Найти расстояние между несколькими точками - Lat/Long

Question

У меня есть большой стол с записью и отбрасыванием данных lat/long. Эта таблица содержит несколько сотен тысяч записей, и я хочу найти расстояние между каждым пикапом и выпадением.

Можно ли это сделать, используя SQL в BigQuery?

Answer 1

Try ниже, должно быть хорошим началом для вас

SELECT 
    orderid, 
    car_number, 
    ROUND(distance) AS distance, 
    ROUND(next_distance) AS next_distance 
FROM JS(
    (
    // input table 
    SELECT 
    orderid, 
    car_number, 
    pickup_lon, 
    pickup_lat, 
    dropoff_lon, 
    dropoff_lat, 
    LEAD(pickup_lon) OVER(PARTITION BY car_number ORDER BY orderid) AS next_pickup_lon, 
    LEAD(pickup_lat) OVER(PARTITION BY car_number ORDER BY orderid) AS next_pickup_lat 
    FROM 
    (SELECT 1 AS orderid, 1 AS car_number, -121.23200000000001 AS pickup_lon, 38.1964 AS pickup_lat, -117.48 AS dropoff_lon, 34.5894 AS dropoff_lat), 
    (SELECT 2 AS orderid, 1 AS car_number, -118.76 AS pickup_lon, 34.1445 AS pickup_lat, -122.26 AS dropoff_lon, 37.7606 AS dropoff_lat), 
    (SELECT 3 AS orderid, 2 AS car_number, -117.736 AS pickup_lon, 33.5761 AS pickup_lat, -117.19333333333333 AS dropoff_lon, 34.47484444444444 AS dropoff_lat)  
) , 
// input columns 
orderid, car_number, pickup_lon, pickup_lat, dropoff_lon, dropoff_lat, next_pickup_lon, next_pickup_lat, 
// output schema 
"[{name: 'orderid', type: 'integer'}, 
{name: 'car_number', type: 'integer'}, 
{name: 'distance', type: 'float'}, 
{name: 'next_distance', type: 'float'}]", 
// function 
"function(r, emit){ 

    emit({ 
    orderid: r.orderid, car_number: r.car_number, 
    distance: dist(r.pickup_lon, r.pickup_lat, r.dropoff_lon, r.dropoff_lat), 
    next_distance: dist(r.dropoff_lon, r.dropoff_lat, r.next_pickup_lon, r.next_pickup_lat) 
    }); 

    function deg2rad(deg) { 
    return deg * (Math.PI/180) 
    } 

    function dist(pickup_lon, pickup_lat, dropoff_lon, dropoff_lat) { 
    var R = 3959; // Radius of the earth in miles 
    var dLat = deg2rad(dropoff_lat-pickup_lat); 
    var dLon = deg2rad(dropoff_lon-pickup_lon); 
    var a = Math.sin(dLat/2) * Math.sin(dLat/2) + 
     Math.cos(deg2rad(pickup_lat)) * Math.cos(deg2rad(dropoff_lat)) * 
     Math.sin(dLon/2) * Math.sin(dLon/2); 
    var c = 2 * R * Math.atan2(Math.sqrt(a), Math.sqrt(1-a)); 
    return c; 
    } 

}" 
) 

результат:

orderid car_number distance next_distance  
1  1   325.0  79.0  
2  1   317.0  NaN 
3  2   69.0  NaN 

Из комментариев: Моя схема таблицы как таковой:

car_number  (string) 
pu_datetime (timestamp) 
do_datetime (timestamp) 
pu_lat   (float) 
pu_long  (float) 
do_lat   (float) 
do_long  (float) 

