Tugas2
Setiawan Djody, Randi Farhan Al-Khair, Syafweldy Sihombing, Michael Situmorang,Alfi Fakhira
2024-01-18
install.packages("tidyverse")## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.3'
## (as 'lib' is unspecified)library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.4.4 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ tidyr 1.3.0
## ✔ purrr 1.0.2## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errorsinstall.packages("dplyr")## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.3'
## (as 'lib' is unspecified)library(dplyr)
install.packages("caret")## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.3'
## (as 'lib' is unspecified)library(caret)## Loading required package: lattice
##
## Attaching package: 'caret'
##
## The following object is masked from 'package:purrr':
##
## liftinstall.packages("readxl")## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.3'
## (as 'lib' is unspecified)library(readxl)
install.packages("corrplot")## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.3'
## (as 'lib' is unspecified)library(corrplot)## corrplot 0.92 loadedinstall.packages("e1071")## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.3'
## (as 'lib' is unspecified)library(e1071)
install.packages("glmnet")## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.3'
## (as 'lib' is unspecified)library(glmnet)## Loading required package: Matrix
##
## Attaching package: 'Matrix'
##
## The following objects are masked from 'package:tidyr':
##
## expand, pack, unpack
##
## Loaded glmnet 4.1-8install.packages("zoo")## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.3'
## (as 'lib' is unspecified)library(zoo)##
## Attaching package: 'zoo'
##
## The following objects are masked from 'package:base':
##
## as.Date, as.Date.numeric1. OBSTAIN
data <- read_excel("Inflasi_Kota_Medan 1.xlsx")
head(data)## # A tibble: 6 × 3
## Bulan Tahun Inflasi
## <chr> <dbl> <chr>
## 1 Januari 2010 0,41
## 2 Februari 2010 0,49
## 3 Maret 2010 -0,18
## 4 April 2010 -0,8
## 5 Mei 2010 1,37
## 6 Juni 2010 -1,7tail(data)## # A tibble: 6 × 3
## Bulan Tahun Inflasi
## <chr> <dbl> <chr>
## 1 Juli 2021 0,28
## 2 Agustus 2021 -0,27
## 3 September 2021 -0,31
## 4 Oktober 2021 0,44
## 5 November 2021 0,3
## 6 Desember 2021 0,952. SCRUB
#Melihat struktur data
glimpse(data)## Rows: 144
## Columns: 3
## $ Bulan <chr> "Januari", "Februari", "Maret", "April", "Mei", "Juni", "Juli"…
## $ Tahun <dbl> 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 20…
## $ Inflasi <chr> "0,41", "0,49", "-0,18", "-0,8", "1,37", "-1,7", "2,1", "1,22"…#Merubah isi data agar bisa di convert ke numeric
data$Inflasi <- gsub(",", ".", data$Inflasi)#Merubah Tipe data
data$Inflasi <- as.numeric(data$Inflasi)
glimpse(data)## Rows: 144
## Columns: 3
## $ Bulan <chr> "Januari", "Februari", "Maret", "April", "Mei", "Juni", "Juli"…
## $ Tahun <dbl> 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 20…
## $ Inflasi <dbl> 0.41, 0.49, -0.18, -0.80, 1.37, -1.70, 2.10, 1.22, 0.45, -0.70…summary(data)## Bulan Tahun Inflasi
## Length:144 Min. :2010 Min. :-2.1000
## Class :character 1st Qu.:2013 1st Qu.:-0.3650
## Mode :character Median :2016 Median : 0.3000
## Mean :2016 Mean : 0.3431
## 3rd Qu.:2018 3rd Qu.: 0.9425
## Max. :2021 Max. : 3.9600#Mencari data Kosong
colSums(is.na(data))## Bulan Tahun Inflasi
## 0 0 03. Explore Data
dataCopy <- data
