Printing out the metrics after you perform a cluster and added a true…

…/false condition for shuffling

R/Cluster.R

@@ -13,12 +13,12 @@
 #' @param cutoff A cutoff value
 #' @param iterations The number of iterations
 #' @return A data.frame of the clusters.
-opti_cluster <- function(sparse_matrix, cutoff, iterations) {
+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 <- MatrixToOpiMatrixCluster(index_one_list, index_two_list, value_list, cutoff,
-                                                       iterations)
+                                                       iterations, shuffle)
   df <- t(read.table(text = clustering_output_string,
                      sep = "\t", header = TRUE))
   df <- data.frame(df[-1, ])

R/RcppExports.R

@@ -1,7 +1,7 @@
 # Generated by using Rcpp::compileAttributes() -> do not edit by hand
 # Generator token: 10BE3573-1514-4C36-9D1C-5A225CD40393
 
-MatrixToOpiMatrixCluster <- function(xPosition, yPosition, data, cutoff, iterations = 2L) {
-    .Call(`_Opticluster_MatrixToOpiMatrixCluster`, xPosition, yPosition, data, cutoff, iterations)
+MatrixToOpiMatrixCluster <- function(xPosition, yPosition, data, cutoff, iterations = 2L, shuffle = TRUE) {
+    .Call(`_Opticluster_MatrixToOpiMatrixCluster`, xPosition, yPosition, data, cutoff, iterations, shuffle)
 }
 

src/ClusterCommand.cpp

@@ -17,16 +17,16 @@ ClusterCommand::~ClusterCommand() {
 /// @param optiMatrix
 /// @return
 std::string ClusterCommand::runOptiCluster(OptiMatrix *optiMatrix) {
-    std::string clusterOutputData;
+    std::string clusterMetrics;
     std::string sensFile;
     std::string outStep;
     std::string clusterMatrixOutput;
     if (!cutOffSet) {
-        clusterOutputData += ("\nYou did not set a cutoff, using 0.03.\n");
+        clusterMetrics += ("\nYou did not set a cutoff, using 0.03.\n");
         cutoff = 0.05;
     }
 
-    clusterOutputData += ("\nClustering " + distfile + "\n");
+    clusterMetrics += ("\nClustering " + distfile + "\n");
 
     ClusterMetric *metric = nullptr;
     metricName = "mcc";
@@ -57,11 +57,11 @@ std::string ClusterCommand::runOptiCluster(OptiMatrix *optiMatrix) {
     // string distfile = columnfile;
     // if (format == "phylip") { distfile = phylipfile; }
     //
-    // sensFile += "label\tcutoff\ttp\ttn\tfp\tfn\tsensitivity\tspecificity\tppv\tnpv\tfdr\taccuracy\tmcc\tf1score\n";
-    // clusterOutputData += (
-    //     "\n\niter\ttime\tlabel\tnum_otus\tcutoff\ttp\ttn\tfp\tfn\tsensitivity\tspecificity\tppv\tnpv\tfdr\taccuracy\tmcc\tf1score\n");
-    // outStep +=
-    //         "iter\ttime\tlabel\tnum_otus\tcutoff\ttp\ttn\tfp\tfn\tsensitivity\tspecificity\tppv\tnpv\tfdr\taccuracy\tmcc\tf1score\n";
+    sensFile += "label\tcutoff\ttp\ttn\tfp\tfn\tsensitivity\tspecificity\tppv\tnpv\tfdr\taccuracy\tmcc\tf1score\n";
+    clusterMetrics += (
+        "\n\niter\ttime\tlabel\tnum_otus\tcutoff\ttp\ttn\tfp\tfn\tsensitivity\tspecificity\tppv\tnpv\tfdr\taccuracy\tmcc\tf1score\n");
+    outStep +=
+            "iter\ttime\tlabel\tnum_otus\tcutoff\ttp\ttn\tfp\tfn\tsensitivity\tspecificity\tppv\tnpv\tfdr\taccuracy\tmcc\tf1score\n";
 
     bool printHeaders = true;
 
