def use_debug_parameters(self, reduced_selected_features):
# Define parameters as an array of dicts in case different parameters are used for different optimizations
params_debug = [
{
'scaler': [StandardScaler()],
'sampling':
[modelutil.Nosampler(),
SMOTE(), SMOTEENN(),
ADASYN()],
'feat__cols': reduced_selected_features[0:2],
'model__kernel': ['linear'],
'model__C': [0.1, 1, 10],
'model__gamma': [0.1, 1, 10],
},
{
'scaler': [StandardScaler(), Normalizer()],
'sampling': [modelutil.Nosampler()],
'feat__cols': reduced_selected_features[0:1],
'model__C': [1], # default C=1
'model__kernel': ['rbf'],
'model__gamma': [1]
# Only relevant in rbf, default='auto'=1/n_features
}
]
return params_debug
def use_debug_parameters(self, reduced_selected_features):
### XGBOOST CODE start
params_debug = [{
'scaler': [StandardScaler()],
'sampling': [modelutil.Nosampler(),
SMOTE(),
SMOTEENN(),
ADASYN()],
'feat__cols':
reduced_selected_features[0:2],
'model__nthread':
[4], # when use hyperthread, xgboost may become slower
'model__objective': ['binary:logistic'],
'model__learning_rate': [0.05, 0.5], # so called `eta` value
'model__max_depth': [6, 7, 8],
'model__min_child_weight': [11],
'model__silent': [1],
'model__subsample': [0.8],
'model__colsample_bytree': [0.7],
'model__n_estimators':
[5, 10], # number of trees, change it to 1000 for better results
'model__missing': [-999],
'model__seed': [1337]
}]
return params_debug
def use_parameters(self, X_train, selected_features):
"""
Default Parameter
"""
test_scaler = [
StandardScaler(),
RobustScaler(),
QuantileTransformer(),
Normalizer()
]
test_sampling = [
modelutil.Nosampler(),
ClusterCentroids(),
RandomUnderSampler(),
# NearMiss(version=1),
# EditedNearestNeighbours(),
# AllKNN(),
# CondensedNearestNeighbour(random_state=0),
# InstanceHardnessThreshold(random_state=0,
# estimator=LogisticRegression(solver='lbfgs', multi_class='auto')),
RandomOverSampler(random_state=0),
SMOTE(),
BorderlineSMOTE(),
SMOTEENN(),
SMOTETomek(),
ADASYN()
]
test_C = [1e-3, 1e-2, 1e-1, 1e0, 1e1, 1e2, 1e3]
test_C_linear = [1e-3, 1e-2, 1e-1, 1e0, 1e1, 1e2]
# gamma default parameters
param_scale = 1 / (X_train.shape[1] * np.mean(X_train.var()))
parameters = [{
'scaler': test_scaler,
'sampling': test_sampling,
'feat__cols': selected_features,
'model__C': test_C_linear, # default C=1
'model__kernel': ['linear']
}]
# If no missing values, only one imputer strategy shall be used
if X_train.isna().sum().sum() > 0:
parameters['imputer__strategy'] = [
'mean', 'median', 'most_frequent'
]
print("Missing values used. Test different imputer strategies")
else:
print("No missing values. No imputer necessary")
print("Selected Parameters: ", parameters)
# else:
print("Parameters defined in the input: ", parameters)
return parameters
def create_pipeline(self):
pipe_run = Pipeline([('imputer',
SimpleImputer(missing_values=np.nan,
strategy='median')),
('scaler', StandardScaler()),
('sampling', modelutil.Nosampler()),
('feat', modelutil.ColumnExtractor(cols=None)),
('model', SVC())])
return pipe_run
def create_pipeline(self):
pipe_run = Pipeline([('imputer',
SimpleImputer(missing_values=np.nan,
strategy='median')),
('scaler', StandardScaler()),
('sampling', modelutil.Nosampler()),
('feat', modelutil.ColumnExtractor(cols=None)),
('model',
XGBClassifier(use_label_encoder=False,
eval_metric='logloss'))])
return pipe_run
def use_debug_parameters(self, reduced_selected_features):
# Define parameters as an array of dicts in case different parameters are used for different optimizations
params_debug = [{
