Import the Data:
news <- read.csv("C:/Users/charl/Downloads/ANLY 530--OnlineNewsPopularity.csv")
str(news)
## 'data.frame': 39644 obs. of 61 variables:
## $ url : Factor w/ 39644 levels "http://mashable.com/2013/01/07/amazon-instant-video-browser/",..: 1 2 3 4 5 6 7 8 9 10 ...
## $ timedelta : int 731 731 731 731 731 731 731 731 731 731 ...
## $ n_tokens_title : int 12 9 9 9 13 10 8 12 11 10 ...
## $ n_tokens_content : int 219 255 211 531 1072 370 960 989 97 231 ...
## $ n_unique_tokens : num 0.664 0.605 0.575 0.504 0.416 ...
## $ n_non_stop_words : num 1 1 1 1 1 ...
## $ n_non_stop_unique_tokens : num 0.815 0.792 0.664 0.666 0.541 ...
## $ num_hrefs : int 4 3 3 9 19 2 21 20 2 4 ...
## $ num_self_hrefs : int 2 1 1 0 19 2 20 20 0 1 ...
## $ num_imgs : int 1 1 1 1 20 0 20 20 0 1 ...
## $ num_videos : int 0 0 0 0 0 0 0 0 0 1 ...
## $ average_token_length : num 4.68 4.91 4.39 4.4 4.68 ...
## $ num_keywords : int 5 4 6 7 7 9 10 9 7 5 ...
## $ data_channel_is_lifestyle : int 0 0 0 0 0 0 1 0 0 0 ...
## $ data_channel_is_entertainment: int 1 0 0 1 0 0 0 0 0 0 ...
## $ data_channel_is_bus : int 0 1 1 0 0 0 0 0 0 0 ...
## $ data_channel_is_socmed : int 0 0 0 0 0 0 0 0 0 0 ...
## $ data_channel_is_tech : int 0 0 0 0 1 1 0 1 1 0 ...
## $ data_channel_is_world : int 0 0 0 0 0 0 0 0 0 1 ...
## $ kw_min_min : int 0 0 0 0 0 0 0 0 0 0 ...
## $ kw_max_min : num 0 0 0 0 0 0 0 0 0 0 ...
## $ kw_avg_min : num 0 0 0 0 0 0 0 0 0 0 ...
## $ kw_min_max : int 0 0 0 0 0 0 0 0 0 0 ...
## $ kw_max_max : int 0 0 0 0 0 0 0 0 0 0 ...
## $ kw_avg_max : num 0 0 0 0 0 0 0 0 0 0 ...
## $ kw_min_avg : num 0 0 0 0 0 0 0 0 0 0 ...
## $ kw_max_avg : num 0 0 0 0 0 0 0 0 0 0 ...
## $ kw_avg_avg : num 0 0 0 0 0 0 0 0 0 0 ...
## $ self_reference_min_shares : num 496 0 918 0 545 8500 545 545 0 0 ...
## $ self_reference_max_shares : num 496 0 918 0 16000 8500 16000 16000 0 0 ...
## $ self_reference_avg_sharess : num 496 0 918 0 3151 ...
## $ weekday_is_monday : int 1 1 1 1 1 1 1 1 1 1 ...
## $ weekday_is_tuesday : int 0 0 0 0 0 0 0 0 0 0 ...
## $ weekday_is_wednesday : int 0 0 0 0 0 0 0 0 0 0 ...
## $ weekday_is_thursday : int 0 0 0 0 0 0 0 0 0 0 ...
## $ weekday_is_friday : int 0 0 0 0 0 0 0 0 0 0 ...
## $ weekday_is_saturday : int 0 0 0 0 0 0 0 0 0 0 ...
## $ weekday_is_sunday : int 0 0 0 0 0 0 0 0 0 0 ...
## $ is_weekend : int 0 0 0 0 0 0 0 0 0 0 ...
## $ LDA_00 : num 0.5003 0.7998 0.2178 0.0286 0.0286 ...
## $ LDA_01 : num 0.3783 0.05 0.0333 0.4193 0.0288 ...
## $ LDA_02 : num 0.04 0.0501 0.0334 0.4947 0.0286 ...
## $ LDA_03 : num 0.0413 0.0501 0.0333 0.0289 0.0286 ...
## $ LDA_04 : num 0.0401 0.05 0.6822 0.0286 0.8854 ...
## $ global_subjectivity : num 0.522 0.341 0.702 0.43 0.514 ...
## $ global_sentiment_polarity : num 0.0926 0.1489 0.3233 0.1007 0.281 ...
## $ global_rate_positive_words : num 0.0457 0.0431 0.0569 0.0414 0.0746 ...
## $ global_rate_negative_words : num 0.0137 0.01569 0.00948 0.02072 0.01213 ...
## $ rate_positive_words : num 0.769 0.733 0.857 0.667 0.86 ...
## $ rate_negative_words : num 0.231 0.267 0.143 0.333 0.14 ...
## $ avg_positive_polarity : num 0.379 0.287 0.496 0.386 0.411 ...
## $ min_positive_polarity : num 0.1 0.0333 0.1 0.1364 0.0333 ...
## $ max_positive_polarity : num 0.7 0.7 1 0.8 1 0.6 1 1 0.8 0.5 ...
## $ avg_negative_polarity : num -0.35 -0.119 -0.467 -0.37 -0.22 ...
## $ min_negative_polarity : num -0.6 -0.125 -0.8 -0.6 -0.5 -0.4 -0.5 -0.5 -0.125 -0.5 ...
## $ max_negative_polarity : num -0.2 -0.1 -0.133 -0.167 -0.05 ...
## $ title_subjectivity : num 0.5 0 0 0 0.455 ...
## $ title_sentiment_polarity : num -0.188 0 0 0 0.136 ...
## $ abs_title_subjectivity : num 0 0.5 0.5 0.5 0.0455 ...
## $ abs_title_sentiment_polarity : num 0.188 0 0 0 0.136 ...
## $ shares : int 593 711 1500 1200 505 855 556 891 3600 710 ...
Import the Data
