Graphs.Rmd

---
title: "Graphs - All Years"
author: ""
date: ""
output: 
  html_document:
    fig_height: 3
    fig_width: 5
---
<!-- 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_long", "p_lat", "d_long", "d_lat", "payment_type", "fare", "total")

#yellow taxi data 12/2009
y09_12 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2009-12_clean.csv')
#names(y09_12) <- col_names
y09_12<- y09_12 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 11/2009
y09_11 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2009-11_clean.csv')
#names(y09_11) <- col_names
y09_11<- y09_11 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 10/2009
y09_10 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2009-10_clean.csv')
#names(y09_10) <- col_names
y09_10<- y09_10 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 09/2009
y09_09 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2009-09_clean.csv')
#names(y09_09) <- col_names
y09_09<- y09_09 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 08/2009
y09_08 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2009-08_clean.csv')
#names(y09_08) <- col_names
y09_08<- y09_08 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 07/2009
y09_07 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2009-07_clean.csv')
#names(y09_07) <- col_names
y09_07<- y09_07 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 06/2009
y09_06 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2009-06_clean.csv')
#names(y09_06) <- col_names
y09_06<- y09_06 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 05/2009
y09_05 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2009-05_clean.csv')
#names(y09_05) <- col_names
y09_05 <- y09_05 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 04/2009
y09_04 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2009-04_clean.csv')
#names(y09_04) <- col_names
y09_04 <- y09_04 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 03/2009
y09_03 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2009-03_clean.csv')
#names(y09_03) <- col_names
y09_03 <- y09_03 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 02/2009
y09_02 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2009-02_clean.csv')
#names(y09_02) <- col_names
y09_02 <- y09_02 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 01/2009
y09_01 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2009-01_clean.csv')
#names(y09_01) <- col_names
y09_01 <- y09_01 %>%
  mutate(month = lubridate::month(p_time))

y09 <- rbind(y09_12, y09_11, y09_10, y09_09, y09_08, y09_07, y09_06, y09_05, y09_04, y09_03, y09_02, y09_01)

y09 <- y09 %>%
  mutate(year = 2009) %>%
  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))
```

**Missing Green Taxi Data**
```{r, eval = FALSE}
tot09 <- rbind(y09, g09)
```

```{r}
tot09 <- y09
```

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

#yellow taxi data 12/2010
y10_12 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2010-12_clean.csv')
#names(y10_12) <- col_names
y10_12<- y10_12 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 11/2010
y10_11 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2010-11_clean.csv')
#names(y10_11) <- col_names
y10_11<- y10_11 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 10/2010
y10_10 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2010-10_clean.csv')
#names(y10_10) <- col_names
y10_10<- y10_10 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 09/2010
y10_09 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2010-09_clean.csv')
#names(y10_09) <- col_names
y10_09<- y10_09 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 08/2010
y10_08 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2010-08_clean.csv')
#names(y10_08) <- col_names
y10_08<- y10_08 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 07/2010
y10_07 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2010-07_clean.csv')
#names(y10_07) <- col_names
y10_07<- y10_07 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 06/2010
y10_06 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2010-06_clean.csv')
#names(y10_06) <- col_names
y10_06<- y10_06 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 05/2010
y10_05 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2010-05_clean.csv')
#names(y10_05) <- col_names
y10_05 <- y10_05 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 04/2010
y10_04 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2010-04_clean.csv')
#names(y10_04) <- col_names
y10_04 <- y10_04 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 03/2010
y10_03 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2010-03_clean.csv')
#names(y10_03) <- col_names
y10_03 <- y10_03 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 02/2010
y10_02 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2010-02_clean.csv')
#names(y10_02) <- col_names
y10_02 <- y10_02 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 01/2010
y10_01 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2010-01_clean.csv')
#names(y10_01) <- col_names
y10_01 <- y10_01 %>%
  mutate(month = lubridate::month(p_time))

y10 <- rbind(y10_12, y10_11, y10_10, y10_09, y10_08, y10_07, y10_06, y10_05, y10_04, y10_03, y10_02, y10_01)

y10 <- y10 %>%
  mutate(year = 2010) %>%
  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))
```


