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

best params:{'c1': 0.1226651147490872, 'c2': 0.0059614661118123965}
best CV score:0.8803342557712798
model size: 0.09M

Flat F1: 0.7870322428727526
             precision    recall  f1-score   support

         OD      0.720     0.818     0.766        22
         pH      1.000     1.000     1.000         8
  Technique      1.000     1.000     1.000        23
        Med      1.000     0.962     0.981        53
       Temp      0.857     0.828     0.842        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      0.878     0.847     0.862        85
  Substrain      0.000     0.000     0.000         0
       Supp      0.703     0.813     0.754       134
   Gversion      0.000     0.000     0.000         0

avg / total      0.792     0.792     0.787       451


Top likely transitions:
Agit   -> Agit    6.546314
Temp   -> Temp    6.273908
Med    -> Med     5.505671
OD     -> OD      5.123355
Supp   -> Supp    4.942859
Gversion -> Gversion 4.729429
Anti   -> Anti    4.720916
O      -> O       4.426960
Technique -> Technique 4.406068
Phase  -> Phase   4.280949
Gtype  -> Gtype   3.891716
Air    -> Air     3.810675
pH     -> pH      2.819825
O      -> Technique 1.044775
Substrain -> Gtype   0.705848
Air    -> O       0.556302
O      -> Supp    0.379959
O      -> Gtype   0.375188
Gtype  -> Supp    0.243828
Temp   -> O       0.177380
Supp   -> O       0.169874
Med    -> O       0.125191
O      -> Anti    0.110740
Technique -> Air     0.060678
Phase  -> O       0.013007
O      -> Phase   0.000798
Gtype  -> Air     0.000572
Gversion -> O       -0.000102
Technique -> pH      -0.016599
O      -> OD      -0.024272
O      -> Med     -0.119569
Supp   -> Technique -0.216815
OD     -> O       -0.243487
Gtype  -> Technique -0.497025
Technique -> O       -0.605664
O      -> Air     -0.748418
Gtype  -> Med     -0.888115
Gtype  -> O       -1.060047
Substrain -> O       -1.304321
Med    -> Supp    -2.225828


Top unlikely transitions:
Agit   -> Agit    6.546314
Temp   -> Temp    6.273908
Med    -> Med     5.505671
OD     -> OD      5.123355
Supp   -> Supp    4.942859
Gversion -> Gversion 4.729429
Anti   -> Anti    4.720916
O      -> O       4.426960
Technique -> Technique 4.406068
Phase  -> Phase   4.280949
Gtype  -> Gtype   3.891716
Air    -> Air     3.810675
pH     -> pH      2.819825
O      -> Technique 1.044775
Substrain -> Gtype   0.705848
Air    -> O       0.556302
O      -> Supp    0.379959
O      -> Gtype   0.375188
Gtype  -> Supp    0.243828
Temp   -> O       0.177380
Supp   -> O       0.169874
Med    -> O       0.125191
O      -> Anti    0.110740
Technique -> Air     0.060678
Phase  -> O       0.013007
O      -> Phase   0.000798
Gtype  -> Air     0.000572
Gversion -> O       -0.000102
Technique -> pH      -0.016599
O      -> OD      -0.024272
O      -> Med     -0.119569
Supp   -> Technique -0.216815
OD     -> O       -0.243487
Gtype  -> Technique -0.497025
Technique -> O       -0.605664
O      -> Air     -0.748418
Gtype  -> Med     -0.888115
Gtype  -> O       -1.060047
Substrain -> O       -1.304321
Med    -> Supp    -2.225828


Top positive:
