Dev

.gitignore

@@ -41,7 +41,7 @@ pip-log.txt
 pip-delete-this-directory.txt
 
 # CMakeCheck list via Clion
-CMakeLists.txt
+src/CMakeLists.txt
 
 # Unit test / coverage reports
 htmlcov/
@@ -192,3 +192,4 @@ fabric.properties
 # idea folder, uncomment if you don't need it
 .idea
 src/.DS_Store
+/.vscode

NAMESPACE

@@ -1,5 +1,5 @@
 useDynLib(Opticluster, .registration=TRUE)
 importFrom(Rcpp, evalCpp)
 importFrom("utils", "read.table")
-export(opti_cluster)
 export(cluster)
+export(opti_cluster)

R/Cluster.R

@@ -11,51 +11,79 @@
 #' @export
 #' @param sparse_matrix A Sparse Matrix.
 #' @param cutoff A cutoff value
+#' @param count_table A table of names and the given abundance per group.
 #' @param iterations The number of iterations
-#' @param shuffle a boolean to determine whether or not you want to shuffle the data before you cluster
-#' @return A data.frame of the clusters.
-opti_cluster <- function(sparse_matrix, cutoff, iterations, shuffle = TRUE) {
-  index_one_list <- sparse_matrix@i
-  index_two_list <- sparse_matrix@j
-  value_list <- sparse_matrix@x
-  clustering_output_string_list <- MatrixToOpiMatrixCluster(index_one_list, index_two_list, value_list, cutoff,
-                                                       iterations, shuffle)
-  clustering_output_string <- clustering_output_string_list[1]
-  clustering_metric <- clustering_output_string_list[2]
-  clustering_metric_2 <- clustering_output_string_list[3]
-  df_cluster_metrics <- (read.table(text = clustering_metric,
-                     sep = "\t", header = TRUE))
-  df_other_cluster_metrics <-  (read.table(text = clustering_metric_2,
-                     sep = "\t", header = TRUE))
-
-  df_cluster <- t(read.table(text = clustering_output_string,
-                     sep = "\t", header = TRUE))
-  df_cluster <- data.frame(df_cluster[-1, ])
-
-  colnames(df_cluster)[1] <- "cluster"
-
-  opticluster_data <- list(cluster = df_cluster,
-                           cluster_metrics = df_cluster_metrics,
-                           other_cluster_metrics = df_other_cluster_metrics)
+#' @param shuffle a boolean to determine whether or
+#'  not you want to shuffle the data before you cluster
+#' @param simularity_matrix are you using a simularity matrix or distance matrix
+#' @return A data.frame of the cluster and cluster metrics.
+opti_cluster <- function(sparse_matrix, cutoff, count_table,
+                         iterations = 100, shuffle = TRUE,
+                         simularity_matrix = FALSE) {
+  count_table <- validate_count_table(count_table)
+  cluster_dfs <- MatrixToOpiMatrixCluster(
+    sparse_matrix@i,
+    sparse_matrix@j,
+    sparse_matrix@x,
+    cutoff,
+    count_table,
+    iterations,
+    shuffle,
+    simularity_matrix
+  )
+  opticluster_data <- list(
+    abundance = cluster_dfs[[1]],
+    cluster = cluster_dfs[[4]],
+    cluster_metrics = cluster_dfs[[3]],
+    other_cluster_metrics = cluster_dfs[[2]]
+  )
 
   return(opticluster_data)
 }
 
 
-
 #' Opticluster Description
 #'
 #' Detailed description of the function.
 #'
 #' @export
 #' @param sparse_matrix A Sparse Matrix.
-#' @param cutoff A cutoff value
-#' @param method The type of cluster you wish to conduct. There are four different types:
-#' furthest, nearest, average, weighted.
+#' @param cutoff A cutoff value.
+#' @param method The type of cluster you wish to conduct;
+#'  furthest, nearest, average, weighted.
+#' @param count_table A table of names and the given abundance per group.
+#' @param simularity_matrix are you using a simularity matrix or
+#'  distance matrix.
 #' @return A string of the given cluster.
-cluster <- function(sparse_matrix, cutoff, method)
-{
+cluster <- function(sparse_matrix, cutoff, method,
+                    count_table, simularity_matrix = FALSE) {
+  df <- ClassicCluster(
+    sparse_matrix@i, sparse_matrix@j,
+    sparse_matrix@x, cutoff, method,
+    validate_count_table(count_table),
+    simularity_matrix
+  )
+  return(list(
+    abundance = df[[1]],
+    cluster = df[[2]]
+  ))
+}
 
