def test_regression_random_forest():
estimator = lightgbm.LGBMRegressor(boosting_type="rf",
n_estimators=2,
random_state=1,
max_depth=1,
subsample=0.7,
subsample_freq=1)
utils.get_regression_model_trainer()(estimator)
assembler = assemblers.LightGBMModelAssembler(estimator)
actual = assembler.assemble()
expected = ast.BinNumExpr(
ast.BinNumExpr(
ast.IfExpr(
ast.CompExpr(ast.FeatureRef(12),
ast.NumVal(5.200000000000001), ast.CompOpType.GT),
ast.NumVal(20.195681040256623), ast.NumVal(38.30000037757679)),
ast.IfExpr(
ast.CompExpr(ast.FeatureRef(5), ast.NumVal(6.853000000000001),
ast.CompOpType.GT), ast.NumVal(36.14745794219976),
ast.NumVal(19.778245570310993)), ast.BinNumOpType.ADD),
ast.NumVal(0.5), ast.BinNumOpType.MUL)
assert utils.cmp_exprs(actual, expected)
def test_regression_random_forest():
estimator = lightgbm.LGBMRegressor(boosting_type="rf",
n_estimators=2,
random_state=1,
max_depth=1,
subsample=0.7,
subsample_freq=1)
utils.get_regression_model_trainer()(estimator)
assembler = assemblers.LightGBMModelAssembler(estimator)
actual = assembler.assemble()
expected = ast.BinNumExpr(
ast.BinNumExpr(
ast.BinNumExpr(
ast.NumVal(0),
ast.IfExpr(
ast.CompExpr(ast.FeatureRef(5),
ast.NumVal(6.954000000000001),
ast.CompOpType.GT),
ast.NumVal(37.24347877367631),
ast.NumVal(19.936999995530854)), ast.BinNumOpType.ADD),
ast.IfExpr(
ast.CompExpr(ast.FeatureRef(5), ast.NumVal(6.971500000000001),
ast.CompOpType.GT), ast.NumVal(38.48600037864964),
ast.NumVal(20.183783757300255)), ast.BinNumOpType.ADD),
ast.NumVal(0.5), ast.BinNumOpType.MUL)
assert utils.cmp_exprs(actual, expected)
def test_regression():
estimator = lightgbm.LGBMRegressor(n_estimators=2,
random_state=1,
max_depth=1)
utils.get_regression_model_trainer()(estimator)
assembler = assemblers.LightGBMModelAssembler(estimator)
actual = assembler.assemble()
expected = ast.SubroutineExpr(
ast.BinNumExpr(
ast.BinNumExpr(
ast.NumVal(0),
ast.SubroutineExpr(
ast.IfExpr(
ast.CompExpr(ast.FeatureRef(5), ast.NumVal(6.918),
ast.CompOpType.GT),
ast.NumVal(24.011454621684155),
ast.NumVal(22.289277544391084))),
ast.BinNumOpType.ADD),
ast.SubroutineExpr(
ast.IfExpr(
ast.CompExpr(ast.FeatureRef(12), ast.NumVal(9.63),
ast.CompOpType.GT),
ast.NumVal(-0.49461212269771115),
ast.NumVal(0.7174324413014594))), ast.BinNumOpType.ADD))
assert utils.cmp_exprs(actual, expected)
def test_regression_random_forest():
estimator = lgb.LGBMRegressor(boosting_type="rf",
n_estimators=2,
random_state=1,
max_depth=1,
subsample=0.7,
subsample_freq=1)
utils.get_regression_model_trainer()(estimator)
assembler = LightGBMModelAssembler(estimator)
actual = assembler.assemble()
expected = ast.BinNumExpr(
ast.BinNumExpr(
ast.IfExpr(
ast.CompExpr(ast.FeatureRef(12),
ast.NumVal(9.605), ast.CompOpType.GT),
ast.NumVal(17.398543657369768),
ast.NumVal(29.851408659650296)),
ast.IfExpr(
ast.CompExpr(ast.FeatureRef(5), ast.NumVal(6.888),
ast.CompOpType.GT), ast.NumVal(37.2235298136268),
ast.NumVal(19.948122884684025)), ast.BinNumOpType.ADD),
ast.NumVal(0.5), ast.BinNumOpType.MUL)
assert utils.cmp_exprs(actual, expected)
def test_maybe_sqr_output_transform():
estimator = lightgbm.LGBMRegressor(n_estimators=2,
random_state=1,
max_depth=1,
reg_sqrt=True,
objective="regression_l1")
utils.get_regression_model_trainer()(estimator)
assembler = assemblers.LightGBMModelAssembler(estimator)
actual = assembler.assemble()
raw_output = ast.IdExpr(ast.BinNumExpr(
ast.IfExpr(
ast.CompExpr(ast.FeatureRef(12), ast.NumVal(9.905),
ast.CompOpType.GT), ast.NumVal(4.5658116817),
ast.NumVal(4.6620790482)),
ast.IfExpr(
