def ensemble_submission(self):
"""
For all the models specified in self.d_model,
train them and apply them on the test data to
create a submission file
"""
# Loop over possible ensemblers
for model_name in self.d_model.keys() :
# Only train if desired
if self.d_model[model_name]["train"]:
# Get data
feat_choice = self.d_model[model_name]["feat_choice"]
X_train, y_train, Id_train = prep.prepare_lv2_data(feat_choice, "train")
X_test, dummy, Id_test = prep.prepare_lv2_data(feat_choice, "test")
# X, y, Id = X[:1000,:], y[:1000], Id[:1000]
y_pred_test = self._stack_preds_submission(X_train, y_train, X_test, model_name)
#Save predictions to csv file with pandas
Id_test = np.reshape(Id_test, (Id_test.shape[0],1))
y_pred_test = np.reshape(y_pred_test, (y_pred_test.shape[0], 1))
data = np.hstack((Id_test, y_pred_test))
df = pd.DataFrame(data, columns=["Id", "Response"])
df["Id"] = df["Id"].astype(int)
df = df.sort_values("Id")
out_name = "./Data/Level2_model_files/submission_%s_stack_with_keras.csv" % model_name
df.to_csv(out_name, index = False)
def ensemble_submission(self):
"""
For all the models specified in self.d_model,
train them and apply them on the test data to
create a submission file
"""
# Loop over possible ensemblers
for model_name in self.d_model.keys():
# Only train if desired
if self.d_model[model_name]["train"]:
# Get data
feat_choice = self.d_model[model_name]["feat_choice"]
X_train, y_train, Id_train = prep.prepare_lv2_data(
feat_choice, "train")
X_test, dummy, Id_test = prep.prepare_lv2_data(
feat_choice, "test")
# X, y, Id = X[:1000,:], y[:1000], Id[:1000]
y_pred_test = self._stack_preds_submission(
X_train, y_train, X_test, model_name)
#Save predictions to csv file with pandas
Id_test = np.reshape(Id_test, (Id_test.shape[0], 1))
y_pred_test = np.reshape(y_pred_test,
(y_pred_test.shape[0], 1))
data = np.hstack((Id_test, y_pred_test))
df = pd.DataFrame(data, columns=["Id", "Response"])
df["Id"] = df["Id"].astype(int)
df = df.sort_values("Id")
out_name = "./Data/Level2_model_files/submission_%s_stack_with_keras.csv" % model_name
df.to_csv(out_name, index=False)
def ensemble(self):
"""
For all the models specified in self.d_model,
train them and estimate the CV score
"""
# Loop over possible ensemblers
for model_name in self.d_model.keys() :
# Only train if desired
if self.d_model[model_name]["train"]:
# Get data
feat_choice = self.d_model[model_name]["feat_choice"]
X, y, Id = prep.prepare_lv2_data(feat_choice, "train")
self._stack_preds(X, y, Id, model_name)
def ensemble(self):
"""
For all the models specified in self.d_model,
train them and estimate the CV score
"""
# Loop over possible ensemblers
for model_name in self.d_model.keys():
# Only train if desired
if self.d_model[model_name]["train"]:
# Get data
feat_choice = self.d_model[model_name]["feat_choice"]
X, y, Id = prep.prepare_lv2_data(feat_choice, "train")
self._stack_preds(X, y, Id, model_name)
