Graphs2015.Rmd

---
title: "Graphs - 2015"
author: ""
date: ""
output: 
  html_document:
    fig_height: 6
    fig_width: 10
---
<!-- Don't edit in between this line and the one below -->
```{r include=FALSE}
# Don't delete this chunk if you are using the DataComputing package
library(DataComputing)
```
*Source file* 
```{r, results='asis', echo=FALSE}
includeSourceDocuments()
```
<!-- Don't edit the material above this line -->

**Downloading and Formatting the Data**
```{r}
col_names <- c("p_time", "d_time", "num_passengers", "distance", "p_lat", "p_long", "d_lat", "d_long", "payment_type", "fare", "total")

#yellow taxi data 12/2015
y15_12 <- read.csv('/Users/siyaoma/Desktop/2015/yellow_tripdata_2015-12_clean.csv')
names(y15_12) <- col_names
y15_12<- y15_12 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 11/2015
y15_11 <- read.csv('/Users/siyaoma/Desktop/2015/yellow_tripdata_2015-11_clean.csv')
names(y15_11) <- col_names
y15_11<- y15_11 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 10/2015
y15_10 <- read.csv('/Users/siyaoma/Desktop/2015/yellow_tripdata_2015-10_clean.csv')
names(y15_10) <- col_names
y15_10<- y15_10 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 09/2015
y15_09 <- read.csv('/Users/siyaoma/Desktop/2015/yellow_tripdata_2015-09_clean.csv')
names(y15_09) <- col_names
y15_09<- y15_09 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 08/2015
y15_08 <- read.csv('/Users/siyaoma/Desktop/2015/yellow_tripdata_2015-08_clean.csv')
names(y15_08) <- col_names
y15_08<- y15_08 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 07/2015
y15_07 <- read.csv('/Users/siyaoma/Desktop/2015/yellow_tripdata_2015-07_clean.csv')
names(y15_07) <- col_names
y15_07<- y15_07 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 06/2015
y15_06 <- read.csv('/Users/siyaoma/Desktop/2015/yellow_tripdata_2015-06_clean.csv')
names(y15_06) <- col_names
y15_06<- y15_06 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 05/2015
y15_05 <- read.csv('/Users/siyaoma/Desktop/2015/yellow_tripdata_2015-05_clean.csv')
names(y15_05) <- col_names
y15_05 <- y15_05 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 04/2015
y15_04 <- read.csv('/Users/siyaoma/Desktop/2015/yellow_tripdata_2015-04_clean.csv')
names(y15_04) <- col_names
y15_04 <- y15_04 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 03/2015
y15_03 <- read.csv('/Users/siyaoma/Desktop/2015/yellow_tripdata_2015-03_clean.csv')
names(y15_03) <- col_names
y15_03 <- y15_03 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 02/2015
y15_02 <- read.csv('/Users/siyaoma/Desktop/2015/yellow_tripdata_2015-02_clean.csv')
names(y15_02) <- col_names
y15_02 <- y15_02 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 01/2015
y15_01 <- read.csv('/Users/siyaoma/Desktop/2015/yellow_tripdata_2015-01_clean.csv')
names(y15_01) <- col_names
y15_01 <- y15_01 %>%
  mutate(month = lubridate::month(p_time))

y15 <- rbind(y15_12, y15_11, y15_10, y15_09, y15_08, y15_07, y15_06, y15_05, y15_04, y15_03, y15_02, y15_01)

y15 <- y15 %>%
  mutate(taxi_color = "yellow") %>%
