def test_score_regressor(self):
np.random.seed(0)
df = get_dataset("iris").as_df()
df.drop(['Species'], inplace=True, axis=1)
df.Label = [1 if x == 1 else 0 for x in df.Label]
X_train, X_test, y_train, y_test = \
train_test_split(df.loc[:, df.columns != 'Label'], df['Label'])
lr = FastTreesRegressor(train_threads=1)
e = Pipeline([lr])
e.fit(X_train, y_train.to_frame())
metrics = e.score(X_test, y_test)
print(metrics)
assert_almost_equal(metrics,
0.814061733686017,
decimal=5,
err_msg="L1 loss should be %s" % 0.814061733686017)
def test_score_binary(self):
np.random.seed(0)
df = get_dataset("iris").as_df()
df.drop(['Species'], inplace=True, axis=1)
df.Label = [1 if x == 1 else 0 for x in df.Label]
X_train, X_test, y_train, y_test = \
train_test_split(df.loc[:, df.columns != 'Label'], df['Label'])
lr = LogisticRegressionBinaryClassifier(train_threads=1)
e = Pipeline([lr])
e.fit(X_train, y_train)
metrics = e.score(X_test, y_test)
print(metrics)
assert_almost_equal(metrics,
0.9801136363636364,
decimal=5,
err_msg="AUC should be %s" % 0.9801136363636364)
def test_score_multiclass(self):
np.random.seed(0)
df = get_dataset("iris").as_df()
df.drop(['Species'], inplace=True, axis=1)
df.Label = [1 if x == 1 else 0 for x in df.Label]
X_train, X_test, y_train, y_test = \
train_test_split(df.loc[:, df.columns != 'Label'], df['Label'])
lr = LogisticRegressionClassifier(train_threads=1)
e = Pipeline([lr])
e.fit(X_train, y_train.to_frame())
metrics = e.score(X_test, y_test)
print(metrics)
assert_almost_equal(metrics,
0.7631578947368421,
decimal=5,
err_msg="Accuracy(micro-avg) should be %s" %
0.7631578947368421)
def test_score_clusterer(self):
np.random.seed(0)
df = get_dataset("iris").as_df()
df.drop(['Species'], inplace=True, axis=1)
df.Label = [1 if x == 1 else 0 for x in df.Label]
X_train, X_test, y_train, y_test = \
train_test_split(df.loc[:, df.columns != 'Label'], df['Label'])
lr = KMeansPlusPlus(n_clusters=2,
init_algorithm="Random",
train_threads=1)
e = Pipeline([lr])
e.fit(X_train, y_train.to_frame())
metrics = e.score(X_test, y_test)
print(metrics)
assert_almost_equal(metrics,
0.36840763005544264,
decimal=5,
err_msg="NMI loss should be %s" %
0.36840763005544264)
def test_score_anomalydetection(self):
np.random.seed(0)
df = get_dataset("iris").as_df().drop(['Label', 'Species'], axis=1)
X_train, X_test = train_test_split(df)
X_test.is_copy = False
X_train = X_train[X_train['Setosa'] == 1]
y_test = X_test['Setosa'].apply(lambda x: 1 if x == 0 else 0)
X_train.drop(['Setosa'], axis=1, inplace=True)
X_test.drop(['Setosa'], axis=1, inplace=True)
svm = OneClassSvmAnomalyDetector() # noqa
e = Pipeline([svm])
e.fit(X_train)
if e.nodes[-1].label_column_ is not None:
raise ValueError("'{0}' should be None".format(
e.nodes[-1].label_column_))
assert y_test.name == 'Setosa'
metrics = e.score(X_test, y_test)
print(metrics)
assert_almost_equal(metrics,
1.0,
decimal=5,
err_msg="AUC should be %s" % 1.0)
