df <- read_excel("Dataset_EDA_30_Observasi.xlsx", sheet = "Data") %>%
  mutate(Tanggal = as.Date(Tanggal))

head(df, 10)

dim(df)

names(df)

str(df)

tabel_tipe <- tibble(
  Variabel = names(df),
  Tipe_data = c("Tanggal", "Kategorikal", "Kategorikal",
                "Numerik diskrit", "Numerik kontinu", "Numerik kontinu"),
  Skala_pengukuran = c("Interval waktu/temporal", "Nominal", "Nominal",
                       "Rasio", "Rasio", "Rasio"),
  Alasan = c(
    "Menunjukkan urutan waktu pengamatan harian.",
    "Online dan Offline merupakan kategori tanpa tingkatan.",
    "Reguler, Express, dan Premium merupakan kategori layanan.",
    "Jumlah kejadian transaksi berupa hitungan dan memiliki nol mutlak.",
    "Durasi proses dapat memiliki nilai pecahan dan nol berarti tidak ada durasi.",
    "Nilai uang memiliki nol mutlak dan dapat dibandingkan secara rasio."
  )
)
kable(tabel_tipe, caption = "Identifikasi tipe dan skala pengukuran", booktabs = TRUE)

cek_kualitas <- tibble(
  Pemeriksaan = c("Jumlah baris", "Jumlah kolom", "Missing value",
                  "Baris duplikat", "Tanggal paling awal", "Tanggal paling akhir"),
  Hasil = c(
    nrow(df), ncol(df),
    sum(is.na(df)),
    sum(duplicated(df)),
    as.character(min(df$Tanggal, na.rm = TRUE)),
    as.character(max(df$Tanggal, na.rm = TRUE))
  )
)
kable(cek_kualitas, caption = "Ringkasan pemeriksaan kualitas data")

missing_kolom <- tibble(
  Variabel = names(df),
  Jumlah_missing = sapply(df, function(x) sum(is.na(x)))
)
kable(missing_kolom, caption = "Missing value pada setiap variabel")

buat_frekuensi <- function(x) {
  hasil <- as.data.frame(table(x), stringsAsFactors = FALSE)
  names(hasil) <- c("Kategori", "Frekuensi")
  hasil %>%
    mutate(
      Frekuensi_Relatif = Frekuensi / sum(Frekuensi),
      Persentase = percent(Frekuensi_Relatif, accuracy = 0.1),
      Frekuensi_Kumulatif = cumsum(Frekuensi)
    )
}

freq_kanal <- buat_frekuensi(df$Kanal)
freq_layanan <- buat_frekuensi(df$Jenis_Layanan)

kable(freq_kanal, caption = "Distribusi frekuensi Kanal")

kable(freq_layanan, caption = "Distribusi frekuensi Jenis Layanan")

modus <- function(x) {
  x <- x[!is.na(x)]
  nilai <- unique(x)
  frek <- tabulate(match(x, nilai))
  nilai[frek == max(frek)]
}

variabel_numerik <- c("Jumlah_Transaksi", "Waktu_Proses_Menit",
                      "Nilai_Transaksi_Juta_Rp")

stat_deskriptif <- map_dfr(variabel_numerik, function(v) {
  x <- df[[v]]
  tibble(
    Variabel = v,
    Mean = mean(x, na.rm = TRUE),
    Median = median(x, na.rm = TRUE),
    Modus = paste(modus(x), collapse = ", "),
    Minimum = min(x, na.rm = TRUE),
    Maksimum = max(x, na.rm = TRUE),
    Rentang = diff(range(x, na.rm = TRUE)),
    Varians = var(x, na.rm = TRUE),
    Standar_Deviasi = sd(x, na.rm = TRUE),
    CV_persen = sd(x, na.rm = TRUE) / mean(x, na.rm = TRUE) * 100
  )
})
kable(stat_deskriptif, digits = 2,
      caption = "Statistik deskriptif variabel numerik")

ggplot(df, aes(x = Kanal, fill = Kanal)) +
  geom_bar(width = 0.65, show.legend = FALSE) +
  geom_text(stat = "count", aes(label = after_stat(count)), vjust = -0.5) +
  scale_fill_manual(values = c("Online" = "#4C91B8", "Offline" = "#E6A15C")) +
  labs(title = "Frekuensi Transaksi Berdasarkan Kanal",
       x = "Kanal transaksi", y = "Jumlah pengamatan") +
  tema_uts

pie_data <- df %>% count(Jenis_Layanan) %>%
  mutate(label = paste0(Jenis_Layanan, "\n", percent(n / sum(n), accuracy = 0.1)))
ggplot(pie_data, aes(x = "", y = n, fill = Jenis_Layanan)) +
  geom_col(width = 1, color = "white") +
  coord_polar(theta = "y") +
  geom_text(aes(label = label), position = position_stack(vjust = 0.5),
            size = 3.5) +
  labs(title = "Proporsi Jenis Layanan", x = NULL, y = NULL, fill = "Layanan") +
  tema_uts + theme(axis.text = element_blank(), axis.ticks = element_blank(),
                   panel.grid = element_blank())

par(mfrow = c(3, 1), mar = c(4, 4, 3, 1))
for (v in variabel_numerik) {
  x <- df[[v]]
  hist(x, breaks = "Sturges", col = "#8DB7CC", border = "white",
       main = paste("Histogram", v),
       xlab = v, ylab = "Frekuensi")
}

par(mfrow = c(1, 1))

data_long <- df %>%
  select(all_of(variabel_numerik)) %>%
  pivot_longer(everything(), names_to = "Variabel", values_to = "Nilai")

ggplot(data_long, aes(x = "", y = Nilai)) +
  geom_boxplot(fill = "#8DB7CC", color = "#24536A", width = 0.45) +
  facet_wrap(~ Variabel, scales = "free_y", ncol = 1) +
  labs(title = "Boxplot Variabel Numerik", x = NULL, y = "Nilai") +
  tema_uts

ringkasan_kanal <- df %>%
  group_by(Kanal) %>%
  summarise(
    Jumlah_hari = n(),
    Rata_rata_transaksi = mean(Jumlah_Transaksi, na.rm = TRUE),
    Median_transaksi = median(Jumlah_Transaksi, na.rm = TRUE),
    Rata_rata_waktu = mean(Waktu_Proses_Menit, na.rm = TRUE),
    Rata_rata_nilai = mean(Nilai_Transaksi_Juta_Rp, na.rm = TRUE),
    .groups = "drop"
  )
kable(ringkasan_kanal, digits = 2,
      caption = "Perbandingan ringkasan berdasarkan kanal")

ggplot(ringkasan_kanal, aes(x = Kanal, y = Rata_rata_transaksi, fill = Kanal)) +
  geom_col(width = 0.6, show.legend = FALSE) +
  geom_text(aes(label = round(Rata_rata_transaksi, 1)), vjust = -0.5) +
  scale_fill_manual(values = c("Online" = "#4C91B8", "Offline" = "#E6A15C")) +
  labs(title = "Rata-rata Jumlah Transaksi Berdasarkan Kanal",
       x = "Kanal", y = "Rata-rata transaksi per hari") +
  tema_uts

ggplot(df, aes(x = Kanal, y = Waktu_Proses_Menit, fill = Kanal)) +
  geom_boxplot(alpha = 0.85, show.legend = FALSE) +
  scale_fill_manual(values = c("Online" = "#4C91B8", "Offline" = "#E6A15C")) +
  labs(title = "Sebaran Waktu Proses Berdasarkan Kanal",
       x = "Kanal", y = "Waktu proses (menit)") +
  tema_uts

ggplot(df, aes(x = Jenis_Layanan, y = Nilai_Transaksi_Juta_Rp,
               fill = Jenis_Layanan)) +
  geom_boxplot(show.legend = FALSE, alpha = 0.85) +
  scale_fill_manual(values = c("Reguler" = "#8DB7CC",
                               "Express" = "#E6A15C",
                               "Premium" = "#8BB99B")) +
  labs(title = "Sebaran Nilai Transaksi Berdasarkan Jenis Layanan",
       x = "Jenis layanan", y = "Nilai transaksi (juta rupiah)") +
  tema_uts

ggplot(df, aes(x = Jumlah_Transaksi, y = Nilai_Transaksi_Juta_Rp,
               color = Jenis_Layanan)) +
  geom_point(size = 2.8, alpha = 0.85) +
  geom_smooth(aes(group = 1), method = "lm", se = TRUE,
              color = "#333333", linewidth = 0.8) +
  labs(title = "Hubungan Jumlah Transaksi dan Nilai Transaksi",
       x = "Jumlah transaksi", y = "Nilai transaksi (juta rupiah)",
       color = "Jenis layanan") +
  tema_uts

korelasi <- cor(df$Jumlah_Transaksi, df$Nilai_Transaksi_Juta_Rp,
                use = "complete.obs")
tibble(Hubungan = "Jumlah transaksi dan nilai transaksi",
       Korelasi_Pearson = korelasi)

tren_long <- df %>%
  select(Tanggal, Jumlah_Transaksi, Waktu_Proses_Menit) %>%
  pivot_longer(-Tanggal, names_to = "Variabel", values_to = "Nilai")

