Is_na
is_na is an operation that identifies values representing missing or null data and returns corresponding missingness indicators.
Machine Learning for Tabular Data: XGBoost, Deep Learning, and AI
The pandas isna method identifies values that represent missing data.
- How it is used
- Uses pandas isna during tabular-data examination to identify missing feature samples and quantify missingness by column.
- How deep it goes
- Explains boolean detection and counting with sum, then stops short of implementing imputation or missingness indicators.
- Examples
- Demonstrates column-wise counts on the Auto MPG dataset, finding eight missing mpg values and six missing horsepower values.
- What you can do after
- Diagnose/debug with it, count missing samples by feature, and decide whether missingness needs indicators or imputation.
Read how Machine Learning for Tabular Data: XGBoost, Deep Learning, and AI explains is_na →
Grokking Machine Learning
is_na is a Pandas operation that identifies missing or null entries in a data structure.
- How it is used
- Uses missing-value counts to decide whether dataset columns should be removed or repaired.
- How deep it goes
- Defines the binary result and demonstrates summing it by column, then stops at downstream cleaning choices.
- Examples
- Uses Titanic columns including Age, Cabin, and Embarked to illustrate missing-value counts and repairs.
- What you can do after
- Apply it via Pandas to count missing entries and select column-dropping or value-filling actions.
Related concepts
- isnullequivalent to · isnull is a pandas method that returns Boolean values indicating whether each Series or DataFrame value is null or missing.
- pandaspart of · pandas is an open-source Python library that provides labeled data structures and tools for manipulating and analyzing tabular and other structured data.
- missing data indicatorproduces · A missing data indicator is a binary feature recording whether a corresponding data value is missing.
- missing valuemeasures · A missing value is a marker or condition indicating that an expected data value or reference is absent, unavailable, unknown, or inapplicable.
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.