library(readr)
## Warning: replacing previous import 'lifecycle::last_warnings' by
## 'rlang::last_warnings' when loading 'tibble'
## Warning: replacing previous import 'ellipsis::check_dots_unnamed' by
## 'rlang::check_dots_unnamed' when loading 'tibble'
## Warning: replacing previous import 'ellipsis::check_dots_used' by
## 'rlang::check_dots_used' when loading 'tibble'
## Warning: replacing previous import 'ellipsis::check_dots_empty' by
## 'rlang::check_dots_empty' when loading 'tibble'
## Warning: replacing previous import 'lifecycle::last_warnings' by
## 'rlang::last_warnings' when loading 'pillar'
## Warning: replacing previous import 'ellipsis::check_dots_unnamed' by
## 'rlang::check_dots_unnamed' when loading 'pillar'
## Warning: replacing previous import 'ellipsis::check_dots_used' by
## 'rlang::check_dots_used' when loading 'pillar'
## Warning: replacing previous import 'ellipsis::check_dots_empty' by
## 'rlang::check_dots_empty' when loading 'pillar'
library(readxl)
library(tidyverse)
## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.0 ──
## ✓ ggplot2 3.3.2 ✓ dplyr 1.0.2
## ✓ tibble 3.0.4 ✓ stringr 1.4.0
## ✓ tidyr 1.1.2 ✓ forcats 0.5.0
## ✓ purrr 0.3.4
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()
library(janitor)
##
## Attaching package: 'janitor'
## The following objects are masked from 'package:stats':
##
## chisq.test, fisher.test
library(ggplot2)
#Top 5 big events
JANIEVENTS <- read_csv("JANI Volunteer data set - Results.csv") %>%
janitor::clean_names() %>%
mutate(percentage = `contact_hours` * `students`) %>%
arrange(desc(percentage))
##
## ── Column specification ────────────────────────────────────────────────────────
## cols(
## `Program Year` = col_character(),
## Company = col_character(),
## School = col_character(),
## Grade = col_character(),
## Program = col_character(),
## `Class ID` = col_character(),
## `Contact hours` = col_double(),
## Students = col_double()
## )
## Warning: 374 parsing failures.
## row col expected actual file
## 1402 Students no trailing characters 3,763 'JANI Volunteer data set - Results.csv'
## 1425 Students no trailing characters 3,763 'JANI Volunteer data set - Results.csv'
## 1617 Students no trailing characters 2,729 'JANI Volunteer data set - Results.csv'
## 1618 Students no trailing characters 2,729 'JANI Volunteer data set - Results.csv'
## 1619 Students no trailing characters 2,729 'JANI Volunteer data set - Results.csv'
## .... ........ ...................... ...... .......................................
## See problems(...) for more details.
JANIEVENTS <- filter(JANIEVENTS, percentage >= 3666)
JANIEVENTS
## # A tibble: 14 x 9
## program_year company school grade program class_id contact_hours students
## <chr> <chr> <chr> <chr> <chr> <chr> <dbl> <dbl>
## 1 Program yea… Midwes… Tippe… 12 JA Eco… CL-5818… 72 53
## 2 Program yea… Allen … Wabas… 9 JA Ins… CL-1424… 6 611
## 3 Program yea… Chase Wabas… 9 JA Ins… CL-1424… 6 611
## 4 Program yea… Coldwe… Wabas… 9 JA Ins… CL-1424… 6 611
## 5 Program yea… Conten… Wabas… 9 JA Ins… CL-1424… 6 611
## 6 Program yea… Fort F… Wabas… 9 JA Ins… CL-1424… 6 611
## 7 Program yea… Indian… Wabas… 9 JA Ins… CL-1424… 6 611
## 8 Program yea… Indian… Wabas… 9 JA Ins… CL-1424… 6 611
## 9 Program yea… Nation… Wabas… 9 JA Ins… CL-1424… 6 611
## 10 Program yea… Nation… Wabas… 9 JA Ins… CL-1424… 6 611
## 11 Program yea… Northe… Wabas… 9 JA Ins… CL-1424… 6 611
## 12 Program yea… Northe… Wabas… 9 JA Ins… CL-1424… 6 611
## 13 Program yea… One Lu… Wabas… 9 JA Ins… CL-1424… 6 611
## 14 Program yea… The Wo… Wabas… 9 JA Ins… CL-1424… 6 611
## # … with 1 more variable: percentage <dbl>
ggplot(JANIEVENTS, aes(x = company)) +
geom_boxplot()
ggplot(JANIEVENTS, aes(x = company,
y = percentage)) +
geom_col() +
labs(
x = "company",
y = "percentage",
title = "Each Company's Percentage (contact hours * students)",
subtitle = "Top Companies"
)
#Top 5 interactions
JANIINTERACTIONS <- read_csv("JANI Volunteer data set - Results.csv") %>%
janitor::clean_names() %>%
count(company) %>%
arrange(desc(n))
##
## ── Column specification ────────────────────────────────────────────────────────
## cols(
## `Program Year` = col_character(),
## Company = col_character(),
## School = col_character(),
## Grade = col_character(),
## Program = col_character(),
## `Class ID` = col_character(),
## `Contact hours` = col_double(),
## Students = col_double()
## )
## Warning: 374 parsing failures.
## row col expected actual file
## 1402 Students no trailing characters 3,763 'JANI Volunteer data set - Results.csv'
## 1425 Students no trailing characters 3,763 'JANI Volunteer data set - Results.csv'
## 1617 Students no trailing characters 2,729 'JANI Volunteer data set - Results.csv'
## 1618 Students no trailing characters 2,729 'JANI Volunteer data set - Results.csv'
## 1619 Students no trailing characters 2,729 'JANI Volunteer data set - Results.csv'
## .... ........ ...................... ...... .......................................
## See problems(...) for more details.
JANIINTERACTIONS <- filter(JANIINTERACTIONS, n >= 445)
ggplot(JANIINTERACTIONS, aes(x = company)) +
geom_boxplot()
ggplot(JANIINTERACTIONS, aes(x = company,
y = n)) +
geom_col() +
labs(
x = "Companies",
y = "Contact Hours",
title = "Amount of Contact Hours with Students",
subtitle = "Top 5 Companies"
)
