Problem Research

Prediksi dan Analisis Harga Bahan Baku Pangan

Background Project

Indonesia merupakan salah satu negara terbesar di Asia Tenggara yang memproduksi berbagai macam komoditas bahan pangan. Komoditas sayuran mempunyai kontribusi besar terhadap produksi hortikultura Indonesia dan memberikan pendapatan bagi negara. Dengan berbagai macam jenis makanan di Indonesia, komoditas sayuran yang di produksi di tanah air sebagian besar di peruntukan untuk konsumsi rumah tangga. Di antara bebagai macam sayuran yang di produksi, ada 6 sayuran yang memiliki potensi untuk terus dikembangkan yaitu:

Bawang Merah, produksi 2020 1,82 juta ton.
Bawang Putih, produksi 2020 81,8 ribu ton.
Cabai, produksi 2020 2,77 ton.
Kentang, produksi 2020 1,28 juta ton.
Tomat, produksi 2020 1,08 juta ton.
Wortel, produksi 2020 650,86 ribu ton.

**data produksi tahun 2021 saat ini belum di publish oleh Badan Pusat Statistik

sumber

Tingkat konsumsi sayuran khusus nya rumah tangga meningkat di masa pandemi Covid-19 karena banyak masyarakat mulai sadar akan pentingnya konsumsi sayuran untuk mendukung pola hidup yang lebih sehat. Di daerah ibu kota Indonesia, DKI Jakarta, rata-rata konsumsi sayuran di tahun 2021 mencapai 1.500 ton per hari sumber. Meningkat nya tingkat konsumsi warga Jakarta menyebabkan pemerintah harus menambah pasokan sayur di daerah tersebut, karena supply sayuran yang di produksi di Jakarta tidak cukup untuk memenuhi kebutuhan daerah tesebut, sehingga sebagian besar masih harus di datangkan dari daerah lain. Tingkat kebutuhan sayuran yang meningkat, jika tidak di barengi dengan peningkatan produksi dapat mengakibatkan fluktuasi tinggi pada harga sayuran.

**Fluktuasi harga bawang merah di awal pandemi Covid-19

Pada bulanan Oktober 2020, harga bawang putih sempat melonjak disebabkan kelangkaan pasokan bawang putih di pasaran. Berdasarkan hal tersebut Kementrian Perdagangan melakukan upaya untuk menekan harga bawang putih yang naik dengan melakukan impor sumber.

**Harga bawang putih Oktober 2020

Ada beberapa faktor yang menyebabkan kenaikan harga sayur seperti faktor cuaca di daerah pertanian yang dapat menyebabkan gagal panen, faktor naik turunnya inflasi di suatu daerah hingga permainan tengkulak / distributor yang menahan distribusi produk demi menaikan harga pasar. Peningkatan harga sayuran dapat menyebabkan konsumen, khususnya sektor rumah tangga dan pelaku bisnis makanan harus menyesuaikan budget belanja mereka. Terlebih bila harga meningkat cukup signifikan, menyebabkan biaya produksi makanan untuk pelaku bisnis makanan membengkak, sehingga seringkali pelaku bisnis harus menghitung ulang harga jual mereka untuk menghindari kerugian.

Business Impact

Membuat model prediksi & rekomendasi untuk harga bahan baku komoditas pasar seperti bawang, cabai, kentang dll di daerah DKI Jakarta. Model prediksi nantinya diharapkan dapat membantu User untuk memprediksi harga bahan baku kedepannya, sehingga dapat membantu User seperti UMKM yang ingin membuat budgeting. Untuk model rekomendasi di tujukan untuk User yang ingin mendapatkan “best price” atas suatu komoditas pada tanggal tertentu, di suatu pasar berdasarkan lokasi tempat tinggal.

User & Benefit

Target user : Pemilik bisnis dan individual yang terbiasa membeli bahan baku di pasar.
Benefit : Mendapatkan informasi perkiraan harga suatu komoditas di masa mendatang yang bisa digunakan untuk membuat budget. Mendapatkan informasi “best price” untuk suatu komoditas berdasarkan lokasi pasar.

Implementation to other business

Forecast untuk pendapatan (revenue), penggunaan persediaan bahan baku (inventory) & harga rumah.
Rekomendasi harga rumah, tempat tinggal berdasarkan kepadatan penduduk & pemilihan best produk.

Output

Membuat dashboard yang berisikan informasi pergerakan suatu harga komoditas bahan baku pasar dari tahun Januari 2020 sampai Maret 2022 (jika data nya memungkinkan).
Prediksi harga suatu komoditas hingga 3 bulan kedepan.
Rekomendasi “best price” suatu komoditas berdasarkan lokasi pasar.

Library

library(tidyverse) #data wrangling and visualization
library(leaflet) #map visualization
library(glue) #visualization label
library(plotly) #Interactive Visualization
library(forecast) # time series library
library(tseries) # for adf.test
library(MLmetrics) # calculate error
theme_set(theme_minimal())

Read and Clean Dataset

Dalam melakukan prediksi dan analisis harga bahan baku kita akan menggunakan 2 data yaitu:

market yang berisi informasi harga bahan baku per lokasi pasar di daerah DKI Jakarta dari tahun 2020 - 2021.
city yang berisi informasi harga bahan baku per lokasi kota bagian di daerah DKI Jakarta dari tahun 2020 - 2021.
Inflation yang berisi informasi inflasi per bulan dari situs BEI

Kedua data market dan city di peroleh secara manual per bulan melalui situs Info Pangan. Untuk informasi latitude dan longitude pada data market diperoleh dari google map.

Market

market <- readxl::read_xlsx("pasar.xlsx")
head(market)

Berdasarkan observasi pada 6 data pertama, kita dapat melihat bahwa data market memiliki 42 kolom yang berisi:

market: Nama pasar
city : Lokasi pasar berdasarkan kota bagian di DKI Jakarta
latitude & longitude : Titik koordinat lokasi
date : tanggal per hari
sisa 37 kolom merupakan informasi jenis bahan baku beserta harganya

#to check unique value 
unique(market$market)

##  [1] "Pasar Anyer Bahari"         "Pasar Baru Metro Atom"     
##  [3] "Pasar Cempaka Putih"        "Pasar Cijantung"           
##  [5] "Pasar Cipete"               "Pasar Ciplak"              
##  [7] "Pasar Glodok"               "Pasar Gondangdia"          
##  [9] "Pasar Grogol"               "Pasar Induk Kramat Jati"   
## [11] "Pasar Jatinegara"           "Pasar Jembatan Lima"       
## [13] "Pasar Jembatan Merah"       "Pasar Johar Baru"          
## [15] "Pasar Kalibaru"             "Pasar Kalideres"           
## [17] "Pasar Kebayoran Lama"       "Pasar Kelapa Gading"       
## [19] "Pasar Koja Baru"            "Pasar Kramat Jati"         
## [21] "Pasar Lenteng Agung"        "Pasar Mampang Prapatan"    
## [23] "Pasar Mayestik"             "Pasar Pademangan Timur"    
## [25] "Pasar Pal Merah"            "Pasar Cengkareng"          
## [27] "Pasar Minggu"               "Pasar Petojo Ilir"         
## [29] "Pasar Senen Blok III - VI"  "Pasar Paseban"             
## [31] "Pasar Perumnas Klender"     "Pasar Pesanggrahan"        
## [33] "Pasar Pluit"                "Pasar Pondok Labu"         
## [35] "Pasar Pos Pengumben"        "Pasar Pramuka"             
## [37] "Pasar Pulo Gadung"          "Pasar Rawa Badak"          
## [39] "Pasar Rumput"               "Pasar Sunter Podomoro"     
## [41] "Pasar Tanah Abang Blok A-G" "Pasar Tebet Barat"         
## [43] "Pasar Tomang Barat"

Pada data market, terdapat kurang lebih 43 lokasi pasar dan 5 kota bagian di DKI Jakarta.

