##. strore the twitter data in a data frame and remove empty and non relevant columns.
library(car)
library(psych)
##
## Attaching package: 'psych'
## The following object is masked from 'package:car':
##
## logit
twitter.df <- read.csv(paste("twitter.csv"),sep = ",")
twitter.df<- twitter.df[,-c(160:934)]
##. determine the class of each column of the dataframe
sapply(twitter.df,class)
## contributors
## "logical"
## coordinates
## "logical"
## created_at
## "factor"
## entities.urls.0.display_url
## "factor"
## entities.urls.0.expanded_url
## "factor"
## entities.urls.0.indices.0
## "integer"
## entities.urls.0.indices.1
## "integer"
## entities.urls.0.url
## "factor"
## favorite_count
## "integer"
## favorited
## "logical"
## geo
## "logical"
## id
## "numeric"
## id_str
## "numeric"
## in_reply_to_screen_name
## "factor"
## in_reply_to_status_id
## "numeric"
## in_reply_to_status_id_str
## "numeric"
## in_reply_to_user_id
## "numeric"
## in_reply_to_user_id_str
## "numeric"
## is_quote_status
## "logical"
## lang
## "factor"
## place
## "logical"
## possibly_sensitive
## "logical"
## retweet_count
## "integer"
## retweeted
## "logical"
## source
## "factor"
## text
## "factor"
## truncated
## "logical"
## user.contributors_enabled
## "logical"
## user.created_at
## "factor"
## user.default_profile
## "logical"
## user.default_profile_image
## "logical"
## user.description
## "factor"
## user.entities.url.urls.0.display_url
## "factor"
## user.entities.url.urls.0.expanded_url
## "factor"
## user.entities.url.urls.0.indices.0
## "integer"
## user.entities.url.urls.0.indices.1
## "integer"
## user.entities.url.urls.0.url
## "factor"
## user.favourites_count
## "integer"
## user.follow_request_sent
## "logical"
## user.followers_count
## "integer"
## user.following
## "logical"
## user.friends_count
## "integer"
## user.geo_enabled
## "logical"
## user.has_extended_profile
## "logical"
## user.id
## "numeric"
## user.id_str
## "numeric"
## user.is_translation_enabled
## "logical"
## user.is_translator
## "logical"
## user.lang
## "factor"
## user.listed_count
## "integer"
## user.location
## "factor"
## user.name
## "factor"
## user.notifications
## "logical"
## user.profile_background_color
## "integer"
## user.profile_background_image_url
## "factor"
## user.profile_background_image_url_https
## "factor"
## user.profile_background_tile
## "logical"
## user.profile_banner_url
## "factor"
## user.profile_image_url
## "factor"
## user.profile_image_url_https
## "factor"
## user.profile_link_color
## "factor"
## user.profile_sidebar_border_color
## "integer"
## user.profile_sidebar_fill_color
## "integer"
## user.profile_text_color
## "integer"
## user.profile_use_background_image
## "logical"
## user.protected
## "logical"
## user.screen_name
## "factor"
## user.statuses_count
## "integer"
## user.time_zone
## "factor"
## user.translator_type
## "factor"
## user.url
## "factor"
## user.utc_offset
## "integer"
## user.verified
## "logical"
## entities.hashtags.0.indices.0
## "integer"
## entities.hashtags.0.indices.1
## "integer"
## entities.hashtags.0.text
## "factor"
## entities.user_mentions.0.id
## "numeric"
## entities.user_mentions.0.id_str
## "numeric"
## entities.user_mentions.0.indices.0
## "integer"
## entities.user_mentions.0.indices.1
## "integer"
## entities.user_mentions.0.name
## "factor"
## entities.user_mentions.0.screen_name
## "factor"
## retweeted_status.contributors
## "logical"
## retweeted_status.coordinates
## "logical"
## retweeted_status.created_at
## "factor"
## retweeted_status.entities.urls.0.display_url
## "factor"
## retweeted_status.entities.urls.0.expanded_url
## "factor"
## retweeted_status.entities.urls.0.indices.0
## "integer"
## retweeted_status.entities.urls.0.indices.1
## "integer"
## retweeted_status.entities.urls.0.url
## "factor"
## retweeted_status.favorite_count
## "integer"