'scaler': [StandardScaler()],
'sampling': [modelutil.Nosampler(),
SMOTE(),
SMOTEENN(),
ADASYN()],
'feat__cols':
reduced_selected_features[0:2],
'model__var_smoothing':
np.logspace(0, -9, num=100)
}]
return params_debug
def use_debug_parameters(self, reduced_selected_features):
# Define parameters as an array of dicts in case different parameters are used for different optimizations
params_debug = [{
'scaler': [StandardScaler()],
'sampling': [modelutil.Nosampler(),
SMOTE(),
SMOTEENN(),
ADASYN()],
'feat__cols':
reduced_selected_features[0:2],
'model__n_neighbors': [3, 5],
'model__weights': ['uniform', 'distance']
}]
return params_debug
def create_pipeline(self):
n_jobs = multiprocessing.cpu_count() - 1
n_jobs = 10
print("Number of CPUs: {}. Using {}".format(
multiprocessing.cpu_count(), n_jobs))
pipe_run = Pipeline([('imputer',
SimpleImputer(missing_values=np.nan,
strategy='median')),
('scaler', StandardScaler()),
('sampling', modelutil.Nosampler()),
('feat', modelutil.ColumnExtractor(cols=None)),
('model',
XGBClassifier(use_label_encoder=False,
eval_metric='logloss',
n_jobs=n_jobs))])
return pipe_run
def run_basic_svm(X_train,
y_train,
selected_features,
scorers,
refit_scorer_name,
subset_share=0.1,
n_splits=5,
parameters=None):
'''Run an extensive grid search over all parameters to find the best parameters for SVM Classifier.
The search shall be done only with a subset of the data. Default subset is 0.1. Input is training and test data.
subset_share=0.1
'''
# Create a subset to train on
print("[Step 1]: Create a data subset")
subset_min = 300 # Minimal subset is 100 samples.
if subset_share * X_train.shape[0] < subset_min:
number_of_samples = subset_min
print("minimal number of samples used: ", number_of_samples)
else:
number_of_samples = subset_share * X_train.shape[0]
X_train_subset, y_train_subset = modelutil.extract_data_subset(
X_train, y_train, number_of_samples)
print("Got subset sizes X train: {} and y train: {}".format(
X_train_subset.shape, y_train_subset.shape))
print("[Step 2]: Define test parameters")
if parameters is None: # If no parameters have been defined, then do full definition
# Guides used from
# https://www.kaggle.com/evanmiller/pipelines-gridsearch-awesome-ml-pipelines
# Main set of parameters for the grid search run 1: Select scaler, sampler and kernel for the problem
test_scaler = [
StandardScaler(),
RobustScaler(),
QuantileTransformer(),
Normalizer()
]
test_sampling = [
modelutil.Nosampler(),
#ClusterCentroids(),
#RandomUnderSampler(),
#NearMiss(version=1),
#EditedNearestNeighbours(),
#AllKNN(),
#CondensedNearestNeighbour(random_state=0),
#InstanceHardnessThreshold(random_state=0,
# estimator=LogisticRegression(solver='lbfgs', multi_class='auto')),
SMOTE(),
SMOTEENN(),
SMOTETomek(),
ADASYN()
]
test_C = [1e-3, 1e-2, 1e-1, 1e0, 1e1, 1e2, 1e3]
test_C_linear = [1e-3, 1e-2, 1e-1, 1e0, 1e1, 1e2]
# gamma default parameters
param_scale = 1 / (X_train.shape[1] * np.mean(X_train.var()))
parameters = [
{
'scaler': test_scaler,
'sampling': test_sampling,
'feat__cols': selected_features,
'svm__C': test_C, # default C=1
'svm__kernel': ['sigmoid']
},
{
'scaler': test_scaler,
'sampling': test_sampling,
'feat__cols': selected_features,
'svm__C': test_C_linear, # default C=1
'svm__kernel': ['linear']
},
{
'scaler': test_scaler,
'sampling': test_sampling,
'feat__cols': selected_features,
'svm__C': test_C, # default C=1
'svm__kernel': ['poly'],
'svm__degree': [2, 3] # Only relevant for poly
},
{
