Nietzsche corpus analysis

load required packages

require(readtext)

## Loading required package: readtext

require(LIWCalike)

## Loading required package: LIWCalike

require(quanteda)

## Loading required package: quanteda

## Package version: 2.1.2

## Parallel computing: 2 of 8 threads used.

## See https://quanteda.io for tutorials and examples.

## 
## Attaching package: 'quanteda'

## The following object is masked from 'package:utils':
## 
##     View

require(dplyr)

## Loading required package: dplyr

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

require(tidytext)

## Loading required package: tidytext

Read into R and transform into a corpus

nietzsche <- readtext("~/Dropbox/nietzsche/*")
nietzsche

## readtext object consisting of 19 documents and 0 docvars.
## # Description: df[,2] [19 × 2]
##   doc_id  text                 
##   <chr>   <chr>                
## 1 A.txt   "\"\n \nGötzen-\"..."
## 2 BGE.txt "\"\n \nJenseit\"..."
## 3 BT.txt  "\"\n \nDie Geb\"..."
## 4 CW.txt  "\"\n \nDer Fal\"..."
## 5 D.txt   "\"\n \nMorgenr\"..."
## 6 DS.txt  "\"\n \nUnzeitg\"..."
## # … with 13 more rows

nietzsche_corpus <- corpus(nietzsche)

Summarize the full corpus. This reveals that there are, for example, 1026 sentences in The Antichrist, 1856 sentences in Beyond Good and Evil, and 802 sentences in Schopenhauer as Editor.

summary(nietzsche_corpus)

## Corpus consisting of 19 documents, showing 19 documents:
## 
##     Text Types Tokens Sentences
##    A.txt  5773  31225      1023
##  BGE.txt 11081  70629      1854
##   BT.txt  8620  47967      1110
##   CW.txt  3275  14250       597
##    D.txt 13016  96480      3047
##   DS.txt  6124  29620       825
##   EH.txt  6363  36108       977
##   GM.txt  9363  55585      1230
##   GS.txt 12919  92819      3097
##  HH1.txt 13817 100232      2966
##  HH2.txt 13744  92481      2848
##   HL.txt  6298  31133       736
##  RWB.txt  5689  27711       603
##   SE.txt  6305  32736       803
##   TI.txt  5773  31225      1023
##   Z1.txt  3756  23481      1458
##   Z2.txt  4078  22589      1228
##   Z3.txt  4778  26815      1366
##   Z4.txt  4893  30266      1799

Tokenize the corpus, remove stopwords and punctuation, and get a list of the most common words:

dfmat_nietzsche <- dfm(nietzsche_corpus, stem = TRUE, remove = stopwords("de"), remove_punct = TRUE)
dfmat_nietzsche

## Document-feature matrix of: 19 documents, 42,084 features (85.0% sparse).
##          features
## docs      götzen-dämmerung hammer philosophirt friedrich nietzsch leipzig
##   A.txt                  3      4            2         2        2       1
##   BGE.txt                0      3            1         5        1       1
##   BT.txt                 0      0            0         1        1       1
##   CW.txt                 0      0            0         2        2       1
##   D.txt                  0      0            0         0        0       1
##   DS.txt                 0      0            0         2        1       1
##          features
## docs      verlag c g neumann
##   A.txt        1 1 3       1
##   BGE.txt      1 1 1       0
##   BT.txt       1 0 0       0
##   CW.txt       1 1 1       1
##   D.txt        1 0 0       0
##   DS.txt       1 0 0       0
## [ reached max_ndoc ... 13 more documents, reached max_nfeat ... 42,074 more features ]

topfeatures(dfmat_nietzsche, 20)

##       dass   menschen      leben       mehr      immer     selber       ganz 
##       5528       2173       1838       1684       1622       1216       1144 
##      macht     mensch      giebt       welt        art      gerad vielleicht 
##       1124       1100       1095        964        951        948        944 
##       zeit      geist         ja        wer       erst        sei 
##        937        934        891        868        850        842

Generate a word cloud

set.seed(100)
textplot_wordcloud(dfmat_nietzsche, min_count = 6, random_order = FALSE,
                   rotation = .25,
                   color = RColorBrewer::brewer.pal(8, "Dark2"))

Run topic models using LDA

set.seed(100)
if (require(topicmodels)) {
    my_lda_fit <- LDA(convert(dfmat_nietzsche, to = "topicmodels"), k = 8)
    get_terms(my_lda_fit, 10)
}

## Loading required package: topicmodels

##       Topic 1    Topic 2       Topic 3    Topic 4    Topic 5    Topic 6   
##  [1,] "dass"     "zarathustra" "dass"     "dass"     "dass"     "dass"    
##  [2,] "musik"    "dass"        "menschen" "menschen" "wagner"   "leben"   
##  [3,] "leben"    "selber"      "immer"    "leben"    "menschen" "mehr"    
##  [4,] "welt"     "oh"          "kunst"    "mehr"     "ideal"    "immer"   
##  [5,] "kunst"    "sprach"      "leben"    "immer"    "immer"    "menschen"
##  [6,] "mehr"     "menschen"    "mehr"     "ganz"     "mehr"     "zeit"    
##  [7,] "tragödi"  "lieb"        "selber"   "mensch"   "gerad"    "mensch"  
##  [8,] "ganz"     "gleich"      "ganz"     "zeit"     "ganz"     "erst"    
##  [9,] "menschen" "wer"         "diess"    "giebt"    "macht"    "gross"   
## [10,] "mensch"   "wahrlich"    "musik"    "macht"    "leben"    "ganz"    
##       Topic 7      Topic 8     
##  [1,] "dass"       "dass"      
##  [2,] "menschen"   "menschen"  
##  [3,] "vielleicht" "immer"     
##  [4,] "mehr"       "mehr"      
##  [5,] "immer"      "selber"    
##  [6,] "giebt"      "leben"     
##  [7,] "gerad"      "diess"     
##  [8,] "mensch"     "unser"     
##  [9,] "heut"       "macht"     
## [10,] "art"        "vielleicht"

To go beyond analyzing the whole corpus as a mass, we can also get the top features of each book

topfeatures(dfmat_nietzsche, 10, decreasing = TRUE, groups = docnames(dfmat_nietzsche))