#to check unique value 
unique(market$city)

## [1] "Jakarta Utara"   "Jakarta Pusat"   "Jakarta Timur"   "Jakarta Selatan"
## [5] "Jakarta Barat"

#to check date range
range(market$date)

## [1] "2020-01-01 UTC" "2021-12-31 UTC"

#to check NA value from each columns
colSums(is.na(market))

##                          market                            city 
##                               0                               0 
##                        latitude                       longitude 
##                               0                               0 
##                            date              Beras IR I (IR 64) 
##                               0                            4686 
##       Beras IR II (IR 64) Ramos            Beras IR III (IR 64) 
##                            4865                            5704 
##                  Beras Muncul I                Beras IR 42/Pera 
##                           11257                            3911 
##           Beras Setra I/Premium    Minyak Goreng (Kuning/Curah) 
##                            6928                             851 
##             Cabe Merah Keriting           Cabe Merah Besar (TW) 
##                               0                            1317 
##                Cabe Rawit Merah                Cabe Rawit Hijau 
##                               0                               0 
##                    Bawang Merah                    Bawang Putih 
##                               0                               0 
## Daging Sapi Has (Paha Belakang)       Daging Sapi Murni (Semur) 
##                            3717                            1128 
##                Ayam Broiler/Ras                  Telur Ayam Ras 
##                            2955                             731 
##                      Gula Pasir                   Tepung Terigu 
##                             731                             731 
##                     Garam Dapur                Kentang (sedang) 
##                            1462                               0 
##                      Tomat Buah                    Kelapa Kupas 
##                               0                            2224 
##                        Semangka                     Jeruk Medan 
##                            7999                            8153 
##                  Daging Kambing            Daging Babi Berlemak 
##                           12264                           17810 
##           Ikan Bandeng (sedang)                        Ikan Mas 
##                            4621                            5418 
##                       Ikan Lele                  Gas Elpiji 3kg 
##                            5400                           17142 
##        Susu Bubuk Bendera 400gr         Susu Bubuk Dancow 400gr 
##                           23456                           20041 
##       Susu Kental Bendera 200gr          Susu Kental Enak 200gr 
##                             761                            3844 
##           Margarin Blueband Cup        Margarin Blueband Sachet 
##                            3341                             930

Berdasarkan pengecekan kolom NA dari data market, kita dapat melihat ada banyak sekali kolom yang tidak memiliki informasi harga. Hal ini dikarenakan ada beberapa pasar yang tidak menjual keseluruhan 37 bahan baku, sehingga tidak ada informasi harga yang ditampilkan. Oleh karena itu, kita hanya akan melakukan prediksi dan analisis harga bahan baku pada kolom yang tidak memiliki NA value yaitu:

Cabe Merah Keriting
Cabe Rawit Merah
Cabe Rawit Hijau
Bawang Merah
Bawang Putih
Kentang (sedang)
Tomat Buah

Sekarang kita akan melakukan cleansing data dengan merubah format pada kolom market, city & date dan melakukan select pada kolom yang tidak memiliki NA.

#cleansing data
market_clean <-
market %>% 
  select(market, city, latitude, longitude, date, "Cabe Merah Keriting", "Cabe Rawit Merah", "Cabe Rawit Hijau", "Bawang Merah", "Bawang Putih", "Kentang (sedang)", "Tomat Buah") %>% 
  arrange(date) %>% 
  gather(key = commodity, value = price, "Cabe Merah Keriting":"Tomat Buah") %>% 
   mutate(market = as.factor(market),
         city = as.factor(city), 
         date = as.Date(date),
         commodity = as.factor(commodity))

head(market_clean)

Data yang digunakan untuk periode tahun 2020 - 2021 di ambil pada bulan Januari 2022, agar hasil prediksi bisa lebih up to date sekarang kita akan menambahkan data untuk tahun 2022 yang di ambil di bulan Maret 2022. Dikarenakan kita sudah menentukan commodity yang akan kita prediksi, kita dapat mengambil data dari website Info Pangan berdasarkan komoditas saja. Format tabel apabila kita mengambil data per komoditas sedikit berbeda dengan data sebelumnya market, jadi kita harus melakukan data wrangling terlebih dahulu untuk menyamakan format sebelum di gabung.

market2 <- readxl::read_xlsx("pasar 2022.xlsx")
head(market2)

market2 <-
market2 %>% 
  gather(key = market, value = price, "Pasar Induk Kramat Jati":"Pasar Anyer Bahari") %>% 
  mutate_if(is.character, as.factor) %>% 
  mutate(date = as.Date(date))

location <-
  market_clean %>% 
  distinct(city, market, latitude, longitude)

market2_comb <- 
  (merge(location, market2, by = "market"))

head(market2_comb)

market_clean <- 
rbind(market_clean, market2_comb)

City

city <- readxl::read_xlsx("kota.xlsx")
head(city)

Berdasarkan observasi pada 6 data pertama, kita dapat melihat bahwa data city memiliki 42 kolom yang berisi:

market: Lokasi pasar berdasarkan kota bagian DKI Jakarta
date : tanggal per hari
sisa 37 kolom merupakan informasi jenis bahan baku beserta harganya

#check unique value
unique(city$market)

## [1] "Jakarta Barat"   "Jakarta Pusat"   "Jakarta Selatan" "Jakarta Timur"  
## [5] "Jakarta Utara"

Pada data city terdapat 5 kota bagian di DKI Jakarta.

#to check date range
range(city$date)

## [1] "2020-01-01 UTC" "2022-02-28 UTC"

#to check NA value
colSums(is.na(city))

##                          market                            date 
##                               0                               0 
##              Beras IR I (IR 64)       Beras IR II (IR 64) Ramos 
##                               0                               0 
##            Beras IR III (IR 64)                  Beras Muncul I 
##                               0                               0 
##                Beras IR 42/Pera           Beras Setra I/Premium 
##                               0                               0 
##    Minyak Goreng (Kuning/Curah)             Cabe Merah Keriting 
##                               0                               0 
##           Cabe Merah Besar (TW)                Cabe Rawit Merah 
##                               0                               0 
##                Cabe Rawit Hijau                    Bawang Merah 
##                               0                               0 
##                    Bawang Putih Daging Sapi Has (Paha Belakang) 
##                               0                               0 
##       Daging Sapi Murni (Semur)                Ayam Broiler/Ras 
##                               0                               0 
##                  Telur Ayam Ras                      Gula Pasir 
##                               0                               0 
##                   Tepung Terigu                     Garam Dapur 
##                               0                               0 
##                Kentang (sedang)                      Tomat Buah 
##                               0                               0 
##                    Kelapa Kupas                        Semangka 
##                               0                               0 
##                     Jeruk Medan                  Daging Kambing 
##                               0                               0 
##            Daging Babi Berlemak           Ikan Bandeng (sedang) 
##                               0                               0 
##                        Ikan Mas                       Ikan Lele 
##                               0                               0 
##                  Gas Elpiji 3kg        Susu Bubuk Bendera 400gr 
##                               0                               0 
##         Susu Bubuk Dancow 400gr       Susu Kental Bendera 200gr 
##                               0                               0 
##          Susu Kental Enak 200gr           Margarin Blueband Cup 
##                               0                               0 
##        Margarin Blueband Sachet 
##                               0

Data city tidak memiliki NA Value. Berdasarkan pemilihan kolom yang akan digunakan untuk analisis & prediksi dari data market, hal yang sama akan di aplikasikan juga untuk data city. Kita juga akan melakukan perubahan format pada kolom market & date.

#Cleansing Data
city_clean <-
city %>% 
  select(market, date, "Cabe Merah Keriting", "Cabe Rawit Merah", "Cabe Rawit Hijau", "Bawang Merah", "Bawang Putih", "Kentang (sedang)", "Tomat Buah") %>%
  gather(key = commodity, value = price, "Cabe Merah Keriting":"Tomat Buah") %>%
  mutate(market = as.factor(market),
         date = as.Date(date),
         commodity = as.factor(commodity)) %>% 
  arrange(date)

tail(city_clean)

Inflation

inflation <- readxl::read_xlsx("inflasi.xlsx")
head(inflation)

# Rename inflation column to Inflasi
names(inflation)[3] <- "Inflasi"

inflation <-
inflation %>%
mutate(Inflasi = ifelse(grepl("%", Inflasi),
                as.numeric(gsub("%", "", Inflasi)), as.numeric(Inflasi))) %>% # To delete "%" value in Inflasi column
  separate(Periode, sep = " ", into = c("Month", "Year")) # to seperate Periode value into Month and Year column

inflation$Month <- plyr::mapvalues(inflation$Month, from = c("Januari", "Februari", "Maret", "Mei", "Juni", "Juli", "Agustus", "Oktober", "Desember"),
                                           to = c("January", "February", "March", "May", "June", "July", "August", "October", "December")) # to translate month into English

# to join column Month and Year
inflation <-
  inflation %>% 
  mutate(Periode = paste(Month, Year, sep = " "),
         Inflasi = Inflasi * 100) %>% 
  select(Periode, Inflasi)

#To create date column in daily format
date <-
city %>% 
  filter(market == "Jakarta Barat") %>% 
  select(date) %>% 
  mutate(Periode = format(date, "%B %Y"))

#Combine inflation rate to each date
inflasi <-
(merge(inflation, date, by = "Periode")) %>% 
  arrange(date)

head(inflasi)

Visualization EDA

Market Visualization

Cabe Merah Keriting

market_clean %>% 
  group_by(market, commodity) %>% 
  summarise(mean_price = mean(price)) %>%
  arrange(mean_price) %>% 
  filter(commodity == "Cabe Merah Keriting") %>% 
ggplot(aes(x = market, y = mean_price))+
  geom_segment( aes(x=reorder(market, mean_price) ,xend=market, y=0, yend=mean_price))+
  geom_point(size=3, color="steelblue")+
  coord_flip()+
  scale_y_continuous(labels = scales::comma)+
  ggtitle("Average Price by Commodity")+
  labs(x = "Market",
       y = "Average Price (IDR)", fill = "")+
  theme(axis.text = element_text(colour = "navyblue"),
        plot.title = element_text(hjust = 0.5))+
  facet_wrap(~commodity)

Cabe Rawit Merah

market_clean %>% 
  group_by(market, commodity) %>% 
  summarise(mean_price = mean(price)) %>%
  arrange(mean_price) %>% 
  filter(commodity == "Cabe Rawit Merah") %>% 
ggplot(aes(x = market, y = mean_price))+
  geom_segment( aes(x=reorder(market, mean_price) ,xend=market, y=0, yend=mean_price))+
  geom_point(size=3, color="steelblue")+
  coord_flip()+
  scale_y_continuous(labels = scales::comma)+
  ggtitle("Average Price by Commodity")+
  labs(x = "Market",
       y = "Average Price (IDR)", fill = "")+
  theme(axis.text = element_text(colour = "navyblue"),
        plot.title = element_text(hjust = 0.5))+
  facet_wrap(~commodity)

Cabe Rawit Hijau

market_clean %>% 
  group_by(market, commodity) %>% 
  summarise(mean_price = mean(price)) %>%
  arrange(mean_price) %>% 
  filter(commodity == "Cabe Rawit Hijau") %>% 
ggplot(aes(x = market, y = mean_price))+
  geom_segment( aes(x=reorder(market, mean_price) ,xend=market, y=0, yend=mean_price))+
  geom_point(size=3, color="steelblue")+
  coord_flip()+
  scale_y_continuous(labels = scales::comma)+
  ggtitle("Average Price by Commodity")+
  labs(x = "Market",
       y = "Average Price (IDR)", fill = "")+
  theme(axis.text = element_text(colour = "navyblue"),
        plot.title = element_text(hjust = 0.5))+
  facet_wrap(~commodity)

Bawang Merah

market_clean %>% 
  group_by(market, commodity) %>% 
  summarise(mean_price = mean(price)) %>%
  arrange(mean_price) %>% 
  filter(commodity == "Bawang Merah") %>% 
ggplot(aes(x = market, y = mean_price))+
  geom_segment( aes(x=reorder(market, mean_price) ,xend=market, y=0, yend=mean_price))+
  geom_point(size=3, color="steelblue")+
  coord_flip()+
  scale_y_continuous(labels = scales::comma)+
  ggtitle("Average Price by Commodity")+
  labs(x = "Market",
       y = "Average Price (IDR)", fill = "")+
  theme(axis.text = element_text(colour = "navyblue"),
        plot.title = element_text(hjust = 0.5))+
  facet_wrap(~commodity)

Bawang Putih

market_clean %>% 
  group_by(market, commodity) %>% 
  summarise(mean_price = mean(price)) %>%
  arrange(mean_price) %>% 
  filter(commodity == "Bawang Putih") %>% 
ggplot(aes(x = market, y = mean_price))+
  geom_segment( aes(x=reorder(market, mean_price) ,xend=market, y=0, yend=mean_price))+
  geom_point(size=3, color="steelblue")+
  coord_flip()+
  scale_y_continuous(labels = scales::comma)+
  ggtitle("Average Price by Commodity")+
  labs(x = "Market",
       y = "Average Price (IDR)", fill = "")+
  theme(axis.text = element_text(colour = "navyblue"),
        plot.title = element_text(hjust = 0.5))+
  facet_wrap(~commodity)

