Klasifikasi Tingkat Harga Smartphone Berdasarkan Spesifikasi: Ordinal Logistik Regression
Citra Ardhia Intan Nurhapsari
2025-05-26
1 Load Dataset
dataset <- read.csv("C:/SEMESTER 4/ANALISIS MULTIVARIAT/Mobile Price Train.csv")
head(dataset)## battery_power blue clock_speed dual_sim fc four_g int_memory m_dep mobile_wt
## 1 842 0 2.2 0 1 0 7 0.6 188
## 2 1021 1 0.5 1 0 1 53 0.7 136
## 3 563 1 0.5 1 2 1 41 0.9 145
## 4 615 1 2.5 0 0 0 10 0.8 131
## 5 1821 1 1.2 0 13 1 44 0.6 141
## 6 1859 0 0.5 1 3 0 22 0.7 164
## n_cores pc px_height px_width ram sc_h sc_w talk_time three_g touch_screen
## 1 2 2 20 756 2549 9 7 19 0 0
## 2 3 6 905 1988 2631 17 3 7 1 1
## 3 5 6 1263 1716 2603 11 2 9 1 1
## 4 6 9 1216 1786 2769 16 8 11 1 0
## 5 2 14 1208 1212 1411 8 2 15 1 1
## 6 1 7 1004 1654 1067 17 1 10 1 0
## wifi price_range
## 1 1 1
## 2 0 2
## 3 0 2
## 4 0 2
## 5 0 1
## 6 0 1str(dataset)## 'data.frame': 2000 obs. of 21 variables:
## $ battery_power: int 842 1021 563 615 1821 1859 1821 1954 1445 509 ...
## $ blue : int 0 1 1 1 1 0 0 0 1 1 ...
## $ clock_speed : num 2.2 0.5 0.5 2.5 1.2 0.5 1.7 0.5 0.5 0.6 ...
## $ dual_sim : int 0 1 1 0 0 1 0 1 0 1 ...
## $ fc : int 1 0 2 0 13 3 4 0 0 2 ...
## $ four_g : int 0 1 1 0 1 0 1 0 0 1 ...
## $ int_memory : int 7 53 41 10 44 22 10 24 53 9 ...
## $ m_dep : num 0.6 0.7 0.9 0.8 0.6 0.7 0.8 0.8 0.7 0.1 ...
## $ mobile_wt : int 188 136 145 131 141 164 139 187 174 93 ...
## $ n_cores : int 2 3 5 6 2 1 8 4 7 5 ...
## $ pc : int 2 6 6 9 14 7 10 0 14 15 ...
## $ px_height : int 20 905 1263 1216 1208 1004 381 512 386 1137 ...
## $ px_width : int 756 1988 1716 1786 1212 1654 1018 1149 836 1224 ...
## $ ram : int 2549 2631 2603 2769 1411 1067 3220 700 1099 513 ...
## $ sc_h : int 9 17 11 16 8 17 13 16 17 19 ...
## $ sc_w : int 7 3 2 8 2 1 8 3 1 10 ...
## $ talk_time : int 19 7 9 11 15 10 18 5 20 12 ...
## $ three_g : int 0 1 1 1 1 1 1 1 1 1 ...
## $ touch_screen : int 0 1 1 0 1 0 0 1 0 0 ...
## $ wifi : int 1 0 0 0 0 0 1 1 0 0 ...
## $ price_range : int 1 2 2 2 1 1 3 0 0 0 ...2 Pre-processing
missing_values <- colSums(is.na(dataset))
cat("Missing values per kolom:\n")## Missing values per kolom:print(missing_values)## battery_power blue clock_speed dual_sim fc
## 0 0 0 0 0
## four_g int_memory m_dep mobile_wt n_cores
## 0 0 0 0 0
## pc px_height px_width ram sc_h
## 0 0 0 0 0
## sc_w talk_time three_g touch_screen wifi
## 0 0 0 0 0
## price_range
## 0Cek Data Duplikat
duplicate_count <- sum(duplicated(dataset))
cat("Jumlah data duplikat:", duplicate_count, "\n")## Jumlah data duplikat: 0dataset <- dataset %>%
mutate(
blue = as.factor(blue),
dual_sim = as.factor(dual_sim),
four_g = as.factor(four_g),
three_g = as.factor(three_g),
touch_screen = as.factor(touch_screen),
wifi = as.factor(wifi),
price_range = recode(as.character(price_range),
"0" = "low cost",
"1" = "medium cost",
"2" = "high cost",
"3" = "very high cost"),
price_range = ordered(price_range,
levels = c("low cost", "medium cost", "high cost", "very high cost"))
