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

best params:{'c1': 0.19555004078116134, 'c2': 0.013719557943369584}
best CV score:0.8266077920368616
model size: 0.11M

Flat F1: 0.8150979684771513
             precision    recall  f1-score   support

         OD      0.789     0.405     0.536        37
         pH      1.000     1.000     1.000        12
  Technique      1.000     0.909     0.952        22
        Med      0.893     0.877     0.885        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     0.895     0.944        19
        Air      0.810     0.758     0.783        62
       Anti      1.000     0.667     0.800         9
     Strain      1.000     1.000     1.000         1
      Gtype      0.937     0.840     0.886       106
  Substrain      0.000     0.000     0.000         1
       Supp      0.853     0.684     0.759       136
   Gversion      0.000     0.000     0.000         0

avg / total      0.882     0.767     0.815       480


Top likely transitions:
OD     -> OD      7.029011
Agit   -> Agit    6.826413
Temp   -> Temp    5.979472
Med    -> Med     5.720420
Anti   -> Anti    5.293877
Gversion -> Gversion 4.696471
Technique -> Technique 4.642372
Air    -> Air     4.554023
Supp   -> Supp    4.536382
Phase  -> Phase   4.521590
Gtype  -> Gtype   4.384473
O      -> O       3.790788
pH     -> pH      2.512302
Gtype  -> Supp    1.227863
O      -> Supp    1.192139
O      -> Technique 0.934775
O      -> Gtype   0.662404
Substrain -> Gtype   0.296928
Med    -> O       0.185994
O      -> Anti    0.184766
Air    -> O       0.174165
Temp   -> O       0.096665
O      -> Gversion 0.076653
O      -> Temp    0.057678
OD     -> Phase   0.022845
Technique -> Air     0.001578
O      -> Strain  0.000001
O      -> Med     -0.054605
Technique -> pH      -0.057365
Supp   -> O       -0.119271
Anti   -> O       -0.138393
Supp   -> Technique -0.159198
O      -> OD      -0.170727
Supp   -> Med     -0.220567
Phase  -> OD      -0.414455
Air    -> Temp    -0.424565
OD     -> Air     -0.495373
Gtype  -> Anti    -0.639969
Agit   -> O       -0.781636
Technique -> O       -0.863862
Gtype  -> O       -0.926865
OD     -> O       -1.090238
Substrain -> O       -1.190917
Med    -> Supp    -1.321707
O      -> Air     -1.398663


Top unlikely transitions:
OD     -> OD      7.029011
Agit   -> Agit    6.826413
Temp   -> Temp    5.979472
Med    -> Med     5.720420
Anti   -> Anti    5.293877
Gversion -> Gversion 4.696471
Technique -> Technique 4.642372
Air    -> Air     4.554023
Supp   -> Supp    4.536382
Phase  -> Phase   4.521590
Gtype  -> Gtype   4.384473
O      -> O       3.790788
pH     -> pH      2.512302
Gtype  -> Supp    1.227863
O      -> Supp    1.192139
O      -> Technique 0.934775
O      -> Gtype   0.662404
Substrain -> Gtype   0.296928
Med    -> O       0.185994
O      -> Anti    0.184766
Air    -> O       0.174165
Temp   -> O       0.096665
O      -> Gversion 0.076653
O      -> Temp    0.057678
OD     -> Phase   0.022845
Technique -> Air     0.001578
