Text-only version of this email
Hi, your model is only as good as your data.
Data preparation methods are required to get the most out of your data and in turn your predictive models.
Cut through the confusion and patchwork descriptions with my book:
>> Data Preparation for Machine Learning
(use the offer code 20offdata to get 20% off)
You cannot fit machine learning models on raw data directly, because:
* Implementations require data to be numeric
* Algorithms impose specific requirements
* Raw data contains errors
* Columns may be redundant or irrelevant
These problems require specialized techniques including:
...Data Cleaning to delete duplicate rows are redundant columns
...Outlier Detection and removal
...Missing Value identification and imputation
...Feature Selection with statistics and models
...Feature Importance with models
...Data Transforms to change data scales, types, and distributions
...Dimensionality Reduction to create low-dimensional projections
And so much more...
I have developed a playbook titled "Data Preparation for Machine Learning" designed for developers to get you up to speed on the
techniques you need to know for data preparation with Python.
It covers:
* Only the topics that are most relevant to applied machine learning.
* Everything is explained with complete and working Python code examples.
* There are no proofs, no derivations, just the practical methods.
>> Click to bring these techniques to your next project
As a valued reader, I want to give you a discount on this book.
Enter the offer code 20offdata and click "apply" to get 20% off the price of the standalone book.
I'll speak to you soon.
Jason.
To make sure you keep getting these emails, please add [email protected] to your address book or whitelist us. Want
out of the loop? .
Our postal address: PO Box 206, Vermont Victoria 3133, Australia
Show all