The table below gives the data handling limits for each XLMiner major feature. "Unlimited" indicates that no limit is imposed by XLMiner, but other limits may apply based on your computer resources and Excel version.
XLMiner Feature | XLMiner Platform | XLMiner Pro | XLMiner Education | Partitioning |
---|---|---|---|
# of Records (original data) | Unlimited | 500,000 | 65,000 |
# of Records (training partition) | Unlimited | 10,000 | 10,000 |
# of Variables (original data) | Unlimited | Unlimited | Unlimited |
# Variables (output) | Unlimited | 200 | 100 |
Sampling | |||
Worksheet | |||
# of Records (original data) | Unlimited | Unlimited | 65,000 |
# of Records (output) | Unlimited | 500,000 | 65,000 |
# of Variables (original data) | Unlimited | Unlimited | Unlimited |
# of Variables (output) | Unlimited | 200 | 100 |
# of Strata (Stratified Sampling) | Unlimited | 30 | 30 | Database |
# of Records (table) | Unlimited | 10,000,000 | 1,000,000 |
# of Records (output) | Unlimited | 500,000 | 65,000 |
# of Variables (table) | Unlimited | Unlimited | Unlimited |
# of Variables (output) | Unlimited | 200 | 100 |
# of Strata (Stratified Sampling) | Unlimited | 30 | 30 |
File System | |||
# of Files | Unlimited | N/A | 20 |
Text Mining | |||
# Documents | Unlimited | N/A | 20 |
# Characters (per document) | Unlimited | N/A | 5,000 |
# Terms in final vocabulary | Unlimited | N/A | 30 |
# Text columns | Unlimited | N/A | 1 |
Transformation | Missing Data Handling | ||
# of Records | Unlimited | 500,000 | 65,000 |
# of Variables | Unlimited | 200 | 100 |
# of Missing values | Unlimited | 500,000 | 65,000 |
Binning Continuous Data | |||
# of Records | Unlimited | 500,000 | 65,000 | # of Variables (data range) | Unlimited | 200 | 100 |
Transforming Categorical Data | # of Records | Unlimited | 500,000 | 65,000 |
# of Variables (data range) | Unlimited | 200 | 100 |
# of Distinct values | Unlimited | 30 | 30 |
# of Variables (output) | Unlimited | 30 | 30 |
Time Series Analysis | |||
# of Records | Unlimited | 10,000 | 10,000 |
Classification and Prediction | |||
Common | |||
# of Records (total) | Unlimited | 500,000 | 65,000 |
# of Records (training partition) | Unlimited | 10,000 | 10,000 |
# of Records (new data for scoring) | Unlimited | 65,000 | 65,000 |
# of Variables (data range) | Unlimited | 200 | 100 |
# of Variables (input variables) | Unlimited | 100 | 100 |
# of Distinct classes (output variable) | Unlimited | 2 | 30 |
# of Distinct values (categorical input variables) | Unlimited | 1,000 | 100 |
k-Nearest Neighbors | |||
k-Nearest neighbors | 50 | 20 | 20 |
Regression/Classification Trees | |||
# of Splits | Unlimited | 2,000 | 1,000 |
# of Nodes | Unlimited | 5,000 | 1,000 |
# of Levels | Unlimited | 1,000 | 1,000 |
# Levels in Tree Drawing | Unlimited | 7 | 7 |
Ensemble Methods | |||
# Weak learners | Unlimited | 50 | 50 |
Feature Selection | |||
# of Records | Unlimited | 10,000 | 10,000 |
# of Variables | Unlimited | 200 | 100 |
# of Distinct classes (output variable) | Unlimited | 2 | 30 |
# of Distinct values (input variables) | Unlimited | 1,000 | 100 |
Association Rules | |||
# of Transactions | Unlimited | 500,000 | 65,000 |
# of Distinct items | 5,000 | 5,000 | 1,000 |
# of Items in a Transaction | Unlimited | 200 | 100 |
# of Rules | Unlimited | 500,000 | 65,000 |
Clustering | |||
k-Means | |||
# of Records | Unlimited | 10,000 | 10,000 |
# of Variables | Unlimited | 200 | 100 |
# of Clusters | Unlimited | 20 | 20 |
# of Iterations | Unlimited | 50 | 50 |
Hierarchical | |||
# of Records | Unlimited | 4,000 | 4,000 |
# of Variables | Unlimited | 200 | 100 |
# of Clusters in a Dendrogram | Unlimited | 30 | 30 |
Size of distance matrix | Unlimited | 4,000 x 4,000 | 4,000 x 4,000 |
Charts | |||
# of Records | Unlimited | Unlimited | 65,000 |
# of Variables (original data) | Unlimited | 200 | 100 |
General | |||
Model pane | Included | Included | Included |
Big Data sampling/summarization | Included | Included | Included |
Model storage and scoring | Included | Included | Included |