Examples with NumDistinctValueEstimator org.apache.hadoop.hive.common.ndv.NumDistinctValueEstimator used on opensource projects

Example 1 with NumDistinctValueEstimator

use of org.apache.hadoop.hive.common.ndv.NumDistinctValueEstimator in project hive by apache.

the class DateColumnStatsAggregator method aggregate.

@Override
public ColumnStatisticsObj aggregate(List<ColStatsObjWithSourceInfo> colStatsWithSourceInfo, List<String> partNames, boolean areAllPartsFound) throws MetaException {
    ColumnStatisticsObj statsObj = null;
    String colType = null;
    String colName = null;
    // check if all the ColumnStatisticsObjs contain stats and all the ndv are
    // bitvectors
    boolean doAllPartitionContainStats = partNames.size() == colStatsWithSourceInfo.size();
    NumDistinctValueEstimator ndvEstimator = null;
    for (ColStatsObjWithSourceInfo csp : colStatsWithSourceInfo) {
        ColumnStatisticsObj cso = csp.getColStatsObj();
        if (statsObj == null) {
            colName = cso.getColName();
            colType = cso.getColType();
            statsObj = ColumnStatsAggregatorFactory.newColumnStaticsObj(colName, colType, cso.getStatsData().getSetField());
            LOG.trace("doAllPartitionContainStats for column: {} is: {}", colName, doAllPartitionContainStats);
        }
        DateColumnStatsDataInspector dateColumnStats = (DateColumnStatsDataInspector) cso.getStatsData().getDateStats();
        if (dateColumnStats.getNdvEstimator() == null) {
            ndvEstimator = null;
            break;
        } else {
            // check if all of the bit vectors can merge
            NumDistinctValueEstimator estimator = dateColumnStats.getNdvEstimator();
            if (ndvEstimator == null) {
                ndvEstimator = estimator;
            } else {
                if (ndvEstimator.canMerge(estimator)) {
                    continue;
                } else {
                    ndvEstimator = null;
                    break;
                }
            }
        }
    }
    if (ndvEstimator != null) {
        ndvEstimator = NumDistinctValueEstimatorFactory.getEmptyNumDistinctValueEstimator(ndvEstimator);
    }
    LOG.debug("all of the bit vectors can merge for " + colName + " is " + (ndvEstimator != null));
    ColumnStatisticsData columnStatisticsData = new ColumnStatisticsData();
    if (doAllPartitionContainStats || colStatsWithSourceInfo.size() < 2) {
        DateColumnStatsDataInspector aggregateData = null;
        long lowerBound = 0;
        long higherBound = 0;
        double densityAvgSum = 0.0;
        for (ColStatsObjWithSourceInfo csp : colStatsWithSourceInfo) {
            ColumnStatisticsObj cso = csp.getColStatsObj();
            DateColumnStatsDataInspector newData = (DateColumnStatsDataInspector) cso.getStatsData().getDateStats();
            lowerBound = Math.max(lowerBound, newData.getNumDVs());
            higherBound += newData.getNumDVs();
            densityAvgSum += (diff(newData.getHighValue(), newData.getLowValue())) / newData.getNumDVs();
            if (ndvEstimator != null) {
                ndvEstimator.mergeEstimators(newData.getNdvEstimator());
            }
            if (aggregateData == null) {
                aggregateData = newData.deepCopy();
            } else {
                aggregateData.setLowValue(min(aggregateData.getLowValue(), newData.getLowValue()));
                aggregateData.setHighValue(max(aggregateData.getHighValue(), newData.getHighValue()));
                aggregateData.setNumNulls(aggregateData.getNumNulls() + newData.getNumNulls());
                aggregateData.setNumDVs(Math.max(aggregateData.getNumDVs(), newData.getNumDVs()));
            }
        }
        if (ndvEstimator != null) {
            // 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 {
            long estimation;
            if (useDensityFunctionForNDVEstimation) {
                // We have estimation, lowerbound and higherbound. We use estimation
                // if it is between lowerbound and higherbound.
                double densityAvg = densityAvgSum / partNames.size();
                estimation = (long) (diff(aggregateData.getHighValue(), aggregateData.getLowValue()) / densityAvg);
                if (estimation < lowerBound) {
                    estimation = lowerBound;
                } else if (estimation > higherBound) {
                    estimation = higherBound;
                }
            } else {