)summary(dataset)## battery_power blue clock_speed dual_sim fc four_g
## Min. : 501.0 0:1010 Min. :0.500 0: 981 Min. : 0.000 0: 957
## 1st Qu.: 851.8 1: 990 1st Qu.:0.700 1:1019 1st Qu.: 1.000 1:1043
## Median :1226.0 Median :1.500 Median : 3.000
## Mean :1238.5 Mean :1.522 Mean : 4.309
## 3rd Qu.:1615.2 3rd Qu.:2.200 3rd Qu.: 7.000
## Max. :1998.0 Max. :3.000 Max. :19.000
## int_memory m_dep mobile_wt n_cores
## Min. : 2.00 Min. :0.1000 Min. : 80.0 Min. :1.000
## 1st Qu.:16.00 1st Qu.:0.2000 1st Qu.:109.0 1st Qu.:3.000
## Median :32.00 Median :0.5000 Median :141.0 Median :4.000
## Mean :32.05 Mean :0.5018 Mean :140.2 Mean :4.521
## 3rd Qu.:48.00 3rd Qu.:0.8000 3rd Qu.:170.0 3rd Qu.:7.000
## Max. :64.00 Max. :1.0000 Max. :200.0 Max. :8.000
## pc px_height px_width ram
## Min. : 0.000 Min. : 0.0 Min. : 500.0 Min. : 256
## 1st Qu.: 5.000 1st Qu.: 282.8 1st Qu.: 874.8 1st Qu.:1208
## Median :10.000 Median : 564.0 Median :1247.0 Median :2146
## Mean : 9.916 Mean : 645.1 Mean :1251.5 Mean :2124
## 3rd Qu.:15.000 3rd Qu.: 947.2 3rd Qu.:1633.0 3rd Qu.:3064
## Max. :20.000 Max. :1960.0 Max. :1998.0 Max. :3998
## sc_h sc_w talk_time three_g touch_screen
## Min. : 5.00 Min. : 0.000 Min. : 2.00 0: 477 0: 994
## 1st Qu.: 9.00 1st Qu.: 2.000 1st Qu.: 6.00 1:1523 1:1006
## Median :12.00 Median : 5.000 Median :11.00
## Mean :12.31 Mean : 5.767 Mean :11.01
## 3rd Qu.:16.00 3rd Qu.: 9.000 3rd Qu.:16.00
## Max. :19.00 Max. :18.000 Max. :20.00
## wifi price_range
## 0: 986 low cost :500
## 1:1014 medium cost :500
## high cost :500
## very high cost:500
##
## str(dataset)## 'data.frame': 2000 obs. of 21 variables:
## $ battery_power: int 842 1021 563 615 1821 1859 1821 1954 1445 509 ...
## $ blue : Factor w/ 2 levels "0","1": 1 2 2 2 2 1 1 1 2 2 ...
## $ clock_speed : num 2.2 0.5 0.5 2.5 1.2 0.5 1.7 0.5 0.5 0.6 ...
## $ dual_sim : Factor w/ 2 levels "0","1": 1 2 2 1 1 2 1 2 1 2 ...
## $ fc : int 1 0 2 0 13 3 4 0 0 2 ...
## $ four_g : Factor w/ 2 levels "0","1": 1 2 2 1 2 1 2 1 1 2 ...
## $ int_memory : int 7 53 41 10 44 22 10 24 53 9 ...
## $ m_dep : num 0.6 0.7 0.9 0.8 0.6 0.7 0.8 0.8 0.7 0.1 ...
## $ mobile_wt : int 188 136 145 131 141 164 139 187 174 93 ...
## $ n_cores : int 2 3 5 6 2 1 8 4 7 5 ...
## $ pc : int 2 6 6 9 14 7 10 0 14 15 ...
## $ px_height : int 20 905 1263 1216 1208 1004 381 512 386 1137 ...
## $ px_width : int 756 1988 1716 1786 1212 1654 1018 1149 836 1224 ...
## $ ram : int 2549 2631 2603 2769 1411 1067 3220 700 1099 513 ...
## $ sc_h : int 9 17 11 16 8 17 13 16 17 19 ...
