Predicting fare through Analytics on Google Cloud

In this project:

1) Worked to write a optimal query for our analytic model on BigQuery Service.

2) Training our Machine Learning model.

First of all I’m taking a public dataset named New York City yellow taxi cab trips.

We will start first by exploring our dataset.

#standardSQL
SELECT
  TIMESTAMP_TRUNC(pickup_datetime,
    MONTH) month,
  COUNT(*) trips
FROM
  `bigquery-public-data.new_york.tlc_yellow_trips_2015`
GROUP BY
  1
ORDER BY
  1

This query will give you output with column’s as Month and count of total trips completed in that month.

Now we will select features(columns) for training of our model.

• Tolls Amount
• Fare Amount
• Hour of Day
• Pick up address
• Drop off address
• Number of passengers

#standardSQL
WITH params AS (
    SELECT
    1 AS TRAIN,
    2 AS EVAL
    ),
  daynames AS
    (SELECT ['Sun', 'Mon', 'Tues', 'Wed', 'Thurs', 'Fri', 'Sat'] AS daysofweek),
  taxitrips AS (
  SELECT
    (tolls_amount + fare_amount) AS total_fare,
    daysofweek[ORDINAL(EXTRACT(DAYOFWEEK FROM pickup_datetime))] AS dayofweek,
    EXTRACT(HOUR FROM pickup_datetime) AS hourofday,
    pickup_longitude AS pickuplon,
    pickup_latitude AS pickuplat,
    dropoff_longitude AS dropofflon,
    dropoff_latitude AS dropofflat,
    passenger_count AS passengers
  FROM
    `nyc-tlc.yellow.trips`, daynames, params
  WHERE
    trip_distance > 0 AND fare_amount > 0
    AND MOD(ABS(FARM_FINGERPRINT(CAST(pickup_datetime AS STRING))),1000) = params.TRAIN
  )
  SELECT *
  FROM taxitrips

For creating a BigQuery ML model, we have to first create a dataset in our gcp project.

— I’m naming my dataset id to taxi .

Now let’s create and train our Machine Learning.

This model should be a linear regression type of, because we have to predict a certain value.

CREATE or REPLACE MODEL taxi.taxifare_model
OPTIONS
  (model_type='linear_reg', labels=['total_fare']) AS
WITH params AS (
    SELECT
    1 AS TRAIN,
    2 AS EVAL
    ),

  daynames AS
    (SELECT ['Sun', 'Mon', 'Tues', 'Wed', 'Thurs', 'Fri', 'Sat'] AS daysofweek),

  taxitrips AS (
  SELECT
    (tolls_amount + fare_amount) AS total_fare,
    daysofweek[ORDINAL(EXTRACT(DAYOFWEEK FROM pickup_datetime))] AS dayofweek,
    EXTRACT(HOUR FROM pickup_datetime) AS hourofday,
    pickup_longitude AS pickuplon,
    pickup_latitude AS pickuplat,
    dropoff_longitude AS dropofflon,
    dropoff_latitude AS dropofflat,
    passenger_count AS passengers
  FROM
    `nyc-tlc.yellow.trips`, daynames, params
  WHERE
    trip_distance > 0 AND fare_amount > 0
    AND MOD(ABS(FARM_FINGERPRINT(CAST(pickup_datetime AS STRING))),1000) = params.TRAIN
  )

  SELECT *
  FROM taxitrips

Now we will evaluate our ML model.

#standardSQL
SELECT
  SQRT(mean_squared_error) AS rmse
FROM
  ML.EVALUATE(MODEL taxi.taxifare_model,
  (
  WITH params AS (
    SELECT
    1 AS TRAIN,
    2 AS EVAL
    ),
  daynames AS
    (SELECT ['Sun', 'Mon', 'Tues', 'Wed', 'Thurs', 'Fri', 'Sat'] AS daysofweek),
  taxitrips AS (
  SELECT
    (tolls_amount + fare_amount) AS total_fare,
    daysofweek[ORDINAL(EXTRACT(DAYOFWEEK FROM pickup_datetime))] AS dayofweek,
    EXTRACT(HOUR FROM pickup_datetime) AS hourofday,
    pickup_longitude AS pickuplon,
    pickup_latitude AS pickuplat,
    dropoff_longitude AS dropofflon,
    dropoff_latitude AS dropofflat,
    passenger_count AS passengers
  FROM
    `nyc-tlc.yellow.trips`, daynames, params
  WHERE
    trip_distance > 0 AND fare_amount > 0
    AND MOD(ABS(FARM_FINGERPRINT(CAST(pickup_datetime AS STRING))),1000) = params.EVAL
  )
  SELECT *
  FROM taxitrips
  ))

After evaluating our model you get a RMSE of $9.47…

Finally we are going to predict fare for a taxi ride with this Data Analytics Model.

#standardSQL
SELECT
*
FROM
  ml.PREDICT(MODEL `taxi.taxifare_model`,
   (
 WITH params AS (
    SELECT
    1 AS TRAIN,
    2 AS EVAL
    ),
  daynames AS
    (SELECT ['Sun', 'Mon', 'Tues', 'Wed', 'Thurs', 'Fri', 'Sat'] AS daysofweek),
  taxitrips AS (
  SELECT
    (tolls_amount + fare_amount) AS total_fare,
    daysofweek[ORDINAL(EXTRACT(DAYOFWEEK FROM pickup_datetime))] AS dayofweek,
    EXTRACT(HOUR FROM pickup_datetime) AS hourofday,
    pickup_longitude AS pickuplon,
    pickup_latitude AS pickuplat,
    dropoff_longitude AS dropofflon,
    dropoff_latitude AS dropofflat,
    passenger_count AS passengers
  FROM
    `nyc-tlc.yellow.trips`, daynames, params
  WHERE
    trip_distance > 0 AND fare_amount > 0
    AND MOD(ABS(FARM_FINGERPRINT(CAST(pickup_datetime AS STRING))),1000) = params.EVAL
  )
  SELECT *
  FROM taxitrips
));

Finally, we can easily see in the output table, in which there is predicted value of that particular trip .i.e. predicted_total_fare based upon the parameters we have provided, with the actual fare i.e. total_fare to compare the predictions.

Yayyy !! We have successfully created a model and predicted a value for taxi fare , all of it on Google Cloud Platform!✌