Academatica Data Analysis

knitr::opts_chunk$set(warning = FALSE, message = FALSE)
library(dplyr)
library(lubridate)
library(ggplot2)
library(tm)
library(wordcloud)

Cargar la data

Los archivos para correr este notebok estan en,

• Data academatica

videos <- read_csv("academatica_videos.csv")
metadata <- read_csv("academatica_videos_metadata.csv")
stats <- read_csv("academatica_video_stats.csv")

Videos subidos por año

videos %>% 
  mutate(year = year(ymd_hms(contentDetails.videoPublishedAt)),
         month = month(ymd_hms(contentDetails.videoPublishedAt),label = TRUE),
         year = as.factor(year)) %>% 
  group_by(year, month) %>% 
  summarise(uploaded_videos = n_distinct(id)) %>%
  ggplot(aes(x=month,
             y=uploaded_videos,
             fill=year))+
  geom_col(position = 'dodge')

Word Cloud

docs <- Corpus(VectorSource(metadata$title))
toSpace <- content_transformer(function (x , pattern ) gsub(pattern, " ", x))
docs <- tm_map(docs, toSpace, "-")
docs <- tm_map(docs, toSpace, "\\(")
docs <- tm_map(docs, toSpace, "\\)")
docs <- tm_map(docs, toSpace, "\\|")

docs <- tm_map(docs, content_transformer(tolower))
docs <- tm_map(docs, removeNumbers)
docs <- tm_map(docs, removeWords, stopwords("spanish"))
docs <- tm_map(docs, content_transformer(tolower))
docs <- tm_map(docs, removeNumbers)
docs <- tm_map(docs, removeWords, stopwords("english"))
docs <- tm_map(docs, removeWords, c("video", 
                                    "problema",
                                    "ejemplo",
                                    "parte",
                                    "ejercicio",
                                    "ejercicios",
                                    "ejemplos")) 
docs <- tm_map(docs, removePunctuation)
docs <- tm_map(docs, stripWhitespace)

dtm <- TermDocumentMatrix(docs)
m <- as.matrix(dtm)
v <- sort(rowSums(m),decreasing=TRUE)
d <- data.frame(word = names(v),freq=v)
head(d, 10)

set.seed(1234)
wordcloud(words = d$word, freq = d$freq, min.freq = 1,
          max.words=100, random.order=TRUE, rot.per=0.1, 
          colors=brewer.pal(8, "Dark2"))

Kpis del canal

stats %>% 
  summarise(total_views = sum(viewCount),
            total_likes = sum(likeCount),
            total_dislike = sum(dislikeCount),
            total_favorite = sum(favoriteCount),
            total_comments = sum(commentCount))

stats %>% 
  mutate(hasComment = if_else(commentCount>0,"si","no" )) %>% 
  group_by(hasComment) %>% 
  summarise(total_hasComment=n())

stats %>% 
  mutate(hasLike = if_else(likeCount>0,"si","no" )) %>% 
  group_by(hasLike) %>% 
  summarise(total_hasLike=n())

stats %>% 
  mutate(hasLike = if_else(likeCount>0,"si","no" )) %>% 
  filter(hasLike == 'no') %>% 
  left_join(metadata, by = c("id"="video_id")) %>% 
  select(id,title)