## $A.txt
##     dass    leben     mehr      art    moral   mensch instinkt     erst 
##      185      111       77       66       58       56       55       54 
##    giebt menschen 
##       54       47 
## 
## $BGE.txt
##       dass   menschen vielleicht       mehr      immer      giebt      gerad 
##        444        204        146        140        138        123        116 
##     mensch       heut        art 
##        115        108        106 
## 
## $BT.txt
##         dass        musik      tragödi        kunst         welt        leben 
##          280          172          147          124          113           91 
## dionysischen       mythus   dionysisch        natur 
##           89           79           78           77 
## 
## $CW.txt
##    wagner     musik      dass      ganz      mehr     macht     kunst      wort 
##       179        87        85        33        28        27        26        26 
## geschmack     leben 
##        25        24 
## 
## $D.txt
##     dass menschen   selber     mehr    immer    unser    diess    macht 
##      613      261      207      204      191      187      183      163 
##    leben    giebt 
##      140      134 
## 
## $DS.txt
##      dass   strauss         s    kultur deutschen   philist       sei   glauben 
##       240       146        76        56        50        50        47        45 
##     recht     gerad 
##        43        43 
## 
## $EH.txt
##        dass       leben zarathustra        erst       immer        mehr 
##         227          82          77          63          61          61 
##        wort      wagner   deutschen     begriff 
##          61          59          58          55 
## 
## $GM.txt
##     dass menschen    ideal    immer    gerad     mehr     ganz    leben 
##      308      127      116      105      101       93       88       87 
##    macht   mensch 
##       85       80 
## 
## $GS.txt
##       dass   menschen      immer      leben       mehr     selber       ganz 
##        577        239        228        207        186        178        138 
## vielleicht      macht        art 
##        137        126        123 
## 
## $HH1.txt
##     dass menschen     mehr    immer    leben   mensch    macht    giebt 
##      666      383      213      207      206      154      144      139 
##     ganz    diess 
##      139      139 
## 
## $HH2.txt
##     dass menschen    immer   selber    leben     mehr    diess    kunst 
##      523      200      181      157      154      148      139      123 
##     ganz     zeit 
##      123      123 
## 
## $HL.txt
##       dass      leben       mehr       zeit   menschen    histori      immer 
##        226        137         81         81         80         79         76 
## historisch  geschicht     mensch 
##         56         55         53 
## 
## $RWB.txt
##     dass   wagner    kunst    musik    leben     ganz menschen     mehr 
##      135      115      107       80       70       66       64       61 
## künstler    immer 
##       54       53 
## 
## $SE.txt
##       dass   menschen      leben       mehr schopenhau      gerad       zeit 
##        251        129        108         86         71         68         67 
## philosophi     mensch        gar 
##         64         57         56 
## 
## $TI.txt
##     dass    leben     mehr      art    moral   mensch instinkt     erst 
##      185      111       77       66       58       56       55       54 
##    giebt menschen 
##       54       47 
## 
## $Z1.txt
## zarathustra        dass        lieb      selber      sprach        leib 
##         137          87          84          67          55          53 
##        mehr       leben       geist      tugend 
##          52          52          52          51 
## 
## $Z2.txt
##        dass zarathustra      selber    wahrlich      gleich       leben 
##         153          94          84          72          61          60 
##       diess      sprach        will         ach 
##          54          53          52          52 
## 
## $Z3.txt
##        dass          oh zarathustra      selber         wer        lieb 
##         185         140          95          93          74          57 
##        seel      gleich       schon    wahrlich 
##          52          51          51          51 
## 
## $Z4.txt
## zarathustra        dass    menschen          oh      sprach      selber 
##         265         158         110         108         104          97 
##       schon        gott         wer      gleich 
##          75          68          66          64

We can use hierarchical clustering to establish the pairwise similarity of all books, then plot the results as a dendrogram.

tstat_dist <- textstat_dist(dfm_weight(dfmat_nietzsche, scheme = "prop"))
nietzsche_cluster <- hclust(as.dist(tstat_dist))
nietzsche_cluster$labels <- docnames(dfmat_nietzsche)
plot(nietzsche_cluster, xlab = "", sub = "",
     main = "Euclidean Distance on Normalized Token Frequency")

To get a better sense of which terms are distinctively associated with which books, calculate term frequency-inverse document frequency (tf-idf).

tfidf_nietzsche <- dfm_tfidf(dfmat_nietzsche)
transposetfidf_nietzsche <- t(tfidf_nietzsche)
tfidf.df <- as.data.frame(transposetfidf_nietzsche)

## Warning: 'as.data.frame.dfm' is deprecated.
## Use 'convert(x, to = "data.frame")' instead.
## See help("Deprecated")

a <- tfidf.df[order(tfidf.df$A.txt, decreasing = TRUE),]
head(a)

##        doc_id     A.txt   BGE.txt     BT.txt   CW.txt     D.txt    DS.txt
## 703  instinkt 13.054850 12.817489  1.1868046 2.136248 0.0000000 0.4747218
## 481     bloss 10.206519  1.898887  0.4747218 3.085692 0.0000000 1.1868046
## 561  décadent  8.797017  0.000000  0.0000000 7.443630 0.0000000 0.0000000
## 671  décadenc  7.443630  0.000000  0.0000000 8.797017 0.0000000 0.0000000
## 519    sokrat  6.785460  1.995724 11.5751966 0.000000 0.7982894 0.0000000
## 3430    l'art  6.413059  3.206529  0.0000000 0.000000 0.0000000 0.0000000
##          EH.txt     GM.txt    GS.txt  HH1.txt   HH2.txt    HL.txt RWB.txt
## 703   8.5449930 10.4438803 2.8483310 0.000000 0.2373609 0.0000000       0
## 481   9.2570757  3.7977747 0.2373609 0.000000 0.0000000 0.7120827       0
## 561  10.1504041  0.0000000 0.0000000 0.000000 0.0000000 0.0000000       0
## 671   4.0601617  0.0000000 0.0000000 0.000000 0.0000000 0.0000000       0
## 519   0.9978618  0.3991447 1.7961512 1.397006 1.3970065 0.1995724       0
## 3430  0.0000000  0.0000000 0.0000000 0.000000 0.0000000 0.0000000       0
##         SE.txt    TI.txt Z1.txt Z2.txt Z3.txt Z4.txt
## 703  0.2373609 13.054850      0      0      0      0
## 481  0.9494437 10.206519      0      0      0      0
## 561  0.0000000  8.797017      0      0      0      0
## 671  0.0000000  7.443630      0      0      0      0
## 519  0.3991447  6.785460      0      0      0      0
## 3430 0.0000000  6.413059      0      0      0      0

bge <- tfidf.df[order(tfidf.df$BGE.txt, decreasing = TRUE),]
head(bge)

##           doc_id      A.txt   BGE.txt    BT.txt    CW.txt    D.txt    DS.txt
## 703     instinkt 13.0548504 12.817489 1.1868046 2.1362482 0.000000 0.4747218
## 2344      europa  0.9888615 12.031148 0.4944307 0.6592410 4.944307 0.0000000
## 405        moral  5.9544158  9.547598 1.1292858 1.3346104 7.597013 0.3079870
## 5232       ideen  0.0000000  9.015927 1.1269908 0.0000000 0.000000 0.7513272
## 226  philosophen  2.3612339  8.931624 0.3079870 0.7186364 2.463896 0.1026623
## 4903  hauptstück  0.0000000  8.799512 0.0000000 0.0000000 0.000000 0.0000000
##         EH.txt    GM.txt   GS.txt  HH1.txt   HH2.txt    HL.txt   RWB.txt
## 703  8.5449930 10.443880 2.848331 0.000000 0.2373609 0.0000000 0.0000000
## 2344 1.6481025  3.625825 5.933169 2.142533 3.2962050 0.0000000 0.1648102
## 405  4.3118184  3.901169 4.619805 2.874546 2.7718832 0.4106494 0.0000000
## 5232 0.7513272  2.253982 2.253982 0.000000 0.7513272 0.0000000 0.0000000
## 226  1.2319481  3.079870 3.695844 3.285195 1.2319481 0.2053247 0.4106494
## 4903 0.0000000  0.000000 0.000000 8.799512 0.0000000 0.0000000 0.0000000
##         SE.txt     TI.txt    Z1.txt Z2.txt Z3.txt    Z4.txt
## 703  0.2373609 13.0548504 0.0000000      0      0 0.0000000
## 2344 0.0000000  0.9888615 0.0000000      0      0 0.3296205
## 405  0.1026623  5.9544158 0.2053247      0      0 0.0000000
## 5232 0.7513272  0.0000000 0.0000000      0      0 0.0000000
## 226  5.3384418  2.3612339 0.0000000      0      0 0.0000000
## 4903 0.0000000  0.0000000 0.0000000      0      0 0.0000000

bt <- tfidf.df[order(tfidf.df$BT.txt, decreasing = TRUE),]
head(bt)

##              doc_id     A.txt BGE.txt   BT.txt    CW.txt D.txt DS.txt    EH.txt
## 12466       euripid 0.0000000       0 57.68569 0.0000000     0      0 0.0000000
## 3048   dionysischen 4.0584852       0 51.60074 0.0000000     0      0 4.6382688
## 11768      dionysus 0.0000000       0 49.87139 0.0000000     0      0 0.0000000
## 11534          chor 0.0000000       0 43.01984 0.0000000     0      0 0.9777236
## 11453        mythus 0.0000000       0 39.54759 0.5006024     0      0 0.0000000
## 3099  apollinischen 0.6766936       0 39.24823 0.0000000     0      0 0.0000000
##       GM.txt   GS.txt   HH1.txt  HH2.txt    HL.txt  RWB.txt    SE.txt    TI.txt
## 12466      0 0.000000 0.9777236 0.000000 0.0000000 0.000000 0.0000000 0.0000000
## 3048       0 1.739351 0.0000000 0.000000 0.0000000 0.000000 0.0000000 4.0584852
## 11768      0 0.000000 0.0000000 0.000000 0.0000000 0.000000 0.0000000 0.0000000
## 11534      0 0.000000 0.0000000 0.000000 0.0000000 0.000000 0.0000000 0.0000000
## 11453      0 0.000000 1.5018071 1.501807 0.0000000 5.506626 0.5006024 0.0000000
## 3099       0 0.000000 0.0000000 0.000000 0.6766936 0.000000 0.0000000 0.6766936
##       Z1.txt Z2.txt Z3.txt Z4.txt
## 12466      0      0      0      0
## 3048       0      0      0      0
## 11768      0      0      0      0
## 11534      0      0      0      0
## 11453      0      0      0      0
## 3099       0      0      0      0

cw <- tfidf.df[order(tfidf.df$CW.txt, decreasing = TRUE),]
head(cw)

##         doc_id     A.txt   BGE.txt    BT.txt    CW.txt    D.txt    DS.txt
## 2513    wagner 0.3296205 2.4721537  1.153672 29.501035 0.659241 0.0000000
## 16047    brahm 0.0000000 0.0000000  0.000000 10.230029 0.000000 0.0000000
## 15395  wagnern 0.0000000 0.0000000  0.000000  9.619588 0.000000 0.0000000
## 422      musik 0.9239611 4.1064937 17.657923  8.931624 6.467728 0.5133117
## 671   décadenc 7.4436297 0.0000000  0.000000  8.797017 0.000000 0.0000000
## 10363    bizet 0.0000000 0.9777236  0.000000  7.821789 0.000000 0.0000000
##         EH.txt    GM.txt    GS.txt   HH1.txt   HH2.txt    HL.txt   RWB.txt
## 2513  9.723805 2.3073435 2.6369640 0.3296205 0.9888615 0.0000000 18.953179
## 16047 0.000000 0.0000000 0.0000000 0.0000000 0.0000000 0.0000000  0.000000
## 15395 3.206529 0.0000000 0.8016323 0.0000000 0.0000000 0.0000000  0.000000
## 422   2.669221 0.9239611 6.6730522 4.2091560 9.2396108 0.2053247  8.212987
## 671   4.060162 0.0000000 0.0000000 0.0000000 0.0000000 0.0000000  0.000000
## 10363 0.000000 0.0000000 0.0000000 0.0000000 0.0000000 0.0000000  0.000000
##          SE.txt    TI.txt Z1.txt Z2.txt Z3.txt Z4.txt
## 2513  0.6592410 0.3296205      0      0      0      0
## 16047 0.0000000 0.0000000      0      0      0      0
## 15395 0.0000000 0.0000000      0      0      0      0
## 422   0.5133117 0.9239611      0      0      0      0
## 671   0.0000000 7.4436297      0      0      0      0
## 10363 0.0000000 0.0000000      0      0      0      0

d <- tfidf.df[order(tfidf.df$D.txt, decreasing = TRUE),]
head(d)

