getwd()
## [1] "/Users/victoriaecheverri/Desktop/UTSA Classes/Applied Quantitative Methods/My Class Stuff/Monday Class/victoriasustainabilitydata"
library(readr)
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(pastecs)
##
## Attaching package: 'pastecs'
## The following objects are masked from 'package:dplyr':
##
## first, last
bike_trend <- read_csv("bike_trend.csv")
## Rows: 198 Columns: 3
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## dbl (2): Bicycling_Trips, Rolling_Avg
## date (1): date
##
## 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.
For this assignment, I selected the variable
Bicycling_Trips from the bike_trend.csv
dataset. This variable measures the total number of bicycling trips
recorded for each observation in the data. It is useful because it
provides a direct measure of bicycling activity over time and helps
describe patterns in transportation behavior.
library(readr)
library(dplyr)
library(pastecs)
bike_trend <- read_csv("bike_trend.csv")
## Rows: 198 Columns: 3
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## dbl (2): Bicycling_Trips, Rolling_Avg
## date (1): date
##
## 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.
stat.desc(bike_trend$Bicycling_Trips)
## nbr.val nbr.null nbr.na min max range
## 198.0000000 0.0000000 0.0000000 1.0000000 24.0000000 23.0000000
## sum median mean SE.mean CI.mean.0.95 var
## 1500.0000000 6.0000000 7.5757576 0.3509556 0.6921123 24.3876327
## std.dev coef.var
## 4.9383836 0.6518666
bike_trend_clean <- bike_trend %>%
filter(!is.na(Bicycling_Trips))
hist(bike_trend_clean$Bicycling_Trips,
main = "Histogram of Bicycling Trips",
xlab = "Bicycling Trips")
bike_trend_clean <- bike_trend_clean %>%
mutate(log_Bicycling_Trips = log(Bicycling_Trips + 1))
hist(bike_trend_clean$log_Bicycling_Trips,
main = "Histogram of Log-Transformed Bicycling Trips",
xlab = "Log(Bicycling Trips + 1)")