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

best params:{'c1': 0.07838162718183349, 'c2': 0.05887606797757319}
best CV score:0.87030448615518
model size: 0.16M

Flat F1: 0.7823412170507693
             precision    recall  f1-score   support

         OD      1.000     0.818     0.900        22
         pH      1.000     1.000     1.000         8
  Technique      1.000     0.913     0.955        23
        Med      1.000     0.925     0.961        53
       Temp      0.917     0.759     0.830        29
       Vess      1.000     1.000     1.000         1
       Agit      0.000     0.000     0.000         0
      Phase      0.875     0.933     0.903        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      0.849     0.859     0.854        85
  Substrain      0.000     0.000     0.000         0
       Supp      0.686     0.813     0.744       134
   Gversion      0.000     0.000     0.000         0

avg / total      0.798     0.778     0.782       451


Top likely transitions:
Temp   -> Temp    4.911417
OD     -> OD      4.541853
Med    -> Med     4.405893
Supp   -> Supp    4.305413
Agit   -> Agit    4.272648
Anti   -> Anti    3.837258
O      -> O       3.787660
Gtype  -> Gtype   3.752687
Gversion -> Gversion 3.628661
Air    -> Air     3.521236
Phase  -> Phase   3.320009
Technique -> Technique 2.966375
pH     -> pH      2.362986
Substrain -> Gtype   1.121355
O      -> Technique 0.896285
Gtype  -> Supp    0.860650
O      -> Supp    0.689540
O      -> Gtype   0.595827
Gtype  -> Air     0.530941
Technique -> Air     0.501834
Air    -> O       0.490782
Gtype  -> pH      0.392258
Temp   -> O       0.195983
Med    -> O       0.164949
Supp   -> O       0.068384
O      -> Temp    0.032340
O      -> pH      0.007653
O      -> Strain  -0.003076
Gversion -> Gtype   -0.013131
Gversion -> Air     -0.016755
Supp   -> Anti    -0.028664
Vess   -> O       -0.036195
Agit   -> Supp    -0.042183
Gtype  -> Phase   -0.047540
Supp   -> Technique -0.060640
Supp   -> pH      -0.062714
O      -> Phase   -0.068478
Technique -> OD      -0.069783
Supp   -> OD      -0.073453
O      -> Agit    -0.079631
Phase  -> Air     -0.079705
Anti   -> Med     -0.089699
Anti   -> Gtype   -0.095119
Gtype  -> Gversion -0.100232
Temp   -> Air     -0.116744
OD     -> O       -0.129801
Phase  -> Med     -0.135688
Air    -> Agit    -0.138019
Phase  -> O       -0.139580
pH     -> Supp    -0.141124


Top unlikely transitions:
Supp   -> Technique -0.060640
Supp   -> pH      -0.062714
O      -> Phase   -0.068478
Technique -> OD      -0.069783
Supp   -> OD      -0.073453
O      -> Agit    -0.079631
Phase  -> Air     -0.079705
Anti   -> Med     -0.089699
Anti   -> Gtype   -0.095119
Gtype  -> Gversion -0.100232
Temp   -> Air     -0.116744
OD     -> O       -0.129801
Phase  -> Med     -0.135688
Air    -> Agit    -0.138019
Phase  -> O       -0.139580
pH     -> Supp    -0.141124
Air    -> Temp    -0.146478
OD     -> Supp    -0.177929
Gversion -> O       -0.195235
Med    -> Air     -0.218392
Technique -> Supp    -0.218928
O      -> OD      -0.220859
Anti   -> O       -0.227867
Anti   -> Supp    -0.241653
Temp   -> Med     -0.265069
Air    -> Gtype   -0.270959
Gversion -> Supp    -0.271472
Phase  -> OD      -0.278093
O      -> Med     -0.292957
Supp   -> Phase   -0.310262
Agit   -> O       -0.315551
Technique -> O       -0.317964
Agit   -> Air     -0.327189
Air    -> Phase   -0.332685
Supp   -> Gtype   -0.386391
Gtype  -> Technique -0.394676
Supp   -> Air     -0.403362
Gtype  -> Anti    -0.428993
Phase  -> Supp    -0.440098
Air    -> Supp    -0.449326
Technique -> pH      -0.462944
Air    -> Med     -0.469469
OD     -> Air     -0.509283
Gtype  -> Med     -0.621751
Supp   -> Med     -0.659958
Gtype  -> O       -0.671881
O      -> Air     -0.712510
Technique -> Gtype   -1.006943
Substrain -> O       -1.077790
Med    -> Supp    -1.486790


Top positive:
4.124249 Anti     b'-2:lemma:antibody'
3.641687 Air      b'word:Aerobic'
3.497811 O        b'-2:lemma:_'
3.258366 Air      b'lemma:anaerobic'
3.145552 O        b'lemma:_'
3.145552 O        b'word:_'
3.024671 Gtype    b'-2:lemma:genotype/variation'
2.928771 Air      b'postag:RB'
2.783339 Technique b'word:ChIP-Seq'
2.697083 O        b'lemma:2'
2.697083 O        b'word:2'
2.670728 Phase    b'-2:lemma:phase'
2.637125 O        b'postag::'
2.618748 O        b'word:Cra'
2.610104 Technique b'word:ChIP-exo'
2.571728 O        b'lemma:1'
2.571728 O        b'word:1'
2.511177 O        b'postag:IN'
2.472685 Gtype    b'-2:lemma:genotype'
2.396386 Supp     b'lemma:pq'
2.396386 Supp     b'word:PQ'
2.337247 O        b'lemma:.'
2.337247 O        b'postag:.'
2.337247 O        b'word:.'
2.332296 Technique b'lemma:rna-seq'
2.320371 Gtype    b'word:WT'
2.309222 Gtype    b'lemma:wt'
2.274976 O        b'-2:lemma:flagtag'
2.273949 Technique b'word:ChIPSeq'
2.258997 Technique b'lemma:ChIP-exo'
2.199264 Air      b'word:Anaerobic'
2.142635 O        b'-1:lemma:ChIP-exo'
2.096906 Supp     b'lemma:nh4cl'
2.072818 Phase    b'lemma:mid-log'
2.072818 Phase    b'word:mid-log'
2.053563 Gtype    b'lemma:wild-type'
2.044128 O        b'lemma:rpob'
2.044128 O        b'word:RpoB'
2.020270 O        b'postag:VBN'
2.020107 O        b'lemma:3'
2.020107 O        b'word:3'
2.011865 Supp     b'-1:word:Cra'
1.983566 Gtype    b'lemma:type'
1.983566 Gtype    b'word:type'
1.975796 O        b'lemma:-'
1.975796 O        b'word:-'
1.959537 O        b'-2:lemma:medium'
1.955236 Gtype    b'-2:lemma:affyexp'
1.942868 Gtype    b'lemma:\xce\xb4cra'
1.939375 Gtype    b'word:\xce\x94cra'
1.938173 Technique b'lemma:chipseq'
1.890561 Supp     b'lemma:Iron'
1.890561 Supp     b'word:Iron'
1.890561 Supp     b'+1:word:Deficient'
1.890561 Supp     b'-2:lemma:Anaerobic'
1.874088 Supp     b'lemma:acetate'
1.874088 Supp     b'word:acetate'
1.819674 pH       b'+1:postag:CD'
1.788257 O        b'lemma:b'
1.788257 O        b'word:B'
1.782368 O        b'word:A'
1.774988 O        b'+2:lemma:\xc2\xb0c'
1.768402 O        b'+2:postag:JJ'
1.762269 Gtype    b'lemma:\xe2\x88\x86'
1.762269 Gtype    b'word:\xe2\x88\x86'
1.746520 Med      b'lemma:MOPS'
1.746520 Med      b'word:MOPS'
1.723641 Supp     b'+2:lemma:iptg'
1.722034 Air      b'lemma:Aerobic'
1.705697 O        b'-1:word:Aerobic'
1.703316 Anti     b'+2:lemma:antibody'
1.702891 O        b'postag:CC'
1.699990 Supp     b'-1:lemma:with'
1.699990 Supp     b'-1:word:with'
1.688533 Supp     b'lemma:glucose'
1.688533 Supp     b'word:glucose'
1.674465 Supp     b'lemma:no3'
1.674465 Supp     b'word:NO3'
1.666479 Supp     b'lemma:nacl'
1.666479 Supp     b'word:NaCl'
1.641938 Supp     b'lemma:arginine'
1.638237 Substrain b'lemma:mg1655'
1.638237 Substrain b'word:MG1655'
1.637725 Supp     b'+1:lemma:\xc2\xb5m'
1.637725 Supp     b'+1:word:\xc2\xb5M'
1.636903 Med      b'isUpper'
1.611838 O        b'+1:postag:NNP'
1.611343 O        b'lemma:a'
1.607795 Technique b'+2:lemma:ph5'
1.602510 Air      b'word:anaerobic'
1.599293 O        b'+1:postag:RB'
1.590988 Gtype    b'-1:lemma:\xe2\x88\x86'
1.590988 Gtype    b'-1:word:\xe2\x88\x86'
1.589631 Gtype    b'-2:postag:DT'
1.583352 Med      b'+2:postag:CC'
1.579250 O        b'isLower'
1.578231 Gtype    b'+2:lemma:glucose'
1.552685 Gtype    b'+1:lemma:type'
1.552685 Gtype    b'+1:word:type'
1.528892 Substrain b'-2:lemma:substr'
1.515887 Supp     b'lemma:nitrate'
1.515887 Supp     b'word:nitrate'
1.503178 O        b'-1:lemma:tag'
1.473485 Gtype    b'lemma:\xce\xb4soxr'
1.473485 Gtype    b'word:\xce\x94soxR'
1.456677 O        b'-1:word:tag'
1.455346 Gtype    b'lemma:flag-tag'
1.455346 Gtype    b'-1:lemma:c-terminal'
1.455346 Gtype    b'word:Flag-tag'
1.455346 Gtype    b'-1:word:C-terminal'
1.451462 Technique b'word:RNA-Seq'
1.434331 Supp     b'-1:lemma:Cra'
1.432730 O        b'+1:word:ChIP-Seq'
1.426572 O        b'-1:lemma:anaerobic'
1.425108 Gtype    b'lemma:\xce\xb4fur'
1.425108 Gtype    b'word:\xce\x94fur'
1.425025 Technique b'lemma:rnaseq'
1.425025 Technique b'word:RNASeq'
1.416012 O        b'postag:VBG'
1.415750 Gversion b'-2:lemma:nc'
1.408974 Gversion b'lemma:chip-seq'
1.379843 O        b'+1:lemma:arca-8myc'
1.379843 O        b'+1:word:ArcA-8myc'
1.374672 O        b'lemma:with'
1.374672 O        b'word:with'
1.374577 O        b'lemma:Cra'
1.373182 Gversion b'word:ChIP-Seq'
1.372454 Gtype    b'-2:lemma:delta'
1.369100 O        b'+2:lemma:cra'
1.367463 O        b'-1:lemma:0.3'
1.367463 O        b'-1:word:0.3'
1.366576 O        b'-2:lemma:myc'
1.365144 O        b'lemma:ompr'
1.365144 O        b'word:OmpR'
1.358116 Supp     b'-1:postag:CC'
1.351356 Gtype    b'postag:JJ'
1.340661 Strain   b'+1:lemma:substr'
1.340661 Strain   b'+1:word:substr'
1.340661 Strain   b'-2:lemma:str'
1.337333 Gtype    b'+1:lemma:with'
1.337333 Gtype    b'+1:word:with'
1.331237 Supp     b'-2:lemma:agent'
1.319017 Air      b'+1:postag:IN'
1.313717 O        b'lemma:harbor'
1.313717 O        b'word:harboring'
1.311281 Technique b'-1:lemma:chip-exo'
1.310088 Air      b'lemma:aerobic'
1.301908 Temp     b'isNumber'
1.296057 O        b'lemma:chip'
1.294021 Med      b'+2:lemma:b2'
1.290231 O        b'+1:lemma:pq'
