N1h1l1sT/DescriptiveStatsR: Descriptive Statistics, Statistical Inference and Plots, easily and for any DataFrame

This package allows you to easily create and save a wide range of Statistical analyses that can help you delve deeper into your dataset and understand it better. Works for any DataFrame, no special treatment needed - just call the function. Retrieve a table of the Categorical Variables that enumerates their values and Frequency percentage of each. A table of the Min, Q1, Mean, Median, Max, SD, IQR, Observations, NAs for each numerical variable. Tables of the Pearson and Spearman Correlations of the variables, in original order or ordered using a statistic, like PCA to make better groups. Tables of the Pearson and Spearman Correlations' p-values, so that you can differentiate between statistically significant correlations or not. These tables also come as a beautiful plot with Strong positive correlations drawn red, whilst strong negative ones, blue, and non-statistically significant are crossed out with an 'X'. The Categorical Distributions are plotted through a Bar chart. The Numerical Distributions are plotted as Histograms with a Density plot overlayed, and there is a separate Boxplot graph as well. When the Dependent Variable is Numerical, the 'Numerical Independent VS Dependent' are depicted as a scatter plot, and the 'Categorical Independent VS Dependent' are the distribution of the Dependent variable by a boxplot for each category. When the Dependent variable is Categorical, the 'Numerical Independent VS Dependent' are boxplots of the Independent's distribution for each category, and the 'Categorical Independent VS Dependent' are stacked Barplots. Lastly, for Time-Series data, you can see the data's behaviour over time.

install.packages("remotes")
remotes::install_github("N1h1l1sT/DescriptiveStatsR")