def subject_regularize(rfcs,
X_int,
X_other,
Y,
oob=False,
regularize=[0.75, 0.3, 0.65]):
if len(regularize) == 1:
regularize = regularize * 3
observed_ = []
predicted_ = []
for subject in range(1, 50):
observed = Y['subject'][subject]
rfc = rfcs[1][subject]
if oob:
predicted = rfc.oob_prediction_
else:
predicted = rfc.predict(X_other)
predicted_int = rfc.predict(X_int)
predicted[:, 0] = predicted_int[:, 0]
observed_.append(observed)
predicted_.append(predicted)
predicted = np.dstack(predicted_)
observed = np.ma.dstack(observed_)
predicted_mean = np.mean(predicted, axis=2, keepdims=True)
predicted_std = np.std(predicted, axis=2, keepdims=True)
predicted_mean_std = np.hstack((predicted_mean, predicted_std)).squeeze()
predicted_int = regularize[0]*(predicted_mean)\
+ (1-regularize[0])*predicted
predicted_ple = regularize[1]*(predicted_mean)\
+ (1-regularize[1])*predicted
predicted_dec = regularize[2]*(predicted_mean)\
+ (1-regularize[2])*predicted
predicted = regularize[0]*(predicted_mean)\
+ (1-regularize[0])*predicted
r_int = scoring.r('int', predicted_int, observed)
r_ple = scoring.r('ple', predicted_ple, observed)
r_dec = scoring.r('dec', predicted_dec, observed)
score1_ = scoring.score(predicted, observed, n_subjects=49)
score1 = scoring.rs2score(r_int, r_ple, r_dec)
#print(score1_,score1)
print("For subchallenge %d, score = %.3f (%.3f,%.3f,%.3f)"\
% (1,score1,r_int,r_ple,r_dec))
score2 = scoring.score2(predicted_mean_std, Y['mean_std'])
r_int_mean = scoring.r2('int', 'mean', predicted_mean_std, Y['mean_std'])
r_ple_mean = scoring.r2('ple', 'mean', predicted_mean_std, Y['mean_std'])
r_dec_mean = scoring.r2('dec', 'mean', predicted_mean_std, Y['mean_std'])
r_int_std = scoring.r2('int', 'std', predicted_mean_std, Y['mean_std'])
r_ple_std = scoring.r2('ple', 'std', predicted_mean_std, Y['mean_std'])
r_dec_std = scoring.r2('dec', 'std', predicted_mean_std, Y['mean_std'])
print("For subchallenge %d, score = %.2f (%.2f,%.2f,%.2f,%.2f,%.2f,%.2f)"%\
(2,score2,r_int_mean,r_ple_mean,r_dec_mean,
r_int_std,r_ple_std,r_dec_std))
return (r_int, r_ple, r_dec, r_int_mean, r_ple_mean, r_dec_mean, r_int_std,
r_ple_std, r_dec_std)
def rfc_(X_train,
Y_train,
X_test_int,
X_test_other,
Y_test,
max_features=1500,
n_estimators=1000,
max_depth=None,
min_samples_leaf=1):
print(max_features)
def rfc_maker():
return RandomForestRegressor(max_features=max_features,
n_estimators=n_estimators,
max_depth=max_depth,
min_samples_leaf=min_samples_leaf,
n_jobs=-1,
oob_score=True,
random_state=0)
rfc = rfc_maker()
rfc.fit(X_train, Y_train)
scores = {}
for phase, X, Y in [('train', X_train, Y_train),
('test', (X_test_int, X_test_other), Y_test)]:
if phase == 'train':
predicted = rfc.oob_prediction_
else:
predicted = rfc.predict(X[1])
predicted_int = rfc.predict(X[0])
predicted[:, 0] = predicted_int[:, 0]
predicted[:, 21] = predicted_int[:, 21]
observed = Y
score = scoring.score2(predicted, observed)
r_int = scoring.r2('int', 'mean', predicted, observed)
r_ple = scoring.r2('ple', 'mean', predicted, observed)
r_dec = scoring.r2('dec', 'mean', predicted, observed)
r_int_sig = scoring.r2('int', 'sigma', predicted, observed)
r_ple_sig = scoring.r2('ple', 'sigma', predicted, observed)
r_dec_sig = scoring.r2('dec', 'sigma', predicted, observed)
print("For subchallenge 2, %s phase, score = %.2f (%.2f,%.2f,%.2f,%.2f,%.2f,%.2f)" \
% (phase,score,r_int,r_ple,r_dec,r_int_sig,r_ple_sig,r_dec_sig))
scores[phase] = (score, r_int, r_ple, r_dec, r_int_sig, r_ple_sig,
