# 変数の消去
rm(list = ls())

# パッケージ　`pacman`を使って必要なパッケージをインストール
if(!require("pacman")) install.packages("pacman")
##  要求されたパッケージ pacman をロード中です
pacman::p_load("tidyverse", 
               "skimr")

# 表示を科学表示から変更
 options(scipen = 999)
library(readr)
readLines("C:/Users/01102/OneDrive/デスクトップ/データ３/tairyo_navi_Flounder_teaching2023.csv", n = 5)
## [1] "Landing_Date,Market,Gear_Type,Species,Standard,Landing_Amount,Landing_Price,Highest_Price,Average_Price,Lowest_Price"
## [2] "2004-04-03,八木,底刺網,ヒラメ,活魚,1.2,3120,2600,2600,2600"                                                          
## [3] "1994-07-05,大槌,小延縄,ヒラメ,活魚,41.6,46011,1869,1106.03,820"                                                      
## [4] "2001-08-13,久慈,底刺網,ヒラメ,活魚,470,596807,2760,1269.8,1090"                                                      
## [5] "2017-07-12,大船渡,定置網,ヒラメ,山,3.5,1250,0,357.14,0"
market_data_raw <- 
      readr::read_csv("C:/Users/01102/OneDrive/デスクトップ/データ３/tairyo_navi_Flounder_teaching2023.csv")
## Rows: 1937 Columns: 10
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr  (4): Market, Gear_Type, Species, Standard
## dbl  (5): Landing_Amount, Landing_Price, Highest_Price, Average_Price, Lowes...
## date (1): Landing_Date
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
skimr::skim(market_data_raw)
Data summary
Name market_data_raw
Number of rows 1937
Number of columns 10
_______________________
Column type frequency:
character 4
Date 1
numeric 5
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
Market 0 1 2 3 0 14 0
Gear_Type 0 1 2 6 0 11 0
Species 0 1 3 3 0 1 0
Standard 0 1 1 2 0 4 0

Variable type: Date

skim_variable n_missing complete_rate min max median n_unique
Landing_Date 0 1 1994-06-20 2021-09-03 2007-10-06 1675

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
Landing_Amount 0 1 17.62 44.69 -7 1.8 5.50 17.00 836.30 ▇▁▁▁▁
Landing_Price 0 1 19936.37 55647.62 -11188 1971.0 6491.00 21850.00 1842700.00 ▇▁▁▁▁
Highest_Price 0 1 1758.92 1316.78 0 860.0 1500.00 2420.00 10000.00 ▇▃▁▁▁
Average_Price 0 1 1341.93 1348.62 0 700.0 1092.81 1696.03 43873.81 ▇▁▁▁▁
Lowest_Price 0 1 801.69 845.92 0 300.0 600.00 1000.00 8500.00 ▇▁▁▁▁ 
library(readxl)
readxl::excel_sheets("C:/Users/01102/OneDrive/デスクトップ/データ３/tairyo_navi_Flounder_teaching.xlsx")
## [1] "data_2" "data_1"
market_data_raw_xls <- readxl::read_excel("C:/Users/01102/OneDrive/デスクトップ/データ３/tairyo_navi_Flounder_teaching.xlsx")
skimr::skim(market_data_raw_xls)
Data summary
Name market_data_raw_xls
Number of rows 1
Number of columns 1
_______________________
Column type frequency:
character 1
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
テスト 0 1 3 3 0 1 0 
market_data_raw_xls <- readxl::read_excel("C:/Users/01102/OneDrive/デスクトップ/データ３/tairyo_navi_Flounder_teaching.xlsx", sheet = "data_1")
skimr::skim(market_data_raw_xls)
Data summary
Name market_data_raw_xls
Number of rows 193738
Number of columns 10
_______________________
Column type frequency:
character 4
numeric 5
POSIXct 1
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
Market 0 1 2 3 0 14 0
Gear_Type 0 1 2 10 0 23 0
Species 0 1 2 3 0 3 0
Standard 0 1 1 2 0 8 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
Landing_Amount 0 1 18.75 44.28 -58.40 1.80 5.6 18.00 4181.8 ▇▁▁▁▁
Landing_Price 0 1 19843.10 37140.40 -101196.00 1901.00 6760.0 21780.00 1992600.0 ▇▁▁▁▁
Highest_Price 0 1 1736.06 1312.04 0.00 800.00 1500.0 2400.00 15800.0 ▇▁▁▁▁
Average_Price 0 1 1304.34 1045.87 -5197.06 684.55 1075.0 1660.45 91100.0 ▇▁▁▁▁
Lowest_Price 0 1 785.80 815.32 -5000.00 300.00 580.0 1000.00 10700.0 ▁▇▂▁▁