## retweeted_status.favorited
## "logical"
## retweeted_status.geo
## "logical"
## retweeted_status.id
## "numeric"
## retweeted_status.id_str
## "numeric"
## retweeted_status.in_reply_to_screen_name
## "logical"
## retweeted_status.in_reply_to_status_id
## "logical"
## retweeted_status.in_reply_to_status_id_str
## "logical"
## retweeted_status.in_reply_to_user_id
## "logical"
## retweeted_status.in_reply_to_user_id_str
## "logical"
## retweeted_status.is_quote_status
## "logical"
## retweeted_status.lang
## "factor"
## retweeted_status.place
## "logical"
## retweeted_status.possibly_sensitive
## "logical"
## retweeted_status.retweet_count
## "integer"
## retweeted_status.retweeted
## "logical"
## retweeted_status.source
## "factor"
## retweeted_status.text
## "factor"
## retweeted_status.truncated
## "logical"
## retweeted_status.user.contributors_enabled
## "logical"
## retweeted_status.user.created_at
## "factor"
## retweeted_status.user.default_profile
## "logical"
## retweeted_status.user.default_profile_image
## "logical"
## retweeted_status.user.description
## "factor"
## retweeted_status.user.entities.url.urls.0.display_url
## "factor"
## retweeted_status.user.entities.url.urls.0.expanded_url
## "factor"
## retweeted_status.user.entities.url.urls.0.indices.0
## "integer"
## retweeted_status.user.entities.url.urls.0.indices.1
## "integer"
## retweeted_status.user.entities.url.urls.0.url
## "factor"
## retweeted_status.user.favourites_count
## "integer"
## retweeted_status.user.follow_request_sent
## "logical"
## retweeted_status.user.followers_count
## "integer"
## retweeted_status.user.following
## "logical"
## retweeted_status.user.friends_count
## "integer"
## retweeted_status.user.geo_enabled
## "logical"
## retweeted_status.user.has_extended_profile
## "logical"
## retweeted_status.user.id
## "numeric"
## retweeted_status.user.id_str
## "numeric"
## retweeted_status.user.is_translation_enabled
## "logical"
## retweeted_status.user.is_translator
## "logical"
## retweeted_status.user.lang
## "factor"
## retweeted_status.user.listed_count
## "integer"
## retweeted_status.user.location
## "factor"
## retweeted_status.user.name
## "factor"
## retweeted_status.user.notifications
## "logical"
## retweeted_status.user.profile_background_color
## "factor"
## retweeted_status.user.profile_background_image_url
## "factor"
## retweeted_status.user.profile_background_image_url_https
## "factor"
## retweeted_status.user.profile_background_tile
## "logical"
## retweeted_status.user.profile_banner_url
## "factor"
## retweeted_status.user.profile_image_url
## "factor"
## retweeted_status.user.profile_image_url_https
## "factor"
## retweeted_status.user.profile_link_color
## "factor"
## retweeted_status.user.profile_sidebar_border_color
## "factor"
## retweeted_status.user.profile_sidebar_fill_color
## "factor"
## retweeted_status.user.profile_text_color
## "factor"
## retweeted_status.user.profile_use_background_image
## "logical"
## retweeted_status.user.protected
## "logical"
## retweeted_status.user.screen_name
## "factor"
## retweeted_status.user.statuses_count
## "integer"
## retweeted_status.user.time_zone
## "factor"
## retweeted_status.user.translator_type
## "factor"
## retweeted_status.user.url
## "factor"
## retweeted_status.user.utc_offset
## "integer"
## retweeted_status.user.verified
## "logical"
## quoted_status.contributors
## "logical"
## quoted_status.coordinates
## "logical"
## quoted_status.created_at
## "factor"
## quoted_status.entities.urls.0.display_url
## "factor"
##. determine the type of each column of dataframe
sapply(twitter.df,typeof)
