openaq_engine package

Subpackages

• openaq_engine.config package
  • Submodules
  • openaq_engine.config.model_settings module
    • BuildFeaturesConfig
      • BuildFeaturesConfig.ALL_MODEL_FEATURES
      • BuildFeaturesConfig.CATEGORICAL_FEATURES
      • BuildFeaturesConfig.CITY
      • BuildFeaturesConfig.CORE_FEATURES
      • BuildFeaturesConfig.COUNTRY
      • BuildFeaturesConfig.SATELLITE_FEATURES
      • BuildFeaturesConfig.TARGET_COL
      • BuildFeaturesConfig.TARGET_VARIABLE
    • CohortBuilderConfig
      • CohortBuilderConfig.CITY
      • CohortBuilderConfig.COUNTRY
      • CohortBuilderConfig.DATE_COL
      • CohortBuilderConfig.ENTITY_ID_COLS
      • CohortBuilderConfig.FILTER_DICT
      • CohortBuilderConfig.LOCAL_DATA
      • CohortBuilderConfig.REGION
      • CohortBuilderConfig.S3_BUCKET
      • CohortBuilderConfig.S3_OUTPUT
      • CohortBuilderConfig.SCHEMA_NAME
      • CohortBuilderConfig.SENSOR_TYPE
      • CohortBuilderConfig.SOURCE
      • CohortBuilderConfig.TABLE_NAME
      • CohortBuilderConfig.TARGET_VARIABLE
    • EEConfig
      • EEConfig.ALL_SATELLITES
      • EEConfig.AOD_IMAGE_BAND
      • EEConfig.AOD_IMAGE_COLLECTION
      • EEConfig.AOD_IMAGE_PERIOD
      • EEConfig.AOD_IMAGE_RES
      • EEConfig.BUCKET_NAME
      • EEConfig.DATE_COL
      • EEConfig.LANDSAT_IMAGE_BAND
      • EEConfig.LANDSAT_IMAGE_COLLECTION
      • EEConfig.LANDSAT_PERIOD
      • EEConfig.LANDSAT_RES
      • EEConfig.LAND_COVER_IMAGE_BAND
      • EEConfig.LAND_COVER_IMAGE_COLLECTION
      • EEConfig.LAND_COVER_IMAGE_RES
      • EEConfig.LAND_COVER_PERIOD
      • EEConfig.LOOKBACK_N
      • EEConfig.METEROLOGICAL_IMAGE_BAND
      • EEConfig.METEROLOGICAL_IMAGE_COLLECTION
      • EEConfig.METEROLOGICAL_IMAGE_PERIOD
      • EEConfig.METEROLOGICAL_IMAGE_RES
      • EEConfig.NIGHTTIME_LIGHT_IMAGE_BAND
      • EEConfig.NIGHTTIME_LIGHT_IMAGE_COLLECTION
      • EEConfig.NIGHTTIME_LIGHT_PERIOD
      • EEConfig.NIGHTTIME_LIGHT_RES
      • EEConfig.PATH_TO_PRIVATE_KEY
      • EEConfig.POPULATION_IMAGE_BAND
      • EEConfig.POPULATION_IMAGE_COLLECTION
      • EEConfig.POPULATION_IMAGE_RES
      • EEConfig.POPULATION_PERIOD
      • EEConfig.SERVICE_ACCOUNT
      • EEConfig.TABLE_NAME
    • HyperparamConfig
      • HyperparamConfig.MODEL_HYPERPARAMS
      • HyperparamConfig.MODEL_TYPES
    • MatrixGeneratorConfig
      • MatrixGeneratorConfig.ALGORITHM
      • MatrixGeneratorConfig.ID_COLUMN_LIST
    • ModelTrainerConfig
      • ModelTrainerConfig.All_MODEL_FEATURES
      • ModelTrainerConfig.ID_COLS_TO_REMOVE
      • ModelTrainerConfig.MODEL_NAMES_LIST
      • ModelTrainerConfig.RANDOM_STATE
    • ModelVisualizerConfig
      • ModelVisualizerConfig.PLOT
      • ModelVisualizerConfig.PLOTS_SCHEMA_NAME
      • ModelVisualizerConfig.PLOTS_TABLE_NAME
      • ModelVisualizerConfig.PLOT_METRICS
      • ModelVisualizerConfig.RESULTS_TABLE_NAME
    • TimeSplitterConfig
      • TimeSplitterConfig.AWS_ACCESS_KEY
      • TimeSplitterConfig.AWS_SECRET_ACCESS_KEY
      • TimeSplitterConfig.CITY
      • TimeSplitterConfig.COUNTRY
      • TimeSplitterConfig.DATABASE
      • TimeSplitterConfig.DATE_COL
      • TimeSplitterConfig.LOCAL_DATA
      • TimeSplitterConfig.REGION
      • TimeSplitterConfig.RESOURCE
      • TimeSplitterConfig.S3_BUCKET
      • TimeSplitterConfig.S3_OUTPUT
      • TimeSplitterConfig.SENSOR_TYPE
      • TimeSplitterConfig.SOURCE
      • TimeSplitterConfig.TABLE_NAME
      • TimeSplitterConfig.TARGET_VARIABLE
      • TimeSplitterConfig.TIME_WINDOW_LENGTH
      • TimeSplitterConfig.TRAIN_VALIDATION_DICT
      • TimeSplitterConfig.WINDOW_COUNT
      • TimeSplitterConfig.WITHIN_WINDOW_SAMPLER
  • Module contents
• openaq_engine.src package
  • Subpackages
    • openaq_engine.src.preprocessing package
      • Submodules
      • openaq_engine.src.preprocessing.filter module
      • Module contents
    • openaq_engine.src.utils package
      • Submodules
      • openaq_engine.src.utils.utils module
      • Module contents
  • Submodules
  • openaq_engine.src.cohort_builder module
  • openaq_engine.src.matrix_generator module
  • openaq_engine.src.preprocess module
  • openaq_engine.src.time_splitter module
  • openaq_engine.src.train_model module
  • Module contents