Variable type: POSIXct

skim_variable n_missing complete_rate min max median n_unique
Landing_Date 0 1 1994-01-05 2021-09-08 2007-08-08 8233 
# 変数の消去
rm(list = ls())

# パッケージ　`pacman`を使って必要なパッケージをインストール
if(!require("pacman")) install.packages("pacman")

pacman::p_load("tidyverse", 
               "skimr", "gt")

# 表示を科学表示から変更
 options(scipen = 999)
library(skimr) # 表を作るパッケージ
market_data_raw <- 
      readr::read_csv("C:/Users/01102/OneDrive/デスクトップ/データ３/tairyo_navi_Flounder_teaching2023.csv")
## Rows: 1937 Columns: 10
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr  (4): Market, Gear_Type, Species, Standard
## dbl  (5): Landing_Amount, Landing_Price, Highest_Price, Average_Price, Lowes...
## date (1): Landing_Date
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
market_data_raw |> skimr::skim()
Data summary
Name market_data_raw
Number of rows 1937
Number of columns 10
_______________________
Column type frequency:
character 4
Date 1
numeric 5
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
Market 0 1 2 3 0 14 0
Gear_Type 0 1 2 6 0 11 0
Species 0 1 3 3 0 1 0
Standard 0 1 1 2 0 4 0

Variable type: Date

skim_variable n_missing complete_rate min max median n_unique
Landing_Date 0 1 1994-06-20 2021-09-03 2007-10-06 1675

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
Landing_Amount 0 1 17.62 44.69 -7 1.8 5.50 17.00 836.30 ▇▁▁▁▁
Landing_Price 0 1 19936.37 55647.62 -11188 1971.0 6491.00 21850.00 1842700.00 ▇▁▁▁▁
Highest_Price 0 1 1758.92 1316.78 0 860.0 1500.00 2420.00 10000.00 ▇▃▁▁▁
Average_Price 0 1 1341.93 1348.62 0 700.0 1092.81 1696.03 43873.81 ▇▁▁▁▁
Lowest_Price 0 1 801.69 845.92 0 300.0 600.00 1000.00 8500.00 ▇▁▁▁▁ 
market_data_raw |> distinct(Market)
## # A tibble: 14 × 1
##    Market
##    <chr> 
##  1 八木  
##  2 大槌  
##  3 久慈  
##  4 大船渡
##  5 宮古  
##  6 船越  
##  7 釜石  
##  8 山田  
##  9 田野畑
## 10 田老  
## 11 普代  
## 12 野田  
## 13 種市  
## 14 細浦
market_data_raw |> ggplot(aes(x = Market)) + geom_bar() +   theme(text = element_text(family = "HiraKakuPro-W3")) 
## Warning in grid.Call(C_stringMetric, as.graphicsAnnot(x$label)): Windows
## のフォントデータベースにフォントファミリが見付かりません

## Warning in grid.Call(C_stringMetric, as.graphicsAnnot(x$label)): Windows
## のフォントデータベースにフォントファミリが見付かりません
## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, :
## Windows のフォントデータベースにフォントファミリが見付かりません

## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, :
## Windows のフォントデータベースにフォントファミリが見付かりません

## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, :
## Windows のフォントデータベースにフォントファミリが見付かりません

## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, :
## Windows のフォントデータベースにフォントファミリが見付かりません

## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, :
## Windows のフォントデータベースにフォントファミリが見付かりません

## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, :
## Windows のフォントデータベースにフォントファミリが見付かりません
## Warning in grid.Call.graphics(C_text, as.graphicsAnnot(x$label), x$x, x$y, :
## Windows のフォントデータベースにフォントファミリが見付かりません

market_data_raw |> group_by(Market) |> summarize(n =n())     
## # A tibble: 14 × 2
##    Market     n
##    <chr>  <int>
##  1 久慈     265
##  2 八木     152
##  3 大槌     108
##  4 大船渡   306
##  5 宮古     307
##  6 山田     138
##  7 普代      88
##  8 田老      72
##  9 田野畑    76
## 10 種市      50
## 11 細浦       2
## 12 船越     105
## 13 野田      88
## 14 釜石     180
market_data_raw |> group_by(Species) |> summarize(n =n())     
## # A tibble: 1 × 2
##   Species     n
##   <chr>   <int>
## 1 ヒラメ   1937