'values': [train[col].max()]
}
for col in continuous + discrete
})
# BINNER_CONFIG = [{ col: {'bins': 3} for col in continuous + discrete },
# # { col: {'bins': 5} for col in continuous + discrete },
# { col: {'bins': 7} for col in continuous + discrete },
# { col: {'values': [train[col].max()]} for col in continuous + discrete }]
top_cont = [
'LotFrontage', 'BsmtFinSF1', 'MasVnrArea', '1stFlrSF',
'GarageArea', 'TotalBsmtSF', 'GrLivArea'
]
BOX_COX = BOX_COX_HO
elif dataset == 'heart':
data, labels, continuous, discrete, dummy, categorical, target, missing = get_heart(
missing=MISSING)
train = data.drop(target, axis=1)
cv = KFold(5, shuffle=True, random_state=0)
scorer = error_rate
predictors = [
LogisticRegression(),
SVC(),
RandomForestClassifier(),
DecisionTreeClassifier(),
KNeighborsClassifier(n_neighbors=5),
]
# BINNER_CONFIG = { col: {'bins': 3} for col in continuous + discrete }
binner = CustomBinner(
{col: {
'bins': 3
}
def get_test_config_heart(missing=True):
data, labels, continuous, discrete, dummy, categorical, target, missing = get_heart(
test=False, missing=missing)
test_data, test_labels = get_heart(test=True, missing=missing)[0:2]
test = test_data.drop(target, axis=1)
scorer = error_rate
one_hot = CustomOneHotEncoder(columns=categorical)
model = Pipeline([
('onehot', one_hot),
('clipper', None),
('binner', None),
('binner2', None),
('simple_imputer', None),
('zero_filler', ZeroFiller()), # just in case there are any left
('main_imputer', None),
('dropper', FeatureDropper(drop=[])),
('poly', None),
('combinations', None),
('boxcox', None),
('scaler', None),
('reduce_dim', None),
('predictor', None)
])
params = {
'DecisionTreeClassifier_base': {
'params': {
'predictor':
DecisionTreeClassifier(max_depth=None),
'scaler':
None,
'simple_imputer':
FillNaTransformer(
from_dict={},
mean=['trestbps', 'chol', 'thalach', 'oldpeak'],
median=[],
nan_flag=[],
zero=[])
},
'score': 0.1974390243902439,
'std': 0.0756691348271984
},
'KNeighborsClassifier_base': {
'params': {
'predictor':
KNeighborsClassifier(n_neighbors=7
# ,n_jobs=7
),
'scaler':
RobustScaler(),
'simple_imputer':
FillNaTransformer(
from_dict={},
mean=[],
median=['trestbps', 'chol', 'thalach', 'oldpeak'],
nan_flag=[],
zero=[])
},
'score': 0.1924390243902439,
'std': 0.04087385740197896
},
'LogisticRegression_base': {
'params': {
'predictor':
LogisticRegression(
# n_jobs=7,
),
'scaler':
None,
'simple_imputer':
FillNaTransformer(
from_dict={},
mean=['trestbps', 'chol', 'thalach', 'oldpeak'],
median=[],
nan_flag=[],
zero=[])
},
'score': 0.1825609756097561,
'std': 0.04141604180434009
},
# 'XGBClassifier_base': {'params': {'predictor': XGBClassifier(
# base_score=0.5,
# # n_jobs=7,
#
# colsample_bytree=0.8, learning_rate=0.07,
# max_depth=7, n_estimators=200,),
# 'scaler': None,
# 'simple_imputer': FillNaTransformer(from_dict={}, mean=[], median=[], nan_flag=[],
# zero=['trestbps', 'chol', 'thalach', 'oldpeak'])},
# 'score': 0.16743902439024388,
# 'std': 0.04176646782554455},
'DecisionTreeClassifier_best': {
'params': {
'binner2':