  mutate(yday = lubridate::yday(p_time)) %>%
  mutate(mday = lubridate::mday(p_time)) %>%
  mutate(weekday = lubridate::wday(p_time)) %>%
  mutate(hour = str_sub(p_time, -9, -7))
```

```{r}
col_names <- c("p_time", "d_time", "p_lat", "p_long", "d_lat", "d_long", "num_passengers", "distance", "fare", "total", "payment_type")

#green taxi data 12/2015
g15_12 <- read.csv('/Users/siyaoma/Desktop/2015/green_tripdata_2015-12_clean.csv')
names(g15_12) <- col_names
g15_12<- g15_12 %>%
  mutate(month = lubridate::month(p_time))

#green taxi data 11/2015
g15_11 <- read.csv('/Users/siyaoma/Desktop/2015/green_tripdata_2015-11_clean.csv')
names(g15_11) <- col_names
g15_11<- g15_11 %>%
  mutate(month = lubridate::month(p_time))

#green taxi data 10/2015
g15_10 <- read.csv('/Users/siyaoma/Desktop/2015/green_tripdata_2015-10_clean.csv')
names(g15_10) <- col_names
g15_10<- g15_10 %>%
  mutate(month = lubridate::month(p_time))

#green taxi data 09/2015
g15_09 <- read.csv('/Users/siyaoma/Desktop/2015/green_tripdata_2015-09_clean.csv')
names(g15_09) <- col_names
g15_09<- g15_09 %>%
  mutate(month = lubridate::month(p_time))

#green taxi data 08/2015
g15_08 <- read.csv('/Users/siyaoma/Desktop/2015/green_tripdata_2015-08_clean.csv')
names(g15_08) <- col_names
g15_08<- g15_08 %>%
  mutate(month = lubridate::month(p_time))

#green taxi data 07/2015
g15_07 <- read.csv('/Users/siyaoma/Desktop/2015/green_tripdata_2015-07_clean.csv')
names(g15_07) <- col_names
g15_07<- g15_07 %>%
  mutate(month = lubridate::month(p_time))

#green taxi data 06/2015
g15_06 <- read.csv('/Users/siyaoma/Desktop/2015/green_tripdata_2015-06_clean.csv')
names(g15_06) <- col_names
g15_06<- g15_06 %>%
  mutate(month = lubridate::month(p_time))

#green taxi data 05/2015
g15_05 <- read.csv('/Users/siyaoma/Desktop/2015/green_tripdata_2015-05_clean.csv')
names(g15_05) <- col_names
g15_05 <- g15_05 %>%
  mutate(month = lubridate::month(p_time))

#green taxi data 04/2015
g15_04 <- read.csv('/Users/siyaoma/Desktop/2015/green_tripdata_2015-04_clean.csv')
names(g15_04) <- col_names
g15_04 <- g15_04 %>%
  mutate(month = lubridate::month(p_time))

#green taxi data 03/2015
g15_03 <- read.csv('/Users/siyaoma/Desktop/2015/green_tripdata_2015-03_clean.csv')
names(g15_03) <- col_names
g15_03 <- g15_03 %>%
  mutate(month = lubridate::month(p_time))

#green taxi data 02/2015
g15_02 <- read.csv('/Users/siyaoma/Desktop/2015/green_tripdata_2015-02_clean.csv')
names(g15_02) <- col_names
g15_02 <- g15_02 %>%
  mutate(month = lubridate::month(p_time))

#green taxi data 01/2015
g15_01 <- read.csv('/Users/siyaoma/Desktop/2015/green_tripdata_2015-01_clean.csv')
names(g15_01) <- col_names
g15_01 <- g15_01 %>%
  mutate(month = lubridate::month(p_time))

g15 <- rbind(g15_12, g15_11, g15_10, g15_09, g15_08, g15_07, g15_06, g15_05, g15_04, g15_03, g15_02, g15_01)

g15 <- g15 %>%
  mutate(taxi_color = "green") %>%
  mutate(yday = lubridate::yday(p_time)) %>%
  mutate(mday = lubridate::mday(p_time)) %>%
  mutate(weekday = lubridate::wday(p_time)) %>%
  mutate(hour = str_sub(p_time, -9, -7))
```

```{r}
tot15 <- rbind(y15, g15)
```

