read-process-taxi-data

sample_read-process

###---
### Sample Data Preparation
###---

#install.packages("dplyr")
#install.packages("readr")
library(dplyr)
library(readr)

# read dataset
data <- read_csv("http://www.geolink.pt/ecmlpkdd2015-challenge/data/Porto_taxi_data_training.csv")

n_taxis_call_type <- 
  data %>%
  group_by(CALL_TYPE,TAXI_ID) %>%
  summarise( N_TAXIS_CALL_TYPE = n()) %>%
  select(N_TAXIS_CALL_TYPE, CALL_TYPE)

n_taxis_call_type <-
  n_taxis_call_type %>%
  summarise(N_TAXIS_CALL_TYPE = sum(N_TAXIS_CALL_TYPE))

n_taxis_call_type