@@ -74,22 +74,22 @@ std::string ClusterCommand::runOptiCluster(OptiMatrix *optiMatrix) {
         int iters = 0;
         double listVectorMetric = 0; //worst state
         double delta = 1;
-        // long long numBins;
+        long long numBins;
         double tp, tn, fp, fn;
-        vector<double> results;
-        cluster.initialize(listVectorMetric, false, initialize);
-        // results = cluster.getStats(tp, tn, fp, fn);
-        // numBins = cluster.getNumBins();
-        // clusterOutputData += ("0\t0\t" + std::to_string(cutoff) + "\t" + std::to_string(numBins) + "\t" +
-        //                       std::to_string(cutoff) + "\t" + std::to_string(tp) + "\t" + std::to_string(tn) + "\t" +
-        //                       std::to_string(fp) + "\t" + std::to_string(fn) + "\t");
-        // outStep += "0\t0\t" + std::to_string(cutoff) + "\t" + std::to_string(numBins) + "\t" + std::to_string(cutoff) +
-        //         "\t" + std::to_string(tp) + '\t' + std::to_string(tn) + '\t' + std::to_string(fp) + '\t' +
-        //         std::to_string(fn) + '\t';
-        // for (double result : results) {
-        //     clusterOutputData += (std::to_string(result) + "\t");
-        //     outStep += std::to_string(result) + "\t";
-        // }
+        vector<double> stats;
+        cluster.initialize(listVectorMetric, canShuffle, initialize);
+        stats = cluster.getStats(tp, tn, fp, fn);
+        numBins = cluster.getNumBins();
+        clusterMetrics += ("0\t0\t" + std::to_string(cutoff) + "\t" + std::to_string(numBins) + "\t" +
+                              std::to_string(cutoff) + "\t" + std::to_string(tp) + "\t" + std::to_string(tn) + "\t" +
+                              std::to_string(fp) + "\t" + std::to_string(fn) + "\t");
+        outStep += "0\t0\t" + std::to_string(cutoff) + "\t" + std::to_string(numBins) + "\t" + std::to_string(cutoff) +
+                "\t" + std::to_string(tp) + '\t' + std::to_string(tn) + '\t' + std::to_string(fp) + '\t' +
+                std::to_string(fn) + '\t';
+        for (double result : stats) {
+            clusterMetrics += (std::to_string(result) + "\t");
+            outStep += std::to_string(result) + "\t";
+        }
         //m->mothurOutEndLine();
         // outStep += "\n";
         // Stable Metric -> Keep the data stable, to prevent errors (rounding errors)
@@ -104,27 +104,27 @@ std::string ClusterCommand::runOptiCluster(OptiMatrix *optiMatrix) {
             delta = std::abs(oldMetric - listVectorMetric);
             iters++;
 
