Created
June 22, 2016 02:43
-
-
Save chelsyx/22c1d65ac7538e84849da9d3e8b5df6b to your computer and use it in GitHub Desktop.
Hero Drivers in Gotham
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
##### | |
# Goal: | |
# 1) suggest cutoff(no. of trips), and bonus($) | |
# 2) Expected no of additional trips | |
# 3) Total expenditure of the promotion | |
# 4) Other metrics to pay attention to | |
#### | |
library(dplyr) | |
library(ggplot2) | |
data0 <- read.csv("go_data_challenge.csv") | |
data0 <- data0[data0$fare>0, ] | |
data0$request_timestamp <- strptime(data0$request_timestamp, "%Y-%m-%d %H:%M:%S") | |
data0$week <- strftime(data0$request_timestamp,format="%W") | |
range(data0$request_timestamp) # "2015-12-31 16:00:26 PST" "2016-04-07 09:46:36 PDT" | |
table(data0$week) | |
n_driver <- length(unique(data0$driver_id)) # 2401 drivers | |
data0$extra_fare <- (1-1/data0$surge_multiplier)*data0$fare | |
data0$surge_trip <- data0$surge_multiplier > 1 | |
trip_count <- data0[,-2] %>% | |
group_by(driver_id, week) %>% | |
summarise(n_trip=length(X), extra_rev=sum(extra_fare), extra_trip=sum(surge_trip)) | |
trip_count <- as.data.frame(trip_count) | |
# Delete week00, 52, 14. reason: 1)holiday 2)not a 7-day week | |
week_mask <- trip_count$week %in% c("00","52","14") | |
trip_count1 <- trip_count[!week_mask,] | |
plot1 <- qplot(trip_count1$n_trip, xlab="Number of Trips per Week") # highly skewed to zero, long tail | |
plot2 <- qplot(trip_count1$extra_rev, trip_count1$extra_trip, xlab="Extra Revenue", ylab="Number of Surge Trips(Extra Trips)") | |
########## | |
uber_perc <- 0.25 | |
xxmask <- trip_count1$extra_rev > 0 | |
yy <- trip_count1$extra_trip[xxmask] | |
xx <- (1-uber_perc)*trip_count1$extra_rev[xxmask] | |
fit_lm <- lm(yy~xx) | |
summary(fit_lm) | |
bonus <- 100 | |
extra_trips <- coef(fit_lm)[1] + coef(fit_lm)[2]*bonus | |
driver_count <- trip_count1 %>% | |
group_by(week) %>% | |
summarise(n_driver=n()) | |
# num of driver is increasing | |
avg_n_driver <- mean(driver_count$n_driver) | |
########## | |
uber_perc <- 0.25 | |
for (cutoff in ceiling(extra_trips):max(trip_count1$n_trip)){ | |
mot_perc <- sum(trip_count1$n_trip < cutoff)/dim(trip_count1)[1] | |
add_trip <- extra_trips*avg_n_driver*mot_perc | |
total_extra_rev <- mean(data0$fare)*add_trip*uber_perc | |
driver_mask <- trip_count1$n_trip > (cutoff-extra_trips) | |
driver_perc <- sum(driver_mask)/dim(trip_count1)[1] | |
to_expense <- avg_n_driver*driver_perc*bonus | |
if(to_expense <= total_extra_rev){ | |
least_cutoff <- cutoff | |
break | |
} | |
} | |
########## | |
uber_perc <- 0.25 | |
bonus_list <- c(25,50,75,100,125,150,175,200,225,250) | |
results <- data.frame(Bonus=bonus_list, Least_Cutoff=rep(NA, length(bonus_list)), | |
Add_Trips=rep(NA, length(bonus_list)), Expenditure=rep(NA, length(bonus_list)) ) | |
for (i in 1:length(bonus_list)){ | |
bonus <- bonus_list[i] | |
extra_trips <- coef(fit_lm)[1] + coef(fit_lm)[2]*bonus | |
for (cutoff in ceiling(extra_trips):max(trip_count1$n_trip)){ | |
mot_perc <- sum(trip_count1$n_trip < cutoff)/dim(trip_count1)[1] | |
add_trip <- extra_trips*avg_n_driver*mot_perc | |
total_extra_rev <- mean(data0$fare)*add_trip*uber_perc | |
driver_mask <- trip_count1$n_trip > (cutoff-extra_trips) | |
driver_perc <- sum(driver_mask)/dim(trip_count1)[1] | |
to_expense <- avg_n_driver*driver_perc*bonus | |
if(to_expense <= total_extra_rev){ | |
results[i, "Least_Cutoff"] <- cutoff | |
results[i, "Add_Trips"] <- add_trip | |
results[i, "Expenditure"] <- to_expense | |
break | |
} | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment