********** TRAINING AND TESTING REPORT **********
Training file: training-data-set-70.txt

best params:{'c1': 0.025397838188738985, 'c2': 0.010943674737961755}
best CV score:0.866151069813274
model size: 0.15M

Flat F1: 0.7919663066130411
             precision    recall  f1-score   support

         OD      1.000     0.818     0.900        22
         pH      1.000     1.000     1.000         8
  Technique      0.955     0.913     0.933        23
        Med      1.000     0.925     0.961        53
       Temp      1.000     0.724     0.840        29
       Vess      1.000     1.000     1.000         1
       Agit      0.000     0.000     0.000         0
      Phase      0.882     1.000     0.938        15
        Air      0.556     0.362     0.439        69
       Anti      1.000     1.000     1.000        11
     Strain      0.000     0.000     0.000         1
      Gtype      0.886     0.824     0.854        85
  Substrain      0.000     0.000     0.000         0
       Supp      0.745     0.806     0.774       134
   Gversion      0.000     0.000     0.000         0

avg / total      0.826     0.769     0.792       451


Top likely transitions:
Temp   -> Temp    5.760887
Med    -> Med     5.678477
Anti   -> Anti    5.326115
Agit   -> Agit    5.286360
Supp   -> Supp    5.206097
Gtype  -> Gtype   5.054366
OD     -> OD      4.762019
O      -> O       4.584226
Gversion -> Gversion 4.568451
Phase  -> Phase   4.187286
Technique -> Technique 4.138629
Air    -> Air     4.000035
pH     -> pH      2.729965
Substrain -> Gtype   1.627917
O      -> Technique 1.124864
O      -> Gtype   0.872372
Technique -> Air     0.731367
Gtype  -> Supp    0.637844
Gtype  -> Air     0.628544
Gtype  -> pH      0.590887
Temp   -> O       0.369557
Air    -> O       0.111207
O      -> Temp    0.069854
Strain -> O       0.060323
O      -> pH      0.012969
O      -> Gversion 0.008119
O      -> Anti    0.005882
O      -> Strain  -0.000031
O      -> Substrain -0.000043
Supp   -> Gversion -0.000207
Vess   -> O       -0.012750
Phase  -> Anti    -0.021251
Supp   -> OD      -0.026454
Gtype  -> OD      -0.036196
O      -> Phase   -0.036759
pH     -> O       -0.045025
Phase  -> Air     -0.050032
Phase  -> Technique -0.056805
Gtype  -> Technique -0.057557
Supp   -> Phase   -0.061193
Med    -> O       -0.061484
O      -> Supp    -0.071678
Agit   -> O       -0.081937
Anti   -> Gtype   -0.086639
Anti   -> Phase   -0.088763
OD     -> Med     -0.098634
Supp   -> pH      -0.101552
Supp   -> O       -0.105915
Gtype  -> Phase   -0.115027
pH     -> Supp    -0.117891


Top unlikely transitions:
O      -> Supp    -0.071678
Agit   -> O       -0.081937
Anti   -> Gtype   -0.086639
Anti   -> Phase   -0.088763
OD     -> Med     -0.098634
Supp   -> pH      -0.101552
Supp   -> O       -0.105915
Gtype  -> Phase   -0.115027
pH     -> Supp    -0.117891
Gtype  -> Gversion -0.121895
Anti   -> O       -0.201256
Technique -> Supp    -0.229809
Gversion -> O       -0.230521
Med    -> Air     -0.267137
O      -> Agit    -0.281266
Gversion -> Supp    -0.287197
Supp   -> Gtype   -0.291702
Anti   -> Supp    -0.353269
Technique -> OD      -0.362376
Technique -> O       -0.381273
Supp   -> Anti    -0.420491
Anti   -> Temp    -0.442117
Air    -> OD      -0.473267
Temp   -> Air     -0.506469
O      -> OD      -0.516111
Air    -> Agit    -0.518285
OD     -> Supp    -0.549851
OD     -> O       -0.692796
Gtype  -> O       -0.708611
Supp   -> Air     -0.710521
Gtype  -> Anti    -0.742633
Gtype  -> Med     -0.747450
Phase  -> Med     -0.781570
OD     -> Air     -0.812786
O      -> Med     -0.889466
Agit   -> Air     -0.930785
Phase  -> OD      -0.941459
Technique -> pH      -1.069982
Phase  -> Supp    -1.109907
Air    -> Med     -1.179927
Air    -> Phase   -1.299860
Substrain -> O       -1.308161
Temp   -> Med     -1.308517
Phase  -> O       -1.327800
Air    -> Temp    -1.331056
Air    -> Supp    -1.346362
O      -> Air     -1.390028
Technique -> Gtype   -1.424338
Supp   -> Med     -1.619256
Med    -> Supp    -2.800528


Top positive:
