Final-Project-R-code/final-project.Rmd at main · Hyliu1222/Final-Project-R-code · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
---
title: "final project"
author: "Heye Liu"
date: "12/18/2020"
output:
  html_document: default
  pdf_document: default
  word_document: default
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
library(tidyverse)
install.packages("survey")
library(survey)
library(ggplot2)
library(tinytex)
tinytex::install_tinytex()
```

raw data
```{r}
vgsales <- read.csv("~/Downloads/vgsales.csv")
vg <- vgsales %>% filter(Rank <= 500)%>% select(Platform, Genre, Publisher, NA_Sales, EU_Sales, JP_Sales, Global_Sales)
dp <- count(vg, Platform)%>%arrange(desc(n))
ddp<- ggplot(dp, aes(x="", y=n, fill=Platform))+
geom_bar(width = 1, stat = "identity")
pie1 <- ddp + coord_polar("y", start=0)
pie1

dg <- count(vg, Genre)%>%arrange(desc(n))
ddg<- ggplot(dg, aes(x="", y=n, fill=Genre))+
geom_bar(width = 1, stat = "identity")
pie2 <- ddg + coord_polar("y", start=0)
pie2

dpu <- count(vg, Publisher)%>%arrange(desc(n))
pie(dpu$n, labels = dpu$Publisher, main = "Publisher", cex = 0.7)

```


linear regressions
```{r}
vg %>% ggplot(aes(x = JP_Sales, y = Global_Sales)) + geom_point() + geom_smooth(method = "lm", se = FALSE) + theme_minimal()
vg %>% ggplot(aes(x = NA_Sales, y = Global_Sales)) + geom_point() + geom_smooth(method = "lm", se = FALSE) + theme_minimal()
vg %>% ggplot(aes(x = EU_Sales, y = Global_Sales)) + geom_point() + geom_smooth(method = "lm", se = FALSE) + theme_minimal()
model <- lm(Global_Sales ~ JP_Sales + NA_Sales + EU_Sales, data = vg)
```

multiple regression survey sampling
```{r}
N <- 1000
n <- length(vg$Global_Sales)
fpc.srs = rep(N, n)

vg.design <- svydesign(id=~1, data = vg, fpc = fpc.srs)

model <- svyglm(Global_Sales ~ JP_Sales + NA_Sales +
               EU_Sales + Platform + Genre + Publisher, vg.design)
summary(model)
```

Stratified Random Sampling
```{r}
set.seed(124)

#platform
p1 <- ggplot(dp,aes(x=Platform,y=n,fill=Platform)) + geom_bar(stat="identity")+
 geom_text(aes(label=n),vjust=1.6) +
 theme(legend.position = "none")
p1

pp1 <- sample(dp$Platform,replace = TRUE,prob = dp$n,1000)
ps1 <- as.data.frame(pp1)

p12 <- ggplot(ps1,aes(x=pp1,y=n,fill=pp1)) + geom_bar(stat="identity")+
 theme(legend.position = "none")
p12

#genre
p2 <- ggplot(dg,aes(x=Genre,y=n,fill=Genre)) + geom_bar(stat="identity")+
 geom_text(aes(label=n),vjust=1.6) +
 theme(legend.position = "none")
p2

pp2 <- sample(dg$Genre,replace = TRUE,prob = dg$n,1000)
ps2 <- as.data.frame(pp2)

p22 <- ggplot(ps2,aes(x=pp2,y=n,fill=pp2)) + geom_bar(stat="identity")+
 theme(legend.position = "none")
p22

#publisher
p3 <- ggplot(dpu,aes(x=Publisher,y=n,fill=Publisher)) + geom_bar(stat="identity")+
 geom_text(aes(label=n),vjust=1.6) +
 theme(legend.position = "none")
p3

pp3 <- sample(dpu$Publisher,replace = TRUE,prob = dpu$n,1000)
ps3 <- as.data.frame(pp3)

p32 <- ggplot(ps3,aes(x=pp3,y=n,fill=pp3)) + geom_bar(stat="identity")+
 theme(legend.position = "none")
p32
```