ptm <- proc.time()# ERIC
"aptitude-treatment interaction" AND PEER(yes) AND (stype.exact("Scholarly Journals") AND pd(20130101-20231231))
# PsycInfo
全てのフィールド: "aptitude-treatment interaction"
出版日: 20130101-
出版物タイプ: Peer Reviewed Journal
言語: English, Japanese\}\n を \}\n\n に置換しておく# ダウンロードしたbibファイルを読み
e <- readr::read_file(file = "../bib/ERIC.bib")
p <- readr::read_file(file = "../bib/PsycInfo.bib")
# 1論文1行にして
e2 <- data.frame(base::strsplit(e, split = "\n\n")[[1]])
p2 <- data.frame(base::strsplit(p, split = "\n\n")[[1]])
# データベースごとの行数のデータを作り
e2.row <- c(1:nrow(e2))
p2.row <- c(1:nrow(p2))
# 1論文1つのcsvファイルで保存して
for(i in e2.row){
file <- data.frame(base::strsplit(e2[i,], split=",\n"))
setwd("../ERIC")
csvname <- paste("e_", i, ".csv", sep = "")
write.csv(file, csvname)
}
for(i in p2.row){
file <- data.frame(base::strsplit(p2[i,], split=",\n"))
setwd("../PsycInfo")
csvname <- paste("p_", i, ".csv", sep = "")
write.csv(file, csvname)
}
# csvファイルを読み出し
for(i in e2.row){
name <- paste("e_", i, sep = "")
dataname <- paste("e.csv.", i, sep = "")
assign(dataname, read.csv(paste("../ERIC/", name, ".csv", sep = "")))
}
for(i in p2.row){
name <- paste("p_", i, sep = "")
dataname <- paste("p.csv.", i, sep = "")
assign(dataname, read.csv(paste("../PsycInfo/", name, ".csv", sep = "")))
}e.nrow <- data.frame(matrix(c(
1, nrow(e.csv.1), 2, nrow(e.csv.2), 3, nrow(e.csv.3),
4, nrow(e.csv.4), 5, nrow(e.csv.5), 6, nrow(e.csv.6),
7, nrow(e.csv.7), 8, nrow(e.csv.8), 9, nrow(e.csv.9),
10, nrow(e.csv.10), 11, nrow(e.csv.11), 12, nrow(e.csv.12),
13, nrow(e.csv.13), 14, nrow(e.csv.14), 15, nrow(e.csv.15),
16, nrow(e.csv.16), 17, nrow(e.csv.17), 18, nrow(e.csv.18),
19, nrow(e.csv.19), 20, nrow(e.csv.20), 21, nrow(e.csv.21),
22, nrow(e.csv.22), 23, nrow(e.csv.23), 24, nrow(e.csv.24),
25, nrow(e.csv.25), 26, nrow(e.csv.26), 27, nrow(e.csv.27),
28, nrow(e.csv.28), 29, nrow(e.csv.29), 30, nrow(e.csv.30),
31, nrow(e.csv.31), 32, nrow(e.csv.32), 33, nrow(e.csv.33),
34, nrow(e.csv.34), 35, nrow(e.csv.35), 36, nrow(e.csv.36),
37, nrow(e.csv.37), 38, nrow(e.csv.38), 39, nrow(e.csv.39),
40, nrow(e.csv.40), 41, nrow(e.csv.41), 42, nrow(e.csv.42),
43, nrow(e.csv.43), 44, nrow(e.csv.44), 45, nrow(e.csv.45),
46, nrow(e.csv.46), 47, nrow(e.csv.47), 48, nrow(e.csv.48),
49, nrow(e.csv.49), 50, nrow(e.csv.50), 51, nrow(e.csv.51),
52, nrow(e.csv.52), 53, nrow(e.csv.53), 54, nrow(e.csv.54),
55, nrow(e.csv.55), 56, nrow(e.csv.56), 57, nrow(e.csv.57),
58, nrow(e.csv.58), 59, nrow(e.csv.59), 60, nrow(e.csv.60),
