********** TRAINING AND TESTING REPORT **********
Training file: training-data-set-70_v4.txt

best params:{'c1': 0.07999002423801141, 'c2': 0.000868661924339573}
best CV score:0.8083684694714717
model size: 0.12M

Flat F1: 0.797188910586862
             precision    recall  f1-score   support

         OD      1.000     0.405     0.577        37
         pH      1.000     1.000     1.000        12
  Technique      0.952     0.909     0.930        22
        Med      0.878     0.754     0.811        57
       Temp      0.818     1.000     0.900        18
       Vess      0.000     0.000     0.000         0
       Agit      0.000     0.000     0.000         0
      Phase      1.000     0.947     0.973        19
        Air      1.000     0.742     0.852        62
       Anti      0.571     0.444     0.500         9
     Strain      1.000     1.000     1.000         1
      Gtype      0.842     0.802     0.821       106
  Substrain      0.000     0.000     0.000         1
       Supp      0.819     0.699     0.754       136
   Gversion      0.000     0.000     0.000         0

avg / total      0.880     0.744     0.797       480


Top likely transitions:
Agit   -> Agit    6.851914
Temp   -> Temp    6.755805
Anti   -> Anti    6.408411
OD     -> OD      6.070648
Med    -> Med     5.592163
Gtype  -> Gtype   5.552172
Gversion -> Gversion 5.270252
Air    -> Air     4.673888
Supp   -> Supp    4.485002
Phase  -> Phase   4.276420
O      -> O       4.272212
Technique -> Technique 3.801130
pH     -> pH      2.239489
Gtype  -> Supp    1.797612
O      -> Gtype   1.020757
O      -> Technique 0.845864
O      -> Supp    0.684262
O      -> Anti    0.542673
Substrain -> Gtype   0.423988
Technique -> Air     0.409033
O      -> Temp    0.245701
Med    -> O       0.105696
O      -> Gversion 0.000171
Gtype  -> pH      0.000014
Technique -> OD      -0.019259
Vess   -> O       -0.025654
pH     -> O       -0.063409
Air    -> OD      -0.082675
Air    -> Temp    -0.095090
Air    -> O       -0.133376
Supp   -> OD      -0.159102
Anti   -> O       -0.247448
OD     -> Air     -0.261699
Gtype  -> Med     -0.274175
OD     -> Gtype   -0.277593
Strain -> O       -0.369145
Phase  -> Air     -0.387062
O      -> Phase   -0.394932
Phase  -> O       -0.493736
Supp   -> O       -0.534752
Air    -> Phase   -0.600512
Supp   -> Air     -0.640514
OD     -> Med     -0.713090
Technique -> O       -0.754114
Technique -> Gtype   -0.754511
O      -> OD      -0.776176
O      -> Med     -0.780627
Gtype  -> O       -0.801612
Gtype  -> OD      -0.934362
Air    -> Med     -1.257535


Top unlikely transitions:
Supp   -> Supp    4.485002
Phase  -> Phase   4.276420
O      -> O       4.272212
Technique -> Technique 3.801130
pH     -> pH      2.239489
Gtype  -> Supp    1.797612
O      -> Gtype   1.020757
O      -> Technique 0.845864
O      -> Supp    0.684262
O      -> Anti    0.542673
Substrain -> Gtype   0.423988
Technique -> Air     0.409033
O      -> Temp    0.245701
Med    -> O       0.105696
O      -> Gversion 0.000171
Gtype  -> pH      0.000014
Technique -> OD      -0.019259
Vess   -> O       -0.025654
pH     -> O       -0.063409
Air    -> OD      -0.082675
Air    -> Temp    -0.095090
Air    -> O       -0.133376
Supp   -> OD      -0.159102
Anti   -> O       -0.247448
OD     -> Air     -0.261699
Gtype  -> Med     -0.274175
OD     -> Gtype   -0.277593
Strain -> O       -0.369145
Phase  -> Air     -0.387062
O      -> Phase   -0.394932
Phase  -> O       -0.493736
Supp   -> O       -0.534752
Air    -> Phase   -0.600512
Supp   -> Air     -0.640514
OD     -> Med     -0.713090
Technique -> O       -0.754114
Technique -> Gtype   -0.754511
O      -> OD      -0.776176
O      -> Med     -0.780627
Gtype  -> O       -0.801612
Gtype  -> OD      -0.934362
Air    -> Med     -1.257535
Gtype  -> Anti    -1.262843
OD     -> O       -1.377165
Supp   -> Med     -1.741716
Agit   -> O       -1.885756
Substrain -> O       -1.895216
Med    -> Supp    -2.409765
O      -> Air     -2.508634
Phase  -> OD      -2.584465


Top positive:
11.849885 Air      b'word:Aerobic'
7.837435 Air      b'lemma:anaerobic'
7.665723 O        b'word:Cra'
7.042313 Air      b'word:Anaerobic'
6.037970 O        b'lemma:_'
6.037970 O        b'word:_'
5.584218 O        b'postag::'
5.431231 O        b'-1:lemma:ChIP-exo'
5.349382 Med      b'lemma:MOPS'
5.349382 Med      b'word:MOPS'
5.289872 Technique b'word:ChIP-Seq'
5.021757 Supp     b'lemma:nh4cl'
4.898148 O        b'lemma:Custom'
4.898148 O        b'word:Custom'
4.861257 Phase    b'lemma:stationary'
4.861257 Phase    b'word:stationary'
4.814387 Technique b'lemma:rna-seq'
4.799463 Technique b'word:ChIPSeq'
4.773443 Supp     b'lemma:nitrate'
4.773443 Supp     b'word:nitrate'
4.681396 O        b'+1:postag:RB'
4.678066 Supp     b'-1:word:Cra'
4.674952 Technique b'word:ChIP-exo'
4.673460 O        b'lemma:rpob'
4.673460 O        b'word:RpoB'
4.632286 Med      b'word:LB'
4.272192 Supp     b'lemma:pq'
4.272192 Supp     b'word:PQ'
4.216477 Supp     b'lemma:arginine'
4.158847 O        b'lemma:1'
4.158847 O        b'word:1'
4.061171 Gtype    b'lemma:wild-type'
4.017592 O        b'lemma:chip'
3.861964 OD       b'+1:lemma:stationary'
3.861964 OD       b'+1:word:stationary'
3.805796 O        b'-1:lemma:tag'
3.744431 O        b'-1:word:Aerobic'
3.714272 Supp     b'lemma:Iron'
3.714272 Supp     b'word:Iron'
3.714272 Supp     b'+1:word:Deficient'
3.713062 Strain   b'lemma:k-12'
3.713062 Strain   b'word:K-12'
3.708676 Technique b'lemma:ChIP-exo'
3.655103 O        b'lemma:at'
3.537057 Air      b'postag:RB'
3.506119 Gversion b'lemma:asm584v2'
3.506119 Gversion b'word:ASM584v2'
3.457008 O        b'-1:word:Anaerobic'
3.440372 O        b'lemma:for'
3.381566 Gversion b'lemma:chip-seq'
3.373670 Gtype    b'lemma:delta-fnr'
3.373670 Gtype    b'word:delta-fnr'
3.345890 O        b'lemma:a'
3.268014 Gversion b'-1:lemma:nc'
3.268014 Gversion b'-1:word:NC'
3.225995 Air      b'word:anaerobic'
3.223526 Substrain b'lemma:mg1655'
3.223526 Substrain b'word:MG1655'
3.207086 O        b'word:Lrp'
3.199909 Gversion b'lemma:nc'
3.199909 Gversion b'word:NC'
3.184836 O        b'lemma:2'
3.184836 O        b'word:2'
3.184258 O        b'-1:word:tag'
3.161968 Gtype    b'lemma:type'
3.161968 Gtype    b'word:type'
3.129124 O        b'lemma:.'
3.129124 O        b'postag:.'
3.129124 O        b'word:.'
3.035046 O        b'lemma:2-3'
3.035046 O        b'word:2-3'
3.031993 Gtype    b'lemma:\xce\xb4cra'
3.023750 Gtype    b'word:\xce\x94cra'
3.015053 O        b'-1:lemma:lb'
2.985389 O        b'postag:IN'
2.963040 O        b'+1:word:ChIP-Seq'
2.954499 Gtype    b'-1:lemma:\xe2\x88\x86'
2.954499 Gtype    b'-1:word:\xe2\x88\x86'
2.921032 Gtype    b'lemma:flag-tag'
2.921032 Gtype    b'-1:lemma:c-terminal'
2.921032 Gtype    b'word:Flag-tag'
2.921032 Gtype    b'-1:word:C-terminal'
2.914388 O        b'lemma:3'
2.914388 O        b'word:3'
2.889633 Supp     b'+1:lemma:\xc2\xb5m'
2.889633 Supp     b'+1:word:\xc2\xb5M'
2.855964 Technique b'-1:lemma:chip-exo'
2.841382 Temp     b'-1:word:sample'
2.838133 Med      b'lemma:LB'
2.837407 Gtype    b'lemma:wt'
2.815709 Phase    b'lemma:mid-log'
2.815709 Phase    b'word:mid-log'
2.815078 O        b'word:OmpR'
2.800233 Temp     b'-1:lemma:sample'
2.743118 Anti     b'lemma:seqa'
2.743118 Anti     b'word:SeqA'
2.738947 Gtype    b'lemma:arca8myc'
2.738947 Gtype    b'word:ArcA8myc'
2.734940 Supp     b'lemma:rifampicin'
2.734940 Supp     b'word:rifampicin'
2.713912 Technique b'lemma:rnaseq'
2.713912 Technique b'word:RNASeq'
2.676140 O        b'+1:postag:NNP'
2.668046 Gtype    b'postag:-RRB-'
2.666708 O        b'lemma:rep1'
2.666708 O        b'word:rep1'
2.639615 O        b'word:for'
2.628763 O        b'lemma:with'
2.628763 O        b'word:with'
2.602495 O        b'lemma:b'
2.602495 O        b'word:B'
2.600005 O        b'+1:postag:VBP'
2.593478 Supp     b'+1:word:hours'
2.586011 Technique b'lemma:chipseq'
2.559150 Strain   b'+1:lemma:substr'
2.559150 Strain   b'+1:word:substr'
2.527855 Supp     b'lemma:no3'
2.527855 Supp     b'word:NO3'
2.521274 O        b'lemma:-'
2.521274 O        b'word:-'
2.481893 O        b'lemma:rep3'
2.481893 O        b'word:rep3'
2.477491 Gtype    b'word:WT'
2.457514 Gtype    b'+1:lemma:type'
2.457514 Gtype    b'+1:word:type'
2.445177 Supp     b'lemma:Fe'
2.445177 Supp     b'word:Fe'
2.387444 O        b'lemma:rep2'
2.387444 O        b'word:rep2'
2.380978 OD       b'lemma:od600'
2.380978 OD       b'word:OD600'
2.377956 Anti     b'lemma:anti-rpos'
2.377956 Anti     b'word:anti-RpoS'
2.363736 O        b'lemma:oxyr'
2.363736 O        b'word:OxyR'
2.360999 Anti     b'lemma:none'
2.360999 Anti     b'word:none'
2.343495 Gtype    b'word:wt'
2.342659 Supp     b'lemma:dpd'
2.342659 Supp     b'word:DPD'
2.334798 Gtype    b'lemma:\xce\xb4ompr'
2.334798 Gtype    b'word:\xce\x94ompR'
2.303303 O        b'-1:lemma:0.3'
2.303303 O        b'-1:word:0.3'
2.262158 O        b'lemma:\xcf\x8332'
2.262158 O        b'word:\xcf\x8332'
2.249986 O        b'word:A'
2.245441 Vess     b'lemma:flask'
2.245441 Vess     b'-1:lemma:warm'
2.245441 Vess     b'word:flask'
2.245441 Vess     b'-1:word:warmed'
2.238883 O        b'+1:lemma:od600'
2.238883 O        b'+1:word:OD600'
2.225888 O        b'postag:DT'
2.181011 O        b'-1:lemma:0.3-0.35'
2.181011 O        b'-1:word:0.3-0.35'
2.166240 O        b'lemma:or'
2.166240 O        b'word:or'
2.155012 Supp     b'lemma:acetate'
2.155012 Supp     b'word:acetate'
2.153135 OD       b'lemma:od450'
2.153135 OD       b'word:OD450'
2.153135 OD       b'-1:word:At'
2.131868 Supp     b'lemma:glucose'
2.131868 Supp     b'word:glucose'
2.127183 Anti     b'+1:lemma:antibody'
2.127183 Anti     b'+1:word:antibody'
2.127102 O        b'lemma:culture'
2.121306 Med      b'+1:lemma:0.4'
2.121306 Med      b'+1:word:0.4'
2.104976 Anti     b'lemma:anti-myc'
2.104976 Anti     b'word:anti-myc'
2.090073 Supp     b'lemma:iptg'
2.090073 Supp     b'word:IPTG'
2.088014 O        b'lemma:chip-fnr'
2.088014 O        b'word:chip-Fnr'
2.087065 Gtype    b'lemma:nsrr'
2.087065 Gtype    b'word:NsrR'
2.069607 O        b'+1:postag::'
2.049162 Phase    b'-1:word:growing'
2.041081 Gversion b'word:ChIP-Seq'
2.034077 O        b'-1:word:fnr'
2.027233 Gtype    b'+1:postag::'
2.026441 Gtype    b'postag:JJ'
2.012468 O        b'postag:VBN'
2.003087 O        b'lemma:soxs'
2.003087 O        b'word:SoxS'
2.003087 O        b'lemma:soxr'
2.003087 O        b'word:SoxR'
1.984406 O        b'+1:lemma:o.d.'
1.984406 O        b'+1:word:O.D.'
1.975363 OD       b'+1:postag:JJ'
1.968960 Air      b'-1:lemma:ChIP-Seq'
1.968960 Air      b'-1:word:ChIP-Seq'
1.963497 Gtype    b'lemma:pk4854'
1.963497 Gtype    b'word:PK4854'
1.957953 Gtype    b'word:cra'
1.957254 Air      b'lemma:anerobically'
1.957254 Air      b'word:anerobically'
1.954863 O        b'+1:lemma:pq'


Top negative:
-0.090059 O        b'-1:lemma:e.'
-0.092645 O        b'+1:postag:-RRB-'
-0.095582 O        b'-1:word:the'
-0.095914 O        b'+1:lemma:minimal'
-0.095914 O        b'+1:word:minimal'
-0.096813 Strain   b'postag:NN'
-0.100844 O        b'word:LB'
-0.102252 O        b'lemma:anaerobic'
-0.106574 OD       b'+1:postag:CC'
-0.107348 Air      b'+1:postag:NN'
-0.107934 O        b'-1:word:grown'
-0.108595 Supp     b'-1:postag:VBG'
-0.108740 pH       b'postag:NN'
-0.112315 O        b'-1:lemma:ml'
-0.112801 O        b'+1:lemma:rep1'
-0.112801 O        b'+1:word:rep1'
-0.112908 O        b'-1:lemma:od600'
-0.112908 O        b'-1:word:OD600'
-0.115106 Air      b'-1:postag:CC'
-0.115496 O        b'lemma:co2'
-0.115496 O        b'word:CO2'
-0.122244 O        b'-1:lemma:the'
-0.124640 O        b'-1:lemma:~'
-0.124640 O        b'-1:word:~'
-0.127544 OD       b'+1:lemma:and'
-0.127544 OD       b'+1:word:and'
-0.129259 O        b'-1:lemma:-lrb-'
-0.129259 O        b'-1:word:-LRB-'
-0.133618 O        b'+1:lemma:_'
-0.133618 O        b'+1:word:_'
-0.135372 O        b'+1:lemma:\xc2\xb0c'
-0.135372 O        b'+1:word:\xc2\xb0C'
-0.136841 Technique b'isNumber'
-0.139019 O        b'lemma:30'
-0.139019 O        b'word:30'
-0.139199 Phase    b'-1:postag:NN'
-0.149458 O        b'+1:lemma:5'
-0.149458 O        b'+1:word:5'
-0.151250 OD       b'postag:JJ'
-0.152851 Supp     b'+1:lemma:acetate'
-0.152851 Supp     b'+1:word:acetate'
-0.156762 O        b'+1:lemma:.'
-0.156762 O        b'+1:postag:.'
-0.156762 O        b'+1:word:.'
-0.158764 O        b'-1:postag:-LRB-'
-0.161868 Gversion b'-1:postag:NN'
-0.163014 pH       b'isLower'
-0.167779 O        b'-1:lemma:30'
-0.167779 O        b'-1:word:30'
-0.171168 O        b'lemma:150'
-0.171168 O        b'+1:lemma:mg/ml'
-0.171168 O        b'word:150'
-0.171168 O        b'+1:word:mg/mL'
-0.176143 O        b'lemma:0.3'
-0.176143 O        b'word:0.3'
-0.187819 O        b'lemma:aerobically'
-0.187819 O        b'word:aerobically'
-0.198962 O        b'word:hours'
-0.212759 Med      b'+1:postag:NNS'
-0.224619 Gtype    b'-1:postag:SYM'
-0.228665 O        b'lemma:fecl2'
-0.228665 O        b'word:FeCl2'
-0.233718 O        b'+1:lemma:or'
-0.233718 O        b'+1:word:or'
-0.234368 O        b'lemma:e.'
-0.236980 O        b'lemma:dissolve'
-0.236980 O        b'word:dissolved'
-0.241256 Supp     b'+1:lemma:rifampicin'
-0.241256 Supp     b'+1:word:rifampicin'
-0.241793 O        b'-1:word:ml'
-0.242844 O        b'-1:lemma:mid-log'
-0.242844 O        b'-1:word:mid-log'
-0.244892 O        b'-1:lemma:o2'
-0.244892 O        b'-1:word:O2'
-0.250659 O        b'-1:lemma:0.2'
-0.250659 O        b'-1:word:0.2'
-0.257587 Air      b'-1:postag:JJ'
-0.275537 O        b'+1:postag:IN'
-0.276339 Agit     b'isUpper'
-0.288029 O        b'lemma:minimal'
-0.288029 O        b'word:minimal'
-0.288682 O        b'lemma:0.2'
-0.288682 O        b'word:0.2'
-0.295170 O        b'+1:lemma:%'
-0.295170 O        b'+1:word:%'
-0.312769 Supp     b'+1:postag:IN'
-0.314136 O        b'lemma:of'
-0.314136 O        b'word:of'
-0.316019 O        b'lemma:phase'
-0.316019 O        b'word:phase'
-0.317543 O        b'-1:lemma:rpob'
-0.317543 O        b'-1:word:RpoB'
-0.352099 O        b'lemma:0.1'
-0.352099 O        b'word:0.1'
-0.354536 O        b'-1:lemma:grow'
-0.355121 O        b'+1:postag:NNS'
-0.360104 O        b'lemma:dpd'
-0.360104 O        b'word:DPD'
-0.361422 Med      b'postag:CD'
-0.374440 Air      b'+1:postag:JJ'
-0.374640 O        b'+1:lemma:c'
-0.386040 O        b'lemma:medium'
-0.386040 O        b'word:medium'
-0.425432 OD       b'+1:postag:NN'
-0.433655 Med      b'+1:postag:NN'
-0.442754 Supp     b'-1:postag:NNP'
-0.444075 O        b'-1:postag:IN'
-0.462977 O        b'-1:lemma:IP'
-0.462977 O        b'-1:word:IP'
-0.473099 O        b'lemma:od600'
-0.473099 O        b'word:OD600'
-0.475947 Supp     b'-1:lemma:%'
-0.475947 Supp     b'-1:word:%'
-0.478194 Supp     b'+1:postag:VBN'
-0.493813 O        b'-1:lemma:dissolve'
-0.493813 O        b'+1:lemma:methanol'
-0.493813 O        b'-1:word:dissolved'
-0.493813 O        b'+1:word:methanol'
-0.496860 Temp     b'+1:lemma:to'
-0.496860 Temp     b'+1:postag:TO'
-0.496860 Temp     b'+1:word:to'
-0.499631 O        b'word:WT'
-0.513610 Temp     b'postag:NN'
-0.514977 O        b'lemma:glucose'
-0.514977 O        b'word:glucose'
-0.536212 OD       b'lemma:-lrb-'
-0.536212 OD       b'word:-LRB-'
-0.551562 O        b'lemma:media'
-0.551562 O        b'word:media'
-0.560747 O        b'+1:lemma:fecl2'
-0.560747 O        b'+1:word:FeCl2'
-0.568774 O        b'-1:lemma:co2'
-0.568774 O        b'-1:word:CO2'
-0.570589 O        b'lemma:20'
-0.570589 O        b'word:20'
-0.601473 O        b'-1:lemma:37'
-0.601473 O        b'-1:word:37'
-0.606741 O        b'+1:word:ChIP-exo'
-0.613813 O        b'+1:lemma:g/l'
-0.613813 O        b'+1:word:g/L'
-0.619083 OD       b'postag:-LRB-'
-0.649236 O        b'+1:word:C'
-0.665832 O        b'+1:lemma:supplement'
-0.665832 O        b'+1:word:supplemented'
-0.674327 O        b'lemma:37'
-0.674327 O        b'word:37'
-0.686899 O        b'lemma:2h'
-0.686899 O        b'-1:lemma:additional'
-0.686899 O        b'word:2h'
-0.686899 O        b'-1:word:additional'
-0.702076 O        b'+1:lemma:in'
-0.702076 O        b'+1:word:in'
-0.720953 Med      b'-1:postag:NN'
-0.734913 Med      b'+1:postag:IN'
-0.738740 O        b'postag:RB'
-0.780009 Supp     b'-1:postag:NN'
-0.812687 Phase    b'-1:postag:JJ'
-0.862547 O        b'+1:lemma:at'
-0.862547 O        b'+1:word:at'
-0.884705 O        b'lemma:anaerobically'
-0.884705 O        b'word:anaerobically'
-0.954289 O        b'lemma:rifampicin'
-0.954289 O        b'word:rifampicin'
-0.975364 O        b'+1:lemma:hour'
-0.985559 O        b'-1:lemma:nsrr'
-0.985559 O        b'-1:word:NsrR'
-0.997260 O        b'-1:postag::'
-1.064484 O        b'+1:lemma:2'
-1.064484 O        b'+1:word:2'
-1.067361 O        b'+1:postag:VBG'
-1.084453 Temp     b'isLower'
-1.090676 Technique b'isLower'
-1.096556 Air      b'postag:NN'
-1.130890 O        b'-1:postag:VBG'
-1.137066 O        b'lemma:methanol'
-1.137066 O        b'word:methanol'
-1.146647 Med      b'-1:postag:IN'
-1.273126 Gtype    b'isUpper'
-1.333154 OD       b'isNumber'
-1.341950 Anti     b'postag:NNP'
-1.346674 O        b'lemma:wt'
-1.359316 O        b'-1:lemma:2'
-1.359316 O        b'-1:word:2'
-1.393623 O        b'lemma:mid-log'
-1.393623 O        b'word:mid-log'
-1.528613 Supp     b'postag:CC'
-1.536721 O        b'-1:lemma:ompr'
-1.544831 O        b'+1:lemma:1'
-1.544831 O        b'+1:word:1'
-1.748788 Gtype    b'isLower'
-2.010239 O        b'+1:word:hours'
-2.214812 Gversion b'isLower'
-2.235984 O        b'-1:lemma:_'
-2.235984 O        b'-1:word:_'
-2.367089 Supp     b'postag:JJ'
-2.519281 O        b'-1:lemma::'
-2.519281 O        b'-1:word::'
-2.594531 O        b'word:cells'
-3.006120 Gtype    b'isNumber'
-3.055847 Phase    b'postag:JJ'