def model(self):
#cname = sys._getframe().f_code.co_name
cname = 'keras'
train, y, test = self.train_, self.y_, self.test_
np.random.seed(1234)
train.drop('id', axis=1, inplace=True)
test.drop('id', axis=1, inplace=True)
from sklearn import pipeline
pipe = pipeline.make_pipeline(preprocessing.Imputer(),
preprocessing.RobustScaler())
train = pipe.fit_transform(train)
test = pipe.transform(test)
self.input_dims_ = train.shape[1]
def build_model():
return self.build_keras_model()
batch_size = self.batch_size_
build_model().summary(line_length=120)
ss = model_selection.StratifiedKFold(n_splits = self.num_splits_,
random_state = 11,
shuffle = True)
scores = list()
model_path = self.temp_name('keras_mlp_weights')
v, z = self.v_, self.z_
v[cname] = 0
z[cname] = 0
for n, (itrain, ival) in enumerate(ss.split(train, y)):
xtrain, xval = train[itrain], train[ival]
ytrain, yval = y[itrain], y[ival]
model = build_model()
model.fit(
xtrain, ytrain,
batch_size = batch_size,
epochs = 10000,
validation_data = (xval, yval),
verbose = 0,
callbacks = build_keras_fit_callbacks(model_path),
shuffle = True
)
model.load_weights(model_path)
p = model.predict(xval)
v.loc[ival, cname] += p.ravel()
score = metrics.log_loss(y[ival], p)
if score != score:
raise Exception('NaN score!!!')
print(cname, 'fold %d: '%(n+1), score, self.now())
scores.append(score)
z[cname] += model.predict(test).ravel()
del model
for i in range(3): gc.collect(i)
print('scores:', scores, np.mean(scores), np.std(scores))
self.drop_temp(model_path)
cv=np.mean(scores)
z[cname] /= self.num_splits_
z['y'] = z[cname]
return cv, None
评论列表
文章目录
