def test_load_from_data_encodes_data():
encoder = OneHotEncoder(['animal', 'color'], ['weight'],
max_levels_default=100)
data = [{
'animal': 'cat',
'color': 'blue',
'weight': 1.0
}, {
'animal': 'cat',
'color': 'red',
'weight': 3.0
}, {
'animal': 'dog',
'color': 'yellow',
'weight': 5.5
}, {
'animal': 'fish',
'color': 'blue',
'weight': 7.0
}, {
'animal': 'cat',
'color': 'blue',
'weight': 2.0
}, {
'animal': 'cat',
'color': 'blue',
'weight': 0.0
}, {
'animal': 'cat',
'color': 'blue',
'weight': 99.9
}]
encoder.load_from_data_stream(data)
encoded_data = [encoder.encode_row(row) for row in data]
assert len(encoded_data) == len(data)
assert len(encoded_data[0]) != len(data[0])
def test_load_from_data_encodes_data_correctly():
encoder = OneHotEncoder(['animal', 'color'], ['weight'],
max_levels_default=100)
data = [{
'animal': 'cat',
'color': 'blue',
'weight': 6.0
}, {
'animal': 'cat',
'color': 'red',
'weight': 3.0
}, {
'animal': 'dog',
'color': 'yellow',
'weight': 5.5
}, {
'animal': 'fish',
'color': 'blue',
'weight': 7.0
}, {
'animal': 'cat',
'color': 'magenta',
'weight': 2.0
}, {
'animal': 'mouse',
'color': 'purple',
'weight': 0.0
}, {
'animal': 'mouse',
'color': 'black',
'weight': 99.9
}]
encoder.load_from_data_stream(data)
encoded_data = [encoder.encode_row(row) for row in data]
assert len(encoded_data) == len(data)
assert len(encoded_data[0]) != len(data[0])
first_row = encoded_data[0]
expected = [
6.0, # weight is numeric and comes first
1.0, # animal is first categorical and cat is the most common, first row is cat
0.0, # animal, mouse is next most common, not a mouse
0.0, # animal, dog and fish tied for frequency but dog first alphabetically
0.0, # animal, fish, cat is not a fish
1.0, # color is next categorical alphabetically and blue is most common, first row blue
0.0, # black
0.0, # magenta
0.0, # purple
0.0, # red
0.0
] # yellow
assert first_row == expected
second_row = encoded_data[1]
expected = [
3.0, # weight is numeric and comes first
1.0, # animal is first categorical and cat is the most common, first row is cat
0.0, # animal, mouse is next most common, not a mouse
0.0, # animal, dog and fish tied for frequency but dog first alphabetically
0.0, # animal, fish, cat is not a fish
0.0, # color is next categorical alphabetically and blue is most common, first row blue
0.0, # black next alphabetically for ones with frequency 1
0.0, # magenta next
0.0, # purple
1.0, # red, this is red
0.0
] # yellow
assert second_row == expected
last_row = encoded_data[-1]
expected = [
99.9, # weight is numeric and comes first
0.0, # animal is first categorical and cat is the most common, first row is cat
1.0, # animal, mouse is next most common, not a mouse
0.0, # animal, dog and fish tied for frequency but dog first alphabetically
0.0, # animal, fish, cat is not a fish
0.0, # color is next categorical alphabetically and blue is most common, first row blue
1.0, # black next alphabetically for ones with frequency 1, this one black
0.0, # magenta next
0.0, # purple
0.0, # red
0.0
] # yellow
assert last_row == expected
expected_total = [[6.0, 1.0, 0.0, 0.0, 0.0, 1.0, 0.0, 0.0, 0.0, 0.0, 0.0],
[3.0, 1.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 1.0, 0.0],
[5.5, 0.0, 0.0, 1.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 1.0],
[7.0, 0.0, 0.0, 0.0, 1.0, 1.0, 0.0, 0.0, 0.0, 0.0, 0.0],
[2.0, 1.0, 0.0, 0.0, 0.0, 0.0, 0.0, 1.0, 0.0, 0.0, 0.0],
[0.0, 0.0, 1.0, 0.0, 0.0, 0.0, 0.0, 0.0, 1.0, 0.0, 0.0],
[99.9, 0.0, 1.0, 0.0, 0.0, 0.0, 1.0, 0.0, 0.0, 0.0, 0.0]]
assert encoded_data == expected_total