-  return (ClassicCluster(sparse_matrix@i, sparse_matrix@j,
-                           sparse_matrix@x, cutoff, method))
+
+#' Opticluster Description
+#'
+#' Detailed description of the function.
+#'
+#' @export
+#' @param count_table_df The count table,
+#' which contains all your abundance information for each sequence.
+#' @return Validated count table.
+validate_count_table <- function(count_table_df) {
+  if (ncol(count_table_df) > 2) {
+    return(count_table_df)
+  }
+  totals <- count_table_df$total
+  count_table_df <- cbind(count_table_df, totals)
+  names(count_table_df)[3] <- "no_group"
+  count_table_df[[1]] <- as.character(count_table_df[[1]])
 }

R/RcppExports.R

@@ -1,15 +1,15 @@
 # Generated by using Rcpp::compileAttributes() -> do not edit by hand
 # Generator token: 10BE3573-1514-4C36-9D1C-5A225CD40393
 
-WritePhylipFile <- function(xPosition, yPosition, data, cutoff, saveLocation) {
-    invisible(.Call(`_Opticluster_WritePhylipFile`, xPosition, yPosition, data, cutoff, saveLocation))
+WritePhylipFile <- function(xPosition, yPosition, data, cutoff, countTable, saveLocation) {
+    invisible(.Call(`_Opticluster_WritePhylipFile`, xPosition, yPosition, data, cutoff, countTable, saveLocation))
 }
 
-MatrixToOpiMatrixCluster <- function(xPosition, yPosition, data, cutoff, maxIterations = 100L, shuffle = TRUE) {
-    .Call(`_Opticluster_MatrixToOpiMatrixCluster`, xPosition, yPosition, data, cutoff, maxIterations, shuffle)
+MatrixToOpiMatrixCluster <- function(xPosition, yPosition, data, cutoff, countTable, maxIterations = 100L, shuffle = TRUE, isSim = FALSE) {
+    .Call(`_Opticluster_MatrixToOpiMatrixCluster`, xPosition, yPosition, data, cutoff, countTable, maxIterations, shuffle, isSim)
 }
 
-ClassicCluster <- function(xPosition, yPosition, data, cutoff, method) {
-    .Call(`_Opticluster_ClassicCluster`, xPosition, yPosition, data, cutoff, method)
+ClassicCluster <- function(xPosition, yPosition, data, cutoff, method, countTable, isSimularity) {
+    .Call(`_Opticluster_ClassicCluster`, xPosition, yPosition, data, cutoff, method, countTable, isSimularity)
 }
 

src/Adapters/CountTableAdapter.h

@@ -0,0 +1,32 @@
+//
+// Created by gregj on 8/27/2024.
+//
+
+#ifndef COUNTTABLEADAPTER_H
+#define COUNTTABLEADAPTER_H
+#include <Rcpp.h>
+#include <vector>
+#include <string>
+#include <unordered_map>
+#include <algorithm>
+
+class CountTableAdapter {
+public:
+    CountTableAdapter() = default;
+    bool CreateDataFrameMap(const Rcpp::DataFrame& countTable);
+    // Going to ensure that each count_table atleast has a group
+    // And if there is no count table inputted, I will create a base one.
+    double FindAbundanceBasedOnGroup(const std::string& group, const std::string& sampleName) const;
+    double FindTotalAbundance(const std::string& sampleName) const;
+    std::string GetNameByIndex(int) const;
+    std::vector<double> GetColumnByName (const std::string& name) const;
+    std::vector<std::string> GetGroups() const;
+private:
+    std::vector<std::string> sampleNames;
+    std::unordered_map<std::string, std::vector<double>> dataFrameMap;
+    std::vector<std::string> groups;
+};
+
+
+
+#endif //COUNTTABLEADAPTER_H

src/Adapters/DataFrameAdapter.h

@@ -0,0 +1,19 @@
+//
+// Created by Gregory Johnson on 8/29/24.
+//
+
+#ifndef DATAFRAMEADAPTER_H
+#define DATAFRAMEADAPTER_H
+#include <Rcpp.h>
+#include <unordered_map>
+#include <vector>
+#include <string>
+
+class DataFrameAdapter {
+public:
+    static Rcpp::DataFrame UnorderedMapToDataFrame(const std::unordered_map<std::string, std::vector<std::string>> &map);
+};
+
+
+
+#endif //DATAFRAMEADAPTER_H

