library(tidyverse)
## 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'
## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.0 ──
## ✓ ggplot2 3.3.2     ✓ purrr   0.3.4
## ✓ tibble  3.0.4     ✓ dplyr   1.0.2
## ✓ tidyr   1.1.2     ✓ stringr 1.4.0
## ✓ readr   1.4.0     ✓ forcats 0.5.0
## ── 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(dplyr)
JANI_Base <- read_csv("JANI Volunteer data set.csv")
## 
## ── 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.csv'
## 1425 Students no trailing characters  3,763 'JANI Volunteer data set.csv'
## 1617 Students no trailing characters  2,729 'JANI Volunteer data set.csv'
## 1618 Students no trailing characters  2,729 'JANI Volunteer data set.csv'
## 1619 Students no trailing characters  2,729 'JANI Volunteer data set.csv'
## .... ........ ...................... ...... .............................
## See problems(...) for more details.
tibble(JANI_Base)
## # A tibble: 24,034 x 8
##    Program_Year  Company  School  Grade Program  Class_ID Contact_Hours Students
##    <chr>         <chr>    <chr>   <chr> <chr>    <chr>            <dbl>    <dbl>
##  1 Program year… #1 Adva… East A… 12    JA Laun… CL-6038…             1       29
##  2 Program year… #1 Adva… East A… 12    JA Laun… CL-6038…             1       24
##  3 Program year… 12 Corn… Benton… 10    JA Care… CL-1074…             7       17
##  4 Program year… 12 Corn… Benton… 12    JA Care… CL-8034…             7       18
##  5 Program year… 1st Ass… Lakewo… 6     JA BizT… CL-7148…            26       20
##  6 Program year… 1st Ass… Centra… 7     JA Econ… CL-1247…             6       28
##  7 Program year… 1st Ass… Timoth… 6     JA Econ… CL-1363…             6       22
##  8 Program year… 1st Ass… East N… 11    JA Laun… CL-6089…             1       26
##  9 Program year… 1st Ass… East N… 7     JA Econ… CL-6230…             6       26
## 10 Program year… 1st Ass… Centra… 8     JA Econ… CL-7136…             6       25
## # … with 24,024 more rows
ggplot(data = JANI_Base,
      mapping = aes(x = Students,
                    y = Program_Year)) +
  geom_point()
## Warning: Removed 374 rows containing missing values (geom_point).

JANI_Hours <- JANI_Base %>%
  mutate(total_hours = `Contact_Hours` * `Students`) %>%
  arrange(desc(total_hours))
tibble(JANI_Hours)
## # A tibble: 24,034 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
## # … with 24,024 more rows, and 1 more variable: total_hours <dbl>
Lil_JANI_Hours <- JANI_Hours %>%
  count(Company)%>%
  filter(n>100)%>%
  arrange(desc(n))
tibble(Lil_JANI_Hours)
## # A tibble: 27 x 2
##    Company                          n
##    <chr>                        <int>
##  1 Purdue University Fort Wayne  1096
##  2 Lake City Bank                 797
##  3 1st Source Bank                571
##  4 Indiana Tech                   567
##  5 Lincoln Financial Group        445
##  6 3Rivers Federal Credit Union   308
##  7 Ivy Tech Community College     288
##  8 University of Saint Francis    186
##  9 First Merchants Bank           178
## 10 Zimmer Biomet                  169
## # … with 17 more rows
ggplot(data = Lil_JANI_Hours,
       aes(x = n, y = Company)) +
  geom_point()+
  labs(title = "Top 30 Companies",
       subtitle = "In JA Northeast Indiana",
       x = "Count")