It is defined as
d (x,y) = ((x-y) T S -1 (x-y)) 1/2
Whereby x and y are two random vectors on the same distribution with the convariance matrix S.
Explanation:
Assume that we have a data set in a 2-dimensional Euclidean space and we want to estimate the
probability that a point P1 (x,y) is part of this set. Obviously, the 'closer' the P1 is to the center
of mass in the set, the more likely it is contained. Also we have to consider the spread of the data. A
Data set with correlated variables will form a ellipse around the center of mass in the 2-dimensional
Euclidean space. So the probability that a test point is contained in the set is also depend on the
direction of the axis of that ellipse - or ellipsoid in a N-dimensional Euclidean space. The ellipsoid
that best represents the set's probability distribution can be estimated by building the covariance
matrix of the samples, which is actually used by the Mahalanobis distance.
If the covariance matrix is the identity matrix the variables of the data set are not correlated and the
Mahalanobis distance reduces to the Euclidean distance.
Use case:
A typical use case is the outlier detection. These are intuitively points with a very high Mahalanobis
distance in contrast to points in the data set.
Options
Popular Predecessors
Linear Correlation13 %K Nearest Neighbor (Distance Function)6 %- ARFF Reader4 %
- k-Means4 %
- Color Manager4 %
- Excel Reader3 %
Scorer3 %PCA3 %- Normalizer3 %
- Pivot3 %
- Mahalanobis Distance2 %
PCA Compute2 %Excel Reader (XLS)2 %- Distance Matrix Calculate2 %
- Concatenate2 %
- Math Formula2 %
- Joiner2 %
- CASE Switch Start2 %
- X-Partitioner1 %
- Numeric Outliers1 %
- DBSCAN1 %
- Auto-Binner1 %
Number To String1 %- Similarity Search1 %
- Table Reader1 %
File Reader< 1 %- Missing Value Column Filter< 1 %
Row Splitter (deprecated)< 1 %- Similarity Calculator< 1 %
CSV Reader< 1 %- PCA Apply< 1 %
- Low Variance Filter< 1 %
- Data Generator< 1 %
- Linear Correlation< 1 %
- Value Counter< 1 %
- Matlab Snippet< 1 %
Row Filter (deprecated)< 1 %- GroupBy< 1 %
- Denormalizer< 1 %
- Normalizer (PMML)< 1 %
- Distance Matrix Reader< 1 %
- K Nearest Neighbor (Distance Function)< 1 %
- Chunk Loop Start< 1 %
- PCA< 1 %
- Correlation Filter< 1 %
- RowID< 1 %
- Row Sampling< 1 %
Color Appender< 1 %- k-Medoids< 1 %
Python Script (2⇒1)< 1 %- Linear Discriminant Analysis< 1 %
- Try (Data Ports)< 1 %
- Table Creator< 1 %
- Group Loop Start< 1 %
PCA Apply< 1 %- Column Filter< 1 %
Joiner< 1 %- Partitioning< 1 %
- Missing Value< 1 %
- Table Transposer< 1 %
Rank Correlation< 1 %Table Row To Variable Loop Start< 1 %- Image to Table< 1 %
K Nearest Neighbor< 1 %- K Nearest Neighbor< 1 %
- PCA Compute< 1 %
Concatenate (Optional in)< 1 %- Bootstrap Sampling< 1 %
- Column Auto Type Cast< 1 %
- Number to String< 1 %
String To Number< 1 %- Column Resorter< 1 %
- Double to Integer< 1 %
- Normalizer (Apply)< 1 %
- Column Splitter< 1 %
- Statistics< 1 %
- Crosstab< 1 %
- Box Plot (legacy)< 1 %
Word Vector Apply (legacy)< 1 %- Line Plot (JavaScript)< 1 %
Python Script (2⇒2)< 1 %- R Snippet< 1 %
- Fuzzy c-Means< 1 %
- String to Number< 1 %
- Reference Column Filter< 1 %
- Nominal Value Row Filter< 1 %
- String Manipulation (Multi Column)< 1 %
Views
- This node has no views
Workflows
03_NIR_Spectral_Data_Inhouse_Database_SearchKNIME Hub- 03_NIR_Spectral_Data_Inhouse_Database_SearchKNIME Hub
- 15. Fraud_Detection-EmbeddingsKNIME Hub
- 17887 Mahalanobis distanceKNIME Hub
- JKISeason3-18_ayatoKNIME Hub
Links
- No links available
Developers
You want to see the source code for this node? Click the following button and we’ll use our super-powers to find it for you.