dataCopy <- dataCopy %>% mutate(Bulan = case_when(Bulan == "Januari" ~ 1, Bulan == "Februari" ~ 2, Bulan == "Maret" ~ 3, Bulan == "April" ~ 4, Bulan == "Mei" ~ 5, Bulan == "Juni" ~ 6, Bulan == "Juli" ~ 7, Bulan == "Agustus" ~ 8, Bulan == "September" ~ 9, Bulan == "Oktober" ~ 10, Bulan == "November" ~ 11, Bulan == "Desember" ~ 12))
str ( dataCopy$Bulan)## num [1:144] 1 2 3 4 5 6 7 8 9 10 ...dataCopy2 <- dataCopydataCopy$Bulan <- as.character(dataCopy$Bulan)
glimpse(dataCopy$Bulan)## chr [1:144] "1" "2" "3" "4" "5" "6" "7" "8" "9" "10" "11" "12" "1" "2" "3" ...dataCopy$Per_Bulan <- paste(dataCopy$Tahun, dataCopy$Bulan, sep = "-")
glimpse(dataCopy)## Rows: 144
## Columns: 4
## $ Bulan <chr> "1", "2", "3", "4", "5", "6", "7", "8", "9", "10", "11", "12…
## $ Tahun <dbl> 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, …
## $ Inflasi <dbl> 0.41, 0.49, -0.18, -0.80, 1.37, -1.70, 2.10, 1.22, 0.45, -0.…
## $ Per_Bulan <chr> "2010-1", "2010-2", "2010-3", "2010-4", "2010-5", "2010-6", …dataCopy$Per_Bulan <- as.Date(as.yearmon(dataCopy$Per_Bulan, "%Y-%m"))
print(dataCopy$Per_Bulan)## [1] "2010-01-01" "2010-02-01" "2010-03-01" "2010-04-01" "2010-05-01"
## [6] "2010-06-01" "2010-07-01" "2010-08-01" "2010-09-01" "2010-10-01"
## [11] "2010-11-01" "2010-12-01" "2011-01-01" "2011-02-01" "2011-03-01"
## [16] "2011-04-01" "2011-05-01" "2011-06-01" "2011-07-01" "2011-08-01"
## [21] "2011-09-01" "2011-10-01" "2011-11-01" "2011-12-01" "2012-01-01"
## [26] "2012-02-01" "2012-03-01" "2012-04-01" "2012-05-01" "2012-06-01"
## [31] "2012-07-01" "2012-08-01" "2012-09-01" "2012-10-01" "2012-11-01"
## [36] "2012-12-01" "2013-01-01" "2013-02-01" "2013-03-01" "2013-04-01"
## [41] "2013-05-01" "2013-06-01" "2013-07-01" "2013-08-01" "2013-09-01"
## [46] "2013-10-01" "2013-11-01" "2013-12-01" "2014-01-01" "2014-02-01"
## [51] "2014-03-01" "2014-04-01" "2014-05-01" "2014-06-01" "2014-07-01"
## [56] "2014-08-01" "2014-09-01" "2014-10-01" "2014-11-01" "2014-12-01"
## [61] "2015-01-01" "2015-02-01" "2015-03-01" "2015-04-01" "2015-05-01"
## [66] "2015-06-01" "2015-07-01" "2015-08-01" "2015-09-01" "2015-10-01"
## [71] "2015-11-01" "2015-12-01" "2016-01-01" "2016-02-01" "2016-03-01"
## [76] "2016-04-01" "2016-05-01" "2016-06-01" "2016-07-01" "2016-08-01"
## [81] "2016-09-01" "2016-10-01" "2016-11-01" "2016-12-01" "2017-01-01"
## [86] "2017-02-01" "2017-03-01" "2017-04-01" "2017-05-01" "2017-06-01"
## [91] "2017-07-01" "2017-08-01" "2017-09-01" "2017-10-01" "2017-11-01"
## [96] "2017-12-01" "2018-01-01" "2018-02-01" "2018-03-01" "2018-04-01"
## [101] "2018-05-01" "2018-06-01" "2018-07-01" "2018-08-01" "2018-09-01"
## [106] "2018-10-01" "2018-11-01" "2018-12-01" "2019-01-01" "2019-02-01"
## [111] "2019-03-01" "2019-04-01" "2019-05-01" "2019-06-01" "2019-07-01"
## [116] "2019-08-01" "2019-09-01" "2019-10-01" "2019-11-01" "2019-12-01"
## [121] "2020-01-01" "2020-02-01" "2020-03-01" "2020-04-01" "2020-05-01"
## [126] "2020-06-01" "2020-07-01" "2020-08-01" "2020-09-01" "2020-10-01"
## [131] "2020-11-01" "2020-12-01" "2021-01-01" "2021-02-01" "2021-03-01"
## [136] "2021-04-01" "2021-05-01" "2021-06-01" "2021-07-01" "2021-08-01"
## [141] "2021-09-01" "2021-10-01" "2021-11-01" "2021-12-01"dataCopy <- select(dataCopy, -1)
glimpse(dataCopy)## Rows: 144
## Columns: 3
## $ Tahun <dbl> 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, 2010, …
## $ Inflasi <dbl> 0.41, 0.49, -0.18, -0.80, 1.37, -1.70, 2.10, 1.22, 0.45, -0.…
## $ Per_Bulan <date> 2010-01-01, 2010-02-01, 2010-03-01, 2010-04-01, 2010-05-01,…#Visualisasi Inflasi pertahun
ggplot(dataCopy, aes(x = Per_Bulan ,y = Inflasi)) +
