def test_wines(self):
df = load_wines_dataset()
X = df.drop(['quality', 'color'], axis=1)
X = X[['alcohol', 'volatile_acidity', 'density']]
y = df['quality']
color = df['color']
X_train, X_test, y_train, y_test, color_train, color_test = train_test_split(
X, y, color)
model = SkBaseLearnerCategory("color",
LogisticRegression(solver="liblinear"))
new_x_train = pandas.concat([X_train, color_train], axis=1)
model.fit(new_x_train, y_train)
new_x_test = pandas.concat([X_test, color_test], axis=1)
acc1 = accuracy_score(y_test, model.predict(new_x_test))
try:
self.assertEqualDataFrame(model.models['red'].coef_,
model.models['white'].coef_)
ok = False
except AssertionError as e:
ok = True
self.assertTrue(ok)
clr = LogisticRegression(solver="liblinear")
clr.fit(X_train, y_train)
acc2 = accuracy_score(y_test, clr.predict(X_test))
self.assertGreater(acc1, 0.45)
self.assertGreater(acc2, 0.45)
self.assertGreater(acc1, acc2 * 0.99)
recense tous les prétraitements que la librairie
:epkg:`scikit-learn` implémente.
.. contents::
:local:
"""
#########################################
# Un jeu de données
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import Normalizer
from sklearn.preprocessing import normalize
from papierstat.datasets import load_wines_dataset
df = load_wines_dataset()
X = df.drop(['quality', 'color'], axis=1)
y = df['quality']
print(X.head())
#########################################
# Normalisation naïve
# -------------------
X_norm = normalize(X)
print(X_norm[:5])
#########################################
# Normalisation supervisée
# ------------------------
#
def test_wines_local(self):
df = load_wines_dataset(download=False, shuffle=True)
self.assertEqual(df.shape, (6497, 13))