R: قراءة وكتابة ملفات CSV: دليل شامل لمكتبة readr

id,date,product,region,amount
1,2024-01-15,Cell Phone,Beijing,2999
2,2024-01-15,Computer,Shanghai,5999
3,2024-01-16,Cell Phone,Guangzhou,2899
...
(@,000 rows of)

# 1. Use readr Smart Reading(5 s)
library(readr)
sales <- read_csv("sales.csv")

# 2. Automatic Type Inference
# id → integer, date → date, product → character,
# region → character, amount → double

# 3. Read only the rows you need(Speed Up 3x)
sales_sample <- read_csv("sales.csv", n_max = 10000)

# 4. Write clean reports
write_csv(sales_sample, "sales_clean.csv")

Name,Age,City
Alice,25,Beijing
Bob,30,Shanghai
Charlie,35,Guangzhou

# Basics R(Common Issues with Legacy Code)
df_old <- read.csv("data.csv")
# Default behavior:Convert all string arrays factor(Pitfall!)

# tidyverse(Recommendations)
library(readr)
df_new <- read_csv("data.csv")
# Intelligent Inference Types,Character retains character

read_csv(file, col_types = TRUE, col_names = TRUE, na = "NA",
         skip = 0, n_max = Inf, locale = default_locale(),
         progress = TRUE)

library(readr)

# 1. Basic Reading(Intelligent Inference Types)
df <- read_csv("data.csv")

# 2. Specify Column Type(Avoiding Fallacies in Reasoning)
df <- read_csv("data.csv", col_types = cols(
  id = col_integer(),
  date = col_date(format = "%Y-%m-%d"),
  amount = col_double(),
  name = col_character()
))

# 3. Skip to the beginning 5 Line Comments
df <- read_csv("data.csv", skip = 5)

# 4. Custom NA Mark(CSV For internal use "NULL" Indicates missing)
df <- read_csv("data.csv", na = c("", "NA", "NULL", "N/A"))

# 5. Read-only before 1000 row(For debugging purposes)
df <- read_csv("data.csv", n_max = 1000)

# 6. Skip Column(Use col_types Set as col_skip())
df <- read_csv("data.csv", col_types = cols(
  temp_col = col_skip()
))

# Examples of Inference
sales <- read_csv("sales.csv")
spec(sales)  # View the inference results
# cols(
#   id = col_integer(),
#   date = col_date(format = "%Y-%m-%d"),
#   product = col_character(),
#   region = col_character(),
#   amount = col_double()
# )

write_csv(x, file, na = "NA", append = FALSE, col_names = TRUE)

# 1. Basic Output
write_csv(sales, "sales_clean.csv")

# 2. Output to the specified path
write_csv(sales, "output/2024_sales.csv")

# 3. Append to the existing file(Do not cover)
write_csv(new_data, "sales.csv", append = TRUE, col_names = FALSE)

# 4. Custom NA indicates
write_csv(df, "output.csv", na = "")

# Write
write_csv(sales, "sales.csv")

# Read it again
sales_loaded <- read_csv("sales.csv")
# Type by read_csv Re-inference

# 1. Read Using a Specified Encoding
df <- read_csv("data.csv", locale = locale(encoding = "UTF-8"))
# Or
df <- read_csv("data.csv", locale = locale(encoding = "GBK"))

# 2. Check the file encoding
guess_encoding("data.csv")
# Returns in most cases "UTF-8" or "GBK"

# 3. Specify the encoding when writing
write_csv(df, "output.csv")  # Default UTF-8

# 1. Tab-separated(TSV)
df <- read_tsv("data.tsv")  # sep = "\t"

# 2. Semicolon-separated(Commonly Used in Europe)
df <- read_csv2("data.csv")  # sep = ";"

# 3. Custom Delimiters(e.g. |)
df <- read_delim("data.txt", delim = "|")

# European Format:1.234,56(A percentile is .,A decimal is ,)
df <- read_csv("data_eu.csv",
               locale = locale(grouping_mark = ".", decimal_mark = ","))

# 1. Read only the required columns(Speed Up 2-3x)
df <- read_csv("big.csv", col_select = c(id, amount))

# 2. Use col_types Skip Column
df <- read_csv("big.csv", col_types = cols(
  temp_col_1 = col_skip(),
  temp_col_2 = col_skip()
))

