End-to-End Deep Learning for Price Prediction
In this practical series of liveProjects, you’ll learn how to bring the power of deep learning to your structured, tabular data. Go hands-on with an open dataset detailing Airbnb rentals in New York City, and take on the challenge of creating an end-to-end deep learning solution for predicting prices. Each project revolves around an essential task of the deep learning pipeline, and is a great way to get started applying deep learning to real-world problems. Work from beginning to end, or dive into whichever section will best augment your skills.
These projects are designed for learning purposes and are not complete, production-ready applications or solutions.
here's what's included
Project 1: Prepare Tabular Data
In this liveProject, you’ll use the Python tools pandas and Folium to prepare the Airbnb dataset for training a deep learning model. You’ll learn Python concepts that ensure the application you build on this data is robust and maintainable, and implement geospatial and visualization techniques to illustrate the geographic distribution of Airbnb rentals.
Project 2: Train a DL Model
In this liveProject, you’ll create and train your deep learning model to predict where a new Airbnb listing will be priced above or below average pricing. You’ll put pandas, Keras, and scikit-learn into action, and master key deep learning techniques for tracking model performance. You’ll learn to harness callbacks in the Keras deep learning framework to make model training more efficient, and how to ensure consistent results in multiple training runs.
Project 3: Deploy a DL Model
In this liveProject, you’ll deploy a completed deep learning model so that it can be easily used by your clients. You’ll use the Flask Python library to build a web page that will host your model, and use HTML, CSS, and JavaScript to build a simple web interface. Finally, you’ll take your model out into the world by using ngrok to make locally-served web pages available anywhere.
Prerequisites
This liveProject is for intermediate data scientists looking to expand their skill set with applied deep learning capabilities. To begin this liveProject, you will need to be familiar with:TOOLS
- Intermediate Python
- Basics of Pandas
- Basics of Folium
- Basics of Flask
- Basics of scikit-learn
- Basics of Keras
- Basics of Ngrok
- Basics of Google Colab
- Basics of Jupyter Notebook
- Basics of HTML, CSS, and JavaScript
- Deep learning model layer assembly
- Deep learning model training
- Trained deep learning model one-off scoring
- Invoking deep learning models
- Basics of web development
you will learn
In these liveProjects, you’ll master all the skills you need to build a complete deep learning model and deploy it to production. You’ll get to grips with a common Python stack used for deep learning across numerous companies and industries.- Manipulate tabular data
- Make geospatial visualizations
- Use Keras to interface with TensorFlow
- Adapt pipeline classes to encapsulate data preparation steps
- Utilize Keras callbacks
- Track and assess model performance
- Create a web server with Flask
- Serve deployment web pages
features
- Self-paced
- You choose the schedule and decide how much time to invest as you build your project.
- Project roadmap
- Each project is divided into several achievable steps.
- Get Help
- While within the liveProject platform, get help from other participants and our expert mentors.
- Compare with others
- For each step, compare your deliverable to the solutions by the author and other participants.
- book resources
- Get full access to select books for 90 days. Permanent access to excerpts from Manning products are also included, as well as references to other resources.