Regression

How to log your model schema for regression models

Regression Model Overview

Regression models have a continuous, numeric output. (Examples: click-through rates, sales forecasting, customer lifetime value, ETA models, etc.)

Performance Metrics

MAPE, MAE, RMSE, MSE, R-Squared, Mean Error

Allowed Metric Families: Regression

Click here for all valid model types and metric combinations.

Regression Code Example

Python Pandas

Google Colaboratory

Example Row

price (float)	pos_approved (bool)	zip_code	age	prediction_score	actual_score	prediction_ts
88.5	False	12345	25	100	90	1671572541

# feature & tag columns can be optionally defined with typing:
tag_columns = TypedColumns(
    inferred=["name"],
    to_int=["zip_code", "age"]
)

# Declare the schema of the dataframe you're sending (feature columns, predictions, timestamp, actuals) 
schema = Schema(
    prediction_id_column_name="prediction_id",
    timestamp_column_name="prediction_ts",
    prediction_score_column_name="prediction_score",
    actual_score_column_name="actual_score",
    feature_column_names=["price", "pos_approved"],
    tag_column_names=tag_columns,
)
# Log the dataframe with the schema mapping
response = client.log(
    model_id='sample-model-1', 
    model_version='v1', 
    model_type=ModelTypes.REGRESSION,
    metrics_validation=[Metrics.REGRESSION],
    environment=Environments.PRODUCTION,
    dataframe=test_dataframe,
    schema=schema
)

Python Single Record

Google Colaboratory

# features & tags can be optionally defined with typing
features = {
    'score': '88.5',
    'pos_approved': TypedValue(value=False, type=ArizeTypes.INT)
}  
    
tags = {
    'zip_code': '12345'
    'age': '25'
}

response = client.log(
    model_id='sample-model-1', 
    model_version='v1', 
    model_type=ModelTypes.REGRESSION,
    environment=Environments.PRODUCTION,
    features = features, 
    tags=tags
    prediction_label=100,
    actual_label=90
)

Data Connector

Download an example Parquet file: Open parquet reader here.

https://storage.cloud.google.com/arize-assets/documentation-sample-data/data-ingestion/regression-assets/regression_data.parquetstorage.cloud.google.com

Download an example CSV file:

https://storage.googleapis.com/arize-assets/fixtures/demand_forecast_prod.csv

Learn how to upload files via various Data Connectors:

Google Cloud Storage (GCS)AWS S3Azure Blob StorageGoogle BigQuery

Quick Definitions

Prediction Label: The numeric value of the prediction (float | int)

Actual Label: The numeric value of the actual (float | int)