7.575252 O        b'lemma:2'
6.809640 Air      b'word[:2]:Ae'
6.662167 O        b'lemma:1'
6.403734 O        b'word[:2]:re'
6.054204 Anti     b'-2:lemma:antibody'
5.739687 O        b'lemma:3'
5.489244 Gtype    b'word[:1]:\xce\x94'
5.302961 Technique b'word[:2]:Ch'
5.137089 O        b'-2:lemma:_'
5.097720 O        b'lemma:with'
4.688056 Air      b'word[:2]:An'
4.594330 O        b'lemma:-'
4.473065 Substrain b'word[:2]:MG'
4.408720 Phase    b'-2:lemma:phase'
4.331788 O        b'postag:IN'
4.219811 O        b'lemma:a'
4.171346 Air      b'lemma:anaerobic'
4.154474 Phase    b'lemma:mid-log'
4.118404 Gtype    b'-1:lemma:\xe2\x88\x86'
4.098792 O        b'postag:CC'
4.072045 O        b'-1:lemma:tag'
3.984012 O        b'+2:lemma:\xc2\xb0c'
3.862377 O        b'lemma:.'
3.862377 O        b'postag:.'
3.844935 O        b'+2:lemma:cra'
3.743179 Gversion b'lemma:chip-seq'
3.675544 O        b'postag:VBN'
3.627422 Supp     b'lemma:arginine'
3.618052 O        b'lemma:_'
3.618052 O        b'word[:1]:_'
3.608645 Supp     b'word[:2]:ni'
3.520948 Technique b'word[:2]:RN'
3.500782 Supp     b'-1:lemma:Cra'
3.401140 Air      b'postag:RB'
3.388544 Gtype    b'lemma:type'
3.388544 Gtype    b'word[:2]:ty'
3.357883 Med      b'lemma:MOPS'
3.357883 Med      b'word[:2]:MO'
3.356317 Supp     b'+1:lemma:\xc2\xb5m'
3.344199 O        b'-2:lemma:medium'
3.257816 Supp     b'lemma:Iron'
3.257816 Supp     b'word[:2]:Ir'
3.257816 Supp     b'-2:lemma:Anaerobic'
3.226031 Supp     b'+2:lemma:iptg'
3.178102 Supp     b'-1:lemma:with'
3.157084 Gtype    b'word[:2]:Fl'
3.102194 O        b'word[:1]:G'
3.053652 O        b'-1:lemma:anaerobic'
3.026889 O        b'word[:2]:ge'
2.969238 Med      b'+2:postag:CC'
2.948927 O        b'-1:lemma:\xc2\xb0c'
2.927664 O        b'-1:lemma:glucose'
2.925690 O        b'+1:lemma:pq'
2.916048 O        b'-1:lemma:0.3'
2.909720 Gtype    b'lemma:wt'
2.897608 Supp     b'lemma:acetate'
2.896988 O        b'-1:lemma:lb'
2.865201 Temp     b'-1:lemma:sample'
2.856196 Gtype    b'-2:lemma:genotype/variation'
2.769228 Supp     b'word[:1]:I'
2.666120 O        b'word[:1]:S'
2.649328 Supp     b'+1:lemma:1'
2.649075 Gtype    b'-2:lemma:delta'
2.642282 pH       b'word[:2]:pH'
2.634945 Anti     b'+1:lemma:antibody'
2.626979 Strain   b'+1:lemma:substr'
2.626979 Strain   b'-2:lemma:str'
2.616241 Gtype    b'word[:1]:d'
2.594465 O        b'postag::'
2.590957 O        b'word[:2]:Cr'
2.572107 O        b'word[:1]:B'
2.554486 Phase    b'word[:2]:ex'
2.536212 O        b'-1:lemma:media'
2.524774 Anti     b'+2:lemma:antibody'
2.488471 O        b'-2:lemma:myc'
2.482474 Supp     b'lemma:nacl'
2.459061 O        b'word[:2]:ha'
2.450073 Supp     b'-1:postag:CC'
2.444363 Gtype    b'word[:1]:W'
2.438081 Supp     b'-1:lemma:+'
2.395443 Supp     b'word[:2]:Fe'
2.329329 Supp     b'lemma:pq'
