def balance_class_balance(path="images/class_balance.png"):
data = load_game()
y = data["outcome"]
oz = ClassBalance(labels=["draw", "loss", "win"])
oz.fit(y)
return oz.poof(outpath=path)
def balance_class_balance(path="images/class_balance.png"):
data = load_game()
y = data["outcome"]
oz = ClassBalance(labels=["draw", "loss", "win"])
oz.fit(y)
return oz.poof(outpath=path)
def class_prediction_error(ax=None):
data = load_game(return_dataset=True)
X, y = data.to_numpy()
X = OneHotEncoder().fit_transform(X).toarray()
viz = ClassPredictionError(GaussianNB(), ax=ax)
return tts_plot(viz, X, y)
def rocauc(dataset):
if dataset == "binary":
X, y = load_occupancy()
model = GaussianNB()
elif dataset == "multiclass":
X, y = load_game()
X = OrdinalEncoder().fit_transform(X)
model = RidgeClassifier()
else:
raise ValueError("uknown dataset")
X_train, X_test, y_train, y_test = tts(X, y, test_size=0.2)
oz = ROCAUC(model, ax=newfig())
oz.fit(X_train, y_train)
oz.score(X_test, y_test)
savefig(oz, "rocauc_{}".format(dataset))
def validation_curve_classifier_knn(path="images/validation_curve_classifier_knn.png"):
X, y = load_game()
X = OneHotEncoder().fit_transform(X)
_, ax = plt.subplots()
cv = StratifiedKFold(4)
param_range = np.arange(3, 20, 2)
print("warning: generating the KNN validation curve can take a very long time!")
oz = ValidationCurve(
KNeighborsClassifier(),
ax=ax,
param_name="n_neighbors",
param_range=param_range,
cv=cv,
scoring="f1_weighted",
n_jobs=8,
)
oz.fit(X, y)
oz.show(outpath=path)
def validation_curve_classifier_svc(path="images/validation_curve_classifier_svc.png"):
X, y = load_game()
X = OneHotEncoder().fit_transform(X)
_, ax = plt.subplots()
cv = StratifiedKFold(12)
param_range = np.logspace(-6, -1, 12)
print("warning: generating the SVC validation curve can take a very long time!")
oz = ValidationCurve(
SVC(),
ax=ax,
param_name="gamma",
param_range=param_range,
logx=True,
cv=cv,
scoring="f1_weighted",
n_jobs=8,
)
oz.fit(X, y)
oz.show(outpath=path)
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))