liveBook · Manning

Data wrangling

Data wrangling is the process of cleaning, transforming, restructuring, organizing, and combining raw data into a form suitable for analysis or downstream processing.

How 5 Manning books explain it

Statistics Slam Dunk

Data wrangling is the process of cleaning, transforming, reshaping, filtering, summarizing, and combining data for analysis.

How it is used
Prepares web-sourced NBA data for exploration, visualization, statistical testing, and modeling.
How deep it goes
Demonstrates step-by-step dplyr and tidyr operations, including filtering, reshaping, derived variables, summaries, and joins.
Examples
Uses NBA box scores, payrolls, win shares, player seasons, and play-by-play records as messy source data.
What you can do after
Apply it via dplyr, tidyr, readr, and base R to turn raw CSV files into analysis-ready datasets.

Read how Statistics Slam Dunk explains data wrangling →

Delivering Machine Learning Projects: From design to deployment

Data wrangling is the process of restructuring, cleaning, and transforming data into a form suitable for analysis or modeling.

How it is used
Identifies data preparation work that must be considered when estimating an ML project.
How deep it goes
Flags the need for data manipulation without prescribing transformation steps.
Examples
Uses a bike retailer’s five-year transaction history, including noisy legacy records and cleaner recent records.
What you can do after
Evaluate data wrangling complexity from fragmented transaction tables and differences in data quality.

Read how Delivering Machine Learning Projects: From design to deployment explains data wrangling →

Statistics Every Programmer Needs

Data wrangling is the process of transforming and preparing raw data into a clean, consistent, and analysis-ready format.

How it is used
Prepares imperfect datasets for statistical analysis, visualization, and models such as decision trees and random forests.
How deep it goes
Demonstrates filtering, missing-value handling, recoding, feature creation, and validation in Python, without developing general data-integration strategies.
Examples
Uses fourth-down NFL play data and East Baton Rouge Parish street-address records to demonstrate filtering, cleaning, extraction, and type conversion.
What you can do after
Apply via Python pandas and NumPy to produce validated, model-ready variables and analysis-specific subsets.

Read how Statistics Every Programmer Needs explains data wrangling →

D3.js in Action, Third Edition

Data wrangling is the process of transforming, cleaning, and reshaping data for subsequent use or analysis.

How it is used
Uses data wrangling to prepare datasets for analysis, prototyping, and custom visualization.
How deep it goes
Explains property access, type conversion, iteration, mapping, filtering, and finding, but does not cover all manipulation techniques.
Examples
Demonstrates employee records, numeric ID conversion, name extraction, conditional filtering, and unique-record lookup.
What you can do after
Apply it via JavaScript array methods to clean, reshape, and select records for visualization.

Read how D3.js in Action, Third Edition explains data wrangling →

The Complete Obsolete Guide to Generative AI

The process of transforming, cleaning, and structuring raw data into a consistent machine-readable form.

How it is used
Prepares raw business data for analysis and question-answering workflows.
How deep it goes
Defines wrangling as parsing data into consistent machine-readable form, then illustrates downstream querying rather than implementation details.
Examples
Uses an audio transcript PDF and an anonymized bank-customer dataset queried for wealth and investment prospects.
What you can do after
Apply it via GPT-based indexing and targeted queries over prepared documents or datasets.

Read how The Complete Obsolete Guide to Generative AI explains data wrangling →

Also covered in

What to know first

Related concepts

Questions about data wrangling

What is data wrangling?

Data wrangling is the process of cleaning, transforming, restructuring, organizing, and combining raw data into a form suitable for analysis or downstream processing.

Which Manning books explain data wrangling?

Statistics Slam Dunk, Delivering Machine Learning Projects: From design to deployment, Statistics Every Programmer Needs, D3.js in Action, Third Edition and The Complete Obsolete Guide to Generative AI.

What should I know before learning data wrangling?

Manning books that teach data wrangling usually introduce data warehouse, CSV, current working directory and proportion first.

What are the parts of data wrangling?

Data wrangling includes data reshaping and data subsetting.

These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.