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

Example 21 with ColumnStatistics

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

the class BooleanColumnStatsAggregator method aggregate.

@Override
public ColumnStatisticsObj aggregate(String colName, List<String> partNames, List<ColumnStatistics> css) throws MetaException {
    ColumnStatisticsObj statsObj = null;
    BooleanColumnStatsData aggregateData = null;
    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());
        }
        BooleanColumnStatsData newData = cso.getStatsData().getBooleanStats();
        if (aggregateData == null) {
            aggregateData = newData.deepCopy();
        } else {
            aggregateData.setNumTrues(aggregateData.getNumTrues() + newData.getNumTrues());
            aggregateData.setNumFalses(aggregateData.getNumFalses() + newData.getNumFalses());
            aggregateData.setNumNulls(aggregateData.getNumNulls() + newData.getNumNulls());
        }
    }
    ColumnStatisticsData columnStatisticsData = new ColumnStatisticsData();
    columnStatisticsData.setBooleanStats(aggregateData);
    statsObj.setStatsData(columnStatisticsData);
    return statsObj;
}

Example 22 with ColumnStatistics

use of org.apache.hadoop.hive.metastore.api.ColumnStatistics 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 23 with ColumnStatistics

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

the class HBaseReadWrite method buildColStats.

private ColumnStatistics buildColStats(byte[] key, boolean fromTable) throws IOException {
    // We initialize this late so that we don't create extras in the case of
    // partitions with no stats
    ColumnStatistics colStats = new ColumnStatistics();
    ColumnStatisticsDesc csd = new ColumnStatisticsDesc();
    // If this is a table key, parse it as one
    List<String> reconstructedKey;
    if (fromTable) {
        reconstructedKey = Arrays.asList(HBaseUtils.deserializeKey(key));
        csd.setIsTblLevel(true);
    } else {
        reconstructedKey = HBaseUtils.deserializePartitionKey(key, this);
        csd.setIsTblLevel(false);
    }
    csd.setDbName(reconstructedKey.get(0));
    csd.setTableName(reconstructedKey.get(1));
    if (!fromTable) {
        // Build the part name, for which we need the table
        Table table = getTable(reconstructedKey.get(0), reconstructedKey.get(1));
        if (table == null) {
            throw new RuntimeException("Unable to find table " + reconstructedKey.get(0) + "." + reconstructedKey.get(1) + " even though I have a partition for it!");
        }
        csd.setPartName(HBaseStore.buildExternalPartName(table, reconstructedKey.subList(2, reconstructedKey.size())));
    }
    colStats.setStatsDesc(csd);
    return colStats;
}

Example 24 with ColumnStatistics

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

the class HBaseStore method getPartitionColumnStatistics.

@Override
public List<ColumnStatistics> getPartitionColumnStatistics(String dbName, String tblName, List<String> partNames, List<String> colNames) throws MetaException, NoSuchObjectException {
    List<List<String>> partVals = new ArrayList<List<String>>(partNames.size());
    for (String partName : partNames) {
        partVals.add(partNameToVals(partName));
    }
    boolean commit = false;
    openTransaction();
    try {
        List<ColumnStatistics> cs = getHBase().getPartitionStatistics(dbName, tblName, partNames, partVals, colNames);
        commit = true;
        return cs;
    } catch (IOException e) {
        LOG.error("Unable to fetch column statistics", e);
        throw new MetaException("Failed fetching column statistics, " + e.getMessage());
    } finally {
        commitOrRoleBack(commit);
    }
}

Example 25 with ColumnStatistics

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

the class ColumnStatsTask method persistColumnStats.

private int persistColumnStats(Hive db) throws HiveException, MetaException, IOException {
    // Construct a column statistics object from the result
    List<ColumnStatistics> colStats = constructColumnStatsFromPackedRows(db);
    // Persist the column statistics object to the metastore
    // Note, this function is shared for both table and partition column stats.
    SetPartitionsStatsRequest request = new SetPartitionsStatsRequest(colStats);
    if (work.getColStats() != null && work.getColStats().getNumBitVector() > 0) {
        request.setNeedMerge(true);
    }
    db.setPartitionColumnStatistics(request);
    return 0;
}