61, nrow(e.csv.61), 62, nrow(e.csv.62), 63, nrow(e.csv.63),
64, nrow(e.csv.64), 65, nrow(e.csv.65), 66, nrow(e.csv.66),
67, nrow(e.csv.67), 68, nrow(e.csv.68), 69, nrow(e.csv.69),
70, nrow(e.csv.70), 71, nrow(e.csv.71), 72, nrow(e.csv.72),
73, nrow(e.csv.73), 74, nrow(e.csv.74), 75, nrow(e.csv.75),
76, nrow(e.csv.76), 77, nrow(e.csv.77), 78, nrow(e.csv.78),
79, nrow(e.csv.79), 80, nrow(e.csv.80), 81, nrow(e.csv.81),
82, nrow(e.csv.82), 83, nrow(e.csv.83), 84, nrow(e.csv.84),
85, nrow(e.csv.85), 86, nrow(e.csv.86), 87, nrow(e.csv.87),
88, nrow(e.csv.88), 89, nrow(e.csv.89), 90, nrow(e.csv.90),
91, nrow(e.csv.91), 92, nrow(e.csv.92), 93, nrow(e.csv.93),
94, nrow(e.csv.94), 95, nrow(e.csv.95), 96, nrow(e.csv.96),
97, nrow(e.csv.97), 98, nrow(e.csv.98), 99, nrow(e.csv.99),
100, nrow(e.csv.100), 101, nrow(e.csv.101), 102, nrow(e.csv.102),
103, nrow(e.csv.103), 104, nrow(e.csv.104), 105, nrow(e.csv.105),
106, nrow(e.csv.106), 107, nrow(e.csv.107), 108, nrow(e.csv.108),
109, nrow(e.csv.109), 110, nrow(e.csv.110), 111, nrow(e.csv.111),
112, nrow(e.csv.112), 113, nrow(e.csv.113), 114, nrow(e.csv.114),
115, nrow(e.csv.115), 116, nrow(e.csv.116), 117, nrow(e.csv.117),
118, nrow(e.csv.118), 119, nrow(e.csv.119), 120, nrow(e.csv.120),
121, nrow(e.csv.121)
),ncol = 2, byrow =TRUE))
colnames(e.nrow) <- c("seq", "nrow")
p.nrow <- data.frame(matrix(c(
1, nrow(p.csv.1), 2, nrow(p.csv.2), 3, nrow(p.csv.3),
4, nrow(p.csv.4), 5, nrow(p.csv.5), 6, nrow(p.csv.6),
7, nrow(p.csv.7), 8, nrow(p.csv.8), 9, nrow(p.csv.9),
10, nrow(p.csv.10), 11, nrow(p.csv.11), 12, nrow(p.csv.12),
13, nrow(p.csv.13), 14, nrow(p.csv.14), 15, nrow(p.csv.15),
16, nrow(p.csv.16), 17, nrow(p.csv.17), 18, nrow(p.csv.18),
19, nrow(p.csv.19), 20, nrow(p.csv.20), 21, nrow(p.csv.21),
22, nrow(p.csv.22), 23, nrow(p.csv.23), 24, nrow(p.csv.24),
25, nrow(p.csv.25), 26, nrow(p.csv.26), 27, nrow(p.csv.27),
28, nrow(p.csv.28), 29, nrow(p.csv.29), 30, nrow(p.csv.30),
31, nrow(p.csv.31), 32, nrow(p.csv.32), 33, nrow(p.csv.33),
34, nrow(p.csv.34), 35, nrow(p.csv.35), 36, nrow(p.csv.36),
37, nrow(p.csv.37), 38, nrow(p.csv.38), 39, nrow(p.csv.39),
40, nrow(p.csv.40), 41, nrow(p.csv.41), 42, nrow(p.csv.42),
43, nrow(p.csv.43), 44, nrow(p.csv.44), 45, nrow(p.csv.45),
46, nrow(p.csv.46)
),ncol = 2, byrow =TRUE))
colnames(p.nrow) <- c("seq", "nrow")
#table(e.nrow[c("nrow")])
#table(p.nrow[c("nrow")])e.nrow.15.seq <- subset(e.nrow, nrow == 15); e.nrow.15.seq[c("seq")]## seq
## 16 16
## 17 17
## 18 18
## 19 19
## 20 20
## 22 22
## 23 23
## 24 24
## 28 28
## 29 29
## 31 31
## 33 33
## 34 34
## 40 40
## 41 41
## 43 43
## 45 45
## 46 46
## 47 47
## 48 48
## 49 49
## 50 50
## 62 62
## 63 63
## 64 64
## 65 65
## 72 72
## 73 73
## 74 74
## 75 75
## 76 76
## 77 77
## 78 78
## 79 79
## 80 80
## 81 81
## 82 82
## 83 83
## 84 84
## 86 86
## 87 87
## 88 88
## 89 89
## 90 90
## 91 91
## 92 92
## 108 108
## 114 114
## 115 115
## 118 118e.nrow.14.seq <- subset(e.nrow, nrow == 14); e.nrow.14.seq[c("seq")]## seq
## 1 1
## 2 2
## 3 3
## 4 4
## 5 5
## 6 6
## 7 7
## 9 9
## 10 10
## 12 12
## 13 13
## 14 14
## 15 15
## 21 21
## 25 25
## 26 26
## 27 27
## 32 32
## 35 35
## 36 36
## 37 37
## 38 38
## 39 39
## 42 42
## 44 44
## 51 51
## 52 52
## 53 53
## 55 55
## 56 56
## 58 58
## 59 59
## 60 60
## 61 61
## 66 66
## 67 67
## 68 68
## 70 70
## 71 71
## 85 85
## 93 93
## 94 94
## 95 95
## 96 96
## 97 97
## 98 98
## 99 99
## 100 100
## 101 101
## 102 102
## 103 103
## 104 104
## 105 105
## 106 106
## 107 107
## 109 109
## 110 110
## 111 111
## 112 112
## 113 113
## 116 116
## 117 117
## 119 119
## 120 120
## 121 121e.nrow.13.seq <- subset(e.nrow, nrow == 13); e.nrow.13.seq[c("seq")]## seq
## 8 8
## 11 11
## 30 30
## 54 54
## 57 57
## 69 69#e.nrow.15.seq
#e.nrow.14.seq
#e.nrow.13.seqe.nrow.15_ <- cbind(e.csv.16[,2], e.csv.17[,2], e.csv.18[,2],
e.csv.19[,2], e.csv.20[,2], e.csv.22[,2],
e.csv.23[,2], e.csv.24[,2], e.csv.28[,2],
e.csv.29[,2], e.csv.31[,2], e.csv.33[,2],
e.csv.34[,2], e.csv.40[,2], e.csv.41[,2],
e.csv.43[,2], e.csv.45[,2], e.csv.46[,2],
e.csv.47[,2], e.csv.48[,2], e.csv.49[,2],
e.csv.50[,2], e.csv.62[,2], e.csv.63[,2],
e.csv.64[,2], e.csv.65[,2], e.csv.72[,2],
e.csv.73[,2], e.csv.74[,2], e.csv.75[,2],
e.csv.76[,2], e.csv.77[,2], e.csv.78[,2],
e.csv.79[,2], e.csv.80[,2], e.csv.81[,2],
e.csv.82[,2], e.csv.83[,2], e.csv.84[,2],
e.csv.86[,2], e.csv.87[,2], e.csv.88[,2],
e.csv.89[,2], e.csv.90[,2], e.csv.91[,2],
e.csv.92[,2], e.csv.108[,2], e.csv.114[,2],
e.csv.115[,2],e.csv.118[,2])
e.nrow.14_ <- cbind(e.csv.1[,2], e.csv.2[,2], e.csv.3[,2],
e.csv.4[,2], e.csv.5[,2], e.csv.6[,2],
e.csv.7[,2], e.csv.9[,2], e.csv.10[,2],
e.csv.12[,2], e.csv.13[,2], e.csv.14[,2],
e.csv.15[,2], e.csv.21[,2], e.csv.25[,2],
e.csv.26[,2], e.csv.27[,2], e.csv.32[,2],
e.csv.35[,2], e.csv.36[,2], e.csv.37[,2],
e.csv.38[,2], e.csv.39[,2], e.csv.42[,2],
e.csv.44[,2], e.csv.51[,2], e.csv.52[,2],
e.csv.53[,2], e.csv.55[,2], e.csv.56[,2],
e.csv.58[,2], e.csv.59[,2], e.csv.60[,2],
e.csv.61[,2], e.csv.66[,2], e.csv.67[,2],
e.csv.68[,2], e.csv.70[,2], e.csv.71[,2],
e.csv.85[,2], e.csv.93[,2], e.csv.94[,2],
e.csv.95[,2], e.csv.96[,2], e.csv.97[,2],
e.csv.98[,2], e.csv.99[,2], e.csv.100[,2],
e.csv.101[,2], e.csv.102[,2], e.csv.103[,2],
e.csv.104[,2], e.csv.105[,2], e.csv.106[,2],
e.csv.107[,2], e.csv.109[,2], e.csv.110[,2],
e.csv.111[,2], e.csv.112[,2], e.csv.113[,2],
e.csv.116[,2], e.csv.117[,2], e.csv.119[,2],
e.csv.120[,2], e.csv.121[,2])
e.nrow.13_ <- cbind(e.csv.8[,2], e.csv.11[,2], e.csv.30[,2],
e.csv.54[,2], e.csv.57[,2],e.csv.69[,2])
# 保存
e.nrow.15 <- data.frame(t(e.nrow.15_))
e.nrow.14 <- data.frame(t(e.nrow.14_))
e.nrow.13 <- data.frame(t(e.nrow.13_))
library(openxlsx)
write.xlsx(e.nrow.15, "../Data/e_nrow_15.xlsx")
write.xlsx(e.nrow.14, "../Data/e_nrow_14.xlsx")
write.xlsx(e.nrow.13, "../Data/e_nrow_13.xlsx")p.nrow.13_ <- cbind(p.csv.6[,2], p.csv.7[,2], p.csv.8[,2],
p.csv.9[,2], p.csv.10[,2], p.csv.11[,2],
p.csv.12[,2], p.csv.13[,2], p.csv.14[,2],
p.csv.15[,2], p.csv.16[,2], p.csv.17[,2],
p.csv.18[,2], p.csv.19[,2], p.csv.20[,2],
p.csv.21[,2], p.csv.22[,2], p.csv.23[,2],
p.csv.24[,2], p.csv.25[,2], p.csv.26[,2],
p.csv.27[,2], p.csv.28[,2], p.csv.29[,2],
p.csv.30[,2], p.csv.31[,2], p.csv.32[,2],
p.csv.33[,2], p.csv.34[,2], p.csv.35[,2],
p.csv.36[,2], p.csv.37[,2], p.csv.38[,2],
p.csv.39[,2], p.csv.40[,2], p.csv.41[,2],
p.csv.42[,2], p.csv.43[,2], p.csv.44[,2],
p.csv.45[,2], p.csv.46[,2])## Warning in cbind(p.csv.6[, 2], p.csv.7[, 2], p.csv.8[, 2], p.csv.9[, 2], :
## number of rows of result is not a multiple of vector length (arg 2)# 保存
p.nrow.13 <- data.frame(t(p.nrow.13_))
library(openxlsx)
write.xlsx(p.nrow.13, "../Data/p_nrow_13.xlsx")# ERIC
15列
c("author", "year", "month", "title", "journal", "volume", "number", "pages", "note", "abstract", "keywords", "issn", "language", "url", "no.use")
14列，13列
整形して15列にして以下の通りにする
c("author", "year", "month", "title", "journal", "volume", "number", "pages", "note", "abstract", "keywords", "isbn", "language", "url", "no.use")
# PsycInfo
13列
VolumeとURLが入れ替わっているデータがあるので注意
c("no.use.1", "abstract", "author", "issn", "journal", "keywords", "number", "pages", "title", "url", "volume", "year", "no.use2")library(openxlsx)
e.nrow.15r <- read.xlsx("../Data/e_nrow_15r.xlsx", sheet=1)
e.nrow.14r <- read.xlsx("../Data/e_nrow_14r.xlsx", sheet=1)
e.nrow.13r <- read.xlsx("../Data/e_nrow_13r.xlsx", sheet=1)
p.nrow.13r <- read.xlsx("../Data/p_nrow_13r.xlsx", sheet=1)
eric.col <- c("author", "year", "month", "title", "journal", "volume", "number", "pages", "note", "abstract", "keywords", "issn", "language", "url", "no.use")