**Fares**
```{r}
#total amount paid (including surchage, tolls, etc) v. distance traveled
#outliers filtered out

tot15 %>% #entire year
  ggplot(aes(y = total, x = distance)) +
  geom_point() +
  geom_smooth(se = FALSE) +
  ggtitle("Amount v. Distance - Entire Year w/ outliers")

tot15 %>% #entire year
  ggplot(aes(y = total, x = distance, color = taxi_color)) +
  geom_point() +
  geom_smooth(se = FALSE) +
  ggtitle("Amount v. Distance - Entire Year w/ outliers (Green v. Yellow Taxi)")

tot15 %>% #faceted by month
  ggplot(aes(y = total, x = distance)) +
  geom_point() +
  geom_smooth(se = FALSE) +
  facet_wrap(~ month) +
  ggtitle("Amount v. Distance - Monthly w/ outliers")
```

**OUTLIERS FILTERED OUT FOR ALL SUBSEQUENT GRAPHS**
```{r}
tot15 <- tot15 %>%
  filter(distance < 50, total > 0, total < 100) 

tot15 %>% #entire year, without outliers
  ggplot(aes(y = total, x = distance)) +
  geom_point() +
  geom_smooth(se = FALSE) + 
  ggtitle("Amount v. Distance - Entire Year")

tot15 %>% #faceted by month, without outliers
  ggplot(aes(y = total, x = distance)) +
  geom_point() +
  geom_smooth(se = FALSE) +
  facet_wrap(~ month) + 
  ggtitle("Amount v. Distance - Monthly")
```

```{r}
#average fare by month, without outliers
tot15_month_ave_fare <- tot15 %>%
  group_by(month)%>%
  summarize(ave=mean(total))

tot15_month_ave_fare %>%
  ggplot(aes(x=month, y=ave)) +
  geom_point() +
  geom_line() +
  scale_x_continuous(breaks=seq(1,12,1)) + 
  ggtitle("Average Fare v. Month")

#average fare by day of the week, without outliers
tot15_day_ave_fare <- tot15 %>%
  group_by(weekday)%>%
  summarize(ave=mean(total))
  
tot15_day_ave_fare %>%
  ggplot(aes(x=weekday, y=ave)) +
  geom_point() +
  geom_line() +
  scale_x_continuous(breaks=seq(1,7,1)) + 
  ggtitle("Average Fare v. Day")

tot15_day_ave_fare %>%
  ggplot(aes(x=weekday, y=ave)) +
  geom_bar(stat ="identity") +
  scale_x_continuous(breaks=seq(1,7,1)) + 
  ggtitle("Average Fare v. Day")

#average fare by time of day, without outliers
tot15_hour_ave_fare <- tot15 %>%
  group_by(hour) %>%
  summarize(ave=mean(total))

tot15_hour_ave_fare %>%
  ggplot(aes(x=hour, y=ave)) +
  geom_point() +
  geom_line() +
  ggtitle("Average Fare v. Hour")

tot15_hour_ave_fare %>%
  ggplot(aes(x=hour, y=ave)) +
  geom_bar(stat ="identity") + 
  ggtitle("Average Fare v. Hour")
```

**Trip Length**
```{r}
#average trip length by month, without outliers
tot15_month_ave_dist <- tot15 %>%
  filter(distance > 0, distance < 50) %>%
  group_by(month)%>%
  summarize(ave=mean(distance))

tot15_month_ave_dist %>%
  ggplot(aes(x=month, y=ave)) +
  geom_point() +
  geom_line() + 
  scale_x_continuous(breaks=seq(1,12,1)) + 
  ggtitle("Average Trip Length v. Month")

tot15_month_ave_dist %>%
  ggplot(aes(x=month, y=ave)) +
  geom_bar(stat ="identity") + 
  scale_x_continuous(breaks=seq(1,12,1)) + 
  ggtitle("Average Trip Length v. Month")

#average trip length by day of the week, without outliers
tot15_day_ave_dist <- tot15 %>%
  filter(distance > 0, distance < 50) %>%
  group_by(weekday)%>%
  summarize(ave=mean(distance))

tot15_day_ave_dist %>%
  ggplot(aes(x=weekday, y=ave)) +
  geom_point() +
  geom_line() +
  scale_x_continuous(breaks=seq(1,7,1)) + 
  ggtitle("Average Trip Length v. Day")

tot15_day_ave_dist %>%
  ggplot(aes(x=weekday, y=ave)) +
  geom_bar(stat ="identity") + 
  scale_x_continuous(breaks=seq(1,7,1)) + 
  ggtitle("Average Trip Length v. Day")

#average trip length by time of day
tot15_hour_ave_dist <- tot15 %>%
  filter(distance > 0, distance < 50) %>%
  group_by(hour) %>%
  summarize(ave=mean(distance))

tot15_hour_ave_dist %>%
  ggplot(aes(x=hour, y=ave)) +
  geom_point() +
  geom_line() + 
  ggtitle("Average Trip Length v. Hour")

tot15_hour_ave_dist %>%
  ggplot(aes(x=hour, y=ave)) +
  geom_bar(stat ="identity") + 
  ggtitle("Average Trip Length v. Hour")
```