ast.CompExpr(ast.FeatureRef(12), ast.NumVal(9.77),
ast.CompOpType.GT), ast.NumVal(-0.0340889740),
ast.NumVal(0.0543687153)), ast.BinNumOpType.ADD),
to_reuse=True)
expected = ast.BinNumExpr(ast.AbsExpr(raw_output), raw_output,
ast.BinNumOpType.MUL)
assert utils.cmp_exprs(actual, expected)
def test_regression_random_forest():
estimator = lightgbm.LGBMRegressor(boosting_type="rf",
n_estimators=2,
random_state=1,
max_depth=1,
subsample=0.7,
subsample_freq=1)
utils.get_regression_model_trainer()(estimator)
assembler = assemblers.LightGBMModelAssembler(estimator)
actual = assembler.assemble()
expected = ast.BinNumExpr(
ast.BinNumExpr(
ast.IfExpr(
ast.CompExpr(ast.FeatureRef(12),
ast.NumVal(5.200000000000001), ast.CompOpType.GT),
ast.NumVal(20.206688945020474), ast.NumVal(38.30000037757679)),
ast.IfExpr(
ast.CompExpr(ast.FeatureRef(5), ast.NumVal(6.837500000000001),
ast.CompOpType.GT), ast.NumVal(36.40634951405711),
ast.NumVal(19.57067132709245)), ast.BinNumOpType.ADD),
ast.NumVal(0.5), ast.BinNumOpType.MUL)
assert utils.cmp_exprs(actual, expected)
def test_exp_output_transform():
estimator = lightgbm.LGBMRegressor(n_estimators=2, random_state=1,
max_depth=1, objective="poisson")
utils.get_regression_model_trainer()(estimator)
assembler = assemblers.LightGBMModelAssembler(estimator)
actual = assembler.assemble()
expected = ast.ExpExpr(
ast.BinNumExpr(
ast.IfExpr(
ast.CompExpr(
ast.FeatureRef(5),
ast.NumVal(6.918),
ast.CompOpType.GT),
ast.NumVal(3.1480683932),
ast.NumVal(3.1101554907)),
ast.IfExpr(
ast.CompExpr(
ast.FeatureRef(12),
ast.NumVal(9.63),
ast.CompOpType.GT),
ast.NumVal(-0.0111969636),
ast.NumVal(0.0160298303)),
ast.BinNumOpType.ADD))
assert utils.cmp_exprs(actual, expected)
def test_regression_saved_without_feature_names():
base_score = 0.6
estimator = xgboost.XGBRegressor(n_estimators=2,
random_state=1,
max_depth=1,
base_score=base_score)
utils.get_regression_model_trainer()(estimator)
with utils.tmp_dir() as tmp_dirpath:
filename = os.path.join(tmp_dirpath, "tmp.file")
estimator.save_model(filename)
estimator = xgboost.XGBRegressor(base_score=base_score)
estimator.load_model(filename)
assembler = assemblers.XGBoostModelAssemblerSelector(estimator)
actual = assembler.assemble()
expected = ast.SubroutineExpr(
ast.BinNumExpr(
ast.BinNumExpr(
ast.NumVal(base_score),
ast.SubroutineExpr(
ast.IfExpr(
ast.CompExpr(ast.FeatureRef(12),
ast.NumVal(9.72500038),
ast.CompOpType.GTE),
ast.NumVal(1.6614188), ast.NumVal(2.91697121))),
ast.BinNumOpType.ADD),
ast.SubroutineExpr(
ast.IfExpr(
ast.CompExpr(ast.FeatureRef(5), ast.NumVal(6.94099998),
ast.CompOpType.GTE), ast.NumVal(3.33810854),
ast.NumVal(1.71813202))), ast.BinNumOpType.ADD))
assert utils.cmp_exprs(actual, expected)
def test_regression_random_forest():
base_score = 0.6
estimator = xgboost.XGBRFRegressor(n_estimators=2, random_state=1,
max_depth=1, base_score=base_score)
utils.get_regression_model_trainer()(estimator)
assembler = assemblers.XGBoostModelAssemblerSelector(estimator)
actual = assembler.assemble()
expected = ast.BinNumExpr(
ast.NumVal(base_score),
ast.BinNumExpr(
ast.IfExpr(
ast.CompExpr(
ast.FeatureRef(5),
ast.NumVal(6.94099998),
ast.CompOpType.GTE),
ast.NumVal(18.1008453),
ast.NumVal(9.60167599)),
ast.IfExpr(
ast.CompExpr(
ast.FeatureRef(5),
ast.NumVal(6.79699993),
ast.CompOpType.GTE),
ast.NumVal(17.780262),
ast.NumVal(9.51712894)),
ast.BinNumOpType.ADD),
ast.BinNumOpType.ADD)
assert utils.cmp_exprs(actual, expected)
def test_regression():
base_score = 0.6
estimator = xgboost.XGBRegressor(n_estimators=2, random_state=1,
max_depth=1, base_score=base_score)