                estimation = (long) (lowerBound + (higherBound - lowerBound) * ndvTuner);
            }
            aggregateData.setNumDVs(estimation);
        }
        columnStatisticsData.setDateStats(aggregateData);
    } else {
        // we need extrapolation
        LOG.debug("start extrapolation for " + colName);
        Map<String, Integer> indexMap = new HashMap<>();
        for (int index = 0; index < partNames.size(); index++) {
            indexMap.put(partNames.get(index), index);
        }
        Map<String, Double> adjustedIndexMap = new HashMap<>();
        Map<String, ColumnStatisticsData> adjustedStatsMap = new HashMap<>();
        // while we scan the css, we also get the densityAvg, lowerbound and
        // higerbound when useDensityFunctionForNDVEstimation is true.
        double densityAvgSum = 0.0;
        if (ndvEstimator == null) {
            // the traditional extrapolation methods.
            for (ColStatsObjWithSourceInfo csp : colStatsWithSourceInfo) {
                ColumnStatisticsObj cso = csp.getColStatsObj();
                String partName = csp.getPartName();
                DateColumnStatsData newData = cso.getStatsData().getDateStats();
                if (useDensityFunctionForNDVEstimation) {
                    densityAvgSum += diff(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.
            StringBuilder pseudoPartName = new StringBuilder();
            double pseudoIndexSum = 0;
            int length = 0;
            int curIndex = -1;
            DateColumnStatsDataInspector aggregateData = null;
            for (ColStatsObjWithSourceInfo csp : colStatsWithSourceInfo) {
                ColumnStatisticsObj cso = csp.getColStatsObj();
                String partName = csp.getPartName();
                DateColumnStatsDataInspector newData = (DateColumnStatsDataInspector) cso.getStatsData().getDateStats();
                // 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.setDateStats(aggregateData);
                        adjustedStatsMap.put(pseudoPartName.toString(), csd);
                        if (useDensityFunctionForNDVEstimation) {
                            densityAvgSum += diff(aggregateData.getHighValue(), aggregateData.getLowValue()) / aggregateData.getNumDVs();
                        }
                        // reset everything
                        pseudoPartName = new StringBuilder();
                        pseudoIndexSum = 0;
                        length = 0;
                        ndvEstimator = NumDistinctValueEstimatorFactory.getEmptyNumDistinctValueEstimator(ndvEstimator);
                    }
                    aggregateData = null;
                }
                curIndex = indexMap.get(partName);
                pseudoPartName.append(partName);
                pseudoIndexSum += curIndex;
                length++;
                curIndex++;
                if (aggregateData == null) {
                    aggregateData = newData.deepCopy();
                } else {
                    aggregateData.setLowValue(min(aggregateData.getLowValue(), newData.getLowValue()));
                    aggregateData.setHighValue(max(aggregateData.getHighValue(), newData.getHighValue()));
                    aggregateData.setNumNulls(aggregateData.getNumNulls() + newData.getNumNulls());
                }
                ndvEstimator.mergeEstimators(newData.getNdvEstimator());
            }
            if (length > 0) {
                // we have to set ndv
                adjustedIndexMap.put(pseudoPartName.toString(), pseudoIndexSum / length);
                aggregateData.setNumDVs(ndvEstimator.estimateNumDistinctValues());
                ColumnStatisticsData csd = new ColumnStatisticsData();
                csd.setDateStats(aggregateData);
                adjustedStatsMap.put(pseudoPartName.toString(), csd);
                if (useDensityFunctionForNDVEstimation) {
                    densityAvgSum += diff(aggregateData.getHighValue(), aggregateData.getLowValue()) / aggregateData.getNumDVs();
                }
            }
        }
        extrapolate(columnStatisticsData, partNames.size(), colStatsWithSourceInfo.size(), adjustedIndexMap, adjustedStatsMap, densityAvgSum / adjustedStatsMap.size());
    }
    LOG.debug("Ndv estimatation for {} is {} # of partitions requested: {} # of partitions found: {}", colName, columnStatisticsData.getDateStats().getNumDVs(), partNames.size(), colStatsWithSourceInfo.size());
    statsObj.setStatsData(columnStatisticsData);
    return statsObj;
}