1.290231 O        b'+1:word:PQ'
1.288968 Supp     b'-2:lemma:media'
1.285093 O        b'-1:lemma:lb'
1.285093 O        b'-1:word:LB'
1.284396 O        b'-1:lemma:glucose'
1.284396 O        b'-1:word:glucose'
1.281083 O        b'-1:lemma:media'
1.281083 O        b'-1:word:media'
1.280357 Med      b'lemma:lb'
1.280357 Med      b'word:LB'
1.277491 O        b'+2:lemma:70'
1.276083 Supp     b'lemma:Leu'
1.276083 Supp     b'word:Leu'
1.276083 Supp     b'-2:lemma:Lrp'
1.266271 Supp     b'-2:lemma:induce'
1.263127 Phase    b'lemma:exponential'
1.263127 Phase    b'word:exponential'
1.263127 Phase    b'lemma:stationary'
1.263127 Phase    b'word:stationary'
1.250254 Air      b'-1:lemma:ChIP-Seq'
1.250254 Air      b'-1:word:ChIP-Seq'
1.245392 Air      b'-2:lemma:IP'
1.237417 OD       b'postag:CD'
1.227048 Supp     b'-1:lemma:+'
1.227048 Supp     b'-1:word:+'
1.225001 Gtype    b'-1:postag:VBG'
1.222768 O        b'lemma:Custom'
1.222768 O        b'word:Custom'
1.222690 Strain   b'lemma:k-12'
1.222690 Strain   b'word:K-12'
1.211762 Gversion b'-2:lemma:build'
1.207468 Supp     b'+1:lemma:1'
1.207468 Supp     b'+1:word:1'
1.200932 Air      b'-1:lemma:-'
1.200932 Air      b'-1:word:-'
1.200071 Gversion b'lemma:nc'
1.200071 Gversion b'word:NC'
1.192535 O        b'+2:lemma:fructose'
1.191869 Gtype    b'postag:NN'
1.189235 pH       b'lemma:ph5'
1.189235 pH       b'+1:lemma:.5'
1.189235 pH       b'word:pH5'
1.189235 pH       b'+1:word:.5'
1.180856 O        b'lemma:at'
1.174453 Supp     b'lemma:rifampicin'
1.174453 Supp     b'word:rifampicin'
1.166521 O        b'lemma:argr'
1.166521 O        b'word:ArgR'
1.162681 OD       b'-1:postag:IN'


Top negative:
-0.311652 O        b'+1:word:supplemented'
-0.312640 O        b'-2:lemma:control'
-0.323532 O        b'lemma:minimal'
-0.323532 O        b'word:minimal'
-0.323844 O        b'-1:lemma:ph'
-0.323844 O        b'-1:word:pH'
-0.324956 O        b'lemma:37'
-0.324956 O        b'word:37'
-0.328081 O        b'-1:lemma:cra'
-0.328436 O        b'lemma:methanol'
-0.328436 O        b'word:methanol'
-0.328436 O        b'-2:lemma:dissolve'
-0.332352 O        b'-1:lemma:37'
-0.332352 O        b'-1:word:37'
-0.337835 Anti     b'+1:lemma:anti-fur'
-0.337835 Anti     b'+1:word:anti-Fur'
-0.338497 O        b'+1:lemma:1m'
-0.338497 O        b'+1:word:1M'
-0.338497 O        b'-2:lemma:vol'
-0.340286 O        b'+2:lemma:add'
-0.348253 Supp     b'-1:lemma:10'
-0.348253 Supp     b'-1:word:10'
-0.355580 O        b'-2:lemma:10'
-0.356547 O        b'-2:lemma:minimal'
-0.359288 O        b'-1:lemma:ml'
-0.359288 O        b'-1:word:ml'
-0.361424 O        b'-1:lemma:dissolve'
-0.361424 O        b'+1:lemma:methanol'
-0.361424 O        b'-1:word:dissolved'
-0.361424 O        b'+1:word:methanol'
-0.367262 Substrain b'isLower'
-0.367703 Supp     b'postag:CC'
-0.367998 O        b'-1:lemma:co2'
-0.367998 O        b'-1:word:CO2'
-0.370364 O        b'+2:lemma:-rrb-'
-0.374065 O        b'-2:lemma:genome'
-0.375208 Supp     b'-2:lemma:.'
-0.375208 Supp     b'-2:postag:.'
