Lab 1
Zihao Lin
1/6/2021
install.packages("C50",repos = "http://cran.us.r-project.org")## Installing package into 'C:/Users/FrankLin/Documents/R/win-library/3.6'
## (as 'lib' is unspecified)## package 'C50' successfully unpacked and MD5 sums checked## Warning: cannot remove prior installation of package 'C50'## Warning in file.copy(savedcopy, lib, recursive = TRUE): problem copying C:
## \Users\FrankLin\Documents\R\win-library\3.6\00LOCK\C50\libs\x64\C50.dll
## to C:\Users\FrankLin\Documents\R\win-library\3.6\C50\libs\x64\C50.dll:
## Permission denied## Warning: restored 'C50'##
## The downloaded binary packages are in
## C:\Users\FrankLin\AppData\Local\Temp\Rtmp2vdYWf\downloaded_packagesinstall.packages("randomForest",repos = "http://cran.us.r-project.org")## Installing package into 'C:/Users/FrankLin/Documents/R/win-library/3.6'
## (as 'lib' is unspecified)## package 'randomForest' successfully unpacked and MD5 sums checked## Warning: cannot remove prior installation of package 'randomForest'## Warning in file.copy(savedcopy, lib, recursive = TRUE):
## problem copying C:\Users\FrankLin\Documents\R\win-
## library\3.6\00LOCK\randomForest\libs\x64\randomForest.dll
## to C:\Users\FrankLin\Documents\R\win-
## library\3.6\randomForest\libs\x64\randomForest.dll: Permission denied## Warning: restored 'randomForest'##
## The downloaded binary packages are in
## C:\Users\FrankLin\AppData\Local\Temp\Rtmp2vdYWf\downloaded_packagesinstall.packages("rpart",repos = "http://cran.us.r-project.org")## Installing package into 'C:/Users/FrankLin/Documents/R/win-library/3.6'
## (as 'lib' is unspecified)## package 'rpart' successfully unpacked and MD5 sums checked
##
## The downloaded binary packages are in
## C:\Users\FrankLin\AppData\Local\Temp\Rtmp2vdYWf\downloaded_packagesinstall.packages("caTools",repos = "http://cran.us.r-project.org")## Installing package into 'C:/Users/FrankLin/Documents/R/win-library/3.6'
## (as 'lib' is unspecified)## package 'caTools' successfully unpacked and MD5 sums checked## Warning: cannot remove prior installation of package 'caTools'## Warning in file.copy(savedcopy, lib, recursive = TRUE):
## problem copying C:\Users\FrankLin\Documents\R\win-
## library\3.6\00LOCK\caTools\libs\x64\caTools.dll to C:
## \Users\FrankLin\Documents\R\win-library\3.6\caTools\libs\x64\caTools.dll:
## Permission denied## Warning: restored 'caTools'##
## The downloaded binary packages are in
## C:\Users\FrankLin\AppData\Local\Temp\Rtmp2vdYWf\downloaded_packagesinstall.packages("Metrics",repos = "http://cran.us.r-project.org")## Installing package into 'C:/Users/FrankLin/Documents/R/win-library/3.6'
## (as 'lib' is unspecified)## package 'Metrics' successfully unpacked and MD5 sums checked
##
## The downloaded binary packages are in
## C:\Users\FrankLin\AppData\Local\Temp\Rtmp2vdYWf\downloaded_packagesinstall.packages("rpart.plot",repos = "http://cran.us.r-project.org")## Installing package into 'C:/Users/FrankLin/Documents/R/win-library/3.6'
## (as 'lib' is unspecified)## package 'rpart.plot' successfully unpacked and MD5 sums checked
##
## The downloaded binary packages are in
## C:\Users\FrankLin\AppData\Local\Temp\Rtmp2vdYWf\downloaded_packageslibrary(moments)
##Step 1, Collecting the data##
credit = read.csv("/Users/FrankLin/Desktop/530/credit.csv", header = TRUE)
str(credit)## 'data.frame': 1000 obs. of 21 variables:
## $ Creditability : int 1 1 1 1 1 1 1 1 1 1 ...
## $ Account.Balance : int 1 1 2 1 1 1 1 1 4 2 ...
## $ Duration.of.Credit..month. : int 18 9 12 12 12 10 8 6 18 24 ...
## $ Payment.Status.of.Previous.Credit: int 4 4 2 4 4 4 4 4 4 2 ...
## $ Purpose : int 2 0 9 0 0 0 0 0 3 3 ...
## $ Credit.Amount : int 1049 2799 841 2122 2171 2241 3398 1361 1098 3758 ...
## $ Value.Savings.Stocks : int 1 1 2 1 1 1 1 1 1 3 ...
## $ Length.of.current.employment : int 2 3 4 3 3 2 4 2 1 1 ...
## $ Instalment.per.cent : int 4 2 2 3 4 1 1 2 4 1 ...
## $ Sex...Marital.Status : int 2 3 2 3 3 3 3 3 2 2 ...
## $ Guarantors : int 1 1 1 1 1 1 1 1 1 1 ...
## $ Duration.in.Current.address : int 4 2 4 2 4 3 4 4 4 4 ...
## $ Most.valuable.available.asset : int 2 1 1 1 2 1 1 1 3 4 ...
## $ Age..years. : int 21 36 23 39 38 48 39 40 65 23 ...
## $ Concurrent.Credits : int 3 3 3 3 1 3 3 3 3 3 ...
## $ Type.of.apartment : int 1 1 1 1 2 1 2 2 2 1 ...
## $ No.of.Credits.at.this.Bank : int 1 2 1 2 2 2 2 1 2 1 ...
## $ Occupation : int 3 3 2 2 2 2 2 2 1 1 ...
## $ No.of.dependents : int 1 2 1 2 1 2 1 2 1 1 ...
## $ Telephone : int 1 1 1 1 1 1 1 1 1 1 ...
## $ Foreign.Worker : int 1 1 1 2 2 2 2 2 1 1 ...##Step 2, Exploring the data##
summary(credit$Credit.Amount)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 250 1366 2320 3271 3972 18424table(credit$Creditability)##
## 0 1
## 300 700set.seed(23458)
credit_rand <- credit[order(runif(1000)), ]
summary(credit$Credit.Amount)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 250 1366 2320 3271 3972 18424credit_train <- credit_rand[1:900, ]
credit_test <- credit_rand[901:1000, ]
prop.table(table(credit_train$ Creditability))##
## 0 1
## 0.2988889 0.7011111prop.table(table(credit_test$Creditability))##
## 0 1
## 0.31 0.69##Step 3: Training a model on the data##
library(C50)## Warning: package 'C50' was built under R version 3.6.3credit_train$Creditability<-as.factor(credit_train$Creditability)
str(credit_train$Creditability)## Factor w/ 2 levels "0","1": 2 2 2 2 1 2 2 2 2 1 ...credit_model <- C5.0(x = credit_train[-1], credit_train$Creditability)
summary(credit_model)##
## Call:
## C5.0.default(x = credit_train[-1], y = credit_train$Creditability)
##
##
## C5.0 [Release 2.07 GPL Edition] Thu Jan 07 19:29:59 2021
## -------------------------------
##
## Class specified by attribute `outcome'
##
## Read 900 cases (21 attributes) from undefined.data
##
## Decision tree:
##
## Account.Balance > 2:
## :...Concurrent.Credits <= 2:
## : :...Purpose <= 0:
## : : :...Duration.of.Credit..month. <= 15: 1 (4)
## : : : Duration.of.Credit..month. > 15: 0 (9/1)
## : : Purpose > 0:
## : : :...Purpose <= 4: 1 (32/2)
## : : Purpose > 4:
## : : :...Length.of.current.employment > 3: 1 (7/1)
## : : Length.of.current.employment <= 3:
## : : :...Instalment.per.cent <= 1: 1 (2)
## : : Instalment.per.cent > 1: 0 (8/1)
## : Concurrent.Credits > 2:
## : :...Duration.of.Credit..month. <= 33: 1 (307/29)
## : Duration.of.Credit..month. > 33:
## : :...Length.of.current.employment > 3: 1 (24)
## : Length.of.current.employment <= 3:
## : :...Type.of.apartment <= 1: 0 (4)
## : Type.of.apartment > 1:
## : :...Duration.in.Current.address > 3: 1 (7)
## : Duration.in.Current.address <= 3:
## : :...Payment.Status.of.Previous.Credit <= 1: 1 (3)
## : Payment.Status.of.Previous.Credit > 1: 0 (7/1)
## Account.Balance <= 2:
## :...Payment.Status.of.Previous.Credit <= 1:
## :...Guarantors > 1: 1 (5/1)
## : Guarantors <= 1:
## : :...Type.of.apartment <= 1: 0 (13)
## : Type.of.apartment > 1:
## : :...Type.of.apartment > 2: 0 (11/1)
## : Type.of.apartment <= 2:
## : :...Sex...Marital.Status > 3: 1 (2)
## : Sex...Marital.Status <= 3:
## : :...Value.Savings.Stocks > 2:
## : :...Credit.Amount <= 2064: 0 (2)
## : : Credit.Amount > 2064: 1 (7)
## : Value.Savings.Stocks <= 2:
## : :...Purpose <= 6: 0 (13/1)
## : Purpose > 6:
## : :...Credit.Amount <= 4221: 1 (4)
## : Credit.Amount > 4221: 0 (4)
## Payment.Status.of.Previous.Credit > 1:
## :...Duration.of.Credit..month. > 22:
## :...Value.Savings.Stocks > 3:
## : :...Account.Balance > 1:
## : : :...Credit.Amount <= 9629: 1 (15)
## : : : Credit.Amount > 9629: 0 (2)
## : : Account.Balance <= 1:
## : : :...Most.valuable.available.asset > 2: 0 (7/1)
## : : Most.valuable.available.asset <= 2:
## : : :...Purpose <= 0: 0 (2)
## : : Purpose > 0: 1 (5)
## : Value.Savings.Stocks <= 3:
## : :...Duration.of.Credit..month. > 47:
## : :...Occupation <= 3: 0 (17/1)
## : : Occupation > 3:
## : : :...Purpose <= 4: 0 (4)
## : : Purpose > 4: 1 (2)
## : Duration.of.Credit..month. <= 47:
## : :...Length.of.current.employment > 3:
## : :...Value.Savings.Stocks > 1: 1 (11/1)
## : : Value.Savings.Stocks <= 1:
## : : :...No.of.dependents > 1:
## : : :...Duration.in.Current.address <= 2: 0 (3/1)
## : : : Duration.in.Current.address > 2: 1 (7)
## : : No.of.dependents <= 1:
## : : :...Purpose <= 2: 0 (16/3)
## : : Purpose > 2:
## : : :...Instalment.per.cent <= 3: 0 (3/1)
## : : Instalment.per.cent > 3: 1 (7)
## : Length.of.current.employment <= 3:
## : :...No.of.dependents > 1: 0 (9/1)
## : No.of.dependents <= 1:
## : :...Length.of.current.employment <= 1:
## : :...Sex...Marital.Status <= 3: 1 (8/1)
## : : Sex...Marital.Status > 3: 0 (2)
## : Length.of.current.employment > 1:
## : :...Duration.in.Current.address <= 2:
## : :...Value.Savings.Stocks > 1: 0 (5/1)
## : : Value.Savings.Stocks <= 1:
## : : :...Concurrent.Credits <= 1: 0 (5/1)
## : : Concurrent.Credits > 1: [S1]
## : Duration.in.Current.address > 2:
## : :...Type.of.apartment <= 1: 0 (9)
## : Type.of.apartment > 1:
## : :...Concurrent.Credits <= 2: 0 (5)
## : Concurrent.Credits > 2:
## : :...Credit.Amount <= 3448: 0 (7)
## : Credit.Amount > 3448:
## : :...Account.Balance > 1: 1 (3)
## : Account.Balance <= 1: [S2]
## Duration.of.Credit..month. <= 22:
## :...Guarantors > 2:
## :...Purpose <= 1: 0 (3)
## : Purpose > 1: 1 (24)
## Guarantors <= 2:
## :...Payment.Status.of.Previous.Credit > 2:
## :...Guarantors <= 1: 1 (78/13)
## : Guarantors > 1:
## : :...Credit.Amount <= 2255: 1 (2)
## : Credit.Amount > 2255: 0 (2)
## Payment.Status.of.Previous.Credit <= 2:
## :...No.of.Credits.at.this.Bank > 1:
## :...Sex...Marital.Status <= 2: 0 (6)
## : Sex...Marital.Status > 2: 1 (6/1)
## No.of.Credits.at.this.Bank <= 1:
## :...Purpose > 8: 1 (10)
## Purpose <= 8:
## :...Credit.Amount > 7485: 0 (6)
## Credit.Amount <= 7485:
## :...Credit.Amount > 1372:
## :...Concurrent.Credits <= 2: 1 (4)
## : Concurrent.Credits > 2:
## : :...Telephone > 1: [S3]
## : Telephone <= 1: [S4]
## Credit.Amount <= 1372:
## :...Telephone > 1: [S5]
## Telephone <= 1:
## :...Concurrent.Credits <= 2: 0 (5)
## Concurrent.Credits > 2:
## :...Account.Balance > 1: [S6]
## Account.Balance <= 1: [S7]
##
## SubTree [S1]
##
## Most.valuable.available.asset <= 3: 1 (17/5)
## Most.valuable.available.asset > 3: 0 (2)
##
## SubTree [S2]
##
## Duration.of.Credit..month. <= 30: 1 (2)
## Duration.of.Credit..month. > 30: 0 (2)
##
## SubTree [S3]
##
## Duration.in.Current.address <= 2: 0 (7/2)
## Duration.in.Current.address > 2: 1 (9)
##
## SubTree [S4]
##
## Duration.of.Credit..month. <= 16: 1 (27/2)
## Duration.of.Credit..month. > 16:
## :...Credit.Amount <= 2528: 0 (4)
## Credit.Amount > 2528: 1 (7/1)
##
## SubTree [S5]
##
## Length.of.current.employment <= 2: 0 (3/1)
## Length.of.current.employment > 2: 1 (6)
##
## SubTree [S6]
##
## Sex...Marital.Status > 3: 1 (3)
## Sex...Marital.Status <= 3:
## :...Duration.in.Current.address <= 2: 0 (4)
## Duration.in.Current.address > 2: 1 (9/2)
##
## SubTree [S7]
##
## Most.valuable.available.asset > 1: 0 (13/1)
## Most.valuable.available.asset <= 1:
## :...Age..years. <= 26: 0 (3)
## Age..years. > 26:
## :...Occupation > 2: 1 (3)
## Occupation <= 2:
## :...Sex...Marital.Status <= 3: 0 (2)
## Sex...Marital.Status > 3: 1 (2)
##
##
## Evaluation on training data (900 cases):
##
## Decision Tree
## ----------------
## Size Errors
##
## 74 78( 8.7%) <<
##
##
## (a) (b) <-classified as
## ---- ----
## 210 59 (a): class 0
## 19 612 (b): class 1
##
##
## Attribute usage:
##
## 100.00% Account.Balance
## 87.78% Duration.of.Credit..month.
## 62.11% Concurrent.Credits
## 55.11% Payment.Status.of.Previous.Credit
## 34.33% Guarantors
## 30.67% Purpose
## 23.00% Value.Savings.Stocks
## 21.56% Length.of.current.employment
## 18.78% Credit.Amount
## 15.44% No.of.Credits.at.this.Bank
## 12.56% Duration.in.Current.address
## 12.44% No.of.dependents
## 11.89% Telephone
## 11.67% Type.of.apartment
## 8.22% Sex...Marital.Status
## 6.22% Most.valuable.available.asset
## 3.33% Occupation
## 2.22% Instalment.per.cent
## 1.11% Age..years.
##
##
## Time: 0.0 secs##Step 4: Evaluating Model Performance
cred_pred <- predict(credit_model, credit_test)
library(gmodels)## Warning: package 'gmodels' was built under R version 3.6.3CrossTable(credit_test$Creditability, cred_pred, prop.chisq = FALSE, prop.c = FALSE, prop.r = FALSE, dnn = c( 'Actual Creditability', 'Predicted Creditability'))##
##
## Cell Contents
## |-------------------------|
## | N |
## | N / Table Total |
## |-------------------------|
##
##
## Total Observations in Table: 100
##
##
## | Predicted Creditability
## Actual Creditability | 0 | 1 | Row Total |
## ---------------------|-----------|-----------|-----------|
## 0 | 15 | 16 | 31 |
## | 0.150 | 0.160 | |
## ---------------------|-----------|-----------|-----------|
## 1 | 14 | 55 | 69 |
## | 0.140 | 0.550 | |
## ---------------------|-----------|-----------|-----------|
## Column Total | 29 | 71 | 100 |
## ---------------------|-----------|-----------|-----------|
##
## Q1- If you see an accuracy of 100%, what does it mean? Does this mean that we design a perfect model? This is some thing that needs more discussion. Write a few sentences about accuracy of 100%.
Answer: I think something is wrong in my medol if the accuracy is 100%. No, it’s not perfect model. Probably the test set is very similiar to the training set.
##Method2 Random forest
library(randomForest)## randomForest 4.6-14## Type rfNews() to see new features/changes/bug fixes.credit_train$Creditability <- as.factor(credit_train$Creditability)
random_model <- randomForest(Creditability ~ . , data= credit_train)
summary(random_model)## Length Class Mode
## call 3 -none- call
## type 1 -none- character
## predicted 900 factor numeric
## err.rate 1500 -none- numeric
## confusion 6 -none- numeric
## votes 1800 matrix numeric
## oob.times 900 -none- numeric
## classes 2 -none- character
## importance 20 -none- numeric
## importanceSD 0 -none- NULL
## localImportance 0 -none- NULL
## proximity 0 -none- NULL
## ntree 1 -none- numeric
## mtry 1 -none- numeric
## forest 14 -none- list
## y 900 factor numeric
## test 0 -none- NULL
## inbag 0 -none- NULL
## terms 3 terms callcred_pred <- predict(random_model, credit_test)
(p <- table(cred_pred, credit_test$Creditability))##
## cred_pred 0 1
## 0 11 5
## 1 20 64(Accuracy <- sum(diag(p))/sum(p)*100)## [1] 75##Q2- What are the three most important features in this model? ## Answer: Credit.Amount; Account.Balance;Age..years. ## If change seed to 23458, the accuracy is 75%
importance(random_model)## MeanDecreaseGini
## Account.Balance 39.457314
## Duration.of.Credit..month. 38.019433
## Payment.Status.of.Previous.Credit 22.546142
## Purpose 23.951809
## Credit.Amount 50.541383
## Value.Savings.Stocks 17.205724
## Length.of.current.employment 20.627185
## Instalment.per.cent 15.719838
## Sex...Marital.Status 13.367657
## Guarantors 7.016187
## Duration.in.Current.address 15.719091
## Most.valuable.available.asset 16.545241
## Age..years. 38.381132
## Concurrent.Credits 9.531617
## Type.of.apartment 10.301770
## No.of.Credits.at.this.Bank 7.946921
## Occupation 12.310681
## No.of.dependents 5.217456
## Telephone 7.157283
## Foreign.Worker 1.465606#Method #3. Adding regression to trees
#Step 1: Collecting the Data
wine = read.csv("/Users/FrankLin/Desktop/530/whitewines.csv", header = TRUE)
str(wine)## 'data.frame': 4898 obs. of 12 variables:
## $ fixed.acidity : num 6.7 5.7 5.9 5.3 6.4 7 7.9 6.6 7 6.5 ...
## $ volatile.acidity : num 0.62 0.22 0.19 0.47 0.29 0.14 0.12 0.38 0.16 0.37 ...
## $ citric.acid : num 0.24 0.2 0.26 0.1 0.21 0.41 0.49 0.28 0.3 0.33 ...
## $ residual.sugar : num 1.1 16 7.4 1.3 9.65 0.9 5.2 2.8 2.6 3.9 ...
## $ chlorides : num 0.039 0.044 0.034 0.036 0.041 0.037 0.049 0.043 0.043 0.027 ...
## $ free.sulfur.dioxide : num 6 41 33 11 36 22 33 17 34 40 ...
## $ total.sulfur.dioxide: num 62 113 123 74 119 95 152 67 90 130 ...
## $ density : num 0.993 0.999 0.995 0.991 0.993 ...
## $ pH : num 3.41 3.22 3.49 3.48 2.99 3.25 3.18 3.21 2.88 3.28 ...
## $ sulphates : num 0.32 0.46 0.42 0.54 0.34 0.43 0.47 0.47 0.47 0.39 ...
## $ alcohol : num 10.4 8.9 10.1 11.2 10.9 ...
## $ quality : int 5 6 6 4 6 6 6 6 6 7 ...hist(wine$quality)
#Step2:Exploring and Preparing the Data
wine_train <- wine[1:3750, ]
wine_test <- wine[3751:4898, ]#Step 3: Training a Model on the Data
library(rpart)## Warning: package 'rpart' was built under R version 3.6.3m.rpart <- rpart(quality ~ ., data=wine_train)
m.rpart## n= 3750
##
## node), split, n, deviance, yval
## * denotes terminal node
##
## 1) root 3750 2945.53200 5.870933
## 2) alcohol< 10.85 2372 1418.86100 5.604975
## 4) volatile.acidity>=0.2275 1611 821.30730 5.432030
## 8) volatile.acidity>=0.3025 688 278.97670 5.255814 *
## 9) volatile.acidity< 0.3025 923 505.04230 5.563380 *
## 5) volatile.acidity< 0.2275 761 447.36400 5.971091 *
## 3) alcohol>=10.85 1378 1070.08200 6.328737
## 6) free.sulfur.dioxide< 10.5 84 95.55952 5.369048 *
## 7) free.sulfur.dioxide>=10.5 1294 892.13600 6.391036
## 14) alcohol< 11.76667 629 430.11130 6.173291
## 28) volatile.acidity>=0.465 11 10.72727 4.545455 *
## 29) volatile.acidity< 0.465 618 389.71680 6.202265 *
## 15) alcohol>=11.76667 665 403.99400 6.596992 *library(rpart.plot)## Warning: package 'rpart.plot' was built under R version 3.6.3rpart.plot(m.rpart, digits=3)
rpart.plot(m.rpart, digits=4, fallen.leaves = TRUE, type = 3, extra = 101)
#Step 4: Evaluating Model Performance
p.rpart = predict(m.rpart, wine_test)
summary(p.rpart)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 4.545 5.563 5.971 5.893 6.202 6.597summary(wine_test$quality)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 3.000 5.000 6.000 5.901 6.000 9.000cor(p.rpart, wine_test$quality)## [1] 0.5369525Q3:What is your interpretation about this amount of RMSE?
Answer:The RMSE is 0.74, see below
library(Metrics)## Warning: package 'Metrics' was built under R version 3.6.3rmse(wine_test$quality, p.rpart)## [1] 0.7448093#Method 4. News Popularity
#Step 1: Collecting the Data
news = read.csv("/Users/FrankLin/Desktop/530/OnlineNewsPopularity_for_R.csv", header = TRUE)
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 : num 731 731 731 731 731 731 731 731 731 731 ...
## $ n_tokens_title : num 12 9 9 9 13 10 8 12 11 10 ...
## $ n_tokens_content : num 219 255 211 531 1072 ...
## $ 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 : num 4 3 3 9 19 2 21 20 2 4 ...
## $ num_self_hrefs : num 2 1 1 0 19 2 20 20 0 1 ...
## $ num_imgs : num 1 1 1 1 20 0 20 20 0 1 ...
## $ num_videos : num 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 : num 5 4 6 7 7 9 10 9 7 5 ...
## $ data_channel_is_lifestyle : num 0 0 0 0 0 0 1 0 0 0 ...
## $ data_channel_is_entertainment: num 1 0 0 1 0 0 0 0 0 0 ...
## $ data_channel_is_bus : num 0 1 1 0 0 0 0 0 0 0 ...
## $ data_channel_is_socmed : num 0 0 0 0 0 0 0 0 0 0 ...
## $ data_channel_is_tech : num 0 0 0 0 1 1 0 1 1 0 ...
## $ data_channel_is_world : num 0 0 0 0 0 0 0 0 0 1 ...
## $ kw_min_min : num 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 : num 0 0 0 0 0 0 0 0 0 0 ...
## $ kw_max_max : num 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 : num 1 1 1 1 1 1 1 1 1 1 ...
## $ weekday_is_tuesday : num 0 0 0 0 0 0 0 0 0 0 ...
## $ weekday_is_wednesday : num 0 0 0 0 0 0 0 0 0 0 ...
## $ weekday_is_thursday : num 0 0 0 0 0 0 0 0 0 0 ...
## $ weekday_is_friday : num 0 0 0 0 0 0 0 0 0 0 ...
## $ weekday_is_saturday : num 0 0 0 0 0 0 0 0 0 0 ...
## $ weekday_is_sunday : num 0 0 0 0 0 0 0 0 0 0 ...
## $ is_weekend : num 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 ...#Step 2:Pre-processing
library(caTools)
library(dplyr)##
## Attaching package: 'dplyr'## The following object is masked from 'package:randomForest':
##
## combine## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionnewsShort =
news %>%
select(starts_with("n_"),starts_with("num_"),average_token_length,kw_max_max,global_sentiment_polarity,avg_positive_polarity,starts_with("title"),starts_with("abs"),shares,-n_non_stop_unique_tokens,-num_self_hrefs) %>%
mutate(shares = as.numeric(shares),
shares = case_when(shares >=1400 ~ "yes",
TRUE ~ "no"),
shares = as.factor(shares))
set.seed(12345)
news_split = sample.split(newsShort$shares,SplitRatio = 0.9)
news_train = newsShort[news_split == TRUE,]
news_test = newsShort[news_split == FALSE,]
prop.table(table(news_train$shares))##
## no yes
## 0.4663957 0.5336043prop.table(table(news_test$shares))##
## no yes
## 0.466448 0.533552## Check model
colnames(news_train)## [1] "n_tokens_title" "n_tokens_content"
## [3] "n_unique_tokens" "n_non_stop_words"
## [5] "num_hrefs" "num_imgs"
## [7] "num_videos" "num_keywords"
## [9] "average_token_length" "kw_max_max"
## [11] "global_sentiment_polarity" "avg_positive_polarity"
## [13] "title_subjectivity" "title_sentiment_polarity"
## [15] "abs_title_subjectivity" "abs_title_sentiment_polarity"
## [17] "shares"library(C50)
news_model = C5.0(news_train[-17],news_train$shares)
summary((news_model))##
## Call:
## C5.0.default(x = news_train[-17], y = news_train$shares)
##
##
## C5.0 [Release 2.07 GPL Edition] Thu Jan 07 19:30:08 2021
## -------------------------------
##
## Class specified by attribute `outcome'
##
## Read 35680 cases (17 attributes) from undefined.data
##
## Decision tree:
##
## num_imgs > 3:
## :...kw_max_max <= 15000:
## : :...n_tokens_content <= 1206: no (25/4)
## : : n_tokens_content > 1206: yes (5)
## : kw_max_max > 15000:
## : :...num_keywords <= 5:
## : :...num_videos > 2:
## : : :...abs_title_sentiment_polarity <= 0.1305556: no (49/11)
## : : : abs_title_sentiment_polarity > 0.1305556:
## : : : :...average_token_length <= 4.347826: no (5)
## : : : average_token_length > 4.347826:
## : : : :...num_hrefs > 12: yes (13/1)
## : : : num_hrefs <= 12:
## : : : :...title_subjectivity <= 0.5190476: no (7/1)
## : : : title_subjectivity > 0.5190476: yes (2)
## : : num_videos <= 2:
## : : :...n_tokens_title <= 9:
## : : :...num_videos > 0: yes (78/20)
## : : : num_videos <= 0:
## : : : :...n_tokens_title > 7: yes (206/77)
## : : : n_tokens_title <= 7:
## : : : :...num_keywords <= 4: yes (28/11)
## : : : num_keywords > 4: no (52/20)
## : : n_tokens_title > 9:
## : : :...num_imgs > 30:
## : : :...num_videos <= 0: no (74/25)
## : : : num_videos > 0:
## : : : :...global_sentiment_polarity <= 0.1016769: no (18)
## : : : global_sentiment_polarity > 0.1016769: yes (16/5)
## : : num_imgs <= 30:
## : : :...kw_max_max <= 690400: yes (101/37)
## : : kw_max_max > 690400:
## : : :...num_keywords > 4: yes (356/168)
## : : num_keywords <= 4:
## : : :...num_videos <= 0: no (127/46)
## : : num_videos > 0: yes (45/19)
## : num_keywords > 5:
## : :...n_tokens_content > 2951: yes (68/7)
## : n_tokens_content <= 2951:
## : :...num_hrefs > 11:
## : :...n_tokens_title > 9:
## : : :...n_tokens_content <= 319: yes (634/180)
## : : : n_tokens_content > 319:
## : : : :...n_tokens_title <= 13: yes (2073/781)
## : : : n_tokens_title > 13:
## : : : :...num_keywords <= 9:
## : : : :...abs_title_subjectivity <= 0.325: yes (63/27)
## : : : : abs_title_subjectivity > 0.325: no (70/23)
## : : : num_keywords > 9:
## : : : :...title_sentiment_polarity <= 0.452381: yes (49/16)
## : : : title_sentiment_polarity > 0.452381: no (3)
## : : n_tokens_title <= 9:
## : : :...num_keywords > 6: yes (1640/461)
## : : num_keywords <= 6:
## : : :...n_tokens_content > 2216:
## : : :...global_sentiment_polarity <= 0.2137865: no (14/1)
## : : : global_sentiment_polarity > 0.2137865: yes (3)
## : : n_tokens_content <= 2216:
## : : :...n_tokens_title <= 7:
## : : :...n_tokens_title <= 6:
## : : : :...average_token_length <= 4.889474: yes (19/2)
## : : : : average_token_length > 4.889474: no (3)
## : : : n_tokens_title > 6:
## : : : :...avg_positive_polarity <= 0.3149621: no (3)
## : : : avg_positive_polarity > 0.3149621: yes (43/9)
## : : n_tokens_title > 7:
## : : :...num_hrefs <= 27:
## : : :...average_token_length <= 5.397143: yes (136/49)
## : : : average_token_length > 5.397143: no (7/1)
## : : num_hrefs > 27:
## : : :...avg_positive_polarity <= 0.4811688: yes (36/5)
## : : avg_positive_polarity > 0.4811688: no (6/1)
## : num_hrefs <= 11:
## : :...num_videos > 1: yes (286/94)
## : num_videos <= 1:
## : :...n_tokens_content <= 373:
## : :...title_subjectivity <= 0.6822727:
## : : :...num_imgs <= 41: yes (833/320)
## : : : num_imgs > 41:
## : : : :...title_subjectivity <= 0.2416667: yes (3)
## : : : title_subjectivity > 0.2416667: no (9)
## : : title_subjectivity > 0.6822727:
## : : :...kw_max_max > 690400: yes (155/35)
## : : kw_max_max <= 690400:
## : : :...title_subjectivity <= 0.875: yes (7)
## : : title_subjectivity > 0.875: [S1]
## : n_tokens_content > 373:
## : :...average_token_length > 4.948864:
## : :...title_subjectivity > 0.44375: yes (59/26)
## : : title_subjectivity <= 0.44375:
## : : :...num_videos <= 0: no (101/30)
## : : num_videos > 0:
## : : :...avg_positive_polarity <= 0.4021769: no (33/8)
## : : avg_positive_polarity > 0.4021769: yes (7/1)
## : average_token_length <= 4.948864:
## : :...kw_max_max <= 617900: yes (252/88)
## : kw_max_max > 617900:
## : :...n_tokens_title > 8:
## : :...num_videos > 0:
## : : :...num_hrefs <= 8: yes (300/114)
## : : : num_hrefs > 8: no (93/40)
## : : num_videos <= 0:
## : : :...num_hrefs > 6: yes (413/169)
## : : num_hrefs <= 6:
## : : :...n_tokens_title <= 9: yes (91/40)
## : : n_tokens_title > 9: no (404/182)
## : n_tokens_title <= 8:
## : :...kw_max_max > 690400: yes (182/57)
## : kw_max_max <= 690400:
## : :...n_tokens_content <= 473: no (10)
## : n_tokens_content > 473:
## : :...num_hrefs <= 4: yes (9)
## : num_hrefs > 4: [S2]
## num_imgs <= 3:
## :...n_unique_tokens <= 0.4305239:
## :...kw_max_max <= 663600: yes (248/55)
## : kw_max_max > 663600:
## : :...global_sentiment_polarity > 0.1322018:
## : :...num_videos > 8: no (33/15)
## : : num_videos <= 8:
## : : :...num_hrefs > 7: yes (569/131)
## : : num_hrefs <= 7:
## : : :...num_imgs <= 1: yes (122/44)
## : : num_imgs > 1:
## : : :...title_sentiment_polarity > 0.2071429: no (6)
## : : title_sentiment_polarity <= 0.2071429:
## : : :...n_tokens_content > 1220: no (15/3)
## : : n_tokens_content <= 1220:
## : : :...average_token_length <= 4.381201: no (7/2)
## : : average_token_length > 4.381201: yes (16/1)
## : global_sentiment_polarity <= 0.1322018:
## : :...num_hrefs > 32:
## : :...average_token_length <= 5.10728: yes (49/8)
## : : average_token_length > 5.10728: no (3)
## : num_hrefs <= 32:
## : :...num_videos > 6: no (30/9)
## : num_videos <= 6:
## : :...average_token_length <= 4.709486: yes (1242/520)
## : average_token_length > 4.709486:
## : :...num_hrefs > 16:
## : :...global_sentiment_polarity > 0.06642009: yes (54/13)
## : : global_sentiment_polarity <= 0.06642009:
## : : :...global_sentiment_polarity <= 0.01395874: yes (10/2)
## : : global_sentiment_polarity > 0.01395874: no (23/4)
## : num_hrefs <= 16:
## : :...n_unique_tokens <= 0.3680473:
## : :...avg_positive_polarity <= 0.2991207: no (6/1)
## : : avg_positive_polarity > 0.2991207: yes (17/2)
## : n_unique_tokens > 0.3680473:
## : :...num_videos <= 1:
## : :...n_unique_tokens <= 0.42898: no (153/33)
## : : n_unique_tokens > 0.42898: yes (8/2)
## : num_videos > 1:
## : :...num_keywords <= 5: no (5)
## : num_keywords > 5: yes (15/4)
## n_unique_tokens > 0.4305239:
## :...kw_max_max <= 617900:
## :...kw_max_max > 69100: yes (1766/638)
## : kw_max_max <= 69100:
## : :...num_hrefs > 4: no (1103/546)
## : num_hrefs <= 4:
## : :...kw_max_max <= 37400:
## : :...title_subjectivity <= 0.725: no (86/32)
## : : title_subjectivity > 0.725: yes (14/1)
## : kw_max_max > 37400:
## : :...num_imgs > 0: yes (313/135)
## : num_imgs <= 0:
## : :...num_keywords <= 5:
## : :...num_keywords <= 4: yes (5/1)
## : : num_keywords > 4:
## : : :...average_token_length <= 4.465278: yes (8/2)
## : : average_token_length > 4.465278: no (14/2)
## : num_keywords > 5:
## : :...n_non_stop_words > 0.9999999: yes (213/69)
## : n_non_stop_words <= 0.9999999:
## : :...average_token_length <= 4.954774: yes (8)
## : average_token_length > 4.954774: no (5)
## kw_max_max > 617900:
## :...num_hrefs > 21:
## :...n_tokens_title > 9:
## : :...title_subjectivity > 0.975: yes (53/13)
## : : title_subjectivity <= 0.975:
## : : :...num_imgs <= 0: yes (137/53)
## : : num_imgs > 0: no (559/274)
## : n_tokens_title <= 9:
## : :...kw_max_max <= 690400: yes (83/15)
## : kw_max_max > 690400:
## : :...global_sentiment_polarity > 0.06215278: yes (275/76)
## : global_sentiment_polarity <= 0.06215278:
## : :...num_imgs > 1: no (15/3)
## : num_imgs <= 1:
## : :...average_token_length > 5.667984: no (4)
## : average_token_length <= 5.667984:
## : :...num_hrefs > 37: yes (8)
## : num_hrefs <= 37:
## : :...n_tokens_title <= 7: yes (9/3)
## : n_tokens_title > 7:
## : :...title_subjectivity <= 0.775: no (29/8)
## : title_subjectivity > 0.775: yes (2)
## num_hrefs <= 21:
## :...global_sentiment_polarity <= 0.07039773:
## :...num_imgs <= 0:
## : :...num_videos > 25:
## : : :...n_unique_tokens <= 0.5114286: no (42/6)
## : : : n_unique_tokens > 0.5114286:
## : : : :...num_hrefs <= 4: no (4)
## : : : num_hrefs > 4: yes (11/2)
## : : num_videos <= 25:
## : : :...num_keywords <= 5: no (236/96)
## : : num_keywords > 5:
## : : :...n_tokens_title <= 10: no (381/177)
## : : n_tokens_title > 10:
## : : :...kw_max_max > 690400: yes (414/192)
## : : kw_max_max <= 690400:
## : : :...num_keywords <= 6: yes (12)
## : : num_keywords > 6:
## : : :...n_unique_tokens <= 0.6736842:
## : : :...num_videos <= 0: yes (6/2)
## : : : num_videos > 0: no (17/4)
## : : n_unique_tokens > 0.6736842: [S3]
## : num_imgs > 0:
## : :...n_unique_tokens > 0.7686567:
## : :...title_sentiment_polarity <= -0.35: no (3)
## : : title_sentiment_polarity > -0.35: yes (43/11)
## : n_unique_tokens <= 0.7686567:
## : :...num_hrefs <= 1: no (163/31)
## : num_hrefs > 1:
## : :...average_token_length <= 4.805281:
## : :...num_imgs <= 2:
## : : :...average_token_length <= 4.305466: yes (170/74)
## : : : average_token_length > 4.305466: no (2187/876)
## : : num_imgs > 2:
## : : :...num_hrefs <= 2: no (18/4)
## : : num_hrefs > 2: [S4]
## : average_token_length > 4.805281:
## : :...num_hrefs > 20: yes (26/9)
## : num_hrefs <= 20:
## : :...kw_max_max <= 690400:
## : :...n_tokens_title > 9:
## : : :...num_hrefs <= 5: yes (27/8)
## : : : num_hrefs > 5:
## : : : :...num_videos > 0: [S5]
## : : : num_videos <= 0: [S6]
## : : n_tokens_title <= 9: [S7]
## : kw_max_max > 690400:
## : :...num_keywords <= 6: no (798/218)
## : num_keywords > 6:
## : :...num_imgs <= 1:
## : :...num_videos <= 1: no (646/205)
## : : num_videos > 1: [S8]
## : num_imgs > 1: [S9]
## global_sentiment_polarity > 0.07039773:
## :...num_imgs > 1:
## :...num_keywords > 9: yes (296/97)
## : num_keywords <= 9:
## : :...n_tokens_content <= 579: yes (1266/522)
## : n_tokens_content > 579:
## : :...title_subjectivity > 0.47: no (142/45)
## : title_subjectivity <= 0.47:
## : :...global_sentiment_polarity <= 0.09938672: no (117/41)
## : global_sentiment_polarity > 0.09938672:
## : :...num_hrefs > 3: yes (238/86)
## : num_hrefs <= 3: [S10]
## num_imgs <= 1:
## :...num_videos <= 0:
## :...title_sentiment_polarity <= -0.006397306:
## : :...n_unique_tokens > 0.71875: no (164/25)
## : : n_unique_tokens <= 0.71875:
## : : :...n_tokens_title > 12: no (133/38)
## : : n_tokens_title <= 12:
## : : :...num_imgs > 0:
## : : :...n_tokens_title <= 7: yes (29/11)
## : : : n_tokens_title > 7: no (404/161)
## : : num_imgs <= 0:
## : : :...n_tokens_title > 10: yes (28/7)
## : : n_tokens_title <= 10:
## : : :...num_keywords <= 6: no (13/1)
## : : num_keywords > 6: [S11]
## : title_sentiment_polarity > -0.006397306:
## : :...num_imgs <= 0:
## : :...abs_title_subjectivity > 0.2188552: yes (464/190)
## : : abs_title_subjectivity <= 0.2188552:
## : : :...num_hrefs <= 12:
## : : :...average_token_length <= 4.844927: no (211/84)
## : : : average_token_length > 4.844927:
## : : : :...num_hrefs <= 7: yes (59/16)
## : : : num_hrefs > 7: no (6/1)
## : : num_hrefs > 12: [S12]
## : num_imgs > 0:
## : :...n_tokens_content <= 684:
## : :...n_tokens_content <= 121: yes (106/36)
## : : n_tokens_content > 121:
## : : :...kw_max_max > 690400:
## : : :...num_hrefs > 3: no (3098/1378)
## : : : num_hrefs <= 3:
## : : : :...num_keywords <= 9: no (519/181)
## : : : num_keywords > 9: [S13]
## : : kw_max_max <= 690400:
## : : :...n_unique_tokens > 0.5162601: no (730/318)
## : : n_unique_tokens <= 0.5162601: [S14]
## : n_tokens_content > 684:
## : :...global_sentiment_polarity <= 0.1618714:
## : :...kw_max_max <= 690400:
## : : :...n_unique_tokens > 0.515748: yes (9)
## : : : n_unique_tokens <= 0.515748: [S15]
## : : kw_max_max > 690400:
## : : :...num_hrefs > 9: [S16]
## : : num_hrefs <= 9: [S17]
## : global_sentiment_polarity > 0.1618714:
## : :...kw_max_max <= 690400: [S18]
## : kw_max_max > 690400:
## : :...abs_title_subjectivity <= 0.19375:
## : :...num_keywords > 8: [S19]
## : : num_keywords <= 8: [S20]
## : abs_title_subjectivity > 0.19375: [S21]
## num_videos > 0:
## :...num_videos > 3:
## :...kw_max_max <= 690400:
## : :...num_hrefs <= 4: no (25/11)
## : : num_hrefs > 4: [S22]
## : kw_max_max > 690400:
## : :...num_imgs > 0:
## : :...num_videos <= 11: yes (195/97)
## : : num_videos > 11:
## : : :...num_videos <= 19: yes (63/15)
## : : num_videos > 19: [S23]
## : num_imgs <= 0:
## : :...num_keywords <= 8: yes (220/72)
## : num_keywords > 8:
## : :...global_sentiment_polarity > 0.1930876:
## : :...num_keywords > 9: yes (20/2)
## : : num_keywords <= 9: [S24]
## : global_sentiment_polarity <= 0.1930876: [S25]
## num_videos <= 3:
## :...kw_max_max <= 690400:
## :...num_imgs <= 0: yes (308/115)
## : num_imgs > 0:
## : :...average_token_length <= 4.377551: yes (19/1)
## : average_token_length > 4.377551:
## : :...num_hrefs > 9: yes (42/12)
## : num_hrefs <= 9:
## : :...num_keywords <= 6: yes (45/21)
## : num_keywords > 6: [S26]
## kw_max_max > 690400:
## :...num_imgs > 0:
## :...num_hrefs <= 2: no (137/55)
## : num_hrefs > 2:
## : :...num_keywords > 6: yes (947/426)
## : num_keywords <= 6:
## : :...num_hrefs > 9: [S27]
## : num_hrefs <= 9:
## : :...num_videos > 1: no (75/36)
## : num_videos <= 1: [S28]
## num_imgs <= 0:
## :...n_tokens_title <= 9: no (343/150)
## n_tokens_title > 9:
## :...num_hrefs <= 4: yes (427/179)
## num_hrefs > 4: [S29]
##
## SubTree [S1]
##
## title_sentiment_polarity <= -0.4196429: yes (4)
## title_sentiment_polarity > -0.4196429: no (19/6)
##
## SubTree [S2]
##
## title_subjectivity > 0.4469697: yes (3)
## title_subjectivity <= 0.4469697:
## :...num_keywords <= 7: no (12/2)
## num_keywords > 7:
## :...avg_positive_polarity <= 0.3463925: no (2)
## avg_positive_polarity > 0.3463925: yes (4)
##
## SubTree [S3]
##
## title_sentiment_polarity <= -0.2666667: no (4/1)
## title_sentiment_polarity > -0.2666667: yes (14)
##
## SubTree [S4]
##
## title_sentiment_polarity > -0.06875: yes (105/35)
## title_sentiment_polarity <= -0.06875:
## :...num_hrefs <= 15: no (21/4)
## num_hrefs > 15: yes (3)
##
## SubTree [S5]
##
## abs_title_sentiment_polarity <= 0.1277778: no (4)
## abs_title_sentiment_polarity > 0.1277778: yes (2)
##
## SubTree [S6]
##
## n_tokens_title <= 11: no (44/15)
## n_tokens_title > 11:
## :...abs_title_subjectivity <= 0.19: no (3)
## abs_title_subjectivity > 0.19: yes (11/2)
##
## SubTree [S7]
##
## average_token_length > 5.098591: no (35/5)
## average_token_length <= 5.098591:
## :...title_sentiment_polarity <= -0.1185185: yes (7/1)
## title_sentiment_polarity > -0.1185185:
## :...num_hrefs <= 8: no (31/7)
## num_hrefs > 8:
## :...avg_positive_polarity <= 0.2806667: yes (8)
## avg_positive_polarity > 0.2806667:
## :...average_token_length <= 4.971723: no (9/1)
## average_token_length > 4.971723: yes (8/2)
##
## SubTree [S8]
##
## avg_positive_polarity <= 0.393142: no (33/10)
## avg_positive_polarity > 0.393142: yes (8/1)
##
## SubTree [S9]
##
## n_tokens_content > 280: no (192/64)
## n_tokens_content <= 280:
## :...num_imgs > 2: no (4/1)
## num_imgs <= 2:
## :...num_keywords > 8: yes (11)
## num_keywords <= 8:
## :...num_videos > 0: yes (4)
## num_videos <= 0:
## :...global_sentiment_polarity > 0.035639: no (6)
## global_sentiment_polarity <= 0.035639:
## :...average_token_length <= 4.830716: no (2)
## average_token_length > 4.830716: yes (7)
##
## SubTree [S10]
##
## abs_title_sentiment_polarity <= 0.05833333: no (26/5)
## abs_title_sentiment_polarity > 0.05833333:
## :...num_imgs > 2: yes (4)
## num_imgs <= 2:
## :...n_tokens_content <= 735: yes (4)
## n_tokens_content > 735: no (5)
##
## SubTree [S11]
##
## n_tokens_title <= 8: yes (8)
## n_tokens_title > 8:
## :...num_hrefs <= 5: no (6)
## num_hrefs > 5: yes (5/1)
##
## SubTree [S12]
##
## title_sentiment_polarity > 0.239899: no (28/2)
## title_sentiment_polarity <= 0.239899:
## :...num_hrefs <= 17: no (2)
## num_hrefs > 17: yes (4)
##
## SubTree [S13]
##
## n_unique_tokens <= 0.6868132: yes (33/10)
## n_unique_tokens > 0.6868132: no (4)
##
## SubTree [S14]
##
## global_sentiment_polarity > 0.1258744: yes (101/27)
## global_sentiment_polarity <= 0.1258744:
## :...num_hrefs <= 8:
## :...num_keywords <= 4: yes (2)
## : num_keywords > 4: no (26/5)
## num_hrefs > 8:
## :...n_unique_tokens <= 0.486924: yes (7)
## n_unique_tokens > 0.486924:
## :...n_unique_tokens <= 0.4950298: no (4)
## n_unique_tokens > 0.4950298: yes (9/3)
##
## SubTree [S15]
##
## n_unique_tokens <= 0.5036573: yes (86/38)
## n_unique_tokens > 0.5036573: no (8)
##
## SubTree [S16]
##
## average_token_length <= 4.67347: yes (110/50)
## average_token_length > 4.67347: no (183/60)
##
## SubTree [S17]
##
## num_keywords > 8: yes (42/12)
## num_keywords <= 8:
## :...num_hrefs <= 7: no (85/36)
## num_hrefs > 7:
## :...avg_positive_polarity <= 0.2941558: no (4)
## avg_positive_polarity > 0.2941558: yes (44/13)
##
## SubTree [S18]
##
## avg_positive_polarity > 0.421887: yes (14/1)
## avg_positive_polarity <= 0.421887:
## :...n_tokens_title <= 8: yes (16/5)
## n_tokens_title > 8: no (16/5)
##
## SubTree [S19]
##
## num_hrefs <= 8: no (2)
## num_hrefs > 8: yes (14/1)
##
## SubTree [S20]
##
## average_token_length > 4.915493: no (15/1)
## average_token_length <= 4.915493:
## :...average_token_length <= 4.544326: no (7/1)
## average_token_length > 4.544326: yes (20/4)
##
## SubTree [S21]
##
## avg_positive_polarity <= 0.4100406: yes (108/21)
## avg_positive_polarity > 0.4100406:
## :...avg_positive_polarity <= 0.418595: no (10/1)
## avg_positive_polarity > 0.418595:
## :...global_sentiment_polarity > 0.2345238: yes (13)
## global_sentiment_polarity <= 0.2345238:
## :...num_keywords <= 8: yes (23/5)
## num_keywords > 8:
## :...n_tokens_content <= 1020: no (13/2)
## n_tokens_content > 1020: yes (2)
##
## SubTree [S22]
##
## global_sentiment_polarity > 0.09930704: yes (70/10)
## global_sentiment_polarity <= 0.09930704:
## :...average_token_length <= 4.597379: no (7)
## average_token_length > 4.597379: yes (7/1)
##
## SubTree [S23]
##
## avg_positive_polarity <= 0.5407143: no (9/1)
## avg_positive_polarity > 0.5407143: yes (2)
##
## SubTree [S24]
##
## average_token_length <= 4.452631: no (5)
## average_token_length > 4.452631: yes (12/2)
##
## SubTree [S25]
##
## title_subjectivity > 0.71875: no (9)
## title_subjectivity <= 0.71875:
## :...title_sentiment_polarity <= 0.1840909: no (28/9)
## title_sentiment_polarity > 0.1840909:
## :...average_token_length <= 4.408935: no (2)
## average_token_length > 4.408935: yes (10)
##
## SubTree [S26]
##
## title_sentiment_polarity <= 0.4375: no (74/18)
## title_sentiment_polarity > 0.4375: yes (4)
##
## SubTree [S27]
##
## abs_title_sentiment_polarity <= 0.75: no (127/44)
## abs_title_sentiment_polarity > 0.75: yes (8/1)
##
## SubTree [S28]
##
## num_keywords <= 4: no (56/24)
## num_keywords > 4: yes (273/126)
##
## SubTree [S29]
##
## average_token_length > 4.990991: yes (28/7)
## average_token_length <= 4.990991:
## :...num_videos > 1:
## :...avg_positive_polarity <= 0.2595328: yes (10/1)
## : avg_positive_polarity > 0.2595328: no (132/59)
## num_videos <= 1:
## :...num_hrefs > 8: no (88/29)
## num_hrefs <= 8:
## :...average_token_length <= 4.405406: no (66/21)
## average_token_length > 4.405406:
## :...average_token_length <= 4.456057: yes (10)
## average_token_length > 4.456057:
## :...num_hrefs > 7:
## :...abs_title_sentiment_polarity <= 0.04166667: yes (12)
## : abs_title_sentiment_polarity > 0.04166667:
## : :...n_tokens_title <= 11: no (16/5)
## : n_tokens_title > 11: yes (7/1)
## num_hrefs <= 7:
## :...average_token_length <= 4.646048: no (56/19)
## average_token_length > 4.646048:
## :...title_subjectivity > 0.5166667: yes (9)
## title_subjectivity <= 0.5166667:
## :...avg_positive_polarity > 0.4453349: no (9/1)
## avg_positive_polarity <= 0.4453349:
## :...num_keywords <= 9: yes (29/7)
## num_keywords > 9:
## :...num_hrefs <= 5: yes (2)
## num_hrefs > 5: no (4)
##
##
## Evaluation on training data (35680 cases):
##
## Decision Tree
## ----------------
## Size Errors
##
## 254 13129(36.8%) <<
##
##
## (a) (b) <-classified as
## ---- ----
## 9443 7198 (a): class no
## 5931 13108 (b): class yes
##
##
## Attribute usage:
##
## 100.00% num_imgs
## 100.00% kw_max_max
## 90.75% num_hrefs
## 73.74% n_unique_tokens
## 60.95% global_sentiment_polarity
## 55.50% num_videos
## 48.60% num_keywords
## 44.11% n_tokens_content
## 32.35% n_tokens_title
## 26.93% average_token_length
## 21.13% title_sentiment_polarity
## 7.79% title_subjectivity
## 3.22% abs_title_subjectivity
## 1.91% avg_positive_polarity
## 0.82% abs_title_sentiment_polarity
## 0.63% n_non_stop_words
##
##
## Time: 1.0 secs## Step 3: Evaluation
news_pred <- predict(news_model, news_test)
(p <- table(news_pred, news_test$shares))##
## news_pred no yes
## no 954 714
## yes 895 1401(Accuracy <- sum(diag(p))/sum(p)*100)## [1] 59.40969#Random Forest
library(randomForest)
random_model = randomForest(shares ~ .,data = news_train)
summary(random_model)## Length Class Mode
## call 3 -none- call
## type 1 -none- character
## predicted 35680 factor numeric
## err.rate 1500 -none- numeric
## confusion 6 -none- numeric
## votes 71360 matrix numeric
## oob.times 35680 -none- numeric
## classes 2 -none- character
## importance 16 -none- numeric
## importanceSD 0 -none- NULL
## localImportance 0 -none- NULL
## proximity 0 -none- NULL
## ntree 1 -none- numeric
## mtry 1 -none- numeric
## forest 14 -none- list
## y 35680 factor numeric
## test 0 -none- NULL
## inbag 0 -none- NULL
## terms 3 terms callcred_pred = predict(random_model, news_test)
p = table(cred_pred, news_test$shares)
sum(diag(p))/sum(p)*100## [1] 61.12513