Setting directory
## [1] "D:/DATA/BAYU/05. OTHERS/Gold Price/Data"
Read data
## Month Gold.Price Crude.Oil.Price
## 1 01-Jun-09 $935 $69.78
## 2 01-Jul-09 $939 $64.39
## 3 01-Aug-09 $956 $71.25
## 4 01-Sep-09 $996 $69.50
## 5 01-Oct-09 $1,040 $75.85
## 6 01-Nov-09 $1,176 $78.21
Modifikasi Data
##
## Attaching package: 'lubridate'
## The following object is masked from 'package:base':
##
## date
library(stringr)
gp$Month <- dmy(gp$Month)
gp[,2]<-gsub(",","",gp[,2]) #Menghilangkan koma agar bisa di convert ke numeric
gp[,2]<-str_sub(gp$Gold.Price,3) #Menghilangkan $ agar bisa di convert ke numeric
gp[,2]<-as.numeric(gp[,2])
gp[,3]<-str_sub(gp$Crude.Oil.Price,3)#Menghilangkan $ agar bisa di convert ke numeric
gp[,3]<-as.numeric(gp[,3])
head(gp)## Month Gold.Price Crude.Oil.Price
## 1 2009-06-01 935 69.78
## 2 2009-07-01 939 64.39
## 3 2009-08-01 956 71.25
## 4 2009-09-01 996 69.50
## 5 2009-10-01 1040 75.85
## 6 2009-11-01 1176 78.21
Grafik
Model Regresi
##
## Call:
## lm(formula = Gold.Price ~ Crude.Oil.Price, data = gp)
##
## Residuals:
## Min 1Q Median 3Q Max
## -367.98 -116.95 1.32 86.25 432.17
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 971.1604 53.5534 18.134 < 2e-16 ***
## Crude.Oil.Price 4.7553 0.7019 6.775 5.03e-10 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 165.3 on 119 degrees of freedom
## Multiple R-squared: 0.2784, Adjusted R-squared: 0.2723
## F-statistic: 45.9 on 1 and 119 DF, p-value: 5.034e-10
## Registered S3 methods overwritten by 'ggplot2':
## method from
## [.quosures rlang
## c.quosures rlang
## print.quosures rlang
ggplot(gp,aes(x=gp$Gold.Price,y=gp$Crude.Oil.Price)) +
geom_point(aes(size=gp$Gold.Price)) +
geom_smooth()+ #+
#geom_abline(slope = coef(mpg.hp)[2] ,intersect(coef(mpg.hp)[1]),color="gray", lty=2)
#chart furniture
labs(
title = "Gold Price Vs Crude Oil Price",
#subtitle= "taken from mtcar data sets",
x = "Gold Price",
y= "Crude Oil Price"
)## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
Prediksi Gold Price
crude_oil_price_predict <- data.frame(Crude.Oil.Price=c(100:150))
gold_price_predict <- predict(model_gp, data.frame(Crude.Oil.Price=crude_oil_price_predict))
#gold_price_predict## Crude.Oil.Price y
## 1 100 1446.689
## 2 101 1451.444
## 3 102 1456.199
## 4 103 1460.954
## 5 104 1465.710
## 6 105 1470.465
## 7 106 1475.220
## 8 107 1479.976
## 9 108 1484.731
## 10 109 1489.486
## 11 110 1494.241
## 12 111 1498.997
## 13 112 1503.752
## 14 113 1508.507
## 15 114 1513.262
## 16 115 1518.018
## 17 116 1522.773
## 18 117 1527.528
## 19 118 1532.284
## 20 119 1537.039
## 21 120 1541.794
## 22 121 1546.549
## 23 122 1551.305
## 24 123 1556.060
## 25 124 1560.815
## 26 125 1565.571
## 27 126 1570.326
## 28 127 1575.081
## 29 128 1579.836
## 30 129 1584.592
## 31 130 1589.347
## 32 131 1594.102
## 33 132 1598.858
## 34 133 1603.613
## 35 134 1608.368
## 36 135 1613.123
## 37 136 1617.879
## 38 137 1622.634
## 39 138 1627.389
## 40 139 1632.145
## 41 140 1636.900
## 42 141 1641.655
## 43 142 1646.410
## 44 143 1651.166
## 45 144 1655.921
## 46 145 1660.676
## 47 146 1665.431
## 48 147 1670.187
## 49 148 1674.942
## 50 149 1679.697
## 51 150 1684.453
Grafik Prediksi Gold Price
ggplot(df_predict,aes(x=df_predict$y,y=df_predict$Crude.Oil.Price)) +
geom_point(aes(size=df_predict$Crude.Oil.Price)) +
geom_smooth()+ #+
#geom_abline(slope = coef(mpg.hp)[2] ,intersect(coef(mpg.hp)[1]),color="gray", lty=2)
#chart furniture
labs(
title = "Gold Price Prediction",
#subtitle= "taken from mtcar data sets",
x = "Gold Price",
y= "Crude Oil Price"
)## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
