def linreg_fit(input_dict):
from discomll.regression import linear_regression
fitmodel_url = linear_regression.fit(input_dict["dataset"],
save_results=True)
return {"fitmodel_url": fitmodel_url}
def linreg_fit(input_dict):
from discomll.regression import linear_regression
fitmodel_url = linear_regression.fit(input_dict["dataset"],
save_results=True)
return {"fitmodel_url": fitmodel_url}
def test_lin_reg(self):
# python -m unittest tests_regression.Tests_Regression.test_lin_reg
from sklearn import linear_model
from discomll.regression import linear_regression
x_train, y_train, x_test, y_test = datasets.ex3()
train_data, test_data = datasets.ex3_discomll()
lin_reg = linear_model.LinearRegression() # Create linear regression object
lin_reg.fit(x_train, y_train) # Train the model using the training sets
thetas1 = [lin_reg.intercept_] + lin_reg.coef_[1:].tolist()
prediction1 = lin_reg.predict(x_test)
thetas_url = linear_regression.fit(train_data)
thetas2 = [v for k, v in result_iterator(thetas_url["linreg_fitmodel"])]
results = linear_regression.predict(test_data, thetas_url)
prediction2 = [v[0] for k, v in result_iterator(results)]
self.assertTrue(np.allclose(thetas1, thetas2))
self.assertTrue(np.allclose(prediction1, prediction2))
def test_lin_reg(self):
# python -m unittest tests_regression.Tests_Regression.test_lin_reg
from sklearn import linear_model
from discomll.regression import linear_regression
x_train, y_train, x_test, y_test = datasets.ex3()
train_data, test_data = datasets.ex3_discomll()
lin_reg = linear_model.LinearRegression(
) # Create linear regression object
lin_reg.fit(x_train,
y_train) # Train the model using the training sets
thetas1 = [lin_reg.intercept_] + lin_reg.coef_[1:].tolist()
prediction1 = lin_reg.predict(x_test)
thetas_url = linear_regression.fit(train_data)
thetas2 = [
v for k, v in result_iterator(thetas_url["linreg_fitmodel"])
]
results = linear_regression.predict(test_data, thetas_url)
prediction2 = [v[0] for k, v in result_iterator(results)]
self.assertTrue(np.allclose(thetas1, thetas2))
self.assertTrue(np.allclose(prediction1, prediction2))
from discomll import dataset
from discomll.regression import linear_regression
train = dataset.Data(
data_tag=["http://ropot.ijs.si/data/fraction/train/xaaaaa.gz", "http://ropot.ijs.si/data/fraction/train/xaaabj.gz"],
data_type="gzip",
generate_urls=True,
X_indices=range(1, 14),
id_index=0,
y_index=14,
delimiter=",")
test = dataset.Data(
data_tag=["http://ropot.ijs.si/data/fraction/test/xaaaaa.gz", "http://ropot.ijs.si/data/fraction/test/xaaabj.gz"],
data_type="gzip",
generate_urls=True,
X_indices=range(1, 14),
id_index=0,
y_index=14,
delimiter=",")
fit_model = linear_regression.fit(train)
predictions = linear_regression.predict(test, fit_model)
print predictions
from discomll import dataset
from discomll.regression import linear_regression
from discomll.utils import model_view
# define training dataset
train = dataset.Data(data_tag=["test:ex3"],
data_type="chunk",
X_indices=[0, 1],
y_index=2)
# define test dataset
test = dataset.Data(data_tag=["test:ex3_test"],
data_type="chunk",
X_indices=[0, 1],
y_index=2)
# fit model on training dataset
fit_model = linear_regression.fit(train)
# output model
model = model_view.output_model(fit_model)
print model
# predict test dataset
predictions = linear_regression.predict(test, fit_model)
# output results
for k, v in result_iterator(predictions):
print k, v[0]