utils.get_regression_model_trainer()(estimator)
assembler = assemblers.XGBoostModelAssemblerSelector(estimator)
actual = assembler.assemble()
expected = ast.BinNumExpr(
ast.NumVal(base_score),
ast.BinNumExpr(
ast.IfExpr(
ast.CompExpr(
ast.FeatureRef(12),
ast.NumVal(9.725),
ast.CompOpType.GTE),
ast.NumVal(4.98425627),
ast.NumVal(8.75091362)),
ast.IfExpr(
ast.CompExpr(
ast.FeatureRef(5),
ast.NumVal(6.941),
ast.CompOpType.GTE),
ast.NumVal(8.34557438),
ast.NumVal(3.9141891)),
ast.BinNumOpType.ADD),
ast.BinNumOpType.ADD)
assert utils.cmp_exprs(actual, expected)
def test_regression_best_ntree_limit():
base_score = 0.6
estimator = xgb.XGBRegressor(n_estimators=3,
random_state=1,
max_depth=1,
base_score=base_score)
utils.get_regression_model_trainer()(estimator)
estimator.get_booster().best_ntree_limit = 2
assembler = XGBoostModelAssemblerSelector(estimator)
actual = assembler.assemble()
expected = ast.BinNumExpr(
ast.NumVal(base_score),
ast.BinNumExpr(
ast.IfExpr(
ast.CompExpr(ast.FeatureRef(12),
ast.NumVal(9.72500038), ast.CompOpType.GTE),
ast.NumVal(4.995625019073486), ast.NumVal(8.715502738952637)),
ast.IfExpr(
ast.CompExpr(ast.FeatureRef(5),
ast.NumVal(6.94099998), ast.CompOpType.GTE),
ast.NumVal(8.309040069580078), ast.NumVal(3.930694580078125)),
ast.BinNumOpType.ADD), ast.BinNumOpType.ADD)
assert utils.cmp_exprs(actual, expected)
def test_maybe_sqr_output_transform():
estimator = lgb.LGBMRegressor(n_estimators=2,
random_state=1,
max_depth=1,
reg_sqrt=True,
objective="regression_l1")
utils.get_regression_model_trainer()(estimator)
assembler = LightGBMModelAssembler(estimator)
actual = assembler.assemble()
raw_output = ast.IdExpr(ast.BinNumExpr(
ast.IfExpr(
ast.CompExpr(ast.FeatureRef(12), ast.NumVal(9.725),
ast.CompOpType.GT), ast.NumVal(4.569350528717041),
ast.NumVal(4.663526439666748)),
ast.IfExpr(
ast.CompExpr(ast.FeatureRef(12), ast.NumVal(11.655),
ast.CompOpType.GT), ast.NumVal(-0.04462450027465819),
ast.NumVal(0.033305134773254384)), ast.BinNumOpType.ADD),
to_reuse=True)
expected = ast.BinNumExpr(ast.AbsExpr(raw_output), raw_output,
ast.BinNumOpType.MUL)
assert utils.cmp_exprs(actual, expected)
def test_regression_random_forest():
base_score = 0.6
estimator = xgb.XGBRFRegressor(n_estimators=2,
random_state=1,
max_depth=1,
base_score=base_score)
utils.get_regression_model_trainer()(estimator)
assembler = XGBoostModelAssemblerSelector(estimator)
actual = assembler.assemble()
expected = ast.BinNumExpr(
ast.NumVal(base_score),
ast.BinNumExpr(
ast.IfExpr(
ast.CompExpr(ast.FeatureRef(5),
ast.NumVal(6.94099998), ast.CompOpType.GTE),
ast.NumVal(18.38124656677246), ast.NumVal(9.772658348083496)),
ast.IfExpr(
ast.CompExpr(ast.FeatureRef(12), ast.NumVal(9.539999961853027),
ast.CompOpType.GTE),
ast.NumVal(8.342499732971191), ast.NumVal(15.027499198913574)),
ast.BinNumOpType.ADD), ast.BinNumOpType.ADD)
assert utils.cmp_exprs(actual, expected)
def test_regression_saved_without_feature_names():
base_score = 0.6
estimator = xgb.XGBRegressor(n_estimators=2,
random_state=1,
max_depth=1,
base_score=base_score)
utils.get_regression_model_trainer()(estimator)
with utils.tmp_dir() as tmp_dirpath:
filename = tmp_dirpath / "tmp.file"
estimator.save_model(filename)
estimator = xgb.XGBRegressor(base_score=base_score)
estimator.load_model(filename)
assembler = XGBoostModelAssemblerSelector(estimator)
actual = assembler.assemble()
expected = ast.BinNumExpr(
ast.NumVal(base_score),
ast.BinNumExpr(
ast.IfExpr(
ast.CompExpr(ast.FeatureRef(12),
ast.NumVal(9.72500038), ast.CompOpType.GTE),
ast.NumVal(4.995625019073486), ast.NumVal(8.715502738952637)),