r_dec_sig)
return rfc, scores['train'], scores['test']
def subject_regularize(rfcs,X_int,X_other,Y,oob=False,regularize=[0.75,0.3,0.65]):
if len(regularize)==1:
regularize = regularize*3
observed_ = []
predicted_ = []
for subject in range(1,50):
observed = Y['subject'][subject]
rfc = rfcs[1][subject]
if oob:
predicted = rfc.oob_prediction_
else:
predicted = rfc.predict(X_other)
predicted_int = rfc.predict(X_int)
predicted[:,0] = predicted_int[:,0]
observed_.append(observed)
predicted_.append(predicted)
predicted = np.dstack(predicted_)
observed = np.ma.dstack(observed_)
predicted_mean = np.mean(predicted,axis=2,keepdims=True)
predicted_std = np.std(predicted,axis=2,keepdims=True)
predicted_mean_std = np.hstack((predicted_mean,predicted_std)).squeeze()
predicted_int = regularize[0]*(predicted_mean) + (1-regularize[0])*predicted
predicted_ple = regularize[1]*(predicted_mean) + (1-regularize[1])*predicted
predicted_dec = regularize[2]*(predicted_mean) + (1-regularize[2])*predicted
predicted = regularize[0]*(predicted_mean) + (1-regularize[0])*predicted
r_int = scoring.r('int',predicted_int,observed)
r_ple = scoring.r('ple',predicted_ple,observed)
r_dec = scoring.r('dec',predicted_dec,observed)
score1_ = scoring.score(predicted,observed,n_subjects=49)
score1 = scoring.rs2score(r_int,r_ple,r_dec)
#print(score1_,score1)
print("For subchallenge %d, score = %.3f (%.3f,%.3f,%.3f)" % (1,score1,r_int,r_ple,r_dec))
score2 = scoring.score2(predicted_mean_std,Y['mean_std'])
r_int_mean = scoring.r2('int','mean',predicted_mean_std,Y['mean_std'])
r_ple_mean = scoring.r2('ple','mean',predicted_mean_std,Y['mean_std'])
r_dec_mean = scoring.r2('dec','mean',predicted_mean_std,Y['mean_std'])
r_int_sigma = scoring.r2('int','sigma',predicted_mean_std,Y['mean_std'])
r_ple_sigma = scoring.r2('ple','sigma',predicted_mean_std,Y['mean_std'])
r_dec_sigma = scoring.r2('dec','sigma',predicted_mean_std,Y['mean_std'])
print("For subchallenge %d, score = %.2f (%.2f,%.2f,%.2f,%.2f,%.2f,%.2f)" % \
(2,score2,r_int_mean,r_ple_mean,r_dec_mean,r_int_sigma,r_ple_sigma,r_dec_sigma))
return (r_int,r_ple,r_dec,r_int_mean,r_ple_mean,r_dec_mean,r_int_sigma,r_ple_sigma,r_dec_sigma)
def rfc_(X_train,Y_train,X_test_int,X_test_other,Y_test,
max_features=1500,n_estimators=1000,max_depth=None,min_samples_leaf=1):
print(max_features)
def rfc_maker():
return RandomForestRegressor(max_features=max_features,
n_estimators=n_estimators,
max_depth=max_depth,
min_samples_leaf=min_samples_leaf,
n_jobs=-1,
oob_score=True,
random_state=0)
rfc = rfc_maker()
rfc.fit(X_train,Y_train)
scores = {}
for phase,X,Y in [('train',X_train,Y_train),('test',(X_test_int,X_test_other),Y_test)]:
if phase == 'train':
predicted = rfc.oob_prediction_
else:
predicted = rfc.predict(X[1])
predicted_int = rfc.predict(X[0])
predicted[:,0] = predicted_int[:,0]
predicted[:,21] = predicted_int[:,21]
observed = Y
score = scoring.score2(predicted,observed)
r_int = scoring.r2('int','mean',predicted,observed)
r_ple = scoring.r2('ple','mean',predicted,observed)
r_dec = scoring.r2('dec','mean',predicted,observed)
r_int_sig = scoring.r2('int','sigma',predicted,observed)
r_ple_sig = scoring.r2('ple','sigma',predicted,observed)
r_dec_sig = scoring.r2('dec','sigma',predicted,observed)
print("For subchallenge 2, %s phase, score = %.2f (%.2f,%.2f,%.2f,%.2f,%.2f,%.2f)" \
% (phase,score,r_int,r_ple,r_dec,r_int_sig,r_ple_sig,r_dec_sig))
scores[phase] = (score,r_int,r_ple,r_dec,r_int_sig,r_ple_sig,r_dec_sig)