## $ sc_w : int 7 3 2 8 2 1 8 3 1 10 ...
## $ talk_time : int 19 7 9 11 15 10 18 5 20 12 ...
## $ three_g : Factor w/ 2 levels "0","1": 1 2 2 2 2 2 2 2 2 2 ...
## $ touch_screen : Factor w/ 2 levels "0","1": 1 2 2 1 2 1 1 2 1 1 ...
## $ wifi : Factor w/ 2 levels "0","1": 2 1 1 1 1 1 2 2 1 1 ...
## $ price_range : Ord.factor w/ 4 levels "low cost"<"medium cost"<..: 2 3 3 3 2 2 4 1 1 1 ...3 ANALISIS STATISTIK DESKRIPTIF
statistik deskriptif untuk variabel numerik
describe(dataset %>% select_if(is.numeric))## vars n mean sd median trimmed mad min max
## battery_power 1 2000 1238.52 439.42 1226.0 1236.25 566.35 501.0 1998
## clock_speed 2 2000 1.52 0.82 1.5 1.48 1.19 0.5 3
## fc 3 2000 4.31 4.34 3.0 3.69 4.45 0.0 19
## int_memory 4 2000 32.05 18.15 32.0 31.88 23.72 2.0 64
## m_dep 5 2000 0.50 0.29 0.5 0.50 0.44 0.1 1
## mobile_wt 6 2000 140.25 35.40 141.0 140.22 45.96 80.0 200
## n_cores 7 2000 4.52 2.29 4.0 4.53 2.97 1.0 8
## pc 8 2000 9.92 6.06 10.0 9.89 7.41 0.0 20
## px_height 9 2000 645.11 443.78 564.0 606.95 471.47 0.0 1960
## px_width 10 2000 1251.52 432.20 1247.0 1250.53 557.46 500.0 1998
## ram 11 2000 2124.21 1084.73 2146.5 2122.93 1382.52 256.0 3998
## sc_h 12 2000 12.31 4.21 12.0 12.37 5.93 5.0 19
## sc_w 13 2000 5.77 4.36 5.0 5.40 4.45 0.0 18
## talk_time 14 2000 11.01 5.46 11.0 11.01 7.41 2.0 20
## range skew kurtosis se
## battery_power 1497.0 0.03 -1.23 9.83
## clock_speed 2.5 0.18 -1.32 0.02
## fc 19.0 1.02 0.27 0.10
## int_memory 62.0 0.06 -1.22 0.41
## m_dep 0.9 0.09 -1.28 0.01
## mobile_wt 120.0 0.01 -1.21 0.79
## n_cores 7.0 0.00 -1.23 0.05
## pc 20.0 0.02 -1.17 0.14
## px_height 1960.0 0.67 -0.32 9.92
## px_width 1498.0 0.01 -1.19 9.66
## ram 3742.0 0.01 -1.19 24.26
## sc_h 14.0 -0.10 -1.19 0.09
## sc_w 18.0 0.63 -0.39 0.10
## talk_time 18.0 0.01 -1.22 0.12dataset %>%
select_if(is.numeric) %>%
gather(key = "Variabel", value = "Nilai") %>%
ggplot(aes(x = Nilai)) +
facet_wrap(~ Variabel, scales = "free", ncol = 3) +
geom_histogram(bins = 10, fill = "steelblue", color = "black") +
theme_minimal()
> Boxplot untuk melihat distribusi fitur berdasarkan
harga_kategori
numerik_vars <- names(dataset)[sapply(dataset, is.numeric)]
for (var in numerik_vars) {
p <- ggplot(dataset, aes(x = price_range, y = dataset[[var]], fill = price_range)) +
geom_boxplot() +
labs(title = paste("Distribusi", var, "berdasarkan Harga")) +
theme_minimal() +
theme(legend.position = "none")
print(p)
}## Warning: Use of `dataset[[var]]` is discouraged.