ast.IfExpr(
ast.CompExpr(ast.FeatureRef(5),
ast.NumVal(6.94099998), ast.CompOpType.GTE),
ast.NumVal(8.309040069580078), ast.NumVal(3.930694580078125)),
ast.BinNumOpType.ADD), ast.BinNumOpType.ADD)
assert utils.cmp_exprs(actual, expected)
def test_regression_random_forest():
base_score = 0.6
estimator = xgboost.XGBRFRegressor(n_estimators=2,
random_state=1,
max_depth=1,
base_score=base_score)
utils.get_regression_model_trainer()(estimator)
assembler = assemblers.XGBoostModelAssemblerSelector(estimator)
actual = assembler.assemble()
expected = ast.SubroutineExpr(
ast.BinNumExpr(
ast.BinNumExpr(
ast.NumVal(0.6),
ast.SubroutineExpr(
ast.IfExpr(
ast.CompExpr(ast.FeatureRef(5), ast.NumVal(6.8375001),
ast.CompOpType.GTE),
ast.NumVal(17.3671646), ast.NumVal(9.48354053))),
ast.BinNumOpType.ADD),
ast.SubroutineExpr(
ast.IfExpr(
ast.CompExpr(ast.FeatureRef(12), ast.NumVal(9.72500038),
ast.CompOpType.GTE), ast.NumVal(8.31587982),
ast.NumVal(14.7766275))), ast.BinNumOpType.ADD))
assert utils.cmp_exprs(actual, expected)
def test_regression():
base_score = 0.6
estimator = xgboost.XGBRegressor(n_estimators=2,
random_state=1,
max_depth=1,
base_score=base_score)
utils.get_regression_model_trainer()(estimator)
assembler = assemblers.XGBoostModelAssemblerSelector(estimator)
actual = assembler.assemble()
expected = ast.SubroutineExpr(
ast.BinNumExpr(
ast.BinNumExpr(
ast.NumVal(base_score),
ast.SubroutineExpr(
ast.IfExpr(
ast.CompExpr(ast.FeatureRef(12),
ast.NumVal(9.72500038),
ast.CompOpType.GTE),
ast.NumVal(1.6614188), ast.NumVal(2.91697121))),
ast.BinNumOpType.ADD),
ast.SubroutineExpr(
ast.IfExpr(
ast.CompExpr(ast.FeatureRef(5), ast.NumVal(6.94099998),
ast.CompOpType.GTE), ast.NumVal(3.33810854),
ast.NumVal(1.71813202))), ast.BinNumOpType.ADD))
assert utils.cmp_exprs(actual, expected)
def _prepare_pickled_model(tmp_path):
p = tmp_path / "model.pickle"
estimator = linear_model.LinearRegression()
utils.get_regression_model_trainer()(estimator)
p.write_bytes(pickle.dumps(estimator))
return p
def _get_pickled_trained_model():
estimator = linear_model.LinearRegression()
utils.get_regression_model_trainer()(estimator)
infile = io.BytesIO()
pickle.dump(estimator, infile)
infile.seek(0)
return infile
def test_linear_model():
# Default updater ("shotgun") is nondeterministic
estimator = xgboost.XGBRegressor(n_estimators=2,
random_state=1,
updater="coord_descent",
feature_selector="shuffle",
booster="gblinear")
utils.get_regression_model_trainer()(estimator)
assembler = assemblers.XGBoostModelAssemblerSelector(estimator)
actual = assembler.assemble()
feature_weight_mul = [
ast.BinNumExpr(ast.FeatureRef(0), ast.NumVal(-0.154567),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(1), ast.NumVal(0.0815865),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(2), ast.NumVal(-0.0979713),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(3), ast.NumVal(4.80472),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(4), ast.NumVal(1.35478),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(5), ast.NumVal(0.327222),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(6), ast.NumVal(0.0610654),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(7), ast.NumVal(0.46989),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(8), ast.NumVal(-0.0674318),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(9), ast.NumVal(-0.000506212),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(10), ast.NumVal(0.0732867),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(11), ast.NumVal(0.0108842),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(12), ast.NumVal(-0.140096),
ast.BinNumOpType.MUL),
]
expected = ast.BinNumExpr(
ast.NumVal(0.5),
assemblers.utils.apply_op_to_expressions(ast.BinNumOpType.ADD,
ast.NumVal(11.138),
*feature_weight_mul),
ast.BinNumOpType.ADD)
assert utils.cmp_exprs(actual, expected)
def test_linear_model():
# Default updater ("shotgun") is nondeterministic
estimator = xgboost.XGBRegressor(n_estimators=2,
random_state=1,
updater="coord_descent",
feature_selector="shuffle",
booster="gblinear")
utils.get_regression_model_trainer()(estimator)
assembler = assemblers.XGBoostModelAssemblerSelector(estimator)
actual = assembler.assemble()
feature_weight_mul = [
ast.BinNumExpr(ast.FeatureRef(0), ast.NumVal(-0.151436),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(1), ast.NumVal(0.084474),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(2), ast.NumVal(-0.10035),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(3), ast.NumVal(4.71537),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(4), ast.NumVal(1.39071),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(5), ast.NumVal(0.330592),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(6), ast.NumVal(0.0610453),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(7), ast.NumVal(0.476255),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(8), ast.NumVal(-0.0677851),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(9), ast.NumVal(-0.000543615),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(10), ast.NumVal(0.0717916),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(11), ast.NumVal(0.010832),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(12), ast.NumVal(-0.139375),
ast.BinNumOpType.MUL),
]
expected = ast.BinNumExpr(
ast.NumVal(0.5),
assemblers.utils.apply_op_to_expressions(ast.BinNumOpType.ADD,
ast.NumVal(11.1287),
*feature_weight_mul),
ast.BinNumOpType.ADD)
assert utils.cmp_exprs(actual, expected)
def test_linear_model():
estimator = xgboost.XGBRegressor(n_estimators=2,
random_state=1,
feature_selector="shuffle",
booster="gblinear")
utils.get_regression_model_trainer()(estimator)
assembler = assemblers.XGBoostModelAssemblerSelector(estimator)
actual = assembler.assemble()
feature_weight_mul = [
ast.BinNumExpr(ast.FeatureRef(0), ast.NumVal(-0.00999326),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(1), ast.NumVal(0.0520094),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(2), ast.NumVal(0.10447),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(3), ast.NumVal(0.17387),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(4), ast.NumVal(0.691745),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(5), ast.NumVal(0.296357),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(6), ast.NumVal(0.0288206),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(7), ast.NumVal(0.417822),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(8), ast.NumVal(0.0551116),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(9), ast.NumVal(0.00242449),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(10), ast.NumVal(0.109585),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(11), ast.NumVal(0.00744202),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(12), ast.NumVal(0.0731089),
ast.BinNumOpType.MUL),
]
expected = ast.SubroutineExpr(
ast.BinNumExpr(
ast.NumVal(0.5),
assemblers.utils.apply_op_to_expressions(ast.BinNumOpType.ADD,
ast.NumVal(3.13109),
*feature_weight_mul),
ast.BinNumOpType.ADD))
assert utils.cmp_exprs(actual, expected)
def test_statsmodels_unknown_constant_position():
estimator = utils.StatsmodelsSklearnLikeWrapper(
sm.GLS, dict(init=dict(hasconst=True)))
_, __, estimator = utils.get_regression_model_trainer()(estimator)
assembler = assemblers.StatsmodelsModelAssemblerSelector(estimator)
assembler.assemble()
def test_regression():
estimator = lgb.LGBMRegressor(n_estimators=2, random_state=1, max_depth=1)
utils.get_regression_model_trainer()(estimator)
assembler = LightGBMModelAssembler(estimator)
actual = assembler.assemble()
expected = ast.BinNumExpr(
ast.IfExpr(
ast.CompExpr(ast.FeatureRef(12), ast.NumVal(9.725),
ast.CompOpType.GT), ast.NumVal(22.030283219508686),
ast.NumVal(23.27840740210207)),
ast.IfExpr(
ast.CompExpr(ast.FeatureRef(5), ast.NumVal(6.8375),
ast.CompOpType.GT), ast.NumVal(1.2777791671888081),
ast.NumVal(-0.2686772850549309)), ast.BinNumOpType.ADD)
assert utils.cmp_exprs(actual, expected)
def test_regression():
estimator = lightgbm.LGBMRegressor(n_estimators=2,
random_state=1,
max_depth=1)
utils.get_regression_model_trainer()(estimator)
assembler = assemblers.LightGBMModelAssembler(estimator)
actual = assembler.assemble()
expected = ast.BinNumExpr(
ast.IfExpr(
ast.CompExpr(ast.FeatureRef(5), ast.NumVal(6.837500000000001),
ast.CompOpType.GT), ast.NumVal(23.961356387224317),
ast.NumVal(22.32858336612959)),
ast.IfExpr(
ast.CompExpr(ast.FeatureRef(12), ast.NumVal(9.725000000000003),
ast.CompOpType.GT), ast.NumVal(-0.5031712645462916),
ast.NumVal(0.6885501354513913)), ast.BinNumOpType.ADD)
assert utils.cmp_exprs(actual, expected)
def test_lightning_regression():
estimator = AdaGradRegressor(random_state=1)
utils.get_regression_model_trainer()(estimator)
assembler = assemblers.SklearnLinearModelAssembler(estimator)
actual = assembler.assemble()
feature_weight_mul = [
ast.BinNumExpr(ast.FeatureRef(0), ast.NumVal(-0.0961163452),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(1), ast.NumVal(0.1574398180),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(2), ast.NumVal(-0.0251799219),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(3), ast.NumVal(0.1975142192),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(4), ast.NumVal(0.1189621635),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(5), ast.NumVal(1.2977018274),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(6), ast.NumVal(0.1192977978),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(7), ast.NumVal(0.0331955333),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(8), ast.NumVal(0.1433964513),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(9), ast.NumVal(0.0014943531),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(10), ast.NumVal(0.3116036672),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(11), ast.NumVal(0.0258421936),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(12), ast.NumVal(-0.7386996349),
ast.BinNumOpType.MUL),
]
expected = assemblers.utils.apply_op_to_expressions(
ast.BinNumOpType.ADD, ast.NumVal(0.0), *feature_weight_mul)
assert utils.cmp_exprs(actual, expected)
def test_lightning_regression():
estimator = AdaGradRegressor(random_state=1)
utils.get_regression_model_trainer()(estimator)
assembler = assemblers.SklearnLinearModelAssembler(estimator)
actual = assembler.assemble()
feature_weight_mul = [