geom_line(color = "darkcyan") +
labs(title = "Grafik Inflasi Kota Medan PerTahun",
x = "Tahun",
y = "Inflasi")
#Visualisasi grafik batang Inflasi perbulan
ggplot(dataCopy, aes(x = Per_Bulan ,y = Inflasi)) +
geom_bar(stat = "identity", fill = "darkmagenta") +
labs(title = "Grafik Inflasi Kota Medan PerTahun",
x = "Tahun",
y = "Inflasi")
dataset_cor <- cor(dataCopy2[,1:3])
corrplot(dataset_cor, method = "color", addCoef.col = "red")
dataset_cor## Bulan Tahun Inflasi
## Bulan 1.00000000 0.00000000 0.09970172
## Tahun 0.00000000 1.00000000 -0.08428282
## Inflasi 0.09970172 -0.08428282 1.000000004. Model
#Partisi Dataset dan membangun model prediksi
#Mempartisi data
set.seed(123)
train_index <- sample(1:nrow(dataCopy2), 0.8 * nrow(dataCopy2))
train_data <- dataCopy2[train_index, ]
test_data <- dataCopy2[-train_index, ]
# Model GLM
model_glm <- glm(Inflasi ~ Bulan + Tahun , data = train_data)
glm_predictions <- predict(model_glm, newdata = test_data)
# Model SVR
model_svr <- svm(Inflasi ~ Bulan + Tahun , data = train_data)
svr_predictions <- predict(model_svr, newdata = test_data)Membandingkan antara hasil prediksi dan data asli untuk GLM
result_data_glm <- data.frame( actual= test_data$Inflasi, Predictions = glm_predictions)
ggplot(data = result_data_glm, aes(x = 1:length(test_data$Inflasi))) +
geom_line(aes(y = test_data$Inflasi, color = "Actual"), size = 1) +
geom_line(aes(y = glm_predictions, color = "GLM Prediction"), size = 1) +
labs(x = "Observasi", y = "Inflasi") +
scale_color_manual(values = c("Actual" = "blue", "GLM Prediction" = "green")) +
ggtitle("Perbandingan GLM vs Aktual") +
scale_y_continuous(labels = scales::comma) +
theme_minimal()## Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
## ℹ Please use `linewidth` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
# Membandingkan antara hasil prediksi dan data asli untuk SVR
result_data_svr <- data.frame( actual= test_data$Inflasi, Predictions = svr_predictions)
ggplot(data = result_data_svr, aes(x = 1:length(test_data$Inflasi))) +
geom_line(aes(y = test_data$Inflasi, color = "Actual"), size = 1) +
geom_line(aes(y = svr_predictions, color = "SVR Prediction"), size = 1) +
labs(x = "Observasi", y = "Inflasi") +
scale_color_manual(values = c("Actual" = "purple", "SVR Prediction" = "green")) +
ggtitle("Perbandingan SVR vs Aktual") +
scale_y_continuous(labels = scales::comma) +
theme_minimal()
5. INTERPRETASI
Dari hasil melakukan analitikal data dan analisis regresi terhadap dataset Inflasi Kota Medan. Dataset ini berisikan variabel Bulan, Tahun, dan Inflasi. Tujuan analisis adalah melakukan prediksi inflasi di kota Medan menggunakan model GLM, SVR, dan ANN Regression. dari hasil visualisasi dan evaluasi kami menemukan Model regresi SVR adalah model yang lebih dari pada keduanya
R Markdown
This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.
When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:
summary(cars)## speed dist
## Min. : 4.0 Min. : 2.00
## 1st Qu.:12.0 1st Qu.: 26.00
## Median :15.0 Median : 36.00
## Mean :15.4 Mean : 42.98
## 3rd Qu.:19.0 3rd Qu.: 56.00
## Max. :25.0 Max. :120.00Including Plots
You can also embed plots, for example:
Note that the echo = FALSE parameter was added to the
code chunk to prevent printing of the R code that generated the
plot.