ggplot(tren_long, aes(x = Tanggal, y = Nilai, color = Variabel)) +
  geom_line(linewidth = 0.8) +
  geom_point(size = 1.8) +
  facet_wrap(~ Variabel, scales = "free_y", ncol = 1) +
  scale_x_date(date_labels = "%d %b", date_breaks = "5 days") +
  labs(title = "Perubahan Jumlah Transaksi dan Waktu Proses",
       x = "Tanggal", y = "Nilai", color = "Variabel") +
  tema_uts + theme(axis.text.x = element_text(angle = 45, hjust = 1))

mat_korelasi <- cor(df %>% select(all_of(variabel_numerik)),
                    use = "pairwise.complete.obs")
korelasi_long <- as.data.frame(as.table(mat_korelasi)) %>%
  rename(Variabel_1 = Var1, Variabel_2 = Var2, Korelasi = Freq)

ggplot(korelasi_long, aes(x = Variabel_1, y = Variabel_2, fill = Korelasi)) +
  geom_tile(color = "white") +
  geom_text(aes(label = round(Korelasi, 2)), size = 4) +
  scale_fill_gradient2(low = "#C76D6D", mid = "white", high = "#4C91B8",
                       midpoint = 0, limits = c(-1, 1)) +
  labs(title = "Matriks Korelasi Variabel Numerik",
       x = NULL, y = NULL, fill = "Korelasi") +
  tema_uts + theme(axis.text.x = element_text(angle = 25, hjust = 1))

ringkasan_kombinasi <- df %>%
  group_by(Kanal, Jenis_Layanan) %>%
  summarise(
    Jumlah_hari = n(),
    Rata_rata_transaksi = mean(Jumlah_Transaksi, na.rm = TRUE),
    Rata_rata_waktu = mean(Waktu_Proses_Menit, na.rm = TRUE),
    Rata_rata_nilai = mean(Nilai_Transaksi_Juta_Rp, na.rm = TRUE),
    .groups = "drop"
  )
kable(ringkasan_kombinasi, digits = 2,
      caption = "Ringkasan gabungan kanal dan jenis layanan")

ggplot(ringkasan_kombinasi,
       aes(x = Jenis_Layanan, y = Kanal, fill = Rata_rata_transaksi)) +
  geom_tile(color = "white") +
  geom_text(aes(label = round(Rata_rata_transaksi, 1)), size = 4) +
  scale_fill_gradient(low = "#EAF2F5", high = "#286783") +
  labs(title = "Rata-rata Transaksi Menurut Kanal dan Layanan",
       x = "Jenis layanan", y = "Kanal",
       fill = "Rata-rata transaksi") +
  tema_uts

jumlah_outlier <- hasil_outlier %>%
  group_by(Variabel) %>%
  summarise(
    Jumlah_IQR = sum(Outlier_IQR, na.rm = TRUE),
    Jumlah_z_di_atas_2 = sum(Perlu_diperhatikan_z, na.rm = TRUE),
    Jumlah_z_di_atas_3 = sum(Outlier_ekstrem_z, na.rm = TRUE),
    .groups = "drop"
  )
kable(jumlah_outlier, caption = "Jumlah penanda outlier berdasarkan metode")

ggplot(data_long, aes(x = "", y = Nilai)) +
  geom_boxplot(fill = "#E6AD65", color = "#805A2B", outlier.color = "#B33A3A") +
  facet_wrap(~ Variabel, scales = "free_y", ncol = 1) +
  labs(title = "Pemeriksaan Visual Nilai Ekstrem",
       x = NULL, y = "Nilai") +
  tema_uts

kanal_tertinggi <- ringkasan_kanal %>% slice_max(Rata_rata_transaksi, n = 1, with_ties = FALSE)
kanal_waktu_terendah <- ringkasan_kanal %>% slice_min(Rata_rata_waktu, n = 1, with_ties = FALSE)
layanan_nilai_tertinggi <- ringkasan_kombinasi %>%
  slice_max(Rata_rata_nilai, n = 1, with_ties = FALSE)

cat(
  "Kanal dengan rata-rata transaksi tertinggi adalah", kanal_tertinggi$Kanal,
  "dengan rata-rata", round(kanal_tertinggi$Rata_rata_transaksi, 2),
  "transaksi per hari.\n\n",
  "Kanal dengan rata-rata waktu proses terendah adalah", kanal_waktu_terendah$Kanal,
  "dengan rata-rata", round(kanal_waktu_terendah$Rata_rata_waktu, 2),
  "menit.\n\n",
  "Kombinasi kanal dan layanan dengan rata-rata nilai transaksi tertinggi adalah",
  kanal_nilai <- paste(layanan_nilai_tertinggi$Kanal,
                       layanan_nilai_tertinggi$Jenis_Layanan, sep = " - "),
  "dengan rata-rata", round(layanan_nilai_tertinggi$Rata_rata_nilai, 2),
  "juta rupiah."
)