In this hands-on live session, you will be working through a sales forecasting problem step-by-step with a key focus on problem identification, data wrangling, feature engineering & EDA, and finally modeling using some structured frameworks and methodologies. Open-source libraries in Python will be used in combination with Google Colab so we spend minimal time in setup and focus on the core session itself.
Pre-requisites: Having a basic knowledge of supervised machine learning, Python and Google Colab
Feature Engineering is often one of the overlooked aspects of the Data Science lifecycle but is probably one of the most critical steps which can make or break a Data Science project.
Chapters
00:00 - 1:27 : Introduction
1:27 - 6:30 : Problem Description
6:31 - 8:23 : Load the dataset
8:24 - 13:33 : Data understanding
13:34 - 19:47 : Preparing training and testing datasets
19:48 - 38:32 : Exploratory Data Analysis
38:33 - 1:05:02 : Data Wrangling and Feature Engineering
1:05:03 - 1:29:31 : Modeling
1:29:32 -1:43:39 : Q/A
Download the Jupyter notebook: https://colab.research.google.com/drive/1oAjgaqx5YA7UttrgIRIwFVPK5Xy834wA?usp=sharing
🔗 More action pack session here: https://datahack.analyticsvidhya.com/contest/all/
Stay on top of your industry by interacting with us on our social channels:
Follow us on Instagram: https://www.instagram.com/analytics_vidhya/
Like us on Facebook: https://www.facebook.com/AnalyticsVidhya/
Follow us on Twitter: https://twitter.com/AnalyticsVidhya
Follow us on LinkedIn: https://www.linkedin.com/company/analytics-vidhya