Tutoriel avancé

CREATE TABLE trips
(
    `trip_id` UInt32,
    `vendor_id` Enum8('1' = 1, '2' = 2, '3' = 3, '4' = 4, 'CMT' = 5, 'VTS' = 6, 'DDS' = 7, 'B02512' = 10, 'B02598' = 11, 'B02617' = 12, 'B02682' = 13, 'B02764' = 14, '' = 15),
    `pickup_date` Date,
    `pickup_datetime` DateTime,
    `dropoff_date` Date,
    `dropoff_datetime` DateTime,
    `store_and_fwd_flag` UInt8,
    `rate_code_id` UInt8,
    `pickup_longitude` Float64,
    `pickup_latitude` Float64,
    `dropoff_longitude` Float64,
    `dropoff_latitude` Float64,
    `passenger_count` UInt8,
    `trip_distance` Float64,
    `fare_amount` Float32,
    `extra` Float32,
    `mta_tax` Float32,
    `tip_amount` Float32,
    `tolls_amount` Float32,
    `ehail_fee` Float32,
    `improvement_surcharge` Float32,
    `total_amount` Float32,
    `payment_type` Enum8('UNK' = 0, 'CSH' = 1, 'CRE' = 2, 'NOC' = 3, 'DIS' = 4),
    `trip_type` UInt8,
    `pickup` FixedString(25),
    `dropoff` FixedString(25),
    `cab_type` Enum8('yellow' = 1, 'green' = 2, 'uber' = 3),
    `pickup_nyct2010_gid` Int8,
    `pickup_ctlabel` Float32,
    `pickup_borocode` Int8,
    `pickup_ct2010` String,
    `pickup_boroct2010` String,
    `pickup_cdeligibil` String,
    `pickup_ntacode` FixedString(4),
    `pickup_ntaname` String,
    `pickup_puma` UInt16,
    `dropoff_nyct2010_gid` UInt8,
    `dropoff_ctlabel` Float32,
    `dropoff_borocode` UInt8,
    `dropoff_ct2010` String,
    `dropoff_boroct2010` String,
    `dropoff_cdeligibil` String,
    `dropoff_ntacode` FixedString(4),
    `dropoff_ntaname` String,
    `dropoff_puma` UInt16
)
ENGINE = MergeTree
PARTITION BY toYYYYMM(pickup_date)
ORDER BY pickup_datetime;

INSERT INTO trips
SELECT * FROM s3(
    'https://datasets-documentation.s3.eu-west-3.amazonaws.com/nyc-taxi/trips_{1..2}.gz',
    'TabSeparatedWithNames', "
    `trip_id` UInt32,
    `vendor_id` Enum8('1' = 1, '2' = 2, '3' = 3, '4' = 4, 'CMT' = 5, 'VTS' = 6, 'DDS' = 7, 'B02512' = 10, 'B02598' = 11, 'B02617' = 12, 'B02682' = 13, 'B02764' = 14, '' = 15),
    `pickup_date` Date,
    `pickup_datetime` DateTime,
    `dropoff_date` Date,
    `dropoff_datetime` DateTime,
    `store_and_fwd_flag` UInt8,
    `rate_code_id` UInt8,
    `pickup_longitude` Float64,
    `pickup_latitude` Float64,
    `dropoff_longitude` Float64,
    `dropoff_latitude` Float64,
    `passenger_count` UInt8,
    `trip_distance` Float64,
    `fare_amount` Float32,
    `extra` Float32,
    `mta_tax` Float32,
    `tip_amount` Float32,
    `tolls_amount` Float32,
    `ehail_fee` Float32,
    `improvement_surcharge` Float32,
    `total_amount` Float32,
    `payment_type` Enum8('UNK' = 0, 'CSH' = 1, 'CRE' = 2, 'NOC' = 3, 'DIS' = 4),
    `trip_type` UInt8,
    `pickup` FixedString(25),
    `dropoff` FixedString(25),
    `cab_type` Enum8('yellow' = 1, 'green' = 2, 'uber' = 3),
    `pickup_nyct2010_gid` Int8,
    `pickup_ctlabel` Float32,
    `pickup_borocode` Int8,
    `pickup_ct2010` String,
    `pickup_boroct2010` String,
    `pickup_cdeligibil` String,
    `pickup_ntacode` FixedString(4),
    `pickup_ntaname` String,
    `pickup_puma` UInt16,
    `dropoff_nyct2010_gid` UInt8,
    `dropoff_ctlabel` Float32,
    `dropoff_borocode` UInt8,
    `dropoff_ct2010` String,
    `dropoff_boroct2010` String,
    `dropoff_cdeligibil` String,
    `dropoff_ntacode` FixedString(4),
    `dropoff_ntaname` String,
    `dropoff_puma` UInt16
") SETTINGS input_format_try_infer_datetimes = 0