-            // results = cluster.getStats(tp, tn, fp, fn);
-            // numBins = cluster.getNumBins();
-
-            // clusterOutputData += (std::to_string(iters) + "\t" + std::to_string(time(nullptr) - start) + "\t" +
-            //                       std::to_string(cutoff) + "\t" + std::to_string(numBins) + "\t" +
-            //                       std::to_string(cutoff) + "\t" + std::to_string(tp) + "\t" + std::to_string(tn) + "\t"
-            //                       + std::to_string(fp) + "\t" + std::to_string(fn) + "\t");
-            // outStep += (std::to_string(iters) + "\t" + std::to_string(time(nullptr) - start) + "\t" +
-            //             std::to_string(cutoff) + "\t" + std::to_string(numBins) + "\t" + std::to_string(cutoff) + "\t")
-            //         + std::to_string(tp) + '\t' + std::to_string(tn) + '\t' + std::to_string(fp) + '\t' +
-            //         std::to_string(fn) +
-            //         '\t';
-            // for (double result : results) {
-            //     clusterOutputData += (std::to_string(result) + "\t");
-            //     outStep += std::to_string(result) + "\t";
-            // }
-            // outStep += "\n";
+            stats = cluster.getStats(tp, tn, fp, fn);
+            numBins = cluster.getNumBins();
+
+            clusterMetrics += (std::to_string(iters) + "\t" + std::to_string(time(nullptr) - start) + "\t" +
+                                  std::to_string(cutoff) + "\t" + std::to_string(numBins) + "\t" +
+                                  std::to_string(cutoff) + "\t" + std::to_string(tp) + "\t" + std::to_string(tn) + "\t"
+                                  + std::to_string(fp) + "\t" + std::to_string(fn) + "\t");
+            outStep += (std::to_string(iters) + "\t" + std::to_string(time(nullptr) - start) + "\t" +
+                        std::to_string(cutoff) + "\t" + std::to_string(numBins) + "\t" + std::to_string(cutoff) + "\t")
+                    + std::to_string(tp) + '\t' + std::to_string(tn) + '\t' + std::to_string(fp) + '\t' +
+                    std::to_string(fn) +
+                    '\t';
+            for (double result : stats) {
+                clusterMetrics += (std::to_string(result) + "\t");
+                outStep += std::to_string(result) + "\t";
+            }
+            outStep += "\n";
         }
         ListVector *list = nullptr;
 
-        // clusterOutputData += "\n\n";
+        clusterMetrics += "\n\n";
         list = cluster.getList();
         //
         if (printHeaders) {
@@ -133,13 +133,14 @@ std::string ClusterCommand::runOptiCluster(OptiMatrix *optiMatrix) {
         } else { list->setPrintedLabels(printHeaders); }
         clusterMatrixOutput = list->print(listFile);
         delete list;
-        // results = cluster.getStats(tp, tn, fp, fn);
-        //
-        // sensFile += std::to_string(cutoff) + '\t' + std::to_string(cutoff) + '\t' + std::to_string(tp) + '\t' +
-        //         std::to_string(tn) + '\t' +
-        //         std::to_string(fp) + '\t' + std::to_string(fn) + '\t';
-        // for (double result : results) { sensFile + std::to_string(result) + '\t'; }
-    }
+        stats = cluster.getStats(tp, tn, fp, fn);
+
+        sensFile += std::to_string(cutoff) + '\t' + std::to_string(cutoff) + '\t' + std::to_string(tp) + '\t' +
+                std::to_string(tn) + '\t' +
+                std::to_string(fp) + '\t' + std::to_string(fn) + '\t';
+        for (double result : stats) { sensFile + std::to_string(result) + '\t'; }
+        Rcpp::Rcout << "Metrics for the current cluster:\n\n " << sensFile << "\n\n" << clusterMetrics << "\n\n";
+     }
     delete matrix;
     return clusterMatrixOutput;
 }

src/MothurDependencies/ClusterCommand.h

@@ -20,6 +20,7 @@
 #include <map>
 #include "OptiMatrix.h"
 #include "ListVector.h"
+#include <Rcpp.h>
 #include "Metrics/accuracy.hpp"
 #include "Metrics/f1score.hpp"
 #include "Metrics/fdr.hpp"
@@ -53,6 +54,7 @@ class ClusterCommand {
 	ClusterCommand() {}
 	~ClusterCommand();
 	bool SetMaxIterations(const int iterations) {maxIters = iterations; return maxIters == iterations;}
+	bool SetOpticlusterRandomShuffle(const bool shuffle) {canShuffle = shuffle; return canShuffle;}
 	std::string runOptiCluster(OptiMatrix*);
 
 
@@ -72,6 +74,7 @@ class ClusterCommand {
 	bool print_start;
 	time_t start;
 	unsigned long loops;
+	bool canShuffle;
 	vector<string> outputNames;
 };
 

src/RcppExports.cpp

@@ -11,8 +11,8 @@ Rcpp::Rostream<false>& Rcpp::Rcerr = Rcpp::Rcpp_cerr_get();
 #endif
 
