Skip to content

Minor fixes #581

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
norvig merged 2 commits into from
Jul 10, 2017
Merged

Minor fixes #581

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
bde45b6
Minor fixes
Chipe1 Jul 9, 2017
2fbafe4
Typo fix
Chipe1 Jul 9, 2017
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
112 changes: 65 additions & 47 deletions learning.ipynb
View file
Open in desktop

Large diffs are not rendered by default.

30 changes: 18 additions & 12 deletions learning.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -381,16 +381,21 @@ class DecisionFork:
"""A fork of a decision tree holds an attribute to test, and a dict
of branches, one for each of the attribute's values."""

def __init__(self, attr, attrname=None, branches=None):
def __init__(self, attr, attrname=None, default_child=None, branches=None):
"""Initialize by saying what attribute this node tests."""
self.attr = attr
self.attrname = attrname or attr
self.default_child = default_child
self.branches = branches or {}

def __call__(self, example):
"""Given an example, classify it using the attribute and the branches."""
attrvalue = example[self.attr]
return self.branches[attrvalue](example)
if attrvalue in self.branches:
return self.branches[attrvalue](example)
else:
# return default class when attribute is unknown
return self.default_child(example)

def add(self, val, subtree):
"""Add a branch. If self.attr = val, go to the given subtree."""
Expand Down Expand Up @@ -440,7 +445,7 @@ def decision_tree_learning(examples, attrs, parent_examples=()):
return plurality_value(examples)
else:
A = choose_attribute(attrs, examples)
tree = DecisionFork(A, dataset.attrnames[A])
tree = DecisionFork(A, dataset.attrnames[A], plurality_value(examples))
for (v_k, exs) in split_by(A, examples):
subtree = decision_tree_learning(
exs, removeall(A, attrs), examples)
Expand Down Expand Up @@ -495,27 +500,28 @@ def information_content(values):


def RandomForest(dataset, n=5):
"""A ensemble of Decision trese trained using bagging and feature bagging."""

predictors = [DecisionTreeLearner(examples=data_bagging(dataset),
attrs=dataset.attrs,
attrnames=dataset.attrnames,
target=dataset.target,
inputs=feature_bagging(datatset)) for _ in range(n)]
"""An ensemble of Decision Trees trained using bagging and feature bagging."""

def data_bagging(dataset, m=0):
"""Sample m examples with replacement"""
n = len(dataset.examples)
return weighted_sample_with_replacement(m or n, examples, [1]*n)
return weighted_sample_with_replacement(m or n, dataset.examples, [1]*n)

def feature_bagging(dataset, p=0.7):
"""Feature bagging with probability p to retain an attribute"""
inputs = [i for i in dataset.inputs if probability(p)]
return inputs or dataset.inputs

def predict(example):
print([predictor(example) for predictor in predictors])
return mode(predictor(example) for predictor in predictors)

predictors = [DecisionTreeLearner(DataSet(examples=data_bagging(dataset),
attrs=dataset.attrs,
attrnames=dataset.attrnames,
target=dataset.target,
inputs=feature_bagging(dataset))) for _ in range(n)]

return predict

# ______________________________________________________________________________
Expand Down Expand Up @@ -1046,7 +1052,7 @@ def T(attrname, branches):
branches = {value: (child if isinstance(child, DecisionFork)
else DecisionLeaf(child))
for value, child in branches.items()}
return DecisionFork(restaurant.attrnum(attrname), attrname, branches)
return DecisionFork(restaurant.attrnum(attrname), attrname, print, branches)


""" [Figure 18.2]
Expand Down
8 changes: 8 additions & 0 deletions tests/test_learning.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -123,6 +123,14 @@ def test_decision_tree_learner():
assert dTL([7.5, 4, 6, 2]) == "virginica"


def test_random_forest():
iris = DataSet(name="iris")
rF = RandomForest(iris)
assert rF([5, 3, 1, 0.1]) == "setosa"
assert rF([6, 5, 3, 1.5]) == "versicolor"
assert rF([7.5, 4, 6, 2]) == "virginica"


def test_neural_network_learner():
iris = DataSet(name="iris")
classes = ["setosa", "versicolor", "virginica"]
Expand Down