5.583316 Air      b'word:Aerobic'
5.568452 O        b'lemma:_'
5.568452 O        b'word:_'
5.408845 O        b'word:Cra'
4.999592 Air      b'lemma:anaerobic'
4.519603 Supp     b'-1:word:Cra'
4.085441 Technique b'word:ChIP-Seq'
4.045495 Gtype    b'lemma:wt'
4.028624 Phase    b'lemma:exponential'
4.028624 Phase    b'word:exponential'
4.028624 Phase    b'lemma:stationary'
4.028624 Phase    b'word:stationary'
3.845256 Gtype    b'lemma:wild-type'
3.774295 Supp     b'lemma:Iron'
3.774295 Supp     b'word:Iron'
3.774295 Supp     b'+1:word:Deficient'
3.734294 O        b'lemma:-'
3.734294 O        b'word:-'
3.706486 Supp     b'lemma:nh4cl'
3.556725 O        b'+1:postag:RB'
3.535557 Phase    b'lemma:mid-log'
3.535557 Phase    b'word:mid-log'
3.518403 Air      b'word:Anaerobic'
3.506387 Air      b'postag:RB'
3.497482 O        b'-1:lemma:ChIP-exo'
3.467179 Med      b'lemma:MOPS'
3.467179 Med      b'word:MOPS'
3.455080 Gtype    b'word:WT'
3.454991 Technique b'lemma:ChIP-exo'
3.420923 Gtype    b'lemma:\xce\xb4cra'
3.417588 Gtype    b'word:\xce\x94cra'
3.314327 Supp     b'lemma:pq'
3.314327 Supp     b'word:PQ'
3.305655 Technique b'word:ChIPSeq'
3.233996 O        b'lemma:rpob'
3.233996 O        b'word:RpoB'
3.230643 O        b'-1:word:tag'
3.215437 Technique b'word:ChIP-exo'
3.209263 Gversion b'lemma:asm584v2'
3.209263 Gversion b'word:ASM584v2'
3.172641 O        b'lemma:at'
3.144467 O        b'lemma:Custom'
3.144467 O        b'word:Custom'
3.098885 Technique b'lemma:rna-seq'
3.054449 O        b'lemma:2'
3.054449 O        b'word:2'
3.034553 Supp     b'+1:lemma:\xc2\xb5m'
3.034553 Supp     b'+1:word:\xc2\xb5M'
3.000931 O        b'-1:lemma:tag'
2.989138 O        b'lemma:.'
2.989138 O        b'postag:.'
2.989138 O        b'word:.'
2.981955 Strain   b'+1:lemma:substr'
2.981955 Strain   b'+1:word:substr'
2.977816 Technique b'lemma:chipseq'
2.916006 O        b'lemma:1'
2.916006 O        b'word:1'
2.871451 Supp     b'postag:VBP'
2.856639 Gtype    b'lemma:delta-fnr'
2.856639 Gtype    b'word:delta-fnr'
2.843912 O        b'lemma:ompr'
2.843912 O        b'word:OmpR'
2.751390 Supp     b'lemma:nacl'
2.751390 Supp     b'word:NaCl'
2.716201 O        b'+1:lemma:pq'
2.716201 O        b'+1:word:PQ'
2.704016 O        b'postag:CC'
2.702834 O        b'lemma:a'
2.688516 O        b'lemma:b'
2.688516 O        b'word:B'
2.677526 Gtype    b'lemma:flag-tag'
2.677526 Gtype    b'-1:lemma:c-terminal'
2.677526 Gtype    b'word:Flag-tag'
2.677526 Gtype    b'-1:word:C-terminal'
2.654486 O        b'lemma:with'
2.654486 O        b'word:with'
2.651693 O        b'postag:IN'
2.649950 Gtype    b'lemma:type'
2.649950 Gtype    b'word:type'
2.636720 O        b'lemma:3'
2.636720 O        b'word:3'
2.631937 O        b'-1:lemma:lb'
2.631937 O        b'-1:word:LB'
