Examples with LongColumnStatsData org.apache.hadoop.hive.metastore.api.LongColumnStatsData used on opensource projects

Example 1 with LongColumnStatsData

use of org.apache.hadoop.hive.metastore.api.LongColumnStatsData in project hive by apache.

the class StatObjectConverter method getTableColumnStatisticsObj.

public static ColumnStatisticsObj getTableColumnStatisticsObj(MTableColumnStatistics mStatsObj) {
    ColumnStatisticsObj statsObj = new ColumnStatisticsObj();
    statsObj.setColType(mStatsObj.getColType());
    statsObj.setColName(mStatsObj.getColName());
    String colType = mStatsObj.getColType().toLowerCase();
    ColumnStatisticsData colStatsData = new ColumnStatisticsData();
    if (colType.equals("boolean")) {
        BooleanColumnStatsData boolStats = new BooleanColumnStatsData();
        boolStats.setNumFalses(mStatsObj.getNumFalses());
        boolStats.setNumTrues(mStatsObj.getNumTrues());
        boolStats.setNumNulls(mStatsObj.getNumNulls());
        colStatsData.setBooleanStats(boolStats);
    } else if (colType.equals("string") || colType.startsWith("varchar") || colType.startsWith("char")) {
        StringColumnStatsData stringStats = new StringColumnStatsData();
        stringStats.setNumNulls(mStatsObj.getNumNulls());
        stringStats.setAvgColLen(mStatsObj.getAvgColLen());
        stringStats.setMaxColLen(mStatsObj.getMaxColLen());
        stringStats.setNumDVs(mStatsObj.getNumDVs());
        colStatsData.setStringStats(stringStats);
    } else if (colType.equals("binary")) {
        BinaryColumnStatsData binaryStats = new BinaryColumnStatsData();
        binaryStats.setNumNulls(mStatsObj.getNumNulls());
        binaryStats.setAvgColLen(mStatsObj.getAvgColLen());
        binaryStats.setMaxColLen(mStatsObj.getMaxColLen());
        colStatsData.setBinaryStats(binaryStats);
    } else if (colType.equals("bigint") || colType.equals("int") || colType.equals("smallint") || colType.equals("tinyint") || colType.equals("timestamp")) {
        LongColumnStatsData longStats = new LongColumnStatsData();
        longStats.setNumNulls(mStatsObj.getNumNulls());
        Long longHighValue = mStatsObj.getLongHighValue();
        if (longHighValue != null) {
            longStats.setHighValue(longHighValue);
        }
        Long longLowValue = mStatsObj.getLongLowValue();
        if (longLowValue != null) {
            longStats.setLowValue(longLowValue);
        }
        longStats.setNumDVs(mStatsObj.getNumDVs());
        colStatsData.setLongStats(longStats);
    } else if (colType.equals("double") || colType.equals("float")) {
        DoubleColumnStatsData doubleStats = new DoubleColumnStatsData();
        doubleStats.setNumNulls(mStatsObj.getNumNulls());
        Double doubleHighValue = mStatsObj.getDoubleHighValue();
        if (doubleHighValue != null) {
            doubleStats.setHighValue(doubleHighValue);
        }
        Double doubleLowValue = mStatsObj.getDoubleLowValue();
        if (doubleLowValue != null) {
            doubleStats.setLowValue(doubleLowValue);
        }
        doubleStats.setNumDVs(mStatsObj.getNumDVs());
        colStatsData.setDoubleStats(doubleStats);
    } else if (colType.startsWith("decimal")) {
        DecimalColumnStatsData decimalStats = new DecimalColumnStatsData();
        decimalStats.setNumNulls(mStatsObj.getNumNulls());
        String decimalHighValue = mStatsObj.getDecimalHighValue();
        if (decimalHighValue != null) {
            decimalStats.setHighValue(createThriftDecimal(decimalHighValue));
        }
        String decimalLowValue = mStatsObj.getDecimalLowValue();
        if (decimalLowValue != null) {
            decimalStats.setLowValue(createThriftDecimal(decimalLowValue));
        }
        decimalStats.setNumDVs(mStatsObj.getNumDVs());
        colStatsData.setDecimalStats(decimalStats);
    } else if (colType.equals("date")) {
        DateColumnStatsData dateStats = new DateColumnStatsData();
        dateStats.setNumNulls(mStatsObj.getNumNulls());
        Long highValue = mStatsObj.getLongHighValue();
        if (highValue != null) {
            dateStats.setHighValue(new Date(highValue));
        }
        Long lowValue = mStatsObj.getLongLowValue();
        if (lowValue != null) {
            dateStats.setLowValue(new Date(lowValue));
        }
        dateStats.setNumDVs(mStatsObj.getNumDVs());
        colStatsData.setDateStats(dateStats);
    }
    statsObj.setStatsData(colStatsData);
    return statsObj;
}

Example 2 with LongColumnStatsData

use of org.apache.hadoop.hive.metastore.api.LongColumnStatsData in project hive by apache.

the class StatObjectConverter method getPartitionColumnStatisticsObj.

public static ColumnStatisticsObj getPartitionColumnStatisticsObj(MPartitionColumnStatistics mStatsObj) {
    ColumnStatisticsObj statsObj = new ColumnStatisticsObj();
    statsObj.setColType(mStatsObj.getColType());
    statsObj.setColName(mStatsObj.getColName());
    String colType = mStatsObj.getColType().toLowerCase();
    ColumnStatisticsData colStatsData = new ColumnStatisticsData();
    if (colType.equals("boolean")) {
        BooleanColumnStatsData boolStats = new BooleanColumnStatsData();
        boolStats.setNumFalses(mStatsObj.getNumFalses());
        boolStats.setNumTrues(mStatsObj.getNumTrues());
        boolStats.setNumNulls(mStatsObj.getNumNulls());
        colStatsData.setBooleanStats(boolStats);
    } else if (colType.equals("string") || colType.startsWith("varchar") || colType.startsWith("char")) {
        StringColumnStatsData stringStats = new StringColumnStatsData();
        stringStats.setNumNulls(mStatsObj.getNumNulls());
        stringStats.setAvgColLen(mStatsObj.getAvgColLen());
        stringStats.setMaxColLen(mStatsObj.getMaxColLen());
        stringStats.setNumDVs(mStatsObj.getNumDVs());
        colStatsData.setStringStats(stringStats);
    } else if (colType.equals("binary")) {
        BinaryColumnStatsData binaryStats = new BinaryColumnStatsData();
        binaryStats.setNumNulls(mStatsObj.getNumNulls());
        binaryStats.setAvgColLen(mStatsObj.getAvgColLen());
        binaryStats.setMaxColLen(mStatsObj.getMaxColLen());
        colStatsData.setBinaryStats(binaryStats);
    } else if (colType.equals("tinyint") || colType.equals("smallint") || colType.equals("int") || colType.equals("bigint") || colType.equals("timestamp")) {
        LongColumnStatsData longStats = new LongColumnStatsData();
        longStats.setNumNulls(mStatsObj.getNumNulls());
        if (mStatsObj.getLongHighValue() != null) {
            longStats.setHighValue(mStatsObj.getLongHighValue());
        }
        if (mStatsObj.getLongLowValue() != null) {
            longStats.setLowValue(mStatsObj.getLongLowValue());
        }
        longStats.setNumDVs(mStatsObj.getNumDVs());
        colStatsData.setLongStats(longStats);
    } else if (colType.equals("double") || colType.equals("float")) {
        DoubleColumnStatsData doubleStats = new DoubleColumnStatsData();
        doubleStats.setNumNulls(mStatsObj.getNumNulls());
        if (mStatsObj.getDoubleHighValue() != null) {
            doubleStats.setHighValue(mStatsObj.getDoubleHighValue());
        }
        if (mStatsObj.getDoubleLowValue() != null) {
            doubleStats.setLowValue(mStatsObj.getDoubleLowValue());
        }
        doubleStats.setNumDVs(mStatsObj.getNumDVs());
        colStatsData.setDoubleStats(doubleStats);
    } else if (colType.startsWith("decimal")) {
        DecimalColumnStatsData decimalStats = new DecimalColumnStatsData();
        decimalStats.setNumNulls(mStatsObj.getNumNulls());
        if (mStatsObj.getDecimalHighValue() != null) {
            decimalStats.setHighValue(createThriftDecimal(mStatsObj.getDecimalHighValue()));
        }
        if (mStatsObj.getDecimalLowValue() != null) {
            decimalStats.setLowValue(createThriftDecimal(mStatsObj.getDecimalLowValue()));
        }
        decimalStats.setNumDVs(mStatsObj.getNumDVs());
        colStatsData.setDecimalStats(decimalStats);
    } else if (colType.equals("date")) {
        DateColumnStatsData dateStats = new DateColumnStatsData();
        dateStats.setNumNulls(mStatsObj.getNumNulls());
        dateStats.setHighValue(new Date(mStatsObj.getLongHighValue()));
        dateStats.setLowValue(new Date(mStatsObj.getLongLowValue()));
        dateStats.setNumDVs(mStatsObj.getNumDVs());
        colStatsData.setDateStats(dateStats);
    }
    statsObj.setStatsData(colStatsData);
    return statsObj;
}

