RWEP/SD/20240326_5_dataimport/index.qmd

---
title: "Data import"
subtitle: 《区域水环境污染数据分析实践》<br>Data analysis practice of regional water environment pollution
author: 苏命、王为东<br>中国科学院大学资源与环境学院<br>中国科学院生态环境研究中心
date: today
lang: zh
format:
  revealjs:
    theme: dark
    slide-number: true
    chalkboard:
      buttons: true
    preview-links: auto
    lang: zh
    toc: true
    toc-depth: 1
    toc-title: 大纲
    logo: ./_extensions/inst/img/ucaslogo.png
    css: ./_extensions/inst/css/revealjs.css
    pointer:
      key: "p"
      color: "#32cd32"
      pointerSize: 18
revealjs-plugins:
  - pointer
filters:
  - d2
---


```{r}
#| echo: false
knitr::opts_chunk$set(echo = TRUE)
source("../../coding/_common.R")
library(tidyverse)
```


## 导入csv数据

```{r}
#| echo: false
#| message: false
#| comment: ""

read_lines("../../data/students.csv") |> cat(sep = "\n")
```

## 导入csv数据

```{r}
#| label: tbl-students-table
#| echo: false
#| message: false
#| tbl-cap: Data from the students.csv file as a table.

read_csv("../../data/students.csv") |>
  knitr::kable()
```

## 读取数据

```{r}
#| message: true

(students <- read_csv("../../data/students.csv"))
(students <- read_csv("https://pos.it/r4ds-students-csv"))
```


## 读取数据

```{r}
#| message: false
(students <- read_csv("../../data/students.csv", na = c("N/A", "")))
```

## 列名不要有空格

```{r}
students |> 
  rename(
    student_id = `Student ID`,
    full_name = `Full Name`
  )
```

## `janitor`处理空格

```{r}
#| message: false

students |> janitor::clean_names()
```

## `janitor`处理空格

```{r}
students |>
  janitor::clean_names() |>
  mutate(meal_plan = factor(meal_plan))
```

## `janitor`处理空格

```{r}
students <- students |>
  janitor::clean_names() |>
  mutate(
    meal_plan = factor(meal_plan),
    age = parse_number(if_else(age == "five", "5", age))
  )
students
```

## 直接录入

```{r}
read_csv(
  "a,b,c
  1,2,3
  4,5,6"
)
```

## 直接录入

```{r}
#| message: false

read_csv(
  "The first line of metadata
  The second line of metadata
  x,y,z
  1,2,3",
  skip = 2
)

read_csv(
  "# A comment I want to skip
  x,y,z
  1,2,3",
  comment = "#"
)
```

##

```{r}
#| message: false

read_csv(
  "1,2,3
  4,5,6",
  col_names = FALSE
)
```

##

```{r}
#| message: false

read_csv(
  "1,2,3
  4,5,6",
  col_names = c("x", "y", "z")
)
```

##

    ```{r}
    #| eval: false

    "x,y\n1,'a,b'"
    ```

##

    ```{r}
    #| eval: false

    read_csv("a,b\n1,2,3\n4,5,6")
    read_csv("a,b,c\n1,2\n1,2,3,4")
    read_csv("a,b\n\"1")
    read_csv("a,b\n1,2\na,b")
    read_csv("a;b\n1;3")
    ```

##

    ```{r}
    annoying <- tibble(
      `1` = 1:10,
      `2` = `1` * 2 + rnorm(length(`1`))
    )
    ```

##

```{r}
#| message: false

read_csv("
  logical,numeric,date,string
  TRUE,1,2021-01-15,abc
  false,4.5,2021-02-15,def
  T,Inf,2021-02-16,ghi
")
```

##

```{r}
simple_csv <- "
  x
  10
  .
  20
  30"
```

##

```{r}
#| message: false

read_csv(simple_csv)
```

##

```{r}
df <- read_csv(
  simple_csv, 
  col_types = list(x = col_double())
)
```

##

```{r}
problems(df)
```

##

```{r}
#| message: false

read_csv(simple_csv, na = ".")
```

##

```{r}
another_csv <- "
x,y,z
1,2,3"

read_csv(
  another_csv, 
  col_types = cols(.default = col_character())
)
```

##

```{r}
read_csv(
  another_csv,
  col_types = cols_only(x = col_character())
)
```

##

```{r}
#| message: false

sales_files <- c("../../data/01-sales.csv", "../../data/02-sales.csv", "../../data/03-sales.csv")
read_csv(sales_files, id = "file")
```

##

```{r}
#| eval: false

sales_files <- c(
  "https://pos.it/r4ds-01-sales",
  "https://pos.it/r4ds-02-sales",
  "https://pos.it/r4ds-03-sales"
)
read_csv(sales_files, id = "file")
```

##

```{r}
sales_files <- list.files("../../data", pattern = "sales\\.csv$", full.names = TRUE)
sales_files
```

##

```{r}
#| eval: false

write_csv(students, "students.csv")
```

##

```{r}
#| warning: false
#| message: false

students
write_csv(students, "students-2.csv")
read_csv("students-2.csv")
```

##

```{r}
write_rds(students, "students.rds")
read_rds("students.rds")
```

##

```{r}
#| eval: false

library(arrow)
write_parquet(students, "students.parquet")
read_parquet("students.parquet")
#> # A tibble: 6 × 5
#>   student_id full_name        favourite_food     meal_plan             age
#>        <dbl> <chr>            <chr>              <fct>               <dbl>
#> 1          1 Sunil Huffmann   Strawberry yoghurt Lunch only              4
#> 2          2 Barclay Lynn     French fries       Lunch only              5
#> 3          3 Jayendra Lyne    NA                 Breakfast and lunch     7
#> 4          4 Leon Rossini     Anchovies          Lunch only             NA
#> 5          5 Chidiegwu Dunkel Pizza              Breakfast and lunch     5
#> 6          6 Güvenç Attila    Ice cream          Lunch only              6
```

##

```{r}
#| include: false
file.remove("students-2.csv")
file.remove("students.rds")
```

##

```{r}
tibble(
  x = c(1, 2, 5), 
  y = c("h", "m", "g"),
  z = c(0.08, 0.83, 0.60)
)
```

##

```{r}
tribble(
  ~x, ~y, ~z,
  1, "h", 0.08,
  2, "m", 0.83,
  5, "g", 0.60
)
```