
import pandas as pd
import numpy as np
from scipy import stats
import scikit_posthocs as sp


rocs_tc=pd.read_csv('/public/gkxiao/work/dude_comparison/rocs_TanimotoCombo.csv')
rocs_tvc=pd.read_csv('/public/gkxiao/work/dude_comparison/rocs_RefTverskyCombo.csv')
glide=pd.read_csv('/public/gkxiao/work/dude_comparison/glide_score.csv')
gold=pd.read_csv('/public/gkxiao/work/dude_comparison/gold_score.csv')
dock=pd.read_csv('/public/gkxiao/work/dude_comparison/Mysinger2012.csv')


rocs_tc.head()


rocs_tvc.head()


glide.head()


gold.head()


dock.head()


rocs_tc.mean()

auc                 0.690637
logauc              0.401877
adjusted_logauc     0.257257
bedroc_3219         0.520945
bedroc_805          0.365542
bedroc_20           0.375949
ef_05              32.346422
ef_1               23.130959
ef_5                7.226497
ef_10               4.281168
dtype: float64


rocs_tvc.mean()

auc                 0.755343
logauc              0.453545
adjusted_logauc     0.308925
bedroc_3219         0.543264
bedroc_805          0.405486
bedroc_20           0.432354
ef_05              33.882995
ef_1               25.341441
ef_5                8.416269
ef_10               5.000467
dtype: float64


glide.mean()

auc                 0.798228
logauc              0.461166
adjusted_logauc     0.316546
bedroc_3219         0.481001
bedroc_805          0.384545
bedroc_20           0.440276
ef_05              28.791657
ef_1               22.934048
ef_5                8.652891
ef_10               5.341581
dtype: float64


gold.mean()

auc                 0.717076
logauc              0.339548
adjusted_logauc     0.194928
bedroc_3219         0.291070
bedroc_805          0.232957
bedroc_20           0.294533
ef_05              17.183565
ef_1               13.414270
ef_5                5.722850
ef_10               3.824434
dtype: float64


dock.mean()

AUC       76.483137
logAUC    24.430686
EF_1      19.838235
auc        0.764831
logauc     0.244307
dtype: float64


rocs_tc.median()

auc                 0.720996
logauc              0.372585
adjusted_logauc     0.227965
bedroc_3219         0.519991
bedroc_805          0.325774
bedroc_20           0.343566
ef_05              29.296569
ef_1               18.359102
ef_5                6.335236
ef_10               4.125275
dtype: float64


rocs_tvc.median()

auc                 0.758210
logauc              0.433758
adjusted_logauc     0.289138
bedroc_3219         0.565297
bedroc_805          0.368938
bedroc_20           0.420751
ef_05              34.895504
ef_1               22.963946
ef_5                8.109239
ef_10               5.094502
dtype: float64


glide.median()

auc                 0.820697
logauc              0.451755
adjusted_logauc     0.307135
bedroc_3219         0.517200
bedroc_805          0.377760
bedroc_20           0.429872
ef_05              30.449211
ef_1               22.477159
ef_5                8.521955
ef_10               5.258265
dtype: float64


gold.median()

auc                 0.732792
logauc              0.329154
adjusted_logauc     0.184534
bedroc_3219         0.237596
bedroc_805          0.197072
bedroc_20           0.280156
ef_05              13.579315
ef_1               10.407030
ef_5                5.422138
ef_10               3.818062
dtype: float64


dock.median()

AUC       78.37500
logAUC    22.98500
EF_1      17.45000
auc        0.78375
logauc     0.22985
dtype: float64


logauc_rocs_tc=rocs_tc['adjusted_logauc'].tolist()
logauc_rocs_tvc=rocs_tvc['adjusted_logauc'].tolist()
logauc_glide=glide['adjusted_logauc'].tolist()
logauc_gold=gold['adjusted_logauc'].tolist()
logauc_dock=dock['logauc'].tolist()


data_logauc = np.array([logauc_rocs_tc,logauc_rocs_tvc,logauc_glide,logauc_gold,logauc_dock])


stats.friedmanchisquare(logauc_rocs_tc,logauc_rocs_tvc,logauc_glide,logauc_gold,logauc_dock)

FriedmanchisquareResult(statistic=87.47450980392159, pvalue=4.527108201001697e-18)