2.329329 Supp     b'word[:2]:PQ'
2.326544 Med      b'word[:1]:M'
2.324335 O        b'+1:postag:RB'
2.306092 Substrain b'word[:1]:M'
2.304851 Air      b'word[:1]:A'
2.293822 Phase    b'-2:lemma:until'
2.252925 Gtype    b'word[:2]:PK'
2.249470 Gtype    b'-2:postag:DT'
2.241387 O        b'word[:1]:R'
2.215324 Gtype    b'lemma:nsrr'
2.215324 Gtype    b'word[:2]:Ns'
2.215274 OD       b'word[:1]:O'
2.191687 O        b'postag:DT'
2.188516 Supp     b'-2:lemma:induce'
2.177885 Supp     b'+2:lemma:rifampicin'
2.164470 Supp     b'lemma:fructose'
2.153102 Phase    b'lemma:stationary'
2.149132 O        b'lemma:0.4'
2.135722 O        b'lemma:b'
2.124012 Supp     b'+1:lemma:2'
2.122572 O        b'postag:VBD'
2.116686 O        b'lemma:purr'
2.085879 O        b'+1:lemma:arca-8myc'
2.083414 O        b'+1:postag:NNP'
2.075593 O        b'lemma:growth'
2.055319 Gtype    b'lemma:\xe2\x88\x86'
2.055319 Gtype    b'word[:1]:\xe2\x88\x86'
2.048280 Med      b'word[:1]:L'
2.012888 Temp     b'-2:lemma:\xcf\x8332'
2.007442 Supp     b'-2:lemma:for'
2.006901 O        b'lemma:argr'
2.005941 O        b'word[:2]:Rp'
1.980113 O        b'-1:lemma:aerobically'
1.969163 O        b'word[:1]:c'
1.964013 Supp     b'lemma:Leu'
1.964013 Supp     b'word[:2]:Le'
1.964013 Supp     b'-2:lemma:Lrp'
1.955566 Temp     b'-2:lemma:30'
1.937909 Gtype    b'lemma:flag-tag'
1.937909 Gtype    b'-1:lemma:c-terminal'
1.931820 Med      b'+2:lemma:b2'
1.926115 Gtype    b'word[:1]:F'
1.924551 Supp     b'word[:2]:gl'
1.923659 Gtype    b'-1:lemma:vector'
1.919359 Temp     b'lemma:43'
1.919359 Temp     b'word[:2]:43'
1.905770 Gtype    b'+2:lemma:glucose'
1.901138 Temp     b'-1:lemma:\xcf\x8332'
1.896040 Air      b'+1:postag:IN'
1.895113 Technique b'word[:1]:R'
1.891367 O        b'+1:lemma:250'
1.890079 O        b'+2:lemma:70'
1.889582 Supp     b'-2:lemma:media'
1.886753 O        b'-1:lemma:Aerobic'
1.881608 O        b'word[:2]:In'
1.873786 O        b'-2:lemma:fructose'
1.861532 O        b'word[:2]:Cu'
1.859000 O        b'-2:lemma:ChIP-Seq'
1.840363 Temp     b'+2:postag:DT'
1.822321 Gtype    b'-1:lemma:rpob'
1.816828 Temp     b'-1:lemma:43'
1.814588 O        b'word[:1]:-'
1.800198 O        b'lemma:ompr'
1.800198 O        b'word[:2]:Om'
1.797377 Temp     b'word[:1]:3'
1.790537 Gtype    b'+1:lemma:type'
1.781626 Supp     b'-2:lemma:agent'
1.776197 O        b'lemma:harbor'
1.766609 Med      b'+1:lemma:0.4'
1.759749 O        b'-2:lemma:\xe2\x88\x86'
1.755643 Supp     b'word[:2]:ac'
1.740069 Med      b'lemma:broth'
1.740069 Med      b'-1:lemma:L'
1.740069 Med      b'word[:2]:br'
1.738945 Supp     b'-1:lemma:_'
1.738689 Phase    b'-1:lemma:mid-log'
1.736794 O        b'lemma:ml'
1.736794 O        b'word[:2]:ml'
1.723796 O        b'+2:postag:JJ'
1.674359 O        b'+1:lemma:mid-log'
1.669011 O        b'-1:postag:NNS'
