Load libraries
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.4.4 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ tidyr 1.3.0
## ✔ purrr 1.0.2
## ── 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(nycflights13)
library(tidyquant)
## Loading required package: PerformanceAnalytics
## Loading required package: xts
## Loading required package: zoo
##
## Attaching package: 'zoo'
##
## The following objects are masked from 'package:base':
##
## as.Date, as.Date.numeric
##
##
## ######################### Warning from 'xts' package ##########################
## # #
## # The dplyr lag() function breaks how base R's lag() function is supposed to #
## # work, which breaks lag(my_xts). Calls to lag(my_xts) that you type or #
## # source() into this session won't work correctly. #
## # #
## # Use stats::lag() to make sure you're not using dplyr::lag(), or you can add #
## # conflictRules('dplyr', exclude = 'lag') to your .Rprofile to stop #
## # dplyr from breaking base R's lag() function. #
## # #
## # Code in packages is not affected. It's protected by R's namespace mechanism #
## # Set `options(xts.warn_dplyr_breaks_lag = FALSE)` to suppress this warning. #
## # #
## ###############################################################################
##
## Attaching package: 'xts'
##
## The following objects are masked from 'package:dplyr':
##
## first, last
##
##
## Attaching package: 'PerformanceAnalytics'
##
## The following object is masked from 'package:graphics':
##
## legend
##
## Loading required package: quantmod
## Loading required package: TTR
## Registered S3 method overwritten by 'quantmod':
## method from
## as.zoo.data.frame zoo
library(tidyr)
# Read the CSV file
your_dataset <- 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.
# Select relevant columns and perform the required operations
result <- your_dataset %>%
select(starts_with("LearningPlatformUsefulness")) %>%
gather(key = "learning_platform", value = "usefulness", na.rm = TRUE) %>%
mutate(learning_platform = gsub('LearningPlatformUsefulness', '', learning_platform)) %>%
count(learning_platform, usefulness)
print(result)
## # 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
library(dplyr)
library(tidyr)
# Assuming your dataset is named 'your_dataset'
# Replace 'your_dataset' with the actual name of your data frame
result <- your_dataset %>%
gather(key = "learning_platform", value = "usefulness", na.rm = TRUE) %>%
mutate(learning_platform = gsub('LearningPlatformUsefulness', '', learning_platform),
perc_usefulness = as.numeric(usefulness == "Very useful" | usefulness == "Somewhat useful")) %>%
group_by(learning_platform) %>%
summarise(count = n(),
tot = sum(perc_usefulness),
perc_usefulness = mean(perc_usefulness))
print(result)
## # A tibble: 47 × 4
## learning_platform count tot perc_usefulness
## <chr> <int> <dbl> <dbl>
## 1 Age 16385 0 0
## 2 Arxiv 2391 2354 0.985
## 3 Blogs 4765 4720 0.991
## 4 College 3359 3258 0.970
## 5 Communities 1142 1126 0.986
## 6 Company 981 940 0.958
## 7 Conferences 2182 2063 0.945
## 8 Courses 5992 5945 0.992
## 9 CurrentJobTitleSelect 11830 0 0
## 10 DataScienceIdentitySelect 12671 0 0
## # ℹ 37 more rows
library(ggplot2)
library(forcats)
# Assuming 'result' is the name of your previous result data frame
# Replace 'result' with the actual name if it's different
# Reorder the learning_platform factor by percentage of usefulness
result <- result %>%
mutate(learning_platform = fct_reorder(learning_platform, perc_usefulness))
# Convert 'tot' to numeric for continuous fill scale
result$tot <- as.numeric(result$tot)
# Create the plot
ggplot(result, aes(x = learning_platform, y = perc_usefulness, fill = tot)) +
geom_bar(stat = "identity", position = "stack") +
scale_fill_gradient(low = "aquamarine1", high = "darkgoldenrod1") +
coord_flip() +
labs(title = "Percentage of Useful Responses by Learning Platform",
x = "Learning Platform",
y = "Percentage of Usefulness") +
theme_minimal()