Kentang (sedang)

market_clean %>% 
  group_by(market, commodity) %>% 
  summarise(mean_price = mean(price)) %>%
  arrange(mean_price) %>% 
  filter(commodity == "Kentang (sedang)") %>% 
ggplot(aes(x = market, y = mean_price))+
  geom_segment( aes(x=reorder(market, mean_price) ,xend=market, y=0, yend=mean_price))+
  geom_point(size=3, color="steelblue")+
  coord_flip()+
  scale_y_continuous(labels = scales::comma)+
  ggtitle("Average Price by Commodity")+
  labs(x = "Market",
       y = "Average Price (IDR)", fill = "")+
  theme(axis.text = element_text(colour = "navyblue"),
        plot.title = element_text(hjust = 0.5))+
  facet_wrap(~commodity)

Tomat Buah

market_clean %>% 
  group_by(market, commodity) %>% 
  summarise(mean_price = mean(price)) %>%
  arrange(mean_price) %>% 
  filter(commodity == "Tomat Buah") %>% 
ggplot(aes(x = market, y = mean_price))+
  geom_segment( aes(x=reorder(market, mean_price) ,xend=market, y=0, yend=mean_price))+
  geom_point(size=3, color="steelblue")+
  coord_flip()+
  scale_y_continuous(labels = scales::comma)+
  ggtitle("Average Price by Commodity")+
  labs(x = "Market",
       y = "Average Price (IDR)", fill = "")+
  theme_minimal()+
  theme(axis.text = element_text(colour = "navyblue"),
        plot.title = element_text(hjust = 0.5))+
  facet_wrap(~commodity)

Berdasarkan visualisasi rata-rata harga sayuran per lokasi pasar di daerah DKI Jakarta, Pasar Mayestik yang berlokasi di daerah Jakarta Selatan memiliki harga rata-rata tertinggi untuk sayuran cabe rawit merah, cabe rawit hijau, bawang merah, bawang putih dan tomat buah. Untuk harga rata-rata tertinggi sayuran cabe merah keriting dan kentang berlokasi di Pasar Pluit dan Pasar Jembatan Merah.

Market Location in DKI Jakarta

#create icon for leaflet
icons <- 
  awesomeIcons(icon = "map-pin",
                      iconColor = "red",
                      markerColor = "black",
                      library = "fa")

#create market popup name
name <- unique(market$market)

Berikut peta persebaran lokasi 43 pasar yang ada di daerah DKI Jakarta.

market_clean %>% 
  group_by(market) %>% 
  summarise(latitude = mean(latitude),
            longitude = mean(longitude)) %>% 
leaflet() %>% 
  addTiles() %>% 
  addMarkers(lng = ~longitude, 
             lat = ~latitude, 
             popup = name, 
             clusterOptions = markerClusterOptions())

Number of Market per Inner City

unique(market_clean$commodity)

## [1] Cabe Merah Keriting Cabe Rawit Merah    Cabe Rawit Hijau   
## [4] Bawang Merah        Bawang Putih        Kentang (sedang)   
## [7] Tomat Buah         
## 7 Levels: Bawang Merah Bawang Putih Cabe Merah Keriting ... Tomat Buah

market_clean %>% 
  group_by(city, market) %>% 
  summarise(n = mean(longitude)) %>% 
  select(-n) %>% 
  group_by(city) %>% 
  tally() %>% 
ggplot(aes(x = reorder(city, n), y = n))+
  geom_bar(stat = "identity", aes(fill=city))+
  labs(x = "Inner City",
       y = "Number of Market")+
  theme(legend.position = "none")+
  coord_flip()

Daerah Jakarta Selatan dan Jakarta Pusat memiliki jumlah pasar tradisional terbanyak di bandingkan dengan 3 daerah lain nya di DKI Jakarta.

City Visualization

Cabe Merah Keriting

city_clean %>%
  group_by(market, commodity) %>% 
  summarise(mean_price = mean(price)) %>%
  arrange(mean_price) %>% 
  filter(commodity == "Cabe Merah Keriting") %>% 
  arrange(mean_price) %>% 
  ggplot(aes(x=reorder(market, mean_price), y=mean_price)) + 
  geom_bar(stat = "identity", aes(fill = mean_price))+
  coord_flip()+
  scale_y_continuous(labels = scales::comma)+
  ggtitle("Cabe Merah Keriting")+
  theme(legend.position = "none")+
  labs(x = "Market Location",
       y = "Average Price (IDR)", fill = "")

Cabe Rawit Merah

city_clean %>%
  group_by(market, commodity) %>% 
  summarise(mean_price = mean(price)) %>%
  arrange(mean_price) %>% 
  filter(commodity == "Cabe Rawit Merah") %>% 
  arrange(mean_price) %>% 
  ggplot(aes(x=reorder(market, mean_price), y=mean_price)) + 
  geom_bar(stat = "identity", aes(fill = mean_price))+
  coord_flip()+
  scale_y_continuous(labels = scales::comma)+
  ggtitle("Cabe Rawit Merah")+
  theme(legend.position = "none")+
  labs(x = "Market Location",
       y = "Average Price (IDR)", fill = "")

Cabe Rawit Hijau

city_clean %>%
  group_by(market, commodity) %>% 
  summarise(mean_price = mean(price)) %>%
  arrange(mean_price) %>% 
  filter(commodity == "Cabe Rawit Hijau") %>% 
  arrange(mean_price) %>% 
  ggplot(aes(x=reorder(market, mean_price), y=mean_price)) + 
  geom_bar(stat = "identity", aes(fill = mean_price))+
  coord_flip()+
  scale_y_continuous(labels = scales::comma)+
  theme(legend.position = "none")+
  ggtitle("Cabe Rawit Hijau")+
  labs(x = "Market Location",
       y = "Average Price (IDR)", fill = "")

Bawang Merah

city_clean %>%
  group_by(market, commodity) %>% 
  summarise(mean_price = mean(price)) %>%
  arrange(mean_price) %>% 
  filter(commodity == "Bawang Merah") %>% 
  arrange(mean_price) %>% 
  ggplot(aes(x=reorder(market, mean_price), y=mean_price)) + 
  geom_bar(stat = "identity", aes(fill = mean_price))+
  coord_flip()+
  scale_y_continuous(labels = scales::comma)+
  theme(legend.position = "none")+
  ggtitle("Bawang Merah")+
  labs(x = "Market Location",
       y = "Average Price (IDR)", fill = "")

