Cache graph data on creation

readme.md

@@ -159,8 +159,10 @@ Structure:
 Graph and Data files are serialized binaries of a Java object containing the weigthed bipartite graph representation of a
 Sample Plate, along with the necessary metadata for matching and results output. Making them requires a Cell Sample file 
 (to construct a list of correct sequence pairs for checking the accuracy of BiGpairSEQ simulations) and a 
-Sample Plate file (to construct the associated occupancy graph). These files can be several gigabytes in size.
+Sample Plate file (to construct the associated occupancy graph).
-Writing them to a file lets us generate a graph and its metadata once, then use it for multiple different BiGpairSEQ simulations.
+
+These files can be several gigabytes in size. Writing them to a file lets us generate a graph and its metadata once,
+then use it for multiple different BiGpairSEQ simulations.
 
 Options for creating a Graph and Data file:
 * The Cell Sample file to use
@@ -172,7 +174,11 @@ portable data format may be implemented in the future. The tricky part is encodi
 ---
 
 #### Matching Results Files 
-Matching results files consist of the results of a BiGpairSEQ matching simulation.
+Matching results files consist of the results of a BiGpairSEQ matching simulation. Making them requires a Graph and 
+Data file. To save file I/O time, the data from the most recent Graph and Data file read or generated is cached
+by the simulator. Subsequent BiGpairSEQ simulations run with the same input filename will use the cached version
+rather than reading in again from disk.
+
 Files are in CSV format. Rows are sequence pairings with extra relevant data. Columns are pairing-specific details.
 Metadata about the matching simulation is included as comments. Comments are preceded by `#`.
 
@@ -239,7 +245,7 @@ slightly less time than the simulation itself. Real elapsed time from start to f
 ## TODO
 
 * ~~Try invoking GC at end of workloads to reduce paging to disk~~ DONE
-* Hold graph data in memory until another graph is read-in? ~~ABANDONED~~ UNABANDONED
+* Hold graph data in memory until another graph is read-in? ~~ABANDONED~~ ~~UNABANDONED~~ DONE
   * ~~*No, this won't work, because BiGpairSEQ simulations alter the underlying graph based on filtering constraints. Changes would cascade with multiple experiments.*~~
   * Might have figured out a way to do it, by taking edges out and then putting them back into the graph. This may actually be possible. If so, awesome.
 * See if there's a reasonable way to reformat Sample Plate files so that wells are columns instead of rows. 

src/main/java/GraphDataObjectReader.java

@@ -13,6 +13,8 @@ public class GraphDataObjectReader {
             BufferedInputStream fileIn = new BufferedInputStream(new FileInputStream(filename));
                 ObjectInputStream in = new ObjectInputStream(fileIn))
         {
+            System.out.println("Reading graph data from file. This may take some time");
+            System.out.println("File I/O time is not included in results");
             data = (GraphWithMapData) in.readObject();
         } catch (FileNotFoundException | ClassNotFoundException ex) {
             ex.printStackTrace();

src/main/java/GraphDataObjectWriter.java

@@ -18,8 +18,11 @@ public class GraphDataObjectWriter {
 
     public void writeDataToFile() {
         try (BufferedOutputStream bufferedOut = new BufferedOutputStream(new FileOutputStream(filename));
+
              ObjectOutputStream out = new ObjectOutputStream(bufferedOut);
         ){
+            System.out.println("Writing graph and occupancy data to file. This may take some time.");
+            System.out.println("File I/O time is not included in results.");
             out.writeObject(data);
         } catch (IOException ex) {
             ex.printStackTrace();

src/main/java/GraphModificationFunctions.java

@@ -4,6 +4,7 @@ import org.jgrapht.graph.SimpleWeightedGraph;
 import java.util.ArrayList;
 import java.util.List;
 import java.util.Map;
+import java.util.Set;
 
 public abstract class GraphModificationFunctions {
 
@@ -18,9 +19,11 @@ public abstract class GraphModificationFunctions {
                 Integer weight = (int) graph.getEdgeWeight(e);
                 Integer[] edge = {source, target, weight};
                 removedEdges.add(edge);
-                graph.removeEdge(e);
             }
         }
+        for (Integer[] edge : removedEdges) {
+            graph.removeEdge(edge[0], edge[1]);
+        }
         return removedEdges;
     }
 
