black and pylint added for linting and code formatting. tested

.github/workflows/python-app.yml

@@ -28,12 +28,12 @@ jobs:
  python -m pip install --upgrade pip
  pip install flake8 pytest
  if [ -f requirements/requirements.txt ]; then pip install -r requirements/requirements.txt; fi
- - name: Lint with flake8
+ - name: Code formatting with black
  run: |
- # stop the build if there are Python syntax errors or undefined names
-  flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
-  # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
- flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
+  black
+ - name: Lint with pylint
+ run: |
+ pylint
  - name: Train the model
  run: |
  python bikeshare_model/train_pipeline.py

bikeshare_model/__init__.py

@@ -1,9 +1,11 @@
 import sys
 from pathlib import Path
+
 file = Path(__file__).resolve()
 parent, root = file.parent, file.parents[1]
 sys.path.append(str(root))
 
 from bikeshare_model.config.core import PACKAGE_ROOT, config
+
 with open(PACKAGE_ROOT / "VERSION") as version_file:
- __version__ = version_file.read().strip()
+ __version__ = version_file.read().strip()

bikeshare_model/config/core.py

@@ -1,6 +1,7 @@
 # Path setup, and access the config.yml file, datasets folder & trained models
 import sys
 from pathlib import Path
+
 file = Path(__file__).resolve()
 parent, root = file.parent, file.parents[1]
 sys.path.append(str(root))
@@ -17,7 +18,7 @@
 PACKAGE_ROOT = Path(bikeshare_model.__file__).resolve().parent
 ROOT = PACKAGE_ROOT.parent
 CONFIG_FILE_PATH = PACKAGE_ROOT / "config.yml"
-#print(CONFIG_FILE_PATH)
+# print(CONFIG_FILE_PATH)
 
 DATASET_DIR = PACKAGE_ROOT / "datasets"
 TRAINED_MODEL_DIR = PACKAGE_ROOT / "trained_models"
@@ -43,7 +44,7 @@ class ModelConfig(BaseModel):
  target: str
  features: List[str]
  unused_fields: List[str]
- 
+
  date_var: str
  yr_var: str
  mnth_var: str
@@ -57,16 +58,16 @@ class ModelConfig(BaseModel):
  atemp_var: str
  hum_var: str
  windspeed_var: str
- 
+
  yr_mappings: Dict[int, int]
  mnth_mappings: Dict[str, int]
  season_mappings: Dict[str, int]
  weathersit_mappings: Dict[str, int]
  holiday_mappings: Dict[str, int]
  workingday_mappings: Dict[str, int]
  hr_mappings: Dict[str, int]
- 
- test_size:float
+
+ test_size: float
  random_state: int
  n_estimators: int
  max_depth: int
@@ -81,10 +82,10 @@ class Config(BaseModel):
 
 def find_config_file() -> Path:
  """Locate the configuration file."""
- 
+
  if CONFIG_FILE_PATH.is_file():
  return CONFIG_FILE_PATH
- 
+
  raise Exception(f"Config not found at {CONFIG_FILE_PATH!r}")
 
 
@@ -98,7 +99,7 @@ def fetch_config_from_yaml(cfg_path: Path = None) -> YAML:
  with open(cfg_path, "r") as conf_file:
  parsed_config = load(conf_file.read())
  return parsed_config
- 
+
  raise OSError(f"Did not find config file at path: {cfg_path}")
 
 
@@ -109,11 +110,11 @@ def create_and_validate_config(parsed_config: YAML = None) -> Config:
 
  # specify the data attribute from the strictyaml YAML type.
  _config = Config(
- app_config = AppConfig(**parsed_config.data),
- model_config = ModelConfig(**parsed_config.data),
+ app_config=AppConfig(**parsed_config.data),
+ model_config=ModelConfig(**parsed_config.data),
  )
 
  return _config
 
 
-config = create_and_validate_config()
+config = create_and_validate_config()

bikeshare_model/pipeline.py

@@ -1,5 +1,6 @@
 import sys
 from pathlib import Path
+
 file = Path(__file__).resolve()
 parent, root = file.parent, file.parents[1]
 sys.path.append(str(root))
@@ -13,43 +14,96 @@
 from bikeshare_model.processing.features import Mapper
 from bikeshare_model.processing.features import OutlierHandler, WeekdayOneHotEncoder
 