-0.378770 O        b'+2:lemma:at'
-0.385912 O        b'-1:lemma:fresh'
-0.385912 O        b'-1:word:fresh'
-0.389093 Strain   b'isLower'
-0.389489 Temp     b'-2:postag:NN'
-0.390296 O        b'lemma:aerobic'
-0.391758 O        b'-2:lemma:aerobically'
-0.393460 O        b'-1:lemma:2'
-0.393460 O        b'-1:word:2'
-0.397723 O        b'+1:lemma:mm'
-0.397723 O        b'+1:word:mM'
-0.398729 O        b'-1:lemma:rpob'
-0.398729 O        b'-1:word:RpoB'
-0.401643 O        b'-1:lemma:mm'
-0.401643 O        b'-1:word:mM'
-0.402690 Supp     b'-2:lemma:grow'
-0.403521 O        b'-2:lemma:pahse'
-0.404104 O        b'-1:lemma:grow'
-0.411213 O        b'lemma:nitrogen'
-0.411213 O        b'word:nitrogen'
-0.411373 O        b'+1:lemma:+'
-0.411373 O        b'+1:word:+'
-0.415137 Gtype    b'-2:postag:CD'
-0.424176 O        b'+1:word:ChIP-exo'
-0.437712 O        b'-2:postag:SYM'
-0.445165 Supp     b'+1:lemma:,'
-0.445165 Supp     b'+1:postag:,'
-0.445165 Supp     b'+1:word:,'
-0.453707 O        b'lemma:fructose'
-0.453707 O        b'word:fructose'
-0.457985 O        b'-2:lemma:nh4cl'
-0.460272 O        b'lemma:anaerobically'
-0.460272 O        b'word:anaerobically'
-0.460899 O        b'+2:lemma:reference'
-0.461152 O        b'lemma:2h'
-0.461152 O        b'-1:lemma:additional'
-0.461152 O        b'word:2h'
-0.461152 O        b'-1:word:additional'
-0.465651 O        b'-2:lemma:rpob'
-0.467210 O        b'lemma:anaerobic'
-0.482841 Supp     b'+1:lemma:-lrb-'
-0.482841 Supp     b'+1:word:-LRB-'
-0.487123 O        b'-1:lemma:\xe2\x88\x86'
-0.487123 O        b'-1:word:\xe2\x88\x86'
-0.490214 O        b'lemma:aerobically'
-0.490214 O        b'word:aerobically'
-0.493650 O        b'lemma:of'
-0.493650 O        b'word:of'
-0.498710 O        b'+2:lemma:mid-log'
-0.499349 O        b'-1:lemma:30'
-0.499349 O        b'-1:word:30'
-0.499545 O        b'+2:lemma:fnr'
-0.506778 Supp     b'+1:postag:-LRB-'
-0.511585 O        b'word:ChIP-exo'
-0.513406 O        b'-1:lemma:chip-exo'
-0.517504 Supp     b'+2:lemma:glucose'
-0.518174 O        b'+1:lemma:g/l'
-0.518174 O        b'+1:word:g/L'
-0.520916 O        b'-2:lemma:anaerobically'
-0.530292 O        b'+2:postag:-RRB-'
-0.531458 Med      b'-1:postag:NN'
-0.532473 O        b'lemma:nh4cl'
-0.535293 O        b'-2:lemma:IP'
-0.538050 Gtype    b'-2:lemma:\xe2\x88\x86'
-0.542753 pH       b'isUpper'
-0.559582 O        b'lemma:glucose'
-0.559582 O        b'word:glucose'
-0.563071 O        b'-2:lemma:dpd'
-0.568245 O        b'+1:lemma:until'
-0.568245 O        b'+1:word:until'
-0.569455 Supp     b'-2:postag:NNS'
-0.569843 Air      b'+1:postag:JJ'
-0.573996 O        b'lemma:\xce\xb4fur'
-0.573996 O        b'word:\xce\x94fur'
-0.574100 O        b'+1:postag:IN'
-0.583141 O        b'+1:lemma:in'
-0.583141 O        b'+1:word:in'
-0.584211 O        b'lemma:30'
-0.584211 O        b'word:30'
