def test_id3_ut18(self, tn=18):
"""
Find all examples with Outlook=Rain and check that they include 3 positive and 2 negative
examples.
"""
print('\n============ ID3 UT {} ======================='.format(tn))
examples, colnames = bin_id3.parse_csv_file_into_examples('play_tennis.csv')
outlook_rain_examples = bin_id3.find_examples_given_attrib_val(examples, 'Outlook', 'Rain')
print('Examples with Outlook=Rain:\n')
for i, ex in enumerate(outlook_rain_examples):
print('{}) {}'.format(i+1, ex))
assert len(bin_id3.find_examples_given_attrib_val(outlook_rain_examples, 'PlayTennis', 'Yes')) == 3
assert len(bin_id3.find_examples_given_attrib_val(outlook_rain_examples, 'PlayTennis', 'No')) == 2
print('\n============ ID3 UT {} passed ================'.format(tn))
def test_id3_ut14(self, tn=14):
"""
Find all examples with Outlook=Overcast and check that those examples consist of
4 postive examples and 0 negative examples.
"""
print('\n============ ID3 UT {} ======================='.format(tn))
examples, colnames = bin_id3.parse_csv_file_into_examples('play_tennis.csv')
outlook_over_examples = bin_id3.find_examples_given_attrib_val(examples, 'Outlook', 'Overcast')
print('Examples with Outlook=Overcast:\n')
for i, ex in enumerate(outlook_over_examples):
print('{}) {}'.format(i+1, ex))
assert len(bin_id3.find_examples_given_attrib_val(outlook_over_examples, 'PlayTennis', 'Yes')) == 4
assert len(bin_id3.find_examples_given_attrib_val(outlook_over_examples, 'PlayTennis', 'No')) == 0
print('\n============ ID3 UT {} passed ================'.format(tn))
def test_id3_ut20(self, tn=20):
"""
Let S =
1) {'Day': 'D1', 'Outlook': 'Sunny', 'Temperature': 'Hot', 'Humidity': 'High', 'Wind': 'Weak', 'PlayTennis': 'No'}
2) {'Day': 'D2', 'Outlook': 'Sunny', 'Temperature': 'Hot', 'Humidity': 'High', 'Wind': 'Strong', 'PlayTennis': 'No'}
3) {'Day': 'D8', 'Outlook': 'Sunny', 'Temperature': 'Mild', 'Humidity': 'High', 'Wind': 'Weak', 'PlayTennis': 'No'}
4) {'Day': 'D9', 'Outlook': 'Sunny', 'Temperature': 'Cool', 'Humidity': 'Normal', 'Wind': 'Weak', 'PlayTennis': 'Yes'}
5) {'Day': 'D11', 'Outlook': 'Sunny', 'Temperature': 'Mild', 'Humidity': 'Normal', 'Wind': 'Strong', 'PlayTennis': 'Yes'}
Find most common value for attribute PlayTennis
Find most common value for attribute Humdity
Find most common value for attribute Wind
Find most common value for attribute Temperature
"""
print('\n============ ID3 UT {} ======================='.format(tn))
examples, colnames = bin_id3.parse_csv_file_into_examples('play_tennis.csv')
outlook_sunny_examples = bin_id3.find_examples_given_attrib_val(examples, 'Outlook', 'Sunny')
avt = bin_id3.construct_attrib_values_from_examples(examples, colnames[1:])
atv, cnt = bin_id3.find_most_common_attrib_val(outlook_sunny_examples, 'PlayTennis', avt)
assert atv == 'No'
assert cnt == 3
atv, cnt = bin_id3.find_most_common_attrib_val(outlook_sunny_examples, 'Humidity', avt)
assert atv == 'High'
assert cnt == 3
atv, cnt = bin_id3.find_most_common_attrib_val(outlook_sunny_examples, 'Wind', avt)
assert atv == 'Weak'
assert cnt == 3
atv, cnt = bin_id3.find_most_common_attrib_val(outlook_sunny_examples, 'Temperature', avt)
assert atv == 'Hot' or atv == 'Mild'
assert cnt == 2
print('\n============ ID3 UT {} passed ================'.format(tn))
def test_id3_ut05(self, tn=5):
"""
- Finds the examples with Outlook=Sunny;
- In the examples with Outlook=Sunny finds all examples with PlayTennis=Yes;
- In the examples with Outlook=Sunny finds all examples with PlayTennis=No.
"""
print('\n============ ID3 UT {} ======================='.format(tn))
examples, colnames = bin_id3.parse_csv_file_into_examples('play_tennis.csv')
outlook_sunny_examples = bin_id3.find_examples_given_attrib_val(examples, 'Outlook', 'Sunny')
print('Examples with Outlook=Sunny:\n')
for i, ex in enumerate(outlook_sunny_examples):
print('{}) {}'.format(i+1, ex))
assert len(bin_id3.find_examples_given_attrib_val(outlook_sunny_examples, 'PlayTennis', 'Yes')) \
== 2
assert len(bin_id3.find_examples_given_attrib_val(outlook_sunny_examples, 'PlayTennis', 'No')) \
== 3
def test_id3_ut17(self, tn=17):
"""
Find all examples with Outlook=Overcast and compute info gain of Wind.
