# Ejemplo WoS data
# library(dplyr)
# library(stringr)
# library(scimetr)

# Session > Set Working Directory > To Source...
source("wos.R")

# Importar datos en archivos de texto
dir(pattern='*.txt')
## [1] "savedrecs1.txt" "savedrecs2.txt"
# Se combinan los ficheros:
wosdf <- ImportSources.wos(other = FALSE)
## Warning in ImportSources.wos(other = FALSE): Sources with no ISSN found;
## droped...
# Abrir datos filtrados
load("wosdf.RData") # 856 registros filtrados
as.data.frame(attr(wosdf, "variable.labels"))
##     attr(wosdf, "variable.labels")
## PT                Publication type
## AU                          Author
## BA                    Book authors
## BE                          Editor
## GP                    Group author
## AF                     Author full
## BF           Book authors fullname
## CA                Corporate author
## TI                           Title
## SO                Publication name
## SE                    Series title
## BS                     Book series
## LA                        Language
## DT                   Document type
## CT                Conference title
## CY                 Conference year
## CL                Conference place
## SP             Conference sponsors
## HO                 Conference host
## DE                        Keywords
## ID                   Keywords Plus
## AB                        Abstract
## C1                       Addresses
## RP                  Reprint author
## EM                    Author email
## RI           Researcher id numbers
## OI                   Orcid numbers
## FU Funding agency and grant number
## FX                    Funding text
## CR                Cited references
## NR      Number of cited references
## TC                     Times cited
## Z9        Total times cited count 
## U1     Usage Count (Last 180 Days)
## U2        Usage Count (Since 2013)
## PU                       Publisher
## PI                  Publisher city
## PA               Publisher address
## SN                            ISSN
## EI                           eISSN
## BN                            ISBN
## J9                     Journal.ISI
## JI                     Journal.ISO
## PD                Publication date
## PY                  Year published
## VL                          Volume
## IS                           Issue
## PN                     Part number
## SU                      Supplement
## SI                   Special issue
## MA                Meeting abstract
## BP                  Beginning page
## EP                     Ending page
## AR                  Article number
## DI                             DOI
## D2                        Book DOI
## PG                      Page count
## WC                    WOS category
## SC                  Research areas
## GA        Document delivery number
## UT                   Access number
## PM                      Pub Med ID
# Generar tablas (lista de data.frames)
# Se crea la base de datos:
# db <- CreateDB.wos(wosdf)

db <- readRDS("db_udc_2015.rds")
str(db, 1)
## List of 11
##  $ Docs      :'data.frame':  856 obs. of  26 variables:
##  $ Authors   :'data.frame':  4051 obs. of  4 variables:
##  $ AutDoc    :'data.frame':  5511 obs. of  2 variables:
##  $ Categories:'data.frame':  189 obs. of  2 variables:
##  $ CatDoc    :'data.frame':  1495 obs. of  2 variables:
##  $ Areas     :'data.frame':  121 obs. of  2 variables:
##  $ AreaDoc   :'data.frame':  1364 obs. of  2 variables:
##  $ Addresses :'data.frame':  3655 obs. of  5 variables:
##  $ AddAutDoc :'data.frame':  7751 obs. of  3 variables:
##  $ Journals  :'data.frame':  520 obs. of  12 variables:
##   ..- attr(*, "variable.labels")= Named chr [1:62] "Publication type" "Author" "Book authors" "Editor" ...
##   .. ..- attr(*, "names")= chr [1:62] "PT" "AU" "BA" "BE" ...
##  $ label     : chr ""
##  - attr(*, "class")= chr "wos.db"
variable.labels <- attr(db, "variable.labels")
as.data.frame(variable.labels)
## data frame with 0 columns and 0 rows

Combinar la tabla de documentos con la de revistas

str(db$Docs) # View(db$Docs)
## 'data.frame':    856 obs. of  26 variables:
##  $ idd: int  1 2 3 4 5 6 7 8 9 10 ...
##  $ idj: int  260 37 86 272 64 429 14 408 333 214 ...
##  $ TI : chr  "Fractionation of Miscanthus x giganteus via modification of the Formacell process" "Role of Temperature and Pressure on the Multisensitive Multiferroic Dicyanamide Framework [TPrA][Mn(dca)(3)] wi"| __truncated__ "Methane and carbon dioxide emissions from constructed wetlands receiving anaerobically pretreated sewage" "Exceptionally Inert Lanthanide(III) PARACEST MRI Contrast Agents Based on an 18-Membered Macrocyclic Platform" ...
##  $ PT : Factor w/ 2 levels "Journal","Series": 1 1 1 1 1 1 1 1 1 1 ...
##  $ DT : Factor w/ 9 levels "Article","Book Review",..: 1 1 1 1 5 1 6 9 1 1 ...
##  $ NR : int  40 45 35 78 2 59 0 53 20 50 ...
##  $ TC : int  1 5 2 2 1 0 0 10 0 1 ...
##  $ Z9 : int  1 5 2 2 1 0 0 10 0 1 ...
##  $ U1 : int  5 0 10 4 0 1 0 26 0 3 ...
##  $ U2 : int  6 0 61 21 2 5 0 66 2 4 ...
##  $ PD : chr  "DEC 23" "DEC 21" "DEC 15" "DEC 14" ...
##  $ PY : int  2015 2015 2015 2015 2015 2015 2015 2015 2015 2015 ...
##  $ VL : chr  "77" "54" "538" "21" ...
##  $ IS : chr  "" "24" "" "51" ...
##  $ PN : chr  "" "" "" "" ...
##  $ SU : chr  "" "" "" "" ...
##  $ SI : chr  "" "" "" "" ...
##  $ MA : chr  "" "" "" "" ...
##  $ BP : chr  "275" "11680" "824" "18662" ...
##  $ EP : chr  "281" "11687" "833" "18670" ...
##  $ AR : chr  "" "" "" "" ...
##  $ DI : chr  "10.1016/j.indcrop.2015.08.066" "10.1021/acs.inorgchem.5b01652" "10.1016/j.scitotenv.2015.08.090" "10.1002/chem.201502937" ...
##  $ D2 : chr  "" "" "" "" ...
##  $ PG : int  7 8 10 9 2 28 3 16 4 25 ...
##  $ UT : num  3.66e+11 3.67e+11 3.63e+11 3.68e+11 3.66e+11 ...
##  $ an : num  3 9 4 8 3 5 8 5 3 3 ...
str(db$Journals) # View(db$Journals)
## 'data.frame':    520 obs. of  12 variables:
##  $ idj: int  1 2 3 4 5 6 7 8 9 10 ...
##  $ SO : chr  "TISSUE ANTIGENS" "ACTA NEUROLOGICA SCANDINAVICA" "ACTA PSYCHOLOGICA" "AFINIDAD" ...
##  $ SE : chr  "" "" "" "" ...
##  $ BS : chr  "" "" "" "" ...
##  $ LA : chr  "English" "English" "English" "English" ...
##  $ PU : chr  "WILEY-BLACKWELL" "WILEY-BLACKWELL" "ELSEVIER SCIENCE BV" "ASOC QUIMICOS" ...
##  $ PI : chr  "HOBOKEN" "HOBOKEN" "AMSTERDAM" "BARCELONA" ...
##  $ PA : chr  "111 RIVER ST, HOBOKEN 07030-5774, NJ USA" "111 RIVER ST, HOBOKEN 07030-5774, NJ USA" "PO BOX 211, 1000 AE AMSTERDAM, NETHERLANDS" "INST QUIMICO SARRIA, VIA AUGUSTA, 390, 08017 BARCELONA, SPAIN" ...
##  $ SN : chr  "0001-2815" "0001-6314" "0001-6918" "0001-9704" ...
##  $ EI : chr  "1399-0039" "1600-0404" "1873-6297" "" ...
##  $ J9 : chr  "TISSUE ANTIGENS" "ACTA NEUROL SCAND" "ACTA PSYCHOL" "AFINIDAD" ...
##  $ JI : chr  "Tissue Antigens" "Acta Neurol. Scand." "Acta Psychol." "Afinidad" ...
##  - attr(*, "variable.labels")= Named chr  "Publication type" "Author" "Book authors" "Editor" ...
##   ..- attr(*, "names")= chr  "PT" "AU" "BA" "BE" ...
ii <- match(db$Docs$idj, db$Journals$idj)
docs2 <- db$Docs[, c("PY", "TI")]
docs2$Journal <- db$Journals$SO[ii]
head(docs2)
##     PY
## 1 2015
## 2 2015
## 3 2015
## 4 2015
## 5 2015
## 6 2015
##                                                                                                                                            TI
## 1                                                           Fractionation of Miscanthus x giganteus via modification of the Formacell process
## 2 Role of Temperature and Pressure on the Multisensitive Multiferroic Dicyanamide Framework [TPrA][Mn(dca)(3)] with Perovskite-like Structure
## 3                                    Methane and carbon dioxide emissions from constructed wetlands receiving anaerobically pretreated sewage
## 4                               Exceptionally Inert Lanthanide(III) PARACEST MRI Contrast Agents Based on an 18-Membered Macrocyclic Platform
## 5                                                                                      Community-Acquired Pneumonia Requiring Hospitalization
## 6                                                                             Low-latency Java communication devices on RDMA-enabled networks
##                                             Journal
## 1                     INDUSTRIAL CROPS AND PRODUCTS
## 2                               INORGANIC CHEMISTRY
## 3                  SCIENCE OF THE TOTAL ENVIRONMENT
## 4                      CHEMISTRY-A EUROPEAN JOURNAL
## 5                   NEW ENGLAND JOURNAL OF MEDICINE
## 6 CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE

Documentos correspondientes a revistas:

iidj <- with(db$Journals, idj[grepl('Chem', JI)])
db$Journals$JI[iidj]
##  [1] "J. Am. Chem. Soc."                  "Inorg. Chem."                      
##  [3] "J. Chem. Phys."                     "J. Chem. Thermodyn."               
##  [5] "J. Solid State Chem."               "Chemosphere"                       
##  [7] "Antimicrob. Agents Chemother."      "Trac-Trends Anal. Chem."           
##  [9] "Eur. J. Med. Chem."                 "J. Chem. Technol. Biotechnol."     
## [11] "J. Antimicrob. Chemother."          "Food Chem."                        
## [13] "Cancer Chemother. Pharmacol."       "Int. J. Chem. Kinet."              
## [15] "Chem.-Eur. J."                      "J. Phys. Chem. A"                  
## [17] "New J. Chem."                       "Chem. Commun."                     
## [19] "Chem. Eng. J."                      "Comb. Chem. High Throughput Screen"
## [21] "Mini-Rev. Med. Chem."               "Phys. Chem. Chem. Phys."           
## [23] "Org. Biomol. Chem."                 "J. Chem Inf. Model."               
## [25] "ACS Chem. Biol."                    "Environ. Chem. Lett."              
## [27] "Anal. Bioanal. Chem."               "J. Cheminformatics"                
## [29] "J. Mat. Chem. B"
idd <- with(db$Docs, idj %in% iidj)
which(idd)
##  [1]   2   4  16  23  43  69 119 126 138 175 188 190 203 208 226 240 272 337 338
## [20] 341 342 357 382 385 386 387 388 394 411 412 428 460 483 518 525 584 600 604
## [39] 605 616 620 665 697 751 753 775 784 796 806 808 847 848
# View(db$Docs[idd, ])
head(db$Docs[idd, 1:3])
##    idd idj
## 2    2  37
## 4    4 272
## 16  16 195
## 23  23 436
## 43  43 455
## 69  69  37
##                                                                                                                                                                                                                                 TI
## 2                                                                                      Role of Temperature and Pressure on the Multisensitive Multiferroic Dicyanamide Framework [TPrA][Mn(dca)(3)] with Perovskite-like Structure
## 4                                                                                                                    Exceptionally Inert Lanthanide(III) PARACEST MRI Contrast Agents Based on an 18-Membered Macrocyclic Platform
## 16 Reduced susceptibility to biocides in Acinetobacter baumannii: association with resistance to antimicrobials, epidemiological behaviour, biological cost and effect on the expression of genes encoding porins and efflux pumps
## 23                                                       Two Catechol Siderophores, Acinetobactin and Amonabactin, Are Simultaneously Produced by Aeromonas salmonicida subsp salmonicida Sharing Part of the Biosynthetic Pathway
## 43                                                                                                                                                                        Conservation of stony materials in the built environment
## 69                                                                                                                                                         Gd3+-Based Magnetic Resonance Imaging Contrast Agent Responsive to Zn2+

Documentos correspondientes a autores:

# View(db$Authors)
iida <- with(db$Authors, ida[grepl('Abad', AF)])
db$Authors$AF[iida]
## [1] "Mato Abad, Virginia" "Abad, Maria-Jose"    "Abad Vicente, J."   
## [4] "Abada, Sabah"
idd <- with(db$AutDoc, idd[ida %in% iida])
idd
## [1] 273 291 518 586
# View(db$Docs[idd, ])
head(db$Docs[idd, 1:3])
##     idd idj
## 273 273 282
## 291 291 141
## 518 518 272
## 586 586 311
##                                                                                                                                                                                      TI
## 273                                 Classification of mild cognitive impairment and Alzheimer's Disease with machine-learning techniques using H-1 Magnetic Resonance Spectroscopy data
## 291 Identifying a population of patients suitable for the implantation of a subcutaneous defibrillator (S-ICD) among patients implanted with a conventional transvenous device (TV-ICD)
## 518           Importance of Outer-Sphere and Aggregation Phenomena in the Relaxation Properties of Phosphonated Gadolinium Complexes with Potential Applications as MRI Contrast Agents
## 586                                                                      Enhanced thermal conductivity of rheologically percolated carbon nanofiber reinforced polypropylene composites