## ℹ Use `.data[[var]]` instead.
## Warning: Use of `dataset[[var]]` is discouraged.
## ℹ Use `.data[[var]]` instead.
## Warning: Use of `dataset[[var]]` is discouraged.
## ℹ Use `.data[[var]]` instead.
## Warning: Use of `dataset[[var]]` is discouraged.
## ℹ Use `.data[[var]]` instead.
## Warning: Use of `dataset[[var]]` is discouraged.
## ℹ Use `.data[[var]]` instead.
## Warning: Use of `dataset[[var]]` is discouraged.
## ℹ Use `.data[[var]]` instead.
## Warning: Use of `dataset[[var]]` is discouraged.
## ℹ Use `.data[[var]]` instead.
## Warning: Use of `dataset[[var]]` is discouraged.
## ℹ Use `.data[[var]]` instead.
## Warning: Use of `dataset[[var]]` is discouraged.
## ℹ Use `.data[[var]]` instead.
## Warning: Use of `dataset[[var]]` is discouraged.
## ℹ Use `.data[[var]]` instead.
## Warning: Use of `dataset[[var]]` is discouraged.
## ℹ Use `.data[[var]]` instead.
## Warning: Use of `dataset[[var]]` is discouraged.
## ℹ Use `.data[[var]]` instead.
## Warning: Use of `dataset[[var]]` is discouraged.
## ℹ Use `.data[[var]]` instead.
## Warning: Use of `dataset[[var]]` is discouraged.
## ℹ Use `.data[[var]]` instead.
Korelasi antar variabel numerik
numeric_data <- dataset %>% select_if(is.numeric)
cor_matrix <- cor(numeric_data, use = "complete.obs")
ggcorr(numeric_data,label = TRUE,label_size = 3, hjust = 0.95, layout.exp = 3, name = "Correlation") +
ggtitle("Matriks Korelasi Tiap Variabel") +
theme(
plot.title = element_text(size = 16, face = "bold", hjust = 0.5),
legend.title = element_text(size = 12),
legend.text = element_text(size = 10)
)
Statistik Deskriptif berdasarkan Kategori Harga
ggplot(dataset, aes(x = price_range, fill = price_range)) +
geom_bar() +
scale_fill_brewer(palette = "Set2") +
labs(
title = "Distribusi Variabel Price Range",
x = "Price Range",
y = "Jumlah Data",
fill = "Price Range"
) +
theme_minimal(base_size = 14) +
theme(legend.position = "right")
4 Pengelompokkan Harga
dataset %>%
group_by(price_range) %>%
summarise(across(where(is.numeric),
list(mean = ~mean(.x, na.rm = TRUE),
sd = ~sd(.x, na.rm = TRUE)),
.names = "{.col}_{.fn}"))## # A tibble: 4 × 29
## price_range battery_power_mean battery_power_sd clock_speed_mean
## <ord> <dbl> <dbl> <dbl>
## 1 low cost 1117. 411. 1.55
## 2 medium cost 1229. 439. 1.49
## 3 high cost 1228. 453. 1.53
## 4 very high cost 1380. 415. 1.52
## # ℹ 25 more variables: clock_speed_sd <dbl>, fc_mean <dbl>, fc_sd <dbl>,
## # int_memory_mean <dbl>, int_memory_sd <dbl>, m_dep_mean <dbl>,
## # m_dep_sd <dbl>, mobile_wt_mean <dbl>, mobile_wt_sd <dbl>,
## # n_cores_mean <dbl>, n_cores_sd <dbl>, pc_mean <dbl>, pc_sd <dbl>,
## # px_height_mean <dbl>, px_height_sd <dbl>, px_width_mean <dbl>,
## # px_width_sd <dbl>, ram_mean <dbl>, ram_sd <dbl>, sc_h_mean <dbl>,
## # sc_h_sd <dbl>, sc_w_mean <dbl>, sc_w_sd <dbl>, talk_time_mean <dbl>, …head(dataset)## battery_power blue clock_speed dual_sim fc four_g int_memory m_dep mobile_wt
## 1 842 0 2.2 0 1 0 7 0.6 188
## 2 1021 1 0.5 1 0 1 53 0.7 136
## 3 563 1 0.5 1 2 1 41 0.9 145
## 4 615 1 2.5 0 0 0 10 0.8 131
## 5 1821 1 1.2 0 13 1 44 0.6 141
## 6 1859 0 0.5 1 3 0 22 0.7 164
## n_cores pc px_height px_width ram sc_h sc_w talk_time three_g touch_screen
## 1 2 2 20 756 2549 9 7 19 0 0
## 2 3 6 905 1988 2631 17 3 7 1 1
## 3 5 6 1263 1716 2603 11 2 9 1 1
## 4 6 9 1216 1786 2769 16 8 11 1 0
## 5 2 14 1208 1212 1411 8 2 15 1 1
## 6 1 7 1004 1654 1067 17 1 10 1 0
## wifi price_range
## 1 1 medium cost
## 2 0 high cost
## 3 0 high cost
## 4 0 high cost
## 5 0 medium cost
## 6 0 medium costmemastikan price_range adalah factor ordinal
dataset$price_range <- factor(dataset$price_range, ordered = TRUE)standarisasi semua kolom numerik