-bikeshare_pipe = Pipeline([
-
- ######### Imputation ###########
- ('weekday_imputation', WeekdayImputer(variable = config.model_config.weekday_var, 
- date_var= config.model_config.date_var)),
- ('weathersit_imputation', WeathersitImputer(variable = config.model_config.weathersit_var)),
-
- ######### Mapper ###########
- ('map_yr', Mapper(variable = config.model_config.yr_var, mappings = config.model_config.yr_mappings)),
-
- ('map_mnth', Mapper(variable = config.model_config.mnth_var, mappings = config.model_config.mnth_mappings)),
-
- ('map_season', Mapper(variable = config.model_config.season_var, mappings = config.model_config.season_mappings)),
-
- ('map_weathersit', Mapper(variable = config.model_config.weathersit_var, mappings = config.model_config.weathersit_mappings)),
-
- ('map_holiday', Mapper(variable = config.model_config.holiday_var, mappings = config.model_config.holiday_mappings)),
-
- ('map_workingday', Mapper(variable = config.model_config.workingday_var, mappings = config.model_config.workingday_mappings)),
-
- ('map_hr', Mapper(variable = config.model_config.hr_var, mappings = config.model_config.hr_mappings)),
-
- ######## Handle outliers ########
- ('handle_outliers_temp', OutlierHandler(variable = config.model_config.temp_var)),
- ('handle_outliers_atemp', OutlierHandler(variable = config.model_config.atemp_var)),
- ('handle_outliers_hum', OutlierHandler(variable = config.model_config.hum_var)),
- ('handle_outliers_windspeed', OutlierHandler(variable = config.model_config.windspeed_var)),
-
- ######## One-hot encoding ########
- ('encode_weekday', WeekdayOneHotEncoder(variable = config.model_config.weekday_var)),
-
- # Scale features
- ('scaler', StandardScaler()),
-
- # Regressor
- ('model_rf', RandomForestRegressor(n_estimators = config.model_config.n_estimators, 
- max_depth = config.model_config.max_depth,
- random_state = config.model_config.random_state))
-
- ])
+bikeshare_pipe = Pipeline(
+ [
+ ######### Imputation ###########
+ (
+ "weekday_imputation",
+ WeekdayImputer(
+ variable=config.model_config.weekday_var,
+ date_var=config.model_config.date_var,
+ ),
+ ),
+ (
+ "weathersit_imputation",
+ WeathersitImputer(variable=config.model_config.weathersit_var),
+ ),
+ ######### Mapper ###########
+ (
+ "map_yr",
+ Mapper(
+ variable=config.model_config.yr_var,
+ mappings=config.model_config.yr_mappings,
+ ),
+ ),
+ (
+ "map_mnth",
+ Mapper(
+ variable=config.model_config.mnth_var,
+ mappings=config.model_config.mnth_mappings,
+ ),
+ ),
+ (
+ "map_season",
+ Mapper(
+ variable=config.model_config.season_var,
+ mappings=config.model_config.season_mappings,
+ ),
+ ),
+ (
+ "map_weathersit",
+ Mapper(
+ variable=config.model_config.weathersit_var,
+ mappings=config.model_config.weathersit_mappings,
+ ),
+ ),
+ (
+ "map_holiday",
+ Mapper(
+ variable=config.model_config.holiday_var,
+ mappings=config.model_config.holiday_mappings,
+ ),
+ ),
+ (
+ "map_workingday",
+ Mapper(
+ variable=config.model_config.workingday_var,
+ mappings=config.model_config.workingday_mappings,
+ ),
+ ),
+ (
+ "map_hr",
+ Mapper(
+ variable=config.model_config.hr_var,
+ mappings=config.model_config.hr_mappings,
+ ),
+ ),
+ ######## Handle outliers ########
+ ("handle_outliers_temp", OutlierHandler(variable=config.model_config.temp_var)),
+ (
+ "handle_outliers_atemp",
+ OutlierHandler(variable=config.model_config.atemp_var),
+ ),
+ ("handle_outliers_hum", OutlierHandler(variable=config.model_config.hum_var)),
+ (
+ "handle_outliers_windspeed",
+ OutlierHandler(variable=config.model_config.windspeed_var),
+ ),
+ ######## One-hot encoding ########
+ (
+ "encode_weekday",
+ WeekdayOneHotEncoder(variable=config.model_config.weekday_var),
+ ),
+ # Scale features
+ ("scaler", StandardScaler()),
+ # Regressor
+ (
+ "model_rf",
+ RandomForestRegressor(
+ n_estimators=config.model_config.n_estimators,
+ max_depth=config.model_config.max_depth,
+ random_state=config.model_config.random_state,
+ ),
+ ),
+ ]
+)

