-
Notifications
You must be signed in to change notification settings - Fork 0
/
.Rhistory
293 lines (293 loc) · 11.9 KB
/
.Rhistory
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
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
# Define the path to your Excel file
file_path <- "E:/GitHub/sherlock-final-project/pooled_data.xlsx"
# Load the necessary packages
library(readxl)
library(tseries)
library(vars)
# Define the path to your Excel file
file_path <- "E:/GitHub/sherlock-final-project/pooled_data.xlsx"
# Read the data from the Excel file
data <- read_excel(file_path, sheet = 1)
# View the first few rows of the data to understand its structure
head(data)
# Perform the Terasvirta test
terasvirta.test(data$x1, data$y, type=c("F"), scale=TRUE)
terasvirta.test(data$x2, data$y, type=c("F"), scale=TRUE)
terasvirta.test(data$x3, data$y, type=c("F"), scale=TRUE)
# Load the necessary packages
library(readxl)
library(tseries)
library(vars)
# Define the path to your Excel file
file_path <- "E:/GitHub/sherlock-final-project/pooled_data.xlsx"
# Read the data from the Excel file
data <- read_excel(file_path, sheet = 1)
# View the first few rows of the data to understand its structure
head(data)
# Perform the Terasvirta test
terasvirta.test(data$x1, data$y, type=c("F"), scale=TRUE)
terasvirta.test(data$x2, data$y, type=c("F"), scale=TRUE)
terasvirta.test(data$x3, data$y, type=c("F"), scale=TRUE)
# Load the necessary packages
lapply(c("readxl", "tseries", "vars", "car", "MVN", "ggplot2", "GGally", "dplyr", "biotools", "stats",
"MASS", "sf", "RColorBrewer", "viridis"), library, character.only = TRUE)
file_path <- "E:/GitHub/sherlock-final-project/pooled_data.xlsx"
data <- read_excel(file_path, sheet = 1)
y_lag <- data$y[1:578]
data <- data[35:612,]
data$x4 <- y_lag
# Perform the Terasvirta test
terasvirta.test(data$x1, data$y, type=c("F"), scale=TRUE)
terasvirta.test(data$x2, data$y, type=c("F"), scale=TRUE)
terasvirta.test(data$x3, data$y, type=c("F"), scale=TRUE)
terasvirta.test(data$x4, data$y, type=c("F"), scale=TRUE)
# ACF-PACF Test
# Plot ACF and PACF for the aggregated data
plot_acf_pacf <- function(series, title) {
par(mfrow=c(1,2))
acf(series, main=paste(title, "- ACF"), lag.max=136)
pacf(series, main=paste(title, "- PACF"), lag.max=136)
par(mfrow=c(1,1))
}
# Function to determine significant lags based on PACF
significant_pacf_lags <- function(series, threshold=0.2) {
pacf_values <- pacf(series, plot=FALSE)$acf
significant_lags <- which(abs(pacf_values) > threshold)
significant_lags <- significant_lags[significant_lags != 1] - 1
return(significant_lags)
}
# Function to check for stationarity
check_stationarity <- function(series, alpha=0.05) {
result <- adf.test(series)
p_value <- result$p.value
return(p_value < alpha) # If TRUE, the series is stationary
}
# Function to make the series stationary
make_stationary <- function(series) {
differenced_series <- diff(series)
return(na.omit(differenced_series))
}
# Function to determine the best N_PAST
determine_best_n_past <- function(aggregated_series, seasonal_period=34) {
# Check if the series is stationary
if (!check_stationarity(aggregated_series)) {
cat("Series is not stationary. Applying differencing...\n")
aggregated_series <- make_stationary(aggregated_series)
}
plot_acf_pacf(aggregated_series, "ACF and PACF for Aggregated Data")
# Calculate significant lags for the aggregated data
significant_lags <- significant_pacf_lags(aggregated_series)
# Determine a common N_PAST
max_significant_lag <- ifelse(length(significant_lags) > 0, max(significant_lags), 1)
# Adjust N_PAST to be a multiple of the seasonal period
common_n_past <- ceiling(max_significant_lag / seasonal_period) * seasonal_period
cat("Suggested common N_PAST (iterations):", common_n_past / seasonal_period, "\n")
cat("Actual N_PAST (data points):", common_n_past, "\n")
}
# Assuming `data` is a data frame with columns 'x1', 'x2', 'x3'
determine_best_n_past(data$x1)
determine_best_n_past(data$x2)
determine_best_n_past(data$x3)
#Clustering Visualization
indo_sf <- st_read("E:/GitHub/sherlock-final-project/map_cluster/indo_province_map.shp")