Example 2 with NumDistinctValueEstimator

use of org.apache.hadoop.hive.common.ndv.NumDistinctValueEstimator in project hive by apache.

the class DecimalColumnStatsMerger method merge.

@Override
public void merge(ColumnStatisticsObj aggregateColStats, ColumnStatisticsObj newColStats) {
    DecimalColumnStatsDataInspector aggregateData = (DecimalColumnStatsDataInspector) aggregateColStats.getStatsData().getDecimalStats();
    DecimalColumnStatsDataInspector newData = (DecimalColumnStatsDataInspector) newColStats.getStatsData().getDecimalStats();
    Decimal lowValue = aggregateData.getLowValue() != null && (aggregateData.getLowValue().compareTo(newData.getLowValue()) > 0) ? aggregateData.getLowValue() : newData.getLowValue();
    aggregateData.setLowValue(lowValue);
    Decimal highValue = aggregateData.getHighValue() != null && (aggregateData.getHighValue().compareTo(newData.getHighValue()) > 0) ? aggregateData.getHighValue() : newData.getHighValue();
    aggregateData.setHighValue(highValue);
    aggregateData.setNumNulls(aggregateData.getNumNulls() + newData.getNumNulls());
    if (aggregateData.getNdvEstimator() == null || newData.getNdvEstimator() == null) {
        aggregateData.setNumDVs(Math.max(aggregateData.getNumDVs(), newData.getNumDVs()));
    } else {
        NumDistinctValueEstimator oldEst = aggregateData.getNdvEstimator();
        NumDistinctValueEstimator newEst = newData.getNdvEstimator();
        long ndv = -1;
        if (oldEst.canMerge(newEst)) {
            oldEst.mergeEstimators(newEst);
            ndv = oldEst.estimateNumDistinctValues();
            aggregateData.setNdvEstimator(oldEst);
        } else {
            ndv = Math.max(aggregateData.getNumDVs(), newData.getNumDVs());
        }
        LOG.debug("Use bitvector to merge column " + aggregateColStats.getColName() + "'s ndvs of " + aggregateData.getNumDVs() + " and " + newData.getNumDVs() + " to be " + ndv);
        aggregateData.setNumDVs(ndv);
    }
}

Example 3 with NumDistinctValueEstimator

use of org.apache.hadoop.hive.common.ndv.NumDistinctValueEstimator in project hive by apache.

the class StringColumnStatsMerger method merge.

@Override
public void merge(ColumnStatisticsObj aggregateColStats, ColumnStatisticsObj newColStats) {
    StringColumnStatsDataInspector aggregateData = (StringColumnStatsDataInspector) aggregateColStats.getStatsData().getStringStats();
    StringColumnStatsDataInspector newData = (StringColumnStatsDataInspector) newColStats.getStatsData().getStringStats();
    aggregateData.setMaxColLen(Math.max(aggregateData.getMaxColLen(), newData.getMaxColLen()));
    aggregateData.setAvgColLen(Math.max(aggregateData.getAvgColLen(), newData.getAvgColLen()));
    aggregateData.setNumNulls(aggregateData.getNumNulls() + newData.getNumNulls());
    if (aggregateData.getNdvEstimator() == null || newData.getNdvEstimator() == null) {
        aggregateData.setNumDVs(Math.max(aggregateData.getNumDVs(), newData.getNumDVs()));
    } else {
        NumDistinctValueEstimator oldEst = aggregateData.getNdvEstimator();
        NumDistinctValueEstimator newEst = newData.getNdvEstimator();
        long ndv = -1;
        if (oldEst.canMerge(newEst)) {
            oldEst.mergeEstimators(newEst);
            ndv = oldEst.estimateNumDistinctValues();
            aggregateData.setNdvEstimator(oldEst);
        } else {
            ndv = Math.max(aggregateData.getNumDVs(), newData.getNumDVs());
        }
        LOG.debug("Use bitvector to merge column " + aggregateColStats.getColName() + "'s ndvs of " + aggregateData.getNumDVs() + " and " + newData.getNumDVs() + " to be " + ndv);
        aggregateData.setNumDVs(ndv);
    }
}

Example 4 with NumDistinctValueEstimator

use of org.apache.hadoop.hive.common.ndv.NumDistinctValueEstimator in project hive by apache.

the class FMSketch method deserialize.

@Override
public NumDistinctValueEstimator deserialize(byte[] buf) {
    InputStream is = new ByteArrayInputStream(buf);
    try {
        NumDistinctValueEstimator n = FMSketchUtils.deserializeFM(is);
        is.close();
        return n;
    } catch (IOException e) {
        throw new RuntimeException(e);
    }
}

Example 5 with NumDistinctValueEstimator

use of org.apache.hadoop.hive.common.ndv.NumDistinctValueEstimator in project hive by apache.

the class DecimalColumnStatsAggregator method aggregate.