SELECT count() FROM trips

SELECT
    pickup_datetime,
    dropoff_datetime,
    total_amount,
    pickup_nyct2010_gid,
    dropoff_nyct2010_gid,
    CASE
        WHEN dropoff_nyct2010_gid = 138 THEN 'LGA'
        WHEN dropoff_nyct2010_gid = 132 THEN 'JFK'
    END AS airport_code,
    EXTRACT(YEAR FROM pickup_datetime) AS year,
    EXTRACT(DAY FROM pickup_datetime) AS day,
    EXTRACT(HOUR FROM pickup_datetime) AS hour
FROM trips
WHERE dropoff_nyct2010_gid IN (132, 138)
ORDER BY pickup_datetime

SELECT * FROM taxi_zone_dictionary

SELECT dictGet('taxi_zone_dictionary', 'Borough', 132)

┌─dictGet('taxi_zone_dictionary', 'Borough', 132)─┐
│ Queens                                          │
└─────────────────────────────────────────────────┘

1 rows in set. Elapsed: 0.004 sec.

SELECT dictHas('taxi_zone_dictionary', 132)

SELECT dictHas('taxi_zone_dictionary', 4567)

SELECT
    count(1) AS total,
    dictGetOrDefault('taxi_zone_dictionary','Borough', toUInt64(pickup_nyct2010_gid), 'Unknown') AS borough_name
FROM trips
WHERE dropoff_nyct2010_gid = 132 OR dropoff_nyct2010_gid = 138
GROUP BY borough_name
ORDER BY total DESC

┌─total─┬─borough_name──┐
│ 23683 │ Unknown       │
│  7053 │ Manhattan     │
│  6828 │ Brooklyn      │
│  4458 │ Queens        │
│  2670 │ Bronx         │
│   554 │ Staten Island │
│    53 │ EWR           │
└───────┴───────────────┘

7 rows in set. Elapsed: 0.019 sec. Processed 2.00 million rows, 4.00 MB (105.70 million rows/s., 211.40 MB/s.)

SELECT
    count(1) AS total,
    Borough
FROM trips
JOIN taxi_zone_dictionary ON toUInt64(trips.pickup_nyct2010_gid) = taxi_zone_dictionary.LocationID
WHERE dropoff_nyct2010_gid = 132 OR dropoff_nyct2010_gid = 138
GROUP BY Borough
ORDER BY total DESC

┌─total─┬─Borough───────┐
│  7053 │ Manhattan     │
│  6828 │ Brooklyn      │
│  4458 │ Queens        │
│  2670 │ Bronx         │
│   554 │ Staten Island │
│    53 │ EWR           │
└───────┴───────────────┘

6 rows in set. Elapsed: 0.034 sec. Processed 2.00 million rows, 4.00 MB (59.14 million rows/s., 118.29 MB/s.)

SELECT *
FROM trips
JOIN taxi_zone_dictionary
    ON trips.dropoff_nyct2010_gid = taxi_zone_dictionary.LocationID
WHERE tip_amount > 0
ORDER BY tip_amount DESC
LIMIT 1000