Skip to content

Chris/anova #8

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
cphalpert wants to merge 8 commits into
base: master
Choose a base branch
from
Open

Chris/anova #8

Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
5e68d63
fixed anova
Dec 15, 2015
6253439
Merge branch 'master' of https://github.com/cphalpert/bikes into chri…
Dec 15, 2015
160cb9f
More anova changes
Dec 15, 2015
152bd74
Merge branch 'master' of https://github.com/cphalpert/bikes into chri…
Dec 15, 2015
03df943
Merge branch 'master' of https://github.com/cphalpert/bikes into chri…
Dec 15, 2015
2bcfa92
Gam changes
Dec 15, 2015
9fcb3c3
merge fix
Dec 15, 2015
2062b63
throwaway
Dec 15, 2015
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
29 changes: 10 additions & 19 deletions bikes_analysis.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -177,24 +177,16 @@ kruskal.test(count ~ windspeed, data=train)
summary(aov(count ~ day, data=train))

summary(aov(count ~ hour, data=train))

summary(aov(count ~ season, data=train))

summary(aov(count ~ weather, data=train))

summary(aov(count ~ day+hour, data=train))
anova.fit <- aov(count ~ day+hour+season, data=train)

summary(aov(count ~ day+hour+season, data=train))

anova.fit <- aov(log(count + 1) ~ day+hour+season+weather+year, data=train)
summary(anova.fit)

print(model.tables(anova.fit,"means"),digits=3)

par(mfrow=c(2,2))
plot(anova.fit)

#pairwise.t.test(train$count, train$day, p.adjust="bonferroni")



Expand Down Expand Up @@ -247,7 +239,7 @@ library(leaps)
library(caret)

train.model.mat <- model.matrix(formula, data=train.data)

set.seed(1)
k.cv = 10
p <- dim(train.model.mat)[2] - 1
Expand Down Expand Up @@ -284,8 +276,9 @@ summary(lm.bestfit)
par(mfrow=c(2,2))
plot(lm.bestfit)


#### Forward selection with log transformed response variable ####
###########################################
#### Log transformed response variable ####
###########################################

# Specify functional form
formulalog <- as.formula(log(count)~.)
Expand Down Expand Up @@ -344,7 +337,7 @@ library(boot)
# 0.89 adj r^2
f <- as.formula(count~(atemp+humidity+windspeed+days.from.start+holiday+day)*hour)
rf <- glm(f, data=train)
cv.glm(train, rf, K = 5)$delta[1]
cvs <- cv.glm(train, rf, K = 10)$delta[1]
summary(lm(f, data=train))

f <- as.formula(log(count)~(atemp+humidity+windspeed+days.from.start+holiday+day)*hour)
Expand All @@ -356,8 +349,8 @@ summary(lm(f, data=train))


f <- as.formula(count~season+atemp+humidity+windspeed+hour+day+days.from.start+weather)
#rf <- glm(f, data=train)
#cv.glm(train, rf, K = 7)$delta[1]
rf <- glm(f, data=train)
cv.glm(train, rf, K = 7)$delta[1]
summary(lm(f, data=train))

f <- as.formula(log(count)~(atemp+humidity+windspeed+days.from.start+holiday+day*hour))
Expand Down Expand Up @@ -404,17 +397,15 @@ lines(lower, lwd=2, col='grey', lty=2)
#######################
library(mgcv)
library(gamclass)
#form <- as.formula(log(count)~s(as.integer(hour))+s(humidity)+s(temp)+s(windspeed)+s(as.integer(days.from.start))
form <- as.formula(log(count)~hour+weather+ns(humidity)+ns(atemp)+ns(windspeed)+s(as.integer(days.from.start)))
gam.fit <- gam(form, data=train)
par(mfrow=c(2,2))
plot(gam.fit)
summary(gam.fit)


gam.cv=CVgam(form, data=train, nfold=10, seed=1)
mean((exp(gam.cv$fitted)-train$count)^2)

par(mfrow=c(2,2))
plot(gam.fit)



Expand Down