-0.587080 Agit     b'isUpper'
-0.591540 Supp     b'-1:postag:NNP'
-0.595806 O        b'-1:postag::'
-0.599170 O        b'-2:lemma:phase'
-0.601235 O        b'+2:lemma:b'
-0.602048 O        b'+2:lemma:then'
-0.608335 O        b'-1:lemma:1'
-0.608335 O        b'-1:word:1'
-0.608384 Anti     b'isUpper'
-0.617575 O        b'-2:lemma:until'
-0.617630 O        b'lemma:mid-log'
-0.617630 O        b'word:mid-log'
-0.621155 O        b'-2:lemma:fresh'
-0.626295 O        b'-2:lemma:media'
-0.635986 Phase    b'isUpper'
-0.639041 O        b'+2:lemma:250'
-0.644310 Supp     b'-2:postag:JJ'
-0.653651 O        b'+1:lemma:at'
-0.653651 O        b'+1:word:at'
-0.658042 Supp     b'-2:lemma:treat'
-0.664028 Med      b'+2:postag:VBN'
-0.670366 O        b'-1:lemma:nsrr'
-0.670366 O        b'-1:word:NsrR'
-0.670591 O        b'-2:postag:DT'
-0.674143 O        b'-1:lemma:vol'
-0.674143 O        b'-1:word:vol'
-0.674143 O        b'-2:lemma:1/100'
-0.674143 O        b'+2:lemma:1m'
-0.698342 Med      b'-2:postag:VBN'
-0.715097 O        b'+1:lemma:2.0'
-0.715097 O        b'+1:word:2.0'
-0.721531 pH       b'isLower'
-0.742327 O        b'-1:lemma:sample'
-0.752266 O        b'lemma:nitrate'
-0.752266 O        b'word:nitrate'
-0.767047 O        b'-2:lemma::'
-0.787116 O        b'lemma:rifampicin'
-0.787116 O        b'word:rifampicin'
-0.792673 O        b'+2:lemma:rifampicin'
-0.797812 O        b'+1:postag:VBG'
-0.816000 O        b'lemma:wt'
-0.816563 O        b'-1:lemma:IP'
-0.816563 O        b'-1:word:IP'
-0.834409 O        b'lemma:0.3'
-0.834409 O        b'word:0.3'
-0.837034 Supp     b'+2:postag:CD'
-0.838689 O        b'postag:VBP'
-0.840231 Technique b'isNumber'
-0.846346 Air      b'postag:NN'
-0.850091 Gtype    b'postag:VBG'
-0.854432 O        b'-2:postag:RB'
-0.883296 Gtype    b'isLower'
-0.888784 O        b'lemma:media'
-0.888784 O        b'word:media'
-0.895754 Gversion b'isLower'
-0.904522 Temp     b'postag:NN'
-0.924495 O        b'+2:lemma:+'
-0.935152 Gtype    b'+2:lemma:cra'
-0.943613 Gtype    b'isNumber'
-0.975059 O        b'postag:RB'
-1.021612 Med      b'-2:lemma:grow'
-1.024421 Anti     b'+2:lemma:polyclonal'
-1.031484 O        b'-2:lemma:rifampicin'
-1.059929 O        b'+1:lemma:1'
-1.059929 O        b'+1:word:1'
-1.084068 Supp     b'+2:lemma:fructose'
-1.123084 Technique b'isLower'
-1.132053 O        b'-2:lemma:0.3'
-1.168749 Supp     b'+2:lemma:1'
-1.183772 OD       b'+1:postag:NN'
-1.263288 OD       b'+2:lemma:aerobically'
-1.270174 Supp     b'+2:lemma:2'
-1.329893 Anti     b'postag:NNP'
-1.366300 O        b'+1:lemma:2'
-1.366300 O        b'+1:word:2'
-1.389405 Phase    b'-1:postag:JJ'
-1.607302 Supp     b'postag:JJ'
-1.676382 O        b'-1:postag:VBG'
-1.773723 O        b'-1:lemma::'
-1.773723 O        b'-1:word::'
-1.857508 Phase    b'postag:JJ'
-1.945074 O        b'-1:lemma:_'
-1.945074 O        b'-1:word:_'