Group Impute
Upload a dataset to begin
Supported formats: .csv,.xlsx,.xls,.xlsm,.xlsb,.tsv
Sign in for free for unlimited files, no payment required.
About Group Impute
Fill missing values based on group averages.
Instead of filling every gap in a column with one dataset-wide average, this tool first splits your rows by a category column you choose, then fills missing values using the average (or median) computed within that row's own group.
This matters because a global average can be misleading when subgroups behave differently, filling a missing "Salary" with the company-wide average ignores that engineering and sales pay scales differ.
It's a more context-aware alternative to basic mean imputation, built specifically for datasets where a natural grouping column already exists.
Category: AI & Machine LearningCommon Use Cases
- Filling missing salary values using the average for each department
- Imputing missing product ratings based on the average within each category
- Estimating missing regional sales figures using the average for that region
Key Features
- Group-Aware Averaging
- Mean or Median Fill Strategy
- Automatic Group Detection from a Chosen Column
- Falls Back to Global Average for Empty Groups
Choose the category column you'd normally pass to Group By as the grouping key here, so missing values get filled with a group-specific average instead of a single dataset-wide number from Fill Missing.
Frequently Asked Questions
Instead of filling every missing value with one global average, it fills them using the average within each row's group, which is usually more accurate.
Whatever category column you choose to group by before computing the fill value.
A more accurate fix for analysts and data engineers dealing with missing values across naturally distinct subgroups.
Read the related guide →