thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-11-21 23:21:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #8086 from ClickHouse/geodist-less-wrong

Browse Source 
Make the code of geodist less wrong.
This commit is contained in:
alexey-milovidov 2019-12-09 20:38:29 +03:00 committed by GitHub
commit 36ca1a0a24
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
5 changed files with 182 additions and 102 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

241
dbms/src/Functions/greatCircleDistance.cpp
View File

@ -14,70 +14,102 @@
namespace DB
{
namespace ErrorCodes
{
extern const int ARGUMENT_OUT_OF_BOUND;
extern const int ILLEGAL_COLUMN;
extern const int LOGICAL_ERROR;
}
/** https://en.wikipedia.org/wiki/Great-circle_distance
/** Calculates the distance between two geographical locations.
* There are two variants:
* greatCircleDistance: calculates the distance on a sphere: https://en.wikipedia.org/wiki/Great-circle_distance
* geoDistance: calculates the distance on WGS-84 ellipsoid.
*
* The function calculates distance in meters between two points on Earth specified by longitude and latitude in degrees.
* The function uses great circle distance formula https://en.wikipedia.org/wiki/Great-circle_distance .
* Throws exception when one or several input values are not within reasonable bounds.
*
* Latitude must be in [-90, 90], longitude must be [-180, 180].
* Original code of this implementation of this function is here https://github.com/sphinxsearch/sphinx/blob/409f2c2b5b2ff70b04e38f92b6b1a890326bad65/src/sphinxexpr.cpp#L3825.
*
* Original code of this implementation of this function is here:
* https://github.com/sphinxsearch/sphinx/blob/409f2c2b5b2ff70b04e38f92b6b1a890326bad65/src/sphinxexpr.cpp#L3825.
* Andrey Aksenov, the author of original code, permitted to use this code in ClickHouse under the Apache 2.0 license.
* Presentation about this code from Highload++ Siberia 2019 is here https://github.com/ClickHouse/ClickHouse/files/3324740/1_._._GEODIST_._.pdf
* The main idea of this implementation is optimisations based on Taylor series, trigonometric identity and calculated constants once for cosine, arcsine(sqrt) and look up table.
* The main idea of this implementation is optimisations based on Taylor series, trigonometric identity
* and calculated constants once for cosine, arcsine(sqrt) and look up table.
*/
namespace
{
constexpr double PI = 3.14159265358979323846;
constexpr float TO_RADF = static_cast<float>(PI / 180.0);
constexpr float TO_RADF2 = static_cast<float>(PI / 360.0);
constexpr float RAD_IN_DEG = static_cast<float>(PI / 180.0);
constexpr float RAD_IN_DEG_HALF = static_cast<float>(PI / 360.0);
constexpr size_t GEODIST_TABLE_COS = 1024; // maxerr 0.00063%
constexpr size_t GEODIST_TABLE_ASIN = 512;
constexpr size_t GEODIST_TABLE_K = 1024;
constexpr size_t COS_LUT_SIZE = 1024; // maxerr 0.00063%
constexpr size_t ASIN_SQRT_LUT_SIZE = 512;
constexpr size_t METRIC_LUT_SIZE = 1024;
/** We use "WGS-84 ellipsoidal quadratic mean radius of Earth" as the approximation to calculate distances on sphere.
* The motivation for it is explained here: https://math.wikia.org/wiki/Ellipsoidal_quadratic_mean_radius
*
* Brief explanation:
* - the radius of sphere is choosen to minimize the difference between distance on that sphere and distance on WGS-84 ellipsoid between two points,
* averaged uniformly (?) by all angles (?) between points.
* This sounds not clear enough for me: what set we are averaging and by what measure?
*
* The value should be calculated this way:
* WITH 6378137.0 AS a, 6356752.314245 AS b SELECT sqrt(3 * a * a + b * b) / 2
*
