1. Intro

1.1 Greetings

Helo, Welcome to My Rmd In this Rmd I would explore about Length and Weight Relationship

1.2 Brief

I want to know Length and Weight Relationship Bream Spesies with Regression Linear Model

1.3 Problem Background

It is important to find out the relationship of length and weight, in order to know which factors are the most influential, between internal and external factors

1.4 Library

library(tidyverse)
library(ggthemes)
library(GGally)
library(dplyr)
library(MLmetrics)
library(lmtest)
library(car)

1.5 Dataset

Dataset is from Kaggel.com “fish_market”

fish <- read.csv("Fish.csv")

2. Data Preparation

Inspect dataset

head(fish)
glimpse(fish)
## Rows: 159
## Columns: 7
## $ Species <chr> "Bream", "Bream", "Bream", "Bream", "Bream", "Bream", "Bream",…
## $ Weight  <dbl> 242, 290, 340, 363, 430, 450, 500, 390, 450, 500, 475, 500, 50…
## $ Length1 <dbl> 23.2, 24.0, 23.9, 26.3, 26.5, 26.8, 26.8, 27.6, 27.6, 28.5, 28…
## $ Length2 <dbl> 25.4, 26.3, 26.5, 29.0, 29.0, 29.7, 29.7, 30.0, 30.0, 30.7, 31…
## $ Length3 <dbl> 30.0, 31.2, 31.1, 33.5, 34.0, 34.7, 34.5, 35.0, 35.1, 36.2, 36…
## $ Height  <dbl> 11.5200, 12.4800, 12.3778, 12.7300, 12.4440, 13.6024, 14.1795,…
## $ Width   <dbl> 4.0200, 4.3056, 4.6961, 4.4555, 5.1340, 4.9274, 5.2785, 4.6900…

Select Colomn

Karena mencari hubungan panjang berat, maka saya hanya memerlukan data berat dan panjang saja

fish <- fish %>% 
  select(Species, Weight, Length1, Length2, Length3)
head(fish)

Change Colom Names

Di Ilmu Perikanan, pengukuran panjang terbagi menjadi 3, Standard Length, Fork Length dan Total Length. Saya ubah terlebih dahulu sesuai dengan istilah yg sering di gunakan

fish <- fish %>% 
  rename(Standard_Length = Length1,
         Fork_Length = Length2,
         Total_Length = Length3)

Check Missing Value

anyNA(fish)
## [1] FALSE

Check Correlation

ggcorr(fish, label = TRUE, label_size = 4, hjust = 0.7,)
## Warning in ggcorr(fish, label = TRUE, label_size = 4, hjust = 0.7, ): data in
## column(s) 'Species' are not numeric and were ignored

Divide Dataset by Species

Check Spesies

unique(fish$Species)
## [1] "Bream"     "Roach"     "Whitefish" "Parkki"    "Perch"     "Pike"     
## [7] "Smelt"

Split Dataset

Bream <- fish %>% 
  filter(Species == "Bream")
Perch <- fish %>% 
  filter(Species == "Perch")

Check Outlier

boxplot((Bream$Total_Length), (Perch$Total_Length))

Select colomn Weight and Length3

Bream <- Bream %>% 
  select(Weight,Total_Length)

3. Modeling

Cross Validation

Bream

set.seed(123)
RNGkind()
## [1] "Mersenne-Twister" "Inversion"        "Rejection"
row_data <- nrow(Bream)
index <- sample(row_data, row_data*0.8)

Bream_train <- Bream[ index, ]
Bream_test <- Bream[ -index, ]
model_bream <- lm(Weight ~ Total_Length, Bream_train)
model_bream
## 
## Call:
## lm(formula = Weight ~ Total_Length, data = Bream_train)
## 
## Coefficients:
##  (Intercept)  Total_Length  
##     -1235.08         48.23
summary(model_bream)
## 
## Call:
## lm(formula = Weight ~ Total_Length, data = Bream_train)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -224.066  -27.709   -9.479   32.724  180.291 
## 
## Coefficients:
##               Estimate Std. Error t value Pr(>|t|)    
## (Intercept)  -1235.083    134.103   -9.21 1.14e-09 ***
## Total_Length    48.235      3.463   13.93 1.44e-13 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 73.84 on 26 degrees of freedom
## Multiple R-squared:  0.8818, Adjusted R-squared:  0.8773 
## F-statistic:   194 on 1 and 26 DF,  p-value: 1.444e-13
plot(Bream$Total_Length, Bream$Weight) 
abline(model_bream$coefficients[1],model_bream$coefficients[2])

hist(model_bream$residuals)

Prediction

bream_pred <- predict(model_bream, Bream_test)
MAE(bream_pred, Bream$Weight )
## [1] 223.0489
MAPE(bream_pred, Bream$Weight)
## [1] 0.3845915
MSE(bream_pred, Bream$Weight)
## [1] 78668.78
RMSE(bream_pred, Bream$Weight)
## [1] 280.4795

Normalitas

hist(model_bream$residuals)

shapiro.test(model_bream$residuals)
## 
##  Shapiro-Wilk normality test
## 
## data:  model_bream$residuals
## W = 0.93088, p-value = 0.06489

Heteroscedasticity

bptest(model_bream)
## 
##  studentized Breusch-Pagan test
## 
## data:  model_bream
## BP = 0.1262, df = 1, p-value = 0.7224
data.frame(prediction = model_bream$fitted.values,
           residual = model_bream$residuals) %>% 
  ggplot(aes(prediction, residual)) +
  geom_hline(yintercept = 0, color = "red2") +
  geom_point( color = "skyblue4") +
  theme_minimal()

Multicolinearity

Tidak dapat di ukur, karena prediktor hanya 1

4. Conclusion