Predicting Taxi fares in NYC using Google Cloud AI Platform (Billion + rows) Par...
source link: https://www.tuicool.com/articles/NzIjmu3
Go to the source link to view the article. You can view the picture content, updated content and better typesetting reading experience. If the link is broken, please click the button below to view the snapshot at that time.
Taxis | Photo by Life of Pix on pexels.com
In this series of articles, we are working on a real-world dataset of taxi rides in NYC which is hosted in BigQuery to be able to estimate the fare amount.
In theprevious post, we set up a project on the Google Cloud Platform, started an AI notebook instance with TensorFlow pre-installed, and prepared/cleaned/sampled the data. Now comes the part where we build a model to predict the target variable.
We are going to use tf.estimator , a high-level TensorFlow API to build our models. Detailed information can be found here .
There are four major steps to use this API.
- Create a function to import the dataset
- Define the feature columns
- Instantiate the Estimator
- Train/Evaluate
Create a function to import the dataset
Recommend
About Joyk
Aggregate valuable and interesting links.
Joyk means Joy of geeK