1.668164 O        b'postag:VBG'
1.662173 O        b'+1:lemma:od600'
1.661476 Supp     b'-1:lemma:final'
1.654403 Supp     b'lemma:rifampicin'
1.652994 Gtype    b'word[:1]:w'
1.648808 pH       b'word[:1]:p'
1.646604 O        b'word[:2]:Pu'
1.633654 O        b'+2:lemma:fructose'
1.630978 Supp     b'word[:2]:ri'
1.623384 Gtype    b'+1:lemma:with'
1.614375 Supp     b'lemma:Adenine'
1.614375 Supp     b'word[:2]:Ad'
1.596390 O        b'lemma:at'
1.588885 Med      b'lemma:L'
1.588885 Med      b'+1:lemma:broth'
1.583682 O        b'-2:postag:FW'
1.554727 Supp     b'-2:lemma:supplement'
1.549286 O        b'word[:2]:ch'
1.545587 O        b'-1:lemma:type'
1.543468 Gtype    b'-2:lemma:genotype'
1.542533 Med      b'+2:lemma:b1'
1.538337 O        b'+1:lemma:chip-seq'
1.537052 Gtype    b'word[:2]:WT'
1.520544 Air      b'word[:1]:a'
1.520380 Gtype    b'hGreek'
1.520335 O        b'lemma:A'
1.516773 Air      b'-2:lemma:%'
1.514240 Supp     b'lemma:no3'
1.514240 Supp     b'word[:2]:NO'
1.492873 Gversion b'lemma:.2'
1.492873 Gversion b'-1:lemma:u00096'
1.492873 Gversion b'word[:2]:.2'
1.488140 O        b'+2:lemma:allow'
1.476148 O        b'word[:1]:h'
1.475371 Supp     b'-1:lemma:vol'
1.475371 Supp     b'-2:lemma:1/100'
1.475371 Supp     b'+2:lemma:1m'


Top negative:
-0.162054 Phase    b'-2:postag:NN'
-0.163078 Gtype    b'word[:1]:-'
-0.164615 Supp     b'+2:lemma:glucose'
-0.165684 O        b'-1:lemma:30'
-0.169375 Supp     b'+1:postag:-RRB-'
-0.170442 Med      b'+1:postag:IN'
-0.172422 O        b'+1:postag:-RRB-'
-0.174439 O        b'word[:2]:ae'
-0.175236 Supp     b'-2:postag:-LRB-'
-0.177435 Temp     b'hGreek'
-0.181562 O        b'lemma:of'
-0.181562 O        b'word[:2]:of'
-0.184084 O        b'+1:lemma:-rrb-'
-0.189656 O        b'+2:lemma:at'
-0.190247 O        b'word[:2]:0.'
-0.194061 O        b'+2:lemma:until'
-0.195801 O        b'-2:postag:SYM'
-0.202103 O        b'-1:lemma:0.2'
-0.203062 O        b'-2:lemma:30'
-0.203787 Supp     b'+2:postag:NNP'
-0.211804 O        b'lemma:co2'
-0.211804 O        b'word[:2]:CO'
-0.213063 O        b'-2:lemma:2'
-0.216419 O        b'-1:lemma:until'
-0.216729 O        b'lemma:1m'
-0.216729 O        b'word[:2]:1M'
-0.221397 O        b'-2:lemma:genome'
-0.225533 Air      b'+2:lemma:95'
-0.228195 O        b'-1:lemma:g/l'
-0.228754 Supp     b'+2:lemma:-rrb-'
-0.236812 O        b'-1:lemma:iptg'
-0.242981 O        b'-2:lemma:10'
-0.249890 Supp     b'+2:postag:-RRB-'
-0.253101 Supp     b'-1:postag:NNP'
-0.254872 O        b'word[:1]:2'
-0.258890 Supp     b'-1:lemma:-lrb-'
-0.259217 O        b'-1:lemma:minimal'
-0.261201 O        b'-2:postag:-LRB-'
-0.263028 O        b'+1:lemma:phosphate'
-0.263082 O        b'lemma:methanol'
-0.263082 O        b'-2:lemma:dissolve'
-0.269144 O        b'+1:lemma:.'
-0.269144 O        b'+1:postag:.'
