library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.1 ✔ stringr 1.5.2
## ✔ ggplot2 4.0.0 ✔ tibble 3.3.0
## ✔ lubridate 1.9.4 ✔ tidyr 1.3.1
## ✔ purrr 1.1.0
## ── 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
library(lubridate)
library(tidyquant)
## Registered S3 method overwritten by 'quantmod':
## method from
## as.zoo.data.frame zoo
## ── Attaching core tidyquant packages ─────────────────────── tidyquant 1.0.11 ──
## ✔ PerformanceAnalytics 2.0.8 ✔ TTR 0.24.4
## ✔ quantmod 0.4.28 ✔ xts 0.14.1
## ── Conflicts ────────────────────────────────────────── tidyquant_conflicts() ──
## ✖ zoo::as.Date() masks base::as.Date()
## ✖ zoo::as.Date.numeric() masks base::as.Date.numeric()
## ✖ dplyr::filter() masks stats::filter()
## ✖ xts::first() masks dplyr::first()
## ✖ dplyr::lag() masks stats::lag()
## ✖ xts::last() masks dplyr::last()
## ✖ PerformanceAnalytics::legend() masks graphics::legend()
## ✖ quantmod::summary() masks base::summary()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(nycflights13)
df <- read_csv("multipleChoiceResponses1.csv")
## Rows: 16716 Columns: 47
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (46): LearningPlatformUsefulnessArxiv, LearningPlatformUsefulnessBlogs, ...
## dbl (1): Age
##
## 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.
use_cols <- df %>% select(starts_with("LearningPlatformUsefulness"))
use_tbl <- use_cols %>%
pivot_longer(
cols = everything(),
names_to = "learning_platform",
values_to = "usefulness"
) %>%
filter(!is.na(usefulness)) %>%
mutate(
learning_platform = str_replace(learning_platform, "LearningPlatformUsefulness", "")
) %>%
count(learning_platform, usefulness, name = "n") %>%
arrange(learning_platform, usefulness)
print(use_tbl)
## # A tibble: 54 × 3
## learning_platform usefulness n
## <chr> <chr> <int>
## 1 Arxiv Not Useful 37
## 2 Arxiv Somewhat useful 1038
## 3 Arxiv Very useful 1316
## 4 Blogs Not Useful 45
## 5 Blogs Somewhat useful 2406
## 6 Blogs Very useful 2314
## 7 College Not Useful 101
## 8 College Somewhat useful 1405
## 9 College Very useful 1853
## 10 Communities Not Useful 16
## # ℹ 44 more rows
totals <- use_tbl %>%
group_by(learning_platform) %>%
summarise(tot = sum(n), .groups = "drop")
useful_counts <- use_tbl %>%
filter(tolower(usefulness) != "not useful") %>%
group_by(learning_platform) %>%
summarise(count = sum(n), .groups = "drop")
result2 <- useful_counts %>%
left_join(totals, by = "learning_platform") %>%
mutate(perc_usefulness = count / tot) %>%
arrange(desc(count))
print(result2)
## # A tibble: 18 × 4
## learning_platform count tot perc_usefulness
## <chr> <int> <int> <dbl>
## 1 Kaggle 6527 6583 0.991
## 2 Courses 5945 5992 0.992
## 3 SO 5576 5640 0.989
## 4 YouTube 5125 5229 0.980
## 5 Projects 4755 4794 0.992
## 6 Blogs 4720 4765 0.991
## 7 Textbook 4112 4181 0.983
## 8 College 3258 3359 0.970
## 9 Arxiv 2354 2391 0.985
## 10 Documentation 2279 2321 0.982
## 11 Conferences 2063 2182 0.945
## 12 Friends 1530 1581 0.968
## 13 Tutoring 1394 1426 0.978
## 14 Communities 1126 1142 0.986
## 15 Podcasts 1090 1214 0.898
## 16 Newsletters 1033 1089 0.949
## 17 Company 940 981 0.958
## 18 TradeBook 324 333 0.973
total_useful <- sum(result2$count)
top10 <- result2 %>%
arrange(desc(count)) %>%
mutate(
count1 = count,
pct = count1 / total_useful,
cum_pct = cumsum(pct)
) %>%
slice(1:10) %>%
select(learning_platform, count1, cum_pct)
other_val <- result2 %>%
arrange(desc(count)) %>%
slice(11:n()) %>%
summarise(count1 = sum(count)) %>%
pull(count1)
top10_out <- top10 %>%
bind_rows(tibble(learning_platform = "Other", count1 = other_val, cum_pct = 1.0))
print(top10_out)
## # A tibble: 11 × 3
## learning_platform count1 cum_pct
## <chr> <int> <dbl>
## 1 Kaggle 6527 0.121
## 2 Courses 5945 0.230
## 3 SO 5576 0.333
## 4 YouTube 5125 0.428
## 5 Projects 4755 0.516
## 6 Blogs 4720 0.603
## 7 Textbook 4112 0.679
## 8 College 3258 0.739
## 9 Arxiv 2354 0.782
## 10 Documentation 2279 0.825
## 11 Other 9500 1
top10_out %>%
mutate(learning_platform = fct_reorder(learning_platform, count1)) %>%
ggplot(aes(x = count1, y = learning_platform)) +
geom_col() +
labs(
title = "Top 10 Learning Platforms (At Least Useful)",
x = "Number of responses with at least usefulness",
y = "Learning Platform"
) +
theme_minimal()
write_csv(top10_out, "top10_learning_platforms.csv")
message("Saved top10_learning_platforms.csv to working directory.")
## Saved top10_learning_platforms.csv to working directory.