def fixture_learners_data(breast_cancer_data, boston_data,
boston_survival_data):
"""
Returns:
A list of iterables,
each iterable containing a fitted model and
X data and the predictions for the X_data
"""
models_data = []
X_class_train, _, Y_class_train, _ = breast_cancer_data
ngb = NGBClassifier(verbose=False, n_estimators=10)
ngb.fit(X_class_train, Y_class_train)
models_data.append((ngb, X_class_train, ngb.predict(X_class_train)))
X_reg_train, _, Y_reg_train, _ = boston_data
ngb = NGBRegressor(verbose=False, n_estimators=10)
ngb.fit(X_reg_train, Y_reg_train)
models_data.append((ngb, X_reg_train, ngb.predict(X_reg_train)))
X_surv_train, _, T_surv_train, E_surv_train, _ = boston_survival_data
ngb = NGBSurvival(verbose=False, n_estimators=10)
ngb.fit(X_surv_train, T_surv_train, E_surv_train)
models_data.append((ngb, X_surv_train, ngb.predict(X_surv_train)))
ngb = NGBRegressor(Dist=MultivariateNormal(2), n_estimators=10)
ngb.fit(X_surv_train, np.vstack([T_surv_train, E_surv_train]).T)
models_data.append((ngb, X_surv_train, ngb.predict(X_surv_train)))
return models_data
def test_classification():
from sklearn.datasets import load_breast_cancer
from sklearn.metrics import roc_auc_score, log_loss
data, target = load_breast_cancer(True)
x_train, x_test, y_train, y_test = train_test_split(data,
target,
test_size=0.2,
random_state=42)
ngb = NGBClassifier(Dist=Bernoulli, verbose=False)
ngb.fit(x_train, y_train)
preds = ngb.predict(x_test)
score = roc_auc_score(y_test, preds)
assert score >= 0.95
preds = ngb.predict_proba(x_test)
score = log_loss(y_test, preds)
assert score <= 0.20
score = ngb.score(x_test, y_test)
assert score <= 0.20
dist = ngb.pred_dist(x_test)
assert isinstance(dist, Bernoulli)
score = roc_auc_score(y_test, preds[:, 1])
assert score >= 0.95
def test_classification(breast_cancer_data):
from sklearn.metrics import roc_auc_score, log_loss
x_train, x_test, y_train, y_test = breast_cancer_data
ngb = NGBClassifier(Dist=Bernoulli, verbose=False)
ngb.fit(x_train, y_train)
preds = ngb.predict(x_test)
score = roc_auc_score(y_test, preds)
# loose score requirement so it isn't failing all the time
assert score >= 0.85
preds = ngb.predict_proba(x_test)
score = log_loss(y_test, preds)
assert score <= 0.30
score = ngb.score(x_test, y_test)
assert score <= 0.30
dist = ngb.pred_dist(x_test)
assert isinstance(dist, Bernoulli)
score = roc_auc_score(y_test, preds[:, 1])
assert score >= 0.85
class myNGBoostClassifier:
def make(self , params ):
self.model = NGBClassifier(**params )
return self
def fit(self, xtrain, ytrain, xtest=None, ytest=None, fit_params={}):
if type(xtrain) == pd.core.frame.DataFrame:
xtrain = xtrain.values
ytrain = ytrain.values
if type(xtest) != type(None) and type(ytest) != type(None):
xtest = xtest.values
ytest = ytest.values
if type(xtest) == type(None) or type(ytest) == type(None) :
self.model.fit( xtrain , ytrain , **fit_params )
else:
self.model.fit( xtrain , ytrain , X_val = xtest , Y_val = ytest ,**fit_params )
def predict(self , xs ):
return self.model.predict(xs)
def predict_proba(self, xs):
if len(xs.shape) == 1:
return self.model.predict_proba(xs.reshape(1,-1))
else:
return self.model.predict_proba(xs)
def test_bernoulli(learner, breast_cancer_data: Tuple4Array):
X_cls_train, X_cls_test, Y_cls_train, Y_cls_test = breast_cancer_data
# test early stopping features
# test other args, n_trees, LR, minibatching- args as fixture
ngb = NGBClassifier(Dist=Bernoulli, Score=LogScore, Base=learner, verbose=False)
ngb.fit(X_cls_train, Y_cls_train)
y_pred = ngb.predict(X_cls_test)
y_prob = ngb.predict_proba(X_cls_test)
y_dist = ngb.pred_dist(X_cls_test)
