pairwise_corr: Pairwise Correlation

In DKundnani/FeatureCorr: Finding associations through prime feature and pairwise correlations

Pairwise Correlation

Description

Get Pair wise correlations for a given list of features

Usage

pairwise_corr(df,featurelist, featuregroup,visorder,corrmeth, clustno=NULL)

Arguments

df	numerical dataframe with rows having series of values for a single feature
featurelist	list of features in the sequence as it occurs in the Dataframe
featuregroup	(optional)list of TRUE/FALSE values for features to be observed vs rest of the features(ordering/clustering is disabled)
visorder	The ordering method of the correlation matrix.'original' for original order ,'AOE' for the angular order of the eigenvectors, 'FPC' for the first principal component order, 'hclust'(default) for the hierarchical clustering order, 'alphabet' for alphabetical order.
corrmeth	Correlation method used. 'pearson' or 'spearman' (default='pearson')
clustno	number of clusters expected to be drawn on the plot (default = NULL)

Examples

corr_pair<-pairwise_corr(df=logTCGA40,featurelist=rownames(logTCGA40), visorder="hclust", clustno=2)
featgroup<-grepl( "RNASE",rownames(logTCGA40)) #optional, a set of TRUE/FALSE of length featurelist
corr_pair<-pairwisecorr <- pairwise_corr(df=logTCGA40,featurelist=rownames(logTCGA40),
                                         featuregroup=featgroup)

DKundnani/FeatureCorr documentation built on April 24, 2022, 7:59 p.m.