print(head(indo_sf))
print(indo_sf)
# Read the cluster data from the Excel file
cluster_data <- read_excel("E:/GitHub/sherlock-final-project/cluster_summary.xlsx", sheet='Sheet1')
cluster_data$kmedoids <- cluster_data$kmedoids +1
# Merge the shapefile data with the cluster data
merged_data <- indo_sf %>%
left_join(cluster_data, by = c("PROVINSI" = "province"))
# Visualize with ggplot2 using viridis color palette
ggplot(data = merged_data) +
geom_sf(aes(fill = factor(kmeans))) +
scale_fill_viridis_d(option = "viridis", name = "kmeans") +
theme_minimal() +
labs(title = "Klaster Tingkat Kemiskinan Indonesia - K-means")
# Visualize with ggplot2 using viridis color palette
ggplot(data = merged_data) +
geom_sf(aes(fill = factor(kmedoids))) +
scale_fill_viridis_d(option = "viridis", name = "kmedoids") +
theme_minimal() +
labs(title = "Klaster Tingkat Kemiskinan Indonesia - K-medoids")
#MANOVA
data_check <- read_excel("E:/GitHub/sherlock-final-project/cluster_summary.xlsx", sheet='Sheet1')
# Mardia Test
data_multivariate <- data_check[, c('x1', 'x2', 'x3')]
result_mvn <- mvn(data = data_multivariate, mvnTest = "mardia", multivariatePlot = "qq")
# ACF-PACF Test
# Plot ACF and PACF for the aggregated data
plot_acf_pacf <- function(series, title) {
par(mfrow=c(1,2))
acf(series, main=paste(title, "- ACF"), lag.max=136)
pacf(series, main=paste(title, "- PACF"), lag.max=136)
par(mfrow=c(1,1))
}
significant_pacf_lags <- function(series, alpha=0.05) {
pacf_result <- pacf(series, plot=FALSE)
pacf_values <- pacf_result$acf
n <- length(series)
critical_value <- qnorm(1 - alpha / 2) / sqrt(n)
significant_lags <- which(abs(pacf_values) > critical_value)
significant_lags <- significant_lags[significant_lags != 1] - 1
return(significant_lags)
}
# Function to check for stationarity
check_stationarity <- function(series, alpha=0.05) {
result <- adf.test(series)
p_value <- result$p.value
return(p_value < alpha) # If TRUE, the series is stationary
}
# Function to make the series stationary
make_stationary <- function(series) {
differenced_series <- diff(series)
return(na.omit(differenced_series))
}
# Function to determine the best N_PAST
determine_best_n_past <- function(aggregated_series, seasonal_period=34) {
# Check if the series is stationary
if (!check_stationarity(aggregated_series)) {
cat("Tidak stasioner, differencing\n")
aggregated_series <- make_stationary(aggregated_series)
}
plot_acf_pacf(aggregated_series, "ACF and PACF for Aggregated Data")
# Calculate significant lags for the aggregated data
significant_lags <- significant_pacf_lags(aggregated_series)
# Determine a common N_PAST
max_significant_lag <- ifelse(length(significant_lags) > 0, max(significant_lags), 1)
# Adjust N_PAST to be a multiple of the seasonal period
common_n_past <- ceiling(max_significant_lag / seasonal_period) * seasonal_period
cat("Suggested common N_PAST (iterations):", common_n_past / seasonal_period, "\n")
cat("Actual N_PAST (data points):", common_n_past, "\n")
}
# Assuming `data` is a data frame with columns 'x1', 'x2', 'x3'
determine_best_n_past(data$x1)
determine_best_n_past(data$x2)
determine_best_n_past(data$x3)
# ACF-PACF Test
# Plot ACF and PACF for the aggregated data
plot_acf_pacf <- function(series, title) {
par(mfrow=c(1,2))
acf(series, main=paste(title, "- ACF"), lag.max=136)
pacf(series, main=paste(title, "- PACF"), lag.max=136)
par(mfrow=c(1,1))
}
significant_pacf_lags <- function(series, alpha=0.05) {
pacf_result <- pacf(series, plot=FALSE)
pacf_values <- pacf_result$acf
n <- length(series)
critical_value <- qnorm(1 - alpha / 2) / sqrt(n)
significant_lags <- which(abs(pacf_values) > critical_value)
significant_lags <- significant_lags[significant_lags != 1] - 1
return(significant_lags)
}
# Function to check for stationarity
check_stationarity <- function(series, alpha=0.05) {
result <- adf.test(series)
p_value <- result$p.value
return(p_value < alpha) # If TRUE, the series is stationary
}
# Function to make the series stationary
make_stationary <- function(series) {
differenced_series <- diff(series)
return(na.omit(differenced_series))
}