newsShort <- data.frame(news$n_tokens_title, news$n_tokens_content, news$n_unique_tokens, news$n_non_stop_words, news$num_hrefs, news$num_imgs, news$num_videos, news$average_token_length, news$num_keywords, news$kw_max_max, news$global_sentiment_polarity, news$avg_positive_polarity, news$title_subjectivity, news$title_sentiment_polarity, news$abs_title_subjectivity, news$abs_title_sentiment_polarity, news$shares)
colnames(newsShort) <- c("n_tokens_title", "n_tokens_content", "n_unique_tokens", "n_non_stop_words", "num_hrefs", "num_imgs", "num_videos", "average_token_length", "num_keywords", "kw_max_max", "global_sentiment_polarity", "avg_positive_polarity", "title_subjectivity", "title_sentiment_polarity", "abs_title_subjectivity", "abs_title_sentiment_polarity", "shares")
Pre-Processing the Data
newsShort$popular = rep('na', nrow(newsShort))
for(i in 1:39644) {
if(newsShort$shares[i] >= 1400) {
newsShort$popular[i] = "yes"}
else {newsShort$popular[i] = "no"}
}
newsShort$shares = newsShort$popular
newsShort$shares <- as.factor(newsShort$shares)
set.seed(12345)
news_rand <- newsShort[order(runif(10000)), ]
Let us start the classification analysis:
#Split the data into training and test datasets
news_train <- news_rand[1:9000, ]
news_test <- news_rand[9001:10000, ]
Check the proportion of Data after randomization:
prop.table(table(news_train$shares))
##
## no yes
## 0.4308889 0.5691111
prop.table(table(news_test$shares))
##
## no yes
## 0.414 0.586
Let us Train the Model:
news_model <- C5.0(news_train[-17], news_train$shares)
summary(news_model)
##
## Call:
## C5.0.default(x = news_train[-17], y = news_train$shares)
##
##
## C5.0 [Release 2.07 GPL Edition] Sun Jul 01 19:20:32 2018
## -------------------------------
##
## Class specified by attribute `outcome'
##
## Read 9000 cases (18 attributes) from undefined.data
##
## Decision tree:
##
## popular = no: no (3878)
## popular = yes: yes (5122)
##
##
## Evaluation on training data (9000 cases):
##
## Decision Tree
## ----------------
## Size Errors
##
## 2 0( 0.0%) <<
##
##
## (a) (b) <-classified as
## ---- ----
## 3878 (a): class no
## 5122 (b): class yes
##
##
## Attribute usage:
##
## 100.00% popular
##
##
## Time: 0.1 secs
Evaluate the Model:
news_pred <- predict(news_model, news_test)
(p <- table(news_pred, news_test$shares))
##
## news_pred no yes
## no 414 0
## yes 0 586
(Accuracy <- sum(diag(p))/sum(p)*100)
## [1] 100
Let’s Visualize the Model:
plot(newsShort$shares)
As above, our dichotomy is the following:
summary(news_test$shares)
## no yes
## 414 586
Finally, let us re-evaluate part of the model:
library(gmodels)
CrossTable(news_test$shares, news_pred, prop.chisq = FALSE, prop.c = FALSE, prop.r = FALSE, dnn = c('actual shares', 'predicted shares'))
##
##
## Cell Contents
## |-------------------------|
## | N |
## | N / Table Total |
## |-------------------------|
##
##
## Total Observations in Table: 1000
##
##
## | predicted shares
## actual shares | no | yes | Row Total |
## --------------|-----------|-----------|-----------|
## no | 414 | 0 | 414 |
## | 0.414 | 0.000 | |
## --------------|-----------|-----------|-----------|
## yes | 0 | 586 | 586 |
## | 0.000 | 0.586 | |
## --------------|-----------|-----------|-----------|
## Column Total | 414 | 586 | 1000 |
## --------------|-----------|-----------|-----------|
##
##