visualization project

library(janitor)

## 
## Attaching package: 'janitor'

## The following objects are masked from 'package:stats':
## 
##     chisq.test, fisher.test

library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.5.2     ✔ tibble    3.3.0
## ✔ lubridate 1.9.4     ✔ tidyr     1.3.1
## ✔ purrr     1.0.4

## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

tvshows<-read_csv("tvshows.csv")

## Rows: 40 Columns: 6
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (3): Show, Network, Genre
## dbl (3): PE, GRP, Duration
## 
## 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.

tvshows<-read_csv("tvshows.csv")

## Rows: 40 Columns: 6
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (3): Show, Network, Genre
## dbl (3): PE, GRP, Duration
## 
## 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.

head(tvshows)

## # A tibble: 6 × 6
##   Show                               Network    PE   GRP Genre          Duration
##   <chr>                              <chr>   <dbl> <dbl> <chr>             <dbl>
## 1 Living with Ed                     HGTV     54   151   Reality              30
## 2 Monarch Cove                       LIFE     64.6 376.  Drama/Adventu…       60
## 3 Top Chef                           BRAVO    78.6 808.  Reality              60
## 4 Iron Chef America                  FOOD     62.6  17.3 Reality              30
## 5 Trading Spaces: All Stars          TLC      56    44.1 Reality              60
## 6 Lisa Williams: Life Among the Dead LIFE     56.2 383.  Reality              60

ggplot(tvshows,aes(GRP,PE))+
  geom_point()

ggplot(tvshows,aes(GRP,PE,col))+
  geom_point()

ggplot(tvshows,aes(GRP,PE,shape=Genre))+
  geom_point()

ggplot(tvshows,aes(GRP,PE))+
  geom_point()+
  facet_wrap(~Genre)

power_christmas2015<-read_csv("power_christmas2015.csv")

## Rows: 24 Columns: 2
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## dbl (2): hour, ERCOT
## 
## 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.

head(power_christmas2015)

## # A tibble: 6 × 2
##    hour  ERCOT
##   <dbl>  <dbl>
## 1     0 31209.
## 2     1 29631.
## 3     2 28487.
## 4     3 27650.
## 5     4 27212.
## 6     5 27234.

ggplot(power_christmas2015,aes(hour,ERCOT))+
  geom_line()

rapidcity<-read_csv("rapidcity.csv")

## Rows: 6159 Columns: 4
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## dbl (4): Year, Month, Day, Temp
## 
## 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.

head(rapidcity)

## # A tibble: 6 × 4
##    Year Month   Day  Temp
##   <dbl> <dbl> <dbl> <dbl>
## 1  1995     1     1  12.6
## 2  1995     1     2  19.9
## 3  1995     1     3   9.2
## 4  1995     1     4   6.2
## 5  1995     1     5  16  
## 6  1995     1     6  17.8

ggplot(rapidcity,aes(Temp))+
  geom_histogram()

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

ggplot(rapidcity,aes(Temp),binwidth=1)+
  geom_histogram()

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

ggplot(rapidcity,aes(Temp),binwidth=20)+
  geom_histogram()

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

ggplot(rapidcity,aes(Temp),binwidth=3)+
  geom_histogram()

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

ggplot(rapidcity,aes(Temp),binwidth=3)+
  geom_histogram()+
  facet_wrap(~Month)

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

ggplot(rapidcity, aes(Temp), binwidth=3)+
  geom_histogram()+
  facet_wrap(~Month, nrow = 12)

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.