def getLogisticRegressionClf(self, X, Y):
clfName = "Logistic_Regression"
## http://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html
clf = LogisticRegression(
penalty='l2',
dual=False,
tol=0.0001,
C=1.0,
fit_intercept=True,
intercept_scaling=1,
class_weight=None,
random_state=None,
solver='liblinear',
max_iter=100,
multi_class='ovr',
verbose=0,
)
if self._gridSearchFlag == True:
log(clfName + " start searching param...")
param_dist = {
"penalty": ['l2', 'l2'],
"C": sp_randf(1.0,3.0),
"solver": [ 'lbfgs', 'liblinear'],
}
clf = self.doRandomSearch(clfName, clf, param_dist, X, Y)
else:
clf.fit(X,Y)
return clf
def getRandomForestClf(self, X, Y, param_list):
clfName = "Random_Forest"
## http://scikit-learn.org/stable/modules/generated/sklearn.ensemble.RandomForestClassifier.html
clf = rf(n_estimators=300, max_depth=None, min_samples_split=1, random_state=0, bootstrap=True, oob_score = True)
if self._gridSearchFlag == True:
log(clfName + " start searching param...")
tmpLowDepth = 8
tmpHighDepth = 30
param_dist = {
"max_depth": sp_randint(tmpLowDepth, tmpHighDepth),
"max_features": sp_randf(0,1),
"min_samples_split": sp_randint(1, 11),
"min_samples_leaf": sp_randint(1, 11),
"criterion": ["gini", "entropy"],
"n_estimators" : sp_randint(5, 12),
}
clf = self.doRandomSearch(clfName, clf, param_dist, X, Y)
else:
if not param_list is None:
clf = rf()
clf.set_params(**param_list)
clf.fit(X,Y)
return clf
def getLogisticRegressionClf(self, X, Y):
clfName = "Logistic_Regression"
## http://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html
clf = LogisticRegression(
penalty='l2',
dual=False,
tol=0.0001,
C=1.0,
fit_intercept=True,
intercept_scaling=1,
class_weight=None,
random_state=None,
solver='liblinear',
max_iter=100,
multi_class='ovr',
verbose=0,
)
if self._gridSearchFlag == True:
log(clfName + " start searching param...")
param_dist = {
"penalty": ['l2', 'l2'],
"C": sp_randf(1.0, 3.0),
"solver": ['lbfgs', 'liblinear'],
}
clf = self.doRandomSearch(clfName, clf, param_dist, X, Y)
return clf
def getRandomForestClf(self, X, Y):
clfName = "Random_Forest"
## http://scikit-learn.org/stable/modules/generated/sklearn.ensemble.RandomForestClassifier.html
clf = rf(n_estimators=300,
max_depth=None,
min_samples_split=1,
random_state=0,
bootstrap=True,
oob_score=True)
if self._gridSearchFlag == True:
log(clfName + " start searching param...")
tmpLowDepth = 10
tmpHighDepth = 50
param_dist = {
"max_depth": sp_randint(tmpLowDepth, tmpHighDepth),
"max_features": sp_randf(0, 1),
"min_samples_split": sp_randint(1, 11),
"min_samples_leaf": sp_randint(1, 11),
"criterion": ["gini", "entropy"],
"n_estimators": sp_randint(100, 300),
}
clf = self.doRandomSearch(clfName, clf, param_dist, X, Y)
return clf
def getExtraTressClf(self, X, Y):
clfName = "Extra_Trees"
## http://scikit-learn.org/stable/modules/generated/sklearn.ensemble.ExtraTreesClassifier.html
clf = ExtraTreesClassifier(n_estimators=10,
criterion='gini',
max_depth=None,
min_samples_split=2,
min_samples_leaf=1,
min_weight_fraction_leaf=0.0,
max_features='auto',
max_leaf_nodes=None,
bootstrap=False,
oob_score=False,
n_jobs=1,
random_state=None,
verbose=0,
warm_start=False,
class_weight=None)
if self._gridSearchFlag == True:
log(clfName + " start searching param...")
tmpLowDepth = int(len(X.columns) * 0.7)
tmpHighDepth = int(len(X.columns))
param_dist = {
"max_depth": sp_randint(tmpLowDepth, tmpHighDepth),
"max_features": sp_randf(0, 1),
"min_samples_split": sp_randint(1, 11),
"min_samples_leaf": sp_randint(1, 11),
"bootstrap": [True, True],
"criterion": ["gini", "entropy"],
"oob_score": [True, True],
"n_estimators": sp_randint(100, 300),
}
clf = self.doRandomSearch(clfName, clf, param_dist, X, Y)
return clf
test_parse_str = sys.argv[2] # "*s1024_pext_0_stru_his_txt_features.csv"
output_prefix = sys.argv[3]
basic_features = [] # do not include patch location
lin_svm_params = {"C": [1.0, 10.0, 100.0]}
rf_params = {"n_estimators": [10, 30, 50, 100],
"max_depth": [10, 20, 40, None],
"min_samples_leaf": [5, 20, 50, 100],
"max_features": [0.2, 0.5, 'auto']}
rf_param_dist = {"n_estimators": sp_randint(40, 100),
"max_depth": sp_randint(10, 25),
"min_samples_leaf": sp_randint(1, 10),
"min_samples_split": sp_randint(4, 15),
"max_features": sp_randf(loc=0.1, scale=0.45)
}
knn_params = {"n_neighbors": [3, 5, 10, 40, 60]}
label_dict = {'NO': -1, 'TU': 1, 'BO': 1, 'OT': 1}
algorithms = [#(LinearSVC(), lin_svm_params, "Linear SVM"),
(RandomForestClassifier(class_weight="balanced", oob_score=False, n_jobs=4,
bootstrap=True, criterion='gini'), rf_param_dist, "RandomForest", "RAND"),
# (KNeighborsClassifier(), knn_params, "KNN Clf")
]
add_features = [#["sprel_", "sp_"],
# ["tx_", "wx_"],
# ["wx_cE", "wx_cH", "sprel_", "sp_"],
# ["HIST_", "wx_cE", "wx_cH"],
["hist_u", "hist_cG", "wx_", "sp_num", "sp_mean", "rel_area", "scale"],