Kubernetes on Supporting 1 Million Bike-Taxi Drivers in Indonesia Giri Kuncoro and Iqbal Farabi KubeCon + CloudNativeCon China 2018 Hello! Giri Kuncoro System Engineer Go-Jek Indonesia @girikuncoro

com/google-research/bert Data 数据不均 • Why are my tip predictions bad in the morning hours? 16 Chicago Taxi Cab Dataset Tensorflow/Keras中的网络 Custom training with TPUs • https://www.tensorflow.org/tutori Transform( input_data=example_gen.outputs.examples, schema=infer_schema.outputs.output, module_file=taxi_module_file) Configuration for key in _DENSE_FLOAT_FEATURE_KEYS: outputs[_transformed_name(key)] KEY)] = tf.where( tf.is_nan(taxi_fare), tf.cast(tf.zeros_like(taxi_fare), tf.int64), # Test if the tip was > 20% of the fare. tf.cast( tf.greater(tips, tf.multiply(taxi_fare, tf.constant(0.2))), tf.int64))

• Walkthrough an example Taxi Rides Dataset Taxi Ride Events rideId Long a unique id for each ride taxiId Long a unique id for each taxi driverId Long of passengers on the ride Taxi Fare Dataset Taxi Fare Events rideId Long a unique id for each ride taxiId Long a unique id for each taxi driverId Long

manage deployments? Approach 1: Multiple repositories /taxi-config-stage.git /taxi-config-test.git /taxi-config-prod.git /taxi-config-dev.git /taxi.git Approach 2 : Single Repository ├── apps │ └──

Machine Learning with ClickHouse Nikolai Kochetov, ClickHouse developer Experimental dataset NYC Taxi and Uber Trips › Where to download: https://www1.nyc.gov/site/tlc/about/tlc-trip-record-data.page yandex/docs/en/getting_started/example_datasets/nyc_taxi/ › What you can also read: https://toddwschneider.com/posts/ analyzing-1-1-billion-nyc-taxi-and-uber-trips-with-a-vengeance/ 3 / 62 External

Machine Learning with ClickHouse Nikolai Kochetov, ClickHouse developer Experimental dataset NYC Taxi and Uber Trips › Where to download: https://www1.nyc.gov/site/tlc/about/tlc-trip-record-data.page yandex/docs/en/getting_started/example_datasets/nyc_taxi/ › What you can also read: https://toddwschneider.com/posts/ analyzing-1-1-billion-nyc-taxi-and-uber-trips-with-a-vengeance/ 3 / 62 External

setStreamTimeCharacteristic(TimeCharacteristic.EventTime);
 // taxi ride events (start, end)
 DataStream rides = env.addSource(…)).keyBy("rideId");
 // taxi fare events (payment, tip)
 DataStream

interface Car { 6. manufacturer: string; 7. model: string; 8. year: number; 9. } 10. let taxi: Car = { 11. manufacturer: 'Toyota', 12. model: 'Camry', 13. year: 2014 14. }; 15 string[] = pluck(taxi, ['manufacturer', 'model']); 19. 20. // If we try to pluck model and year, we get an 21. // array of a union type: (string | number)[] 22. let modelYear = pluck(taxi, ['model', 'year']) 但编译器会检查你是否传入 了正确的属性名给 pluck ： 1. // error, 'unknown' is not in 'manufacturer' | 'model' | 'year' 2. pluck(taxi, ['year', 'unknown']); 第二个操作符是 T[K] ，索引访问操作符。 在这里，类型语法反映了表达式语法。 这意味 高级类型 - 185 - 本文档使用 书栈网 · BookStack

3 млрд строк SELECT passenger_count, avg(total_amount) FROM trips GROUP BY passenger_count NYC taxi benchmark Шардов 1 3 140 Время, с. 1,224 0,438 0,043 Ускорени е x2.8 x28.5 Запись в Distributed

Industrial monitoring Sensor data IoT Self-driving cars Agriculture Smart cities, surveillance Delivery Taxi Food tech HoReCa Scientific datasets Scientific datasets Genomics Particle physics Astronomy & astrophysics