def test_padding_paramterised_transformer():
# load data
name = 'JapaneseVowels'
X_train, y_train = _load_dataset(name, split='train', return_X_y=True)
X_test, y_test = _load_dataset(name, split='test', return_X_y=True)
# print(X_train)
padding_transformer = PaddingTransformer(pad_length=40)
Xt = padding_transformer.fit_transform(X_train)
# when we tabulrize the data it has 12 dimensions
# and we've truncated them all to (10-2) long.
data = tabularize(Xt)
assert len(data.columns) == 40 * 12
def test_padding_transformer():
# load data
name = 'JapaneseVowels'
X_train, y_train = _load_dataset(name, split='train', return_X_y=True)
X_test, y_test = _load_dataset(name, split='test', return_X_y=True)
# print(X_train)
padding_transformer = PaddingTransformer()
Xt = padding_transformer.fit_transform(X_train)
# when we tabulrize the data it has 12 dimensions
# and we've padded them to there normal length of 29
data = tabularize(Xt)
assert len(data.columns) == 29 * 12
def test_truncation_transformer():
# load data
name = 'JapaneseVowels'
X_train, y_train = _load_dataset(name, split='train', return_X_y=True)
X_test, y_test = _load_dataset(name, split='test', return_X_y=True)
# print(X_train)
truncated_transformer = TruncationTransformer(5)
Xt = truncated_transformer.fit_transform(X_train)
# when we tabulrize the data it has 12 dimensions
# and we've truncated them all to 5 long.
data = tabularize(Xt)
assert len(data.columns) == 5 * 12
def test_truncation_paramterised_transformer():
# load data
name = "JapaneseVowels"
X_train, y_train = _load_dataset(name, split="train", return_X_y=True)
X_test, y_test = _load_dataset(name, split="test", return_X_y=True)
# print(X_train)
truncated_transformer = TruncationTransformer(2, 10)
Xt = truncated_transformer.fit_transform(X_train)
# when we tabulrize the data it has 12 dimensions
# and we've truncated them all to (10-2) long.
data = from_nested_to_2d_array(Xt)
assert len(data.columns) == 8 * 12
def test_padding_fill_value_transformer():
# load data
name = "JapaneseVowels"
X_train, y_train = _load_dataset(name, split="train", return_X_y=True)
X_test, y_test = _load_dataset(name, split="test", return_X_y=True)
# print(X_train)
padding_transformer = PaddingTransformer(pad_length=40, fill_value=1)
Xt = padding_transformer.fit_transform(X_train)
# when we tabulrize the data it has 12 dimensions
# and we've truncated them all to (10-2) long.
data = from_nested_to_2d_array(Xt)
assert len(data.columns) == 40 * 12
def test():
matplotlib.use('TkAgg')
df = _load_dataset("PLAID", None, False)
# We need this later
cols = df.columns
# Convert all of our values into lists
querys = df.values.tolist()
querydata = []
for row in querys:
querydata.append(row[0].tolist())
# Collect all the class values to a sepperate list
# for usage later
classes = []
for row in querys:
classes.append(row[1])
# Get longest element to be our candidate
candidate = []
for row in querydata:
if len(row) > len(candidate):
candidate = row
#print("Before scaling...")
#for x in range(0, 15):
# print(len(querydata[x]))
# Scale our data
scaleddata = []
for row in querydata:
scaleddata.append(us(row, candidate))
#print("After scaling...")
#for x in range(0, 15):
# print(len(scaleddata[x]))
# Crate the new dataframe from our scaled elements.
result = pd.DataFrame(columns=cols)
for row, classval in zip(scaleddata, classes):
result.append(row, classval)
make_graphs(querydata, scaleddata)