## contributors
## "logical"
## coordinates
## "logical"
## created_at
## "integer"
## entities.urls.0.display_url
## "integer"
## entities.urls.0.expanded_url
## "integer"
## entities.urls.0.indices.0
## "integer"
## entities.urls.0.indices.1
## "integer"
## entities.urls.0.url
## "integer"
## favorite_count
## "integer"
## favorited
## "logical"
## geo
## "logical"
## id
## "double"
## id_str
## "double"
## in_reply_to_screen_name
## "integer"
## in_reply_to_status_id
## "double"
## in_reply_to_status_id_str
## "double"
## in_reply_to_user_id
## "double"
## in_reply_to_user_id_str
## "double"
## is_quote_status
## "logical"
## lang
## "integer"
## place
## "logical"
## possibly_sensitive
## "logical"
## retweet_count
## "integer"
## retweeted
## "logical"
## source
## "integer"
## text
## "integer"
## truncated
## "logical"
## user.contributors_enabled
## "logical"
## user.created_at
## "integer"
## user.default_profile
## "logical"
## user.default_profile_image
## "logical"
## user.description
## "integer"
## user.entities.url.urls.0.display_url
## "integer"
## user.entities.url.urls.0.expanded_url
## "integer"
## user.entities.url.urls.0.indices.0
## "integer"
## user.entities.url.urls.0.indices.1
## "integer"
## user.entities.url.urls.0.url
## "integer"
## user.favourites_count
## "integer"
## user.follow_request_sent
## "logical"
## user.followers_count
## "integer"
## user.following
## "logical"
## user.friends_count
## "integer"
## user.geo_enabled
## "logical"
## user.has_extended_profile
## "logical"
## user.id
## "double"
## user.id_str
## "double"
## user.is_translation_enabled
## "logical"
## user.is_translator
## "logical"
## user.lang
## "integer"
## user.listed_count
## "integer"
## user.location
## "integer"
## user.name
## "integer"
## user.notifications
## "logical"
## user.profile_background_color
## "integer"
## user.profile_background_image_url
## "integer"
## user.profile_background_image_url_https
## "integer"
## user.profile_background_tile
## "logical"
## user.profile_banner_url
## "integer"
## user.profile_image_url
## "integer"
## user.profile_image_url_https
## "integer"
## user.profile_link_color
## "integer"
## user.profile_sidebar_border_color
## "integer"
## user.profile_sidebar_fill_color
## "integer"
## user.profile_text_color
## "integer"
## user.profile_use_background_image
## "logical"
## user.protected
## "logical"
## user.screen_name
## "integer"
## user.statuses_count
## "integer"
## user.time_zone
## "integer"
## user.translator_type
## "integer"
## user.url
## "integer"
## user.utc_offset
## "integer"
## user.verified
## "logical"
## entities.hashtags.0.indices.0
## "integer"
## entities.hashtags.0.indices.1
## "integer"
## entities.hashtags.0.text
## "integer"
## entities.user_mentions.0.id
## "double"
## entities.user_mentions.0.id_str
## "double"
## entities.user_mentions.0.indices.0
## "integer"
## entities.user_mentions.0.indices.1
## "integer"
## entities.user_mentions.0.name
## "integer"
## entities.user_mentions.0.screen_name
## "integer"
## retweeted_status.contributors
## "logical"
## retweeted_status.coordinates
## "logical"
## retweeted_status.created_at
## "integer"
## retweeted_status.entities.urls.0.display_url
## "integer"
## retweeted_status.entities.urls.0.expanded_url
## "integer"
## retweeted_status.entities.urls.0.indices.0
## "integer"
## retweeted_status.entities.urls.0.indices.1
## "integer"
## retweeted_status.entities.urls.0.url
## "integer"
## retweeted_status.favorite_count
## "integer"
## retweeted_status.favorited
## "logical"
## retweeted_status.geo
## "logical"
## retweeted_status.id
## "double"
## retweeted_status.id_str
## "double"
## retweeted_status.in_reply_to_screen_name
## "logical"
## retweeted_status.in_reply_to_status_id
## "logical"
## retweeted_status.in_reply_to_status_id_str
## "logical"
## retweeted_status.in_reply_to_user_id
## "logical"
## retweeted_status.in_reply_to_user_id_str
## "logical"
## retweeted_status.is_quote_status
## "logical"
## retweeted_status.lang
## "integer"
## retweeted_status.place
## "logical"
## retweeted_status.possibly_sensitive
## "logical"
## retweeted_status.retweet_count