Bawang Putih

city_clean %>%
  group_by(market, commodity) %>% 
  summarise(mean_price = mean(price)) %>%
  arrange(mean_price) %>% 
  filter(commodity == "Bawang Putih") %>% 
  arrange(mean_price) %>% 
  ggplot(aes(x=reorder(market, mean_price), y=mean_price)) + 
  geom_bar(stat = "identity", aes(fill = mean_price))+
  coord_flip()+
  scale_y_continuous(labels = scales::comma)+
  theme(legend.position = "none")+
  ggtitle("Bawang Putih")+
  labs(x = "Market Location",
       y = "Average Price (IDR)", fill = "")

Kentang (sedang)

city_clean %>%
  group_by(market, commodity) %>% 
  summarise(mean_price = mean(price)) %>%
  arrange(mean_price) %>% 
  filter(commodity == "Kentang (sedang)") %>% 
  arrange(mean_price) %>% 
  ggplot(aes(x=reorder(market, mean_price), y=mean_price)) + 
  geom_bar(stat = "identity", aes(fill = mean_price))+
  coord_flip()+
  scale_y_continuous(labels = scales::comma)+
  theme(legend.position = "none")+
  ggtitle("Kentang (sedang)")+
  labs(x = "Market Location",
       y = "Average Price (IDR)", fill = "")

Tomat Buah

city_clean %>%
  group_by(market, commodity) %>% 
  summarise(mean_price = mean(price)) %>%
  arrange(mean_price) %>% 
  filter(commodity == "Tomat Buah") %>% 
  arrange(mean_price) %>% 
  ggplot(aes(x=reorder(market, mean_price), y=mean_price)) + 
  geom_bar(stat = "identity", aes(fill = mean_price))+
  coord_flip()+
  scale_y_continuous(labels = scales::comma)+
  theme(legend.position = "none")+
  ggtitle("Tomat Buah")+
  labs(x = "Market Location",
       y = "Average Price (IDR)", fill = "")

Berdasarkan rata-rata harga per daerah bagian DKI Jakarta, harga rata-rata tertinggi dari cabe rawit merah, cabe rawit hijau, bawang merah, kentang dan tomat buah berlokasi di Jakarta Selatan. Untuk bawang putih dan cabe merah keriting harga rata-rata tertinggi berlokasi di Jakarta Utara.

Daily Price Visualization

Cabe Merah Keriting

city_clean %>%
  filter(commodity == "Cabe Merah Keriting") %>% 
  arrange(price) %>% 
  ggplot(aes(x = date, y = price, color = market))+
  geom_point(size = 0.1)+
  geom_line()+
  scale_x_date(date_breaks = "4 month",
             date_labels = "%B")+
  scale_y_continuous(labels = scales::comma)+
  ggtitle("Cabe Merah Keriting")+
  labs(x = "Date",
       y = "Price")+
  theme(legend.position = "none",
        plot.title = element_text(hjust = 0.5),
        axis.text.x = element_text(angle = 35, hjust = 1))+
  facet_wrap(~market)

Harga Cabe Merah Keriting mengalami kenaikan di awal tahun 2020 lalu turun secara signifikan dan mencapai titik terendah di bulan Agustus 2020. Mendekati akhir tahun 2020, harga kembali melambung naik

Cabe Rawit Merah

city_clean %>%
  filter(commodity == "Cabe Rawit Merah") %>% 
  arrange(price) %>% 
  ggplot(aes(x = date, y = price, color = market))+
  geom_point(size = 0.1)+
  geom_line()+
  scale_x_date(date_breaks = "4 month",
             date_labels = "%B")+
  scale_y_continuous(labels = scales::comma)+
  ggtitle("Cabe Rawit Merah")+
  labs(x = "Date",
       y = "Price")+
  theme(legend.position = "none",
        plot.title = element_text(hjust = 0.5),
        axis.text.x = element_text(angle = 35, hjust = 1))+
  facet_wrap(~market)

Cabe Rawit Hijau

city_clean %>%
  filter(commodity == "Cabe Rawit Hijau") %>% 
  arrange(price) %>% 
  ggplot(aes(x = date, y = price, color = market))+
  geom_point(size = 0.1)+
  geom_line()+
  scale_x_date(date_breaks = "4 month",
             date_labels = "%B")+
  scale_y_continuous(labels = scales::comma)+
  ggtitle("Cabe Rawit Hijau")+
  labs(x = "Date",
       y = "Price")+
  theme(legend.position = "none",
        plot.title = element_text(hjust = 0.5),
        axis.text.x = element_text(angle = 35, hjust = 1))+
  facet_wrap(~market)

Bawang Merah

city_clean %>%
  filter(commodity == "Bawang Merah") %>% 
  arrange(price) %>% 
  ggplot(aes(x = date, y = price, color = market))+
  geom_point(size = 0.1)+
  geom_line()+
  scale_x_date(date_breaks = "4 month",
             date_labels = "%B")+
  scale_y_continuous(labels = scales::comma)+
  ggtitle("Bawang Merah")+
  labs(x = "Date",
       y = "Price")+
  theme(legend.position = "none",
        plot.title = element_text(hjust = 0.5),
        axis.text.x = element_text(angle = 35, hjust = 1))+
  facet_wrap(~market)

Bawang Putih

city_clean %>%
  filter(commodity == "Bawang Putih") %>% 
  arrange(price) %>% 
  ggplot(aes(x = date, y = price, color = market))+
  geom_point(size = 0.1)+
  geom_line()+
  scale_x_date(date_breaks = "4 month",
             date_labels = "%B")+
  scale_y_continuous(labels = scales::comma)+
  ggtitle("Bawang Putih")+
  labs(x = "Date",
       y = "Price")+
  theme(legend.position = "none",
        plot.title = element_text(hjust = 0.5),
        axis.text.x = element_text(angle = 35, hjust = 1))+
  facet_wrap(~market)

Kentang (sedang)

city_clean %>%
  filter(commodity == "Kentang (sedang)") %>% 
  arrange(price) %>% 
  ggplot(aes(x = date, y = price, color = market))+
  geom_point(size = 0.1)+
  geom_line()+
  scale_x_date(date_breaks = "4 month",
             date_labels = "%B")+
  scale_y_continuous(labels = scales::comma)+
  ggtitle("Kentang (sedang)")+
  labs(x = "Date",
       y = "Price")+
  theme(legend.position = "none",
        plot.title = element_text(hjust = 0.5),
        axis.text.x = element_text(angle = 35, hjust = 1))+
  facet_wrap(~market)

Tomat Buah

city_clean %>%
  filter(commodity == "Tomat Buah") %>% 
  arrange(price) %>% 
  ggplot(aes(x = date, y = price, color = market))+
  geom_point(size = 0.1)+
  geom_line()+
  scale_x_date(date_breaks = "4 month",
             date_labels = "%B")+
  scale_y_continuous(labels = scales::comma)+
  ggtitle("Tomat Buah")+
  labs(x = "Date",
       y = "Price")+
  theme(legend.position = "none",
        plot.title = element_text(hjust = 0.5),
        axis.text.x = element_text(angle = 35, hjust = 1))+
  facet_wrap(~market)

Average Price per Inner City

Read data GADM

library(rgdal)
gadm <- readOGR(dsn = "GDAM/gadm36_IDN_shp", layer = "gadm36_IDN_2")