* But for unknown reason, slightly different value is used.
* This constant may be changed in future with a note about backward incompatible change in the changelog.
*
* See also:
* https://github.com/Project-OSRM/osrm-backend/blob/bb1f4a025a3cefd3598a38b9d3e55485d1080ec5/third_party/libosmium/include/osmium/geom/haversine.hpp#L58-L59
* https://github.com/Project-OSRM/osrm-backend/issues/5051
* https://github.com/mapbox/turf-swift/issues/26
* https://github.com/Project-OSRM/osrm-backend/pull/5041
* https://en.wikipedia.org/wiki/Talk:Great-circle_distance/Archive_1
*/
constexpr float EARTH_RADIUS = 6372797.560856;
constexpr float EARTH_DIAMETER = 2 * EARTH_RADIUS;
float cos_lut[COS_LUT_SIZE + 1]; /// cos(x) table
float asin_sqrt_lut[ASIN_SQRT_LUT_SIZE + 1]; /// asin(sqrt(x)) * earth_diameter table
float sphere_metric_lut[METRIC_LUT_SIZE + 1]; /// sphere metric: the distance for one degree across longitude depending on latitude
float wgs84_metric_lut[2 * (METRIC_LUT_SIZE + 1)]; /// ellipsoid metric: the distance across one degree latitude/longitude depending on latitude
float g_GeoCos[GEODIST_TABLE_COS + 1]; /// cos(x) table
float g_GeoAsin[GEODIST_TABLE_ASIN + 1]; /// asin(sqrt(x)) table
float g_GeoFlatK[GEODIST_TABLE_K + 1][2]; /// geodistAdaptive() flat ellipsoid method k1, k2 coeffs table
inline double sqr(double v)
{
return v * v;
}
inline float fsqr(float v)
inline float sqrf(float v)
{
return v * v;
}
void geodistInit()
{
for (size_t i = 0; i <= GEODIST_TABLE_COS; ++i)
g_GeoCos[i] = static_cast<float>(cos(2 * PI * i / GEODIST_TABLE_COS)); // [0, 2 * pi] -> [0, COSTABLE]
for (size_t i = 0; i <= COS_LUT_SIZE; ++i)
cos_lut[i] = static_cast<float>(cos(2 * PI * i / COS_LUT_SIZE)); // [0, 2 * pi] -> [0, COS_LUT_SIZE]
for (size_t i = 0; i <= GEODIST_TABLE_ASIN; ++i)
g_GeoAsin[i] = static_cast<float>(asin(
sqrt(static_cast<double>(i) / GEODIST_TABLE_ASIN))); // [0, 1] -> [0, ASINTABLE]
for (size_t i = 0; i <= ASIN_SQRT_LUT_SIZE; ++i)
asin_sqrt_lut[i] = static_cast<float>(EARTH_DIAMETER * asin(
sqrt(static_cast<double>(i) / ASIN_SQRT_LUT_SIZE))); // [0, 1] -> [0, ASIN_SQRT_LUT_SIZE]
for (size_t i = 0; i <= GEODIST_TABLE_K; ++i)
for (size_t i = 0; i <= METRIC_LUT_SIZE; ++i)
{
double x = PI * i / GEODIST_TABLE_K - PI * 0.5; // [-pi / 2, pi / 2] -> [0, KTABLE]
g_GeoFlatK[i][0] = static_cast<float>(sqr(111132.09 - 566.05 * cos(2 * x) + 1.20 * cos(4 * x)));
g_GeoFlatK[i][1] = static_cast<float>(sqr(111415.13 * cos(x) - 94.55 * cos(3 * x) + 0.12 * cos(5 * x)));
double latitude = i * (PI / METRIC_LUT_SIZE) - PI * 0.5; // [-pi / 2, pi / 2] -> [0, METRIC_LUT_SIZE]
/// Squared metric coefficients (for the distance in meters) on a tangent plane, for latitude and longitude (in degrees),
/// depending on the latitude (in radians).
wgs84_metric_lut[i * 2] = static_cast<float>(sqr(111132.09 - 566.05 * cos(2 * latitude) + 1.20 * cos(4 * latitude)));
wgs84_metric_lut[i * 2 + 1] = static_cast<float>(sqr(111415.13 * cos(latitude) - 94.55 * cos(3 * latitude) + 0.12 * cos(5 * latitude)));
sphere_metric_lut[i] = static_cast<float>(sqr((EARTH_DIAMETER * PI / 360) * cos(latitude)));
}
}
inline float geodistDegDiff(float f)
{
f = static_cast<float>(fabs(f));
f = fabsf(f);
while (f > 360)
f -= 360;
if (f > 180)
@ -87,50 +119,113 @@ inline float geodistDegDiff(float f)
inline float geodistFastCos(float x)
{
float y = static_cast<float>(fabs(x) * GEODIST_TABLE_COS / PI / 2);
int i = static_cast<int>(y);
float y = fabsf(x) * (COS_LUT_SIZE / PI / 2);
size_t i = static_cast<size_t>(y);
y -= i;
i &= (GEODIST_TABLE_COS - 1);
return g_GeoCos[i] + (g_GeoCos[i + 1] - g_GeoCos[i]) * y;
i &= (COS_LUT_SIZE - 1);
