Question

我正在使用MonetDBLite R包来创建MonetDB。我可以使用here中的说明使用以下代码创建数据库表：

library(DBI)
library(MonetDBLite)

# Write tsv file of mtcars
write.table(mtcars, "mtcars.tsv", row.names=FALSE, sep= "\t")

# Initialize MonetDB
dbdir <- "/Users/admin/my_directory"
con <- dbConnect(MonetDBLite::MonetDBLite(), dbdir)

# Write table
dbWriteTable(con, "test4", "mtcars.tsv", delim="\t")

以及以下查询提供

> dbGetQuery(con, "SELECT * FROM test4 LIMIT 3")
mpg cyl  disp  hp drat    wt  qsec vs am gear carb
1  21.0   6 160.0 110 3.90 2.620 16.46  0  1    4    4
2  21.0   6 160.0 110 3.90 2.875 17.02  0  1    4    4
3  22.8   4 108.0  93 3.85 2.320 18.61  1  1    4    1

到目前为止一切顺利。但是，假设我有另一个文件mtcars2具有不同的mpg值：

mtcars2 <- mtcars
mtcars2$mpg <- mtcars2$mpg + 5
write.table(mtcars2, "mtcars2.tsv", row.names= FALSE, sep = "\t")

我可以将它加载到另一个表中：

dbWriteTable(con, "test5", "mtcars2.tsv", delim = "\t")
> dbGetQuery(con, "SELECT * FROM test5 LIMIT 3")
mpg cyl disp  hp drat    wt  qsec vs am gear carb
1 26.0   6  160 110 3.90 2.620 16.46  0  1    4    4
2 26.0   6  160 110 3.90 2.875 17.02  0  1    4    4
3 27.8   4  108  93 3.85 2.320 18.61  1  1    4    1

也很好。但我的问题是这样的：我想稍后查找mpg所有6 cyl的汽车，并知道它来自哪个数据集（mtcars或mtcars2）。根据我对SQL索引的理解（这不是很多，基本上我读过here），我应该在一个表中拥有所有数据以获得最有效的搜索。我尝试加载第一个tsv文件，然后使用ALTER TABLE test4 ADD dataset TEXT和UPDATE test4 SET dataset = dataset1 sql命令添加另一个列 -

dbSendQuery(con, "UPDATE test4 SET dataset = dataset1")
dbSendQuery(con, "UPDATE test4 SET dataset = 1")
> dbGetQuery(con, "SELECT * FROM test4 LIMIT 3")
mpg cyl disp  hp drat    wt  qsec vs am gear carb dataset
1 21.0   6  160 110 3.90 2.620 16.46  0  1    4    4       1
2 21.0   6  160 110 3.90 2.875 17.02  0  1    4    4       1
3 22.8   4  108  93 3.85 2.320 18.61  1  1    4    1       1

但是当我尝试将mtcars2附加到表中时，它有不同数量的列（正如我应该预料的那样）。什么是将具有相同列的多个tsv文件中的数据连接到单个表中的最佳方法，同时跟踪数据的来源？

编辑 - 您可能已经猜到了，真正的数据不是mtcars-它是平坦的tsv文件长达数百万行，这意味着我想避免将整个文件读入内存并使用R进行操作。

Answer 1

根据xQbert的建议，我只解决了使用SQL命令的问题（必要且比bash命令更快，考虑到我的数据是10个文件，每个数百万行长）。

library(DBI)
library(MonetDBLite)

# Write tsv file of mtcars
write.table(mtcars, "mtcars.tsv", row.names=FALSE, sep= "\t")

# Write tsv of second mtcars
mtcars2 <- mtcars
mtcars2$mpg <- mtcars2$mpg + 5
write.table(mtcars2, "mtcars2.tsv", row.names= FALSE, sep = "\t")

# Initialize MonetDB
dbdir <- "/Users/admin/"
con <- dbConnect(MonetDBLite::MonetDBLite(), dbdir)

# Write table
dbWriteTable(con, "test4", "mtcars.tsv", delim="\t")

# Add data source information
dbSendQuery(con, "ALTER TABLE test4 ADD source TEXT")
dbSendQuery(con, "UPDATE test4 SET source = 'dataset1'")

# Write second dataset to a temporary table
dbWriteTable(con, "temptable", "mtcars2.tsv", delim="\t")

# Add data source information
dbSendQuery(con, "ALTER TABLE temptable ADD source TEXT")
dbSendQuery(con, "UPDATE temptable SET source = 'dataset2'")