**Missing Green Taxi Data**
```{r, eval = FALSE}
tot10 <- rbind(y10, g10)
```

```{r}
tot10 <- y10
```

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

#yellow taxi data 12/2011
y11_12 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2011-12_clean.csv')
#names(y11_12) <- col_names
y11_12<- y11_12 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 11/2011
y11_11 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2011-11_clean.csv')
#names(y11_11) <- col_names
y11_11<- y11_11 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 10/2011
y11_10 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2011-10_clean.csv')
#names(y11_10) <- col_names
y11_10<- y11_10 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 09/2011
y11_09 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2011-09_clean.csv')
#names(y11_09) <- col_names
y11_09<- y11_09 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 08/2011
y11_08 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2011-08_clean.csv')
#names(y11_08) <- col_names
y11_08<- y11_08 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 07/2011
y11_07 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2011-07_clean.csv')
#names(y11_07) <- col_names
y11_07<- y11_07 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 06/2011
y11_06 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2011-06_clean.csv')
#names(y11_06) <- col_names
y11_06<- y11_06 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 05/2011
y11_05 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2011-05_clean.csv')
#names(y11_05) <- col_names
y11_05 <- y11_05 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 04/2011
y11_04 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2011-04_clean.csv')
#names(y11_04) <- col_names
y11_04 <- y11_04 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 03/2011
y11_03 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2011-03_clean.csv')
#names(y11_03) <- col_names
y11_03 <- y11_03 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 02/2011
y11_02 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2011-02_clean.csv')
#names(y11_02) <- col_names
y11_02 <- y11_02 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 01/2011
y11_01 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2011-01_clean.csv')
#names(y11_01) <- col_names
y11_01 <- y11_01 %>%
  mutate(month = lubridate::month(p_time))

y11 <- rbind(y11_12, y11_11, y11_10, y11_09, y11_08, y11_07, y11_06, y11_05, y11_04, y11_03, y11_02, y11_01)

y11 <- y11 %>%
  mutate(year = 2011) %>%
  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))
```


**Missing Green Taxi Data**
```{r, eval = FALSE}
tot11 <- rbind(y11, g11)
```

```{r}
tot11 <- y11
```

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

#yellow taxi data 12/2012
y12_12 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2012-12_clean.csv')
#names(y12_12) <- col_names
y12_12<- y12_12 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 11/2012
y12_11 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2012-11_clean.csv')
#names(y12_11) <- col_names
y12_11<- y12_11 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 10/2012
y12_10 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2012-10_clean.csv')
#names(y12_10) <- col_names
y12_10<- y12_10 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 09/2012
y12_09 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2012-09_clean.csv')
#names(y12_09) <- col_names
y12_09<- y12_09 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 08/2012
y12_08 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2012-08_clean.csv')
#names(y12_08) <- col_names
y12_08<- y12_08 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 07/2012
y12_07 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2012-07_clean.csv')
#names(y12_07) <- col_names
y12_07<- y12_07 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 06/2012
y12_06 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2012-06_clean.csv')
#names(y12_06) <- col_names
y12_06<- y12_06 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 05/2012
y12_05 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2012-05_clean.csv')
#names(y12_05) <- col_names
y12_05 <- y12_05 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 04/2012
y12_04 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2012-04_clean.csv')
#names(y12_04) <- col_names
y12_04 <- y12_04 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 03/2012
y12_03 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2012-03_clean.csv')
#names(y12_03) <- col_names
y12_03 <- y12_03 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 02/2012
y12_02 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2012-02_clean.csv')
#names(y12_02) <- col_names
y12_02 <- y12_02 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 01/2012
y12_01 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2012-01_clean.csv')
#names(y12_01) <- col_names
y12_01 <- y12_01 %>%
  mutate(month = lubridate::month(p_time))

y12 <- rbind(y12_12, y12_11, y12_10, y12_09, y12_08, y12_07, y12_06, y12_05, y12_04, y12_03, y12_02, y12_01)

y12 <- y12 %>%
  mutate(year = 2012) %>%
  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))
```


