicted power generation of this site for the given time interval']
   created_utc timestamp [not null]
   forecast_uuid uuid [not null, note: 'The forecast sequence this forcast value belongs to']
-  
+
   Note: '''
-    Each forecast_value row is a prediction for the power output 
+    Each forecast_value row is a prediction for the power output
     of a site over a target datetime interval. Many predictions
     are made for each site at each target interval.
-    
-    *Approximate size: *  
+
+    *Approximate size: *
     One forecast value every 5 minutes per site per forecast.
     Each forecast's prediction sequence covers 24 hours of target
     intervals = ~324,000,000 rows per day
@@ -96,14 +96,14 @@ Table latest_forecast_values {
   forecast_uuid uuid [not null, note: 'The forecast sequence this forcast value belongs to']
   site_uuid uuid [not null, note: 'The site for which the forecast sequence was generated']
   forecast_version varchar(32) [not null, note: 'The semantic version of the model used to generate the forecast']
-  
+
   Note: '''
-    Each forecast_value row is a prediction for the power output 
-    of a site over a target datetime interval. Only the most recent 
+    Each forecast_value row is a prediction for the power output
+    of a site over a target datetime interval. Only the most recent
     prediction for each target time interval is stored in this table
     per site.
-    
-    *Approximate size: *  
+
+    *Approximate size: *
     One forecast value every 5 minutes per site per forecast
     sequence = ~1,125,000 rows per day
   '''
@@ -113,11 +113,11 @@ Table clients {
   client_uuid uuid [primary key, not null]
   client_name varchar(255) [not null]
   created_utc timestamp [not null]
-  
+
   Note: '''
   Each client row defines a provider of site data
-  
-  *Approximate size: *  
+
+  *Approximate size: *
   One row per client = ~4 rows
   '''
 }
@@ -127,16 +127,16 @@ Table datetime_intervals {
   start_utc timestamp [not null]
   end_utc timestamp [not null]
   created_utc timestamp [not null]
-  
+
   Indexes {
     start_utc
     end_utc
   }
-  
+
   Note: '''
   Each datetime_interval row defines a timespan between a start and end time
-  
-  *Approximate size: *  
+
+  *Approximate size: *
   One interval every 5 minutes per day = ~288 rows per day
   '''
 }
@@ -150,8 +150,8 @@ Table status {
   Note: '''
   Each status row defines a message reporting on the status of the
   services within the nowcasting domain
-  
-  *Approximate size: *  
+
+  *Approximate size: *
   ~1 row per day
   '''
 }

diff --git a/sdk/python/pvsite_datamodel/__init__.py b/sdk/python/pvsite_datamodel/__init__.py
@@ -1,6 +1,4 @@
-"""
-Python SDK for reading/writing to/from pvsite database
-"""
+"""Python SDK for reading/writing to/from pvsite database."""
 
 from .connection import DatabaseConnection
 from .sqlmodels import (

diff --git a/sdk/python/pvsite_datamodel/connection.py b/sdk/python/pvsite_datamodel/connection.py
@@ -1,4 +1,4 @@
-""" Database Connection class"""
+"""Database Connection class."""
 import logging
 
 from sqlalchemy import create_engine
@@ -10,19 +10,20 @@
 
 
 class DatabaseConnection:
-    """Database connection class"""
+    """Database connection class."""
 
     def __init__(self, url: URL | str, echo: bool = True):
-        """
-        Set up database connection
+        """Set up database connection.
 
-        url: the database url, used for connecting
+        :param url: the database url, used for connecting
+        :param echo: whether to echo
         """
         self.url = url
         self.engine = create_engine(self.url, echo=echo)
         self.Session = sessionmaker(bind=self.engine)
-        assert self.url is not None, Exception("Need to set url for database connection")
+        if self.url is None:
+            raise Exception("Need to set url for database connection")
 
     def get_session(self) -> Session:
-        """Get sqlalamcy session"""
+        """Get sqlalchemy session."""
         return self.Session()
diff --git a/sdk/python/pvsite_datamodel/read/generation.py b/sdk/python/pvsite_datamodel/read/generation.py
@@ -1,12 +1,13 @@
-""" Read pv generation functions """
+"""Read pv generation functions."""
 import logging
 import uuid
 from datetime import datetime
 from typing import List, Optional
 
-from pvsite_datamodel.sqlmodels import ClientSQL, DatetimeIntervalSQL, GenerationSQL, SiteSQL
 from sqlalchemy.orm import Session
 
+from pvsite_datamodel.sqlmodels import ClientSQL, DatetimeIntervalSQL, GenerationSQL, SiteSQL
+
 from .utils import filter_query_by_datetime_interval
 
 logger = logging.getLogger(__name__)
@@ -18,16 +19,14 @@ def get_pv_generation_by_client(
     end_utc: Optional[datetime] = None,
     client_names: Optional[List[str]] = None,
 ) -> List[GenerationSQL]:
-    """
-    Get the generation data by client
+    """Get the generation data by client.
 
     :param session: database session
     :param end_utc: search filters < on 'datetime_utc'. Can be None
     :param start_utc: search filters >= on 'datetime_utc'. Can be None
     :param client_names: optional list of provider names
-    :return:list of pv yields
+    :return:list of pv yields.
     """
-
     # start main query
     query = session.query(GenerationSQL)
     query = query.join(SiteSQL)
@@ -58,16 +57,14 @@ def get_pv_generation_by_sites(
     end_utc: Optional[datetime] = None,
     site_uuids: Optional[List[uuid.UUID]] = None,
 ) -> List[GenerationSQL]:
-    """
-    Get the generation data by site
+    """Get the generation data by site.
 
     :param session: database session
     :param start_utc: search filters >= on 'datetime_utc'
     :param end_utc: search fileters < on 'datetime_utc'
     :param site_uuids: optional list of site uuids
     :return: list of pv yields
     """
-
     # start main query
     query = session.query(GenerationSQL)
     query = query.join(SiteSQL)
-Original file line number
+Diff line change
@@ Expand Up / @@ -28,7 +28,7 @@ class Sites(Base): @@
         ml_id = sa.Column(sa.Integer(), autoincrement=True)
         __table_args__ = (
         UniqueConstraint("client_site_id",client_uuid, name='idx_client')
                 )
@@ Expand Down @@