 // MatrixToOpiMatrixCluster
-std::string MatrixToOpiMatrixCluster(const std::vector<int>& xPosition, const std::vector<int>& yPosition, const std::vector<double>& data, const double cutoff, const int iterations);
-RcppExport SEXP _Opticluster_MatrixToOpiMatrixCluster(SEXP xPositionSEXP, SEXP yPositionSEXP, SEXP dataSEXP, SEXP cutoffSEXP, SEXP iterationsSEXP) {
+std::string MatrixToOpiMatrixCluster(const std::vector<int>& xPosition, const std::vector<int>& yPosition, const std::vector<double>& data, const double cutoff, const int iterations, const bool shuffle);
+RcppExport SEXP _Opticluster_MatrixToOpiMatrixCluster(SEXP xPositionSEXP, SEXP yPositionSEXP, SEXP dataSEXP, SEXP cutoffSEXP, SEXP iterationsSEXP, SEXP shuffleSEXP) {
 BEGIN_RCPP
     Rcpp::RObject rcpp_result_gen;
     Rcpp::RNGScope rcpp_rngScope_gen;
@@ -21,15 +21,16 @@ BEGIN_RCPP
     Rcpp::traits::input_parameter< const std::vector<double>& >::type data(dataSEXP);
     Rcpp::traits::input_parameter< const double >::type cutoff(cutoffSEXP);
     Rcpp::traits::input_parameter< const int >::type iterations(iterationsSEXP);
-    rcpp_result_gen = Rcpp::wrap(MatrixToOpiMatrixCluster(xPosition, yPosition, data, cutoff, iterations));
+    Rcpp::traits::input_parameter< const bool >::type shuffle(shuffleSEXP);
+    rcpp_result_gen = Rcpp::wrap(MatrixToOpiMatrixCluster(xPosition, yPosition, data, cutoff, iterations, shuffle));
     return rcpp_result_gen;
 END_RCPP
 }
 
 RcppExport SEXP run_testthat_tests(SEXP);
 
 static const R_CallMethodDef CallEntries[] = {
-    {"_Opticluster_MatrixToOpiMatrixCluster", (DL_FUNC) &_Opticluster_MatrixToOpiMatrixCluster, 5},
+    {"_Opticluster_MatrixToOpiMatrixCluster", (DL_FUNC) &_Opticluster_MatrixToOpiMatrixCluster, 6},
     {"run_testthat_tests", (DL_FUNC) &run_testthat_tests, 1},
     {NULL, NULL, 0}
 };

src/main.cpp

@@ -14,11 +14,12 @@
 //[[Rcpp::export]]
 std::string MatrixToOpiMatrixCluster(const std::vector<int> &xPosition,
                         const std::vector<int> &yPosition, const std::vector<double> &data, const double cutoff,
-                        const int iterations = 2)
+                        const int iterations = 2, const bool shuffle = true)
 {
     OptimatrixAdapter adapter(cutoff);
     const auto optiMatrix = adapter.ConvertToOptimatrix(xPosition,yPosition,data);
     auto* command = new ClusterCommand();
+    command ->SetOpticlusterRandomShuffle(shuffle);
     command->SetMaxIterations(iterations);
     return command->runOptiCluster(optiMatrix);
 }

tests/testthat/test-test-opticluster.R

@@ -1,7 +1,7 @@
 test_that("Clustering returns proper results", {
   expected_df <- readRDS(test_path("extdata","df_test_file.RDS"))
   matrix <- readRDS(test_path("extdata","matrix_data.RDS"))
-  df <- Opticluster::opti_cluster(matrix, 0.2, 2)
+  df <- Opticluster::opti_cluster(matrix, 0.2, 2, FALSE)
   df$exists <- do.call(paste0, df) %in% do.call(paste0, expected_df)
   expect_equal(class(df), "data.frame")
   expect_true(all(df$exists == TRUE))