def test_subset_fit():
"""[Subsemble] 'fit' and 'predict' runs correctly."""
meta = OLS()
meta.fit(F, y)
g = meta.predict(P)
ens = Subsemble()
ens.add(ECM, partitions=2, folds=3, dtype=np.float64)
ens.add_meta(OLS(), dtype=np.float64)
ens.fit(X, y)
pred = ens.predict(X)
np.testing.assert_array_equal(pred, g)
def add_subsemble(name, models, X_train, Y_train, X_test, Y_test):
# Establish and reset variables
acc_score_cv = None
acc_score = None
time_ = None
ensemble = Subsemble(scorer=accuracy_score, random_state=seed)
ensemble.add(models)
# Attach the final meta estimator
ensemble.add(SVC(), meta=True)
start = time.time()
ensemble.fit(X_train, Y_train)
preds = ensemble.predict(X_test)
acc_score = accuracy_score(preds, Y_test)
end = time.time()
time_ = end - start
return {
"Ensemble": name,
"Meta_Classifier": "SVC",
"Accuracy_Score": acc_score,
"Runtime": time_
}
else:
model = Subsemble(partitions=2, random_state=42, n_jobs=1)
model.add(KNeighborsRegressor())
model.add(RandomForestRegressor())
model.add(BayesianRidge())
model.add_meta(Lasso())
# train and predict
train_predict = pd.DataFrame()
test_predict = pd.DataFrame()
for j in Y.columns:
# train the model
model.fit(X.iloc[train_idx, :], Y.loc[train_idx, j])
# predict training and testing data
train_predict_j = pd.DataFrame(model.predict(X.iloc[train_idx, :]), columns=[j])
test_predict_j = pd.DataFrame(model.predict(X.iloc[test_idx, :]), columns=[j])
train_predict = pd.concat([train_predict, train_predict_j], axis=1)
test_predict = pd.concat([test_predict, test_predict_j], axis=1)
print("-- " + j + " --")
# In[2]: Collect the predictions
# reshape all of the predictions into a single table
predictions = pd.DataFrame()
for j in range(outputs):
# collect training data
predict_j = np.array(train_predict.iloc[:,j])
actual_j = np.array(Y.iloc[train_idx, j])
name_j = Y.columns[j]