psyc.col <- c("no.use.1", "abstract", "author", "issn", "journal", "keywords", "number", "pages", "title", "volume", "url", "year", "no.use2")
colnames(e.nrow.15r) <- eric.col
colnames(e.nrow.14r) <- eric.col
colnames(e.nrow.13r) <- eric.col
colnames(p.nrow.13r) <- psyc.col
library(dplyr)
e.raw <- dplyr::bind_rows(e.nrow.15r, e.nrow.14r, e.nrow.13r)
p.raw <- p.nrow.13rauthor.rm <- c("author=\\{")
rm.2 <- c("\\}")
year.rm <- c("year=\\{")
month.rm <- c("month=\\{")
title.rm <- c("title=\\{")
journal.rm <- c("journal=\\{")
volume.rm <- c("volume=\\{")
number.rm <- c("number=\\{")
pages.rm <- c("pages=\\{")
abstract.rm <- c("abstract=\\{")
keywords.rm <- c("keywords=\\{")
issn.rm <- c("isbn=\\{")
url.rm <- c("url=\\{")
library(stringr)
e.raw$author <- str_replace_all(e.raw$author, pattern = author.rm, replacement = "")
e.raw$author <- str_replace_all(e.raw$author, rm.2, "")
e.raw$year <- str_replace_all(e.raw$year, pattern = year.rm, replacement = "")
e.raw$year <- str_replace_all(e.raw$year, rm.2, "")
e.raw$month <- str_replace_all(e.raw$month, pattern = month.rm, replacement = "")
e.raw$month <- str_replace_all(e.raw$month, rm.2, "")
e.raw$title <- str_replace_all(e.raw$title, pattern = title.rm, replacement = "")
e.raw$title <- str_replace_all(e.raw$title, rm.2, "")
e.raw$journal <- str_replace_all(e.raw$journal, pattern = journal.rm, replacement = "")
e.raw$journal <- str_replace_all(e.raw$journal, rm.2, "")
e.raw$volume <- str_replace_all(e.raw$volume, pattern = volume.rm, replacement = "")
e.raw$volume <- str_replace_all(e.raw$volume, rm.2, "")
e.raw$number <- str_replace_all(e.raw$number, pattern = number.rm, replacement = "")
e.raw$number <- str_replace_all(e.raw$number, rm.2, "")
e.raw$pages <- str_replace_all(e.raw$pages, pattern = pages.rm, replacement = "")
e.raw$pages <- str_replace_all(e.raw$pages, rm.2, "")
e.raw$abstract <- str_replace_all(e.raw$abstract, pattern = abstract.rm, replacement = "")
e.raw$abstract <- str_replace_all(e.raw$abstract, rm.2, "")
e.raw$keywords <- str_replace_all(e.raw$keywords, pattern = keywords.rm, replacement = "")
e.raw$keywords <- str_replace_all(e.raw$keywords, rm.2, "")
e.raw$issn <- str_replace_all(e.raw$issn, pattern = issn.rm, replacement = "")
e.raw$issn <- str_replace_all(e.raw$issn, rm.2, "")
e.raw$url <- str_replace_all(e.raw$url, pattern = url.rm, replacement = "")
e.raw$url <- str_replace_all(e.raw$url, rm.2, "")
