Update Preprocessing/OneHotEncoder.eclCo-authored-by: Lily <lilix@g.clemson.edu>

Author: vzeufack

Preprocessing/LabelEncoder.ecl

@@ -56,7 +56,6 @@ EXPORT LabelEncoder := MODULE
     RETURN Result;
   ENDMACRO;
 
-<<<<<<< HEAD
 /**
   * Builds a lookup table that maps each category of a feature to a unique number.
   * Each category is assigned its index in the category set.
@@ -88,8 +87,6 @@ EXPORT LabelEncoder := MODULE
     RETURN LabelEncoder.MapCategoriesToValues(key);
   ENDMACRO;
 
-=======
->>>>>>> e119eb11b4b077b1c2a25099f826d07112ea1d23
   /**
     * Replaces each categorical value in the data with its index in the key.
     * Every unknown category (not in the key) is replaced by -1.

Preprocessing/OneHotEncoder.ecl

@@ -4,7 +4,7 @@
 
 /**
   * For categorical features within a dataset, 
-  * this module creates new binary and numeric features. The new binary features only takes a value * of 0 or 1 indicating the true value of the category.
+  * this module creates new binary and numeric features. The new binary features only takes a value of 0 or 1 indicating the true value of the category.
   *
   * @param baseData: DATASET(NumericField), default = DATASET([], NumericField).
   *   <p> Data from which categories are extracted for encoding/decoding.
@@ -67,17 +67,8 @@ EXPORT OneHotEncoder(DATASET(NumericField) baseData = DATASET([], NumericField),
     END;
 
     featureNumbers := DATASET(SET(baseData(id = 1), number), numberLayout);
-<<<<<<< HEAD
     Result := PROJECT(featureNumbers, extract(LEFT));
     RETURN Result; 
-=======
-    //display warning if some of the featureIds provided does not exists in baseData
-    assertFeatIdsValid := IF(EXISTS(featureIdDS-featureNumbers), 
-                          STD.System.Log.addWorkunitWarning('Inexisting featureIds found!', 1));  
-
-    Result := PROJECT(featureNumbers, extract(LEFT));
-    RETURN WHEN(Result, assertFeatIdsValid); 
->>>>>>> e119eb11b4b077b1c2a25099f826d07112ea1d23
   END;
 
   /**
@@ -270,4 +261,4 @@ EXPORT OneHotEncoder(DATASET(NumericField) baseData = DATASET([], NumericField),
     Result := ROLLUP(groupedData, GROUP, convert(LEFT, ROWS(LEFT)));
     RETURN Result;
   END;
-END;
+END;

Preprocessing/README.md

@@ -5,9 +5,6 @@ Machine Learning Preprocessing Bundle for HPCC Systems
 - OneHotEncoder
 - MinMaxScaler
 - StandardScaler
-<<<<<<< HEAD
 - Normaliz
 - Split
 - StratifiedSplit
-=======
->>>>>>> e119eb11b4b077b1c2a25099f826d07112ea1d23

Preprocessing/StandardScaler.ecl

@@ -26,7 +26,7 @@ EXPORT StandardScaler(DATASET(NumericField) baseData = DATASET([], NumericField)
   SHARED numberLayout := Preprocessing.Types.numberLayout;
 
   /**
-    * Computes averages and stdevs for each feature in baseData.
+    * Computes averages and standard deviation (stdevs) for each feature in baseData.
     *
     * @return avgandStdevByFeature: DATASET(KeyLayout).
     */

Preprocessing/Test/Functional/RunFunctionalTests.ecl

@@ -9,9 +9,6 @@ $.TestLabelEncoder.RunLabelEncoderTests;
 $.TestOneHotEncoder.RunOneHotEncoderTests;
 $.TestStandardScaler.RunStandardScalerTests;
 $.TestMinMaxScaler.RunMinMaxScalerTests;
-<<<<<<< HEAD
 $.TestNormalize.RunNormalizTests;
 $.TestSplit.RunSplitTests;
-=======
->>>>>>> e119eb11b4b077b1c2a25099f826d07112ea1d23
 $.TestUtils.RunUtilsTests;

Preprocessing/Test/Functional/TestUtils/TestDatasetComparator/RunDatasetComparatorTests.ecl

