def test_DTree_best_split_minority():
# Using minority class
model = DTree(metric=minority_class)
X = avocados.iloc[:, :-1]
y = avocados.iloc[:, -1]
feature, impurity = model._best_split(X, y)
assert feature == 'firmness'
assert impurity == 0.25
def test_DTree_best_split_gini():
# Using gini
model = DTree(metric=gini)
X = avocados.iloc[:, :-1]
y = avocados.iloc[:, -1]
feature, impurity = model._best_split(X, y)
assert feature == 'firmness'
assert 0.33 < impurity < 0.34
def test_DTree_fit_recusively_child_labels():
""" Check recursively if each node is labeled """
def recursive(model):
assert model._label is not None, "Each node should be labeled."
if model._split:
recursive(model._yes)
recursive(model._no)
X = avocados.iloc[:, :-1]
y = avocados.iloc[:, -1]
model = DTree(metric=minority_class)
model.fit(X, y)
recursive(model)
def test_DTree_fit_children():
""" Check if the root node has split (it should) and has child nodes """
X = avocados.iloc[:, :-1]
y = avocados.iloc[:, -1]
model = DTree(metric=minority_class)
assert model._split is False, "Before fitting, this should not be set yet."
assert model._yes is None, "Before fitting, this should not be set yet."
assert model._no is None, "Before fitting, this should not be set yet."
model.fit(X, y)
assert model._split is not False, "After fitting, the top node should have split"
assert isinstance(model._yes,
DTree), "The Yes child node should be a subtree"
assert isinstance(model._no,
DTree), "The No child node should be a subtree"
def test_DTree_fit_recusively_children():
""" Check recursively if each node is either a leaf, or split and has two children """
def recursive(model):
if model._split:
assert isinstance(model._yes,
DTree), "The Yes child node should be a subtree"
assert isinstance(model._no,
DTree), "The No child node should be a subtree"
recursive(model._yes)
recursive(model._no)
X = avocados.iloc[:, :-1]
y = avocados.iloc[:, -1]
model = DTree(metric=minority_class)
model.fit(X, y)
recursive(model)
def test_DTree_fit_text_string():
""" Check if we've learned the RIGHT model """
X = avocados.iloc[:, :-1]
y = avocados.iloc[:, -1]
model = DTree(metric=minority_class)
model.fit(X, y)
text = model.to_text()
# Compare the text that you actually got to what it should be:
assert '\n' + text == ("""
|---firmness = no
| |---0 (2)
|---firmness = yes
| |---nub_loose = no
| | |---0 (3)
| |---nub_loose = yes
| | |---1 (3)
"""), "The tree should look like this"
def test_DTree_fit_recusively_decreasing_impurity():
""" Check if the weighted impurity of children is always lower than that of the parent """
def recursive_impurity(model):
if model._split:
yes_impurity, yes_samples = recursive_impurity(model._yes)
no_impurity, no_samples = recursive_impurity(model._no)
weighted_impurity = (yes_impurity * yes_samples) + (no_impurity *
no_samples)
assert weighted_impurity < (model._impurity * model._samples), (
"The weighted impurity of the children should be smaller than the parent"
)
return model._impurity, model._samples
X = avocados.iloc[:, :-1]
y = avocados.iloc[:, -1]
model = DTree(metric=minority_class)
model.fit(X, y)
recursive_impurity(model)