def _pdi_gs_full_r1(method,
xM_l,
yV,
X_concat=None,
mode="Ridge",
expension=False,
n_folds=20,
alphas_log=(-3, 2, (2 - (-3)) * 2 + 1)):
if mode == "Ridge":
xM = np.concatenate(xM_l, axis=1)
gs = jgrid.gs_Ridge(xM, yV, alphas_log, n_folds=n_folds)
elif mode == "BIKE_Ridge":
# print "BIKE_Ridge mode is working now."
A_l = xM_l
gs = jgrid.gs_BIKE_Ridge(A_l,
yV,
alphas_log=alphas_log,
X_concat=X_concat,
n_folds=n_folds)
else:
print("Mode {} is not supported.".format(mode))
# gs.grid_scores_
if expension:
pdi = pdi_gs(method, gs.grid_scores_, expension=expension)
else:
pdi = pdi_gs(method, gs.grid_scores_)
pdi.plot(kind='line',
x='alpha',
y='mean(r2)',
yerr='std(r2)',
logx=True)
plt.ylabel(r"E[$r^2$]")
return pdi
def grid_BIKE2(pdr, alphas_log, y_id = 'Solubility_log_mol_l'): print "BIKE with (A+B)+W" xM1 = jpd.pd_get_xM( pdr, radius=6, nBits=4096) xM2 = jpd.pd_get_xM_MACCSkeys( pdr) yV = jpd.pd_get_yV( pdr, y_id = y_id) #A1 = jpyx.calc_tm_sim_M( xM1) #A2 = jpyx.calc_tm_sim_M( xM2) #A = np.concatenate( ( A1, A2), axis = 1) xM = np.concatenate( ( xM1, xM2), axis = 1) A = jpyx.calc_tm_sim_M( xM1) print A.shape molw_l = jchem.rdkit_molwt( pdr.SMILES.tolist()) print np.shape( molw_l) A_molw = jchem.add_new_descriptor( A, molw_l) print A_molw.shape gs = jgrid.gs_Ridge( A_molw, yV, alphas_log=alphas_log) jutil.show_gs_alpha( gs.grid_scores_) jgrid.cv( 'Ridge', A_molw, yV, alpha = gs.best_params_['alpha']) return gs
def set_pdi_d_full(pdi_d, method, xM_l, yV):
xM = np.concatenate(xM_l, axis = 1)
gs = jgrid.gs_Ridge(xM, yV, (-3, 2, 10), n_folds=20)
# gs.grid_scores_
set_pdi_d(pdi_d, method, gs.grid_scores_)
pdi_d[ method].plot(kind ='line', x='alpha', y='mean(r2)', yerr='std(r2)', logx=True)
plt.ylabel(r"E[$r^2$]")
return pdi_d[method]
def _pdi_gs_full_r0( method, xM_l, yV, expension = False):
xM = np.concatenate( xM_l, axis = 1)
gs = jgrid.gs_Ridge( xM, yV, (-3, 2, 10), n_folds=20)
# gs.grid_scores_
if expension:
pdi = pdi_gs( method, gs.grid_scores_, expension = expension)
else:
pdi = pdi_gs( pdi_d, method, gs.grid_scores_)
pdi.plot( kind ='line', x = 'alpha', y = 'mean(r2)', yerr = 'std(r2)', logx = True)
plt.ylabel( r"E[$r^2$]")
return pdi
def grid_MLR_B(pdr, alphas_log, y_id = 'Solubility_log_mol_l'): print "MLR with B" xM2 = jpd.pd_get_xM_MACCSkeys( pdr) xM_molw = xM2 yV = jpd.pd_get_yV( pdr, y_id = y_id) gs = jgrid.gs_Ridge( xM_molw, yV, alphas_log=alphas_log) jutil.show_gs_alpha( gs.grid_scores_) jgrid.cv( 'Ridge', xM_molw, yV, alpha = gs.best_params_['alpha']) return gs
def grid_MLR_A(pdr, alphas_log, y_id = 'Solubility_log_mol_l'): print "MLR with A" xM1 = jpd.pd_get_xM( pdr, radius=6, nBits=4096) xM_molw = xM1 yV = jpd.pd_get_yV( pdr, y_id = y_id) gs = jgrid.gs_Ridge( xM_molw, yV, alphas_log=alphas_log) jutil.show_gs_alpha( gs.grid_scores_) jgrid.cv( 'Ridge', xM_molw, yV, alpha = gs.best_params_['alpha']) return gs
def set_pdi_d_full(pdi_d, method, xM_l, yV):
xM = np.concatenate(xM_l, axis=1)
gs = jgrid.gs_Ridge(xM, yV, (-3, 2, 10), n_folds=20)
# gs.grid_scores_
set_pdi_d(pdi_d, method, gs.grid_scores_)
pdi_d[method].plot(kind='line',
x='alpha',
y='mean(r2)',
yerr='std(r2)',
logx=True)
plt.ylabel(r"E[$r^2$]")
return pdi_d[method]
def _pdi_gs_full_r0(method, xM_l, yV, expension=False):
xM = np.concatenate(xM_l, axis=1)
gs = jgrid.gs_Ridge(xM, yV, (-3, 2, 10), n_folds=20)
# gs.grid_scores_
if expension:
pdi = pdi_gs(method, gs.grid_scores_, expension=expension)
else:
pdi = pdi_gs(pdi_d, method, gs.grid_scores_)
pdi.plot(kind='line',
x='alpha',
y='mean(r2)',
yerr='std(r2)',
logx=True)
plt.ylabel(r"E[$r^2$]")
return pdi
def _pdi_gs_full_r0( method, xM_l, yV, X_concat = None, mode = "Ridge", expension = False, n_folds=20):
if mode == "Ridge":
xM = np.concatenate( xM_l, axis = 1)
gs = jgrid.gs_Ridge( xM, yV, (-3, 2, 12), n_folds=n_folds)
elif mode == "BIKE_Ridge":
# print "BIKE_Ridge mode is working now."
A_l = xM_l
gs = jgrid.gs_BIKE_Ridge( A_l, yV, alphas_log=(-3, 2, 12), X_concat = X_concat, n_folds=n_folds)
else:
print("Mode {} is not supported.".format( mode))
# gs.grid_scores_
if expension:
pdi = pdi_gs( method, gs.grid_scores_, expension = expension)
else:
pdi = pdi_gs( method, gs.grid_scores_)
pdi.plot( kind ='line', x = 'alpha', y = 'mean(r2)', yerr = 'std(r2)', logx = True)
plt.ylabel( r"E[$r^2$]")
return pdi
