def rforest_grid_tuned(train, target):
clf = RandomForestClassifier(n_estimators=800,
max_depth=6,
min_samples_leaf=6,
max_features=0.33)
try:
source = list2dataframe(train)
except IOError:
source = train
source = SMOTE(source)
# use a full grid over all parameters
param_grid = {"max_depth": [3, None],
"max_features": [1, 3, 10],
"min_samples_split": [1, 3, 10],
"min_samples_leaf": [1, 3, 10],
"bootstrap": [True, False],
"criterion": ["gini", "entropy"]}
source.loc[source[source.columns[-1]] == 0, source.columns[-1]] = False
features = source.columns[:-1]
klass = list(source[source.columns[-1]])
clf = GridSearchCV(clf, param_grid).fit(source[features], klass)
preds = clf.predict(target[target.columns[:-1]])
distr = clf.predict_proba(target[target.columns[:-1]])[:, 1]
return preds, distr
def xgboost_grid_tuned(train, target):
try:
source = list2dataframe(train)
except IOError:
source = train
source = SMOTE(source)
# Tune with grid search
param_grid = {
"n_estimators": [80],#, 40, 20],
"learning_rate": [0.1],
# "max_depth": [4, 6],
# "min_samples_leaf": [3, 5, 9, 17],
# "max_features": [1.0, 0.3, 0.1]
}
clf = GradientBoostingClassifier()
source.loc[source[source.columns[-1]] == 0, source.columns[-1]] = False
features = source.columns[:-1]
klass = list(source[source.columns[-1]])
clf = GridSearchCV(clf, param_grid).fit(source[features], klass)
preds = clf.predict(target[target.columns[:-1]])
distr = clf.predict_proba(target[target.columns[:-1]])[:, 1]
return preds, distr
def rforest(train, target):
clf = RandomForestClassifier(n_estimators=100, random_state=1)
try:
source = list2dataframe(train)
except IOError:
source = train
# source = SMOTE(source)
source.loc[source[source.columns[-1]] == 0, source.columns[-1]] = False
features = source.columns[:-1]
klass = list(source[source.columns[-1]])
clf.fit(source[features], klass)
preds = clf.predict(target[target.columns[:-1]])
distr = clf.predict_proba(target[target.columns[:-1]])[:, 1]
return preds, distr
def xgboost(train, target):
try:
source = list2dataframe(train)
except IOError:
source = train
# source = SMOTE(source)
clf = GradientBoostingClassifier(n_estimators=80,
max_depth=6,
min_samples_leaf=6,
learning_rate=0.085,
subsample=True,
max_features=0.33)
source.loc[source[source.columns[-1]] == 0, source.columns[-1]] = False
features = source.columns[:-1]
klass = list(source[source.columns[-1]])
clf.fit(source[features], klass)
preds = clf.predict(target[target.columns[:-1]])
distr = clf.predict_proba(target[target.columns[:-1]])[:, 1]
preds = [1 if val > 0.77 else 0 for val in distr]
return preds, distr
featureTot = 0
information_gain = []
for i in range(0, len(nz[0])):
if (i != 0 and nz[0][i] != pre):
for notappear in range(pre + 1, nz[0][i]):
information_gain.append(0)
ig = _calIg()
information_gain.append(ig)
pre = nz[0][i]
classCnt = {}
featureTot = 0
featureTot = featureTot + 1
yclass = y[nz[1][i]]
if yclass not in classCnt:
classCnt[yclass] = 1
else:
classCnt[yclass] = classCnt[yclass] + 1
ig = _calIg()
information_gain.append(ig)
return np.asarray(information_gain)
if __name__ == "__main__":
data = DefectData.get_all_projects()["Apache"]
test_data = list2dataframe(data["ant"].data)
indep_var = test_data[test_data.columns[:-1]]
depen_var = test_data[test_data.columns[-1]]
information_gain(indep_var.values, depen_var.values)
set_trace()