# 3. Close the progress bar
df <- read_csv("big.csv", progress = FALSE)

# 4. A Faster Solution:data.table::fread
# fread("big.csv") is 5-10x faster than read_csv

col_types = cols(
  id = col_integer(),       # Integer
  name = col_character(),   # Character
  amount = col_double(),    # Double-precision floating-point
  date = col_date(),        # Date
  time = col_time(),        # Time
  datetime = col_datetime(),# Date and Time
  is_active = col_logical(),# Logic
  skip = col_skip(),        # Skip this column
  guess = col_guess()       # Let readr infer
)

# Use "i" "c" "d" "D" "l" Abbreviation
col_types = cols(
  id = "i",          # integer
  name = "c",        # character
  amount = "d",      # double
  date = "D",        # date
  is_active = "l"    # logical
)

# All Inferences(Default)
col_types = TRUE

# Using a list(Sequence-Mapped Columns)
col_types = list(
  id = col_integer(),
  name = col_character()
)

# ============================================
# Importing and Processing Sales Data
# Features:Read CSV → Cleaning → Analysis → Generate Report
# ============================================

library(readr)
library(dplyr)

# 1. Preparing Sample Data
sample_data <- tibble(
  id = 1:10,
  date = as.Date("2024-01-01") + 0:9,
  product = c("Cell Phone", "Computer", "Cell Phone", "Tablet", "Cell Phone",
              "Computer", "Tablet", "Cell Phone", "Computer", "Cell Phone"),
  region = c("Beijing", "Shanghai", "Guangzhou", "Beijing", "Shenzhen",
            "Shanghai", "Guangzhou", "Beijing", "Shenzhen", "Shanghai"),
  amount = c(2999, 5999, 2899, 3999, 3099,
            6299, 3899, 2899, 5999, 3199),
  note = c(NA, "Promo", NA, NA, "New Products", NA, NA, "Promo", NA, NA)
)

# Write Example CSV(UTF-8 Coding)
write_csv(sample_data, "sales_demo.csv")

cat("=== The file has been generated ===\n")

# 2. Read CSV(Intelligent Inference)
sales <- read_csv("sales_demo.csv",
                  na = c("", "NA"),
                  col_types = cols(
                    id = col_integer(),
                    date = col_date(format = "%Y-%m-%d"),
                    product = col_character(),
                    region = col_character(),
                    amount = col_double(),
                    note = col_character()
                  ))

cat("=== Read the results ===\n")
print(sales)

# 3. Data Quality Check
cat("\n=== Data Structures ===\n")
str(sales)

# 4. Data Analysis
cat("\n=== Sales Statistics ===\n")
summary_stats <- sales |>
  group_by(region) |>
  summarise(
    Number of Orders = n(),
    Total Sales = sum(amount),
    Average Order = round(mean(amount), 2),
    Highest Order = max(amount)
  ) |>
  arrange(desc(Total Sales))

print(summary_stats)

# 5. Find promotional orders
cat("\n=== Promotional Orders ===\n")
promo <- sales |> filter(!is.na(note))
print(promo)

# 6. By Product Category
cat("\n=== Product Sales ===\n")
product_stats <- sales |>
  group_by(product) |>
  summarise(Sales = n(), Sales = sum(amount))
print(product_stats)

# 7. Generate clean reports
write_csv(summary_stats, "sales_by_region.csv")
write_csv(product_stats, "sales_by_product.csv")
cat("\n=== The report has been generated ===\n")
cat("  - sales_by_region.csv(By Region)\n")
cat("  - sales_by_product.csv(By Product)\n")

# 8. Use RDS Reserved Types(Recommendations)
saveRDS(sales, "sales_clean.rds")
sales_reloaded <- readRDS("sales_clean.rds")
cat("\nRDS Type After Loading:\n")
print(sapply(sales_reloaded, class))

=== Sales Statistics ===
# A tibble: 4 × 5
  region Number of Orders Total Sales Average Order Highest Order
  <chr>   <int>   <dbl>    <dbl>    <dbl>
1 Beijing       3   9897    3299     3999
2 Shanghai       3  15497    5166.    6299
3 Guangzhou       2   6798    3399     3899
4 Shenzhen       2   9098    4549.    5999

=== Promotional Orders ===
# A tibble: 2 × 6
     id date       product region amount note
  <int> <date>     <chr>   <chr>   <dbl> <chr>
1     2 2024-01-02 Computer    Shanghai     5999 Promo
2     8 2024-01-08 Cell Phone    Beijing     2899 Promo