def feature_selection(self,features_importance_print=False):
clf = ExtraTreesClassifier()
features_available = self.used_features()
clf.max_features = len(features_available)
clf = clf.fit(self.training_data[features_available].values, self.training_data["label"])
for importance in clf.feature_importances_:
index = np.where(clf.feature_importances_==importance)[0][0]
self.features_importance_dict[importance] =features_available[index]
if features_importance_print:
for feature_score in sorted(self.features_importance_dict.keys(),reverse=True):
print self.features_importance_dict[feature_score],feature_score
param_grid = tuple([n_vals, n_minleaf, n_minsplit, n_maxfeat])
param_grid = list(product(*param_grid))
# storage structure for forecasts
mvalid = np.zeros((xtrain.shape[0], len(param_grid)))
mfull = np.zeros((xtest.shape[0], len(param_grid)))
## build 2nd level forecasts
for i in range(len(param_grid)):
print "processing parameter combo:", i
# configure model with j-th combo of parameters
x = param_grid[i]
model.n_estimators = x[0]
model.min_samples_leaf = x[1]
model.min_samples_split = x[2]
model.max_features = x[3]
# loop over folds
for j in range(0, n_folds):
idx0 = np.where(fold_index != j)
idx1 = np.where(fold_index == j)
x0 = np.array(xtrain)[idx0, :][0]
x1 = np.array(xtrain)[idx1, :][0]
y0 = np.array(y_train)[idx0]
y1 = np.array(y_train)[idx1]
# fit the model on observations associated with subject whichSubject in this fold
model.fit(x0, y0)
mvalid[idx1, i] = model.predict_proba(x1)[:, 1]
y_pre = model.predict_proba(x1)[:, 1]
scores = roc_auc_score(y1, y_pre)
f1.write('\nmodel type:'); f1.write(str(model_type))
f1.write('\nseed value: '); f1.write(str(seed_value))
f1.write('\nparameter grid \n'); f1.write(str(param_grid) )
f1.close()
# storage structure for forecasts
mvalid = np.zeros((xtrain.shape[0],len(param_grid)))
mfull = np.zeros((xtest.shape[0],len(param_grid)))
## build 2nd level forecasts
for i in range(len(param_grid)):
print "processing parameter combo:", i
# configure model with j-th combo of parameters
x = param_grid[i]
model.max_depth = int(x[0])
model.max_features = int(x[1])
model.max_features = int(x[2])
model.min_samples_leaf = int(x[3])
model.min_weight_fraction_leaf = x[4]
model.n_estimators = int(x[5])
# loop over folds
for j in range(0,n_folds):
idx0 = np.where(fold_index != j)
idx1 = np.where(fold_index == j)
x0 = np.array(xtrain)[idx0,:][0];
x1 = np.array(xtrain)[idx1,:][0]
y0 = np.array(y)[idx0];
y1 = np.array(y)[idx1]
model.fit(x0, y0)
def init_hyperparameters(self, trial, X, y):
self.name = id_name('SelectKBest')
self.k_fraction = trial.suggest_uniform(self.name + 'k_fraction', 0.0,
1.0)
self.sparse = False
score_func = trial.suggest_categorical(self.name + 'score_func', [
'chi2', 'f_classif', 'mutual_info', 'ExtraTreesClassifier',
'LinearSVC'
])
if score_func == "chi2":
self.score_func = sklearn.feature_selection.chi2
elif score_func == "f_classif":
self.score_func = sklearn.feature_selection.f_classif
elif score_func == "mutual_info":
self.score_func = sklearn.feature_selection.mutual_info_classif
elif score_func == 'ExtraTreesClassifier':
new_name = self.name + '_' + score_func + '_'
model = ExtraTreesClassifier()
model.n_estimators = 100
model.criterion = trial.suggest_categorical(
new_name + "criterion", ["gini", "entropy"])
model.max_features = trial.suggest_uniform(
new_name + "max_features", 0, 1)
model.max_depth = None
model.max_leaf_nodes = None
model.min_samples_split = trial.suggest_int(new_name +
"min_samples_split",
2,
20,
log=False)
model.min_samples_leaf = trial.suggest_int(new_name +
"min_samples_leaf",
1,
20,
log=False)
model.min_weight_fraction_leaf = 0.
model.min_impurity_decrease = 0.
model.bootstrap = trial.suggest_categorical(
new_name + "bootstrap", [True, False])
self.score_func = functools.partial(
model_score, estimator=model) #bindFunction1(model)
elif score_func == 'LinearSVC':
new_name = self.name + '_' + score_func + '_'
model = sklearn.svm.LinearSVC()
model.penalty = "l1"
model.loss = "squared_hinge"
model.dual = False
model.tol = trial.suggest_loguniform(new_name + "tol", 1e-5, 1e-1)
model.C = trial.suggest_loguniform(new_name + "C", 0.03125, 32768)
model.multi_class = "ovr"
model.fit_intercept = True
model.intercept_scaling = 1
self.score_func = functools.partial(model_score, estimator=model)
f1.write(str(seed_value))
f1.write('\nparameter grid \n')
f1.write(str(param_grid))
f1.close()
# storage structure for forecasts
mvalid = np.zeros((xtrain.shape[0], len(param_grid)))
mfull = np.zeros((xtest.shape[0], len(param_grid)))
## build 2nd level forecasts
for i in range(len(param_grid)):
print "processing parameter combo:", i
# configure model with j-th combo of parameters
x = param_grid[i]
model.max_depth = int(x[0])
model.max_features = int(x[1])
model.max_features = int(x[2])
model.min_samples_leaf = int(x[3])
model.min_weight_fraction_leaf = x[4]
model.n_estimators = int(x[5])
# loop over folds
for j in range(0, n_folds):
idx0 = np.where(fold_index != j)
idx1 = np.where(fold_index == j)
x0 = np.array(xtrain)[idx0, :][0]
x1 = np.array(xtrain)[idx1, :][0]
y0 = np.array(y)[idx0]
y1 = np.array(y)[idx1]
model.fit(x0, y0)
param_grid = tuple([n_vals, n_minleaf, n_minsplit, n_maxfeat])
param_grid = list(product(*param_grid))
# storage structure for forecasts
mvalid = np.zeros((xtrain.shape[0],len(param_grid)))
mfull = np.zeros((xtest.shape[0],len(param_grid)))
## build 2nd level forecasts
for i in range(len(param_grid)):
print "processing parameter combo:", i
# configure model with j-th combo of parameters
x = param_grid[i]
model.n_estimators = x[0]
model.min_samples_leaf = x[1]
model.min_samples_split = x[2]
model.max_features = x[3]
# loop over folds
for j in range(0,n_folds):
idx0 = np.where(fold_index != j)
idx1 = np.where(fold_index == j)
x0 = np.array(xtrain)[idx0,:][0];
x1 = np.array(xtrain)[idx1,:][0]
y0 = np.array(y_train)[idx0];
y1 = np.array(y_train)[idx1]
# fit the model on observations associated with subject whichSubject in this fold
model.fit(x0, y0)
mvalid[idx1,i] = model.predict_proba(x1)[:,1]
y_pre = model.predict_proba(x1)[:,1]
scores = roc_auc_score(y1,y_pre)