(#258) CSVDataFrameParser handles null values, Stacktrace printed for…

… error in QueryEngine, and Macrobase -> MacroBase

core/src/main/java/edu/stanford/futuredata/macrobase/pipeline/BasicBatchPipeline.java

@@ -7,12 +7,9 @@
 import edu.stanford.futuredata.macrobase.analysis.summary.aplinear.APLOutlierSummarizer;
 import edu.stanford.futuredata.macrobase.analysis.summary.BatchSummarizer;
 import edu.stanford.futuredata.macrobase.analysis.summary.fpg.FPGrowthSummarizer;
-import edu.stanford.futuredata.macrobase.analysis.summary.ratios.ExplanationMetric;
-import edu.stanford.futuredata.macrobase.analysis.summary.ratios.GlobalRatioMetric;
-import edu.stanford.futuredata.macrobase.analysis.summary.ratios.RiskRatioMetric;
 import edu.stanford.futuredata.macrobase.datamodel.DataFrame;
 import edu.stanford.futuredata.macrobase.datamodel.Schema;
-import edu.stanford.futuredata.macrobase.util.MacrobaseException;
+import edu.stanford.futuredata.macrobase.util.MacroBaseException;
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
 
@@ -75,7 +72,7 @@ public BasicBatchPipeline (PipelineConfig conf) {
         numThreads = conf.get("numThreads", Runtime.getRuntime().availableProcessors());
     }
 
-    public Classifier getClassifier() throws MacrobaseException {
+    public Classifier getClassifier() throws MacroBaseException {
         switch (classifierType.toLowerCase()) {
             case "percentile": {
                 PercentileClassifier classifier = new PercentileClassifier(metric);
@@ -93,12 +90,12 @@ public Classifier getClassifier() throws MacrobaseException {
                 return classifier;
             }
             default : {
-                throw new MacrobaseException("Bad Classifier Type");
+                throw new MacroBaseException("Bad Classifier Type");
             }
         }
     }
 
-    public BatchSummarizer getSummarizer(String outlierColumnName) throws MacrobaseException {
+    public BatchSummarizer getSummarizer(String outlierColumnName) throws MacroBaseException {
         switch (summarizerType.toLowerCase()) {
             case "fpgrowth": {
                 FPGrowthSummarizer summarizer = new FPGrowthSummarizer();
@@ -120,7 +117,7 @@ public BatchSummarizer getSummarizer(String outlierColumnName) throws MacrobaseE
                 return summarizer;
             }
             default: {
-                throw new MacrobaseException("Bad Summarizer Type");
+                throw new MacroBaseException("Bad Summarizer Type");
             }
         }
     }

core/src/main/java/edu/stanford/futuredata/macrobase/pipeline/CubePipeline.java

@@ -12,7 +12,7 @@
 import edu.stanford.futuredata.macrobase.datamodel.DataFrame;
 import edu.stanford.futuredata.macrobase.datamodel.Schema;
 import edu.stanford.futuredata.macrobase.ingest.CSVDataFrameWriter;
-import edu.stanford.futuredata.macrobase.util.MacrobaseException;
+import edu.stanford.futuredata.macrobase.util.MacroBaseException;
 import java.io.PrintWriter;
 import java.util.ArrayList;
 import java.util.HashMap;
@@ -143,17 +143,17 @@ public APLExplanation results() throws Exception {
         return explanation;
     }
 
-    private Map<String, Schema.ColType> getColTypes() throws MacrobaseException {
+    private Map<String, Schema.ColType> getColTypes() throws MacroBaseException {
         Map<String, Schema.ColType> colTypes = new HashMap<>();
         colTypes.put(countColumn, Schema.ColType.DOUBLE);
         switch (classifierType) {
             case "meanshift":
             case "arithmetic": {
                 colTypes.put(meanColumn
-                        .orElseThrow(() -> new MacrobaseException("mean column not present in config")),
+                        .orElseThrow(() -> new MacroBaseException("mean column not present in config")),
                     Schema.ColType.DOUBLE);
                 colTypes.put(stdColumn
-                        .orElseThrow(() -> new MacrobaseException("std column not present in config")),
+                        .orElseThrow(() -> new MacroBaseException("std column not present in config")),
                     Schema.ColType.DOUBLE);
                 return colTypes;
             }
@@ -166,33 +166,33 @@ private Map<String, Schema.ColType> getColTypes() throws MacrobaseException {
             case "predicate": {
                 if (isStrPredicate) {
                     colTypes.put(metric.orElseThrow(
-                        () -> new MacrobaseException("metric column not present in config")),
+                        () -> new MacroBaseException("metric column not present in config")),
                         Schema.ColType.STRING);
                 } else {
                     colTypes.put(metric.orElseThrow(
-                        () -> new MacrobaseException("metric column not present in config")),
+                        () -> new MacroBaseException("metric column not present in config")),
                         Schema.ColType.DOUBLE);
                 }
                 return colTypes;
             }
             case "raw": {
                 colTypes.put(meanColumn.orElseThrow(
-                    () -> new MacrobaseException("mean column not present in config")),
+                    () -> new MacroBaseException("mean column not present in config")),
                     Schema.ColType.DOUBLE);
             }
             default:
-                throw new MacrobaseException("Bad Classifier Name");
+                throw new MacroBaseException("Bad Classifier Name");
         }
     }
 