**Number of Trips**
```{r}
#total number of taxi rides for each day of the year 2015
tot15_year <- tot15 %>%
  group_by(yday) %>%
  summarise(tot = n())

tot15_year %>%
  ggplot(aes(y = tot, x = yday, col = yday)) +
  geom_bar(stat ="identity") + 
  ggtitle("Number of Trips v. Day of Year")

tot15_year %>%
  ggplot(aes(y = tot, x = yday, col = yday)) +
  geom_line() + 
  ggtitle("Number of Trips v. Day of Year")

#total number of taxi rides per month
tot15_month <- tot15 %>%
  group_by(mday) %>%
  summarise(tot = n()) 

tot15_month %>%
  ggplot(aes(y = tot, x = mday, col = mday)) +
  geom_bar(stat ="identity") +
  scale_x_continuous(breaks=seq(1,12,1)) + 
  ggtitle("Number of Trips v. Month")

#total number of taxi rides for each day of week
tot15_day <- tot15 %>%
  group_by(weekday) %>%
  summarise(tot = n())

tot15_day %>%
  ggplot(aes(y = tot, x = weekday, col = weekday)) +
  geom_bar(stat ="identity") +
  scale_x_continuous(breaks=seq(1,7,1)) + 
  ggtitle("Number of Trips v. Day of Week")

#total number of taxi rides for each day of the week (normalized)
total <- sum(tot15_day$tot)
tot15_day_ave <- tot15_day %>%
  mutate(ave = tot15_day$tot/total)

tot15_day_ave %>%
  ggplot(aes(y = ave, x = weekday)) +
  geom_bar(stat ="identity") +
  scale_x_continuous(breaks=seq(1,7,1)) + 
  ggtitle("Number of Trips v. Day of Week - Normalized")

#total number of taxi rides per hour
tot15_hour <- tot15 %>%
  group_by(hour, weekday) %>%
  summarise(tot = n())

tot15_hour %>%
  ggplot(aes(y = tot, x = hour, fill = weekday)) +
  geom_bar(stat ="identity") + 
  ggtitle("Number of Trips v. Hour")

#total number of taxi rides per hour (normalized) 
tot15_hour_ave <- tot15 %>%
  group_by(hour) %>%
  summarise(tot = n()) %>%
  mutate(ave = tot/sum(tot))

tot15_hour_ave %>%
  ggplot(aes(y = ave, x = hour)) +
  geom_bar(stat ="identity") + 
  ggtitle("Number of Trips v. Hour - Normalized")
```

**Number of Passengers**
```{r}
#number of passengers per day of year
tot15_passengers_year <- tot15 %>%
  group_by(yday) %>%
  summarize(tot = sum(num_passengers))
  
tot15_passengers_year %>%
  ggplot(aes(x = yday, y = tot)) +
  geom_bar(stat ="identity") + 
  ggtitle("Number of Passengers v. Day of Year")

#number of passengers per month
tot15_passengers_month <- tot15 %>%
  group_by(month) %>%
  summarize(tot = sum(num_passengers))
  
tot15_passengers_month %>%
  ggplot(aes(x = month, y = tot)) +
  geom_bar(stat ="identity") + 
  scale_x_continuous(breaks=seq(1,12,1)) + 
  ggtitle("Number of Passengers v. Month")

#number of passengers per weekday
tot15_passengers_day <- tot15 %>%
  group_by(weekday) %>%
  summarize(tot = sum(num_passengers))
  
tot15_passengers_day %>%
  ggplot(aes(x = weekday, y = tot)) +
  geom_bar(stat ="identity") + 
  scale_x_continuous(breaks=seq(1,7,1)) + 
  ggtitle("Number of Passengers v. Day of Week")

#number of passengers per hour
tot15_passengers_hour <- tot15 %>%
  group_by(hour) %>%
  summarize(tot = sum(num_passengers))
  
tot15_passengers_hour %>%
  ggplot(aes(x = hour, y = tot)) +
  geom_bar(stat ="identity") + 
  ggtitle("Number of Passengers v. Hour")
```