@Override
public ColumnStatisticsObj aggregate(List<ColStatsObjWithSourceInfo> colStatsWithSourceInfo, List<String> partNames, boolean areAllPartsFound) throws MetaException {
    ColumnStatisticsObj statsObj = null;
    String colType = null;
    String colName = null;
    // check if all the ColumnStatisticsObjs contain stats and all the ndv are
    // bitvectors
    boolean doAllPartitionContainStats = partNames.size() == colStatsWithSourceInfo.size();
    NumDistinctValueEstimator ndvEstimator = null;
    for (ColStatsObjWithSourceInfo csp : colStatsWithSourceInfo) {
        ColumnStatisticsObj cso = csp.getColStatsObj();
        if (statsObj == null) {
            colName = cso.getColName();
            colType = cso.getColType();
            statsObj = ColumnStatsAggregatorFactory.newColumnStaticsObj(colName, colType, cso.getStatsData().getSetField());
            LOG.trace("doAllPartitionContainStats for column: {} is: {}", colName, doAllPartitionContainStats);
        }
        DecimalColumnStatsDataInspector decimalColumnStatsData = (DecimalColumnStatsDataInspector) cso.getStatsData().getDecimalStats();
        if (decimalColumnStatsData.getNdvEstimator() == null) {
            ndvEstimator = null;
            break;
        } else {
            // check if all of the bit vectors can merge
            NumDistinctValueEstimator estimator = decimalColumnStatsData.getNdvEstimator();
            if (ndvEstimator == null) {
                ndvEstimator = estimator;
            } else {
                if (ndvEstimator.canMerge(estimator)) {
                    continue;
                } else {
                    ndvEstimator = null;
                    break;
                }
            }
        }
    }
    if (ndvEstimator != null) {
        ndvEstimator = NumDistinctValueEstimatorFactory.getEmptyNumDistinctValueEstimator(ndvEstimator);
    }
    LOG.debug("all of the bit vectors can merge for " + colName + " is " + (ndvEstimator != null));
    ColumnStatisticsData columnStatisticsData = new ColumnStatisticsData();
    if (doAllPartitionContainStats || colStatsWithSourceInfo.size() < 2) {
        DecimalColumnStatsDataInspector aggregateData = null;
        long lowerBound = 0;
        long higherBound = 0;
        double densityAvgSum = 0.0;
        for (ColStatsObjWithSourceInfo csp : colStatsWithSourceInfo) {
            ColumnStatisticsObj cso = csp.getColStatsObj();
            DecimalColumnStatsDataInspector newData = (DecimalColumnStatsDataInspector) cso.getStatsData().getDecimalStats();
            lowerBound = Math.max(lowerBound, newData.getNumDVs());
            higherBound += newData.getNumDVs();
            densityAvgSum += (MetaStoreUtils.decimalToDouble(newData.getHighValue()) - MetaStoreUtils.decimalToDouble(newData.getLowValue())) / newData.getNumDVs();
            if (ndvEstimator != null) {
                ndvEstimator.mergeEstimators(newData.getNdvEstimator());
            }
            if (aggregateData == null) {
                aggregateData = newData.deepCopy();
            } else {
                if (MetaStoreUtils.decimalToDouble(aggregateData.getLowValue()) < MetaStoreUtils.decimalToDouble(newData.getLowValue())) {
                    aggregateData.setLowValue(aggregateData.getLowValue());
                } else {
                    aggregateData.setLowValue(newData.getLowValue());
                }
                if (MetaStoreUtils.decimalToDouble(aggregateData.getHighValue()) > MetaStoreUtils.decimalToDouble(newData.getHighValue())) {
                    aggregateData.setHighValue(aggregateData.getHighValue());
                } else {
                    aggregateData.setHighValue(newData.getHighValue());
                }
                aggregateData.setNumNulls(aggregateData.getNumNulls() + newData.getNumNulls());
                aggregateData.setNumDVs(Math.max(aggregateData.getNumDVs(), newData.getNumDVs()));
            }
        }
        if (ndvEstimator != null) {
            // 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 {
            long estimation;
            if (useDensityFunctionForNDVEstimation) {
                // We have estimation, lowerbound and higherbound. We use estimation
                // if it is between lowerbound and higherbound.
                double densityAvg = densityAvgSum / partNames.size();
                estimation = (long) ((MetaStoreUtils.decimalToDouble(aggregateData.getHighValue()) - MetaStoreUtils.decimalToDouble(aggregateData.getLowValue())) / densityAvg);
                if (estimation < lowerBound) {
                    estimation = lowerBound;
                } else if (estimation > higherBound) {
                    estimation = higherBound;
                }
            } else {
                estimation = (long) (lowerBound + (higherBound - lowerBound) * ndvTuner);
            }
            aggregateData.setNumDVs(estimation);
        }
        columnStatisticsData.setDecimalStats(aggregateData);
    } else {
