def balance_yellowbrick(
X,
y,
features,
):
plt.switch_backend('agg')
plt.clf()
X_train, X_test, y_train, y_test = train_test_split(X[features],
y,
stratify=y,
test_size=0.01)
X = pd.DataFrame(X_test, columns=features)
y = pd.Series(y_test)
visualizer = ClassBalance()
visualizer.fit(y)
visualizer.finalize()
return plt
display(X.shape)
display(y.shape)
#%%
import matplotlib.pyplot as plt
from yellowbrick.target import ClassBalance
_, y_counts = np.unique(y, return_counts=True)
class_labels = ["survived", "deceased"]
fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(9,4.5))
ax1.pie(y_counts, explode=(0, 0.05), labels = class_labels)
visualizer = ClassBalance(labels = class_labels, ax = ax2)
visualizer.fit(y)
visualizer.finalize()
plt.show()
#%%
print("Number of missing values:", X.isna().sum().sum())
#%%
X["timerecurrence"].describe()
#%%
# for column in X.columns[2:16]:
# plt.scatter(X[column], y)
# plt.xlabel(column)
# plt.show()