def test_categorical(k: int, learner, breast_cancer_data: Tuple4Array):
X_train, X_test, y_train, _ = breast_cancer_data
dist = k_categorical(k)
y_train = np.random.randint(0, k, (len(y_train)))
# test early stopping features
ngb = NGBClassifier(Dist=dist, Score=LogScore, Base=learner, verbose=False)
ngb.fit(X_train, y_train)
y_pred = ngb.predict(X_test)
y_prob = ngb.predict_proba(X_test)
y_dist = ngb.pred_dist(X_test)
def test_bernoulli(self, learners, cls_data): X_cls_train, X_cls_test, Y_cls_train, Y_cls_test = cls_data for Learner in learners: # test early stopping features # test other args, n_trees, LR, minibatching- args as fixture ngb = NGBClassifier(Dist=Bernoulli, Score=LogScore, Base=Learner, verbose=False) ngb.fit(X_cls_train, Y_cls_train) y_pred = ngb.predict(X_cls_test) y_prob = ngb.predict_proba(X_cls_test) y_dist = ngb.pred_dist(X_cls_test)
def test_categorical(self, learners, cls_data): X_cls_train, X_cls_test, Y_cls_train, Y_cls_test = cls_data for K in [2,4,7]: Dist = k_categorical(K) Y_cls_train = np.random.randint(0,K,(len(Y_cls_train))) for Learner in learners: # test early stopping features ngb = NGBClassifier(Dist=Dist, Score=LogScore, Base=Learner, verbose=False) ngb.fit(X_cls_train, Y_cls_train) y_pred = ngb.predict(X_cls_test) y_prob = ngb.predict_proba(X_cls_test) y_dist = ngb.pred_dist(X_cls_test)
def NGBoost(self, args): ## Natural gradient Boosting
logger.info("Running Natural Gradient Boosting ... ")
## https://stanfordmlgroup.github.io/ngboost/1-useage.html
from ngboost.learners import default_tree_learner
from ngboost.distns import k_categorical, Bernoulli ##Classifier
from ngboost.distns import Exponential, Normal, LogNormal ## Regressor
from ngboost.scores import MLE, LogScore, CRPScore
## Base Learner
from sklearn.tree import DecisionTreeRegressor, DecisionTreeClassifier
# NGBoost
## Comment: If error with singular matrix, increase size of input data from 0.05 to 0.15
if args.predictor.lower() == 'classifier':
from ngboost import NGBClassifier as ngb
learner = DecisionTreeRegressor(criterion='friedman_mse',
max_depth=6,
random_state=SEED)
ngb = ngb(Base=learner,
n_estimators=2000,
Score=MLE,
Dist=Bernoulli,
random_state=SEED)
elif args.predictor.lower() == 'regressor':
from ngboost import NGBRegressor as ngb
learner = DecisionTreeRegressor(criterion='friedman_mse',
max_depth=3,
random_state=SEED)
ngb = ngb(Base=default_tree_learner,
Dist=Exponential,
Score=LogScore,
learning_rate=0.01,
minibatch_frac=0.6,
col_sample=0.6)
## Fit model
ngb.fit(self.X_train, np.asarray(self.y_train).astype(int))
## Predict the labels
self.y_pred = ngb.predict(self.X_data)
if args.predictor.lower() == 'regressor':
self.y_pred = logistic.cdf(self.y_pred)
self.data['boosting_score'] = self.y_pred
self.model = ngb
return self
from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split
from sklearn.metrics import confusion_matrix, classification_report
from ngboost import NGBClassifier
from ngboost.distns import k_categorical
if __name__ == "__main__":
X, y = load_breast_cancer(True)
y[0:
15] = 2 # artificially make this a 3-class problem instead of a 2-class problem
X_train, X_test, Y_train, Y_test = train_test_split(X, y, test_size=0.2)
ngb = NGBClassifier(Dist=k_categorical(
3)) # tell ngboost that there are 3 possible outcomes
ngb.fit(X_train, Y_train) # Y should have only 3 values: {0,1,2}
# predicted probabilities of class 0, 1, and 2 (columns) for each observation (row)
preds_proba = ngb.predict_proba(X_test)
preds = ngb.predict(X_test)
print(confusion_matrix(Y_test, preds))
print(classification_report(Y_test, preds))