# タイトルを先頭だけ大文字，あとは小文字
e.raw$title <- str_to_sentence(e.raw$title)abstract.rm <- c("Abstract = \\{")
author.rm <- c("Author = \\{")
issn.rm <- c("ISSN = \\{")
journal.rm <- c("Journal = \\{")
keywords.rm <- c("Keywords = \\{")
number.rm <- c("Number = \\{")
pages.rm <- c("Pages = \\{")
title.rm <- c("Title = \\{")
url.rm <- c("URL = \\{")
volume.rm <- c("Volume = \\{")
year.rm <- c("Year = \\{")
rm.2 <- c("\\}")
period <- c("\\.")
library(stringr)
p.raw$abstract <- str_replace_all(p.raw$abstract, pattern = abstract.rm, replacement = "")
p.raw$abstract <- str_replace_all(p.raw$abstract, rm.2, "")
p.raw$author <- str_replace_all(p.raw$author, pattern = author.rm, replacement = "")
p.raw$author <- str_replace_all(p.raw$author, rm.2, "")
p.raw$issn <- str_replace_all(p.raw$issn, pattern = issn.rm, replacement = "")
p.raw$issn <- str_replace_all(p.raw$issn, rm.2, "")
p.raw$journal <- str_replace_all(p.raw$journal, pattern = journal.rm, replacement = "")
p.raw$journal <- str_replace_all(p.raw$journal, rm.2, "")
p.raw$keywords <- str_replace_all(p.raw$keywords, pattern = keywords.rm, replacement = "")
p.raw$keywords <- str_replace_all(p.raw$keywords, rm.2, "")
p.raw$number <- str_replace_all(p.raw$number, pattern = number.rm, replacement = "")
p.raw$number <- str_replace_all(p.raw$number, rm.2, "")
p.raw$pages <- str_replace_all(p.raw$pages, pattern = pages.rm, replacement = "")
p.raw$pages <- str_replace_all(p.raw$pages, rm.2, "")
p.raw$title <- str_replace_all(p.raw$title, pattern = title.rm, replacement = "")
p.raw$title <- str_replace_all(p.raw$title, pattern = period, replacement = "")
p.raw$title <- str_replace_all(p.raw$title, rm.2, "")
p.raw$url <- str_replace_all(p.raw$url, pattern = url.rm, replacement = "")
p.raw$url <- str_replace_all(p.raw$url, rm.2, "")
p.raw$volume <- str_replace_all(p.raw$volume, pattern = volume.rm, replacement = "")
p.raw$volume <- str_replace_all(p.raw$volume, rm.2, "")
p.raw$year <- str_replace_all(p.raw$year, pattern = year.rm, replacement = "")
p.raw$year <- str_replace_all(p.raw$year, rm.2, "")
# キーワード区切りをセミコロンにする
p.raw$keywords <- str_replace_all(p.raw$keywords, pattern = ",", replacement = ";")
# ページ番号の空白をなくす
p.raw$pages <- str_replace_all(p.raw$pages, " ", "")
# タイトルを先頭だけ大文字，あとは小文字
p.raw$title <- str_to_sentence(p.raw$title)# ERIC
e.raw$db <- c("eric")
library(dplyr)
e.raw <- e.raw %>% mutate(seq = row_number())
e.raw$db.seq <- paste(e.raw$db, ".", e.raw$seq, sep = "")
eric <- e.raw[c("db", "seq", "db.seq", "author", "year", "title", "journal",
