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

best params:{'c1': 0.05028906165720029, 'c2': 0.013800616937860201}
best CV score:0.88742941188346
model size: 0.15M

Flat F1: 0.7898290630427373
             precision    recall  f1-score   support

         OD      0.720     0.818     0.766        22
         pH      1.000     1.000     1.000         8
  Technique      0.955     0.913     0.933        23
        Med      1.000     0.962     0.981        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      1.000     1.000     1.000         1
      Gtype      0.897     0.824     0.859        85
  Substrain      0.000     0.000     0.000         0
       Supp      0.732     0.813     0.770       134
   Gversion      0.000     0.000     0.000         0

avg / total      0.813     0.778     0.790       451


Top likely transitions:
Agit   -> Agit    6.109590
Temp   -> Temp    5.811903
Anti   -> Anti    5.262249
Med    -> Med     5.103938
Supp   -> Supp    4.904278
OD     -> OD      4.790162
Gversion -> Gversion 4.698942
Gtype  -> Gtype   4.209922
Phase  -> Phase   4.104196
O      -> O       3.995376
Air    -> Air     3.716034
Technique -> Technique 3.620673
pH     -> pH      3.119671
O      -> Technique 0.701338
Substrain -> Gtype   0.676777
O      -> Gtype   0.289823
Technique -> Air     0.121096
Gtype  -> Supp    0.100772
Air    -> O       0.080919
O      -> Anti    0.071010
O      -> Supp    0.059391
Temp   -> O       0.059203
Gtype  -> Substrain -0.000305
O      -> Substrain -0.001303
O      -> Strain  -0.001660
O      -> Temp    -0.004966
Phase  -> Air     -0.022029
Technique -> Supp    -0.049531
Air    -> Agit    -0.068359
Phase  -> Technique -0.070606
Anti   -> Gtype   -0.083548
OD     -> Supp    -0.090468
Anti   -> Supp    -0.120287
Phase  -> Gtype   -0.143036
Agit   -> Air     -0.174747
Technique -> OD      -0.200986
Anti   -> Temp    -0.205319
Phase  -> OD      -0.217351
Supp   -> Technique -0.233971
Supp   -> Gtype   -0.263727
O      -> Phase   -0.272927
Supp   -> Anti    -0.274653
Anti   -> O       -0.304091
Technique -> Gtype   -0.363832
Gtype  -> Technique -0.369874
Supp   -> Air     -0.382660
Supp   -> O       -0.386124
Temp   -> Med     -0.389357
OD     -> O       -0.415227
Gversion -> O       -0.421904


Top unlikely transitions:
O      -> Supp    0.059391
Temp   -> O       0.059203
Gtype  -> Substrain -0.000305
O      -> Substrain -0.001303
O      -> Strain  -0.001660
O      -> Temp    -0.004966
Phase  -> Air     -0.022029
Technique -> Supp    -0.049531
Air    -> Agit    -0.068359
Phase  -> Technique -0.070606
Anti   -> Gtype   -0.083548
OD     -> Supp    -0.090468
Anti   -> Supp    -0.120287
Phase  -> Gtype   -0.143036
Agit   -> Air     -0.174747
Technique -> OD      -0.200986
Anti   -> Temp    -0.205319
Phase  -> OD      -0.217351
Supp   -> Technique -0.233971
Supp   -> Gtype   -0.263727
O      -> Phase   -0.272927
Supp   -> Anti    -0.274653
Anti   -> O       -0.304091
Technique -> Gtype   -0.363832
Gtype  -> Technique -0.369874
Supp   -> Air     -0.382660
Supp   -> O       -0.386124
Temp   -> Med     -0.389357
OD     -> O       -0.415227
Gversion -> O       -0.421904
OD     -> Air     -0.437118
Med    -> O       -0.457761
Phase  -> Med     -0.566106
Technique -> pH      -0.588485
Air    -> Supp    -0.749133
Gtype  -> Med     -0.749905
Air    -> Phase   -0.761522
O      -> OD      -0.761983
Air    -> Med     -0.800817
Gtype  -> Anti    -0.885857
O      -> Med     -0.928117
Phase  -> O       -0.934773
Technique -> O       -0.944445
Air    -> Temp    -0.967834
Phase  -> Supp    -1.004648
Gtype  -> O       -1.364531
O      -> Air     -1.614738
Substrain -> O       -1.728040
Supp   -> Med     -1.841267
Med    -> Supp    -2.122160


Top positive:
4.639572 Gtype    b'word[:1]:\xce\x94'
4.300520 O        b'word[:2]:re'
4.022984 Air      b'postag:RB'
3.627801 Air      b'lemma:anaerobic'
3.468741 O        b'-1:lemma:tag'
3.363521 Supp     b'-1:word:Cra'
3.318146 O        b'lemma:_'
3.318146 O        b'word[:1]:_'
3.318146 O        b'word:_'
3.308857 Air      b'word[:2]:Ae'
3.308857 Air      b'word:Aerobic'
3.289642 Technique b'word[:2]:Ch'
3.223570 Air      b'word[:2]:An'
3.197124 O        b'postag::'
3.084091 O        b'-1:word:tag'
2.996318 O        b'word:A'
2.988262 O        b'lemma:-'
2.988262 O        b'word:-'
2.840867 Gtype    b'word[:1]:d'
2.829005 O        b'postag:IN'
2.786835 O        b'lemma:with'
2.786835 O        b'word:with'
2.782828 Supp     b'word[:2]:ni'
2.740660 Phase    b'lemma:stationary'
2.740660 Phase    b'word:stationary'
2.739492 Gtype    b'word[:2]:Fl'
2.729139 Gtype    b'lemma:wt'
2.700600 O        b'lemma:2'
2.700600 O        b'word:2'
2.647887 O        b'lemma:.'
2.647887 O        b'postag:.'
2.647887 O        b'word:.'
2.619024 Supp     b'+1:lemma:\xc2\xb5m'
2.619024 Supp     b'+1:word:\xc2\xb5M'
2.615368 O        b'word[:1]:S'
2.613499 Anti     b'word[:2]:an'
2.594946 O        b'+1:postag:RB'
2.569496 Gtype    b'word[:1]:W'
2.549272 Strain   b'+1:lemma:substr'
2.549272 Strain   b'+1:word:substr'
2.513933 O        b'word[:2]:Cu'
2.467059 Air      b'word[:1]:A'
2.464095 O        b'lemma:3'
2.464095 O        b'word:3'
2.462122 Phase    b'word[:1]:e'
2.460202 Phase    b'lemma:mid-log'
2.460202 Phase    b'word:mid-log'
2.433822 Supp     b'-1:lemma:vol'
2.433822 Supp     b'-1:word:vol'
2.404119 O        b'postag:VBN'
2.403872 O        b'lemma:1'
2.403872 O        b'word:1'
2.395598 Supp     b'word[:1]:I'
2.389732 O        b'word[:2]:Rp'
2.385820 Technique b'word[:2]:RN'
2.354852 Supp     b'postag:VBP'
2.345794 O        b'word[:1]:G'
2.326682 Supp     b'lemma:Iron'
2.326682 Supp     b'word[:2]:Ir'
2.326682 Supp     b'word:Iron'
2.326682 Supp     b'+1:word:Deficient'
2.299398 O        b'-1:word:Aerobic'
2.288147 O        b'lemma:Custom'
2.288147 O        b'word:Custom'
2.281710 Technique b'lemma:ChIP-exo'
2.276249 Supp     b'-1:lemma:with'
2.276249 Supp     b'-1:word:with'
2.249269 O        b'-1:lemma:lb'
2.249269 O        b'-1:word:LB'
2.249119 O        b'lemma:a'
2.237257 O        b'word[:2]:Cr'
2.232635 Supp     b'lemma:arginine'
2.214367 Gtype    b'word[:2]:PK'
2.207423 O        b'isNumber'
2.202429 Gtype    b'lemma:arca8myc'
2.202429 Gtype    b'word:ArcA8myc'
2.192107 Gtype    b'word[:1]:w'
2.183043 O        b'lemma:at'
2.175197 Supp     b'word[:2]:Fe'
2.159024 O        b'postag:CC'
2.155380 O        b'-1:lemma:glucose'
2.155380 O        b'-1:word:glucose'
2.119159 Supp     b'lemma:pq'
2.119159 Supp     b'word[:2]:PQ'
2.119159 Supp     b'word:PQ'
2.088381 Technique b'lemma:rna-seq'
2.079903 O        b'+1:lemma:or'
2.079903 O        b'+1:word:or'
2.068009 Supp     b'word[:1]:1'
2.067542 O        b'postag:VBG'
2.066432 O        b'word[:2]:ge'
2.058739 Technique b'word[:1]:C'
2.044761 Supp     b'-1:lemma:Cra'
2.043046 O        b'word:Cra'
2.038603 Temp     b'+1:lemma:in'
2.038603 Temp     b'+1:word:in'
2.015876 O        b'word[:2]:ch'
2.009137 O        b'+1:word:ChIP-Seq'
1.989519 O        b'-1:lemma:0.3'
1.989519 O        b'-1:word:0.3'
1.978424 O        b'+1:postag:NNP'
1.973212 Phase    b'word[:2]:ex'
1.972232 Supp     b'-1:postag:CC'
1.959095 Air      b'word:anaerobic'
1.957164 Gtype    b'word[:1]:t'
1.948276 Gtype    b'word[:2]:cr'
1.939810 Med      b'lemma:MOPS'
1.939810 Med      b'word[:2]:MO'
1.939810 Med      b'word:MOPS'
1.939729 Air      b'+1:postag:IN'
1.934822 Supp     b'lemma:nacl'
1.934822 Supp     b'word:NaCl'
1.926545 O        b'lemma:ompr'
1.926545 O        b'word[:2]:Om'
1.926545 O        b'word:OmpR'
1.924885 pH       b'word[:2]:pH'
1.920642 Med      b'+1:lemma:0.4'
1.920642 Med      b'+1:word:0.4'
1.911633 Technique b'word[:1]:R'
1.891089 O        b'isLower'
1.886521 Supp     b'-1:lemma:+'
1.886521 Supp     b'-1:word:+'
1.870705 Substrain b'word[:2]:MG'
1.852940 O        b'lemma:delta'
1.852940 O        b'word:delta'
1.848066 O        b'word[:1]:E'
1.846119 O        b'word[:1]:R'
1.831986 Gversion b'lemma:chip-seq'
1.821131 Gtype    b'hGreek'
1.820825 Med      b'word[:1]:M'
1.809718 O        b'+1:lemma:pq'
1.809718 O        b'+1:word:PQ'
1.793169 O        b'word[:1]:B'
1.790300 Gtype    b'-1:lemma:\xe2\x88\x86'
1.790300 Gtype    b'-1:word:\xe2\x88\x86'
1.784099 O        b'lemma:purr'
1.784099 O        b'word:PurR'
1.777360 Supp     b'lemma:acetate'
1.777360 Supp     b'word:acetate'
1.774907 Gtype    b'word[:1]:F'
1.753560 Gversion b'word[:2]:00'
1.753502 O        b'postag:DT'
1.733991 Gversion b'lemma:nc'
1.733991 Gversion b'word[:2]:NC'
1.733991 Gversion b'word:NC'
1.727458 Technique b'-1:lemma:chip-exo'
1.727043 Gversion b'lemma:asm584v2'
1.727043 Gversion b'word[:2]:AS'
1.727043 Gversion b'word:ASM584v2'
1.725711 O        b'-1:lemma:0.3-0.35'
1.725711 O        b'-1:word:0.3-0.35'
1.718272 Med      b'-1:lemma:ml'
1.718272 Med      b'-1:word:ml'
1.708599 Air      b'word[:1]:a'
1.705288 Gtype    b'word[:2]:WT'
1.705288 Gtype    b'word:WT'
1.702939 Gtype    b'lemma:type'
1.702939 Gtype    b'word[:2]:ty'
1.702939 Gtype    b'word:type'
1.700727 Gversion b'word:ChIP-Seq'
1.678369 Med      b'word[:1]:L'
1.677602 Substrain b'word[:1]:M'
1.675405 Air      b'word:Anaerobic'
1.673928 O        b'-1:lemma:phase'
1.673928 O        b'-1:word:phase'
1.670556 Gtype    b'symb'
1.664412 Gtype    b'word[:2]:Ar'
1.656247 Air      b'lemma:anaerobically'
1.656247 Air      b'word:anaerobically'
1.629999 O        b'-1:lemma:into'
1.629999 O        b'-1:word:into'
1.625974 Agit     b'+1:lemma:rpm'
1.625974 Agit     b'+1:word:rpm'
1.623101 Air      b'-1:postag::'
1.617445 O        b'word[:1]:C'
1.614655 O        b'+1:lemma:od600'
1.614655 O        b'+1:word:OD600'
1.613598 Supp     b'lemma:rifampicin'
1.613598 Supp     b'word:rifampicin'
1.609900 Supp     b'word[:2]:ri'
1.592698 O        b'lemma:b'
1.592698 O        b'word:B'
1.589084 Gtype    b'lemma:flag-tag'
1.589084 Gtype    b'-1:lemma:c-terminal'
1.589084 Gtype    b'word:Flag-tag'
1.589084 Gtype    b'-1:word:C-terminal'
1.588544 Gtype    b'word[:1]:f'
1.561372 Med      b'+1:lemma:2.0'
1.561372 Med      b'+1:word:2.0'
1.560963 Supp     b'word[:2]:gl'
1.560208 O        b'-1:postag:NNS'
1.547132 O        b'-1:lemma:type'
1.547132 O        b'-1:word:type'
1.539083 O        b'+1:lemma:mid-log'
1.539083 O        b'+1:word:mid-log'
1.531367 Strain   b'lemma:k-12'
1.531367 Strain   b'word[:2]:K-'
1.531367 Strain   b'word:K-12'
1.524189 Med      b'word[:2]:me'
1.516646 Temp     b'-1:word:sample'


Top negative:
-0.288032 O        b'-1:lemma:delta'
-0.288032 O        b'-1:word:delta'
-0.292633 O        b'-1:lemma:mm'
-0.292633 O        b'-1:word:mM'
-0.294985 O        b'-1:lemma:250'
-0.294985 O        b'-1:word:250'
-0.296179 Temp     b'symb'
-0.301980 O        b'-1:lemma:control'
-0.301980 O        b'-1:word:control'
-0.308283 O        b'lemma:sodium'
-0.308283 O        b'word:Sodium'
-0.314104 O        b'word[:2]:OD'
-0.314668 O        b'lemma:20'
-0.314668 O        b'word:20'
-0.316973 O        b'-1:lemma:cra'
-0.318579 OD       b'hUpper'
-0.318579 OD       b'hLower'
-0.320649 Strain   b'isLower'
-0.322585 O        b'+1:lemma:phosphate'
-0.322585 O        b'+1:word:phosphate'
-0.324375 Technique b'-1:postag::'
-0.329447 Vess     b'hUpper'
-0.329447 Vess     b'hLower'
-0.331787 O        b'lemma:37'
-0.331787 O        b'word[:2]:37'
-0.331787 O        b'word:37'
-0.334237 O        b'+1:lemma:antibody'
-0.334237 O        b'+1:word:antibody'
-0.334457 O        b'+1:postag:-RRB-'
-0.344240 O        b'+1:lemma:-rrb-'
-0.344240 O        b'+1:word:-RRB-'
-0.345027 O        b'lemma:30'
-0.345027 O        b'word:30'
-0.346004 O        b'lemma:glucose'
-0.346004 O        b'word:glucose'
-0.346763 O        b'+1:word:for'
-0.348278 O        b'+1:lemma:supplement'
-0.348278 O        b'+1:word:supplemented'
-0.354399 O        b'word[:2]:Fe'
-0.354537 Gtype    b'-1:lemma:mg1655'
-0.354537 Gtype    b'-1:word:MG1655'
-0.357807 O        b'word[:1]:p'
-0.358553 O        b'lemma:fructose'
-0.358553 O        b'word:fructose'
-0.365765 O        b'word[:2]:cr'
-0.366538 O        b'-1:lemma:nsrr'
-0.366538 O        b'-1:word:NsrR'
-0.380953 Gtype    b'lemma:delta'
-0.380953 Gtype    b'word:delta'
-0.384577 O        b'lemma:wt'
-0.388919 O        b'lemma:0.3'
-0.388919 O        b'word:0.3'
-0.393930 O        b'word[:2]:gl'
-0.394132 O        b'-1:lemma:37'
-0.394132 O        b'-1:word:37'
-0.397348 O        b'word[:2]:ae'
-0.400421 Anti     b'symb'
-0.403822 Temp     b'postag:NN'
-0.416428 O        b'+1:lemma:_'
-0.416428 O        b'+1:word:_'
-0.418494 Gtype    b'+1:postag:CD'
-0.429910 O        b'lemma:anaerobically'
-0.429910 O        b'word:anaerobically'
-0.430496 O        b'-1:lemma:\xe2\x88\x86'
-0.430496 O        b'-1:word:\xe2\x88\x86'
-0.435685 Anti     b'isUpper'
-0.439926 O        b'word[:1]:0'
-0.455543 Supp     b'-1:postag:NNP'
-0.459841 O        b'+1:word:ChIP-exo'
-0.467718 O        b'+1:lemma:until'
-0.467718 O        b'+1:word:until'
-0.471394 Technique b'isLower'
-0.477058 O        b'+1:lemma:mm'
-0.477058 O        b'+1:word:mM'
-0.479461 O        b'lemma:methanol'
-0.479461 O        b'word:methanol'
-0.479626 O        b'+1:lemma:2.0'
-0.479626 O        b'+1:word:2.0'
-0.483129 Gtype    b'+1:lemma:-rrb-'
-0.483129 Gtype    b'+1:word:-RRB-'
-0.493814 O        b'-1:lemma:final'
-0.493814 O        b'-1:word:final'
-0.494462 O        b'+1:lemma:1m'
-0.494462 O        b'+1:word:1M'
-0.498667 O        b'word[:2]:ce'
-0.519190 Air      b'-1:postag:JJ'
-0.523733 O        b'-1:lemma:dissolve'
-0.523733 O        b'+1:lemma:methanol'
-0.523733 O        b'-1:word:dissolved'
-0.523733 O        b'+1:word:methanol'
-0.526708 O        b'word:cells'
-0.526835 O        b'lemma:aerobically'
-0.526835 O        b'word:aerobically'
-0.527859 O        b'lemma:mid-log'
-0.527859 O        b'word:mid-log'
-0.533576 O        b'-1:lemma:ml'
-0.533576 O        b'-1:word:ml'
-0.561344 Supp     b'word[:2]:an'
-0.570853 O        b'+1:lemma:+'
-0.570853 O        b'+1:word:+'
-0.571720 O        b'word[:2]:mg'
-0.573354 O        b'-1:lemma:co2'
-0.573354 O        b'-1:word:CO2'
-0.605365 O        b'+1:lemma:at'
-0.605365 O        b'+1:word:at'
-0.606419 O        b'-1:lemma:1'
-0.606419 O        b'-1:word:1'
-0.606723 O        b'-1:lemma:IP'
-0.606723 O        b'-1:word:IP'
-0.612276 Gtype    b'postag::'
-0.613913 O        b'lemma:2h'
-0.613913 O        b'-1:lemma:additional'
-0.613913 O        b'word[:2]:2h'
-0.613913 O        b'word:2h'