**Missing Green Taxi Data**
```{r, eval = FALSE}
tot12 <- rbind(y12, g12)
```

```{r}
tot12 <- y12
```

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

#yellow taxi data 12/2013
y13_12 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2013-12_clean.csv')
#names(y13_12) <- col_names
y13_12<- y13_12 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 11/2013
y13_11 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2013-11_clean.csv')
#names(y13_11) <- col_names
y13_11<- y13_11 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 10/2013
y13_10 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2013-10_clean.csv')
#names(y13_10) <- col_names
y13_10<- y13_10 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 09/2013
y13_09 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2013-09_clean.csv')
#names(y13_09) <- col_names
y13_09<- y13_09 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 08/2013
y13_08 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2013-08_clean.csv')
#names(y13_08) <- col_names
y13_08<- y13_08 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 07/2013
y13_07 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2013-07_clean.csv')
#names(y13_07) <- col_names
y13_07<- y13_07 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 06/2013
y13_06 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2013-06_clean.csv')
#names(y13_06) <- col_names
y13_06<- y13_06 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 05/2013
y13_05 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2013-05_clean.csv')
#names(y13_05) <- col_names
y13_05 <- y13_05 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 04/2013
y13_04 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2013-04_clean.csv')
#names(y13_04) <- col_names
y13_04 <- y13_04 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 03/2013
y13_03 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2013-03_clean.csv')
#names(y13_03) <- col_names
y13_03 <- y13_03 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 02/2013
y13_02 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2013-02_clean.csv')
#names(y13_02) <- col_names
y13_02 <- y13_02 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 01/2013
y13_01 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2013-01_clean.csv')
#names(y13_01) <- col_names
y13_01 <- y13_01 %>%
  mutate(month = lubridate::month(p_time))

y13 <- rbind(y13_12, y13_11, y13_10, y13_09, y13_08, y13_07, y13_06, y13_05, y13_04, y13_03, y13_02, y13_01)

y13 <- y13 %>%
  mutate(year = 2013) %>%
  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))
```


**Missing Green Taxi Data**
```{r, eval = FALSE}
tot13 <- rbind(y13, g13)
```

```{r}
tot13 <- y13
```

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

#yellow taxi data 12/2014
y14_12 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2014-12_clean.csv')
names(y14_12) <- col_names
y14_12<- y14_12 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 11/2014
y14_11 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2014-11_clean.csv')
names(y14_11) <- col_names
y14_11<- y14_11 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 10/2014
y14_10 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2014-10_clean.csv')
names(y14_10) <- col_names
y14_10<- y14_10 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 09/2014
y14_09 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2014-09_clean.csv')
names(y14_09) <- col_names
y14_09<- y14_09 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 08/2014
y14_08 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2014-08_clean.csv')
names(y14_08) <- col_names
y14_08<- y14_08 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 07/2014
y14_07 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2014-07_clean.csv')
names(y14_07) <- col_names
y14_07<- y14_07 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 06/2014
y14_06 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2014-06_clean.csv')
names(y14_06) <- col_names
y14_06<- y14_06 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 05/2014
y14_05 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2014-05_clean.csv')
names(y14_05) <- col_names
y14_05 <- y14_05 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 04/2014
y14_04 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2014-04_clean.csv')
names(y14_04) <- col_names
y14_04 <- y14_04 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 03/2014
y14_03 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2014-03_clean.csv')
names(y14_03) <- col_names
y14_03 <- y14_03 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 02/2014
y14_02 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2014-02_clean.csv')
names(y14_02) <- col_names
y14_02 <- y14_02 %>%
  mutate(month = lubridate::month(p_time))

#yellow taxi data 01/2014
y14_01 <- read.csv('/Users/siyaoma/Desktop/Stats133 Project/Stat133-Final/taxi_data/yellow_tripdata_2014-01_clean.csv')
names(y14_01) <- col_names
y14_01 <- y14_01 %>%
  mutate(month = lubridate::month(p_time))

y14 <- rbind(y14_12, y14_11, y14_10, y14_09, y14_08, y14_07, y14_06, y14_05, y14_04, y14_03, y14_02, y14_01)

y14 <- y14 %>%
  mutate(year = 2014) %>%
  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))
```