return cos_lut[i] + (cos_lut[i + 1] - cos_lut[i]) * y;
}
inline float geodistFastSin(float x)
{
float y = static_cast<float>(fabs(x) * GEODIST_TABLE_COS / PI / 2);
int i = static_cast<int>(y);
float y = fabsf(x) * (COS_LUT_SIZE / PI / 2);
size_t i = static_cast<size_t>(y);
y -= i;
i = (i - GEODIST_TABLE_COS / 4) & (GEODIST_TABLE_COS - 1); // cos(x - pi / 2) = sin(x), costable / 4 = pi / 2
return g_GeoCos[i] + (g_GeoCos[i + 1] - g_GeoCos[i]) * y;
i = (i - COS_LUT_SIZE / 4) & (COS_LUT_SIZE - 1); // cos(x - pi / 2) = sin(x), costable / 4 = pi / 2
return cos_lut[i] + (cos_lut[i + 1] - cos_lut[i]) * y;
}
/// fast implementation of asin(sqrt(x))
/// max error in floats 0.00369%, in doubles 0.00072%
inline float geodistFastAsinSqrt(float x)
{
if (x < 0.122)
if (x < 0.122f)
{
// distance under 4546 km, Taylor error under 0.00072%
float y = static_cast<float>(sqrt(x));
return y + x * y * 0.166666666666666f + x * x * y * 0.075f + x * x * x * y * 0.044642857142857f;
float y = sqrtf(x);
return EARTH_DIAMETER * (y + x * y * 0.166666666666666f + x * x * y * 0.075f + x * x * x * y * 0.044642857142857f);
}
if (x < 0.948)
if (x < 0.948f)
{
// distance under 17083 km, 512-entry LUT error under 0.00072%
x *= GEODIST_TABLE_ASIN;
int i = static_cast<int>(x);
return g_GeoAsin[i] + (g_GeoAsin[i + 1] - g_GeoAsin[i]) * (x - i);
x *= ASIN_SQRT_LUT_SIZE;
size_t i = static_cast<size_t>(x);
return asin_sqrt_lut[i] + (asin_sqrt_lut[i + 1] - asin_sqrt_lut[i]) * (x - i);
}
return asinf(sqrtf(x)); // distance over 17083 km, just compute exact
}
enum class Method
{
SPHERE,
WGS84
};
template <Method method>
float distance(float lon1deg, float lat1deg, float lon2deg, float lat2deg)
{
float lat_diff = geodistDegDiff(lat1deg - lat2deg);
float lon_diff = geodistDegDiff(lon1deg - lon2deg);
if (lon_diff < 13)
{
// points are close enough; use flat ellipsoid model
// interpolate metric coefficients using latitudes midpoint
/// Why comparing only difference in longitude?
/// If longitudes are different enough, there is a big difference between great circle line and a line with constant latitude.
/// (Remember how a plane flies from Moscow to New York)
/// But if longitude is close but latitude is different enough, there is no difference between meridian and great circle line.
float latitude_midpoint = (lat1deg + lat2deg + 180) * METRIC_LUT_SIZE / 360; // [-90, 90] degrees -> [0, KTABLE] indexes
size_t latitude_midpoint_index = static_cast<size_t>(latitude_midpoint) & (METRIC_LUT_SIZE - 1);
/// This is linear interpolation between two table items at index "latitude_midpoint_index" and "latitude_midpoint_index + 1".
float k_lat;
float k_lon;
if constexpr (method == Method::SPHERE)
{
k_lat = sqr(EARTH_DIAMETER * PI / 360);
k_lon = sphere_metric_lut[latitude_midpoint_index]
+ (sphere_metric_lut[latitude_midpoint_index + 1] - sphere_metric_lut[latitude_midpoint_index]) * (latitude_midpoint - latitude_midpoint_index);
}
else if constexpr (method == Method::WGS84)
{
k_lat = wgs84_metric_lut[latitude_midpoint_index * 2]
+ (wgs84_metric_lut[(latitude_midpoint_index + 1) * 2] - wgs84_metric_lut[latitude_midpoint_index * 2]) * (latitude_midpoint - latitude_midpoint_index);
k_lon = wgs84_metric_lut[latitude_midpoint_index * 2 + 1]
+ (wgs84_metric_lut[(latitude_midpoint_index + 1) * 2 + 1] - wgs84_metric_lut[latitude_midpoint_index * 2 + 1]) * (latitude_midpoint - latitude_midpoint_index);
}
/// Metric on a tangent plane: it differs from Euclidean metric only by scale of coordinates.
return sqrtf(k_lat * lat_diff * lat_diff + k_lon * lon_diff * lon_diff);
}
else
{
// points too far away; use haversine
float a = sqrf(geodistFastSin(lat_diff * RAD_IN_DEG_HALF))
