Pinned Repositories
BigDataUniversity_SPSSFundamentalsI
Training material for Predictive Modeling Fundamentals I hosted in BigDataUniversity
IBMPredictiveAnalytics.github.io
Organization page
MLlib_Pagerank
Estimating the relative importance of individuals within a social network using Spark MLlib
Model_Random_Forest
Classification and regression based on a forest of trees using random inputs, utilizing conditional inference trees as base learners.
Plot_Heatmaps
Plot spatial data on a density heatmap in SPSS Modeler
PLS
Partial least squares regression
R_Essentials_Modeler
Download R Essentials required for SPSS Modeler
R_Essentials_Statistics
Download R Essentials required for SPSS Statistics
Simple_Linear_Programming_with_CPLEX
Simple Linear Programming with CPLEX
Weather_Underground_Import
This SPSS Modeler Extension accepts a vector of airport/weather station IDs and returns various weather data points for each location.
IBM SPSS Predictive Analytics's Repositories
IBMPredictiveAnalytics/IBMPredictiveAnalytics.github.io
Organization page
IBMPredictiveAnalytics/PLS
Partial least squares regression
IBMPredictiveAnalytics/PSM
Propensity Score Matching
IBMPredictiveAnalytics/FUZZY
Perform exact or fuzzy case-control matching.
IBMPredictiveAnalytics/SPSSINC_RAKE
Calculate weights to control totals in up to ten dimensions by rim weighting, i.e. raking
IBMPredictiveAnalytics/SPSSINC_MODIFY_TABLES
Modify the appearance of pivot tables.
IBMPredictiveAnalytics/SPSSINC_PROCESS_FILES
Apply a file of syntax to a set of data files
IBMPredictiveAnalytics/SPSSINC_TRANS
Apply a Python function to case data.
IBMPredictiveAnalytics/STATS_MAKE_CASES
A conversion of the custom dialog to make a dataset of random data according to any of the distributions supported in the rv.* functions plus the triangular distribution.
IBMPredictiveAnalytics/STATS_RELIMP
Relative importance measures for regression
IBMPredictiveAnalytics/krr
Fits kernel ridge regression models using the Python sklearn.kernel_ridge.KernelRidge class to estimate a kernel ridge regression of a dependent variable on one or more independent variables with specified model hyperparameters, or selection of hyperparameter values over a specified grid of values via crossvalidation by also using the sklearn.model_selection.GridSearchCV class.
IBMPredictiveAnalytics/Naive_Bayes_Classifier
Naive Bayes classification with optional predictor selection Description: This extension provides a user interface for the NAIVEBAY ES command. It fits the Naive Bayes classification model for a catego rical dependent variable. You can specify whether all available predi ctors are used or whether the procedure selects the best predictors. The extension can also be used for predictor selection without classi fication.
IBMPredictiveAnalytics/SPSSINC_GETURI_DATA
Open an SPSS, Excel, SAS, or Stata dataset from a web url.
IBMPredictiveAnalytics/SPSSINC_PROCESS_FILESORIG
This procedure applies a file of syntax to each of a grou p of selected files. It defines file handles and macros for use in th e syntax file, and provides various options for handling Viewer and d ata output.
IBMPredictiveAnalytics/STATS_CONVERT_PYTHON
This extension command convert SPSS syntax files that contain BEGIN PROGRAM blocks of Python 2 code or Python 2 files to Python 3.
IBMPredictiveAnalytics/STATS_EXTENSION_REPORT
IBMPredictiveAnalytics/STATS_IMBALANCED
This extension improves performance with imbalanced datasets.
IBMPredictiveAnalytics/STATS_LINEAR_ELASTIC_NET_REGRESSION
Fits linear elastic net regression models using Python sklearn classes.
IBMPredictiveAnalytics/STATS_LINEAR_LASSO_REGRESSION
Fits linear lasso regression models using Python sklearn classes.
IBMPredictiveAnalytics/STATS_LINEAR_RIDGE_REGRESSION
Fits linear ridge regression models using Python sklearn classes.
IBMPredictiveAnalytics/STATS_MAKE_CATALOG
Build a dataset of variable information from multiple datasets.
IBMPredictiveAnalytics/STATS_NORMALITY_ANALYSIS
Univariate and muiltivariate tests and plots for normality of a set of variables
IBMPredictiveAnalytics/STATS_NTILE_ANALYSIS
This procedure, also known in the literature as decile analysis, produces a table and charts that group the predicted probabilities from a classification procedure such as logistic regression, trees, and SVM into ntiles in order to better understand their distribution and to assist in using these for formulating decision rules.
IBMPredictiveAnalytics/STATS_PACKAGE_INSTALL
It installs Python or R modules needed by a begin program block or an extension command whose install did not install them. This will make this process easier than the current means and reduce the difficulty of installing packages that need items from PyPI or CRAN. It is not uncommon for CRAN packages not to list all their dependencies.
IBMPredictiveAnalytics/STATS_POPULATION_DESCRIPTIVES
Descriptive Statistics for a Population.
IBMPredictiveAnalytics/STATS_PREPROCESS
Perform selected transformations to modify variable distribut ion properties
IBMPredictiveAnalytics/STATS_PSM
IBMPredictiveAnalytics/STATS_TABLE_CALC
Calculate with pivot table cells
IBMPredictiveAnalytics/STATS_TEXTANALYSIS
This procedure provides tools for working with text variables. It provides frequencies, sentiment analysis, searching, and spelling checks.
IBMPredictiveAnalytics/STATS_UPDATE