-    private CubeClassifier getClassifier() throws MacrobaseException {
+    private CubeClassifier getClassifier() throws MacroBaseException {
         switch (classifierType) {
             case "arithmetic": {
                 ArithmeticClassifier classifier =
                     new ArithmeticClassifier(countColumn, meanColumn.orElseThrow(
-                        () -> new MacrobaseException("mean column not present in config")),
+                        () -> new MacroBaseException("mean column not present in config")),
                         stdColumn.orElseThrow(
-                            () -> new MacrobaseException("std column not present in config")));
+                            () -> new MacroBaseException("std column not present in config")));
                 classifier.setPercentile(cutoff);
                 classifier.setIncludeHigh(includeHi);
                 classifier.setIncludeLow(includeLo);
@@ -210,12 +210,12 @@ private CubeClassifier getClassifier() throws MacrobaseException {
                 if (isStrPredicate) {
                     return new PredicateCubeClassifier(countColumn,
                         metric.orElseThrow(
-                            () -> new MacrobaseException("metric column not present in config")),
+                            () -> new MacroBaseException("metric column not present in config")),
                         predicateStr, strCutoff);
                 }
                 return new PredicateCubeClassifier(countColumn,
                     metric.orElseThrow(
-                        () -> new MacrobaseException("metric column not present in config")),
+                        () -> new MacroBaseException("metric column not present in config")),
                     predicateStr, cutoff);
             }
 
@@ -224,11 +224,11 @@ private CubeClassifier getClassifier() throws MacrobaseException {
                 return new RawClassifier(
                     countColumn,
                     meanColumn.orElseThrow(
-                        () -> new MacrobaseException("mean column not present in config"))
+                        () -> new MacroBaseException("mean column not present in config"))
                 );
             }
             default:
-                throw new MacrobaseException("Bad Classifier Name");
+                throw new MacroBaseException("Bad Classifier Name");
         }
     }
 
@@ -238,9 +238,9 @@ private APLSummarizer getSummarizer(CubeClassifier classifier) throws Exception
                 APLMeanSummarizer summarizer = new APLMeanSummarizer();
                 summarizer.setCountColumn(countColumn);
                 summarizer.setMeanColumn(meanColumn.orElseThrow(
-                        () -> new MacrobaseException("mean column not present in config")));
+                        () -> new MacroBaseException("mean column not present in config")));
                 summarizer.setStdColumn(stdColumn.orElseThrow(
-                        () -> new MacrobaseException("std column not present in config")));
+                        () -> new MacroBaseException("std column not present in config")));
                 summarizer.setAttributes(attributes);
                 summarizer.setMinSupport(minSupport);
                 summarizer.setMinStdDev(minRatioMetric);

core/src/main/java/edu/stanford/futuredata/macrobase/pipeline/PipelineUtils.java

@@ -5,7 +5,7 @@
 import edu.stanford.futuredata.macrobase.datamodel.Schema;
 import edu.stanford.futuredata.macrobase.ingest.CSVDataFrameParser;
 import edu.stanford.futuredata.macrobase.ingest.RESTDataFrameLoader;
-import edu.stanford.futuredata.macrobase.util.MacrobaseException;
+import edu.stanford.futuredata.macrobase.util.MacroBaseException;
 
 import java.util.Map;
 import java.util.List;
@@ -51,13 +51,13 @@ public static DataFrame loadDataFrame(
             DataFrame df = loader.load();
             return df;
         } else {
-            throw new MacrobaseException("Unsupported URI");
+            throw new MacroBaseException("Unsupported URI");
         }
     }
 
     public static Pipeline createPipeline(
             PipelineConfig conf
-    ) throws MacrobaseException {
+    ) throws MacroBaseException {
         String pipelineName = conf.get("pipeline");
         switch (pipelineName) {
             case "BasicBatchPipeline": {
@@ -67,7 +67,7 @@ public static Pipeline createPipeline(
                 return new CubePipeline(conf);
             }
             default: {
-                throw new MacrobaseException("Bad Pipeline");
+                throw new MacroBaseException("Bad Pipeline");
             }
         }
     }

docs/source/user-guide/parameters.md

@@ -1,11 +1,11 @@
 # Configuration Parameters
 
-This document describes the important parameters in Macrobase that
+This document describes the important parameters in MacroBase that
 affect its behavior.
 
 ## Workload-specific parameters
 
-We first describe workload-specific parameters. Macrobase will throw an exception if 
+We first describe workload-specific parameters. MacroBase will throw an exception if 
 parameters that don't have a default value aren't specified.
 
 <table class="table">
@@ -48,7 +48,7 @@ reciprocal of the value for each point (i.e. 1/value).
   <td>(none)</td>
   <td>
   Query used to specify input data source. Can be used to restrict
-the rows or columns Macrobase needs to look at. For example,
+the rows or columns MacroBase needs to look at. For example,
 <code>SELECT tabl1.col1, tabl1.col2, tabl2.col3 FROM tabl1, tabl2 WHERE tabl1.id == tabl2.id;</code>
   </td>
 </tr>

lib/readme.md

@@ -1,4 +1,4 @@
-## Macrobase core operator library
+## MacroBase core operator library
 
 Basic operators for explaining differences in 
 high-dimensional data using categorical attributes.

lib/src/main/java/edu/stanford/futuredata/macrobase/analysis/MBFunction.java

@@ -1,7 +1,7 @@
 package edu.stanford.futuredata.macrobase.analysis;
 
 import edu.stanford.futuredata.macrobase.datamodel.DataFrame;
-import edu.stanford.futuredata.macrobase.util.MacrobaseException;
+import edu.stanford.futuredata.macrobase.util.MacroBaseException;
 import java.lang.reflect.InvocationTargetException;
 import java.util.Arrays;
 import java.util.HashMap;
@@ -49,12 +49,12 @@ protected MBFunction(String columnName) {
      * Call this method to to invoke the function and generate the output column that results from
      * applying it on the DataFrame
      *
-     * @throws MacrobaseException If the column name (specified in the constructor of the
+     * @throws MacroBaseException If the column name (specified in the constructor of the
      * MBFunction) isn't present in the DataFrame, an exception is thrown.
      */
-    public final double[] apply(final DataFrame df) throws MacrobaseException {
+    public final double[] apply(final DataFrame df) throws MacroBaseException {
         if (!df.hasColumn(columnName)) {
-            throw new MacrobaseException(columnName + " not present in DataFrame");
+            throw new MacroBaseException(columnName + " not present in DataFrame");
         }
         final double[] outputCol = new double[df.getNumRows()];
         this.applyFunction(df.getDoubleColumnByName(columnName), outputCol);
@@ -68,11 +68,11 @@ public final double[] apply(final DataFrame df) throws MacrobaseException {
      * would be "normalize"  (or "NORMALIZE"---the funcName is case-agnostic), and the {@param arg}
      * would be "battery_drain".
      *
-     * @throws MacrobaseException If there's an error instantiating the MBFunction (usually due to
+     * @throws MacroBaseException If there's an error instantiating the MBFunction (usually due to
      * incorrect arguments or improperly defined subclasses), an exception is thrown.
      */
     public static MBFunction getFunction(String funcName, String arg)
-        throws MacrobaseException {
+        throws MacroBaseException {
         Class<? extends MBFunction> clazz;
         switch (funcName.toLowerCase()) {
             case "normalize": {
@@ -84,13 +84,13 @@ public static MBFunction getFunction(String funcName, String arg)
                 break;
             }
             default: {
-                throw new MacrobaseException("Bad MBFunction Type: " + funcName);
+                throw new MacroBaseException("Bad MBFunction Type: " + funcName);
             }
         }
         try {
             return clazz.getConstructor(String.class).newInstance(arg);
         } catch (NoSuchMethodException | InstantiationException | InvocationTargetException | IllegalAccessException e) {
-            throw new MacrobaseException(
+            throw new MacroBaseException(
                 "MBFunction Type " + funcName + " incompatible with args (" + arg + ")");
         }
     }

lib/src/main/java/edu/stanford/futuredata/macrobase/analysis/classify/Classifier.java

@@ -1,12 +1,6 @@
 package edu.stanford.futuredata.macrobase.analysis.classify;
 
-import com.google.common.base.Joiner;
-import edu.stanford.futuredata.macrobase.datamodel.DataFrame;
 import edu.stanford.futuredata.macrobase.operator.Transformer;
-import edu.stanford.futuredata.macrobase.util.MacrobaseException;
-import java.lang.reflect.InvocationTargetException;
-import java.util.BitSet;
-import java.util.List;
 
 public abstract class Classifier implements Transformer {
 

lib/src/main/java/edu/stanford/futuredata/macrobase/analysis/classify/PredicateClassifier.java

