def staged_auc(self,X,y):
"""
calculate the AUC after each of the stages.
returns: ns -- list of iteration numbers
aucs -- list of corresponding areas under the curve.
"""
y = np.array(y)
results = [ (n, util.auc(y,p)) for n,p in self.staged_predict(X)]
return zip(*results) # Python idiom unzips list into two parallel ones.
def tune_one_fold(options, i, train_i, test_i):
"""
Tune one fold of the data.
"""
global train
clf = make_pipeline(options)
ftrain = train[train_i]
logging.info('fold %d' % i)
clf.fit(ftrain.Comment, ftrain.Insult)
ypred = clf.predict(ftrain.Comment)
logging.info("%d train auc=%f" % (i, auc(np.array(ftrain.Insult),ypred)))
ypred = clf.predict(train[test_i].Comment)
# record information about the auc at each stage of training.
xs,ys = clf.staged_auc(train[test_i].Comment, train[test_i].Insult)
xs = np.array(xs)
ys = np.array(ys)
return pandas.DataFrame({ ('auc%d' % i):ys}, index=xs)
def auc(self,X,y):
yhat = self.predict(X)
return util.auc(np.array(y),yhat)