**Missing Green Taxi Data**
```{r, eval = FALSE}
tot14 <- rbind(y14, g14)
```

```{r}
tot14 <- y14
```


```{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(year = 2015) %>%
  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, eval = FALSE}
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, eval=FALSE}
tot15 <- rbind(y15, g15)
```

```{r}
tot15 <- y15
```


```{r}
tot <- Reduce(function(x, y) merge(x, y, all=TRUE), list(tot15, tot14, tot13, tot12, tot11, tot10, tot09))
#tot = tot15
#lst <- list(tot14, tot13, tot12, tot11, tot10, tot09)
#lst <- apply(lst, 2, as.numeric())
#for (df in lst) {
#  tot <- left_join(tot, df, by = c("p_time", "d_time", "p_lat", "p_long", #"d_lat", "d_long", "num_passengers", "distance", "total"))
#}
```

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

tot %>% #all years
  ggplot(aes(y = total, x = distance)) +
  geom_point() +
  geom_smooth(se = FALSE) +
  ggtitle("Amount v. Distance - All w/ outliers")

tot %>% #all years
  ggplot(aes(y = total, x = distance, color = taxi_color)) +
  geom_point() +
  geom_smooth(se = FALSE) +
  ggtitle("Amount v. Distance - All w/ outliers (Green v. Yellow Taxi)")

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

tot %>% #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}
tot <- tot %>%
  filter(distance < 50, total > 0, total < 100) 

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

tot %>% #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
tot_month_ave_fare <- tot %>%
  group_by(month)%>%
  summarize(ave=mean(total))

tot_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
tot_day_ave_fare <- tot %>%
  group_by(weekday)%>%
  summarize(ave=mean(total))
  
tot_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")

tot_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
tot_hour_ave_fare <- tot %>%
  group_by(hour) %>%
  summarize(ave=mean(total))

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

tot_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
tot_month_ave_dist <- tot %>%
  filter(distance > 0, distance < 50) %>%
  group_by(month)%>%
  summarize(ave=mean(distance))

tot_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")

tot_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
tot_day_ave_dist <- tot %>%
  filter(distance > 0, distance < 50) %>%
  group_by(weekday)%>%
  summarize(ave=mean(distance))

tot_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")

tot_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
tot_hour_ave_dist <- tot %>%
  filter(distance > 0, distance < 50) %>%
  group_by(hour) %>%
  summarize(ave=mean(distance))

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

tot_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
tot_year <- tot %>%
  group_by(yday) %>%
  summarise(tot = n())

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

tot_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
tot_month <- tot %>%
  group_by(mday) %>%
  summarise(tot = n()) 

tot_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
tot_day <- tot %>%
  group_by(weekday) %>%
  summarise(tot = n())

tot_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(tot_day$tot)
tot_day_ave <- tot_day %>%
  mutate(ave = tot_day$tot/total)

tot_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
tot_hour <- tot %>%
  group_by(hour, weekday) %>%
  summarise(tot = n())

tot_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) 
tot_hour_ave <- tot %>%
  group_by(hour) %>%
  summarise(tot = n()) %>%
  mutate(ave = tot/sum(tot))

tot_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
tot_passengers_year <- tot %>%
  group_by(yday) %>%
  summarize(tot = sum(num_passengers))
  
tot_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
tot_passengers_month <- tot %>%
  group_by(month) %>%
  summarize(tot = sum(num_passengers))
  
tot_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
tot_passengers_day <- tot %>%
  group_by(weekday) %>%
  summarize(tot = sum(num_passengers))
  
tot_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
tot_passengers_hour <- tot %>%
  group_by(hour) %>%
  summarize(tot = sum(num_passengers))
  
tot_passengers_hour %>%
  ggplot(aes(x = hour, y = tot)) +
  geom_bar(stat ="identity") + 
  ggtitle("Number of Passengers v. Hour")
```