version 0.1.0

DESCRIPTION

@@ -0,0 +1,20 @@
+Package: AnalysisLin
+Type: Package
+Title: Exploratory Data Analysis
+Version: 0.1.0
+Authors@R: person("Zhiwei","Lin", ,"zhiweilin27@gmail.com",role = c("aut", "cre"))
+Description: A quick and effective data exploration toolkit. It provides essential features, including a descriptive statistics table for a quick overview of your dataset, interactive distribution plots to visualize variable patterns, Principal Component Analysis for dimensionality reduction and feature analysis, missing value imputation methods, and correlation analysis.
+License: MIT + file LICENSE
+Encoding: UTF-8
+RoxygenNote: 7.2.3
+Suggests: knitr, rmarkdown
+VignetteBuilder: knitr
+Date: 2024-01-22
+Imports: Hmisc, ggplot2, plotly, stats, caret, htmltools, DT, magrittr,
+        RANN
+NeedsCompilation: no
+Packaged: 2024-01-26 11:55:25 UTC; zhiweilin
+Author: Zhiwei Lin [aut, cre]
+Maintainer: Zhiwei Lin <zhiweilin27@gmail.com>
+Repository: CRAN
+Date/Publication: 2024-01-27 12:50:05 UTC

LICENSE

@@ -0,0 +1,2 @@
+YEAR: 2023
+COPYRIGHT HOLDER: AnalysisLin authors

MD5

@@ -0,0 +1,26 @@
+f9b1d4d72fcbc2c971807e74195bce45 *DESCRIPTION
+c3b8c9073f1743068fe2f3c547e0c7ff *LICENSE
+b4a5434c562c8648e792d55ce0c19a43 *NAMESPACE
+a21c7c3ae3d9cef58c217e9c01471458 *R/corr_cluster.R
+c795b4327737a284ed5b0e9e538337d1 *R/corr_matrix.R
+2ae5d3c3b5701c193836a947e46ff52c *R/desc_stat.R
+4480be1d80c42d0095e10c25cadc738d *R/dist_plot.R
+bef1da2b503fd18c4fe44c9b0f1c8fcf *R/missing_impute.R
+c76a25d5f8ec69252ec26fe40c60a18c *R/missing_plot.R
+b2c914b0c2cdbf980e023f2a467415fb *R/pca.R
+bf77b7d497df5b503c425a31821d6467 *build/vignette.rds
+3e14a6e66f147c0cc49fcde8400887c3 *inst/doc/AnalysisLin-vignette.R
+02db1fe4ba7be8ab5fd4f922cc97b98c *inst/doc/AnalysisLin-vignette.Rmd
+fedd95f8a1758c247a42f0736fb7a725 *inst/doc/AnalysisLin-vignette.html
+b536d83b0a9a652f0971a2f6650d79c3 *man/bar_plot.Rd
+a6dbd5a2712c7dcc0386d9970d3900f9 *man/corr_cluster.Rd
+d1dabe155968e77e243559542b2e792b *man/corr_matrix.Rd
+525d244af067b7dcec62433aa5eada61 *man/dens_plot.Rd
+6d0b039d7f09cca6791802831abe8f06 *man/desc_stat.Rd
+8657757094ffe333142e955295e48eff *man/hist_plot.Rd
+d835c5994c7558b867019ca7e75b0096 *man/impute_missing.Rd
+f851eeecafee5f1a3fca9c498b245226 *man/missing_values_plot.Rd
+fe4ce64e7660b6fdbfa1c3dcdb2f0e9d *man/pca.Rd
+144145166e2238c299c254cb1d91e887 *man/pie_plot.Rd
+a40bad185149fad8840d64d9b34cee04 *man/qq_plot.Rd
+02db1fe4ba7be8ab5fd4f922cc97b98c *vignettes/AnalysisLin-vignette.Rmd

NAMESPACE

@@ -0,0 +1,32 @@
+# Generated by roxygen2: do not edit by hand
+
+export(bar_plot)
+export(corr_cluster)
+export(corr_matrix)
+export(dens_plot)
+export(desc_stat)
+export(hist_plot)
+export(impute_missing)
+export(missing_values_plot)
+export(pca)
+export(pie_plot)
+export(qq_plot)
+import(RANN)
+import(ggplot2)
+import(htmltools)
+import(magrittr)
+import(stats)
+importFrom(DT,datatable)
+importFrom(DT,formatStyle)
+importFrom(DT,styleInterval)
+importFrom(Hmisc,rcorr)
+importFrom(caret,preProcess)
+importFrom(grDevices,colors)
+importFrom(htmltools,tagList)
+importFrom(plotly,add_text)
+importFrom(plotly,add_trace)
+importFrom(plotly,colorbar)
+importFrom(plotly,ggplotly)
+importFrom(plotly,layout)
+importFrom(plotly,plot_ly)
+importFrom(plotly,style)