num_vars <- dataset %>% select_if(is.numeric)
num_scaled <- scale(num_vars)5 Train-Test Split
set.seed(123)
data_split <- sample(1:nrow(dataset), 0.7 * nrow(dataset))
train_data <- dataset[data_split, ]
test_data <- dataset[-data_split, ]Memastikan price_range sebagai ordered factor
train_data$price_range <- factor(train_data$price_range, ordered = TRUE)
test_data$price_range <- factor(test_data$price_range, ordered = TRUE)6 uji multikolniearitas (OLR)
model_step1 <- polr(price_range ~ battery_power + ram + mobile_wt + battery_power + sc_h + talk_time, data = train_data, Hess=TRUE)
summary(model_step1)## Call:
## polr(formula = price_range ~ battery_power + ram + mobile_wt +
## battery_power + sc_h + talk_time, data = train_data, Hess = TRUE)
##
## Coefficients:
## Value Std. Error t value
## battery_power 0.004176 0.0001629 25.635
## ram 0.006658 0.0001610 41.356
## mobile_wt -0.006374 0.0019216 -3.317
## sc_h 0.035049 0.0170245 2.059
## talk_time 0.011993 0.0139451 0.860
##
## Intercepts:
## Value Std. Error t value
## low cost|medium cost 12.7786 0.0015 8685.2012
## medium cost|high cost 18.8281 0.2479 75.9548
## high cost|very high cost 25.3718 0.3727 68.0847
##
## Residual Deviance: 1073.895
## AIC: 1089.895null_model <- polr(price_range ~ 1, data=train_data, Hess=TRUE)
full_model <- polr(price_range ~ battery_power + ram + mobile_wt + sc_h + talk_time, data=train_data, Hess=TRUE)
library(MASS)
step_model <- stepAIC(null_model, scope=list(lower=null_model, upper=full_model), direction="both")## Start: AIC=3886.68
## price_range ~ 1
##
## Df AIC
## + ram 1 1529.6
## + battery_power 1 3841.7
## + talk_time 1 3886.4
## <none> 3886.7
## + sc_h 1 3887.8
## + mobile_wt 1 3888.7
##
## Step: AIC=1529.62
## price_range ~ ram
##
## Df AIC
## + battery_power 1 1096.5
## + mobile_wt 1 1527.2
## + sc_h 1 1528.6
## + talk_time 1 1529.0
## <none> 1529.6
## - ram 1 3886.7
##
## Step: AIC=1096.51
## price_range ~ ram + battery_power
##
## Df AIC
## + mobile_wt 1 1090.2
## + sc_h 1 1094.9
## <none> 1096.5
## + talk_time 1 1097.9
## - battery_power 1 1529.6
## - ram 1 3841.7
##
## Step: AIC=1090.16
## price_range ~ ram + battery_power + mobile_wt
##
## Df AIC
## + sc_h 1 1088.6
## <none> 1090.2
## + talk_time 1 1091.5
## - mobile_wt 1 1096.5
## - battery_power 1 1527.2
## - ram 1 3843.7
##
## Step: AIC=1088.59
## price_range ~ ram + battery_power + mobile_wt + sc_h
##
## Df AIC
## <none> 1088.6
## + talk_time 1 1089.9
## - sc_h 1 1090.2
## - mobile_wt 1 1094.9
## - battery_power 1 1526.2
## - ram 1 3844.8summary(step_model)## Call:
## polr(formula = price_range ~ ram + battery_power + mobile_wt +
## sc_h, data = train_data, Hess = TRUE)
##
## Coefficients:
## Value Std. Error t value
## ram 0.006665 0.0001579 42.225
## battery_power 0.004181 0.0001589 26.320
## mobile_wt -0.006350 0.0018925 -3.356
## sc_h 0.034799 0.0169650 2.051
##
## Intercepts:
## Value Std. Error t value
## low cost|medium cost 12.6650 0.0016 8137.3144
## medium cost|high cost 18.7188 0.2470 75.7998
## high cost|very high cost 25.2705 0.3683 68.6083
##
## Residual Deviance: 1074.592
## AIC: 1088.5927 Asumsi Propotional Odds
brant_result <- brant(step_model)## --------------------------------------------
