feat(Samyssmile#23): Prepare

lib/src/main/java/de/edux/data/handler/DropIncompleteRecordsHandler.java

@@ -1,19 +1,24 @@
 package de.edux.data.handler;
 
+import java.util.ArrayList;
 import java.util.List;
 
 public class DropIncompleteRecordsHandler implements IIncompleteRecordsHandler {
   @Override
   public List<String[]> getCleanedDataset(List<String[]> dataset) {
-    List<String[]> cleanedDataset =
+    List<String[]> filteredList =
         dataset.stream().filter(this::containsOnlyCompletedFeatures).toList();
 
-    if (cleanedDataset.size() < dataset.size() * 0.5) {
+    if (filteredList.size() < dataset.size() * 0.5) {
       throw new RuntimeException(
           "More than 50% of the records will be dropped with this IncompleteRecordsHandlerStrategy. "
               + "Consider using another IncompleteRecordsHandlerStrategy or handle this exception.");
     }
 
+    List<String[]> cleanedDataset = new ArrayList<>();
+    for (String[] item : filteredList) {
+      cleanedDataset.add(item);
+    }
     return cleanedDataset;
   }
 

lib/src/main/java/de/edux/data/provider/DataPostProcessor.java

@@ -3,6 +3,7 @@
 import de.edux.functions.imputation.ImputationStrategy;
 
 import java.util.List;
+import java.util.Optional;
 
 public interface DataPostProcessor {
     DataPostProcessor normalize();
@@ -18,4 +19,10 @@ public interface DataPostProcessor {
     DataProcessor split(double splitRatio);
 
 
+    public abstract Optional<Integer> getIndexOfColumn(String columnName);
+
+    public abstract String[] getColumnDataOf(String columnName);
+
+    public abstract String[] getColumnNames();
+
 }

lib/src/main/java/de/edux/data/reader/CSVIDataReader.java

@@ -13,7 +13,7 @@
 
 public class CSVIDataReader implements IDataReader {
 
-    public List<String[]> readFile(File file, char separator) {
+    public List<String[]> readFile(File file, char separator ) {
         CSVParser customCSVParser = new CSVParserBuilder().withSeparator(separator).build();
         List<String[]> result;
         try(CSVReader reader = new CSVReaderBuilder(

lib/src/test/java/de/edux/data/handler/DropIncompleteRecordsHandlerTest.java

@@ -0,0 +1,35 @@
+package de.edux.data.handler;
+
+import de.edux.data.provider.SeabornDataProcessor;
+import de.edux.data.provider.SeabornProvider;
+import org.junit.jupiter.api.Test;
+
+import java.io.File;
+import java.net.URL;
+import java.util.Optional;
+
+class DropIncompleteRecordsHandlerTest {
+    private static final boolean SHUFFLE = true;
+    private static final boolean SKIP_HEADLINE = true;
+    private static final EIncompleteRecordsHandlerStrategy INCOMPLETE_RECORD_HANDLER_STRATEGY = EIncompleteRecordsHandlerStrategy.DROP_RECORDS;
+    private static final double TRAIN_TEST_SPLIT_RATIO = 0.7;
+    private static final String CSV_FILE_PATH = "testdatasets/seaborn-penguins/penguins.csv";
+    private SeabornProvider seabornProvider;
+
+    @Test
+    void shouldReturnColumnData() {
+        URL url = DropIncompleteRecordsHandlerTest.class.getClassLoader().getResource(CSV_FILE_PATH);
+        if (url == null) {
+            throw new IllegalStateException("Cannot find file: " + CSV_FILE_PATH);
+        }
+        File csvFile = new File(url.getPath());
+        var seabornDataProcessor = new SeabornDataProcessor();
+        var dataset = seabornDataProcessor.loadDataSetFromCSV(csvFile, ',', true, true, INCOMPLETE_RECORD_HANDLER_STRATEGY);
+        seabornDataProcessor.normalize(dataset);
+        Optional<Integer> indexOfSpecies =  seabornDataProcessor.getIndexOfColumn("species");
+        String[] speciesData = seabornDataProcessor.getColumnDataOf("species");
+
+        assert indexOfSpecies.isPresent();
+        assert speciesData.length > 0;
+    }
+}