R/corr_cluster.R

@@ -0,0 +1,26 @@
+#' @title Correlation Clustering
+#' @description
+#'   This function performs hierarchical clustering on a correlation matrix, providing insights into the relationships between variables.
+#'   It generates a dendrogram visualizing the hierarchical clustering of variables based on their correlation patterns.
+#'
+#' @param data Input data frame.
+#' @param type The type of correlation to be computed. It can be "pearson", "kendall", or "spearman".
+#' @param method The method for hierarchical clustering. It can be "complete", "single", "average", "ward.D", "ward.D2", "mcquitty", "median", or "centroid".
+#' @param hclust_method The hierarchical clustering method. It can be "complete", "single", "average", "ward.D", "ward.D2", "mcquitty", "median", or "centroid".
+#'
+#' @return 
+#'  A dendrogram visualizing the hierarchical clustering of variables based on the correlation matrix.
+#'
+#' @examples
+#' data(mtcars)
+#' corr_cluster(data = mtcars, type = 'pearson', method = 'complete')
+#'
+#' @importFrom Hmisc rcorr
+#' @import stats
+#' @export
+corr_cluster <- function(data, type = 'pearson', method = 'complete', hclust_method = NULL) {
+  corr <- Hmisc::rcorr(as.matrix(data), type = type)$r
+  dist_matrix <- as.dist(1 - abs(corr))
+  hc <- hclust(dist_matrix, method = method)
+  plot(hc, hang = -1, main = "Feature Distance")
+}

R/corr_matrix.R

@@ -0,0 +1,93 @@
+#' @title Correlation Matrix
+#' @description
+#'   Column 1: Row names representing Variable 1 in the correlation test.
+#'   
+#'   Column 2: Column names representing Variable 2 in the correlation test.
+#'   
+#'   Column 3: The correlation coefficients quantifying the strength and direction of the relationship.
+#'   
+#'   Column 4: The p-values associated with the correlations, indicating the statistical significance
+#'             of the observed relationships. Lower p-values suggest stronger evidence against the null hypothesis.
+#' 
+#' The table provides valuable insights into the relationships between variables, helping to identify
+#' statistically significant correlations.
+#'   
+#' @param data Input dataset.
+#' @param type Pearson or Spearman correlation, default is Pearson.
+#' @param corr_plot Generate a correlation matrix plot, default is false.
+#' @param sig.level Significant level. Default is 0.01.
+#' @param highlight Highlight p-value(s) that is less than sig.level, default is FALSE
+#' 
+#' @return A data frame which contains row names, column names, correlation coefficients, and p-values.
+#' @return A plot of the correlation if corrplot is set to be true.
+#'
+#' @examples
+#' data(mtcars)
+#' corr_matrix(mtcars, type = 'pearson')
+#' @importFrom DT datatable formatStyle styleInterval
+#' @importFrom htmltools tagList
+#' @importFrom Hmisc rcorr
+#' @importFrom plotly plot_ly
+#' @importFrom plotly layout
+#' @importFrom plotly colorbar
+#' 
+#' @export
+corr_matrix <- function(data, type = 'pearson', corr_plot = FALSE, sig.level = 0.01,highlight=FALSE) {
+  result <- list()
+
+  cormat <- Hmisc::rcorr(as.matrix(data), type = type)$r
+
+  pmat <- Hmisc::rcorr(as.matrix(data), type = type)$P
+  pmat[is.na(pmat)] <- 0
+
+  ut <- lower.tri(cormat)
+  data <- data.frame(
+    row = rownames(cormat)[row(cormat)[ut]],
+    column = rownames(cormat)[col(cormat)[ut]],
+    cor = cormat[ut],
+    p = pmat[ut]
+  )
+
+  table1 <- DT::datatable(
+    data,
+    extensions = "Buttons",
+    caption = "Correlation Table",
+    options = list(
+      dom = 'Blfrtip',
+      buttons = c('copy', 'csv', 'excel', 'pdf'),
+      paging = TRUE,
+      searching = FALSE,
+      ordering = TRUE,
+      scrollX = TRUE
+    ),
+    style = 'default',
+    class = 'table-striped table-bordered'
+  )
+
+  if (highlight) {
+    table1 <- table1 %>%
+      formatStyle(
+        columns = c("p"),
+        valueColumns = c("p"),
+        backgroundColor = styleInterval(0.05, c('yellow','transparent'))
+      )
+  }
+
+
+
+  cormat[upper.tri(cormat)] <- NA
+  pmat[upper.tri(cormat)] <- NA
+  cormat[lower.tri(cormat)] <- ifelse(pmat[lower.tri(cormat)] < sig.level,cormat[lower.tri(cormat)], NA)
+  plot <- plot_ly(z = cormat, x = rownames(cormat), y = colnames(cormat),, type = "heatmap", colorscale = "RdBu", reversescale = TRUE) %>%
+    layout(title = "Correlation Heatmap",
+           xaxis = list(title = "Variables", showgrid = FALSE),
+           yaxis = list(title = "Variables", showgrid = FALSE))%>%
+    colorbar(zmin = -1, zmax = 1) 
+  result <- htmltools::tagList()
+  result$table <- table1
+  result$plot <- plot
+  return(if (corr_plot) result else table1)
+}
+
+
+