Learn how to connect to live data sources and prepare time series data for forecasting. You’ll pull hourly electricity demand data from the U.S. EIA API and build your first forecast.

Productionizing your forecast model

Forecasting project architecture

Benefits of experimentation frameworks

Reviewing the input data

import requests
import pandas as pd
import os

# Create the URL
api_url = "____"
api_path = "electricity/rto/region-data/"
api_url_path = api_url + api_path + "data/&data[]=value"
eia_api_key = os.getenv('EIA_API_KEY')

# Create the get_request, including the API key
full_path = api_url_path + "?api_key=" + ____

# Make the request
data = requests.____(____).json()

# Convert the results to a pandas DataFrame
df = pd.____(____["response"]["data"])

import requests
import pandas as pd
import os

# Create the URL
api_url = "https://api.eia.gov/v2/"
api_path = "electricity/rto/region-data/"
api_url_path = api_url + api_path + "data/&data[]=value"
eia_api_key = os.getenv('EIA_API_KEY')

# Create the get_request, including the API key
full_path = api_url_path + "?api_key=" + eia_api_key

# Make the request
data = requests.get(full_path).json()

# Convert the results to a pandas DataFrame
df = pd.DataFrame(data["response"]["data"])

Making an API request

Preparing and visualizing the data

Interpreting time series visualizations

Working with a forecast object

Forecasting with ML Models

Evaluating forecast performance

Visualizing forecast performance

General Architecture

Learn how to design, automate, and monitor scalable forecasting pipelines in Python. This advanced course walks you through the full production workflow—from sourcing data and training models to deployment and monitoring—using tools like MLflow and Airflow. Chapter 1 is available now as part of a prelaunch, with more content coming soon!

Learn how to build robust, scalable forecasting pipelines ready for production. This advanced course is designed for **data scientists**, **machine learning engineers**, and **analytics professionals** who want to move beyond experimentation and put time series forecasting into action. 

You'll work through the full production pipeline—from **sourcing and preparing real-world data** to **training and evaluating multiple forecasting models** using libraries like `statsforecast` and `mlforecast`. You'll then explore how to **automate model training, deployment, and monitoring** using tools such as **MLflow** and **Airflow**.

Along the way, you'll apply forecasting principles to a real dataset from the **U.S. Energy Information Administration** and gain hands-on experience with **API data extraction**, **exception handling**, and **performance logging**.

By the end of the course, you'll be equipped to design forecasting systems that can handle **automation**, **scale**, and **long-term maintenance**.

**Chapter 1 is available now as part of a prelaunch—start learning today while we finish the rest of the pipeline!**


Introduction to Apache Airflow in Python

Introduction to MLflow

Introduction to Data Visualization with Plotly in Python

Time Series Analysis in Python

Learn how to design, automate, and monitor scalable forecasting pipelines in Python. 

Benefits of experimentation frameworks

Forecasting in Practice

Hands-on interactive exercise