## OGR data source with driver: ESRI Shapefile 
## Source: "C:\Users\Terap\Documents\Algoritma\DCD\Pubs\GDAM\gadm36_IDN_shp", layer: "gadm36_IDN_2"
## with 502 features
## It has 13 fields

gadm <- gadm[gadm$NAME_1 == "Jakarta Raya",]

gadm_sf <- sf::st_as_sf(gadm)

Bawang Merah

city_bm <- 
  city_clean %>% 
  filter(commodity == "Bawang Merah") %>% 
  group_by(market, commodity) %>% 
  summarise(price = mean(price))

gadm_bm <- 
gadm_sf %>% 
  left_join(city_bm, by = c("NAME_2"="market"))

mybin_bm <- (fivenum(city_bm$price))

mypalette_bm <- colorBin(palette = "Spectral", domain = gadm_bm, na.color = "transparent", bins = mybin_bm)

mytext_bm <- paste(
  
  gadm_bm$TYPE_2," ", gadm_bm$NAME_2, "<br/>",
  "Commodity ", gadm_bm$commodity, "<br/>",
  "Average Price IDR ", scales::comma(round(gadm_bm$price,0)), "<br/>",
  sep = "") %>% 
  lapply(htmltools::HTML)

leaflet(gadm_bm) %>%
  addProviderTiles(providers$CartoDB.DarkMatter) %>%
  addPolygons(
    fillColor = ~ mypalette_bm(gadm_bm$price),
    weight = 1,
    opacity = 1,
    color = "white",
    dashArray = "2",
    fillOpacity = 0.7,
    label = mytext_bm,
    labelOptions = labelOptions(
      style = list("font-weight" = "normal", padding = "3px 8px"),
      textsize = "13px",
      direction = "auto"
    )
  ) %>% 
  addLegend("bottomleft", 
            pal = mypalette_bm,
            values = ~gadm_bm$price,
            title = "Average Price",
            labFormat = labelFormat(),
            opacity = 1)

Bawang Putih

city_bp <- 
  city_clean %>% 
  filter(commodity == "Bawang Putih") %>% 
  group_by(market, commodity) %>% 
  summarise(price = mean(price))

gadm_bp <- 
gadm_sf %>% 
  left_join(city_bp, by = c("NAME_2"="market"))

mybin_bp <-  (fivenum(city_bp$price))

mypalette_bp <- colorBin(palette = "Spectral", domain = gadm_bp, na.color = "transparent", bins = mybin_bp)

mytext_bp <- paste(
  
  gadm_bp$TYPE_2," ", gadm_bp$NAME_2, "<br/>",
  "Commodity ", gadm_bp$commodity, "<br/>",
  "Average Price IDR ", scales::comma(round(gadm_bp$price,0)), "<br/>",
  sep = "") %>% 
  lapply(htmltools::HTML)

leaflet(gadm_bp) %>%
  addProviderTiles(providers$CartoDB.DarkMatter) %>%
  addPolygons(
    fillColor = ~ mypalette_bp(gadm_bp$price),
    weight = 1,
    opacity = 1,
    color = "white",
    dashArray = "2",
    fillOpacity = 0.7,
    label = mytext_bp,
    labelOptions = labelOptions(
      style = list("font-weight" = "normal", padding = "3px 8px"),
      textsize = "13px",
      direction = "auto"
    )
  ) %>% 
  addLegend("bottomleft", 
            pal = mypalette_bp,
            values = ~gadm_bp$price,
            title = "Average Price",
            labFormat = labelFormat(),
            opacity = 1)

Cabe Merah Keriting

city_cmk <- 
  city_clean %>% 
  filter(commodity == "Cabe Merah Keriting") %>% 
  group_by(market, commodity) %>% 
  summarise(price = mean(price))

gadm_cmk <- 
gadm_sf %>% 
  left_join(city_cmk, by = c("NAME_2"="market"))

mybin_cmk <-  (fivenum(city_cmk$price))

mypalette_cmk <- colorBin(palette = "Spectral", domain = gadm_cmk, na.color = "transparent", bins = mybin_cmk)

mytext_cmk <- paste(
  
  gadm_cmk$TYPE_2," ", gadm_cmk$NAME_2, "<br/>",
  "Commodity ", gadm_cmk$commodity, "<br/>",
  "Average Price IDR ", scales::comma(round(gadm_cmk$price,0)), "<br/>",
  sep = "") %>% 
  lapply(htmltools::HTML)

leaflet(gadm_cmk) %>%
  addProviderTiles(providers$CartoDB.DarkMatter) %>%
  addPolygons(
    fillColor = ~ mypalette_cmk(gadm_cmk$price),
    weight = 1,
    opacity = 1,
    color = "white",
    dashArray = "2",
    fillOpacity = 0.7,
    label = mytext_cmk,
    labelOptions = labelOptions(
      style = list("font-weight" = "normal", padding = "3px 8px"),
      textsize = "13px",
      direction = "auto"
    )
  ) %>% 
  addLegend("bottomleft", 
            pal = mypalette_cmk,
            values = ~gadm_cmk$price,
            title = "Average Price",
            labFormat = labelFormat(),
            opacity = 1)

Cabe Rawit Merah

city_crm <- 
  city_clean %>% 
  filter(commodity == "Cabe Rawit Merah") %>% 
  group_by(market, commodity) %>% 
  summarise(price = mean(price))

gadm_crm <- 
gadm_sf %>% 
  left_join(city_crm, by = c("NAME_2"="market"))

mybin_crm <-  (fivenum(city_crm$price))

mypalette_crm <- colorBin(palette = "Spectral", domain = gadm_crm, na.color = "transparent", bins = mybin_crm)

mytext_crm <- paste(
  
  gadm_crm$TYPE_2," ", gadm_crm$NAME_2, "<br/>",
  "Commodity ", gadm_crm$commodity, "<br/>",
  "Average Price IDR ", scales::comma(round(gadm_crm$price,0)), "<br/>",
  sep = "") %>% 
  lapply(htmltools::HTML)

leaflet(gadm_crm) %>%
  addProviderTiles(providers$CartoDB.DarkMatter) %>%
  addPolygons(
    fillColor = ~ mypalette_crm(gadm_crm$price),
    weight = 1,
    opacity = 1,
    color = "white",
    dashArray = "2",
    fillOpacity = 0.7,
    label = mytext_crm,
    labelOptions = labelOptions(
      style = list("font-weight" = "normal", padding = "3px 8px"),
      textsize = "13px",
      direction = "auto"
    )
  ) %>% 
  addLegend("bottomleft", 
            pal = mypalette_crm,
            values = ~gadm_crm$price,
            title = "Average Price",
            labFormat = labelFormat(),
            opacity = 1)

