def opti_forest(data, n_jobs=1,n_iter=10):
model = RandomForestRegressor()
param_dist = {'n_estimators': rint(15, 30),
# 'criterion': ['mse','mae'], # not in 0.18 but in 0.19
'min_samples_split': rint(2, 10),
'min_samples_leaf': rint(1, 5),
'min_weight_fraction_leaf': [0.02],# opti said this is good
'max_features': [None], # None is best
'min_impurity_split': [0.03, 0.02, 0.01, 0.04], # min_impurity_decrease
"bootstrap": [True], # false conflicts with oob score thing
"oob_score": [False]}
X,y = getXY(data,data.keys())
blu = rsearch(model, param_distributions=param_dist, n_iter=n_iter,n_jobs=n_jobs)
blu.fit(X, y)
print blu.best_params_
print blu.best_score_
def optimize_xgb(data, n_jobs=1, n_iter=10):
model = xgboost.XGBRegressor()
param_dist = {
'max_depth': [14], # 13 and 14 are bestd
'learning_rate': [0.03], # rate id 0.022 and nesti of 94 is also ok
'n_estimators': [65],
'booster': ['gbtree', 'dart'],
'gamma': [0, 0.005, 0.001],
'min_child_weight': [3], # best
'max_delta_step': [1], # best
'reg_alpha': uniform(.8, 1),
'reg_lambda': uniform(0.6, 1)
}
X, y = ss.getXY(data, list(data.keys()))
#X = xgboost.DMatrix(X)
#y= xgboost.DMatrix(y)
blu = rsearch(model,
param_distributions=param_dist,
n_iter=n_iter,
n_jobs=n_jobs)
blu.fit(X, y)
print(blu.best_params_)
print(blu.best_score_)