Cleaning Data In R with Tidyverse and Data.table

Identify and address missing data and outliers to prevent biased analyses. Apply simple and advanced methods to detect, replace outliers, and handle missing values without discarding observations.

Identify missing data types and reasons, then compare deletion, hot deck imputation, mean imputation, interpolation, and multiple imputation methods, including multiple imputation by trained equations, to mitigate bias and uncertainty.

Explore three levels of missing data handling in R, from default na.action to simple imputation and advanced methods like mice, with practical demos using the flower_pics dataset.

Learn to handle missing data in R using the mice package and machine learning methods, performing multiple imputations and pooling results on a flower dataset.

Identify outliers with three-sigma and box plots, and apply multivariate proximity or model-based methods to ensure clean data in R, Python, and Tableau.

Explore simple univariate outlier detection methods, including the esd interval using mean and standard deviation, the box plot approach, and tests from the outliers package such as Dixon and chi-square.

Detect outliers in multivariate datasets using sign one, sign two, and pick out methods from the outlier package, based on PCA distances and a chosen critical value.

Explore the tidyverse, a collection of 70 packages that enable clean data and fast exploratory analysis; learn the pipe operator, tibble, and the tidier package for formatting and string manipulations.

The tidyverse is a collection of R packages that work together to produce clean, tidy data; install and load packages individually to avoid memory strain and conflicts, with pipe-driven workflows.

Learn how the pipe operator changes code syntax within tidyverse workflows and how it enables complex, interactive time series charts with the digraphs package, illustrated by the links dataset.

Explore tibble as a table that contrasts with data frames, preserving column classes, avoiding row names, and preventing recycling, while enabling quick creation with tribble, add_row, and add_column.

Apply the tidyverse principle of tidy data to transform dirty data into clean data. Learn table-level rules where each variable occupies its own column and each observation forms a row.

Convert a wide data frame to long form by gathering weight class columns into a single weight column of counts; compare gather and melt in tidyverse and data.table.

Learn how to split a single mixed column into separate height and sex columns using the separate function, enabling easier analysis with fixed patterns in a data frame.

Convert long-form data to wide form using spread from tidyverse and diecast from data.table, showing one observation per row with separate top and low performance counts.

Learn to clean and manipulate text data in R with stringr: concatenate strings, count patterns, replace text, convert case, measure length, and pad strings, handling encoding concerns.

Explore how query systems in R support data preparation and mining by selecting data subsets with simple to complex criteria, from data.frame to data.table, and the player.

Learn to filter, queering, subset, and reorder data in R using data frame, data table, and table, comparing row and column indexing with box brackets and or conditions.

Explore how deployer enables fast data manipulation with five single-table verbs, filter, arrange, select, mutate, and summarize, allowing direct column references and tidy data frames.

Explore data.table’s query system, using i, j, and .N to count, filter, and group by parameter, then apply set order, transpose, and data frame to data table conversion.

Embark on an applied R project to test your course gains by cleaning a dirty CEV dataset, performing class conversion, missing data handling, and outlier detection with tidyverse and data.table.

Clean and consolidate a car shop sales data set from an ab testing, harmonizing four currencies into one, and prepare eight variables for analysis in R with tidyverse and data.table.

Transform a raw data set into a clean analytics-ready table with tidyverse and data.table. Convert date formats, set category and currency as categorical, fuse names, and convert to USD.

Show how to import data with the reader package in rstudio, adjust column classes (skip X1, set category and currency as factors), fix the date format, and preview results.

Learn to clean data in R using tidyverse and data.table: remove junk columns, unite names, replace outliers with the median, impute missing values with miss, and convert currencies to usd.

Use tidyverse and data.table in R to query a prepared data set, compute category profits, average profit per transaction, and profit margin, while noting imputation variability and data cleaning steps.

Master data cleaning in r using tidyverse and data.table by planning, importing, imputing missing data with mice, detecting outliers, and applying tidyverse filtering and string operations to a real-world project.