library('tidyr')
library('readr')
library('dplyr')
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library('ggplot2')
library('forcats')
library('tidyquant')
## Loading required package: lubridate
##
## Attaching package: 'lubridate'
## The following objects are masked from 'package:base':
##
## date, intersect, setdiff, union
## 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
responses <- read.csv("/cloud/project/multipleChoiceResponses.csv", header = TRUE, stringsAsFactors = FALSE)
## Warning in scan(file = file, what = what, sep = sep, quote = quote, dec = dec,
## : EOF within quoted string
selected_columns <- responses %>%
select(
starts_with("Learning"),
starts_with("Working"),
starts_with("Age"),
starts_with("EmploymentStatus"),
starts_with("CurrentJob"),
starts_with("MLMethod"),
starts_with("Formal")
)
char_columns <- sapply(selected_columns, is.character)
selected_columns[, char_columns] <- lapply(selected_columns[, char_columns], as.factor)
# 1.2
factor_levels <- data.frame(
variable = names(selected_columns),
num_levels = sapply(selected_columns, nlevels)
)
# 1.2
print(factor_levels)
## variable
## LearningDataScience LearningDataScience
## LearningPlatformSelect LearningPlatformSelect
## LearningPlatformUsefulnessArxiv LearningPlatformUsefulnessArxiv
## LearningPlatformUsefulnessBlogs LearningPlatformUsefulnessBlogs
## LearningPlatformUsefulnessCollege LearningPlatformUsefulnessCollege
## LearningPlatformUsefulnessCompany LearningPlatformUsefulnessCompany
## LearningPlatformUsefulnessConferences LearningPlatformUsefulnessConferences
## LearningPlatformUsefulnessFriends LearningPlatformUsefulnessFriends
## LearningPlatformUsefulnessKaggle LearningPlatformUsefulnessKaggle
## LearningPlatformUsefulnessNewsletters LearningPlatformUsefulnessNewsletters
## LearningPlatformUsefulnessCommunities LearningPlatformUsefulnessCommunities
## LearningPlatformUsefulnessDocumentation LearningPlatformUsefulnessDocumentation
## LearningPlatformUsefulnessCourses LearningPlatformUsefulnessCourses
## LearningPlatformUsefulnessProjects LearningPlatformUsefulnessProjects
## LearningPlatformUsefulnessPodcasts LearningPlatformUsefulnessPodcasts
## LearningPlatformUsefulnessSO LearningPlatformUsefulnessSO
## LearningPlatformUsefulnessTextbook LearningPlatformUsefulnessTextbook
## LearningPlatformUsefulnessTradeBook LearningPlatformUsefulnessTradeBook
## LearningPlatformUsefulnessTutoring LearningPlatformUsefulnessTutoring
## LearningPlatformUsefulnessYouTube LearningPlatformUsefulnessYouTube
## LearningDataScienceTime LearningDataScienceTime
## LearningCategorySelftTaught LearningCategorySelftTaught
## LearningCategoryOnlineCourses LearningCategoryOnlineCourses
## LearningCategoryWork LearningCategoryWork
## LearningCategoryUniversity LearningCategoryUniversity
## LearningCategoryKaggle LearningCategoryKaggle
## LearningCategoryOther LearningCategoryOther
## Age Age
## EmploymentStatus EmploymentStatus
## CurrentJobTitleSelect CurrentJobTitleSelect
## MLMethodNextYearSelect MLMethodNextYearSelect
## FormalEducation FormalEducation
## num_levels
## LearningDataScience 444
## LearningPlatformSelect 3435
## LearningPlatformUsefulnessArxiv 430
## LearningPlatformUsefulnessBlogs 421
## LearningPlatformUsefulnessCollege 405
## LearningPlatformUsefulnessCompany 455
## LearningPlatformUsefulnessConferences 434
## LearningPlatformUsefulnessFriends 421
## LearningPlatformUsefulnessKaggle 440
## LearningPlatformUsefulnessNewsletters 391
## LearningPlatformUsefulnessCommunities 428
## LearningPlatformUsefulnessDocumentation 433
## LearningPlatformUsefulnessCourses 410
## LearningPlatformUsefulnessProjects 446
## LearningPlatformUsefulnessPodcasts 453
## LearningPlatformUsefulnessSO 414
## LearningPlatformUsefulnessTextbook 450
## LearningPlatformUsefulnessTradeBook 427
## LearningPlatformUsefulnessTutoring 433
## LearningPlatformUsefulnessYouTube 434
## LearningDataScienceTime 419
## LearningCategorySelftTaught 459
## LearningCategoryOnlineCourses 451
## LearningCategoryWork 462
## LearningCategoryUniversity 473
## LearningCategoryKaggle 445
## LearningCategoryOther 468
## Age 489
## EmploymentStatus 420
## CurrentJobTitleSelect 425
## MLMethodNextYearSelect 475
## FormalEducation 452
# 1.2
top5_levels <- factor_levels %>%
arrange(desc(num_levels)) %>%
head(5)
# 1.2
print(top5_levels)
## variable num_levels
## LearningPlatformSelect LearningPlatformSelect 3435
## Age Age 489
## MLMethodNextYearSelect MLMethodNextYearSelect 475
## LearningCategoryUniversity LearningCategoryUniversity 473
## LearningCategoryOther LearningCategoryOther 468
# 1.3
current_job_levels <- factor_levels %>%
filter(variable == "CurrentJobTitleSelect")
# 1.3
print(current_job_levels)
## variable num_levels
## CurrentJobTitleSelect CurrentJobTitleSelect 425
# 1.4
current_job_levels <- factor_levels %>%
filter(variable == "CurrentJobTitleSelect")
print(current_job_levels)
## variable num_levels
## CurrentJobTitleSelect CurrentJobTitleSelect 425
library(ggplot2)
employer_industry_plot <- ggplot(responses, aes(x = EmployerIndustry)) +
geom_bar() +
coord_flip()
#question_2
#2.1
library(ggplot2)
responses <- read.csv("/cloud/project/multipleChoiceResponses.csv", header = TRUE, stringsAsFactors = FALSE)
## Warning in scan(file = file, what = what, sep = sep, quote = quote, dec = dec,
## : EOF within quoted string
employer_industry_plot <- ggplot(responses, aes(x = EmployerIndustry)) +
geom_bar(stat = "count") +
coord_flip()
print(employer_industry_plot)
#2.2
library(ggplot2)
responses <- read.csv("/cloud/project/multipleChoiceResponses.csv", header = TRUE, stringsAsFactors = FALSE)
## Warning in scan(file = file, what = what, sep = sep, quote = quote, dec = dec,
## : EOF within quoted string
filtered_responses <- na.omit(responses[c("Age", "EmployerIndustry")])
filtered_plot <- ggplot(filtered_responses, aes(x = EmployerIndustry)) +
geom_bar(stat = "count") +
coord_flip()
print(filtered_plot)