## Test for X2 df probability
## --------------------------------------------
## Omnibus 17.35 8 0.03
## ram 2.27 2 0.32
## battery_power 3.36 2 0.19
## mobile_wt 7.06 2 0.03
## sc_h 4.57 2 0.1
## --------------------------------------------
##
## H0: Parallel Regression Assumption holdsprint(brant_result)## X2 df probability
## Omnibus 17.346104 8 0.02670026
## ram 2.270623 2 0.32132196
## battery_power 3.362508 2 0.18614039
## mobile_wt 7.056251 2 0.02935990
## sc_h 4.570134 2 0.10176723pred <- predict(step_model, newdata = test_data, type = "class")actual <- factor(test_data$price_range,
levels = c("low cost", "medium cost", "high cost", "very high cost"),
ordered = TRUE)
pred_label <- factor(pred,
levels = c("low cost", "medium cost", "high cost", "very high cost"),
ordered = TRUE)8 Evaluasi Model
conf_matrix <- confusionMatrix(pred_label, actual)
print(conf_matrix)## Confusion Matrix and Statistics
##
## Reference
## Prediction low cost medium cost high cost very high cost
## low cost 145 18 0 0
## medium cost 10 120 13 0
## high cost 0 21 110 30
## very high cost 0 0 12 121
##
## Overall Statistics
##
## Accuracy : 0.8267
## 95% CI : (0.794, 0.8561)
## No Information Rate : 0.265
## P-Value [Acc > NIR] : < 2.2e-16
##
## Kappa : 0.769
##
## Mcnemar's Test P-Value : NA
##
## Statistics by Class:
##
## Class: low cost Class: medium cost Class: high cost
## Sensitivity 0.9355 0.7547 0.8148
## Specificity 0.9596 0.9478 0.8903
## Pos Pred Value 0.8896 0.8392 0.6832
## Neg Pred Value 0.9771 0.9147 0.9431
## Prevalence 0.2583 0.2650 0.2250
## Detection Rate 0.2417 0.2000 0.1833
## Detection Prevalence 0.2717 0.2383 0.2683
## Balanced Accuracy 0.9475 0.8513 0.8526
## Class: very high cost
## Sensitivity 0.8013
## Specificity 0.9733
## Pos Pred Value 0.9098
## Neg Pred Value 0.9358
## Prevalence 0.2517
## Detection Rate 0.2017
## Detection Prevalence 0.2217
## Balanced Accuracy 0.88739 Cohen’s Kappa
ratings <- data.frame(rater1 = pred_label, rater2 = actual)
kappa_val <- kappa2(ratings, weight = "unweighted")
print(kappa_val)## Cohen's Kappa for 2 Raters (Weights: unweighted)
##
## Subjects = 600
## Raters = 2
## Kappa = 0.769
##
## z = 32.7
## p-value = 0#MAE
actual_num <- as.numeric(actual)
pred_num <- as.numeric(pred_label)
mae <- mean(abs(actual_num - pred_num))
cat("Mean Absolute Error (MAE):", mae, "\n")## Mean Absolute Error (MAE): 0.1733333Akurasi train
train_pred <- predict(step_model, train_data, type = "class")
conf_matrix_train <- table(train_data$price_range, train_pred)
accuracy_train <- sum(diag(conf_matrix_train)) / sum(conf_matrix_train)
print(paste("Akurasi data train:", round(accuracy_train, 4)))## [1] "Akurasi data train: 0.8229"Akurasi test
test_pred <- predict(step_model, test_data, type = "class")
conf_matrix_test <- table(test_data$price_range, test_pred)
accuracy_test <- sum(diag(conf_matrix_test)) / sum(conf_matrix_test)
print(paste("Akurasi data test:", round(accuracy_test, 4)))## [1] "Akurasi data test: 0.8267"