"volume", "number", "pages", "keywords","issn", "abstract")]
# PsycInfo
p.raw$db <- c("psyc")
library(dplyr)
p.raw <- p.raw %>% mutate(seq = row_number())
p.raw$db.seq <- paste(p.raw$db, ".", p.raw$seq, sep = "")
psyc <- p.raw[c("db", "seq", "db.seq", "author", "year", "title", "journal",
"volume", "number", "pages", "keywords","issn", "abstract")]
# まとめる
eric.psyc <- dplyr::bind_rows(eric, psyc)
# ここで保存しておく
library(openxlsx)
write.xlsx(eric, "../Data/ERIC.xlsx")
write.xlsx(psyc, "../Data/Psyc.xlsx")
write.xlsx(eric.psyc, "../Data/ERIC_Psyc.xlsx")# タイトルで重複確認
library("dplyr")
duplicate <- eric.psyc %>% group_by(title) %>% filter(n()>1)
duplicate <- duplicate[order(duplicate$title, decreasing=T),]
duplicate.sec.title <- duplicate[c("db.seq", "title")]
library(openxlsx)
write.xlsx(duplicate.sec.title, "../Data/Duplicate.xlsx")
# 重複は8件
eric.psyc.nodp <- eric.psyc %>%
dplyr::filter(db.seq != "eric.12" &
db.seq != "eric.53" &
db.seq != "eric.56" &
db.seq != "eric.71" &
db.seq != "eric.52" &
db.seq != "eric.120" &
db.seq != "eric.60" &
db.seq != "eric.116")
library(openxlsx)
write.xlsx(eric.psyc.nodp, "../Data/eric_psyc_nodp.xlsx")library(dplyr)
library(tidyverse)
library(deeplr)##データの読み込み
library(openxlsx)
e.p.nodp <- read.xlsx("../Data/eric_psyc_nodp.xlsx")sum(nchar(e.p.nodp$abstract))## [1] 168992Deepl APIの情報（非表示）
動作確認
available_languages(auth_key = api)## # A tibble: 29 × 2
## language name
## <chr> <chr>
## 1 BG Bulgarian
## 2 CS Czech
## 3 DA Danish
## 4 DE German
## 5 EL Greek
## 6 EN English
## 7 ES Spanish
## 8 ET Estonian
## 9 FI Finnish
## 10 FR French
## # ℹ 19 more rows言語の指定
source_lang <- "EN"
target_lang <- "JA"関数
- https://note.com/text_tier2718/n/n3451567126a7
に載っている関数を使う
deepL <- function(Sentence, source_lang = "EN", target_lang = "JA", api_key = api_key) {
a <- system(
paste0(
'curl -s https://api.deepl.com/v2/translate -d "auth_key=',
api_key,
'" -d "text=',
str_replace_all(Sentence, pattern = '"', replacement = "'"), # 翻訳文中に""があるとpaste0と干渉してエラーを起こすので''に変換
'" -d source_lang="',
source_lang,
'" -d "target_lang=',
target_lang,
'"'
),
intern = T
)
b <- strsplit(
strsplit(
as.character(a),
'\"text\":\"'
)[[1]][2],
'\"}]}'
)[[1]][1]
Sys.sleep(1)
return(b)
}翻訳
translation <- map(e.p.nodp$abstract, function(x) {
deepL(
Sentence = x,
source_lang = source_lang,
target_lang = target_lang,
api_key = api
)
})
eric.psyc.ja <- mutate(e.p.nodp, abstract_ja = translation)
library(openxlsx)
write.xlsx(eric.psyc.ja, "../Data/eric_psyc_ja.xlsx")## user system elapsed
## 4.217 2.004 362.960