Selected Verb

#語境詞彙(共16個)_Raw Data
shapiro.test(as.numeric(SelectedIntenVerb$AllPerMillionWord))

## 
##  Shapiro-Wilk normality test
## 
## data:  as.numeric(SelectedIntenVerb$AllPerMillionWord)
## W = 0.94505, p-value = 0.6613

#語境詞彙(共16個)_Raw Data
shapiro.test(as.numeric(SelectedNonIntenVerb$AllPerMillionWord))

## 
##  Shapiro-Wilk normality test
## 
## data:  as.numeric(SelectedNonIntenVerb$AllPerMillionWord)
## W = 0.84782, p-value = 0.09054

#語境詞彙(共16個)_Raw Data

t.test(SelectedIntenVerb$AllPerMillionWord, SelectedNonIntenVerb$AllPerMillionWord)

## 
##  Welch Two Sample t-test
## 
## data:  SelectedIntenVerb$AllPerMillionWord and SelectedNonIntenVerb$AllPerMillionWord
## t = -0.11811, df = 10.103, p-value = 0.9083
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -8.456499  7.603999
## sample estimates:
## mean of x mean of y 
##   8.86875   9.29500

#語境詞彙(共16個)_Raw Data

hist(ContextVerb$AllPerMillionWord, main = '語境詞彙的次數分配', xlab = '語境詞彙的數值', family = 'A')

#語境詞彙(共16個)_Raw Data

ggplot(ContextVerb, aes(x = AllPerMillionWord, fill = VerbType, col = VerbType))+
  geom_histogram(bins = 30)+
  facet_grid(~ VerbType)+
  labs(y = '次數')+ 
  labs(x = '語境詞彙的數值')+
  theme(axis.title.y =element_text(face="bold", hjust = 0.5,angle=90,size=14, family = "A"))+
  theme(axis.title.x =element_text(face="bold", hjust = 0.5,angle=360,size=14, family = "A"))+
  theme(axis.text.y=element_text(face="bold",size=10,color="#333333",family = "A"))+
  theme(axis.text.x=element_text(face="bold",size=10,color="#333333",family = "A"))

#語境詞彙(共16個)_Raw Data
SelectedIntenVerbLog <- log(EightIntentionVerb$AllPerMillionWord) 
SelectedIntenVerb <- cbind(EightIntentionVerb, SelectedIntenVerbLog)
SelectedNonIntenVerbLog <- log(EightUnIntentionVerb$AllPerMillionWord)
SelectedNonIntenVerb <- cbind(EightUnIntentionVerb, SelectedNonIntenVerbLog)

##語境詞彙(共16個)_取Log
shapiro.test(as.numeric(SelectedIntenVerb$SelectedIntenVerbLog))

## 
##  Shapiro-Wilk normality test
## 
## data:  as.numeric(SelectedIntenVerb$SelectedIntenVerbLog)
## W = 0.87107, p-value = 0.1544

##語境詞彙(共16個)_取Log
shapiro.test(as.numeric(SelectedNonIntenVerb$SelectedNonIntenVerbLog))

## 
##  Shapiro-Wilk normality test
## 
## data:  as.numeric(SelectedNonIntenVerb$SelectedNonIntenVerbLog)
## W = 0.94902, p-value = 0.7014

##語境詞彙(共16個)_取Log
t.test(SelectedIntenVerb$SelectedIntenVerbLog, SelectedNonIntenVerb$SelectedNonIntenVerbLog)

## 
##  Welch Two Sample t-test
## 
## data:  SelectedIntenVerb$SelectedIntenVerbLog and SelectedNonIntenVerb$SelectedNonIntenVerbLog
## t = 0.58319, df = 11.621, p-value = 0.5709
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -0.7349831  1.2695964
## sample estimates:
## mean of x mean of y 
##  2.021140  1.753834

#語境詞彙(共16個)_取Log

SelectedVerbLog <- log(ContextVerb$AllPerMillionWord)
SelectedVerbLog <- cbind(ContextVerb, SelectedVerbLog)
hist(SelectedVerbLog$SelectedVerbLog, main = '語境詞彙log值的次數分配', xlab = '語境詞彙的log值', family = 'A')

#語境詞彙(共16個)_取Log

ggplot(SelectedVerbLog, aes(x = SelectedVerbLog, fill = VerbType, col = VerbType))+
  geom_histogram(bins = 30)+
  facet_grid(~ VerbType)+
  labs(y = '次數')+ 
  labs(x = '語境詞彙的log值')+
  theme(axis.title.y =element_text(face="bold", hjust = 0.5,angle=90,size=14, family = "A"))+
  theme(axis.title.x =element_text(face="bold", hjust = 0.5,angle=360,size=14, family = "A"))+
  theme(axis.text.y=element_text(face="bold",size=10,color="#333333",family = "A"))+
  theme(axis.text.x=element_text(face="bold",size=10,color="#333333",family = "A"))