ast.BinNumExpr(ast.FeatureRef(0), ast.NumVal(-0.08558826944690746),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(1), ast.NumVal(0.0803724696787377),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(2), ast.NumVal(-0.03516743076774846),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(3), ast.NumVal(0.26469178947134087),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(4), ast.NumVal(0.15651985221012488),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(5), ast.NumVal(1.5186399078028587),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(6), ast.NumVal(0.10089874009193693),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(7), ast.NumVal(-0.011426237067026246),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(8), ast.NumVal(0.0861987777487293),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(9), ast.NumVal(-0.0057791506839322574),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(10), ast.NumVal(0.3357752757550913),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(11), ast.NumVal(0.020189965076849486),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(12), ast.NumVal(-0.7390647599317609),
ast.BinNumOpType.MUL),
]
expected = assemblers.utils.apply_op_to_expressions(
ast.BinNumOpType.ADD, ast.NumVal(0.0), *feature_weight_mul)
assert utils.cmp_exprs(actual, expected)
def test_lightning_regression():
estimator = AdaGradRegressor(random_state=1)
utils.get_regression_model_trainer()(estimator)
assembler = assemblers.SklearnLinearModelAssembler(estimator)
actual = assembler.assemble()
feature_weight_mul = [
ast.BinNumExpr(ast.FeatureRef(0), ast.NumVal(-0.0610645819),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(1), ast.NumVal(0.0856563713),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(2), ast.NumVal(-0.0562044566),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(3), ast.NumVal(0.2804204925),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(4), ast.NumVal(0.1359261760),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(5), ast.NumVal(1.6307305501),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(6), ast.NumVal(0.0866147265),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(7), ast.NumVal(-0.0726894150),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(8), ast.NumVal(0.0435440193),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(9), ast.NumVal(-0.0077364839),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(10), ast.NumVal(0.2902775116),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(11), ast.NumVal(0.0229879957),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(12), ast.NumVal(-0.7614706871),
ast.BinNumOpType.MUL),
]
expected = assemblers.utils.apply_op_to_expressions(
ast.BinNumOpType.ADD, ast.NumVal(0.0), *feature_weight_mul)
assert utils.cmp_exprs(actual, expected)
def test_exp_output_transform():
estimator = lightgbm.LGBMRegressor(n_estimators=2,
random_state=1,
max_depth=1,
objective="poisson")
utils.get_regression_model_trainer()(estimator)
assembler = assemblers.LightGBMModelAssembler(estimator)
actual = assembler.assemble()
expected = ast.ExpExpr(
ast.BinNumExpr(
ast.IfExpr(
ast.CompExpr(ast.FeatureRef(5), ast.NumVal(6.8375),
ast.CompOpType.GT), ast.NumVal(3.1481886430),
ast.NumVal(3.1123367238)),
ast.IfExpr(
ast.CompExpr(ast.FeatureRef(12), ast.NumVal(9.725),
ast.CompOpType.GT), ast.NumVal(-0.0113689739),
ast.NumVal(0.0153551274)), ast.BinNumOpType.ADD))
assert utils.cmp_exprs(actual, expected)
def test_statsmodels_processmle():
estimator = utils.StatsmodelsSklearnLikeWrapper(
ProcessMLE,
dict(init=dict(
exog_scale=np.ones(
(len(utils.get_regression_model_trainer().y_train), 2)),
exog_smooth=np.ones(
(len(utils.get_regression_model_trainer().y_train), 2)),
exog_noise=np.ones(
(len(utils.get_regression_model_trainer().y_train), 2)),
time=np.kron(
np.ones(
len(utils.get_regression_model_trainer().y_train) // 3),
np.arange(3)),
groups=np.kron(
np.arange(