O      -> Strain  0.000001
O      -> Med     -0.054605
Technique -> pH      -0.057365
Supp   -> O       -0.119271
Anti   -> O       -0.138393
Supp   -> Technique -0.159198
O      -> OD      -0.170727
Supp   -> Med     -0.220567
Phase  -> OD      -0.414455
Air    -> Temp    -0.424565
OD     -> Air     -0.495373
Gtype  -> Anti    -0.639969
Agit   -> O       -0.781636
Technique -> O       -0.863862
Gtype  -> O       -0.926865
OD     -> O       -1.090238
Substrain -> O       -1.190917
Med    -> Supp    -1.321707
O      -> Air     -1.398663


Top positive:
5.312005 O        b'word[:2]:re'
4.884582 Technique b'word[:2]:Ch'
4.406858 Air      b'lemma:anaerobic'
3.944633 O        b'postag::'
3.862898 O        b'lemma:1'
3.862898 O        b'word:1'
3.693885 O        b'word[:1]:S'
3.634278 O        b'postag:IN'
3.455038 Air      b'word[:2]:Ae'
3.455038 Air      b'word:Aerobic'
3.425015 Technique b'word[:2]:RN'
3.411467 O        b'word[:2]:Rp'
3.351922 Gtype    b'word[:1]:\xce\x94'
3.295787 Gtype    b'word[:2]:cr'
3.209157 OD       b'word[:1]:O'
3.145528 Gtype    b'word[:2]:Fl'
3.124141 O        b'lemma:_'
3.124141 O        b'word[:1]:_'
3.124141 O        b'word:_'
3.093107 Air      b'postag:RB'
3.052912 O        b'+1:postag:RB'
2.979721 O        b'word:A'
2.971788 O        b'-1:lemma:tag'
2.882253 O        b'lemma:3'
2.882253 O        b'word:3'
2.855255 O        b'word[:1]:G'
2.826283 O        b'lemma:2'
2.826283 O        b'word:2'
2.801121 Phase    b'lemma:stationary'
2.801121 Phase    b'word:stationary'
2.742452 Gtype    b'word[:1]:d'
2.729707 Air      b'word[:1]:A'
2.725212 Supp     b'-1:word:Cra'
2.626064 Supp     b'lemma:arginine'
2.509102 O        b'-1:word:Aerobic'
2.466965 O        b'word[:2]:ge'
2.441206 Supp     b'+1:word:hours'
2.439697 O        b'word[:2]:or'
2.414611 O        b'lemma:a'
2.383495 O        b'lemma:.'
2.383495 O        b'postag:.'
2.383495 O        b'word:.'
2.376885 Supp     b'word[:1]:I'
2.372488 O        b'+1:word:ChIP-Seq'
2.332104 Air      b'word[:2]:an'
2.319866 O        b'-1:word:tag'
2.286706 O        b'word[:1]:B'
2.264178 Temp     b'word[:1]:3'
2.232768 Technique b'lemma:ChIP-exo'
2.217911 Temp     b'-1:word:sample'
2.211263 O        b'postag:CC'
2.209541 O        b'word[:1]:C'
2.191226 Supp     b'word[:2]:Fe'
2.181901 Supp     b'lemma:nitrate'
2.181901 Supp     b'word[:2]:ni'
2.181901 Supp     b'word:nitrate'
2.175597 O        b'-1:lemma:lb'
2.161370 Air      b'word[:2]:An'
2.161370 Air      b'word:Anaerobic'
2.146764 Temp     b'-1:lemma:sample'
2.122014 O        b'word[:2]:Cu'
2.100150 OD       b'word[:2]:OD'
2.097281 O        b'lemma:with'
2.097281 O        b'word:with'
2.096745 O        b'-1:lemma:anaerobic'
2.095524 O        b'lemma:-'
2.095524 O        b'word:-'
2.085444 Gtype    b'lemma:wt'
2.076545 Gtype    b'word[:1]:W'
2.074067 O        b'postag:VBN'
2.042662 Gversion b'lemma:chip-seq'
2.032616 Gtype    b'lemma:arca8myc'
2.032616 Gtype    b'word:ArcA8myc'
2.019776 Gversion b'word[:2]:00'
1.980973 O        b'postag:DT'
1.968660 Gversion b'-1:lemma:nc'
1.968660 Gversion b'-1:word:NC'
1.961531 Med      b'word[:1]:M'
1.921062 O        b'word[:2]:ch'
1.893301 Gversion b'word:ChIP-Seq'
1.885602 Med      b'word[:1]:L'
1.878552 O        b'isLower'
1.865095 Gtype    b'lemma:type'
1.865095 Gtype    b'word[:2]:ty'
1.865095 Gtype    b'word:type'
1.850010 Supp     b'word[:2]:gl'
1.837123 Phase    b'lemma:mid-log'
1.837123 Phase    b'word:mid-log'
1.811977 Supp     b'lemma:Iron'
1.811977 Supp     b'word[:2]:Ir'
1.811977 Supp     b'word:Iron'
1.811977 Supp     b'+1:word:Deficient'
1.797891 Anti     b'word[:2]:an'
1.792147 O        b'+1:lemma:od600'
1.792147 O        b'+1:word:OD600'
1.788559 Med      b'lemma:MOPS'
1.788559 Med      b'word[:2]:MO'
1.788559 Med      b'word:MOPS'
1.766167 Strain   b'+1:lemma:substr'
1.766167 Strain   b'+1:word:substr'
1.752330 O        b'word[:2]:Cr'
1.752330 O        b'word:Cra'
1.749824 O        b'+1:postag:NNP'
1.679832 Gtype    b'-1:postag:VBG'
1.660773 Air      b'-1:lemma:co2'
1.660773 Air      b'-1:word:CO2'
1.660308 Supp     b'+1:lemma:\xc2\xb5m'
1.660308 Supp     b'+1:word:\xc2\xb5M'
1.651105 Air      b'+1:postag:IN'
1.650444 O        b'word[:1]:E'
1.641207 O        b'lemma:at'
1.630939 Supp     b'word[:1]:1'
1.629832 Gtype    b'lemma:flag-tag'
1.629832 Gtype    b'-1:lemma:c-terminal'
1.629832 Gtype    b'word:Flag-tag'
1.629832 Gtype    b'-1:word:C-terminal'
1.622707 Gtype    b'-1:lemma:\xe2\x88\x86'
1.622707 Gtype    b'-1:word:\xe2\x88\x86'
1.612203 Gtype    b'word[:2]:de'
1.564079 Supp     b'lemma:nh4cl'
1.564079 Supp     b'word[:2]:NH'
1.561438 OD       b'+1:lemma:stationary'
1.561438 OD       b'+1:word:stationary'
1.553871 Technique b'word[:1]:C'
1.517787 Supp     b'+1:lemma:1'
1.517787 Supp     b'+1:word:1'
1.515416 Supp     b'lemma:pq'
1.515416 Supp     b'word[:2]:PQ'
1.515416 Supp     b'word:PQ'
1.510927 O        b'word[:2]:Pu'
1.483322 Vess     b'lemma:flask'
1.483322 Vess     b'-1:lemma:warm'
1.483322 Vess     b'word[:2]:fl'
1.483322 Vess     b'word:flask'
1.483322 Vess     b'-1:word:warmed'
1.475753 Technique b'symb'
1.469180 O        b'word[:1]:T'
1.460811 Gversion b'lemma:asm584v2'
1.460811 Gversion b'word[:2]:AS'
1.460811 Gversion b'word:ASM584v2'
1.446236 Anti     b'+1:lemma:antibody'
1.446236 Anti     b'+1:word:antibody'
1.444397 Air      b'word[:1]:a'
1.443964 Gtype    b'word[:1]:w'
1.416989 Gtype    b'hGreek'
1.397052 Substrain b'lemma:mg1655'
1.397052 Substrain b'word[:2]:MG'
1.397052 Substrain b'word:MG1655'
1.394402 O        b'lemma:\xcf\x8332'
1.394402 O        b'word[:1]:\xcf\x83'
1.394402 O        b'word[:2]:\xcf\x833'
1.394402 O        b'word:\xcf\x8332'
1.377208 O        b'word[:1]:R'
1.375050 Med      b'+1:lemma:0.4'
1.375050 Med      b'+1:word:0.4'
1.364759 O        b'lemma:Custom'
1.364759 O        b'word:Custom'
1.360005 O        b'word[:2]:fo'
1.350754 Supp     b'lemma:rifampicin'
1.350754 Supp     b'word:rifampicin'
1.344579 Strain   b'word[:1]:K'
1.343710 Supp     b'word[:2]:ri'
1.340304 pH       b'lemma:ph5'
1.340304 pH       b'+1:lemma:.5'
1.340304 pH       b'word:pH5'
1.340304 pH       b'+1:word:.5'
1.337816 Gtype    b'lemma:nsrr'
1.337816 Gtype    b'word[:2]:Ns'
1.337816 Gtype    b'word:NsrR'
1.326904 Strain   b'lemma:k-12'
1.326904 Strain   b'word[:2]:K-'
1.326904 Strain   b'word:K-12'
1.314361 Supp     b'+1:lemma:2'
1.314361 Supp     b'+1:word:2'
1.308459 Med      b'word[:2]:LB'
1.308459 Med      b'word:LB'
1.298260 Gtype    b'symb'
1.294311 O        b'+1:lemma:pq'
1.294311 O        b'+1:word:PQ'
1.294271 Substrain b'word[:1]:M'
1.290578 Gtype    b'-1:postag:VBP'
1.283956 Gversion b'word[:2]:Ch'
1.268071 Gtype    b'postag:JJ'
1.261557 O        b'-1:lemma:0.3-0.35'
1.261557 O        b'-1:word:0.3-0.35'
1.259366 O        b'lemma:b'
1.259366 O        b'word:B'
1.257660 O        b'-1:lemma:glucose'
1.257660 O        b'-1:word:glucose'
1.256368 O        b'+1:lemma:nacl'
1.256368 O        b'+1:word:NaCl'
1.250169 O        b'lemma:rpob'
1.250169 O        b'word:RpoB'
1.248890 O        b'word:Lrp'
1.243321 Med      b'+1:lemma:g/l'
1.243321 Med      b'+1:word:g/L'
1.239040 pH       b'+1:postag:CD'
1.232026 O        b'lemma:delta'
1.232026 O        b'word:delta'
1.230236 O        b'word[:1]:H'


Top negative:
-0.068713 Med      b'-1:postag:CD'
-0.070898 pH       b'isLower'
-0.071980 O        b'lemma:dpd'
-0.071980 O        b'word[:2]:DP'
-0.071980 O        b'word:DPD'
-0.072232 O        b'-1:lemma:of'
-0.072232 O        b'-1:word:of'
-0.075191 O        b'-1:lemma:o2'
-0.075191 O        b'-1:word:O2'
-0.078769 Phase    b'+1:postag:NN'
-0.079557 Supp     b'-1:postag:VBG'
-0.079633 Air      b'-1:postag:VBN'
-0.083786 Air      b'postag:CC'
-0.087096 O        b'word[:2]:OD'
-0.093025 Supp     b'postag:CD'
-0.093410 O        b'word[:2]:20'
-0.097736 O        b'+1:lemma:arginine'
-0.099182 O        b'word[:1]:l'
-0.103765 Temp     b'postag:NN'
-0.104490 O        b'-1:postag:-LRB-'
-0.105330 O        b'+1:lemma:fecl2'
-0.105330 O        b'+1:word:FeCl2'
-0.105938 Air      b'-1:postag:CC'
-0.107646 O        b'-1:word:OmpR'
-0.109102 O        b'+1:lemma:\xc2\xb0c'
-0.109102 O        b'+1:word:\xc2\xb0C'
-0.112420 Air      b'postag:-RRB-'
-0.112420 Air      b'word[:2]:-R'
-0.117390 Air      b'isLower'
-0.117817 O        b'-1:lemma:IP'
-0.117817 O        b'-1:word:IP'
-0.119059 Anti     b'+1:lemma:anti-fur'
-0.119059 Anti     b'+1:word:anti-Fur'
-0.120171 O        b'word[:1]:g'
-0.122244 Technique b'isNumber'
-0.123373 O        b'lemma:of'
-0.123373 O        b'word[:2]:of'
-0.123373 O        b'word:of'
-0.125903 O        b'+1:postag:IN'
-0.127562 O        b'+1:lemma:c'
-0.128049 OD       b'postag:CD'
-0.128910 Gtype    b'postag:NNP'
-0.131123 O        b'lemma:anaerobically'
-0.131123 O        b'word:anaerobically'
-0.133893 Supp     b'word[:2]:mi'
-0.136181 O        b'-1:word:the'
-0.136609 O        b'-1:lemma:od600'
-0.136609 O        b'-1:word:OD600'
-0.137723 O        b'+1:lemma:+'
-0.137723 O        b'+1:word:+'
-0.138435 O        b'word[:1]:F'
-0.140881 O        b'word[:2]:0.'
-0.141470 Air      b'symb'
-0.141558 O        b'word[:1]:p'
-0.142135 O        b'lemma:150'
-0.142135 O        b'+1:lemma:mg/ml'
-0.142135 O        b'word[:2]:15'
-0.142135 O        b'word:150'
-0.142135 O        b'+1:word:mg/mL'
-0.143733 Phase    b'-1:word:at'
-0.143958 O        b'-1:lemma:iptg'
-0.143958 O        b'-1:word:IPTG'
-0.145720 Phase    b'-1:lemma:at'
-0.148058 OD       b'+1:lemma:~'
-0.148058 OD       b'+1:word:~'
-0.154564 Anti     b'symb'
-0.168424 O        b'+1:lemma:-rrb-'
-0.168424 O        b'+1:word:-RRB-'
-0.171070 OD       b'+1:postag:CD'
-0.178172 Air      b'-1:lemma:or'
-0.178172 Air      b'-1:word:or'
-0.183332 O        b'-1:postag:VBN'
-0.185846 O        b'lemma:20'
-0.185846 O        b'word:20'
-0.187116 O        b'-1:postag:IN'
-0.187838 Gtype    b'-1:lemma:,'
-0.187838 Gtype    b'-1:postag:,'
-0.187838 Gtype    b'-1:word:,'
-0.197654 OD       b'lemma:~'
-0.197654 OD       b'word[:1]:~'
-0.197654 OD       b'word:~'
-0.209004 O        b'lemma:phase'
-0.209004 O        b'word:phase'
-0.232938 O        b'word[:2]:mg'
-0.241910 O        b'lemma:37'
-0.241910 O        b'word[:2]:37'
-0.241910 O        b'word:37'
-0.256827 O        b'+1:lemma:.'
-0.256827 O        b'+1:postag:.'
-0.256827 O        b'+1:word:.'
-0.258887 O        b'+1:postag:-RRB-'
-0.260688 O        b'word[:1]:K'
-0.271025 Temp     b'hGreek'
-0.272963 O        b'+1:lemma:cell'
-0.279619 O        b'-1:lemma:rpob'
-0.279619 O        b'-1:word:RpoB'
-0.282042 O        b'lemma:2h'
-0.282042 O        b'-1:lemma:additional'
-0.282042 O        b'word[:2]:2h'
-0.282042 O        b'word:2h'
-0.282042 O        b'-1:word:additional'
-0.307901 O        b'word[:1]:m'
-0.310789 O        b'+1:word:cells'
-0.312898 Technique b'isLower'
-0.323122 Supp     b'+1:postag:VBN'
-0.336111 Gtype    b'lemma:delta'
-0.336111 Gtype    b'word:delta'
-0.338083 O        b'-1:lemma:37'
-0.338083 O        b'-1:word:37'
-0.363134 O        b'word[:1]:N'
-0.365622 Supp     b'isUpper'
-0.371038 Temp     b'+1:lemma:to'
-0.371038 Temp     b'+1:postag:TO'
-0.371038 Temp     b'+1:word:to'
-0.375663 O        b'lemma:methanol'
-0.375663 O        b'word:methanol'
-0.386821 O        b'+1:word:C'
-0.390549 O        b'word[:2]:Fe'
-0.398822 O        b'+1:postag:NNS'
-0.400605 O        b'+1:lemma:hour'
-0.402617 OD       b'postag:IN'
-0.405062 Med      b'+1:postag:NN'
-0.406038 O        b'-1:lemma:nsrr'
-0.406038 O        b'-1:word:NsrR'
-0.414701 O        b'-1:lemma:ompr'
-0.416003 Gtype    b'isNumber'
-0.429137 O        b'word[:2]:gl'
-0.433599 O        b'-1:lemma:grow'
-0.446189 Supp     b'word[:2]:an'
-0.449818 Temp     b'isLower'
-0.453449 Supp     b'-1:lemma:%'
-0.453449 Supp     b'-1:word:%'
-0.479179 Med      b'-1:postag:IN'
-0.488851 O        b'word[:2]:ri'
-0.490659 O        b'word[:2]:me'
-0.500177 Med      b'-1:postag:NN'
-0.509290 O        b'word[:2]:ce'
-0.522634 O        b'postag:VBP'
-0.532399 Med      b'+1:postag:IN'
-0.539071 O        b'+1:lemma:supplement'
-0.539071 O        b'+1:word:supplemented'
-0.539739 O        b'lemma:rifampicin'
-0.539739 O        b'word:rifampicin'
-0.552871 O        b'+1:lemma:g/l'
-0.552871 O        b'+1:word:g/L'
-0.560634 Agit     b'hUpper'
-0.560634 Agit     b'hLower'
-0.562608 O        b'-1:lemma:dissolve'
-0.562608 O        b'+1:lemma:methanol'
-0.562608 O        b'-1:word:dissolved'
-0.562608 O        b'+1:word:methanol'
-0.619514 Air      b'-1:postag:JJ'
-0.625491 Phase    b'postag:JJ'
-0.625812 O        b'word[:1]:d'
-0.649550 Supp     b'word[:1]:C'
-0.703665 Phase    b'hUpper'
-0.703665 Phase    b'hLower'
-0.716840 O        b'+1:lemma:at'
-0.716840 O        b'+1:word:at'
-0.763556 Phase    b'-1:postag:JJ'
-0.787727 O        b'lemma:mid-log'
-0.787727 O        b'word:mid-log'
-0.797424 Anti     b'postag:NNP'
-0.811067 O        b'lemma:wt'
-0.815501 O        b'-1:postag:VBG'
-0.817040 O        b'word[:1]:0'
-0.819358 O        b'postag:RB'
-0.827170 O        b'-1:lemma:co2'
-0.827170 O        b'-1:word:CO2'
-0.854780 OD       b'isNumber'
-0.880817 O        b'+1:postag:VBG'
-0.904661 OD       b'+1:postag:NN'
-0.945300 O        b'+1:lemma:in'
-0.945300 O        b'+1:word:in'
-0.951737 O        b'+1:lemma:2'
-0.951737 O        b'+1:word:2'
-0.992231 Air      b'postag:NN'
-1.005360 O        b'word:cells'
-1.012629 O        b'word[:1]:\xce\x94'
-1.013888 Med      b'symb'
-1.045981 O        b'+1:lemma:1'
-1.045981 O        b'+1:word:1'
-1.053560 O        b'-1:lemma:2'
-1.053560 O        b'-1:word:2'
-1.102339 Gtype    b'word[:1]:C'
-1.167989 Gversion b'isLower'
-1.221456 Gtype    b'isUpper'
-1.317978 O        b'-1:postag::'
-1.332231 Supp     b'symb'
-1.384191 Supp     b'postag:JJ'
-1.468390 O        b'word[:1]:P'
-1.498430 O        b'word[:2]:Ch'
-1.650068 Technique b'postag:NN'
-1.692161 O        b'+1:word:hours'
-2.120503 O        b'-1:lemma::'
-2.120503 O        b'-1:word::'
-2.146800 Supp     b'hGreek'
-2.229078 O        b'-1:lemma:_'
-2.229078 O        b'-1:word:_'
-3.855247 OD       b'word[:1]:-'