def test_numpy_integration(self):
"""
Test on a real dataset with NumPy arrays
"""
data = load_mushroom(return_dataset=True)
X, y = data.to_numpy()
X = OneHotEncoder().fit_transform(X).toarray()
cv = StratifiedKFold(n_splits=4, random_state=32)
oz = LearningCurve(GaussianNB(), cv=cv, random_state=23)
oz.fit(X, y)
oz.finalize()
self.assert_images_similar(oz)
def test_numpy_integration(self):
"""
Test on mushroom dataset with NumPy arrays
"""
data = load_mushroom(return_dataset=True)
X, y = data.to_numpy()
X = OneHotEncoder().fit_transform(X).toarray()
cv = StratifiedKFold(n_splits=2, random_state=11)
oz = CVScores(BernoulliNB(), cv=cv)
oz.fit(X, y)
oz.finalize()
self.assert_images_similar(oz, tol=2.0)
def test_numpy_integration(self):
"""
Test on mushroom dataset with NumPy arrays
"""
data = load_mushroom(return_dataset=True)
X, y = data.to_numpy()
X = OneHotEncoder().fit_transform(X).toarray()
cv = StratifiedKFold(n_splits=2, random_state=11)
pr = np.linspace(0.1, 3.0, 6)
oz = ValidationCurve(BernoulliNB(), cv=cv, param_range=pr, param_name="alpha")
oz.fit(X, y)
oz.finalize()
self.assert_images_similar(oz)
def test_pandas_integration(self):
"""
Test on a real dataset with pandas DataFrame and Series
"""
data = load_mushroom(return_dataset=True)
X, y = data.to_pandas()
X = pd.get_dummies(X)
assert isinstance(X, pd.DataFrame)
assert isinstance(y, pd.Series)
cv = StratifiedKFold(n_splits=4, random_state=32)
oz = LearningCurve(GaussianNB(), cv=cv, random_state=23)
oz.fit(X, y)
oz.finalize()
self.assert_images_similar(oz)
def test_pandas_integration(self):
"""
Test on mushroom dataset with pandas DataFrame and Series and NB
"""
data = load_mushroom(return_dataset=True)
X, y = data.to_pandas()
X = pd.get_dummies(X)
assert isinstance(X, pd.DataFrame)
assert isinstance(y, pd.Series)
cv = StratifiedKFold(n_splits=2, random_state=11)
oz = CVScores(BernoulliNB(), cv=cv)
oz.fit(X, y)
oz.finalize()
self.assert_images_similar(oz, tol=2.0)
def test_pandas_integration(self):
"""
Test on mushroom dataset with pandas DataFrame and Series and NB
"""
data = load_mushroom(return_dataset=True)
X, y = data.to_pandas()
X = pd.get_dummies(X)
assert isinstance(X, pd.DataFrame)
assert isinstance(y, pd.Series)
cv = StratifiedKFold(n_splits=2, random_state=11)
pr = np.linspace(0.1, 3.0, 6)
oz = ValidationCurve(BernoulliNB(), cv=cv, param_range=pr, param_name="alpha")
oz.fit(X, y)
oz.finalize()
self.assert_images_similar(oz)
def get_mushroom_data():
X, y = load_mushroom()
labels = y.unique().tolist()
return X, y, labels
}
def visualize_model(X, y, estimator, path, **kwargs):
"""
Test various estimators.
"""
y = LabelEncoder().fit_transform(y)
model = Pipeline([("one_hot_encoder", OneHotEncoder()),
("estimator", estimator)])
_, ax = plt.subplots()
# Instantiate the classification model and visualizer
visualizer = ClassificationReport(model,
classes=["edible", "poisonous"],
cmap="YlGn",
size=(600, 360),
ax=ax,
**kwargs)
visualizer.fit(X, y)
visualizer.score(X, y)
visualizer.poof(outpath=path)
if __name__ == "__main__":
X, y = load_mushroom()
for clf in ESTIMATORS.values():
visualize_model(X, y, clf["model"], clf["path"])
# -*- coding: utf-8 -*-
"""
Spyder Editor
This is a temporary script file.
"""
import matplotlib.pyplot as plt
import pandas as pd
from yellowbrick.datasets import load_mushroom
import seaborn as sn
import numpy as np
dataset = load_mushroom(return_dataset=True)
df = dataset.to_dataframe()
df.head()
X = df.drop(columns=['target'])
y = df['target']
print('\nDataset Mushroom\n')
# Preprocessing
from sklearn.preprocessing import LabelEncoder, OneHotEncoder
le = LabelEncoder()
ohe = OneHotEncoder(handle_unknown='ignore')
y_scale = le.fit_transform(y)
X_scale = ohe.fit_transform(X)
from yellowbrick.target import class_balance
class_balance(y_scale, labels=['edible', 'poisonous'])