def calibration():
steps = []
for n_estimators, k_folds in product(range(50, 300, 100), [2, 5]):
d = data.ClassificationData(n_samples=1000, n_features=100)
d.target = True
est = step.Call(ensemble,
'RandomForestClassifier',
n_estimators=n_estimators)
fit = model.Fit(inputs=[est, d], return_estimator=True)
fit.target = True
predict = model.Predict(inputs=[fit, d])
predict.target = True
cal = step.Call('sklearn.calibration.CalibratedClassifierCV',
cv=k_folds,
inputs=[MapResults([predict], {'y': None})])
cal_est = model.FitPredict(inputs=[cal, d])
cal_est.target = True
steps.append(cal_est)
return steps
def calibration():
steps = []
for n_estimators, k_folds in product(range(50,300,100), [2,5]):
d = data.ClassificationData(target=True, n_samples=1000, n_features=100)
est = step.Construct('sklearn.ensemble.RandomForestClassifier',
n_estimators=n_estimators, name='estimator')
fit = model.Fit(inputs=[est, d], return_estimator=True, target=True, name='uncalibrated')
predict = model.Predict(inputs=[fit,d], target=True, name='y')
cal = step.Construct('sklearn.calibration.CalibratedClassifierCV', cv=k_folds,
inputs=[predict], inputs_mapping={'y':None}, name='calibrator')
cal_est = model.FitPredict(inputs=[cal, d], target=True, name='calibrated')
metrics = model.PrintMetrics([
{'metric':'baseline'},
{'metric':'precision', 'k':100},
{'metric':'precision', 'k':200},
{'metric':'precision', 'k':300},
], inputs=[cal_est])
steps.append(metrics)
return steps
def test_to_hdf():
d = data.ClassificationData()
h = data.ToHDF(inputs=[d], target=True)
h.setup_dump()
h.execute()
r0, r1 = h.get_result(), d.get_result()
for key in r1.keys():
assert r0[key].equals(r1[key])
def product_model():
d = data.ClassificationData(target=True, n_samples=1000, n_features=100)
est = step.Construct('sklearn.ensemble.RandomForestClassifier',
n_estimators=10, name='estimator')
m1 = model.FitPredict(inputs=[est, d], target=True, name='m1')
m2 = model.FitPredict(inputs=[est, d], target=True, name='m2')
p = model.PredictProduct(inputs=[m1,m2], target=True, inputs_mapping=['m1', 'm2'], name='p')
return p
def n_estimators_search():
d = data.ClassificationData(n_samples=1000, n_features=100)
d.target = True
predict = []
for n_estimators in range(1, 4):
e = step.Construct(_class='sklearn.ensemble.RandomForestClassifier',
n_estimators=n_estimators)
f = model.Fit(inputs=[e, d], return_estimator=True, return_feature_importances=True)
p = model.Predict(inputs=[f, d])
p.target = True
predict.append(p)
return predict
def prediction():
# generate the data including a training and test split
d = data.ClassificationData(n_samples=1000, n_features=100)
d.target = True
# construct a random forest estimator
e = step.Construct(_class='sklearn.ensemble.RandomForestClassifier', n_estimators=1)
e.target = False
# fit the estimator
f = model.Fit(inputs=[e, d], return_estimator=True, return_feature_importances=True)
# make predictions
p = model.Predict(inputs=[f, d])
p.target = True
return p
def product_model():
d = data.ClassificationData(n_samples=1000, n_features=100)
d.target = True
est = step.Call(ensemble, 'RandomForestClassifier', n_estimators=10)
est.name = 'estimator'
m1 = model.FitPredict(inputs=[est, d])
m1.target = True
m1.name = 'm1'
m2 = model.FitPredict(inputs=[est, d])
m2.target = True
m2.name = 'm2'
p = model.PredictProduct(inputs=[MapResults([m1, m2], ['m1', 'm2'])])
p.target = True
p.name = 'p'
return p
def product_model():
d = data.ClassificationData(n_samples=1000, n_features=100)
d.target = True
est = step.Construct(_class='sklearn.ensemble.RandomForestClassifier',
n_estimators=10)
est.name = 'estimator'
m1 = model.FitPredict(inputs=[est, d])
m1.target = True
m1.name = 'm1'
m2 = model.FitPredict(inputs=[est, d])
m2.target = True
m2.name = 'm2'
p = model.PredictProduct(inputs=[m1,m2], inputs_mapping=['m1', 'm2'])
p.target = True
p.name = 'p'
return p