##             doc_id     A.txt   BGE.txt   BT.txt CW.txt    D.txt    DS.txt
## 16259        diess 0.0000000 0.0000000 0.000000      0 51.01191 0.0000000
## 3474         unser 0.2053247 0.9239611 5.338442      0 19.19786 4.0038313
## 16280       sodass 0.0000000 0.0000000 0.000000      0 15.07437 0.0000000
## 16260 sittlichkeit 0.0000000 0.0000000 0.000000      0 13.14823 0.3756636
## 16263     desshalb 0.0000000 0.0000000 0.000000      0 12.02124 0.0000000
## 16272    intellect 0.0000000 0.0000000 0.000000      0 11.01589 0.0000000
##       EH.txt    GM.txt    GS.txt    HH1.txt   HH2.txt   HL.txt    RWB.txt
## 16259      0 0.0000000 30.105389 38.7467505 38.746751 0.000000 10.3138832
## 3474       0 0.1026623 10.676884 11.2928576  9.958247 4.209156  3.1825326
## 16280      0 0.0000000  6.377620  0.5797836  7.537187 0.000000  0.5797836
## 16260      0 2.2539817  2.629645  0.7513272  1.126991 0.000000  0.3756636
## 16263      0 0.0000000  4.883627 27.7991074 21.412826 0.000000  0.0000000
## 16272      0 0.0000000  5.797836 14.4945899  5.218052 0.000000  0.5797836
##          SE.txt    TI.txt    Z1.txt     Z2.txt    Z3.txt     Z4.txt
## 16259 0.2787536 0.0000000 9.4776224 15.0526945 7.5263472 10.8713904
## 3474  2.3612339 0.2053247 0.2053247  0.0000000 0.0000000  0.1026623
## 16280 0.0000000 0.0000000 0.0000000  0.0000000 0.0000000  0.0000000
## 16260 1.5026545 0.0000000 0.0000000  0.0000000 0.0000000  0.0000000
## 16263 0.0000000 0.0000000 2.2539817  0.3756636 0.3756636  0.3756636
## 16272 0.0000000 0.0000000 0.0000000  0.0000000 0.0000000  0.0000000

ds <- tfidf.df[order(tfidf.df$DS.txt, decreasing = TRUE),]
head(ds)

##              doc_id     A.txt  BGE.txt   BT.txt    CW.txt     D.txt   DS.txt
## 2421        strauss 0.3756636 0.000000 0.000000 0.3756636 0.0000000 54.84689
## 20907        kultur 0.0000000 0.000000 0.000000 0.0000000 0.0000000 54.75252
## 21026       philist 0.0000000 0.000000 0.000000 0.0000000 0.0000000 33.83468
## 21293        magist 0.0000000 0.000000 0.000000 0.0000000 0.0000000 33.24759
## 11338             s 0.0000000 1.298044 2.271578 0.3245111 0.3245111 24.66284
## 21267 straussischen 0.0000000 0.000000 0.000000 0.0000000 0.0000000 20.46006
##         EH.txt   GM.txt    GS.txt HH1.txt   HH2.txt    HL.txt RWB.txt    SE.txt
## 2421  1.126991 0.000000 0.0000000       0 0.3756636 0.3756636       0  0.000000
## 20907 0.000000 0.000000 0.0000000       0 0.0000000 0.0000000       0 47.908457
## 21026 0.000000 0.000000 0.6766936       0 0.6766936 0.0000000       0  1.353387
## 21293 0.000000 0.000000 0.0000000       0 0.0000000 0.0000000       0  0.000000
## 11338 1.298044 5.516689 0.3245111       0 0.3245111 0.0000000       0  0.000000
## 21267 0.000000 0.000000 0.0000000       0 0.0000000 0.0000000       0  0.000000
##          TI.txt Z1.txt Z2.txt    Z3.txt Z4.txt
## 2421  0.3756636      0      0 0.3756636      0
## 20907 0.0000000      0      0 0.0000000      0
## 21026 0.0000000      0      0 0.0000000      0
## 21293 0.0000000      0      0 0.0000000      0
## 11338 0.0000000      0      0 0.0000000      0
## 21267 0.0000000      0      0 0.0000000      0

eh <- tfidf.df[order(tfidf.df$EH.txt, decreasing = TRUE),]
head(eh)

##            doc_id      A.txt   BGE.txt    BT.txt     CW.txt    D.txt   DS.txt
## 1307  zarathustra  0.7982894 0.1995724 1.1974341  0.1995724 0.000000 0.000000
## 15990           <  0.0000000 0.0000000 0.0000000  0.6766936 2.030081 0.000000
## 15991           >  0.0000000 0.0000000 0.0000000  0.6766936 2.030081 0.000000
## 561      décadent  8.7970169 0.0000000 0.0000000  7.4436297 0.000000 0.000000
## 2513       wagner  0.3296205 2.4721537 1.1536717 29.5010345 0.659241 0.000000
## 481         bloss 10.2065194 1.8988873 0.4747218  3.0856919 0.000000 1.186805
##          EH.txt    GM.txt    GS.txt   HH1.txt   HH2.txt    HL.txt  RWB.txt
## 1307  15.367071 0.7982894 0.9978618 0.0000000 0.0000000 0.0000000  0.00000
## 15990 14.210566 0.0000000 0.0000000 0.6766936 0.0000000 0.0000000  0.00000
## 15991 14.210566 0.0000000 0.0000000 0.6766936 0.0000000 0.0000000  0.00000
## 561   10.150404 0.0000000 0.0000000 0.0000000 0.0000000 0.0000000  0.00000
## 2513   9.723805 2.3073435 2.6369640 0.3296205 0.9888615 0.0000000 18.95318
## 481    9.257076 3.7977747 0.2373609 0.0000000 0.0000000 0.7120827  0.00000
##          SE.txt     TI.txt   Z1.txt  Z2.txt   Z3.txt   Z4.txt
## 1307  0.0000000  0.7982894 27.34141 18.7598 18.95937 52.88667
## 15990 0.0000000  0.0000000  0.00000  0.0000  0.00000  0.00000
## 15991 0.0000000  0.0000000  0.00000  0.0000  0.00000  0.00000
## 561   0.0000000  8.7970169  0.00000  0.0000  0.00000  0.00000
## 2513  0.6592410  0.3296205  0.00000  0.0000  0.00000  0.00000
## 481   0.9494437 10.2065194  0.00000  0.0000  0.00000  0.00000

gm <- tfidf.df[order(tfidf.df$GM.txt, decreasing = TRUE),]
head(gm)