Example 3 with LongColumnStatsData

use of org.apache.hadoop.hive.metastore.api.LongColumnStatsData in project hive by apache.

the class ColumnStatsAggregatorFactory method newColumnStaticsObj.

public static ColumnStatisticsObj newColumnStaticsObj(String colName, String colType, _Fields type) {
    ColumnStatisticsObj cso = new ColumnStatisticsObj();
    ColumnStatisticsData csd = new ColumnStatisticsData();
    cso.setColName(colName);
    cso.setColType(colType);
    switch(type) {
        case BOOLEAN_STATS:
            csd.setBooleanStats(new BooleanColumnStatsData());
            break;
        case LONG_STATS:
            csd.setLongStats(new LongColumnStatsData());
            break;
        case DOUBLE_STATS:
            csd.setDoubleStats(new DoubleColumnStatsData());
            break;
        case STRING_STATS:
            csd.setStringStats(new StringColumnStatsData());
            break;
        case BINARY_STATS:
            csd.setBinaryStats(new BinaryColumnStatsData());
            break;
        case DECIMAL_STATS:
            csd.setDecimalStats(new DecimalColumnStatsData());
            break;
        default:
            throw new RuntimeException("Woh, bad.  Unknown stats type!");
    }
    cso.setStatsData(csd);
    return cso;
}

Example 4 with LongColumnStatsData

use of org.apache.hadoop.hive.metastore.api.LongColumnStatsData in project hive by apache.

the class LongColumnStatsAggregator method aggregate.