Submodules

openaq_engine.main module

openaq_engine.setup module

openaq_engine.setup_environment module

Setup Environment

Tools for connecting to the database.

openaq_engine.setup_environment.connect_to_db(PGPORT=5432)

Context manager for connecting to a PostgreSQL database.

Parameters:

PGPORT (int, optional) – The port number to connect to (default is 5432).

Yields:

conn (SQLAlchemy Connection) – A connection to the PostgreSQL database.

openaq_engine.setup_environment.get_athena_engine()

Creates and returns a SQLAlchemy engine for connecting to AWS Athena.

Returns:

engine – A SQLAlchemy engine connected to AWS Athena.

Return type:

SQLAlchemy Engine

openaq_engine.setup_environment.get_dbengine(PGDATABASE='', PGHOST='', PGPORT=5432, PGPASSWORD='', PGUSER='', DBTYPE='postgresql')

Creates and returns a SQLAlchemy engine for connecting to a PostgreSQL database.

Parameters:

• PGDATABASE (str) – The name of the database to connect to.

• PGHOST (str) – The hostname of the database server.

• PGPORT (int, optional) – The port number to connect to (default is 5432).

• PGPASSWORD (str) – The password for the database user.

• PGUSER (str) – The username for the database.

• DBTYPE (str, optional) – The type of database, default is “postgresql”.

Returns:

engine – A SQLAlchemy engine connected to the specified database.

Return type:

SQLAlchemy Engine

openaq_engine.setup_environment.run_query(query)

Executes a SQL query on the database and returns the result as a pandas DataFrame.

Parameters:

query (str) – The SQL query to execute.

Returns:

data – A DataFrame containing the results of the query.

Return type:

pandas DataFrame

openaq_engine.setup_environment.test_database_connect()

Tests the database connection by running a simple query.

Raises:

AssertionError – If the query returns fewer than 1 row.

Module contents