def test_all_regressors():
x, y = make_friedman2(10000)
x_train, y_train, x_test, y_test = test_helpers.split_dataset(x, y)
#print y_test[:100]
ols = LinearRegression()
ols.fit(x_train, y_train)
ols_pred = ols.predict(x_test)
#print ols_pred[:100]
ols_mse = mean_square_error(y_test, ols_pred)
for fn in regressors:
print fn
model = fn(x_train, y_train)
print model
pred = model.predict(x_test)
#print pred[:100]
mse = mean_square_error(y_test, pred)
print "OLS MSE:", ols_mse, " Current MSE:", mse
print "Ratio:", mse / ols_mse
assert ols_mse > 1.1 * mse
def test_all_regressors():
x, y = make_friedman2(10000)
x_train, y_train, x_test, y_test = test_helpers.split_dataset(x,y)
#print y_test[:100]
ols = LinearRegression()
ols.fit(x_train, y_train)
ols_pred = ols.predict(x_test)
#print ols_pred[:100]
ols_mse = mean_square_error(y_test, ols_pred)
for fn in regressors:
print fn
model = fn(x_train,y_train)
print model
pred = model.predict(x_test)
#print pred[:100]
mse = mean_square_error(y_test, pred)
print "OLS MSE:", ols_mse, " Current MSE:", mse
print "Ratio:", mse / ols_mse
assert ols_mse > 1.1*mse
import recipes
import numpy as np
import sklearn.datasets
from test_helpers import split_dataset
iris = sklearn.datasets.load_iris()
x_train, y_train, x_test, y_test = split_dataset(iris.data, iris.target)
classifiers = [
recipes.train_svm_tree,
recipes.train_sgd_tree,
#recipes.train_svm_forest,
#recipes.train_sgd_forest,
recipes.train_random_forest,
recipes.train_clustered_svm,
recipes.train_clustered_svm_ensemble
]
def test_all_classifiers():
for model_constructor in classifiers:
print model_constructor
model = model_constructor(x_train, y_train)
print model
pred = model.predict(x_test)
num_incorrect = np.sum(pred != y_test)
print "Expected num_incorrect <= 20, got:", num_incorrect
assert num_incorrect <= 15
