Offers useful functions to perform day-to-day data manipulation operations, data quality checks and post modelling statistical checks. One can effortlessly change class of a number of variables to factor, remove duplicate observations from the data, create deciles of a variable, perform data quality checks for continuous (integer or numeric), categorical (factor) and date variables, and compute goodness of fit measures such as auc for statistical models. The functions are consistent for objects of class 'data.frame' and 'data.table', which is an enhanced 'data.frame' implemented in the package 'data.table'.
|Date of publication||2015-03-27 23:46:22|
|Maintainer||Akash Jain <firstname.lastname@example.org>|
accuracy: Confusion matrix and overall accuracy of predicted binary...
actvspred: Comparison of actual and predicted linear response
auc: Area under curve of predicted binary response
contents: Basic summary of the data
decile: Create deciles of a variable
dqcategorical: Data quality check of categorical variables
dqcontinuous: Data quality check of continuous variables
dqdate: Data quality check of date variables
factorise: Change the class of variables to factor
gini: Gini coefficient of a distribution
imputemiss: Impute missing values in a variable
iv: Information value of an independent variable in predicting a...
ks: Kolmogorov-Smirnov statistic for predicted binary response
mape: Compute mean absolute percentage error
outliers: Identify outliers in a variable
pentile: Create pentiles of a variable
randomise: Order the rows of a data randomly
rmdupkey: Remove observations with duplicate keys from data
rmdupobs: Remove duplicate observations from data
splitdata: Split modeling data into test and train set