Cabe Rawit Hijau

city_crh <- 
  city_clean %>% 
  filter(commodity == "Cabe Rawit Hijau") %>% 
  group_by(market, commodity) %>% 
  summarise(price = mean(price))

gadm_crh <- 
gadm_sf %>% 
  left_join(city_crh, by = c("NAME_2"="market"))

mybin_crh <-  (fivenum(city_crh$price))

mypalette_crh <- colorBin(palette = "Spectral", domain = gadm_crh, na.color = "transparent", bins = mybin_crh)

mytext_crh <- paste(
  
  gadm_crh$TYPE_2," ", gadm_crh$NAME_2, "<br/>",
  "Commodity ", gadm_crh$commodity, "<br/>",
  "Average Price IDR ", scales::comma(round(gadm_crh$price,0)), "<br/>",
  sep = "") %>% 
  lapply(htmltools::HTML)

leaflet(gadm_crh) %>%
  addProviderTiles(providers$CartoDB.DarkMatter) %>%
  addPolygons(
    fillColor = ~ mypalette_crh(gadm_crh$price),
    weight = 1,
    opacity = 1,
    color = "white",
    dashArray = "2",
    fillOpacity = 0.7,
    label = mytext_crh,
    labelOptions = labelOptions(
      style = list("font-weight" = "normal", padding = "3px 8px"),
      textsize = "13px",
      direction = "auto"
    )
  ) %>% 
  addLegend("bottomleft", 
            pal = mypalette_crh,
            values = ~gadm_crh$price,
            title = "Average Price",
            labFormat = labelFormat(),
            opacity = 1)

Kentang (sedang)

city_k <- 
  city_clean %>% 
  filter(commodity == "Kentang (sedang)") %>% 
  group_by(market, commodity) %>% 
  summarise(price = mean(price))

gadm_k <- 
gadm_sf %>% 
  left_join(city_k, by = c("NAME_2"="market"))

mybin_k <- (fivenum(city_k$price))

mypalette_k <- colorBin(palette = "Spectral", domain = gadm_k, na.color = "transparent", bins = mybin_k)

mytext_k <- paste(
  
  gadm_k$TYPE_2," ", gadm_k$NAME_2, "<br/>",
  "Commodity ", gadm_k$commodity, "<br/>",
  "Average Price IDR ", scales::comma(round(gadm_k$price,0)), "<br/>",
  sep = "") %>% 
  lapply(htmltools::HTML)

leaflet(gadm_k) %>%
  addProviderTiles(providers$CartoDB.DarkMatter) %>%
  addPolygons(
    fillColor = ~ mypalette_k(gadm_k$price),
    weight = 1,
    opacity = 1,
    color = "white",
    dashArray = "2",
    fillOpacity = 0.7,
    label = mytext_k,
    labelOptions = labelOptions(
      style = list("font-weight" = "normal", padding = "3px 8px"),
      textsize = "13px",
      direction = "auto"
    )
  ) %>% 
  addLegend("bottomleft", 
            pal = mypalette_k,
            values = ~gadm_k$price,
            title = "Average Price",
            labFormat = labelFormat(),
            opacity = 1)

Tomat Buah

city_tb <- 
  city_clean %>% 
  filter(commodity == "Kentang (sedang)") %>% 
  group_by(market, commodity) %>% 
  summarise(price = mean(price))

gadm_tb <- 
gadm_sf %>% 
  left_join(city_tb, by = c("NAME_2"="market"))

mybin_tb <-  (fivenum(city_tb$price))

mypalette_tb <- colorBin(palette = "Spectral", domain = gadm_tb, na.color = "transparent", bins = mybin_tb)

mytext_tb <- paste(
  
  gadm_tb$TYPE_2," ", gadm_tb$NAME_2, "<br/>",
  "Commodity ", gadm_tb$commodity, "<br/>",
  "Average Price IDR ", scales::comma(round(gadm_tb$price,0)), "<br/>",
  sep = "") %>% 
  lapply(htmltools::HTML)

leaflet(gadm_tb) %>%
  addProviderTiles(providers$CartoDB.DarkMatter) %>%
  addPolygons(
    fillColor = ~ mypalette_tb(gadm_tb$price),
    weight = 1,
    opacity = 1,
    color = "white",
    dashArray = "2",
    fillOpacity = 0.7,
    label = mytext_tb,
    labelOptions = labelOptions(
      style = list("font-weight" = "normal", padding = "3px 8px"),
      textsize = "13px",
      direction = "auto"
    )
  ) %>% 
  addLegend("bottomleft", 
            pal = mypalette_tb,
            values = ~gadm_tb$price,
            title = "Average Price",
            labFormat = labelFormat(),
            opacity = 1)

Inflation Visualization

inflasi %>%
  mutate(periode = lubridate::my(Periode)) %>% 
  ggplot(aes(x = periode, y = Inflasi))+
  geom_point()+
  geom_line(color = "red")+
  scale_x_date(date_breaks = "2 month",
             date_labels = "%B %Y")+
  ggtitle("Inflation Rate")+
  labs(x = "Month",
       y = "Inflation Rate")+
  theme(legend.position = "none",
        plot.title = element_text(hjust = 0.5),
        axis.text.x = element_text(angle = 50, hjust = 1))

Berdasarkan visualisasi dari data inflasi, terdapat penurunan yang cukup significant dari awal tahun 2020, tepatnya dari bulan Maret sampai dengan titik terendah di bulan Agustus 2020. Pada pertengahan tahun 2021, inflasi mulai meningkat lagi sampai dengan January 2022.

Visualization TS Object

city_list <-
  city_clean %>%
  select(-date) %>% 
  unite("series", market, commodity, sep = "_") %>% 
  nest(-series)

seasonal <- list(weekly = function(x) ts(x, frequency = 7))

list_crossing <- crossing(city_list, seasonal)

ts <- list_crossing$data %>%  
map2(.y = list_crossing$seasonal,
     .f = ~exec(.y, .x))

Bawang Merah

Jakarta Barat

ts[[1]] %>%
  decompose() %>% 
  autoplot()+
  labs(subtitle = list_crossing$series[1],
       y = "Price", x  = NULL)

Jakarta Pusat

ts[[8]] %>%
  decompose() %>% 
  autoplot()+
  labs(subtitle = list_crossing$series[8],
       y = "Price", x  = NULL)

Jakarta Selatan

ts[[15]] %>%
  decompose() %>% 
  autoplot()+
  labs(subtitle = list_crossing$series[15],
       y = "Price", x  = NULL)

Jakarta Timur

ts[[22]] %>%
  decompose() %>% 
  autoplot()+
  labs(subtitle = list_crossing$series[22],
       y = "Price", x  = NULL)

Jakarta Utara

ts[[29]] %>%
  decompose() %>% 
  autoplot()+
  labs(subtitle = list_crossing$series[29],
       y = "Price", x  = NULL)

Bawang Putih

Jakarta Barat

ts[[2]] %>%
  decompose() %>% 
  autoplot()+
  labs(subtitle = list_crossing$series[2],
       y = "Price", x  = NULL)

Jakarta Pusat

ts[[9]] %>%
  decompose() %>% 
  autoplot()+
  labs(subtitle = list_crossing$series[9],
       y = "Price", x  = NULL)