"""
print('\n============ ID3 UT {} ======================='.format(tn))
examples, colnames = bin_id3.parse_csv_file_into_examples('play_tennis.csv')
outlook_over_examples = bin_id3.find_examples_given_attrib_val(examples, 'Outlook', 'Overcast')
avt = bin_id3.construct_attrib_values_from_examples(examples, colnames[1:])
g = bin_id3.gain(outlook_over_examples, 'PlayTennis', 'Wind', avt)
gt = 0.0
err = 0.0001
print('gain(Wind)={}'.format(g))
assert abs(g - gt) <= err
print('\n============ ID3 UT {} passed ================'.format(tn))
def test_id3_ut12(self, tn=12):
"""
Find all examples with Outlook=Sunny and compute info gain of Temperature.
"""
print('\n============ ID3 UT {} ======================='.format(tn))
examples, colnames = bin_id3.parse_csv_file_into_examples('play_tennis.csv')
outlook_sunny_examples = bin_id3.find_examples_given_attrib_val(examples, 'Outlook', 'Sunny')
avt = bin_id3.construct_attrib_values_from_examples(examples, colnames[1:])
g = bin_id3.gain(outlook_sunny_examples, 'PlayTennis', 'Temperature', avt)
gt = 0.5709505944546686
err = 0.0001
print('gain(Temperature)={}'.format(g))
assert abs(g - gt) <= err
print('\n============ ID3 UT {} passed ================'.format(tn))
def test_id3_ut06b(self, tn=6):
"""
Let S =
1) {'Day': 'D1', 'Outlook': 'Sunny', 'Temperature': 'Hot', 'Humidity': 'High', 'Wind': 'Weak', 'PlayTennis': 'No'}
2) {'Day': 'D2', 'Outlook': 'Sunny', 'Temperature': 'Hot', 'Humidity': 'High', 'Wind': 'Strong', 'PlayTennis': 'No'}
3) {'Day': 'D8', 'Outlook': 'Sunny', 'Temperature': 'Mild', 'Humidity': 'High', 'Wind': 'Weak', 'PlayTennis': 'No'}
4) {'Day': 'D9', 'Outlook': 'Sunny', 'Temperature': 'Cool', 'Humidity': 'Normal', 'Wind': 'Weak', 'PlayTennis': 'Yes'}
5) {'Day': 'D11', 'Outlook': 'Sunny', 'Temperature': 'Mild', 'Humidity': 'Normal', 'Wind': 'Strong', 'PlayTennis': 'Yes'}
Compute Entropy(S) w/ respect to PlayTennis;
"""
print('\n============ ID3 UT {}b ======================='.format(tn))
examples, colnames = bin_id3.parse_csv_file_into_examples('play_tennis.csv')
outlook_sunny_examples = bin_id3.find_examples_given_attrib_val(examples, 'Outlook', 'Sunny')
avt = bin_id3.construct_attrib_values_from_examples(examples, colnames[1:])
H = bin_id3.entropy(outlook_sunny_examples, 'PlayTennis', avt)
gH = 0.9709505944546686
err = 0.0001
print('Entropy(S)={}'.format(H))
assert abs(H - gH) <= err
print('\n============ ID3 UT {}b pass =================='.format(tn))
def test_id3_ut19(self, tn=19):
"""
Let S =
1) {'Day': 'D1', 'Outlook': 'Sunny', 'Temperature': 'Hot', 'Humidity': 'High', 'Wind': 'Weak', 'PlayTennis': 'No'}
2) {'Day': 'D2', 'Outlook': 'Sunny', 'Temperature': 'Hot', 'Humidity': 'High', 'Wind': 'Strong', 'PlayTennis': 'No'}
3) {'Day': 'D8', 'Outlook': 'Sunny', 'Temperature': 'Mild', 'Humidity': 'High', 'Wind': 'Weak', 'PlayTennis': 'No'}
4) {'Day': 'D9', 'Outlook': 'Sunny', 'Temperature': 'Cool', 'Humidity': 'Normal', 'Wind': 'Weak', 'PlayTennis': 'Yes'}
5) {'Day': 'D11', 'Outlook': 'Sunny', 'Temperature': 'Mild', 'Humidity': 'Normal', 'Wind': 'Strong', 'PlayTennis': 'Yes'}
Compute
1) Entropy(S);
2) Gain(Temperature);
3) Gain(Humidity);
4) Gain(Wind);
"""
print('\n============ ID3 UT {} ======================='.format(tn))
examples, colnames = bin_id3.parse_csv_file_into_examples('play_tennis.csv')
outlook_sunny_examples = bin_id3.find_examples_given_attrib_val(examples, 'Outlook', 'Sunny')
avt = bin_id3.construct_attrib_values_from_examples(examples, colnames[1:])
H = bin_id3.entropy(outlook_sunny_examples, 'PlayTennis', avt)
gH = 0.9709505944546686
err = 0.0001
print('Entropy(S)={}'.format(H))
assert abs(H - gH) <= err
g = bin_id3.gain(outlook_sunny_examples, 'PlayTennis', 'Temperature', avt)
gt = 0.5709505944546686
err = 0.0001
print('gain(Temperature)={}'.format(g))
assert abs(g-gt) <= err
g = bin_id3.gain(outlook_sunny_examples, 'PlayTennis', 'Humidity', avt)
gt = 0.9709505944546686
err = 0.0001
print('gain(Humidity)={}'.format(g))
assert abs(g-gt) <= err
g = bin_id3.gain(outlook_sunny_examples, 'PlayTennis', 'Wind', avt)
gt = 0.01997309402197489
err = 0.0001
print('gain(Wind)={}'.format(g))
assert abs(g-gt) <= err
print('\n============ ID3 UT {} passed ================'.format(tn))