def LearnGradientBoost(iX, iy, param_overrides=None, test_ratio=0.2):
"""Learns a model to approximate iy from iX.
Args:
iX: List of pandas.Series.
iy: pandas.Series.
param_overrides: Dict of param overrides for GradientBoost algorithm.
test_ratio: Which part to put into test set.
Returns:
Model.
"""
assert all(len(x) == len(iy) for x in iX), "%s != %d" % (map(len, iX), len(iy))
X, y = PrepareForTraining(iX, iy)
L = len(y)
# print '%d docs have y defined out of total %d docs' % (L, len(iy))
X_test, X_train, y_test, y_train = _SplitIntoTrainAndTest(X, y, test_ratio)
params = {"n_estimators": 500, "max_depth": 1, "min_samples_split": 5, "learn_rate": 0.1, "loss": "ls"}
if param_overrides:
params.update(param_overrides)
clf = ensemble.GradientBoostingRegressor(**params)
clf.fit(X_train, y_train)
best_func = _CutAtBestStep(clf, X_test, y_test)
_PrintDebugInfo(best_func, X_test, X_train, y_test, y_train)
return clf
def LearnGradientBoostInTwoHalves(iX, iy, param_overrides=None, min_steps=10):
"""Learns a model to approximate iy from iX.
Args:
iX: List of pandas.Series.
iy: pandas.Series.
param_overrides: Dict of param overrides for GradientBoost algorithm.
test_ratio: Which part to put into test set.
min_steps: int. If training for any part of the data took more than this number of steps, we retrain.
Returns:
Model.
"""
assert all(len(x) == len(iy) for x in iX), "%s != %d" % (map(len, iX), len(iy))
X, y = PrepareForTraining(iX, iy)
L = len(y)
# print '%d docs have y defined out of total %d docs' % (L, len(iy))
while True:
X_1, X_2, y_1, y_2 = _SplitIntoTrainAndTest(X, y, 0.5)
params = {
"n_estimators": 500,
"max_depth": 1,
"min_samples_split": 5,
"min_samples_leaf": 5,
"learn_rate": 0.1,
"loss": "ls",
}
if param_overrides:
params.update(param_overrides)
clf1 = ensemble.GradientBoostingRegressor(**params)
clf1.fit(X_1, y_1)
step1 = _CutAtBestStep(clf1, X_2, y_2)
if step1 < min_steps:
continue
clf2 = ensemble.GradientBoostingRegressor(**params)
clf2.fit(X_2, y_2)
step2 = _CutAtBestStep(clf2, X_1, y_1)
if step1 >= min_steps and step2 >= min_steps:
print step1, step2
return base_predictor.AveragePredictor(clf1, clf2)
"""