len(utils.get_regression_model_trainer().y_train) // 3),
np.ones(3))),
fit=dict(maxiter=1)))
_, __, estimator = utils.get_regression_model_trainer()(estimator)
assembler = assemblers.ProcessMLEModelAssembler(estimator)
actual = assembler.assemble()
feature_weight_mul = [
ast.BinNumExpr(ast.FeatureRef(0), ast.NumVal(-0.0980302102110356),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(1), ast.NumVal(0.04863869398287732),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(2), ast.NumVal(0.009514054355147874),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(3), ast.NumVal(2.977113829322681),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(4), ast.NumVal(-2.6048073854474705),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(5), ast.NumVal(5.887987153279099),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(6), ast.NumVal(-0.008183580358672775),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(7), ast.NumVal(-0.996428929917054),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(8), ast.NumVal(0.1618353156581333),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(9), ast.NumVal(-0.009213049690188308),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(10), ast.NumVal(-0.3634816838591863),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(11), ast.NumVal(0.014700492832969888),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(12), ast.NumVal(-0.4384298738156768),
ast.BinNumOpType.MUL),
]
expected = assemblers.utils.apply_op_to_expressions(
ast.BinNumOpType.ADD, ast.NumVal(0.0), *feature_weight_mul)
assert utils.cmp_exprs(actual, expected)
def test_statsmodels_processmle():
estimator = utils.StatsmodelsSklearnLikeWrapper(
ProcessMLE,
dict(init=dict(
exog_scale=np.ones(
(len(utils.get_regression_model_trainer().y_train), 2)),
exog_smooth=np.ones(
(len(utils.get_regression_model_trainer().y_train), 2)),
exog_noise=np.ones(
(len(utils.get_regression_model_trainer().y_train), 2)),
time=np.kron(
np.ones(
len(utils.get_regression_model_trainer().y_train) // 3),
np.arange(3)),
groups=np.kron(
np.arange(
len(utils.get_regression_model_trainer().y_train) // 3),
np.ones(3))),
fit=dict(maxiter=1)))
_, __, estimator = utils.get_regression_model_trainer()(estimator)
assembler = assemblers.ProcessMLEModelAssembler(estimator)
actual = assembler.assemble()
feature_weight_mul = [
ast.BinNumExpr(ast.FeatureRef(0), ast.NumVal(-0.0915126856),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(1), ast.NumVal(0.0455368812),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(2), ast.NumVal(-0.0092227692),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(3), ast.NumVal(2.8566616798),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(4), ast.NumVal(-2.1208777964),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(5), ast.NumVal(5.9725253309),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(6), ast.NumVal(-0.0061566965),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(7), ast.NumVal(-0.9414114075),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(8), ast.NumVal(0.1522429507),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(9), ast.NumVal(-0.0092123938),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(10), ast.NumVal(-0.3928508764),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(11), ast.NumVal(0.0134405151),
ast.BinNumOpType.MUL),
ast.BinNumExpr(ast.FeatureRef(12), ast.NumVal(-0.4364996490),
ast.BinNumOpType.MUL),
]
expected = assemblers.utils.apply_op_to_expressions(
ast.BinNumOpType.ADD, ast.NumVal(0.0), *feature_weight_mul)
assert utils.cmp_exprs(actual, expected)