@@ -18,11 +18,4 @@ $.TestAreEqualRows.TestEqualRows();
 $.TestAreEqualRows.TestDifferentRows();
 
 $.TestCompare.TestEqualData();
-<<<<<<< HEAD
-$.TestCompare.TestRowDifference();
-=======
-//$.TestCompare.TestEqualNumericFields();
-$.TestCompare.TestRowDifference();
-$.TestCompare.TestDifferentRecord();
->>>>>>> e119eb11b4b077b1c2a25099f826d07112ea1d23
 $.TestCompare.TestRowDifference();

Preprocessing/Types.ecl

@@ -6,16 +6,10 @@ IMPORT $.^.Types as MLCTypes;
 
 t_FieldNumber := MLCTypes.t_FieldNumber;
 t_FieldReal := MLCTypes.t_FieldReal;
-<<<<<<< HEAD
 t_RecordID := MLCTypes.t_RecordID;
 
 /**
   * Record structures for Preprocessing modules.
-=======
-
-/**
-  * Record structures for Preprocessing modules
->>>>>>> e119eb11b4b077b1c2a25099f826d07112ea1d23
   */
 EXPORT Types := MODULE
   //record structure for storing REAL values
@@ -28,18 +22,13 @@ EXPORT Types := MODULE
     t_FieldNumber number;
   END;
 
-<<<<<<< HEAD
   //record structure for storing ids
   EXPORT idLayout := RECORD
     t_RecordID id;
   END;
 
   /**
     * record structures for OneHotEncoder.
-=======
-  /**
-    * record structures for OneHotEncoder
->>>>>>> e119eb11b4b077b1c2a25099f826d07112ea1d23
     */
   EXPORT OneHotEncoder := MODULE
     //record structure for key.
@@ -57,11 +46,7 @@ EXPORT Types := MODULE
   END;
 
   /**
-<<<<<<< HEAD
     * record structures for StandardScaler.
-=======
-    * record structures for StandardScaler
->>>>>>> e119eb11b4b077b1c2a25099f826d07112ea1d23
     */
   EXPORT StandardScaler := MODULE
     //record structure for storing features' average and standard deviation
@@ -72,13 +57,9 @@ EXPORT Types := MODULE
     END;
   END;
 
-<<<<<<< HEAD
   /**
     * record structures for MinMaxScaler.
     */
-=======
-  //record structures for MinMaxScaler
->>>>>>> e119eb11b4b077b1c2a25099f826d07112ea1d23
   EXPORT MinMaxScaler := MODULE
     //record structure for storing a feature's min and max value
     EXPORT FeatureMinMax := RECORD
@@ -95,7 +76,6 @@ EXPORT Types := MODULE
       DATASET(FeatureMinMax) minsMaxs;
     END;
   END;
-<<<<<<< HEAD
 
   /**
     * record structures for normalize function.
@@ -107,6 +87,4 @@ EXPORT Types := MODULE
       t_FieldReal value;
     END;
   END;
-=======
->>>>>>> e119eb11b4b077b1c2a25099f826d07112ea1d23
 END;

Preprocessing/Utils/DatasetComparator/Compare.ecl

@@ -48,18 +48,12 @@ EXPORT Compare(dta1, dta2) := FUNCTIONMACRO
                      PROJECT(ROWS(LEFT), XF(LEFT)));
 
   #UNIQUENAME(comparisonResult)
-<<<<<<< HEAD
   /*%comparisonResult% := IF(%comp%.AreOfSameType(dta1, dta2),
                            IF(COUNT(dta1) = COUNT(dta2), 
                            IF(%loopResult%[1].isSameRow, 0, %loopResult%[1].cnt - 1), -2), -1);*/
 
   %comparisonResult% := IF(COUNT(dta1) = COUNT(dta2), 
                            IF(%loopResult%[1].isSameRow, 0, %loopResult%[1].cnt - 1), 
                            -2);
-=======
-  %comparisonResult% := IF(%comp%.AreOfSameType(dta1, dta2),
-                        IF(COUNT(dta1) = COUNT(dta2), 
-                         IF(%loopResult%[1].isSameRow, 0, %loopResult%[1].cnt - 1), -2), -1);
->>>>>>> e119eb11b4b077b1c2a25099f826d07112ea1d23
   RETURN %comparisonResult%;
 ENDMACRO;