R Notebook

library(ggplot2)
library(ggthemes)
library(lubridate)

Attaching package: ‘lubridate’

The following objects are masked from ‘package:base’:

    date, intersect, setdiff, union

library(dplyr)

Attaching package: ‘dplyr’

The following objects are masked from ‘package:stats’:

    filter, lag

The following objects are masked from ‘package:base’:

    intersect, setdiff, setequal, union

library(tidyr)
library(tidyverse) # metapackage of all tidyverse packages

Registered S3 methods overwritten by 'dbplyr':
  method         from
  print.tbl_lazy     
  print.tbl_sql      
-- Attaching packages ----------------------------- tidyverse 1.3.1 --
√ tibble  3.1.6     √ stringr 1.4.0
√ readr   2.1.2     √ forcats 0.5.1
√ purrr   0.3.4     
-- Conflicts -------------------------------- tidyverse_conflicts() --
x lubridate::as.difftime() masks base::as.difftime()
x lubridate::date()        masks base::date()
x dplyr::filter()          masks stats::filter()
x lubridate::intersect()   masks base::intersect()
x dplyr::lag()             masks stats::lag()
x lubridate::setdiff()     masks base::setdiff()
x lubridate::union()       masks base::union()

library(DT)

Registered S3 method overwritten by 'htmlwidgets':
  method           from         
  print.htmlwidget tools:rstudio

library(scales)

Attaching package: ‘scales’

The following object is masked from ‘package:purrr’:

    discard

The following object is masked from ‘package:readr’:

    col_factor

colors = c("#CC1011", "#665555", "#05a399", "#cfcaca", "#f5e840", "#0683c9", "#e075b0")


# Read the data for each month separately 
apr <- read.csv("./uber-raw-data-apr14.csv")
may <- read.csv("./uber-raw-data-may14.csv")
june <- read.csv("./uber-raw-data-jun14.csv")
july <- read.csv("./uber-raw-data-jul14.csv")
aug <- read.csv("./uber-raw-data-aug14.csv")
sept <- read.csv("./uber-raw-data-sep14.csv")

# Combine the data together 
data <- rbind(apr, may, june, july, aug, sept)
cat("The dimensions of the data are:", dim(data))

The dimensions of the data are: 4534327 4

# Look at the data
head(data)

data$Date.Time <- as.POSIXct(data$Date.Time, format="%m/%d/%Y %H:%M:%S")
data$Time <- format(as.POSIXct(data$Date.Time, format = "%m/%d/%Y %H:%M:%S"), format="%H:%M:%S")
data$Date.Time <- ymd_hms(data$Date.Time)


# Create individual columns for month day and year
data$day <- factor(day(data$Date.Time))
data$month <- factor(month(data$Date.Time, label=TRUE))
data$year <- factor(year(data$Date.Time))
data$dayofweek <- factor(wday(data$Date.Time, label=TRUE))

# Add Time variables as well 
data$second = factor(second(hms(data$Time)))
data$minute = factor(minute(hms(data$Time)))
data$hour = factor(hour(hms(data$Time)))

head(data)

# Plotting the trips by hours in a day
hourly_data <- data %>% 
                    group_by(hour) %>% 
                            dplyr::summarize(Total = n())

# Shows data in a searchable js table
datatable(hourly_data)

# Plot the data by hour
ggplot(hourly_data, aes(hour, Total)) + 
geom_bar(stat="identity", 
         fill="steelblue", 
         color="red") + 
ggtitle("Trips Every Hour", subtitle = "aggregated today") + 
theme(legend.position = "none", 
      plot.title = element_text(hjust = 0.5), 
      plot.subtitle = element_text(hjust = 0.5)) + 
scale_y_continuous(labels=comma)

# Aggregate the data by month and hour
month_hour_data <- data %>% group_by(month, hour) %>%  dplyr::summarize(Total = n())

`summarise()` has grouped output by 'month'. You can override using
the `.groups` argument.

ggplot(month_hour_data, aes(hour, Total, fill=month)) + 
geom_bar(stat = "identity") + 
ggtitle("Trips by Hour and Month") + 
scale_y_continuous(labels = comma)

# Aggregate data by day of the month 
day_data <- data %>% group_by(day) %>% dplyr::summarize(Trips = n())
day_data

# Plot the data for the day
ggplot(day_data, aes(day, Trips)) + 
geom_bar(stat = "identity", fill = "steelblue") +
ggtitle("Trips by day of the month") + 
theme(legend.position = "none") + 
scale_y_continuous(labels = comma)

day_month_data <- data %>% group_by(dayofweek, month) %>% dplyr::summarize(Trips = n())

`summarise()` has grouped output by 'dayofweek'. You can override
using the `.groups` argument.

day_month_data

# Plot the above data
ggplot(day_month_data, aes(dayofweek, Trips, fill = month)) + 
geom_bar(stat = "identity", aes(fill = month), position = "dodge") + 
ggtitle("Trips by Day and Month") + 
scale_y_continuous(labels = comma) + 
scale_fill_manual(values = colors)

month_data <- data %>% group_by(month) %>% dplyr::summarize(Total = n())

month_data

ggplot(month_data, aes(month, Total, fill = month)) + 
geom_bar(stat = "Identity") + 
ggtitle("Trips in a month") + 
theme(legend.position = "none") + 
scale_y_continuous(labels = comma) + 
scale_fill_manual(values = colors)

day_hour_data <- data %>% group_by(day, hour) %>% dplyr::summarize(Total = n())

`summarise()` has grouped output by 'day'. You can override using the
`.groups` argument.

datatable(day_hour_data)

ggplot(day_hour_data, aes(day, hour, fill = Total)) + 
geom_tile(color = "white") + 
ggtitle("Heat Map by Hour and Day")

# Collect data by month and day

month_day_data <- data %>% group_by(month, day) %>% dplyr::summarize(Trips = n())

`summarise()` has grouped output by 'month'. You can override using
the `.groups` argument.

month_day_data

# Plot a heatmap 

ggplot(month_day_data, aes(day, month, fill = Trips)) + 
geom_tile(color = "white") + 
ggtitle("Heat Map by Month and Day")

# Plot a heatmap by day of the week and month

ggplot(day_month_data, aes(dayofweek, month, fill = Trips)) + 
geom_tile(color = "white") + 
ggtitle("Heat Map by Month and Day of weak")

###### CREATING A MAP VISUALIZATION #####

# Set Map Constants
min_lat <- 40 
max_lat <- 40.91
min_long <- -74.15
max_long <- -73.7004

ggplot(data, aes(x=Lon, y=Lat)) +
  geom_point(size=1, color = "blue") +
     scale_x_continuous(limits=c(min_long, max_long)) +
      scale_y_continuous(limits=c(min_lat, max_lat)) +
        theme_map() +
           ggtitle("NYC MAP BASED ON UBER RIDES DURING 2014 (APR-SEP)")

Warning: Removed 70180 rows containing missing values (geom_point).

ggplot(data, aes(x=Lon, y=Lat, color = Base)) +
  geom_point(size=1) +
     scale_x_continuous(limits=c(min_long, max_long)) +
      scale_y_continuous(limits=c(min_lat, max_lat)) +
       theme_map() +
          ggtitle("NYC MAP BASED ON UBER RIDES DURING 2014 (APR-SEP) by BASE")

Warning: Removed 70180 rows containing missing values (geom_point).