update

DESCRIPTION

@@ -10,7 +10,7 @@ Authors@R:
            role = c("aut", "cre"),
            email = "flystar233@gmail.com")
 Maintainer: Tengfei Xu <flystar233@gmail.com>
-Description: Outqrf package provides a method to find the outlier in custom data by quantile random forests("Quantile Regression Forests", Journal of Machine Learning Research, 7(Jun), 983-999, 2006.). It directly calls the ranger function of the ranger package to perform data fitting and prediction.In outqrf, we also implement the evaluation of outlier prediction results.
+Description: This package provides a method to find the outlier in custom data by quantile random forests("Quantile Regression Forests", Journal of Machine Learning Research, 7(Jun), 983-999, 2006.). It directly calls the ranger function of the ranger package to perform data fitting and prediction.In outqrf, we also implement the evaluation of outlier prediction results.
 LazyData: true
 License: MIT + file LICENSE
 Depends: 
@@ -24,8 +24,9 @@ Imports:
     dplyr,
     missRanger,
     ggpubr,
+    ggplot2,
     tidyr
-URL: https://github.com/flystar233/outqrf, flystar233.github.io/outqrf
+URL: https://github.com/flystar233/outqrf
 BugReports: https://github.com/flystar233/outqrf/issues
 Suggests: 
     renv,

NAMESPACE

@@ -1,5 +1,5 @@
 # Generated by roxygen2: do not edit by hand
-
+importFrom("stats", "predict", "rnorm", "sd")
 S3method(plot,outqrf)
 export(evaluateOutliers)
 export(find_index)

R/plot.r

@@ -10,9 +10,6 @@
 #' qrf <- outqrf(irisWithOutliers)
 #' plot(qrf)
 plot.outqrf<- function(qrf) {
-    library(ggpubr)
-    library(dplyr)
-    library(tidyr)
     result_df <- data.frame()
     data <- qrf$Data
     for (i in seq_along(qrf$outMatrixs)) {
@@ -24,15 +21,15 @@ plot.outqrf<- function(qrf) {
         }
     }
     names(result_df) = names(qrf$outMatrixs)
-    result_df <- mutate(result_df,tag = "predicted")
+    result_df <- dplyr::mutate(result_df,tag = "predicted")
     numeric_features <- names(data)[sapply(data,is.numeric)]
     data <- data[numeric_features]
-    data <- mutate(data,tag = "observed")
+    data <- dplyr::mutate(data,tag = "observed")
     plot_in <-rbind(result_df,data)
-    plot_in_longer<- plot_in|>pivot_longer(!tag,names_to ="features",values_to ="value" )
-    p<- ggpaired(plot_in_longer, x="tag", y="value",
+    plot_in_longer<- plot_in|>tidyr::pivot_longer(!tag,names_to ="features",values_to ="value" )
+    p<- ggpubr::ggpaired(plot_in_longer, x="tag", y="value",
              fill="tag", palette = "jco",
              line.color = "grey", line.size =0.8, width = 0.4,short.panel.labs = FALSE)+
-             stat_compare_means(label = "p.format", paired = TRUE)+theme(legend.position = "none")+facet_wrap(~features, scales = "free")
+        ggpubr::stat_compare_means(label = "p.format", paired = TRUE)+ggplot2::theme(legend.position = "none")+ggplot2::facet_wrap(~features, scales = "free")
     return(p)
 }

inst/doc/outqrf.Rmd

@@ -0,0 +1,83 @@
+---
+title: "Using outqrf"
+author: "lucian xu"
+date: "`r Sys.Date()`"
+link-citations: true
+vignette: >
+  %\VignetteIndexEntry{Using 'outqrf'}
+  %\VignetteEncoding{UTF-8}
+  %\VignetteEngine{knitr::rmarkdown}
+output: html_document
+---
+
+```{r, include = FALSE}
+knitr::opts_chunk$set(
+  collapse = TRUE,
+  comment = "#>",
+  warning = FALSE,
+  message = FALSE,
+  fig.width = 6, 
+  fig.height = 4,
+  fig.align = "center"
+)
+```
+
+## Overview
+
+outqrf is an R package used for outlier detection. Each numeric variable is regressed onto all other variables using a quantile random forest (QRF). We use ranger to perform the fitting and prediction of quantile regression forests (QRF). Next, we will compute the rank of the observed values in the predicted results' quantiles. If the rank of the observed value exceeds the threshold, the observed value is considered an outlier.
+
+Since the same predicted value might be distributed across multiple quantiles in the predicted quantile results, this affects our location finding for the observed value. Therefore, we also used a method similar to the outForest package to compare the observed value with the 50% quantile value again to determine the final quantile result.
+
+## Installation
+
+```{r install, eval=FALSE, include=FALSE}
+# Development version
+devtools::install_github("flystar233/outqrf")
+```
+
+## Usage
+
+```{r usage, echo=TRUE}
+library(outqrf)
+#Generate data with outliers in numeric columns
+irisWithOutliers <- generateOutliers(iris, p = 0.05,seed =2024)
+# Find outliers by quantile random forest regressions
+out <- outqrf(irisWithOutliers,quantiles_type=400)
+out$outliers
+```
+
+## Evaluation on diamonds (Small Dataset)
+
+```{r Evaluation1, echo=TRUE}
+library(outqrf)
+irisWithOutliers <- generateOutliers(iris, p = 0.05,seed =2024)
+qrf <- outqrf(irisWithOutliers,quantiles_type=400)
+
+evaluateOutliers(iris,irisWithOutliers,qrf$outliers)
+```
+
+
+
+```{r Evaluation1_1, eval=FALSE}
+plot(qrf)
+```
+
+```{r Evaluation1_2, echo=FALSE}
+library(outqrf)
+irisWithOutliers <- generateOutliers(iris, p = 0.05,seed =2024)
+qrf <- outqrf(irisWithOutliers,quantiles_type=400)
+plot(qrf)
+```
+
+## Evaluation on diamonds (Big Dataset)
+
+```{r Evaluation2, echo=TRUE}
+library(outqrf)
+library(tidyverse)
+data <- diamonds|>select(price,carat,cut,color,clarity)
+data2 <- outqrf::generateOutliers(data, p = 0.001,seed =2024)
+# 108
+qrf <- outqrf(data2,num.threads=8,quantiles_type=400)
+#The process can be slow because it needs to predict the value at 400|1000 quantiles for each observation. 
+evaluateOutliers(data,data2,qrf$outliers)
+```