+ geodistFastCos(lat1deg * RAD_IN_DEG) * geodistFastCos(lat2deg * RAD_IN_DEG) * sqrf(geodistFastSin(lon_diff * RAD_IN_DEG_HALF));
return geodistFastAsinSqrt(a);
}
return static_cast<float>(asin(sqrt(x))); // distance over 17083km, just compute honestly
}
}
class FunctionGreatCircleDistance : public IFunction
template <Method method>
class FunctionGeoDistance : public IFunction
{
public:
static constexpr auto name = "greatCircleDistance";
static FunctionPtr create(const Context &) { return std::make_shared<FunctionGreatCircleDistance>(); }
static constexpr auto name = (method == Method::SPHERE) ? "greatCircleDistance" : "geoDistance";
static FunctionPtr create(const Context &) { return std::make_shared<FunctionGeoDistance<method>>(); }
private:
String getName() const override { return name; }
@ -143,50 +238,15 @@ private:
for (const auto arg_idx : ext::range(0, arguments.size()))
{
const auto arg = arguments[arg_idx].get();
if (!WhichDataType(arg).isFloat())
if (!isNumber(WhichDataType(arg)))
throw Exception(
"Illegal type " + arg->getName() + " of argument " + std::to_string(arg_idx + 1) + " of function " + getName() + ". Must be Float64",
"Illegal type " + arg->getName() + " of argument " + std::to_string(arg_idx + 1) + " of function " + getName() + ". Must be numeric",
ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT);
}
return std::make_shared<DataTypeFloat32>();
}
Float32 greatCircleDistance(Float32 lon1deg, Float32 lat1deg, Float32 lon2deg, Float32 lat2deg)
{
if (lon1deg < -180 || lon1deg > 180 ||
lon2deg < -180 || lon2deg > 180 ||
lat1deg < -90 || lat1deg > 90 ||
lat2deg < -90 || lat2deg > 90)
{
throw Exception("Arguments values out of bounds for function " + getName(),
ErrorCodes::ARGUMENT_OUT_OF_BOUND);
}
float lat_diff = geodistDegDiff(lat1deg - lat2deg);
float lon_diff = geodistDegDiff(lon1deg - lon2deg);
if (lon_diff < 13)
{
// points are close enough; use flat ellipsoid model
// interpolate sqr(k1), sqr(k2) coefficients using latitudes midpoint
float m = (lat1deg + lat2deg + 180) * GEODIST_TABLE_K / 360; // [-90, 90] degrees -> [0, KTABLE] indexes
size_t i = static_cast<size_t>(m) & (GEODIST_TABLE_K - 1);
float kk1 = g_GeoFlatK[i][0] + (g_GeoFlatK[i + 1][0] - g_GeoFlatK[i][0]) * (m - i);
float kk2 = g_GeoFlatK[i][1] + (g_GeoFlatK[i + 1][1] - g_GeoFlatK[i][1]) * (m - i);
return static_cast<float>(sqrt(kk1 * lat_diff * lat_diff + kk2 * lon_diff * lon_diff));
}
else
{
// points too far away; use haversine
static const float d = 2 * 6371000;
float a = fsqr(geodistFastSin(lat_diff * TO_RADF2)) +
geodistFastCos(lat1deg * TO_RADF) * geodistFastCos(lat2deg * TO_RADF) *
fsqr(geodistFastSin(lon_diff * TO_RADF2));
return static_cast<float>(d * geodistFastAsinSqrt(a));
}
}
void executeImpl(Block & block, const ColumnNumbers & arguments, size_t result, size_t input_rows_count) override
{
auto dst = ColumnVector<Float32>::create();
@ -199,7 +259,7 @@ private:
const IColumn & col_lat2 = *block.getByPosition(arguments[3]).column;
for (size_t row_num = 0; row_num < input_rows_count; ++row_num)
dst_data[row_num] = greatCircleDistance(
dst_data[row_num] = distance<method>(
col_lon1.getFloat32(row_num), col_lat1.getFloat32(row_num),
col_lon2.getFloat32(row_num), col_lat2.getFloat32(row_num));
@ -208,10 +268,11 @@ private:
};
void registerFunctionGreatCircleDistance(FunctionFactory & factory)
void registerFunctionGeoDistance(FunctionFactory & factory)
{
geodistInit();
factory.registerFunction<FunctionGreatCircleDistance>();
factory.registerFunction<FunctionGeoDistance<Method::SPHERE>>();
factory.registerFunction<FunctionGeoDistance<Method::WGS84>>();
}
}