## "integer"
## retweeted_status.retweeted
## "logical"
## retweeted_status.source
## "integer"
## retweeted_status.text
## "integer"
## retweeted_status.truncated
## "logical"
## retweeted_status.user.contributors_enabled
## "logical"
## retweeted_status.user.created_at
## "integer"
## retweeted_status.user.default_profile
## "logical"
## retweeted_status.user.default_profile_image
## "logical"
## retweeted_status.user.description
## "integer"
## retweeted_status.user.entities.url.urls.0.display_url
## "integer"
## retweeted_status.user.entities.url.urls.0.expanded_url
## "integer"
## retweeted_status.user.entities.url.urls.0.indices.0
## "integer"
## retweeted_status.user.entities.url.urls.0.indices.1
## "integer"
## retweeted_status.user.entities.url.urls.0.url
## "integer"
## retweeted_status.user.favourites_count
## "integer"
## retweeted_status.user.follow_request_sent
## "logical"
## retweeted_status.user.followers_count
## "integer"
## retweeted_status.user.following
## "logical"
## retweeted_status.user.friends_count
## "integer"
## retweeted_status.user.geo_enabled
## "logical"
## retweeted_status.user.has_extended_profile
## "logical"
## retweeted_status.user.id
## "double"
## retweeted_status.user.id_str
## "double"
## retweeted_status.user.is_translation_enabled
## "logical"
## retweeted_status.user.is_translator
## "logical"
## retweeted_status.user.lang
## "integer"
## retweeted_status.user.listed_count
## "integer"
## retweeted_status.user.location
## "integer"
## retweeted_status.user.name
## "integer"
## retweeted_status.user.notifications
## "logical"
## retweeted_status.user.profile_background_color
## "integer"
## retweeted_status.user.profile_background_image_url
## "integer"
## retweeted_status.user.profile_background_image_url_https
## "integer"
## retweeted_status.user.profile_background_tile
## "logical"
## retweeted_status.user.profile_banner_url
## "integer"
## retweeted_status.user.profile_image_url
## "integer"
## retweeted_status.user.profile_image_url_https
## "integer"
## retweeted_status.user.profile_link_color
## "integer"
## retweeted_status.user.profile_sidebar_border_color
## "integer"
## retweeted_status.user.profile_sidebar_fill_color
## "integer"
## retweeted_status.user.profile_text_color
## "integer"
## retweeted_status.user.profile_use_background_image
## "logical"
## retweeted_status.user.protected
## "logical"
## retweeted_status.user.screen_name
## "integer"
## retweeted_status.user.statuses_count
## "integer"
## retweeted_status.user.time_zone
## "integer"
## retweeted_status.user.translator_type
## "integer"
## retweeted_status.user.url
## "integer"
## retweeted_status.user.utc_offset
## "integer"
## retweeted_status.user.verified
## "logical"
## quoted_status.contributors
## "logical"
## quoted_status.coordinates
## "logical"
## quoted_status.created_at
## "integer"
## quoted_status.entities.urls.0.display_url
## "integer"
##. no. of tweets from different sources.
table(twitter.df$source)
##
## android iphone periscope tweetdeck web client
## 14 1 4 216 111
##. graphical representation of the same
barplot(table(twitter.df$source))
library("stringr")
a <- c("Mon/","Sun/","Tue/","Wed/","Thu/","Fri/","Sat/")
twitter.df$created_at <- sub(" ","/",twitter.df$created_at)
twitter.df$created_at <- sub(" ","/",twitter.df$created_at)
temp=sapply(strsplit(as.character(twitter.df$created_at)," "),"[",1)
for (i in 1:7) {
temp=sub(a[i],"",temp)
}
##. top five days with highest no of tweets
plot(head(sort(table(temp), decreasing = TRUE)))
##. days with maximum no. of retweets.
dd.df<-aggregate(twitter.df$retweet_count,by=list(rt=temp),sum)
barplot(head(sort(dd.df$x, decreasing = TRUE)),xlab = "5 jan 9 jan 4 jan 27 feb 23 apr 21 apr")
de.df<-aggregate(twitter.df$favorite_count,by=list(rt=temp),sum)
barplot(head(sort(de.df$x, decreasing = TRUE)),xlab = "5 jan 9 jan 4 jan 27 feb 10 apr 02 jan")