@Override
public ColumnStatisticsObj aggregate(String colName, List<String> partNames, List<ColumnStatistics> css) throws MetaException {
    ColumnStatisticsObj statsObj = null;
    // check if all the ColumnStatisticsObjs contain stats and all the ndv are
    // bitvectors
    boolean doAllPartitionContainStats = partNames.size() == css.size();
    boolean isNDVBitVectorSet = true;
    String colType = null;
    for (ColumnStatistics cs : css) {
        if (cs.getStatsObjSize() != 1) {
            throw new MetaException("The number of columns should be exactly one in aggrStats, but found " + cs.getStatsObjSize());
        }
        ColumnStatisticsObj cso = cs.getStatsObjIterator().next();
        if (statsObj == null) {
            colType = cso.getColType();
            statsObj = ColumnStatsAggregatorFactory.newColumnStaticsObj(colName, colType, cso.getStatsData().getSetField());
        }
        if (numBitVectors <= 0 || !cso.getStatsData().getLongStats().isSetBitVectors() || cso.getStatsData().getLongStats().getBitVectors().length() == 0) {
            isNDVBitVectorSet = false;
            break;
        }
    }
    ColumnStatisticsData columnStatisticsData = new ColumnStatisticsData();
    if (doAllPartitionContainStats || css.size() < 2) {
        LongColumnStatsData aggregateData = null;
        long lowerBound = 0;
        long higherBound = 0;
        double densityAvgSum = 0.0;
        NumDistinctValueEstimator ndvEstimator = null;
        if (isNDVBitVectorSet) {
            ndvEstimator = new NumDistinctValueEstimator(numBitVectors);
        }
        for (ColumnStatistics cs : css) {
            ColumnStatisticsObj cso = cs.getStatsObjIterator().next();
            LongColumnStatsData newData = cso.getStatsData().getLongStats();
            if (useDensityFunctionForNDVEstimation) {
                lowerBound = Math.max(lowerBound, newData.getNumDVs());
                higherBound += newData.getNumDVs();
                densityAvgSum += (newData.getHighValue() - newData.getLowValue()) / newData.getNumDVs();
            }
            if (isNDVBitVectorSet) {
                ndvEstimator.mergeEstimators(new NumDistinctValueEstimator(newData.getBitVectors(), ndvEstimator.getnumBitVectors()));
            }
            if (aggregateData == null) {
                aggregateData = newData.deepCopy();
            } else {
                aggregateData.setLowValue(Math.min(aggregateData.getLowValue(), newData.getLowValue()));
                aggregateData.setHighValue(Math.max(aggregateData.getHighValue(), newData.getHighValue()));
                aggregateData.setNumNulls(aggregateData.getNumNulls() + newData.getNumNulls());
                aggregateData.setNumDVs(Math.max(aggregateData.getNumDVs(), newData.getNumDVs()));
            }
        }
        if (isNDVBitVectorSet) {
            // if all the ColumnStatisticsObjs contain bitvectors, we do not need to
            // use uniform distribution assumption because we can merge bitvectors
            // to get a good estimation.
            aggregateData.setNumDVs(ndvEstimator.estimateNumDistinctValues());
        } else {
            if (useDensityFunctionForNDVEstimation) {
                // We have estimation, lowerbound and higherbound. We use estimation
                // if it is between lowerbound and higherbound.
                double densityAvg = densityAvgSum / partNames.size();
                long estimation = (long) ((aggregateData.getHighValue() - aggregateData.getLowValue()) / densityAvg);
                if (estimation < lowerBound) {
                    aggregateData.setNumDVs(lowerBound);
                } else if (estimation > higherBound) {
                    aggregateData.setNumDVs(higherBound);
                } else {
                    aggregateData.setNumDVs(estimation);
                }
            } else {
            // Without useDensityFunctionForNDVEstimation, we just use the
            // default one, which is the max of all the partitions and it is
            // already done.
            }
        }
        columnStatisticsData.setLongStats(aggregateData);
    } else {
        // we need extrapolation
        Map<String, Integer> indexMap = new HashMap<String, Integer>();
        for (int index = 0; index < partNames.size(); index++) {
            indexMap.put(partNames.get(index), index);
        }
        Map<String, Double> adjustedIndexMap = new HashMap<String, Double>();
        Map<String, ColumnStatisticsData> adjustedStatsMap = new HashMap<String, ColumnStatisticsData>();
        // while we scan the css, we also get the densityAvg, lowerbound and
        // higerbound when useDensityFunctionForNDVEstimation is true.
        double densityAvgSum = 0.0;
        if (!isNDVBitVectorSet) {
            // the traditional extrapolation methods.
            for (ColumnStatistics cs : css) {
                String partName = cs.getStatsDesc().getPartName();
                ColumnStatisticsObj cso = cs.getStatsObjIterator().next();
                LongColumnStatsData newData = cso.getStatsData().getLongStats();
                if (useDensityFunctionForNDVEstimation) {
                    densityAvgSum += (newData.getHighValue() - newData.getLowValue()) / newData.getNumDVs();
                }
                adjustedIndexMap.put(partName, (double) indexMap.get(partName));
                adjustedStatsMap.put(partName, cso.getStatsData());
            }
        } else {
            // we first merge all the adjacent bitvectors that we could merge and
            // derive new partition names and index.
            NumDistinctValueEstimator ndvEstimator = new NumDistinctValueEstimator(numBitVectors);
            StringBuilder pseudoPartName = new StringBuilder();
            double pseudoIndexSum = 0;
            int length = 0;
            int curIndex = -1;
            LongColumnStatsData aggregateData = null;
            for (ColumnStatistics cs : css) {
                String partName = cs.getStatsDesc().getPartName();
                ColumnStatisticsObj cso = cs.getStatsObjIterator().next();
                LongColumnStatsData newData = cso.getStatsData().getLongStats();
                // already checked it before.
                if (indexMap.get(partName) != curIndex) {
                    // There is bitvector, but it is not adjacent to the previous ones.
                    if (length > 0) {
                        // we have to set ndv
                        adjustedIndexMap.put(pseudoPartName.toString(), pseudoIndexSum / length);
                        aggregateData.setNumDVs(ndvEstimator.estimateNumDistinctValues());
                        ColumnStatisticsData csd = new ColumnStatisticsData();
                        csd.setLongStats(aggregateData);
                        adjustedStatsMap.put(pseudoPartName.toString(), csd);
                        if (useDensityFunctionForNDVEstimation) {
                            densityAvgSum += (aggregateData.getHighValue() - aggregateData.getLowValue()) / aggregateData.getNumDVs();
                        }
                        // reset everything
                        pseudoPartName = new StringBuilder();
                        pseudoIndexSum = 0;
                        length = 0;
                    }
                    aggregateData = null;
                }
                curIndex = indexMap.get(partName);
                pseudoPartName.append(partName);
                pseudoIndexSum += curIndex;
                length++;
                curIndex++;
                if (aggregateData == null) {
                    aggregateData = newData.deepCopy();
                } else {
                    aggregateData.setLowValue(Math.min(aggregateData.getLowValue(), newData.getLowValue()));
                    aggregateData.setHighValue(Math.max(aggregateData.getHighValue(), newData.getHighValue()));
                    aggregateData.setNumNulls(aggregateData.getNumNulls() + newData.getNumNulls());
                }
                ndvEstimator.mergeEstimators(new NumDistinctValueEstimator(newData.getBitVectors(), ndvEstimator.getnumBitVectors()));
            }
            if (length > 0) {
                // we have to set ndv
                adjustedIndexMap.put(pseudoPartName.toString(), pseudoIndexSum / length);
                aggregateData.setNumDVs(ndvEstimator.estimateNumDistinctValues());
                ColumnStatisticsData csd = new ColumnStatisticsData();
                csd.setLongStats(aggregateData);
                adjustedStatsMap.put(pseudoPartName.toString(), csd);
                if (useDensityFunctionForNDVEstimation) {
                    densityAvgSum += (aggregateData.getHighValue() - aggregateData.getLowValue()) / aggregateData.getNumDVs();
                }
            }
        }
        extrapolate(columnStatisticsData, partNames.size(), css.size(), adjustedIndexMap, adjustedStatsMap, densityAvgSum / adjustedStatsMap.size());
    }
    statsObj.setStatsData(columnStatisticsData);
    return statsObj;
}