CustomBinner(
configuration={
'chol': {
'bins': 3
},
'thalach': {
'bins': 3
},
'oldpeak': {
'bins': 3
},
'trestbps': {
'bins': 3
},
'age': {
'bins': 3
},
'slope': {
'bins': 3
},
'ca': {
'bins': 3
}
}),
'boxcox':
None,
'clipper':
OutliersClipper(
columns=['chol', 'thalach', 'oldpeak', 'trestbps']),
'combinations':
FeatureProduct(
columns=['chol', 'thalach', 'oldpeak', 'trestbps']),
'dropper__drop':
['trestbps_nan', 'chol_nan', 'thalach_nan', 'oldpeak_nan'],
'main_imputer':
HotDeckFullImputer(col_k_pairs=[('trestbps', None),
('chol', None),
('thalach', None),
('oldpeak', None)],
default_k=7),
'poly':
None,
'predictor':
DecisionTreeClassifier(max_depth=4),
'reduce_dim':
None,
'scaler':
None,
'simple_imputer':
FillNaTransformer(
from_dict={},
mean=[],
median=[],
nan_flag=['trestbps', 'chol', 'thalach', 'oldpeak'],
zero=['trestbps', 'chol', 'thalach', 'oldpeak'])
},
'score': 0.14780487804878048,
'std': 0.03090350740255695
},
'LogisticRegression_best': {
'params': {
'binner2':
None,
'boxcox':
BoxCoxTransformer(lambdas_per_column={
'chol': 0,
'thalach': 2,
'trestbps': 0
}),
'clipper':
OutliersClipper(
columns=['chol', 'thalach', 'oldpeak', 'trestbps']),
'combinations':
None,
'dropper__drop': [],
'main_imputer':
ModelBasedFullImputer(
columns=['trestbps', 'chol', 'thalach', 'oldpeak'],
model=LinearRegression(
# n_jobs=7
)),
'poly':
PolynomialsAdder(powers_per_column={
'chol': [2],
'thalach': [2],
'oldpeak': [2],
'trestbps': [2]
}),
'predictor':
LogisticRegression(),
'reduce_dim':
PCA(n_components=10),
'scaler':
None,
'simple_imputer':
FillNaTransformer(
from_dict={},
mean=['trestbps', 'chol', 'thalach', 'oldpeak'],
median=[],
nan_flag=['trestbps', 'chol', 'thalach', 'oldpeak'],
zero=[])
},
'score': 0.14280487804878048,
'std': 0.03915450868377355
},
# 'XGBClassifier_best': {'params':
# {
# 'binner2': CustomBinner(configuration={'chol': {'bins': 3}, 'thalach': {'bins': 3}, 'oldpeak': {'bins': 3}, 'trestbps': {'bins': 3}, 'age': {'bins': 3}, 'slope': {'bins': 3}, 'ca': {'bins': 3}},
# drop=False, nan=False),
# 'boxcox': BoxCoxTransformer(lambdas_per_column={'chol': 0, 'thalach': 2, 'trestbps': 0}),
# 'clipper': OutliersClipper(columns=['chol', 'thalach', 'oldpeak', 'trestbps']),
# 'combinations': None,
# 'dropper__drop': ['trestbps_nan', 'chol_nan', 'thalach_nan', 'oldpeak_nan'],
# 'main_imputer': HotDeckFullImputer(col_k_pairs=[('trestbps', None), ('chol', None), ('thalach', None), ('oldpeak', None)],
# default_k=7),
# 'poly': None,
# 'predictor': XGBClassifier(
# # n_jobs=7,
# base_score=0.5,
# colsample_bytree=0.8, learning_rate=0.07,
# max_depth=7, n_estimators=200,),
# 'reduce_dim': SelectFromModel(estimator=LogisticRegression(C=0.999, penalty='l1',
# # n_jobs=7
# )),
# 'scaler': None,
# 'simple_imputer': FillNaTransformer(from_dict={},
# mean=['trestbps', 'chol', 'thalach', 'oldpeak'], median=[],
# nan_flag=['trestbps', 'chol', 'thalach', 'oldpeak'], zero=[])},
# 'score': 0.15243902439024387,
# 'std': 0.04655758333858798}
}
return data, test, test_labels, scorer, model, params, target