# Insert temp table into main table
dbSendQuery(con, "INSERT INTO test4 SELECT * FROM temptable")

# Drop temp table
dbSendQuery(con, "DROP TABLE temptable")

# Checking the data, truncated for clarity
> dbGetQuery(con, "SELECT * FROM test4")
mpg cyl  disp  hp drat    wt  qsec vs am gear carb   source
1  21.0   6 160.0 110 3.90 2.620 16.46  0  1    4    4 dataset1
2  21.0   6 160.0 110 3.90 2.875 17.02  0  1    4    4 dataset1
3  22.8   4 108.0  93 3.85 2.320 18.61  1  1    4    1 dataset1
...
33 26.0   6 160.0 110 3.90 2.620 16.46  0  1    4    4 dataset2
34 26.0   6 160.0 110 3.90 2.875 17.02  0  1    4    4 dataset2
35 27.8   4 108.0  93 3.85 2.320 18.61  1  1    4    1 dataset2
...
64 26.4   4 121.0 109 4.11 2.780 18.60  1  1    4    2 dataset2

很抱歉，如果我的数据比mtcars大得多，我没有说清楚 - 如果你有中等大小的数据，那么data.tables包可能是比数据库更好的解决方案。

Answer 2

在阅读文件后，在data.frame中创建一个新变量后，您应该能够执行dbWriteTable()所需的操作。类似的东西：

  library(DBI)
  library(MonetDBLite)
  library(data.table)

  # Write tsv file of mtcars
  tmp <- tempfile()
  write.table(mtcars, tmp, row.names=FALSE, sep= "\t")

  # Initialize MonetDB
  dbdir <- "~/Desktop/temp"
  con <- dbConnect(MonetDBLite::MonetDBLite(), dbdir)

  test4df <- fread(tmp)
  test4df$dataset <- 1
  dbWriteTable(con, "test4", test4df)

  dbReadTable(con, "test4")

  test5df <- fread(tmp)
  test5df$mpg <- test5df$mpg + 5
  test5df$dataset <- 2
  dbWriteTable(con, "test4", test5df, append = TRUE)

  dbReadTable(con, "test4")

编辑（不打开文件的方式建议）

如果您想在不打开文件的情况下完成工作，可以执行以下操作来修改文件并附加其他字段。正如我所写，这将适用于具有bash的操作系统。

infile <- tmp
outfile <- tempfile()

# open connections
incon <- file(description = infile, open = "r")
outcon <- file(description = outfile, open = "w")

# count the number of lines (this will work only with Mac/Linux)
com <- paste("wc -l ", infile, " | awk '{ print $1 }'", sep="")
n <- system(command=com, intern=TRUE)

# work with the first line
txt <- scan(file = incon, what = character(), nlines=1, quiet=TRUE)
txt <- c(txt, "dataset")
cat(paste(txt, collapse = "\t"), "\n", file = outcon, sep = "")

# work with the rest of the file
for(i in 2:n) {
  txt <- scan(file = incon, what = character(), nlines=1, quiet=TRUE)
  txt <- c(txt, "1")
  cat(paste(txt, collapse = "\t"), "\n", file = outcon, sep = "")
}
close(incon);close(outcon)
dbWriteTable(con, "test4", outfile, delim = "\t")
# do the similar for other files

Answer 3

这是我要做的，给定一组具有相同结构和最终表中所需文件名的文件，否则它们是所有文件中数据的组合：

# say we have those files
write.table(mtcars, "mtcars1.tsv", row.names=FALSE, sep= "\t")
write.table(mtcars, "mtcars2.tsv", row.names=FALSE, sep= "\t")

# write them individually, and add a column that contains the file name
dbWriteTable(con, "mtcars1", "mtcars1.tsv", delim="\t")
dbSendQuery(con, "ALTER TABLE mtcars1 ADD COLUMN file STRING DEFAULT 'mtcars1.tsv';")
dbWriteTable(con, "mtcars2", "mtcars2.tsv", delim="\t")
dbSendQuery(con, "ALTER TABLE mtcars2 ADD COLUMN file STRING DEFAULT 'mtcars2.tsv';")

# now combine into a new table
dbSendQuery(con, "CREATE TABLE mtcars_mat AS SELECT * FROM mtcars1 UNION ALL SELECT * FROM mtcars2")

# or a view if you don't need to modify the data in the mtcars table (faster)
dbSendQuery(con, "CREATE view mtcars AS SELECT * FROM mtcars1 UNION ALL SELECT * FROM mtcars2")



# and here is the same as a loop with a filename glob and some added robustness (handy if you have 1000 files)
files <- Sys.glob("/some/path/mtcars*.tsv")
tables <- dbQuoteIdentifier(con, tools::file_path_sans_ext(basename(files)))
dbBegin(con)
for (i in 1:length(files)) {
  dbWriteTable(con, tables[i], files[i], delim="\t", transaction=FALSE)
  dbSendQuery(con, paste0("ALTER TABLE ", tables[i], " ADD COLUMN file STRING DEFAULT ",dbQuoteString(con, files[i]),";"))
}
dbSendQuery(con, paste0("CREATE TABLE somefinalresult AS ", paste0("SELECT * FROM ",tables, collapse=" UNION ALL ")))
# remove the parts again, optional
dbSendQuery(con, paste0("DROP TABLE ", tables, ";", collapse=" "))
dbCommit(con)

SQL将许多tsv文件连接到数据库中的单个表中，同时跟踪文件源（MonetDBLite）

3 个答案: