NYC Bike Analysis

# Load libraries
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(readr)

# Read in the CSV data
data <- read_csv("NYC-2016-Summary.csv")

## Rows: 276798 Columns: 5

## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (2): day_of_week, user_type
## dbl (3): duration, month, hour
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

# Convert month to 3-letter abbreviations
month_levels <- c("Jan", "Feb", "Mar", "Apr", "May", "Jun", 
                  "Jul", "Aug", "Sep", "Oct", "Nov", "Dec")
#Convert month to factor 
data <- data %>%
  mutate(
    month = factor(month_levels[month], levels = month_levels, ordered = TRUE)
  )

# Reformat hour as "__:00" time of day
# Convert hour to factor
data <- data %>%
  mutate(
    hour = sprintf("%02d:00", hour),
    hour = factor(hour, levels = sprintf("%02d:00", 0:23), ordered = TRUE)
  )

# Order days starting from Monday or Sunday
day_levels <- c("Monday", "Tuesday", "Wednesday", "Thursday", "Friday", "Saturday", "Sunday")
# Convert day_of_week to factor
data <- data %>%
  mutate(
    day_of_week = factor(day_of_week, levels = day_levels, ordered = TRUE)
  )

# Convert user_type to factor 
user_levels <- c("Subscriber", "Customer")

data <- data %>%
  mutate(
    user_type = factor(user_type, levels = user_levels)
  )

# Test the levels for each factor to confirm correct ordering and no typos
levels(data$month)

##  [1] "Jan" "Feb" "Mar" "Apr" "May" "Jun" "Jul" "Aug" "Sep" "Oct" "Nov" "Dec"

levels(data$hour)

##  [1] "00:00" "01:00" "02:00" "03:00" "04:00" "05:00" "06:00" "07:00" "08:00"
## [10] "09:00" "10:00" "11:00" "12:00" "13:00" "14:00" "15:00" "16:00" "17:00"
## [19] "18:00" "19:00" "20:00" "21:00" "22:00" "23:00"

levels(data$day_of_week)

## [1] "Monday"    "Tuesday"   "Wednesday" "Thursday"  "Friday"    "Saturday" 
## [7] "Sunday"

levels(data$user_type)

## [1] "Subscriber" "Customer"