كتابة البيانات بتنسيقات متعددة

كتابة البيانات من R

library(readr)

# Create a sample data frame to write
df <- data.frame(
  name = c('Alice','Bob','Carol'),
  score = c(85.5, 92.0, 78.3),
  grade = c('B','A','C'),
  passed = c(TRUE, TRUE, TRUE)
)

print(df)
cat('\nWe will save this in multiple formats!')

write_csv() — الحفظ بصيغة CSV

library(readr)

df <- data.frame(
  name = c('Alice','Bob','Carol'),
  score = c(85, 92, 78)
)

# Write to /tmp for demonstration
write_csv(df, '/tmp/students.csv')

# Verify by reading back
read_csv('/tmp/students.csv', show_col_types=FALSE)

خيارات write_csv()

library(readr)

df <- data.frame(
  name = c('Alice','Bob'),
  city = c('New York','Los,Angeles'),  # Contains comma
  score = c(85, NA)
)

# na='' writes NA as empty string (common Excel convention)
write_csv(df, '/tmp/test_write.csv', na='')
cat(paste(read_lines('/tmp/test_write.csv'), collapse='\n'))

write_tsv() — إخراج مفصول بعلامات الجدولة

library(readr)

df <- data.frame(
  address = c('123 Main St, NYC','456 Oak Ave, LA'),
  score = c(85, 92)
)

# TSV avoids delimiter conflict with commas in addresses
write_tsv(df, '/tmp/addresses.tsv')
cat(paste(read_lines('/tmp/addresses.tsv'), collapse='\n'))

saveRDS() — حفظ أي كائن من R

library(readr)

df <- data.frame(
  name = c('Alice','Bob'),
  score = c(85.5, 92.0),
  grade = factor(c('B','A'), levels=c('A','B','C','D'))
)

# Save with full type preservation
saveRDS(df, '/tmp/students.rds')

# Restore exactly
df2 <- readRDS('/tmp/students.rds')
print(df2)
print(class(df2$grade))  # factor — preserved!

saveRDS() مقابل save() — الفرق الأساسي

# saveRDS: single object, flexible on load
model <- lm(mpg ~ wt, data=mtcars)
saveRDS(model, '/tmp/my_model.rds')
best_model <- readRDS('/tmp/my_model.rds')  # Any name!
cat('R-squared:', round(summary(best_model)$r.squared, 3), '\n')

# save: multiple named objects, fixed names on load
# save(model, mtcars, file='/tmp/workspace.RData')
# load('/tmp/workspace.RData')  # Restores 'model' and 'mtcars'

write_delim() — محدِّد مخصص

library(readr)

df <- data.frame(
  id = 1:3,
  name = c('Alice','Bob','Carol'),
  value = c(100, 200, 150)
)

# Write pipe-delimited
write_delim(df, '/tmp/data.psv', delim='|')
cat(paste(read_lines('/tmp/data.psv'), collapse='\n'))

إخراج Excel باستخدام writexl

# writexl::write_xlsx() — example (library not always available)
# library(writexl)

df1 <- data.frame(name=c('Alice','Bob'), score=c(85,92))
df2 <- data.frame(region=c('East','West'), sales=c(100,200))

# Single sheet:
# write_xlsx(df1, '/tmp/students.xlsx')

# Multiple sheets (named list):
# write_xlsx(
#   list(students=df1, sales=df2),
#   '/tmp/report.xlsx'
# )

cat('writexl writes pure .xlsx without Java or Excel!')

ملفات Parquet باستخدام arrow

# arrow::write_parquet() concept
# library(arrow)

# Large CSV -> Parquet (10-100x smaller, 10-100x faster reads)
# df <- read_csv('big_file.csv')
# write_parquet(df, 'big_file.parquet')
# df_back <- read_parquet('big_file.parquet')

# Parquet benefits:
# - Columnar: only reads columns you need
# - Compressed: ~10x smaller than CSV
# - Typed: no type re-guessing on read
# - Partitioned: split by date/region for parallel reads

cat('Parquet is the modern standard for large-scale analytics in R!')

كتابة البيانات ضمن سلسلة أنابيب

library(readr)
library(dplyr)

# Write mid-pipeline as a checkpoint
final_result <- data.frame(
  region=c('East','West','North'),
  sales=c(100,200,80)
) %>%
  mutate(pct = round(100*sales/sum(sales),1)) %>%
  {. ->> checkpoint_df; .} %>%  # Save checkpoint
  filter(sales > 90)

write_csv(checkpoint_df, '/tmp/checkpoint.csv')
print(final_result)

دليل اختيار التنسيق

library(readr)

df <- data.frame(
  id = 1:5,
  value = c(10.5, 20.3, 15.7, 30.1, 25.8)
)

# CSV — universal
write_csv(df, '/tmp/data.csv')

# TSV — when commas are in data
write_tsv(df, '/tmp/data.tsv')

# RDS — R-native, type-preserving
saveRDS(df, '/tmp/data.rds')

cat('Files created:\n')
cat('CSV size:', file.size('/tmp/data.csv'), 'bytes\n')
cat('RDS size:', file.size('/tmp/data.rds'), 'bytes\n')

تحقق سريع

مراجعة: كتابة البيانات

library(readr)

df <- data.frame(
  name = c('Alice','Bob','Carol'),
  score = c(85.5, 92.0, 78.3),
  grade = factor(c('B','A','C'))
)

# CSV: universal but loses factor
write_csv(df, '/tmp/demo.csv')
df_csv <- read_csv('/tmp/demo.csv', show_col_types=FALSE)
cat('CSV grade type:', class(df_csv$grade), '\n')  # character

# RDS: preserves factor
saveRDS(df, '/tmp/demo.rds')
df_rds <- readRDS('/tmp/demo.rds')
cat('RDS grade type:', class(df_rds$grade))  # factor