2.618290 Supp     b'lemma:glucose'
2.618290 Supp     b'word:glucose'
2.608453 O        b'-1:word:Aerobic'
2.600667 Supp     b'lemma:arginine'
2.585328 O        b'lemma:chip'
2.578251 Supp     b'lemma:rifampicin'
2.578251 Supp     b'word:rifampicin'
2.573636 Supp     b'+1:lemma:Deficient'
2.514589 O        b'postag::'
2.492658 O        b'lemma:Cra'
2.487492 Substrain b'lemma:mg1655'
2.487492 Substrain b'word:MG1655'
2.478149 Air      b'word:anaerobic'
2.456656 Gversion b'-1:lemma:nc'
2.456656 Gversion b'-1:word:NC'
2.452611 Anti     b'lemma:seqa'
2.452611 Anti     b'word:SeqA'
2.445869 O        b'postag:VBN'
2.441392 O        b'word:A'
2.434041 O        b'+1:postag:NNP'
2.430022 O        b'-1:lemma:0.3'
2.430022 O        b'-1:word:0.3'
2.411145 Air      b'lemma:Aerobic'
2.390202 Supp     b'lemma:Leu'
2.390202 Supp     b'word:Leu'
2.387116 Gtype    b'lemma:arca8myc'
2.387116 Gtype    b'word:ArcA8myc'
2.375840 Technique b'word:RNA-Seq'
2.359444 O        b'-1:lemma:glucose'
2.359444 O        b'-1:word:glucose'
2.351625 Strain   b'lemma:k-12'
2.351625 Strain   b'word:K-12'
2.318240 Supp     b'-1:lemma:Cra'
2.291182 Gversion b'lemma:chip-seq'
2.291116 Anti     b'lemma:none'
2.291116 Anti     b'word:none'
2.290566 Gversion b'lemma:nc'
2.290566 Gversion b'word:NC'
2.284268 O        b'+1:lemma:or'
2.284268 O        b'+1:word:or'
2.283438 O        b'lemma::'
2.283438 O        b'word::'
2.263553 Supp     b'lemma:acetate'
2.263553 Supp     b'word:acetate'
2.260492 O        b'-1:lemma:0.3-0.35'
2.260492 O        b'-1:word:0.3-0.35'
2.253939 Gversion b'word:ChIP-Seq'
2.250232 Technique b'lemma:rnaseq'
2.250232 Technique b'word:RNASeq'
2.232794 O        b'+1:word:ChIP-Seq'
2.229103 Med      b'-1:lemma:ml'
2.229103 Med      b'-1:word:ml'
2.227590 O        b'lemma:culture'
2.224596 Gtype    b'+1:lemma:type'
2.224596 Gtype    b'+1:word:type'
2.200566 O        b'lemma:rep3'
2.200566 O        b'word:rep3'
2.182661 Anti     b'lemma:\xcf\x8332'
2.182661 Anti     b'word:\xcf\x8332'
2.181231 Air      b'lemma:anaeroibc'
2.181231 Air      b'word:Anaeroibc'
2.181006 Gtype    b'lemma:wildtype'
2.179557 Supp     b'lemma:no3'
2.179557 Supp     b'word:NO3'
2.168687 O        b'+1:word:were'
2.168597 O        b'lemma:rep1'
2.168597 O        b'word:rep1'
2.167529 Air      b'lemma:aerobically'
2.167529 Air      b'word:aerobically'
2.141925 Supp     b'-1:lemma:+'
2.141925 Supp     b'-1:word:+'
2.141556 Air      b'-1:lemma:ChIP-Seq'
2.141556 Air      b'-1:word:ChIP-Seq'
2.136723 Temp     b'+1:lemma:in'
2.136723 Temp     b'+1:word:in'
2.120975 Vess     b'lemma:flask'
2.120975 Vess     b'-1:lemma:warm'
2.120975 Vess     b'word:flask'
2.120975 Vess     b'-1:word:warmed'
2.115337 Gtype    b'-1:lemma:\xe2\x88\x86'
2.115337 Gtype    b'-1:word:\xe2\x88\x86'
2.111591 Gtype    b'lemma:\xce\xb4soxr'
2.111591 Gtype    b'word:\xce\x94soxR'
2.087111 Technique b'-1:lemma:chip-exo'
2.073917 Gtype    b'word:cra'
2.071081 Agit     b'+1:lemma:rpm'
2.071081 Agit     b'+1:word:rpm'
2.070334 Agit     b'lemma:rpm'
2.070334 Agit     b'word:rpm'
2.067325 Gtype    b'lemma:dfnr'
2.067325 Gtype    b'word:dFNR'
2.061229 Air      b'lemma:anaerobically'
2.061229 Air      b'word:anaerobically'
2.054028 Supp     b'-1:lemma:with'
2.054028 Supp     b'-1:word:with'
2.046181 O        b'postag:VBG'
2.032013 Supp     b'lemma:Fe'
2.032013 Supp     b'word:Fe'
2.030145 pH       b'+1:postag:CD'
2.022741 Med      b'-1:lemma:fresh'
2.022741 Med      b'-1:word:fresh'
2.019221 Gtype    b'+1:lemma:with'
2.019221 Gtype    b'+1:word:with'
2.012561 Air      b'lemma:aerobic'
2.012064 Gtype    b'-1:postag:VBG'
2.011339 Med      b'+1:lemma:0.4'
2.011339 Med      b'+1:word:0.4'
2.009320 Supp     b'lemma:Adenine'
2.009320 Supp     b'word:Adenine'
2.007291 Air      b'-1:postag::'
1.983786 Anti     b'+1:postag:VBN'
1.983224 O        b'-1:lemma:into'
1.983224 O        b'-1:word:into'
1.964035 O        b'lemma:rep2'
1.964035 O        b'word:rep2'
1.959783 Gtype    b'lemma:pk4854'
1.959783 Gtype    b'word:PK4854'


Top negative:
-0.303383 Temp     b'isLower'
-0.309535 Air      b'-1:postag:JJ'
-0.310017 Supp     b'postag:-LRB-'
-0.317396 O        b'+1:lemma:_'
-0.317396 O        b'+1:word:_'
-0.325240 Technique b'-1:postag::'
-0.330686 O        b'lemma:20'
-0.330686 O        b'word:20'
-0.332939 Gtype    b'-1:postag:CD'
-0.338184 O        b'+1:lemma:minimal'
-0.338184 O        b'+1:word:minimal'
-0.344465 Gtype    b'+1:lemma:-lrb-'
-0.344465 Gtype    b'+1:word:-LRB-'
-0.348653 O        b'+1:postag:IN'
-0.349230 Strain   b'isLower'
-0.358539 O        b'-1:lemma:n2'
-0.358539 O        b'-1:word:N2'
-0.360467 O        b'-1:lemma:ph'
-0.360467 O        b'-1:word:pH'
-0.372464 O        b'lemma:anaerobic'
-0.376573 O        b'-1:lemma:with'
-0.376573 O        b'-1:word:with'
-0.386822 O        b'-1:lemma:delta'
-0.386822 O        b'-1:word:delta'
-0.388023 pH       b'isNumber'
-0.388961 O        b'-1:postag:IN'
-0.389061 O        b'-1:lemma:mm'
-0.389061 O        b'-1:word:mM'
-0.402376 O        b'+1:lemma:rep2'
-0.402376 O        b'+1:word:rep2'
-0.428619 Supp     b'+1:lemma:rifampicin'
-0.428619 Supp     b'+1:word:rifampicin'
-0.428641 O        b'lemma:k-12'
-0.428641 O        b'word:K-12'
-0.437232 O        b'-1:lemma:co2'
-0.437232 O        b'-1:word:CO2'
-0.452931 O        b'lemma:glucose'
-0.452931 O        b'word:glucose'
-0.457255 O        b'lemma:aerobically'
-0.457255 O        b'word:aerobically'
-0.457512 O        b'+1:lemma:for'
-0.459154 Anti     b'+1:lemma:anti-fur'
-0.459154 Anti     b'+1:word:anti-Fur'
-0.468795 O        b'-1:lemma:dissolve'
-0.468795 O        b'+1:lemma:methanol'
-0.468795 O        b'-1:word:dissolved'
-0.468795 O        b'+1:word:methanol'
-0.471109 Supp     b'lemma:and'
-0.471109 Supp     b'word:and'
-0.472339 O        b'lemma:aerobic'
-0.475261 O        b'lemma:0.3'
-0.475261 O        b'word:0.3'
-0.483590 Air      b'postag:CD'
-0.483923 O        b'+1:postag:-RRB-'
-0.497463 Med      b'-1:postag:NN'
-0.499049 Supp     b'-1:lemma:-lrb-'
-0.499049 Supp     b'-1:word:-LRB-'
-0.501219 O        b'+1:lemma:1m'
-0.501219 O        b'+1:word:1M'
-0.502085 Supp     b'+1:postag::'
-0.515749 Supp     b'+1:postag:VBN'
-0.519934 O        b'+1:lemma:supplement'
-0.519934 O        b'+1:word:supplemented'
-0.531150 O        b'+1:lemma:until'
-0.531150 O        b'+1:word:until'
-0.531590 O        b'lemma:methanol'
-0.531590 O        b'word:methanol'
-0.534769 O        b'lemma:medium'
-0.534769 O        b'word:medium'
-0.537022 O        b'lemma:fructose'
-0.537022 O        b'word:fructose'
-0.537520 O        b'lemma:of'
-0.537520 O        b'word:of'
-0.537621 O        b'+1:lemma:2.0'
-0.537621 O        b'+1:word:2.0'
-0.541851 O        b'+1:lemma:g/l'
-0.541851 O        b'+1:word:g/L'
-0.542060 Supp     b'-1:postag:-LRB-'
-0.549971 Med      b'lemma:-lrb-'
-0.549971 Med      b'word:-LRB-'
-0.564385 O        b'word:cells'
-0.577014 Anti     b'isUpper'
-0.580839 O        b'-1:postag:JJ'
-0.595778 Med      b'+1:postag:IN'
-0.613291 Med      b'postag:CD'
-0.630342 O        b'+1:word:C'
-0.633021 O        b'lemma:purify'
-0.636573 Supp     b'+1:lemma:acetate'
-0.636573 Supp     b'+1:word:acetate'
-0.639384 O        b'-1:lemma:2'
-0.639384 O        b'-1:word:2'
-0.641103 O        b'lemma:37'
-0.641103 O        b'word:37'
-0.657693 O        b'lemma:mid-log'
-0.657693 O        b'word:mid-log'
-0.669108 O        b'-1:lemma:chip-exo'
-0.676699 O        b'-1:lemma:rpob'
-0.676699 O        b'-1:word:RpoB'
-0.683926 Supp     b'+1:lemma:fructose'
-0.683926 Supp     b'+1:word:fructose'
-0.696629 O        b'lemma:\xce\xb4fur'
-0.696629 O        b'word:\xce\x94fur'
-0.716858 Med      b'postag:-LRB-'
-0.717563 O        b'-1:lemma:37'
-0.717563 O        b'-1:word:37'
-0.742255 pH       b'isUpper'
-0.751253 Air      b'postag:NN'
-0.760807 O        b'-1:lemma:\xe2\x88\x86'
-0.760807 O        b'-1:word:\xe2\x88\x86'
-0.762242 O        b'lemma:30'
-0.762242 O        b'word:30'
-0.778777 O        b'+1:lemma:mm'
-0.778777 O        b'+1:word:mM'
-0.782724 O        b'lemma:nitrate'
-0.782724 O        b'word:nitrate'
-0.783200 O        b'-1:lemma:1'
-0.783200 O        b'-1:word:1'
-0.788591 Phase    b'isUpper'
-0.789080 O        b'-1:lemma:30'
-0.789080 O        b'-1:word:30'
-0.790624 Supp     b'postag:CC'
-0.796125 Gtype    b'postag:VBG'
-0.802899 O        b'-1:lemma:nsrr'
-0.802899 O        b'-1:word:NsrR'
-0.828431 Gtype    b'postag::'
-0.831044 O        b'lemma:2h'
-0.831044 O        b'-1:lemma:additional'
-0.831044 O        b'word:2h'
-0.831044 O        b'-1:word:additional'
-0.839187 O        b'lemma:media'
-0.839187 O        b'word:media'
-0.840728 Supp     b'postag::'
-0.863650 Air      b'-1:lemma:or'
-0.863650 Air      b'-1:word:or'
-0.885820 Temp     b'postag:NN'
-0.897688 Med      b'-1:postag:CD'
-0.900253 pH       b'isLower'
-0.911088 O        b'-1:lemma:until'
-0.911088 O        b'-1:word:until'
-0.944420 O        b'+1:word:ChIP-exo'
-0.948977 O        b'lemma:anaerobically'
-0.948977 O        b'word:anaerobically'
-0.951515 Agit     b'isUpper'
-0.983125 Gtype    b'isUpper'
-0.988396 O        b'+1:lemma:at'
-0.988396 O        b'+1:word:at'
-0.995833 Supp     b'+1:lemma:nacl'
-0.995833 Supp     b'+1:word:NaCl'
-0.997040 O        b'-1:lemma:ml'
-0.997040 O        b'-1:word:ml'
-1.018669 Supp     b'-1:postag:NNP'
-1.037921 O        b'lemma:nitrogen'
-1.037921 O        b'word:nitrogen'
-1.040146 O        b'+1:lemma:1'
-1.040146 O        b'+1:word:1'
-1.045534 Med      b'-1:postag:IN'
-1.056151 O        b'word:ChIP-exo'
-1.089520 O        b'lemma:wt'
-1.114097 O        b'+1:lemma:+'
-1.114097 O        b'+1:word:+'
-1.120376 Gtype    b'isLower'
-1.143082 O        b'-1:lemma:IP'
-1.143082 O        b'-1:word:IP'
-1.158305 OD       b'+1:postag:NN'
-1.159364 O        b'-1:postag::'
-1.163927 O        b'+1:lemma:in'
-1.163927 O        b'+1:word:in'
-1.192075 O        b'+1:postag:VBG'
-1.203597 O        b'postag:RB'
-1.328635 O        b'+1:lemma:2'
-1.328635 O        b'+1:word:2'
-1.418108 Technique b'isLower'
-1.442615 O        b'-1:lemma:sample'
-1.516830 O        b'lemma:rifampicin'
-1.516830 O        b'word:rifampicin'
-1.534388 Supp     b'+1:lemma:-lrb-'
-1.534388 Supp     b'+1:word:-LRB-'
-1.563425 Supp     b'+1:postag:-LRB-'
-1.574320 Supp     b'postag:JJ'
-1.581559 O        b'-1:lemma:fresh'
-1.581559 O        b'-1:word:fresh'
-1.612036 Gversion b'isLower'
-1.656921 Anti     b'postag:NNP'
-1.709765 O        b'-1:lemma:vol'
-1.709765 O        b'-1:word:vol'
-1.748581 Air      b'+1:postag:JJ'
-1.800378 Technique b'isNumber'
-1.802484 O        b'postag:VBP'
-1.806249 Supp     b'+1:lemma:,'
-1.806249 Supp     b'+1:postag:,'
-1.806249 Supp     b'+1:word:,'
-2.105469 O        b'-1:lemma:_'
-2.105469 O        b'-1:word:_'
-2.207206 Gtype    b'isNumber'
-2.372723 Phase    b'-1:postag:JJ'
-2.553668 O        b'-1:postag:VBG'
-2.823830 O        b'-1:lemma::'
-2.823830 O        b'-1:word::'
-3.368572 Temp     b'+1:postag:IN'
-3.402875 Phase    b'postag:JJ'