'scaler': test_scaler,
'sampling': test_sampling,
'feat__cols': selected_features,
'svm__C': test_C, # default C=1
'svm__kernel': ['rbf'],
'svm__gamma':
[param_scale, 1e-3, 1e-2, 1e-1, 1e0, 1e1, 1e2, 1e3]
# Only relevant in rbf, default='auto'=1/n_features
}
]
# If no missing values, only one imputer strategy shall be used
if X_train.isna().sum().sum() > 0:
parameters['imputer__strategy'] = [
'mean', 'median', 'most_frequent'
]
print("Missing values used. Test different imputer strategies")
else:
print("No missing values. No imputer necessary")
print("Selected Parameters: ", parameters)
else:
print("Parameters defined in the input: ", parameters)
# Main pipeline for the grid search
pipe_run1 = Pipeline([('imputer',
SimpleImputer(missing_values=np.nan,
strategy='median')),
('scaler', StandardScaler()),
('sampling', modelutil.Nosampler()),
('feat', modelutil.ColumnExtractor(cols=None)),
('svm', SVC())])
print("Pipeline: ", pipe_run1)
print("Stratified KFold={} used.".format(n_splits))
#INFO: KFold Splitter with shuffle=True to get random values
skf = StratifiedKFold(n_splits=n_splits, random_state=3, shuffle=True)
pipe_run1 = pipe_run1
params_run1 = parameters # params_debug #params_run1
grid_search_run1 = GridSearchCV(pipe_run1,
params_run1,
verbose=2,
cv=skf,
scoring=scorers,
refit=refit_scorer_name,
return_train_score=True,
n_jobs=-1).fit(X_train_subset,
y_train_subset)
#grid_search_run1 = GridSearchCV(pipe_run1, params_run1, verbose=1, cv=skf, scoring=scorers, refit=refit_scorer_name,
# return_train_score=True, iid=True, n_jobs=-1).fit(X_train_subset, y_train_subset)
results_run1 = modelutil.generate_result_table(grid_search_run1,
params_run1,
refit_scorer_name)
print("Result size=", results_run1.shape)
print("Number of NaN results: {}. Replace them with 0".format(
np.sum(results_run1['mean_test_' + refit_scorer_name].isna())))
return grid_search_run1, params_run1, pipe_run1, results_run1
def use_parameters(self, X_train, selected_features):
'''
Returns
-------
'''
test_scaler = [
StandardScaler(),
RobustScaler(),
QuantileTransformer(),
Normalizer()
]
test_sampling = [
modelutil.Nosampler(),
ClusterCentroids(),
RandomUnderSampler(),
# NearMiss(version=1),
# EditedNearestNeighbours(),
# AllKNN(),
# CondensedNearestNeighbour(random_state=0),
# InstanceHardnessThreshold(random_state=0,
# estimator=LogisticRegression(solver='lbfgs', multi_class='auto')),
RandomOverSampler(random_state=0),
SMOTE(),
BorderlineSMOTE(),
SMOTEENN(),
SMOTETomek(),
ADASYN()
]
### XGBOOST
parameters = [{
'scaler': test_scaler,
'sampling': test_sampling,
'feat__cols': selected_features,
'model__nthread':
[4], # when use hyperthread, xgboost may become slower
'model__objective': ['binary:logistic'],
'model__learning_rate': [0.005, 0.01, 0.05, 0.1,
0.5], # so called `eta` value
'model__max_depth': [6, 7, 8],
'model__min_child_weight': [11],
'model__silent': [0],
'model__subsample': [0.8],
'model__colsample_bytree': [0.7],
'model__n_estimators':
[5, 100,
1000], # number of trees, change it to 1000 for better results
'model__missing': [-999],
'model__seed': [1337]
}]
# If no missing values, only one imputer strategy shall be used
if X_train.isna().sum().sum() > 0:
parameters['imputer__strategy'] = [
'mean', 'median', 'most_frequent'
]
print("Missing values used. Test different imputer strategies")
else:
print("No missing values. No imputer necessary")
print("Selected Parameters: ", parameters)
# else:
print("Parameters defined in the input: ", parameters)
### XGBOOST
return parameters