return rfc,scores['train'],scores['test']
def rfc_final(X,Y_imp,Y_mask,
max_features,min_samples_leaf,max_depth,et,use_mask,trans_weight,
trans_params,X_test_int=None,X_test_other=None,Y_test=None,n_estimators=100,seed=0,quiet=False):
if X_test_int is None:
X_test_int = X
if X_test_other is None:
X_test_other = X
if Y_test is None:
Y_test = Y_mask
def rfc_maker(n_estimators=n_estimators,max_features=max_features,
min_samples_leaf=min_samples_leaf,max_depth=max_depth,et=False):
if not et:
kls = RandomForestRegressor
kwargs = {'oob_score':False}
else:
kls = ExtraTreesRegressor
kwargs = {}
return kls(n_estimators=n_estimators, max_features=max_features,
min_samples_leaf=min_samples_leaf, max_depth=max_depth,
n_jobs=-1, random_state=seed, **kwargs)
rfcs = {}
for col in range(42):
prog(col,42)
rfcs[col] = rfc_maker(n_estimators=n_estimators,
max_features=max_features[col],
min_samples_leaf=min_samples_leaf[col],
max_depth=max_depth[col],
et=et[col])
if use_mask[col]:
rfcs[col].fit(X,Y_mask[:,col])
else:
rfcs[col].fit(X,Y_imp[:,col])
predicted = np.zeros((X_test_int.shape[0],42))
for col in range(42):
if et[col] or not np.array_equal(X,X_test_int):
# Possibly check in-sample fit because there isn't any alternative.
if col in [0,21]:
predicted[:,col] = rfcs[col].predict(X_test_int)
else:
predicted[:,col] = rfcs[col].predict(X_test_other)
else:
try:
predicted[:,col] = rfcs[col].oob_prediction_
except AttributeError:
if col in [0,21]:
predicted[:,col] = rfcs[col].predict(X_test_int)
else:
predicted[:,col] = rfcs[col].predict(X_test_other)
def f_transform(x, k0, k1):
return 100*(k0*(x/100)**(k1*0.5) - k0*(x/100)**(k1*2))
for col in range(21):
tw = trans_weight[col]
k0,k1 = trans_params[col]
p_m = predicted[:,col]
p_s = predicted[:,col+21]
predicted[:,col+21] = tw*f_transform(p_m,k0,k1) + (1-tw)*p_s
observed = Y_test
score = scoring.score2(predicted,observed)
rs = {}
for kind in ['int','ple','dec']:
rs[kind] = {}
for moment in ['mean','sigma']:
rs[kind][moment] = scoring.r2(kind,moment,predicted,observed)
if not quiet:
print("For subchallenge 2:")
print("\tScore = %.2f" % score)
for kind in ['int','ple','dec']:
for moment in ['mean','sigma']:
print("\t%s_%s = %.3f" % (kind,moment,rs[kind][moment]))
return (rfcs,score,rs)
def rfc_final(X,Y_imp,Y_mask,
max_features,min_samples_leaf,max_depth,et,use_mask,
Y_test=None,n_estimators=100,seed=0):
if Y_test is None:
Y_test = Y_mask
def rfc_maker(n_estimators=n_estimators,max_features=max_features,
min_samples_leaf=min_samples_leaf,max_depth=max_depth,et=False):
if not et:
return RandomForestRegressor(n_estimators=n_estimators,
max_features=max_features,
min_samples_leaf=min_samples_leaf,
max_depth=max_depth,
oob_score=True,
n_jobs=-1,random_state=seed)
else:
return ExtraTreesRegressor(n_estimators=n_estimators,
max_features=max_features,
min_samples_leaf=min_samples_leaf,
max_depth=max_depth,
n_jobs=-1,random_state=seed)
rfcs = {}
for kind in ['int','ple','dec']:
rfcs[kind] = {}
for moment in ['mean','sigma']:
rfcs[kind][moment] = rfc_maker(n_estimators=n_estimators,
max_features=max_features[kind][moment],
min_samples_leaf=min_samples_leaf[kind][moment],
max_depth=max_depth[kind][moment],
et=et[kind][moment])
for kind in ['int','ple','dec']:
for moment in ['mean','sigma']:
if use_mask[kind][moment]:
rfcs[kind][moment].fit(X,Y_mask)
else:
rfcs[kind][moment].fit(X,Y_imp)
predictions = {}
for kind in ['int','ple','dec']:
predictions[kind] = {}
for moment in ['mean','sigma']:
if et[kind][moment]:
# Check in-sample fit because there isn't any alternative.
predictions[kind][moment] = rfcs[kind][moment].predict(X)
else:
predictions[kind][moment] = rfcs[kind][moment].oob_prediction_
predicted = predictions['int']['mean'].copy()
for i,moment in enumerate(['mean','sigma']):
predicted[:,(0+21*i)] = predictions['int'][moment][:,(0+21*i)]
predicted[:,(1+21*i)] = predictions['ple'][moment][:,(1+21*i)]
predicted[:,(2+21*i):(21+21*i)] = predictions['dec'][moment][:,(2+21*i):(21+21*i)]
observed = Y_test
score = scoring.score2(predicted,observed)
rs = {}
predictions = {}
for kind in ['int','ple','dec']:
rs[kind] = {}
for moment in ['mean','sigma']:
rs[kind][moment] = scoring.r2(kind,moment,predicted,observed)
rs['int']['trans'] = scoring.r2(None,None,f_int(predicted[:,0]),observed[:,0])
print("For subchallenge 2:")
print("\tScore = %.2f" % score)
for kind in ['int','ple','dec']:
for moment in ['mean','sigma']:
print("\t%s_%s = %.3f" % (kind,moment,rs[kind][moment]))
return (rfcs,score,rs)
def rfc_final(X,
Y_imp,
Y_mask,
max_features,
min_samples_leaf,
max_depth,
et,
use_mask,
Y_test=None,
n_estimators=100,
seed=0):
if Y_test is None:
Y_test = Y_mask
def rfc_maker(n_estimators=n_estimators,
max_features=max_features,
min_samples_leaf=min_samples_leaf,
max_depth=max_depth,
et=False):
if not et:
return RandomForestRegressor(n_estimators=n_estimators,
max_features=max_features,
min_samples_leaf=min_samples_leaf,
max_depth=max_depth,
oob_score=True,
n_jobs=-1,
random_state=seed)
else:
return ExtraTreesRegressor(n_estimators=n_estimators,
max_features=max_features,
min_samples_leaf=min_samples_leaf,
max_depth=max_depth,
n_jobs=-1,
random_state=seed)
rfcs = {}
for kind in ['int', 'ple', 'dec']:
rfcs[kind] = {}
for moment in ['mean', 'sigma']:
rfcs[kind][moment] = rfc_maker(
n_estimators=n_estimators,
max_features=max_features[kind][moment],
min_samples_leaf=min_samples_leaf[kind][moment],
max_depth=max_depth[kind][moment],
et=et[kind][moment])
for kind in ['int', 'ple', 'dec']:
for moment in ['mean', 'sigma']:
if use_mask[kind][moment]:
rfcs[kind][moment].fit(X, Y_mask)
else:
rfcs[kind][moment].fit(X, Y_imp)
predictions = {}
for kind in ['int', 'ple', 'dec']:
predictions[kind] = {}
for moment in ['mean', 'sigma']:
if et[kind][moment]:
# Check in-sample fit because there isn't any alternative.
predictions[kind][moment] = rfcs[kind][moment].predict(X)
else:
predictions[kind][moment] = rfcs[kind][moment].oob_prediction_
predicted = predictions['int']['mean'].copy()
for i, moment in enumerate(['mean', 'sigma']):
predicted[:, (0 + 21 * i)] = predictions['int'][moment][:,
(0 + 21 * i)]
predicted[:, (1 + 21 * i)] = predictions['ple'][moment][:,
(1 + 21 * i)]
predicted[:,
(2 + 21 * i):(21 + 21 * i)] = predictions['dec'][moment][:, (
2 + 21 * i):(21 + 21 * i)]
observed = Y_test
score = scoring.score2(predicted, observed)
rs = {}
predictions = {}
for kind in ['int', 'ple', 'dec']:
rs[kind] = {}
for moment in ['mean', 'sigma']:
rs[kind][moment] = scoring.r2(kind, moment, predicted, observed)
rs['int']['trans'] = scoring.r2(None, None, f_int(predicted[:, 0]),
observed[:, 0])
print("For subchallenge 2:")
print("\tScore = %.2f" % score)
for kind in ['int', 'ple', 'dec']:
for moment in ['mean', 'sigma']:
print("\t%s_%s = %.3f" % (kind, moment, rs[kind][moment]))
return (rfcs, score, rs)
