R Notebook

library(tidyverse)
library(lubridate)
library(nycflights13)
library(readr)
library(tidytext)
library(stopwords)
lateflights <- flights %>% 
  filter(arr_delay>5) %>% 
  group_by(month) %>% 
  summarise(lateflights = n()) %>% 
  ungroup()

lateflights

total_flights_per_carrier <- flights %>%
  group_by(month, carrier) %>%
  summarise(total_flights_by_carrier = n())

`summarise()` has grouped output by 'month'. You can override using the `.groups` argument.

total_flights_per_month <- flights %>%
  group_by(month) %>%
  summarise(total_flights_per_month = n())
percentage_traffic_per_carrier <- total_flights_per_carrier %>%
  left_join(total_flights_per_month, by = "month") %>%
  mutate(percentage_traffic = (total_flights_by_carrier / total_flights_per_month)) %>%
  mutate(percentage_traffic = scales::percent(percentage_traffic)) %>% 
  select(month, carrier, percentage_traffic)
percentage_traffic_per_carrier %>% spread(key = month, value = percentage_traffic)

flights %>%
  group_by(month) %>%
  filter(dep_delay == max(dep_delay, na.rm = TRUE)) %>% 
  arrange(-desc(month))

multipleChoiceResponses <- read_csv("/cloud/project/multipleChoiceResponses1.csv")

Rows: 16716 Columns: 47
── Column specification ────────────────────────────────────────────────────────────────────
Delimiter: ","
chr (46): LearningPlatformUsefulnessArxiv, LearningPlatformUsefulnessBlogs, LearningPlat...
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.

usefulness_by_platform <- multipleChoiceResponses %>% select(starts_with("LearningPlatformUsefulness")) %>%  
  set_names(names(.) %>% str_replace("LearningPlatformUsefulness", "")) %>% 
  gather(key = "learning_platform", value = "usefulness",convert = FALSE, na.rm = TRUE)
usefulness_by_platform %>% group_by(learning_platform, usefulness) %>% 
  summarise(n = n()) %>% 
  ungroup()

`summarise()` has grouped output by 'learning_platform'. You can override using the
`.groups` argument.

total_usefulness_by_platform <- usefulness_by_platform %>% group_by(learning_platform) %>% summarise(tot = n())
usefulness_count <- usefulness_by_platform %>% filter(!grepl("Not Useful",usefulness,ignore.case = TRUE)) %>% 
  group_by(learning_platform) %>% summarise(count = n())
perc_usefulness <- usefulness_count %>% left_join(total_usefulness_by_platform, by = "learning_platform") %>% 
  mutate(perc_usefulness = count/tot) %>% 
  mutate(perc_usefulness = round(perc_usefulness, digits = 3))
perc_usefulness

perc_usefulness_fct <- perc_usefulness %>% 
  mutate(learning_platform = fct(learning_platform) %>% 
           fct_reorder(perc_usefulness) %>% 
           fct_rev() %>% 
           fct_relevel("Courses", after = 0))
perc_usefulness_fct %>% ggplot(aes(x = learning_platform, y = perc_usefulness))+
  geom_segment(aes(xend = learning_platform, yend=0))+
  geom_point()+
  theme(axis.text.x = element_text(angle = 45, hjust = 1))+
  labs(
    x = "Learning Platform",
    y = "Percent finding at least somewhat useful"
  )+
  scale_y_continuous(labels = scales::percent_format(scale = 100, suffix = "%"))

twitter_data <- readRDS("twitter_data.rds")
twitter_data %>%
  group_by(complaint_label) %>%
  summarise(
    avg_followers = mean(usr_followers_count, na.rm = TRUE),
    min_followers = min(usr_followers_count, na.rm = TRUE),
    max_followers = max(usr_followers_count, na.rm = TRUE)
  )

colnames(twitter_data)

[1] "tweet_id"            "date"                "complaint_label"     "tweet_text"         
[5] "usr_followers_count" "usr_verified"       

twitter_data <- twitter_data %>%
  rename(text = tweet_text)

twitter_data %>%
  unnest_tokens(word, text) %>%
  count(word, sort = TRUE)

twitter_data %>%
  unnest_tokens(word, text) %>%
  anti_join(stop_words, by = "word") %>%
  count(word, sort = TRUE)

twitter_data %>%
  unnest_tokens(word, text) %>%
  count(word, sort = TRUE)