        // we need extrapolation
        LOG.debug("start extrapolation for " + colName);
        Map<String, Integer> indexMap = new HashMap<>();
        for (int index = 0; index < partNames.size(); index++) {
            indexMap.put(partNames.get(index), index);
        }
        Map<String, Double> adjustedIndexMap = new HashMap<>();
        Map<String, ColumnStatisticsData> adjustedStatsMap = new HashMap<>();
        // while we scan the css, we also get the densityAvg, lowerbound and
        // higerbound when useDensityFunctionForNDVEstimation is true.
        double densityAvgSum = 0.0;
        if (ndvEstimator == null) {
            // the traditional extrapolation methods.
            for (ColStatsObjWithSourceInfo csp : colStatsWithSourceInfo) {
                ColumnStatisticsObj cso = csp.getColStatsObj();
                String partName = csp.getPartName();
                DecimalColumnStatsData newData = cso.getStatsData().getDecimalStats();
                if (useDensityFunctionForNDVEstimation) {
                    densityAvgSum += (MetaStoreUtils.decimalToDouble(newData.getHighValue()) - MetaStoreUtils.decimalToDouble(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.
            StringBuilder pseudoPartName = new StringBuilder();
            double pseudoIndexSum = 0;
            int length = 0;
            int curIndex = -1;
            DecimalColumnStatsDataInspector aggregateData = null;
            for (ColStatsObjWithSourceInfo csp : colStatsWithSourceInfo) {
                ColumnStatisticsObj cso = csp.getColStatsObj();
                String partName = csp.getPartName();
                DecimalColumnStatsDataInspector newData = (DecimalColumnStatsDataInspector) cso.getStatsData().getDecimalStats();
                // 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.setDecimalStats(aggregateData);
                        adjustedStatsMap.put(pseudoPartName.toString(), csd);
                        if (useDensityFunctionForNDVEstimation) {
                            densityAvgSum += (MetaStoreUtils.decimalToDouble(aggregateData.getHighValue()) - MetaStoreUtils.decimalToDouble(aggregateData.getLowValue())) / aggregateData.getNumDVs();
                        }
                        // reset everything
                        pseudoPartName = new StringBuilder();
                        pseudoIndexSum = 0;
                        length = 0;
                        ndvEstimator = NumDistinctValueEstimatorFactory.getEmptyNumDistinctValueEstimator(ndvEstimator);
                    }
                    aggregateData = null;
                }
                curIndex = indexMap.get(partName);
                pseudoPartName.append(partName);
                pseudoIndexSum += curIndex;
                length++;
                curIndex++;
                if (aggregateData == null) {
                    aggregateData = newData.deepCopy();
                } else {
                    if (MetaStoreUtils.decimalToDouble(aggregateData.getLowValue()) < MetaStoreUtils.decimalToDouble(newData.getLowValue())) {
                        aggregateData.setLowValue(aggregateData.getLowValue());
                    } else {
                        aggregateData.setLowValue(newData.getLowValue());
                    }
                    if (MetaStoreUtils.decimalToDouble(aggregateData.getHighValue()) > MetaStoreUtils.decimalToDouble(newData.getHighValue())) {
                        aggregateData.setHighValue(aggregateData.getHighValue());
                    } else {
                        aggregateData.setHighValue(newData.getHighValue());
                    }
                    aggregateData.setNumNulls(aggregateData.getNumNulls() + newData.getNumNulls());
                }
                ndvEstimator.mergeEstimators(newData.getNdvEstimator());
            }
            if (length > 0) {
                // we have to set ndv
                adjustedIndexMap.put(pseudoPartName.toString(), pseudoIndexSum / length);
                aggregateData.setNumDVs(ndvEstimator.estimateNumDistinctValues());
                ColumnStatisticsData csd = new ColumnStatisticsData();
                csd.setDecimalStats(aggregateData);
                adjustedStatsMap.put(pseudoPartName.toString(), csd);
                if (useDensityFunctionForNDVEstimation) {
                    densityAvgSum += (MetaStoreUtils.decimalToDouble(aggregateData.getHighValue()) - MetaStoreUtils.decimalToDouble(aggregateData.getLowValue())) / aggregateData.getNumDVs();
                }
            }
        }
        extrapolate(columnStatisticsData, partNames.size(), colStatsWithSourceInfo.size(), adjustedIndexMap, adjustedStatsMap, densityAvgSum / adjustedStatsMap.size());
    }
    LOG.debug("Ndv estimatation for {} is {} # of partitions requested: {} # of partitions found: {}", colName, columnStatisticsData.getDecimalStats().getNumDVs(), partNames.size(), colStatsWithSourceInfo.size());
    statsObj.setStatsData(columnStatisticsData);
    return statsObj;
}