-0.271418 O        b'+1:lemma:1/100'
-0.271418 O        b'-2:lemma:sodium'
-0.271418 O        b'+2:lemma:vol'
-0.272080 Temp     b'postag:NN'
-0.277250 O        b'lemma:nitrate'
-0.277269 O        b'-2:lemma:phase'
-0.280720 O        b'word[:2]:Fe'
-0.292805 O        b'-1:lemma:control'
-0.294148 Gtype    b'word[:1]:h'
-0.311048 Gversion b'-1:postag:NN'
-0.314490 Med      b'+2:postag:VBN'
-0.322935 Supp     b'lemma:10'
-0.323427 O        b'-2:lemma:anaerobically'
-0.325607 O        b'word[:2]:OD'
-0.329365 O        b'lemma:media'
-0.333354 O        b'-2:lemma:at'
-0.333503 O        b'lemma:wt'
-0.333755 O        b'-2:lemma:aerobically'
-0.335336 OD       b'hUpper'
-0.335336 OD       b'hLower'
-0.335952 O        b'lemma:aerobically'
-0.338742 O        b'word[:1]:K'
-0.340286 O        b'+2:lemma:-rrb-'
-0.344360 Supp     b'-1:postag:-LRB-'
-0.350896 O        b'-1:lemma:of'
-0.352645 Med      b'-2:postag:IN'
-0.354858 O        b'-1:lemma:1m'
-0.354858 O        b'+2:lemma:7.6'
-0.372252 Supp     b'symb'
-0.378465 O        b'word[:2]:ri'
-0.381134 Phase    b'+1:postag:NN'
-0.384639 O        b'-2:lemma:pahse'
-0.391314 O        b'+1:lemma:1m'
-0.391314 O        b'-2:lemma:vol'
-0.397247 O        b'-1:lemma:sodium'
-0.397247 O        b'+2:lemma:1/100'
-0.409851 O        b'+1:lemma:supplement'
-0.413141 O        b'-1:lemma:37'
-0.413339 O        b'lemma:rifampicin'
-0.414986 O        b'+2:lemma:10'
-0.415120 O        b'+1:lemma:+'
-0.416764 O        b'+2:lemma:ph'
-0.432602 O        b'word[:1]:F'
-0.434646 Med      b'-1:postag:NN'
-0.435221 O        b'-1:lemma:dissolve'
-0.435221 O        b'+1:lemma:methanol'
-0.438173 Anti     b'+2:postag:JJ'
-0.438380 O        b'lemma:30'
-0.438561 O        b'lemma:2h'
-0.438561 O        b'-1:lemma:additional'
-0.438561 O        b'word[:2]:2h'
-0.438599 Gtype    b'+1:lemma:-rrb-'
-0.448423 O        b'lemma:sodium'
-0.448756 O        b'+1:lemma:_'
-0.449001 Supp     b'-2:postag:JJ'
-0.453606 O        b'word[:1]:0'
-0.454508 O        b'-2:postag:DT'
-0.456094 O        b'-2:lemma:dpd'
-0.459173 O        b'-2:lemma:supplement'
-0.461268 O        b'word[:2]:gl'
-0.474879 Anti     b'+2:lemma:polyclonal'
-0.477585 O        b'lemma:anaerobically'
-0.477773 Supp     b'+1:postag:NNS'
-0.479099 O        b'-1:lemma:IP'
-0.482821 Supp     b'word[:2]:an'
-0.485864 O        b'+1:lemma:g/l'
-0.488474 O        b'-2:lemma:IP'
-0.491811 Gtype    b'postag:VBG'
-0.492017 O        b'-1:lemma:\xe2\x88\x86'
-0.495222 O        b'+2:postag:-RRB-'
-0.498620 Anti     b'+1:lemma:anti-fur'
-0.499738 Med      b'symb'
-0.502087 O        b'+2:lemma:tag'
-0.520791 O        b'+2:lemma:add'
-0.549562 O        b'-1:lemma:mm'
-0.588913 O        b'+1:lemma:until'
-0.589527 O        b'word[:2]:pH'
-0.594102 O        b'+2:lemma:.'