# Function to determine the best N_PAST
determine_best_n_past <- function(aggregated_series, seasonal_period=34) {
# Check if the series is stationary
if (!check_stationarity(aggregated_series)) {
cat("Tidak stasioner, differencing\n")
aggregated_series <- make_stationary(aggregated_series)
}
plot_acf_pacf(aggregated_series, "ACF and PACF for Aggregated Data")
# Calculate significant lags for the aggregated data
significant_lags <- significant_pacf_lags(aggregated_series)
# Determine a common N_PAST
max_significant_lag <- ifelse(length(significant_lags) > 0, max(significant_lags), 1)
# Adjust N_PAST to be a multiple of the seasonal period
common_n_past <- ceiling(max_significant_lag / seasonal_period) * seasonal_period
cat("Suggested common N_PAST (iterations):", common_n_past / seasonal_period, "\n")
cat("Actual N_PAST (data points):", common_n_past, "\n")
}
# Assuming `data` is a data frame with columns 'x1', 'x2', 'x3'
determine_best_n_past(data$x1)
determine_best_n_past(data$x2)
determine_best_n_past(data$x3)
Load the necessary packages
# Load the necessary packages
lapply(c("readxl", "tseries", "vars", "car", "MVN", "ggplot2", "GGally", "dplyr", "biotools", "stats",
"MASS", "sf", "RColorBrewer", "viridis"), library, character.only = TRUE)
file_path <- "E:/GitHub/sherlock-final-project/pooled_data.xlsx"
data <- read_excel(file_path, sheet = 1)
y_lag <- data$y[1:578]
data <- data[35:612,]
data$x4 <- y_lag
# Perform the Terasvirta test
terasvirta.test(data$x1, data$y, type=c("F"), scale=TRUE)
terasvirta.test(data$x2, data$y, type=c("F"), scale=TRUE)
terasvirta.test(data$x3, data$y, type=c("F"), scale=TRUE)
terasvirta.test(data$x4, data$y, type=c("F"), scale=TRUE)
# ACF-PACF Test
# Plot ACF and PACF for the aggregated data
plot_acf_pacf <- function(series, title) {
par(mfrow=c(1,2))
acf(series, main=paste(title, "- ACF"), lag.max=136)
pacf(series, main=paste(title, "- PACF"), lag.max=136)
par(mfrow=c(1,1))
}
# Function to determine significant lags based on PACF
significant_pacf_lags <- function(series, threshold=0.2) {
pacf_values <- pacf(series, plot=FALSE)$acf
significant_lags <- which(abs(pacf_values) > threshold)
significant_lags <- significant_lags[significant_lags != 1] - 1
return(significant_lags)
}
significant_pacf_lags <- function(series, alpha=0.05) {
pacf_result <- pacf(series, plot=FALSE)
pacf_values <- pacf_result$acf
n <- length(series)
critical_value <- qnorm(1 - alpha / 2) / sqrt(n)
significant_lags <- which(abs(pacf_values) > critical_value)
significant_lags <- significant_lags[significant_lags != 1] - 1
return(significant_lags)
}
# Function to check for stationarity
check_stationarity <- function(series, alpha=0.05) {
result <- adf.test(series)
p_value <- result$p.value
return(p_value < alpha) # If TRUE, the series is stationary
}
# Function to make the series stationary
make_stationary <- function(series) {
differenced_series <- diff(series)
return(na.omit(differenced_series))
}
# Function to determine the best N_PAST
determine_best_n_past <- function(aggregated_series, seasonal_period=34) {
# Check if the series is stationary
if (!check_stationarity(aggregated_series)) {
cat("Tidak stasioner, differencing\n")
aggregated_series <- make_stationary(aggregated_series)
}
plot_acf_pacf(aggregated_series, "ACF and PACF for Aggregated Data")
# Calculate significant lags for the aggregated data
significant_lags <- significant_pacf_lags(aggregated_series)
# Determine a common N_PAST
max_significant_lag <- ifelse(length(significant_lags) > 0, max(significant_lags), 1)
# Adjust N_PAST to be a multiple of the seasonal period
common_n_past <- ceiling(max_significant_lag / seasonal_period) * seasonal_period
cat("Suggested common N_PAST (iterations):", common_n_past / seasonal_period, "\n")
cat("Actual N_PAST (data points):", common_n_past, "\n")
}
# Assuming `data` is a data frame with columns 'x1', 'x2', 'x3'
determine_best_n_past(data$x1)
determine_best_n_past(data$x2)
determine_best_n_past(data$x3)
# ACF-PACF Test
auto.arima(data$x1)
# ACF-PACF Test
library(forecast)
auto.arima(data$x1)
check_stationarity(data$x1)
check_stationarity(data$x2)
check_stationarity(data$x3)