Example 5 with LongColumnStatsData

use of org.apache.hadoop.hive.metastore.api.LongColumnStatsData in project hive by apache.

the class ColumnStatsMergerFactory method newColumnStaticsObj.

public static ColumnStatisticsObj newColumnStaticsObj(String colName, String colType, _Fields type) {
    ColumnStatisticsObj cso = new ColumnStatisticsObj();
    ColumnStatisticsData csd = new ColumnStatisticsData();
    cso.setColName(colName);
    cso.setColType(colType);
    switch(type) {
        case BOOLEAN_STATS:
            csd.setBooleanStats(new BooleanColumnStatsData());
            break;
        case LONG_STATS:
            csd.setLongStats(new LongColumnStatsData());
            break;
        case DOUBLE_STATS:
            csd.setDoubleStats(new DoubleColumnStatsData());
            break;
        case STRING_STATS:
            csd.setStringStats(new StringColumnStatsData());
            break;
        case BINARY_STATS:
            csd.setBinaryStats(new BinaryColumnStatsData());
            break;
        case DECIMAL_STATS:
            csd.setDecimalStats(new DecimalColumnStatsData());
            break;
        default:
            throw new RuntimeException("Woh, bad.  Unknown stats type!");
    }
    cso.setStatsData(csd);
    return cso;
}