Jakarta Selatan

ts[[16]] %>%
  decompose() %>% 
  autoplot()+
  labs(subtitle = list_crossing$series[16],
       y = "Price", x  = NULL)

Jakarta Timur

ts[[23]] %>%
  decompose() %>% 
  autoplot()+
  labs(subtitle = list_crossing$series[23],
       y = "Price", x  = NULL)

Jakarta Utara

ts[[30]] %>%
  decompose() %>% 
  autoplot()+
  labs(subtitle = list_crossing$series[30],
       y = "Price", x  = NULL)

Cabe Merah Keriting

Jakarta Barat

ts[[3]] %>%
  decompose() %>% 
  autoplot()+
  labs(subtitle = list_crossing$series[3],
       y = "Price", x  = NULL)

Jakarta Pusat

ts[[10]] %>%
  decompose() %>% 
  autoplot()+
  labs(subtitle = list_crossing$series[10],
       y = "Price", x  = NULL)

Jakarta Selatan

ts[[17]] %>%
  decompose() %>% 
  autoplot()+
  labs(subtitle = list_crossing$series[17],
       y = "Price", x  = NULL)

Jakarta Timur

ts[[24]] %>%
  decompose() %>% 
  autoplot()+
  labs(subtitle = list_crossing$series[24],
       y = "Price", x  = NULL)

Jakarta Utara

ts[[31]] %>%
  decompose() %>% 
  autoplot()+
  labs(subtitle = list_crossing$series[31],
       y = "Price", x  = NULL)

Cabe Merah Keriting

Jakarta Barat

ts[[4]] %>%
  decompose() %>% 
  autoplot()+
  labs(subtitle = list_crossing$series[4],
       y = "Price", x  = NULL)

Jakarta Pusat

ts[[11]] %>%
  decompose() %>% 
  autoplot()+
  labs(subtitle = list_crossing$series[11],
       y = "Price", x  = NULL)

Jakarta Selatan

ts[[18]] %>%
  decompose() %>% 
  autoplot()+
  labs(subtitle = list_crossing$series[18],
       y = "Price", x  = NULL)

Jakarta Timur

ts[[25]] %>%
  decompose() %>% 
  autoplot()+
  labs(subtitle = list_crossing$series[25],
       y = "Price", x  = NULL)

Jakarta Utara

ts[[32]] %>%
  decompose() %>% 
  autoplot()+
  labs(subtitle = list_crossing$series[32],
       y = "Price", x  = NULL)

Cabe Rawit Merah

Jakarta Barat

ts[[5]] %>%
  decompose() %>% 
  autoplot()+
  labs(subtitle = list_crossing$series[5],
       y = "Price", x  = NULL)

Jakarta Pusat

ts[[12]] %>%
  decompose() %>% 
  autoplot()+
  labs(subtitle = list_crossing$series[12],
       y = "Price", x  = NULL)

Jakarta Selatan

ts[[19]] %>%
  decompose() %>% 
  autoplot()+
  labs(subtitle = list_crossing$series[19],
       y = "Price", x  = NULL)

Jakarta Timur

ts[[26]] %>%
  decompose() %>% 
  autoplot()+
  labs(subtitle = list_crossing$series[26],
       y = "Price", x  = NULL)

Jakarta Utara

ts[[33]] %>%
  decompose() %>% 
  autoplot()+
  labs(subtitle = list_crossing$series[33],
       y = "Price", x  = NULL)

Kentang Sedang

Jakarta Barat

ts[[6]] %>%
  decompose() %>% 
  autoplot()+
  labs(subtitle = list_crossing$series[6],
       y = "Price", x  = NULL)

Jakarta Pusat

ts[[13]] %>%
  decompose() %>% 
  autoplot()+
  labs(subtitle = list_crossing$series[13],
       y = "Price", x  = NULL)

Jakarta Selatan

ts[[20]] %>%
  decompose() %>% 
  autoplot()+
  labs(subtitle = list_crossing$series[20],
       y = "Price", x  = NULL)

Jakarta Timur

ts[[27]] %>%
  decompose() %>% 
  autoplot()+
  labs(subtitle = list_crossing$series[27],
       y = "Price", x  = NULL)

Jakarta Utara

ts[[34]] %>%
  decompose() %>% 
  autoplot()+
  labs(subtitle = list_crossing$series[34],
       y = "Price", x  = NULL)

Tomat Buah

Jakarta Barat

ts[[7]] %>%
  decompose() %>% 
  autoplot()+
  labs(subtitle = list_crossing$series[7],
       y = "Price", x  = NULL)

Jakarta Pusat

ts[[14]] %>%
  decompose() %>% 
  autoplot()+
  labs(subtitle = list_crossing$series[14],
       y = "Price", x  = NULL)

Jakarta Selatan

ts[[21]] %>%
  decompose() %>% 
  autoplot()+
  labs(subtitle = list_crossing$series[21],
       y = "Price", x  = NULL)

Jakarta Timur

ts[[28]] %>%
  decompose() %>% 
  autoplot()+
  labs(subtitle = list_crossing$series[28],
       y = "Price", x  = NULL)

Jakarta Utara

ts[[35]] %>%
  decompose() %>% 
  autoplot()+
  labs(subtitle = list_crossing$series[35],
       y = "Price", x  = NULL)

DCD - Tera Putera

Tera Putera

2/2/2022

Problem Research

Background Project

Business Impact

User & Benefit

Implementation to other business

Output

Library

Read and Clean Dataset

Market

City

Inflation

Visualization EDA

Market Visualization

Cabe Merah Keriting

Cabe Rawit Merah

Cabe Rawit Hijau

Bawang Merah

Bawang Putih

Kentang (sedang)

Tomat Buah

Market Location in DKI Jakarta

Number of Market per Inner City

City Visualization

Cabe Merah Keriting

Cabe Rawit Merah

Cabe Rawit Hijau

Bawang Merah

Bawang Putih

Kentang (sedang)

Tomat Buah

Daily Price Visualization

Cabe Merah Keriting

Cabe Rawit Merah

Cabe Rawit Hijau

Bawang Merah

Bawang Putih

Kentang (sedang)

Tomat Buah

Average Price per Inner City

Bawang Merah

Bawang Putih

Cabe Merah Keriting

Cabe Rawit Merah

Cabe Rawit Hijau

Kentang (sedang)

Tomat Buah

Inflation Visualization

Visualization TS Object

Bawang Merah

Jakarta Barat

Jakarta Pusat

Jakarta Selatan

Jakarta Timur

Jakarta Utara

Bawang Putih

Jakarta Barat

Jakarta Pusat

Jakarta Selatan

Jakarta Timur

Jakarta Utara

Cabe Merah Keriting

Jakarta Barat

Jakarta Pusat

Jakarta Selatan

Jakarta Timur

Jakarta Utara

Cabe Merah Keriting

Jakarta Barat

Jakarta Pusat

Jakarta Selatan

Jakarta Timur

Jakarta Utara

Cabe Rawit Merah

Jakarta Barat

Jakarta Pusat

Jakarta Selatan

Jakarta Timur