bikeshare_model/predict.py

@@ -1,5 +1,6 @@
 import sys
 from pathlib import Path
+
 file = Path(__file__).resolve()
 parent, root = file.parent, file.parents[1]
 sys.path.append(str(root))
@@ -11,37 +12,50 @@
 from bikeshare_model import __version__ as _version
 from bikeshare_model.config.core import config
 from bikeshare_model.processing.data_manager import load_pipeline
-from bikeshare_model.processing.data_manager import pre_pipeline_preparation
 from bikeshare_model.processing.validation import validate_inputs
 
 
 pipeline_file_name = f"{config.app_config.pipeline_save_file}{_version}.pkl"
-bikeshare_pipe = load_pipeline(file_name = pipeline_file_name)
+bikeshare_pipe = load_pipeline(file_name=pipeline_file_name)
 
 
 def make_prediction(*, input_data: Union[pd.DataFrame, dict]) -> dict:
- """Make a prediction using a saved model """
- 
- validated_data, errors = validate_inputs(input_df = pd.DataFrame(input_data))
- 
- #validated_data = validated_data.reindex(columns = ['dteday', 'season', 'hr', 'holiday', 'weekday', 'workingday', 
+ """Make a prediction using a saved model"""
+
+ validated_data, errors = validate_inputs(input_df=pd.DataFrame(input_data))
+
+ # validated_data = validated_data.reindex(columns = ['dteday', 'season', 'hr', 'holiday', 'weekday', 'workingday',
  # 'weathersit', 'temp', 'atemp', 'hum', 'windspeed', 'yr', 'mnth'])
- validated_data = validated_data.reindex(columns = config.model_config.features)
- 
+ validated_data = validated_data.reindex(columns=config.model_config.features)
+
  results = {"predictions": None, "version": _version, "errors": errors}
- 
+
  if not errors:
  predictions = bikeshare_pipe.predict(validated_data)
- results = {"predictions": np.floor(predictions), "version": _version, "errors": errors}
+ results = {
+ "predictions": np.floor(predictions),
+ "version": _version,
+ "errors": errors,
+ }
  print(results)
 
  return results
 
 
-
 if __name__ == "__main__":
 
- data_in = {'dteday': ['2012-11-6'], 'season': ['winter'], 'hr': ['6pm'], 'holiday': ['No'], 'weekday': ['Tue'],
- 'workingday': ['Yes'], 'weathersit': ['Clear'], 'temp': [16], 'atemp': [17.5], 'hum': [30], 'windspeed': [10]}
-
- make_prediction(input_data = data_in)
+ data_in = {
+ "dteday": ["2012-11-6"],
+ "season": ["winter"],
+ "hr": ["6pm"],
+ "holiday": ["No"],
+ "weekday": ["Tue"],
+ "workingday": ["Yes"],
+ "weathersit": ["Clear"],
+ "temp": [16],
+ "atemp": [17.5],
+ "hum": [30],
+ "windspeed": [10],
+ }
+
+ make_prediction(input_data=data_in)