ML Study Jam — Forecasting model in BQML

Predict Taxi Fare with a BigQuery ML Forecasting Model

What is ML Study Jam?

A free machine learning program using Qwiklabs.

What is BigQuery?

BigQuery is Google’s fully managed, NoOps, low cost analytics database. With BigQuery you can query terabytes and terabytes of data without having any infrastructure to manage, or needing a database administrator.

BigQuery Machine Learning (BQML, product in beta) is a new feature in BigQuery where data analysts can create, train, evaluate, and predict with machine learning models with minimal coding.

The flow of BigQuery ML Forecasting

The flow of ML forecasting is like the flowchart above.

1. Select valuable fields from your raw data table for predictions.
2. Choose a suitable classfication model to train your model.
3. Evaluate the model performance.
4. If the model performance is not good enough, try to filter the data or change the needed table column.
5. If the model is good enough, use it to predict data.
6. Get the predictions.

Predict Taxi Fare with a BigQuery ML Forecasting Model

In this lab, you will explore millions of New York City yellow taxi cab trips available in a BigQuery Public Dataset. You will then create a machine learning model inside of BigQuery to predict the fare of the cab ride given your model inputs. Lastly, you will evaluate the performance of your model and make predictions with it.

The lesson we’re going to learn is to predict the total_fare by using the New York city taxi open data.

New York City Yellow Taxi Trips Record

https://www1.nyc.gov/site/tlc/about/tlc-trip-record-data.page

Select features and create your training dataset

This is the first step of the flowchart, we select the below fields from our table as good inputs to our fare…