X_train, X_test, y_train, y_test = train_test_split(X_bal,
y_bal,
test_size=0.33,
random_state=9)
rfc = RandomForestClassifier(oob_score=True, random_state=9)
param_grid = {
"max_features": ['sqrt', 4, "log2"],
"n_estimators": [10, 50, 120],
"max_depth": [40, 20, 10],
"max_leaf_nodes": [5, 10, 2]
}
grid, grid_param, grid_score = grid_search(X_train,
y_train,
rfc,
param_grid,
cv=3)
class TestFit(TestCase):
def test_fit(self): # Input parameters tests
args = getargspec(fit)
self.assertEqual(
len(args[0]), 2,
"Expected argument(s) %d, Given %d" % (2, len(args[0])))
def test_fit_default(self): # Input parameter defaults
args = getargspec(fit)
self.assertEqual(
args[3], None,
def fit(X_test,y_test):
grid, grid_param, grid_score = grid_search(X_train, y_train, rfc, param_grid, cv=3)
grid.fit(X_train,y_train)
y_pred = grid.predict(X_test)
return confusion_matrix(y_test,y_pred), classification_report(y_test,y_pred), accuracy_score(y_test,y_pred)