-0.613913 O        b'-1:word:additional'
-0.615802 O        b'-1:lemma:30'
-0.615802 O        b'-1:word:30'
-0.619836 O        b'+1:lemma:rep2'
-0.619836 O        b'+1:word:rep2'
-0.621214 O        b'+1:lemma:for'
-0.640517 O        b'word[:1]:K'
-0.670387 O        b'word[:1]:4'
-0.678961 Med      b'+1:postag:IN'
-0.690560 Supp     b'-1:lemma:-lrb-'
-0.690560 Supp     b'-1:word:-LRB-'
-0.718679 Air      b'-1:lemma:or'
-0.718679 Air      b'-1:word:or'
-0.725669 Technique b'isNumber'
-0.728283 O        b'-1:lemma:rpob'
-0.728283 O        b'-1:word:RpoB'
-0.748299 Gtype    b'isNumber'
-0.754138 Supp     b'-1:postag:-LRB-'
-0.776918 O        b'+1:postag:IN'
-0.784907 O        b'+1:lemma:g/l'
-0.784907 O        b'+1:word:g/L'
-0.790364 Agit     b'symb'
-0.802282 pH       b'isLower'
-0.823837 Air      b'symb'
-0.845641 Supp     b'+1:postag:VBN'
-0.868864 O        b'word[:1]:N'
-0.880681 O        b'word[:1]:M'
-0.885424 O        b'-1:lemma:until'
-0.885424 O        b'-1:word:until'
-0.887496 Med      b'symb'
-0.888872 O        b'+1:postag:VBG'
-0.890184 O        b'word[:2]:ri'
-0.907641 Air      b'postag:NN'
-0.915110 Phase    b'hUpper'
-0.915110 Phase    b'hLower'
-0.929811 O        b'lemma:rifampicin'
-0.929811 O        b'word:rifampicin'
-0.929936 Anti     b'postag:NNP'
-0.930510 O        b'+1:lemma:1'
-0.930510 O        b'+1:word:1'
-0.961858 O        b'word[:2]:ni'
-1.003184 O        b'-1:lemma:sample'
-1.005029 O        b'postag:RB'
-1.007966 O        b'+1:lemma:in'
-1.007966 O        b'+1:word:in'
-1.010292 Supp     b'postag:JJ'
-1.060178 Technique b'postag:NN'
-1.065943 O        b'word[:2]:me'
-1.096716 O        b'word[:2]:30'
-1.098543 O        b'-1:lemma:2'
-1.098543 O        b'-1:word:2'
-1.120503 Agit     b'hUpper'
-1.120503 Agit     b'hLower'
-1.151730 Gtype    b'isUpper'
-1.162851 O        b'word[:2]:fl'
-1.291732 Med      b'-1:postag:IN'
-1.298568 Supp     b'hGreek'
-1.326735 Supp     b'+1:lemma:-lrb-'
-1.326735 Supp     b'+1:word:-LRB-'
-1.328519 O        b'+1:lemma:2'
-1.328519 O        b'+1:word:2'
-1.354230 Supp     b'+1:postag:-LRB-'
-1.356038 O        b'-1:lemma:fresh'
-1.356038 O        b'-1:word:fresh'
-1.359201 Gversion b'isLower'
-1.362233 Supp     b'word[:1]:C'
-1.378443 O        b'-1:postag::'
-1.474890 OD       b'+1:postag:NN'
-1.530172 O        b'postag:VBP'
-1.570112 Supp     b'symb'
-1.647234 Gtype    b'word[:1]:C'
-1.681334 Supp     b'+1:lemma:,'
-1.681334 Supp     b'+1:postag:,'
-1.681334 Supp     b'+1:word:,'
-1.795778 Phase    b'-1:postag:JJ'
-1.890265 O        b'word[:2]:Ch'
-1.929419 O        b'-1:lemma:vol'
-1.929419 O        b'-1:word:vol'
-2.060566 O        b'-1:lemma:_'
-2.060566 O        b'-1:word:_'
-2.190996 O        b'-1:postag:VBG'
-2.302290 O        b'word[:1]:P'
-2.881552 Phase    b'postag:JJ'
-2.952863 O        b'-1:lemma::'
-2.952863 O        b'-1:word::'
-3.410195 Temp     b'+1:postag:IN'