Добавлено соответствовать вашей таблице схемы

SELECT 
    pu_datetime, 
    car_number, 
    ROUND(distance) AS distance, 
    ROUND(next_distance) AS next_distance 
FROM JS(
    (
    // input table 
    SELECT 
    pu_datetime, 
    car_number, 
    pu_lon, 
    pu_lat, 
    do_lon, 
    do_lat, 
    LEAD(pu_lon) OVER(PARTITION BY car_number ORDER BY pu_datetime) AS next_pu_lon, 
    LEAD(pu_lat) OVER(PARTITION BY car_number ORDER BY pu_datetime) AS next_pu_lat 
    FROM 
    (SELECT timestamp('2016-07-01 13:00:00') AS pu_datetime, '1' AS car_number, -121.23200000000001 AS pu_lon, 38.1964 AS pu_lat, -117.48 AS do_lon, 34.5894 AS do_lat), 
    (SELECT timestamp('2016-07-02 10:00:00') AS pu_datetime, '1' AS car_number, -118.76 AS pu_lon, 34.1445 AS pu_lat, -122.26 AS do_lon, 37.7606 AS do_lat), 
    (SELECT timestamp('2016-07-03 11:00:00') AS pu_datetime, '2' AS car_number, -117.736 AS pu_lon, 33.5761 AS pu_lat, -117.19333333333333 AS do_lon, 34.47484444444444 AS do_lat)  
) , 
// input columns 
pu_datetime, car_number, pu_lon, pu_lat, do_lon, do_lat, next_pu_lon, next_pu_lat, 
// output schema 
"[{name: 'pu_datetime', type: 'timestamp'}, 
{name: 'car_number', type: 'string'}, 
{name: 'distance', type: 'float'}, 
{name: 'next_distance', type: 'float'}]", 
// function 
"function(r, emit){ 

    emit({ 
    pu_datetime: r.pu_datetime, car_number: r.car_number, 
    distance: dist(r.pu_lon, r.pu_lat, r.do_lon, r.do_lat), 
    next_distance: dist(r.do_lon, r.do_lat, r.next_pu_lon, r.next_pu_lat) 
    }); 

    function deg2rad(deg) { 
    return deg * (Math.PI/180) 
    } 

    function dist(pu_lon, pu_lat, do_lon, do_lat) { 
    var R = 3959; // Radius of the earth in miles 
    var dLat = deg2rad(do_lat-pu_lat); 
    var dLon = deg2rad(do_lon-pu_lon); 
    var a = Math.sin(dLat/2) * Math.sin(dLat/2) + 
     Math.cos(deg2rad(pu_lat)) * Math.cos(deg2rad(do_lat)) * 
     Math.sin(dLon/2) * Math.sin(dLon/2); 
    var c = 2 * R * Math.atan2(Math.sqrt(a), Math.sqrt(1-a)); 
    return c; 
    } 

}" 
) 

Answer 2

Эта функция рассчитает мили между двумя точками. ЭТО НЕ ДАЕТ РАССТОЯНИЯ. Для этого вам придется использовать API Google, и я считаю, что существует ограничение на 2500 просмотров в день.

SET ANSI_NULLS ON 
GO 
SET QUOTED_IDENTIFIER ON 
GO 
CREATE Function [dbo].[udf-Geo-CalcMiles] (@Long1 float,@Lat1 float,@Long2 float,@Lat2 Float) 
Returns Float as 
Begin 
    Declare @Miles Float 
    Set @Miles = 0 
    Set @Miles = (Sin(Radians(@Lat1)) * Sin(Radians(@Lat2))) + (Cos(Radians(@Lat1)) * Cos(Radians(@Lat2)) * Cos(Radians(@Long2) - Radians(@Long1))) 
    Return Case When @Miles =0 then 0 else abs((3958.75 * Atan(Sqrt(1 - power(@Miles, 2))/@Miles))) end 
End 

Так, например

;with cteBase as (
    Select Top 10 
      Box_Nr 
     ,From_Lat=Box_Lat 
     ,From_Lng=Box_Lng 
     ,To_Lat = Lead(Box_Lat,1) over (Order By Box_Nr) 
     ,To_Lng = Lead(Box_Lng,1) over (Order By Box_Nr) 
    from [dbo].[USPS-Collection-Point] Order by Box_Nr 
) 
Select * 
     ,Distance = [dbo].[udf-Geo-CalcMiles] (From_Lng,From_Lat,To_Lng,To_Lat) 
From cteBase 

Возвращает

Box_Nr From_Lat From_Lng To_Lat  To_Lng  Distance 
1  41.6947535 -71.1394048 41.6980289 -71.1341529 0.353027299635122 
2  41.6980289 -71.1341529 41.682761 -71.124812 1.15978643547294 
3  41.682761 -71.124812 41.7051854 -71.1477813 1.95061187457874 
4  41.7051854 -71.1477813 41.7080851 -71.1441519 0.274205428604983 
5  41.7080851 -71.1441519 41.702242 -71.1282279 0.915266219941071 
6  41.702242 -71.1282279 41.711085 -71.142123 0.941821767229312 
7  41.711085 -71.142123 41.7055301 -71.1516977 0.625473329587972 
8  41.7055301 -71.1516977 41.7071749 -71.1513423 0.115113681673717 
9  41.7071749 -71.1513423 41.7079604 -71.1543306 0.163416766676813 
10  41.7079604 -71.1543306 41.667808 -71.154372 2.77425950023261