def test_chickweight_raise_error_group_col_missing():
df = load_chicken(as_frame=True)
mod = GroupedPredictor(estimator=LinearRegression(), groups="diet")
mod.fit(df[["time", "diet"]], df["weight"])
with pytest.raises(ValueError) as e:
mod.predict(df[["time", "chick"]])
assert "not in columns" in str(e)
def test_chickweight_raise_error_cols_missing2():
df = load_chicken(give_pandas=True)
mod = GroupedEstimator(estimator=LinearRegression(), groups="diet")
mod.fit(df[['time', 'diet']], df['weight'])
with pytest.raises(ValueError) as e:
mod.predict(df[['diet', 'chick']])
assert "not in columns" in str(e)
def test_bad_shrinkage_value_error():
with pytest.raises(ValueError) as e:
df = load_chicken(as_frame=True)
mod = GroupedPredictor(
estimator=LinearRegression(), groups="diet", shrinkage="dinosaurhead"
)
mod.fit(df[["time", "diet"]], df["weight"])
assert "shrinkage function" in str(e)
def test_has_decision_function():
# needed as for example cross_val_score(pipe, X, y, cv=5, scoring="roc_auc", error_score='raise') may fail otherwise, see https://github.com/koaning/scikit-lego/issues/511
df = load_chicken(as_frame=True)
X, y = df.drop(columns='weight'), df['weight']
# This should NOT raise errors
GroupedPredictor(LogisticRegression(),
groups=["diet"]).fit(X, y).decision_function(X)
def test_chickweight_can_do_fallback():
df = load_chicken(give_pandas=True)
mod = GroupedEstimator(estimator=LinearRegression(), groups="diet")
mod.fit(df[['time', 'diet']], df['weight'])
assert set(mod.estimators_.keys()) == {1, 2, 3, 4}
to_predict = pd.DataFrame({"time": [21, 21], "diet": [5, 6]})
assert mod.predict(to_predict).shape == (2, )
assert mod.predict(to_predict)[0] == mod.predict(to_predict)[1]
def test_chickweight_raise_error_value_col_missing():
df = load_chicken(as_frame=True)
mod = GroupedPredictor(estimator=LinearRegression(), groups="diet")
mod.fit(df[["time", "diet"]], df["weight"])
with pytest.raises(ValueError):
# Former test not valid anymore because we don't check for value columns
# mod.predict(df[["diet", "chick"]])
mod.predict(df[["diet"]])
def test_fallback_can_raise_error():
df = load_chicken(give_pandas=True)
mod = GroupedEstimator(estimator=LinearRegression(),
groups="diet",
use_fallback=False)
mod.fit(df[['time', 'diet']], df['weight'])
to_predict = pd.DataFrame({"time": [21, 21], "diet": [5, 6]})
with pytest.raises(ValueError):
mod.predict(to_predict)
def test_bad_shrinkage_value_error():
with pytest.raises(ValueError) as e:
df = load_chicken(give_pandas=True)
mod = GroupedEstimator(
estimator=LinearRegression(),
groups="diet",
shrinkage="dinosaurhead",
)
mod.fit(df[['time', 'diet']], df['weight'])
assert "shrinkage function" in str(e)
def test_chickweight_can_do_fallback_proba():
df = load_chicken(as_frame=True)
y = np.where(df.weight > df.weight.mean(), 1, 0)
mod = GroupedPredictor(estimator=LogisticRegression(), groups="diet")
mod.fit(df[["time", "diet"]], y)
assert set(mod.estimators_.keys()) == {1, 2, 3, 4}
to_predict = pd.DataFrame({"time": [21, 21], "diet": [5, 6]})
assert mod.predict_proba(to_predict).shape == (2, 2)
assert (mod.predict_proba(to_predict)[0] == mod.predict_proba(to_predict)
[1]).all()
def test_fallback_can_raise_error():
df = load_chicken(give_pandas=True)
mod = GroupedEstimator(estimator=LinearRegression(),
groups="diet",
use_global_model=False,
shrinkage=None)
mod.fit(df[['time', 'diet']], df['weight'])
to_predict = pd.DataFrame({"time": [21, 21], "diet": [5, 6]})
with pytest.raises(ValueError) as e:
mod.predict(to_predict)
assert "found a group" in str(e)
def test_chickweigt_string_groups():
df = load_chicken(give_pandas=True)
df['diet'] = ['omgomgomg' + s for s in df['diet'].astype(str)]
X = df[['time', 'diet']]
X_np = np.array(X)
y = df['weight']
# This should NOT raise errors
GroupedEstimator(LinearRegression(), groups=['diet']).fit(X, y).predict(X)
GroupedEstimator(LinearRegression(), groups=1).fit(X_np, y).predict(X_np)
def test_chickweigt_string_groups():
df = load_chicken(as_frame=True)
df["diet"] = ["omgomgomg" + s for s in df["diet"].astype(str)]
X = df[["time", "diet"]]
X_np = np.array(X)
y = df["weight"]
# This should NOT raise errors
GroupedPredictor(LinearRegression(), groups=["diet"]).fit(X, y).predict(X)
GroupedPredictor(LinearRegression(), groups=1).fit(X_np, y).predict(X_np)
def test_missing_check():
df = load_chicken(as_frame=True)
X, y = df.drop(columns='weight'), df['weight']
# create missing value
X.loc[0, 'chick'] = np.nan
model = make_pipeline(SimpleImputer(), LinearRegression())
# Should not raise error, check is disabled
m = GroupedPredictor(model, groups=['diet'], check_X=False).fit(X, y)
m.predict(X)
# Should raise error, check is still enabled
with pytest.raises(ValueError) as e:
GroupedPredictor(model, groups=['diet']).fit(X, y)
assert "contains NaN" in str(e)
def test_chickweight1():
X, y = load_chicken(return_X_y=True)
assert X.shape == (578, 3)
assert y.shape[0] == 578
def test_chickweight_df2_keys():
df = load_chicken(give_pandas=True)
mod = GroupedEstimator(estimator=LinearRegression(), groups="chick")
mod.fit(df[['time', 'chick']], df['weight'])
assert set(mod.estimators_.keys()) == set(range(1, 50 + 1))
def test_chickweight_df1_keys():
df = load_chicken(give_pandas=True)
mod = GroupedEstimator(estimator=LinearRegression(), groups="diet")
mod.fit(df[['time', 'diet']], df['weight'])
assert set(mod.estimators_.keys()) == {1, 2, 3, 4}
def test_chickweight_np_keys():
df = load_chicken(as_frame=True)
mod = GroupedPredictor(estimator=LinearRegression(), groups=[1, 2])
mod.fit(df[["time", "chick", "diet"]].values, df["weight"].values)
# there should still only be 50 groups on this dataset
assert len(mod.estimators_.keys()) == 50
def test_chickweight2():
df = load_chicken(as_frame=True)
assert df.shape == (578, 4)
def test_chickweight2():
df = load_chicken(give_pandas=True)
assert df.shape == (578, 4)
def test_chickweight_df2_keys():
df = load_chicken(as_frame=True)
mod = GroupedPredictor(estimator=LinearRegression(), groups="chick")
mod.fit(df[["time", "chick"]], df["weight"])
assert set(mod.estimators_.keys()) == set(range(1, 50 + 1))
def test_chickweight_df1_keys():
df = load_chicken(as_frame=True)
mod = GroupedPredictor(estimator=LinearRegression(), groups="diet")
mod.fit(df[["time", "diet"]], df["weight"])
assert set(mod.estimators_.keys()) == {1, 2, 3, 4}
def test_chickweight1():
X, y = load_chicken()
assert X.shape == (578, 3)
assert y.shape[0] == 578
def test_chickweight_np_keys():
df = load_chicken(give_pandas=True)
mod = GroupedEstimator(estimator=LinearRegression(), groups=[1, 2])
mod.fit(df[['time', 'chick', 'diet']].values, df['weight'].values)
# there should still only be 50 groups on this dataset
assert len(mod.estimators_.keys()) == 50
def test_chickweight_raise_error_cols_missing1():
df = load_chicken(give_pandas=True)
mod = GroupedEstimator(estimator=LinearRegression(), groups="diet")
mod.fit(df[['time', 'diet']], df['weight'])
with pytest.raises(KeyError):
mod.predict(df[['time', 'chick']])