##            doc_id     A.txt   BGE.txt    BT.txt    CW.txt     D.txt    DS.txt
## 12822   asketisch  0.000000  0.000000 0.6766936 0.0000000 1.3533872 0.6766936
## 18561 asketischen  0.000000  0.000000 0.0000000 0.0000000 0.6766936 0.0000000
## 2805     ressenti  1.353387  0.000000 0.0000000 0.0000000 0.0000000 0.0000000
## 25121   schuldner  0.000000  0.000000 0.0000000 0.0000000 0.0000000 0.0000000
## 241         ideal  1.437273  1.847922 1.2319481 0.7186364 2.5665585 0.3079870
## 703      instinkt 13.054850 12.817489 1.1868046 2.1362482 0.0000000 0.4747218
##          EH.txt   GM.txt   GS.txt   HH1.txt   HH2.txt    HL.txt   RWB.txt
## 12822 0.0000000 39.24823 0.000000 0.0000000 0.0000000 0.0000000 0.0000000
## 18561 0.6766936 27.06774 0.000000 0.6766936 0.0000000 0.0000000 0.0000000
## 2805  4.7368553 19.62411 0.000000 0.0000000 0.0000000 0.0000000 0.0000000
## 25121 0.0000000 14.06629 0.000000 0.0000000 0.0000000 0.0000000 0.0000000
## 241   2.7718832 11.90883 2.874546 0.4106494 1.5399351 0.1026623 0.1026623
## 703   8.5449930 10.44388 2.848331 0.0000000 0.2373609 0.0000000 0.0000000
##          SE.txt    TI.txt Z1.txt Z2.txt Z3.txt Z4.txt
## 12822 0.0000000  0.000000      0      0      0      0
## 18561 0.0000000  0.000000      0      0      0      0
## 2805  0.0000000  1.353387      0      0      0      0
## 25121 0.0000000  0.000000      0      0      0      0
## 241   0.8212987  1.437273      0      0      0      0
## 703   0.2373609 13.054850      0      0      0      0

gs <- tfidf.df[order(tfidf.df$GS.txt, decreasing = TRUE),]
head(gs)

##         doc_id     A.txt   BGE.txt   BT.txt    CW.txt    D.txt   DS.txt EH.txt
## 16259    diess 0.0000000 0.0000000 0.000000 0.0000000 51.01191 0.000000      0
## 3474     unser 0.2053247 0.9239611 5.338442 0.0000000 19.19786 4.003831      0
## 27954 chamfort 0.0000000 0.0000000 0.000000 0.0000000  0.00000 0.000000      0
## 27990   brutus 0.0000000 0.0000000 0.000000 0.0000000  0.00000 0.000000      0
## 9551   corrupt 0.0000000 3.3834680 0.000000 0.0000000  0.00000 1.353387      0
## 15482        b 0.0000000 0.0000000 0.000000 0.6766936 10.82710 0.000000      0
##          GM.txt    GS.txt   HH1.txt   HH2.txt   HL.txt   RWB.txt    SE.txt
## 16259 0.0000000 30.105389 38.746751 38.746751 0.000000 10.313883 0.2787536
## 3474  0.1026623 10.676884 11.292858  9.958247 4.209156  3.182533 2.3612339
## 27954 0.0000000 10.230029  0.000000  0.000000 0.000000  0.000000 0.0000000
## 27990 0.0000000  9.777236  0.000000  0.000000 0.000000  0.000000 0.9777236
## 9551  0.0000000  8.797017  1.353387  0.000000 0.000000  0.000000 0.0000000
## 15482 0.0000000  8.120323  0.000000  2.706774 0.000000  0.000000 0.0000000
##          TI.txt    Z1.txt   Z2.txt   Z3.txt     Z4.txt
## 16259 0.0000000 9.4776224 15.05269 7.526347 10.8713904
## 3474  0.2053247 0.2053247  0.00000 0.000000  0.1026623
## 27954 0.0000000 0.0000000  0.00000 0.000000  0.0000000
## 27990 0.0000000 0.0000000  0.00000 0.000000  0.0000000
## 9551  0.0000000 0.0000000  0.00000 0.000000  0.0000000
## 15482 0.0000000 0.0000000  0.00000 0.000000  0.0000000

hh1 <- tfidf.df[order(tfidf.df$HH1.txt, decreasing = TRUE),]
head(hh1)

##               doc_id    A.txt  BGE.txt    BT.txt    CW.txt     D.txt    DS.txt
## 16259          diess 0.000000 0.000000 0.0000000 0.0000000 51.011909 0.0000000
## 16263       desshalb 0.000000 0.000000 0.0000000 0.0000000 12.021236 0.0000000
## 2339          cultur 2.254635 2.785137 7.4270317 0.1326256  2.917762 0.0000000
## 209       handlungen 1.397006 1.995724 0.9978618 0.0000000  9.579473 0.1995724
## 16272      intellect 0.000000 0.000000 0.0000000 0.0000000 11.015888 0.0000000
## 28176 ueberzeugungen 0.000000 0.000000 0.0000000 0.0000000  0.000000 0.0000000
##          EH.txt   GM.txt    GS.txt  HH1.txt   HH2.txt   HL.txt    RWB.txt
## 16259 0.0000000 0.000000 30.105389 38.74675 38.746751 0.000000 10.3138832
## 16263 0.0000000 0.000000  4.883627 27.79911 21.412826 0.000000  0.0000000
## 2339  1.4588812 1.326256  2.652511 15.51719  4.111393 4.244018  1.4588812
## 209   0.3991447 1.197434  2.794013 15.36707  3.193158 0.000000  0.3991447
## 16272 0.0000000 0.000000  5.797836 14.49459  5.218052 0.000000  0.5797836
## 28176 0.0000000 0.000000  4.809794 13.62775  2.404897 0.000000  0.0000000
##          SE.txt   TI.txt   Z1.txt     Z2.txt    Z3.txt     Z4.txt
## 16259 0.2787536 0.000000 9.477622 15.0526945 7.5263472 10.8713904
## 16263 0.0000000 0.000000 2.253982  0.3756636 0.3756636  0.3756636
## 2339  1.1936301 2.254635 0.000000  0.0000000 0.0000000  0.0000000
## 209   0.0000000 1.397006 0.000000  0.0000000 0.0000000  0.0000000
## 16272 0.0000000 0.000000 0.000000  0.0000000 0.0000000  0.0000000
## 28176 0.0000000 0.000000 0.000000  0.0000000 0.0000000  0.0000000

hh2 <- tfidf.df[order(tfidf.df$HH2.txt, decreasing = TRUE),]
head(hh2)