-0.594102 O        b'+2:postag:.'
-0.605760 O        b'-1:lemma:ph'
-0.618761 Agit     b'symb'
-0.622723 O        b'-2:postag::'
-0.638337 Agit     b'hUpper'
-0.638337 Agit     b'hLower'
-0.641043 Supp     b'word[:1]:C'
-0.660369 O        b'lemma:mid-log'
-0.661070 O        b'+1:lemma:mm'
-0.661103 O        b'word[:2]:mg'
-0.665736 O        b'+1:lemma:2.0'
-0.668595 O        b'word[:2]:ni'
-0.678332 O        b'-1:lemma:rpob'
-0.688468 O        b'-1:lemma:nsrr'
-0.704290 Supp     b'+1:lemma:-lrb-'
-0.704703 Gtype    b'+2:lemma:cra'
-0.711182 Med      b'-2:postag:VBN'
-0.719312 O        b'+2:lemma:a'
-0.720089 O        b'-1:lemma:grow'
-0.723645 Supp     b'+1:postag:-LRB-'
-0.729817 O        b'-2:lemma:glucose'
-0.736832 O        b'word[:2]:me'
-0.752358 O        b'-2:lemma:until'
-0.753413 O        b'-2:postag:RB'
-0.757806 Air      b'-1:postag:JJ'
-0.783439 Supp     b'+1:lemma:,'
-0.783439 Supp     b'+1:postag:,'
-0.848095 O        b'-2:lemma::'
-0.852042 O        b'-1:lemma:final'
-0.866705 Air      b'postag:NN'
-0.881470 O        b'+2:lemma:mid-log'
-0.881613 O        b'-1:postag::'
-0.885739 OD       b'+1:postag:NN'
-0.896826 O        b'+2:lemma:+'
-0.916693 O        b'postag:RB'
-0.920471 O        b'-1:lemma:co2'
-0.941388 Supp     b'+2:postag:CD'
-0.944176 O        b'word[:2]:fl'
-0.945676 Supp     b'postag:JJ'
-0.952271 O        b'+1:postag:IN'
-0.963704 Gtype    b'word[:1]:C'
-0.984734 O        b'postag:VBP'
-1.006778 O        b'word[:1]:d'
-1.044447 Phase    b'hUpper'
-1.044447 Phase    b'hLower'
-1.052063 O        b'+2:lemma:fnr'
-1.114096 O        b'-1:lemma:cra'
-1.134157 O        b'+1:lemma:at'
-1.135934 Supp     b'+2:lemma:fructose'
-1.208365 O        b'-1:lemma:vol'
-1.208365 O        b'-2:lemma:1/100'
-1.208365 O        b'+2:lemma:1m'
-1.221260 O        b'+2:lemma:then'
-1.299098 O        b'-1:lemma:1'
-1.312469 Phase    b'-1:postag:JJ'
-1.321864 O        b'-2:lemma:0.3'
-1.350629 O        b'word[:1]:N'
-1.379890 Med      b'-2:lemma:grow'
-1.438599 O        b'+1:lemma:in'
-1.474734 Technique b'postag:NN'
-1.506938 O        b'lemma:0.3'
-1.612245 O        b'-2:lemma:media'
-1.629029 Supp     b'+2:lemma:2'
-1.633213 O        b'-1:lemma:2'
-1.647783 O        b'+2:lemma:rifampicin'
-1.680381 O        b'-1:postag:VBG'
-1.728533 Anti     b'postag:NNP'
-1.775531 O        b'word[:2]:30'
-1.801903 Supp     b'+2:lemma:1'
-1.869306 O        b'-2:lemma:rifampicin'
-2.061187 O        b'-1:lemma:sample'
-2.202629 Phase    b'postag:JJ'
-2.454625 O        b'word[:2]:Ch'
-2.471569 O        b'word[:1]:P'
-2.513568 O        b'+1:lemma:1'
-2.695155 OD       b'+2:lemma:aerobically'
-3.362641 O        b'+1:lemma:2'
-4.267606 O        b'-1:lemma::'
-5.439386 O        b'-1:lemma:_'