Book Image

Python Feature Engineering Cookbook - Second Edition

By : Soledad Galli
Book Image

Python Feature Engineering Cookbook - Second Edition

By: Soledad Galli

Overview of this book

Feature engineering, the process of transforming variables and creating features, albeit time-consuming, ensures that your machine learning models perform seamlessly. This second edition of Python Feature Engineering Cookbook will take the struggle out of feature engineering by showing you how to use open source Python libraries to accelerate the process via a plethora of practical, hands-on recipes. This updated edition begins by addressing fundamental data challenges such as missing data and categorical values, before moving on to strategies for dealing with skewed distributions and outliers. The concluding chapters show you how to develop new features from various types of data, including text, time series, and relational databases. With the help of numerous open source Python libraries, you'll learn how to implement each feature engineering method in a performant, reproducible, and elegant manner. By the end of this Python book, you will have the tools and expertise needed to confidently build end-to-end and reproducible feature engineering pipelines that can be deployed into production.

Related Content you might be interested in

Current Title:

Small book image
Python Feature Engineering Cookbook - Second Edition
Soledad Galli
Oct, 2022 | 386 pages
Small book image
Data Preprocessing with Python for Absolute Beginners
AI Sciences
Mar, 2021 | 248 pages
Small book image
Data Cleaning and Exploration with Machine Learning
Michael Walker
Aug, 2022 | 542 pages
Small book image
Hands-On Automated Machine Learning
Sibanjan Das | Umit Mert Cakmak
Apr, 2018 | 282 pages
Table of Contents (14 chapters)
Preface
Preface
Who this book is for
What this book covers
To get the most out of this book
Download the color images
Conventions used
Sections
Get in touch
Reviews
Share Your Thoughts
Download a Free PDF copy of this book
1
Chapter 1: Imputing Missing Data
Chapter 1: Imputing Missing Data
Technical requirements
Removing observations with missing data
Performing mean or median imputation
Imputing categorical variables
Replacing missing values with an arbitrary number
Finding extreme values for imputation
Marking imputed values
Performing multivariate imputation by chained equations
Estimating missing data with nearest neighbors
Free Chapter
2
Chapter 2: Encoding Categorical Variables
Chapter 2: Encoding Categorical Variables
Technical requirements
Creating binary variables through one-hot encoding
Performing one-hot encoding of frequent categories
Replacing categories with counts or the frequency of observations
Replacing categories with ordinal numbers
Performing ordinal encoding based on the target value
Implementing target mean encoding
Encoding with the Weight of Evidence
Grouping rare or infrequent categories
Performing binary encoding
3
Chapter 3: Transforming Numerical Variables
Chapter 3: Transforming Numerical Variables
Transforming variables with the logarithm function
Transforming variables with the reciprocal function
Using the square root to transform variables
Using power transformations
Performing Box-Cox transformation
Performing Yeo-Johnson transformation
4
Chapter 4: Performing Variable Discretization
Chapter 4: Performing Variable Discretization
Technical requirements
Performing equal-width discretization
Implementing equal-frequency discretization
Discretizing the variable into arbitrary intervals
Performing discretization with k-means clustering
Implementing feature binarization
Using decision trees for discretization
5
Chapter 5: Working with Outliers
Chapter 5: Working with Outliers
Technical requirements
Visualizing outliers with boxplots
Finding outliers using the mean and standard deviation
Finding outliers with the interquartile range proximity rule
Removing outliers
Capping or censoring outliers
Capping outliers using quantiles
6
Chapter 6: Extracting Features from Date and Time Variables
Chapter 6: Extracting Features from Date and Time Variables
Technical requirements
Extracting features from dates with pandas
Extracting features from time with pandas
Capturing the elapsed time between datetime variables
Working with time in different time zones
Automating feature extraction with Feature-engine
7
Chapter 7: Performing Feature Scaling
Chapter 7: Performing Feature Scaling
Technical requirements
Standardizing the features
Scaling to the maximum and minimum values
Scaling with the median and quantiles
Performing mean normalization
Implementing maximum absolute scaling
Scaling to vector unit length
8
Chapter 8: Creating New Features
Chapter 8: Creating New Features
Technical requirements
Combining features with mathematical functions
Comparing features to reference variables
Performing polynomial expansion
Combining features with decision trees
Creating periodic features from cyclical variables
Creating spline features
9
Chapter 9: Extracting Features from Relational Data with Featuretools
Chapter 9: Extracting Features from Relational Data with Featuretools
Technical requirements
Setting up an entity set and creating features automatically
Creating features with general and cumulative operations
Combining numerical features
Extracting features from date and time
Extracting features from text
Creating features with aggregation primitives
10
Chapter 10: Creating Features from a Time Series with tsfresh
Chapter 10: Creating Features from a Time Series with tsfresh
Technical requirements
Extracting features automatically from a time series
Creating and selecting features for a time series
Tailoring feature creation to different time series
Creating pre-selected features
Embedding feature creation in a scikit-learn pipeline
11
Chapter 11: Extracting Features from Text Variables
Chapter 11: Extracting Features from Text Variables
Technical requirements
Counting characters, words, and vocabulary
Estimating text complexity by counting sentences
Creating features with bag-of-words and n-grams
Implementing term frequency-inverse document frequency
Cleaning and stemming text variables
12
Index
Index
Why subscribe?
13
Other Books You May Enjoy
Other Books You May Enjoy
Packt is searching for authors like you
Share Your Thoughts
Download a Free PDF copy of this book

Scaling with the median and quantiles

When scaling variables to the median and quantiles, the median value is removed from the observations, and the result is divided by the Inter-Quartile Range (IQR). The IQR is the difference between the 1st quartile and the 3rd quartile, or, in other words, the difference between the 25th quantile and the 75th quantile:

This method is known as robust scaling because it produces more robust estimates for the center and value range of the variable and is recommended if the data contains outliers. In this recipe, we will implement scaling with the median and IQR by utilizing scikit-learn.

How to do it...

To begin, we will import the required packages, load the dataset, and prepare the train and test sets:

  1. Import pandas and the required scikit-learn classes and functions: 
    import pandas as pd
from sklearn.datasets import fetch_california_housing
from sklearn.model_selection import train_test_split
from sklearn...
Previous Section
End of Section 5
Next Section