src/Adapters/MatrixAdapter.h

@@ -5,15 +5,17 @@
 #ifndef MATRIXADAPTER_H
 #define MATRIXADAPTER_H
 #include <unordered_map>
+
+#include "CountTableAdapter.h"
 #include "../MothurDependencies/ReadPhylipMatrix.h"
 
 
 class MatrixAdapter {
 public:
     MatrixAdapter(const std::vector<int> &iIndexes, const std::vector<int> &jIndexes,
-        const std::vector<double> &dataValues, double cutoff);
+        const std::vector<double> &dataValues, double cutOff, bool isSimularity, CountTableAdapter table);
     ~MatrixAdapter() = default;
-    ReadPhylipMatrix* ReadPhylipFile(const std::string& path);
+    ReadPhylipMatrix* ReadPhylipFile(const std::string& path) const;
     SparseDistanceMatrix* CreateSparseMatrix();
     ListVector* GetListVector() const {return phylipReader->getListVector();}
     SparseDistanceMatrix* GetSpareDistanceMatrix() const {return phylipReader->getDMatrix();}
@@ -25,11 +27,11 @@ class MatrixAdapter {
 
     ReadPhylipMatrix* phylipReader;
     SparseDistanceMatrix* spareDistanceMatrix = nullptr;
+    CountTableAdapter countTable;
     std::vector<int> xPosition;
     std::vector<int> yPosition;
     std::vector<double> data;
     std::vector<std::string> matrixNames;
-    double cutoff;
 };
 
 

src/Adapters/OptimatrixAdapter.h

@@ -14,6 +14,8 @@
 #include <unordered_map>
 #include <sstream>
 
+#include "../RowData.h"
+
 
 class OptimatrixAdapter {
     ///Closeness is the data represntation, it is a vector of sets that tells us which values are closes to it ->
@@ -27,6 +29,7 @@ class OptimatrixAdapter {
     }
     OptiMatrix* ConvertToOptimatrix(const std::vector<int>
         &xPosition, const std::vector<int>& yPosition, const std::vector<double>& data);
+    OptiMatrix* ConvertToOptimatrix(const std::vector<RowData>&, bool);
     std::vector<std::set<long long>> GetCloseness() {return closeness;}
     std::vector<std::string> GetNameList() {return nameList;}
     std::vector<std::string> GetSingletons() {return singletons;}

src/AverageLinkage.cpp

@@ -2,18 +2,18 @@
 // Created by Gregory Johnson on 6/17/24.
 //
 
+#include <utility>
+
 #include "MothurDependencies/AverageLinkage.h"
 
 /* This class implements the average UPGMA, average neighbor clustering algorithm */
 
 /***********************************************************************/
 
-AverageLinkage::AverageLinkage(RAbundVector* rav, ListVector* lv, SparseDistanceMatrix* dm, float c, std::string s, float a) :
-Cluster(rav, lv, dm, c, s, a)
-{
-    saveRow = -1;
-    saveCol = -1;
-}
+AverageLinkage::AverageLinkage(RAbundVector* rav, ListVector* lv, SparseDistanceMatrix* dm,
+const float c, std::string s, const float a) :
+Cluster(rav, lv, dm, c, std::move(s), a),saveRow(-1), saveCol(-1), rowBin(-1), colBin(-1),totalBin(-1)
+{}
 
 
 /***********************************************************************/
@@ -27,14 +27,15 @@ std::string AverageLinkage::getTag() {
 //This function updates the distance based on the average linkage method.
 bool AverageLinkage::updateDistance(PDistCell& colCell, PDistCell& rowCell) {
     if ((saveRow != smallRow) || (saveCol != smallCol)) {
-        rowBin = rabund->get(smallRow);
-        colBin = rabund->get(smallCol);
+        rowBin = rabund->get(static_cast<int>(smallRow));
+        colBin = rabund->get(static_cast<int>(smallCol));
         totalBin = rowBin + colBin;
         saveRow = smallRow;
         saveCol = smallCol;
     }
 
-    colCell.dist = (colBin * colCell.dist + rowBin * rowCell.dist) / totalBin;
+    colCell.dist = (static_cast<float>(colBin) * colCell.dist + static_cast<float>(rowBin) * rowCell.dist) /
+        static_cast<float>(totalBin);
 
     return(true);
 }