def prcurve(dataset):
if dataset == "binary":
X, y = load_spam()
model = RidgeClassifier()
kws = {}
elif dataset == "multiclass":
X, y = load_game()
X = OrdinalEncoder().fit_transform(X)
y = LabelEncoder().fit_transform(y)
model = MultinomialNB()
kws = {
"per_class": True,
"iso_f1_curves": True,
"fill_area": False,
"micro": False,
}
else:
raise ValueError("uknown dataset")
X_train, X_test, y_train, y_test = tts(X, y, test_size=0.2, shuffle=True)
oz = PRCurve(model, ax=newfig(), **kws)
oz.fit(X_train, y_train)
oz.score(X_test, y_test)
savefig(oz, "precision_recall_{}".format(dataset))
def discrimination():
X, y = load_spam()
oz = DiscriminationThreshold(LogisticRegression(solver="lbfgs"),
ax=newfig())
oz.fit(X, y)
savefig(oz, "discrimination_threshold")
def discrimination_threshold(ax=None):
data = load_spam(return_dataset=True)
X, y = data.to_pandas()
viz = DiscriminationThreshold(RandomForestClassifier(n_estimators=10), ax=ax)
return tts_plot(viz, X, y, score=False)
def confusion_matrix(ax=None):
data = load_spam(return_dataset=True)
X, y = data.to_pandas()
viz = PrecisionRecallCurve(LogisticRegression(), ax=ax)
return tts_plot(viz, X, y)