4
dbms/src/Functions/registerFunctionsGeo.cpp
View File

@ -5,7 +5,7 @@ namespace DB
class FunctionFactory;
void registerFunctionGreatCircleDistance(FunctionFactory & factory);
void registerFunctionGeoDistance(FunctionFactory & factory);
void registerFunctionPointInEllipses(FunctionFactory & factory);
void registerFunctionPointInPolygon(FunctionFactory & factory);
void registerFunctionGeohashEncode(FunctionFactory & factory);
@ -18,7 +18,7 @@ void registerFunctionGeoToH3(FunctionFactory &);
void registerFunctionsGeo(FunctionFactory & factory)
{
registerFunctionGreatCircleDistance(factory);
registerFunctionGeoDistance(factory);
registerFunctionPointInEllipses(factory);
registerFunctionPointInPolygon(factory);
registerFunctionGeohashEncode(factory);

4
dbms/tests/performance/great_circle_dist.xml
View File

@ -9,8 +9,8 @@
</stop_conditions>
<!-- lon [-180; 180], lat [-90; 90] -->
<query>SELECT count() FROM system.numbers WHERE NOT ignore(greatCircleDistance((rand() % 360) * 1. - 180, (number % 150) * 1.2 - 90, (number % 360) + toFloat64(rand()) / 4294967296 - 180, (rand() % 180) * 1. - 90))</query>
<query>SELECT count() FROM system.numbers WHERE NOT ignore(greatCircleDistance((rand(1) % 360) * 1. - 180, (number % 150) * 1.2 - 90, (number % 360) + toFloat64(rand(2)) / 4294967296 - 180, (rand(3) % 180) * 1. - 90))</query>
<!-- 55.755830, 37.617780 is center of Moscow -->
<query>SELECT count() FROM system.numbers WHERE NOT ignore(greatCircleDistance(55. + toFloat64(rand()) / 4294967296, 37. + toFloat64(rand()) / 4294967296, 55. + toFloat64(rand()) / 4294967296, 37. + toFloat64(rand()) / 4294967296))</query>
<query>SELECT count() FROM system.numbers WHERE NOT ignore(greatCircleDistance(55. + toFloat64(rand(1)) / 4294967296, 37. + toFloat64(rand(2)) / 4294967296, 55. + toFloat64(rand(3)) / 4294967296, 37. + toFloat64(rand(4)) / 4294967296))</query>
</test>

8
dbms/tests/queries/0_stateless/01043_geo_distance.reference Normal file
View File

@ -0,0 +1,8 @@
111194.93
111194.93
110567.33
111699.25
10007543
10007543
10007543
10001780

11
dbms/tests/queries/0_stateless/01043_geo_distance.sql Normal file
View File

@ -0,0 +1,11 @@
SELECT greatCircleDistance(0., 0., 0., 1.);
SELECT greatCircleDistance(0., 89., 0, 90.);
SELECT geoDistance(0., 0., 0., 1.);
SELECT geoDistance(0., 89., 0., 90.);
SELECT greatCircleDistance(0., 0., 90., 0.);
SELECT greatCircleDistance(0., 0., 0., 90.);
SELECT geoDistance(0., 0., 90., 0.);
SELECT geoDistance(0., 0., 0., 90.);