Discussion 11

Linear regression on nyc-east-river-bicycle-counts data set

Is the bikers on Manhattan Bridge dependent on high temperature on each day?

bikes <- read_csv("/Users/bchand005c/CUNY/DATA-605/assignment/week-11/nyc-east-river-bicycle-counts.csv")

## Warning: Missing column names filled in: 'X1' [1]

## Parsed with column specification:
## cols(
##   X1 = col_integer(),
##   Date = col_datetime(format = ""),
##   Day = col_datetime(format = ""),
##   `High Temp (°F)` = col_double(),
##   `Low Temp (°F)` = col_double(),
##   Precipitation = col_character(),
##   `Brooklyn Bridge` = col_double(),
##   `Manhattan Bridge` = col_integer(),
##   `Williamsburg Bridge` = col_double(),
##   `Queensboro Bridge` = col_double(),
##   Total = col_integer()
## )

head(bikes)

## # A tibble: 6 x 11
##      X1 Date                Day                 `High Temp (°F)`
##   <int> <dttm>              <dttm>                         <dbl>
## 1     0 2016-04-01 00:00:00 2016-04-01 00:00:00             78.1
## 2     1 2016-04-02 00:00:00 2016-04-02 00:00:00             55  
## 3     2 2016-04-03 00:00:00 2016-04-03 00:00:00             39.9
## 4     3 2016-04-04 00:00:00 2016-04-04 00:00:00             44.1
## 5     4 2016-04-05 00:00:00 2016-04-05 00:00:00             42.1
## 6     5 2016-04-06 00:00:00 2016-04-06 00:00:00             45  
## # ... with 7 more variables: `Low Temp (°F)` <dbl>, Precipitation <chr>,
## #   `Brooklyn Bridge` <dbl>, `Manhattan Bridge` <int>, `Williamsburg
## #   Bridge` <dbl>, `Queensboro Bridge` <dbl>, Total <int>

ggplot(data = bikes, aes(x = `High Temp (°F)`, y = `Manhattan Bridge`)) + 
        geom_point(color='blue') +
        geom_smooth(method = "lm", se = FALSE)

fit <- lm(`Manhattan Bridge` ~ `High Temp (°F)`, data = bikes)

autoplot(fit)