##         doc_id     A.txt   BGE.txt   BT.txt CW.txt     D.txt   DS.txt   EH.txt
## 16259    diess 0.0000000 0.0000000 0.000000      0 51.011909 0.000000 0.000000
## 16263 desshalb 0.0000000 0.0000000 0.000000      0 12.021236 0.000000 0.000000
## 21532    autor 0.0000000 0.0000000 0.000000      0  0.000000 5.506626 1.001205
## 35896  pyrrhon 0.0000000 0.0000000 0.000000      0  0.000000 0.000000 0.000000
## 3474     unser 0.2053247 0.9239611 5.338442      0 19.197858 4.003831 0.000000
## 2752     freud 0.1648102 0.1648102 1.812913      0  4.944307 0.659241 0.000000
##          GM.txt    GS.txt   HH1.txt   HH2.txt   HL.txt    RWB.txt    SE.txt
## 16259 0.0000000 30.105389 38.746751 38.746751 0.000000 10.3138832 0.2787536
## 16263 0.0000000  4.883627 27.799107 21.412826 0.000000  0.0000000 0.0000000
## 21532 0.0000000  0.000000  7.008433 15.518673 1.001205  0.0000000 1.0012047
## 35896 0.0000000  0.000000  0.000000 11.508782 0.000000  0.0000000 0.0000000
## 3474  0.1026623 10.676884 11.292858  9.958247 4.209156  3.1825326 2.3612339
## 2752  1.1536717  3.625825  6.757220  9.723805 0.000000  0.3296205 0.4944307
##          TI.txt    Z1.txt     Z2.txt    Z3.txt     Z4.txt
## 16259 0.0000000 9.4776224 15.0526945 7.5263472 10.8713904
## 16263 0.0000000 2.2539817  0.3756636 0.3756636  0.3756636
## 21532 0.0000000 0.0000000  0.0000000 0.0000000  0.0000000
## 35896 0.0000000 0.0000000  0.0000000 0.0000000  0.0000000
## 3474  0.2053247 0.2053247  0.0000000 0.0000000  0.1026623
## 2752  0.1648102 0.0000000  0.1648102 0.0000000  0.0000000

hl <- tfidf.df[order(tfidf.df$HL.txt, decreasing = TRUE),]
head(hl)

##             doc_id     A.txt   BGE.txt    BT.txt CW.txt     D.txt DS.txt
## 37253  weltprozess 0.0000000 0.0000000 0.0000000      0 0.0000000      0
## 975        histori 0.5987171 0.5987171 0.1995724      0 0.3991447      0
## 36614 antiquarisch 0.0000000 0.0000000 0.0000000      0 0.0000000      0
## 24308 unhistorisch 0.0000000 0.0000000 0.0000000      0 0.0000000      0
## 8361  historischen 0.0000000 1.3937680 1.9512752      0 0.8362608      0
## 12313   uebermaass 0.0000000 0.0000000 4.7368553      0 0.0000000      0
##          EH.txt    GM.txt    GS.txt   HH1.txt   HH2.txt   HL.txt   RWB.txt
## 37253 0.0000000 0.0000000 0.0000000 0.0000000 0.0000000 30.69009 0.0000000
## 975   0.0000000 1.3970065 0.1995724 0.5987171 2.9935853 15.76622 0.9978618
## 36614 0.0000000 0.0000000 0.0000000 0.0000000 0.0000000 14.06629 0.0000000
## 24308 0.0000000 0.8016323 0.0000000 0.8016323 0.0000000 12.02449 0.0000000
## 8361  0.5575072 1.3937680 1.6725216 2.2300288 0.8362608 11.15014 0.2787536
## 12313 0.0000000 0.0000000 1.3533872 0.0000000 2.0300808 10.82710 0.0000000
##         SE.txt    TI.txt Z1.txt Z2.txt Z3.txt Z4.txt
## 37253 0.000000 0.0000000      0      0      0      0
## 975   1.397006 0.5987171      0      0      0      0
## 36614 0.000000 0.0000000      0      0      0      0
## 24308 0.000000 0.0000000      0      0      0      0
## 8361  0.000000 0.0000000      0      0      0      0
## 12313 0.000000 0.0000000      0      0      0      0

rwb <- tfidf.df[order(tfidf.df$RWB.txt, decreasing = TRUE),]
head(rwb)

##             doc_id     A.txt   BGE.txt    BT.txt    CW.txt     D.txt    DS.txt
## 2513        wagner 0.3296205 2.4721537  1.153672 29.501035  0.659241 0.0000000
## 10457 wagnerischen 0.0000000 0.6766936  0.000000  4.060162  0.000000 0.0000000
## 16259        diess 0.0000000 0.0000000  0.000000  0.000000 51.011909 0.0000000
## 422          musik 0.9239611 4.1064937 17.657923  8.931624  6.467728 0.5133117
## 37654   nibelungen 0.0000000 0.0000000  0.000000  0.000000  0.000000 0.0000000
## 38153         styl 0.0000000 0.0000000  0.000000  0.000000  0.000000 0.0000000
##         EH.txt    GM.txt    GS.txt    HH1.txt    HH2.txt    HL.txt   RWB.txt
## 2513  9.723805 2.3073435  2.636964  0.3296205  0.9888615 0.0000000 18.953179
## 10457 0.000000 0.0000000  0.000000  0.0000000  0.6766936 0.0000000 10.827098
## 16259 0.000000 0.0000000 30.105389 38.7467505 38.7467505 0.0000000 10.313883
## 422   2.669221 0.9239611  6.673052  4.2091560  9.2396108 0.2053247  8.212987
## 37654 0.000000 0.0000000  0.000000  0.0000000  0.0000000 0.0000000  7.672522
## 38153 0.000000 0.0000000  0.000000  0.0000000  0.0000000 0.0000000  7.672522
##          SE.txt    TI.txt   Z1.txt   Z2.txt   Z3.txt   Z4.txt
## 2513  0.6592410 0.3296205 0.000000  0.00000 0.000000  0.00000
## 10457 0.0000000 0.0000000 0.000000  0.00000 0.000000  0.00000
## 16259 0.2787536 0.0000000 9.477622 15.05269 7.526347 10.87139
## 422   0.5133117 0.9239611 0.000000  0.00000 0.000000  0.00000
## 37654 0.0000000 0.0000000 0.000000  0.00000 0.000000  0.00000
## 38153 0.0000000 0.0000000 0.000000  0.00000 0.000000  0.00000

se <- tfidf.df[order(tfidf.df$SE.txt, decreasing = TRUE),]
head(se)

##                       doc_id    A.txt   BGE.txt    BT.txt    CW.txt     D.txt
## 20907                 kultur 0.000000 0.0000000 0.0000000 0.0000000 0.0000000
## 38718            erwerbenden 0.000000 0.0000000 0.0000000 0.0000000 0.0000000
## 39153 universitätsphilosophi 0.000000 0.0000000 0.0000000 0.0000000 0.0000000
## 1573              schopenhau 1.334610 1.2319481 1.4372728 0.4106494 2.5665585
## 10914                 genius 0.000000 0.4747218 5.4593011 0.0000000 0.9494437
## 923               philosophi 1.026623 6.6730522 0.8212987 0.4106494 2.4638962
##           DS.txt   EH.txt    GM.txt    GS.txt  HH1.txt   HH2.txt    HL.txt
## 20907 54.7525219 0.000000 0.0000000 0.0000000 0.000000 0.0000000 0.0000000
## 38718  0.0000000 0.000000 0.0000000 0.0000000 0.000000 0.0000000 0.0000000
## 39153  0.0000000 0.000000 0.0000000 0.0000000 0.000000 0.0000000 0.0000000
## 1573   2.4638962 1.334610 2.5665585 2.0532468 1.847922 1.7452598 0.2053247
## 10914  1.6615264 0.000000 0.2373609 0.4747218 6.646106 0.4747218 0.4747218
## 923    0.7186364 1.437273 1.9505845 2.3612339 3.798507 2.5665585 1.0266234
##         RWB.txt    SE.txt   TI.txt Z1.txt Z2.txt Z3.txt Z4.txt
## 20907 0.0000000 47.908457 0.000000      0      0      0      0
## 38718 0.0000000  7.672522 0.000000      0      0      0      0
## 39153 0.0000000  7.672522 0.000000      0      0      0      0
## 1573  0.3079870  7.289026 1.334610      0      0      0      0
## 10914 0.9494437  7.120827 0.000000      0      0      0      0
## 923   0.6159741  6.570390 1.026623      0      0      0      0

ti <- tfidf.df[order(tfidf.df$TI.txt, decreasing = TRUE),]
head(ti)

##        doc_id     A.txt   BGE.txt     BT.txt   CW.txt     D.txt    DS.txt
## 703  instinkt 13.054850 12.817489  1.1868046 2.136248 0.0000000 0.4747218
## 481     bloss 10.206519  1.898887  0.4747218 3.085692 0.0000000 1.1868046
## 561  décadent  8.797017  0.000000  0.0000000 7.443630 0.0000000 0.0000000
## 671  décadenc  7.443630  0.000000  0.0000000 8.797017 0.0000000 0.0000000
## 519    sokrat  6.785460  1.995724 11.5751966 0.000000 0.7982894 0.0000000
## 3430    l'art  6.413059  3.206529  0.0000000 0.000000 0.0000000 0.0000000
##          EH.txt     GM.txt    GS.txt  HH1.txt   HH2.txt    HL.txt RWB.txt
## 703   8.5449930 10.4438803 2.8483310 0.000000 0.2373609 0.0000000       0
## 481   9.2570757  3.7977747 0.2373609 0.000000 0.0000000 0.7120827       0
## 561  10.1504041  0.0000000 0.0000000 0.000000 0.0000000 0.0000000       0
## 671   4.0601617  0.0000000 0.0000000 0.000000 0.0000000 0.0000000       0
## 519   0.9978618  0.3991447 1.7961512 1.397006 1.3970065 0.1995724       0
## 3430  0.0000000  0.0000000 0.0000000 0.000000 0.0000000 0.0000000       0
##         SE.txt    TI.txt Z1.txt Z2.txt Z3.txt Z4.txt
## 703  0.2373609 13.054850      0      0      0      0
## 481  0.9494437 10.206519      0      0      0      0
## 561  0.0000000  8.797017      0      0      0      0
## 671  0.0000000  7.443630      0      0      0      0
## 519  0.3991447  6.785460      0      0      0      0
## 3430 0.0000000  6.413059      0      0      0      0

z1 <- tfidf.df[order(tfidf.df$Z1.txt, decreasing = TRUE),]
head(z1)

##              doc_id     A.txt   BGE.txt    BT.txt    CW.txt      D.txt
## 1307    zarathustra 0.7982894 0.1995724 1.1974341 0.1995724  0.0000000
## 23925  übermenschen 0.0000000 0.0000000 0.0000000 0.0000000  0.0000000
## 16259         diess 0.0000000 0.0000000 0.0000000 0.0000000 51.0119090
## 5415  überflüssigen 0.0000000 1.6032647 0.0000000 0.0000000  0.0000000
## 12637      wahrlich 0.0000000 0.0000000 0.1995724 0.0000000  0.9978618
## 13170        bruder 0.0000000 0.0000000 0.7513272 0.0000000  0.3756636
##          DS.txt     EH.txt    GM.txt     GS.txt   HH1.txt    HH2.txt    HL.txt
## 1307  0.0000000 15.3670713 0.7982894  0.9978618  0.000000  0.0000000 0.0000000
## 23925 0.0000000  1.7393508 0.0000000  0.0000000  0.000000  0.0000000 0.0000000
## 16259 0.0000000  0.0000000 0.0000000 30.1053889 38.746751 38.7467505 0.0000000
## 5415  0.0000000  0.0000000 0.8016323  0.0000000  0.000000  0.0000000 0.0000000
## 12637 0.3991447  0.7982894 0.0000000  1.9957235  0.000000  0.1995724 0.1995724
## 13170 0.0000000  0.0000000 0.0000000  0.3756636  1.126991  0.7513272 0.0000000
##          RWB.txt    SE.txt    TI.txt    Z1.txt   Z2.txt    Z3.txt     Z4.txt
## 1307   0.0000000 0.0000000 0.7982894 27.341413 18.75980 18.959374 52.8866740
## 23925  0.0000000 0.0000000 0.0000000 10.436105  6.37762  1.159567  1.1595672
## 16259 10.3138832 0.2787536 0.0000000  9.477622 15.05269  7.526347 10.8713904
## 5415   0.0000000 0.0000000 0.0000000  8.016323  0.00000  0.000000  0.0000000
## 12637  0.0000000 0.3991447 0.0000000  7.384177 14.36921 10.178190  7.3841771
## 13170  0.7513272 0.0000000 0.0000000  6.010618  0.00000  0.000000  0.7513272

z2 <- tfidf.df[order(tfidf.df$Z2.txt, decreasing = TRUE),]
head(z2)

##            doc_id     A.txt   BGE.txt    BT.txt    CW.txt      D.txt    DS.txt
## 1307  zarathustra 0.7982894 0.1995724 1.1974341 0.1995724  0.0000000 0.0000000
## 16259       diess 0.0000000 0.0000000 0.0000000 0.0000000 51.0119090 0.0000000
## 12637    wahrlich 0.0000000 0.0000000 0.1995724 0.0000000  0.9978618 0.3991447
## 40177   feuerhund 0.0000000 0.0000000 0.0000000 0.0000000  0.0000000 0.0000000
## 22944    gesindel 0.0000000 0.0000000 0.0000000 0.0000000  0.0000000 0.0000000
## 8635      krüppel 0.0000000 0.8016323 0.0000000 0.0000000  0.0000000 0.0000000
##           EH.txt    GM.txt     GS.txt  HH1.txt    HH2.txt    HL.txt  RWB.txt
## 1307  15.3670713 0.7982894  0.9978618  0.00000  0.0000000 0.0000000  0.00000
## 16259  0.0000000 0.0000000 30.1053889 38.74675 38.7467505 0.0000000 10.31388
## 12637  0.7982894 0.0000000  1.9957235  0.00000  0.1995724 0.1995724  0.00000
## 40177  0.0000000 0.0000000  0.0000000  0.00000  0.0000000 0.0000000  0.00000
## 22944  1.7393508 0.0000000  0.0000000  0.00000  0.5797836 0.0000000  0.00000
## 8635   0.0000000 0.0000000  0.0000000  0.00000  0.0000000 0.0000000  0.00000
##          SE.txt    TI.txt    Z1.txt    Z2.txt    Z3.txt     Z4.txt
## 1307  0.0000000 0.7982894 27.341413 18.759801 18.959374 52.8866740
## 16259 0.2787536 0.0000000  9.477622 15.052694  7.526347 10.8713904
## 12637 0.3991447 0.0000000  7.384177 14.369210 10.178190  7.3841771
## 40177 0.0000000 0.0000000  0.000000 11.508782  0.000000  0.0000000
## 22944 0.0000000 0.0000000  0.000000  6.957403  1.159567  2.3191344
## 8635  0.0000000 0.0000000  0.000000  6.413059  0.000000  0.8016323

z3 <- tfidf.df[order(tfidf.df$Z3.txt, decreasing = TRUE),]
head(z3)

##               doc_id     A.txt   BGE.txt    BT.txt    CW.txt     D.txt
## 1307     zarathustra 0.7982894 0.1995724 1.1974341 0.1995724 0.0000000
## 265               oh 0.7957534 2.1220090 0.5305023 0.1326256 2.9177624
## 39568      zerbrecht 0.0000000 0.0000000 0.0000000 0.0000000 0.0000000
## 15778         tafeln 0.0000000 0.0000000 0.0000000 0.6766936 0.0000000
## 12637       wahrlich 0.0000000 0.0000000 0.1995724 0.0000000 0.9978618
## 41218 hochzeitlichen 0.0000000 0.0000000 0.0000000 0.0000000 0.0000000
##          DS.txt     EH.txt    GM.txt    GS.txt HH1.txt   HH2.txt    HL.txt
## 1307  0.0000000 15.3670713 0.7982894 0.9978618       0 0.0000000 0.0000000
## 265   0.0000000  1.8567579 1.7241323 5.0397715       0 0.3978767 0.0000000
## 39568 0.0000000  0.0000000 0.0000000 0.0000000       0 0.0000000 0.0000000
## 15778 0.0000000  2.0300808 0.0000000 0.0000000       0 0.0000000 0.0000000
## 12637 0.3991447  0.7982894 0.0000000 1.9957235       0 0.1995724 0.1995724
## 41218 0.0000000  0.0000000 0.0000000 0.0000000       0 0.0000000 0.0000000
##       RWB.txt    SE.txt    TI.txt     Z1.txt    Z2.txt    Z3.txt    Z4.txt
## 1307        0 0.0000000 0.7982894 27.3414126 18.759801 18.959374 52.886674
## 265         0 0.0000000 0.7957534  0.9283790  3.713516 18.567579 14.323561
## 39568       0 0.0000000 0.0000000  0.9777236  0.000000 13.688130  0.000000
## 15778       0 0.0000000 0.0000000  2.7067744  0.000000 11.503791  0.000000
## 12637       0 0.3991447 0.0000000  7.3841771 14.369210 10.178190  7.384177
## 41218       0 0.0000000 0.0000000  0.0000000  0.000000  8.951275  0.000000

z4 <- tfidf.df[order(tfidf.df$Z4.txt, decreasing = TRUE),]
head(z4)

##            doc_id     A.txt   BGE.txt    BT.txt    CW.txt     D.txt DS.txt
## 1307  zarathustra 0.7982894 0.1995724 1.1974341 0.1995724  0.000000      0
## 265            oh 0.7957534 2.1220090 0.5305023 0.1326256  2.917762      0
## 40871         i-a 0.0000000 0.0000000 0.0000000 0.0000000  0.000000      0
## 33338  hässlichst 0.0000000 0.0000000 0.0000000 0.0000000  0.000000      0
## 16259       diess 0.0000000 0.0000000 0.0000000 0.0000000 51.011909      0
## 41389    blutegel 0.0000000 0.0000000 0.0000000 0.0000000  0.000000      0
##          EH.txt    GM.txt     GS.txt  HH1.txt    HH2.txt HL.txt  RWB.txt
## 1307  15.367071 0.7982894  0.9978618  0.00000  0.0000000      0  0.00000
## 265    1.856758 1.7241323  5.0397715  0.00000  0.3978767      0  0.00000
## 40871  0.000000 0.0000000  0.0000000  0.00000  0.0000000      0  0.00000
## 33338  0.000000 0.0000000  0.0000000  0.00000  0.9777236      0  0.00000
## 16259  0.000000 0.0000000 30.1053889 38.74675 38.7467505      0 10.31388
## 41389  0.000000 0.0000000  0.0000000  0.00000  0.0000000      0  0.00000
##          SE.txt    TI.txt    Z1.txt    Z2.txt     Z3.txt   Z4.txt
## 1307  0.0000000 0.7982894 27.341413 18.759801 18.9593737 52.88667
## 265   0.0000000 0.7957534  0.928379  3.713516 18.5675791 14.32356
## 40871 0.0000000 0.0000000  0.000000  0.000000  0.9777236 12.71041
## 33338 0.0000000 0.0000000  0.000000  0.000000  0.0000000 11.73268
## 16259 0.2787536 0.0000000  9.477622 15.052694  7.5263472 10.87139
## 41389 0.0000000 0.0000000  0.000000  0.000000  0.0000000 10.23003