#perform Nemenyi post-hoc Test
sp.posthoc_nemenyi_friedman(data_logauc.T)

	id	auc	logauc	adjusted_logauc	bedroc_3219	bedroc_805	bedroc_20	ef_05	ef_1	ef_5	ef_10
0	aa2ar	0.686073	0.361098	0.216478	0.571057	0.324910	0.320903	36.077023	20.733921	5.809129	3.755187
1	abl1	0.600522	0.309849	0.165229	0.494143	0.293588	0.292362	26.200999	18.013187	5.817787	3.241165
2	ace	0.760096	0.409436	0.264816	0.492874	0.324567	0.393120	26.152647	18.377536	7.580692	5.174890
3	aces	0.459566	0.136778	-0.007842	0.094878	0.042937	0.059188	3.956608	1.985713	1.103174	0.728368
4	ada	0.935433	0.754320	0.609700	0.962906	0.790928	0.760584	59.591398	55.334869	14.576313	7.838148

	id	auc	logauc	adjusted_logauc	bedroc_3219	bedroc_805	bedroc_20	ef_05	ef_1	ef_5	ef_10
0	aa2ar	0.771078	0.487842	0.343222	0.731100	0.485173	0.477556	51.420124	32.137578	9.460581	5.165975
1	abl1	0.695311	0.348398	0.203778	0.551487	0.293764	0.309255	33.842957	18.013187	5.708018	4.065190
2	ace	0.761047	0.423822	0.279202	0.479790	0.339068	0.419762	26.152647	19.437778	8.076626	5.635668
3	aces	0.625177	0.263480	0.118860	0.151101	0.146089	0.229089	7.913215	7.060314	4.765712	3.222475
4	ada	0.928716	0.757569	0.612949	0.966054	0.798656	0.755293	59.591398	55.334869	14.147598	7.730776

	id	auc	logauc	adjusted_logauc	bedroc_3219	bedroc_805	bedroc_20	ef_05	ef_1	ef_5	ef_10
0	aa2ar	0.880935	0.492185	0.347565	0.363559	0.371942	0.503108	23.221992	22.185296	10.373444	6.618257
1	abl1	0.810886	0.411228	0.266608	0.526228	0.330054	0.360812	31.659540	19.650749	6.366635	4.559605
2	ace	0.896240	0.605319	0.460699	0.789608	0.583127	0.618545	50.184810	36.401658	12.327481	7.088890
3	aces	0.650288	0.285071	0.140451	0.173581	0.193277	0.258135	10.550954	11.252375	5.251108	3.288690
4	ada	0.707181	0.297711	0.153091	0.097487	0.130502	0.246279	4.256528	6.384793	4.715866	3.650644

	id	auc	logauc	adjusted_logauc	bedroc_3219	bedroc_805	bedroc_20	ef_05	ef_1	ef_5	ef_10
0	aa2ar	0.702684	0.276809	0.132189	0.111483	0.117611	0.211602	6.220176	6.427516	4.522822	3.153527
1	abl1	0.756282	0.323613	0.178993	0.301622	0.185755	0.252636	14.192208	10.371229	4.610322	3.790515
2	ace	0.724553	0.419914	0.275294	0.588642	0.400193	0.415882	33.927759	23.678748	8.005778	4.714112
3	aces	0.702930	0.413426	0.268806	0.687749	0.430125	0.391598	43.962308	27.799985	7.325075	4.259847
4	ada	0.712189	0.330099	0.185479	0.421469	0.282841	0.263216	27.667435	19.154378	4.715866	2.899041

	target	AUC	logAUC	EF_1	auc	logauc
0	aa2ar	83.39	28.37	21.8	0.8339	0.2837
1	abl1	81.03	26.11	19.2	0.8103	0.2611
2	ace	71.59	22.31	19.5	0.7159	0.2231
3	aces	80.67	24.73	20.1	0.8067	0.2473
4	ada	76.39	23.85	21.5	0.7639	0.2385

	0	1	2	3	4
0	1.000000	0.001000	0.001000	0.130021	0.601174
1	0.001000	1.000000	0.525782	0.001000	0.028642
2	0.001000	0.525782	1.000000	0.001000	0.001000
3	0.130021	0.001000	0.001000	1.000000	0.001573
4	0.601174	0.028642	0.001000	0.001573	1.000000