@@ -41,9 +44,11 @@ public abstract class GraphModificationFunctions {
                 Integer weight = (int) graph.getEdgeWeight(e);
                 Integer[] edge = {source, target, weight};
                 removedEdges.add(edge);
-                graph.removeEdge(e);
             }
         }
+        for (Integer[] edge : removedEdges) {
+            graph.removeEdge(edge[0], edge[1]);
+        }
         return removedEdges;
     }
 
@@ -66,9 +71,11 @@ public abstract class GraphModificationFunctions {
                 Integer intWeight = (int) graph.getEdgeWeight(e);
                 Integer[] edge = {source, target, intWeight};
                 removedEdges.add(edge);
-                graph.removeEdge(e);
             }
         }
+        for (Integer[] edge : removedEdges) {
+            graph.removeEdge(edge[0], edge[1]);
+        }
         return removedEdges;
     }
 

src/main/java/InteractiveInterface.java

@@ -75,7 +75,6 @@ public class InteractiveInterface {
         assert filename != null;
         CellFileWriter writer = new CellFileWriter(filename, sample);
         writer.writeCellsToFile();
-        System.gc();
     }
 
     //Output a CSV of sample plate
@@ -187,7 +186,6 @@ public class InteractiveInterface {
             System.out.println("Writing Sample Plate to file");
             writer.writePlateFile();
             System.out.println("Sample Plate written to file: " + filename);
-            System.gc();
         }
     }
 
@@ -232,11 +230,11 @@ public class InteractiveInterface {
             GraphWithMapData data = Simulator.makeGraph(cells, plate, true);
             assert filename != null;
             GraphDataObjectWriter dataWriter = new GraphDataObjectWriter(filename, data);
-            System.out.println("Writing graph and occupancy data to file. This may take some time.");
-            System.out.println("File I/O time is not included in results.");
             dataWriter.writeDataToFile();
             System.out.println("Graph and Data file written to: " + filename);
-            System.gc();
+            BiGpairSEQ.setGraph(data);
+            BiGpairSEQ.setGraphFilename(filename);
+            System.out.println("Graph and Data file " + filename + " cached.");
         }
     }
 
@@ -277,11 +275,9 @@ public class InteractiveInterface {
         assert graphFilename != null;
         //check if this is the same graph we already have in memory.
         GraphWithMapData data;
-        if(!(graphFilename.equals(BiGpairSEQ.getGraphFilename()) || BiGpairSEQ.getGraph() == null)) {
+        if(!(graphFilename.equals(BiGpairSEQ.getGraphFilename())) || BiGpairSEQ.getGraph() == null) {
             BiGpairSEQ.clearGraph();
             //read object data from file
-            System.out.println("Reading graph data from file. This may take some time");
-            System.out.println("File I/O time is not included in results");
             GraphDataObjectReader dataReader = new GraphDataObjectReader(graphFilename);
             data = dataReader.getData();
             //set new graph in memory and new filename
@@ -300,7 +296,6 @@ public class InteractiveInterface {
         System.out.println("Writing results to file");
         writer.writeResultsToFile();
         System.out.println("Results written to file: " + filename);
-        System.gc();
     }
 
     ///////

src/main/java/META-INF/MANIFEST.MF

@@ -0,0 +1,3 @@
+Manifest-Version: 1.0
+Main-Class: BiGpairSEQ
+

src/main/java/Simulator.java

@@ -249,13 +249,13 @@ public class Simulator {
         double pairingErrorRate = (double) falseCount / (trueCount + falseCount);
         BigDecimal pairingErrorRateTrunc = new BigDecimal(pairingErrorRate, mc);
         //get list of well concentrations
-        List<Integer> wellPopulations = Arrays.asList(data.getWellConcentrations());
+        Integer[] wellPopulations = data.getWellConcentrations();
         //make string out of concentrations list
         StringBuilder populationsStringBuilder = new StringBuilder();
-        populationsStringBuilder.append(wellPopulations.remove(0).toString());
+        populationsStringBuilder.append(wellPopulations[0].toString());
-        for(Integer i: wellPopulations){
+        for(int i = 1; i < wellPopulations.length; i++){
             populationsStringBuilder.append(", ");
-            populationsStringBuilder.append(i.toString());
+            populationsStringBuilder.append(wellPopulations[i].toString());
         }
         String wellPopulationsString = populationsStringBuilder.toString();
         //total simulation time