@@ -2,7 +2,7 @@
 
 import edu.stanford.futuredata.macrobase.analysis.classify.stats.MBPredicate;
 import edu.stanford.futuredata.macrobase.datamodel.DataFrame;
-import edu.stanford.futuredata.macrobase.util.MacrobaseException;
+import edu.stanford.futuredata.macrobase.util.MacroBaseException;
 import java.util.function.DoublePredicate;
 import java.util.function.Predicate;
 
@@ -36,7 +36,7 @@ public class PredicateClassifier extends Classifier {
      */
     public PredicateClassifier(final String columnName, final String predicateStr,
         final double sentinel)
-        throws MacrobaseException {
+        throws MacroBaseException {
         super(columnName);
         this.predicate = MBPredicate.getDoublePredicate(predicateStr, sentinel);
         this.isStrPredicate = false;
@@ -50,7 +50,7 @@ public PredicateClassifier(final String columnName, final String predicateStr,
      */
     public PredicateClassifier(final String columnName, final String predicateStr,
         final String sentinel)
-        throws MacrobaseException {
+        throws MacroBaseException {
         super(columnName);
         this.strPredicate = MBPredicate.getStrPredicate(predicateStr, sentinel);
         this.isStrPredicate = true;

lib/src/main/java/edu/stanford/futuredata/macrobase/analysis/classify/PredicateCubeClassifier.java

@@ -2,7 +2,7 @@
 
 import edu.stanford.futuredata.macrobase.analysis.classify.stats.MBPredicate;
 import edu.stanford.futuredata.macrobase.datamodel.DataFrame;
-import edu.stanford.futuredata.macrobase.util.MacrobaseException;
+import edu.stanford.futuredata.macrobase.util.MacroBaseException;
 
 import java.util.function.DoublePredicate;
 import java.util.function.Predicate;
@@ -26,14 +26,14 @@ public class PredicateCubeClassifier extends CubeClassifier {
      * @param metricColumnName Column on which to classifier outliers
      * @param predicateStr Predicate used for classification: "==", "!=", "<", ">", "<=", or ">="
      * @param sentinel Sentinel value used when evaluating the predicate to determine outlier
-     * @throws MacrobaseException
+     * @throws MacroBaseException
      */
     public PredicateCubeClassifier(
             final String countColumnName,
             final String metricColumnName,
             final String predicateStr,
             final double sentinel
-    ) throws MacrobaseException {
+    ) throws MacroBaseException {
         super(countColumnName);
         this.metricColumnName = metricColumnName;
         this.predicate = MBPredicate.getDoublePredicate(predicateStr, sentinel);
@@ -45,14 +45,14 @@ public PredicateCubeClassifier(
      * @param metricColumnName Column on which to classifier outliers
      * @param predicateStr Predicate used for classification: "==", "!=", "<", ">", "<=", or ">="
      * @param sentinel Sentinel value used when evaluating the predicate to determine outlier
-     * @throws MacrobaseException
+     * @throws MacroBaseException
      */
     public PredicateCubeClassifier(
             final String countColumnName,
             final String metricColumnName,
             final String predicateStr,
             final String sentinel
-    ) throws MacrobaseException {
+    ) throws MacroBaseException {
         super(countColumnName);
         this.metricColumnName = metricColumnName;
         this.strPredicate = MBPredicate.getStrPredicate(predicateStr, sentinel);

lib/src/main/java/edu/stanford/futuredata/macrobase/analysis/classify/stats/LinearInterpolator.java

@@ -1,6 +1,6 @@
 package edu.stanford.futuredata.macrobase.analysis.classify.stats;
 
-import edu.stanford.futuredata.macrobase.util.MacrobaseInternalError;
+import edu.stanford.futuredata.macrobase.util.MacroBaseInternalError;
 
 /**
  * Performs linear interpolation in a lazy manner: interpolation does not actually
@@ -24,7 +24,7 @@ public LinearInterpolator(double[] x, double[] y) throws IllegalArgumentExceptio
         this.y = y;
     }
 
-    public double evaluate(double value) throws MacrobaseInternalError {
+    public double evaluate(double value) throws MacroBaseInternalError {
         if ((value > x[x.length - 1]) || (value < x[0])) {
             return Double.NaN;
         }
@@ -43,6 +43,6 @@ public double evaluate(double value) throws MacrobaseInternalError {
             return slope * value + intercept;
         }
 
-        throw new MacrobaseInternalError("Linear interpolator implemented incorrectly");
+        throw new MacroBaseInternalError("Linear interpolator implemented incorrectly");
     }
 }