def load(self):
"""Load dataset."""
# load training and test set from separate files
X_train, y_train = load_from_tsfile_to_dataframe(
self._train_path, return_separate_X_and_y=True)
X_test, y_test = load_from_tsfile_to_dataframe(
self._test_path, return_separate_X_and_y=True)
# combine into single dataframe
data_train = pd.concat([X_train, pd.Series(y_train)], axis=1)
data_test = pd.concat([X_test, pd.Series(y_test)], axis=1)
# rename target variable
data_train.rename(columns={data_train.columns[-1]: self._target_name},
inplace=True)
data_test.rename(columns={data_test.columns[-1]: self._target_name},
inplace=True)
# concatenate the two dataframes, keeping training and test split in
# index, necessary for later optional CV
data = pd.concat([data_train, data_test],
axis=0,
keys=["train", "test"]).reset_index(level=1,
drop=True)
return data
def test_write_dataframe_to_ts_success(tmp_path, dataset):
"""Tests whether a dataset can be written by the .ts writer then read in."""
# load an example dataset
path = os.path.join(
os.path.dirname(sktime.__file__),
f"datasets/data/{dataset}/{dataset}_TEST.ts",
)
test_X, test_y = load_from_tsfile_to_dataframe(path)
# output the dataframe in a ts file
write_dataframe_to_tsfile(
data=test_X,
path=tmp_path,
problem_name=dataset,
class_label=np.unique(test_y),
class_value_list=test_y,
comment="""
The data was derived from twelve monthly electrical power demand
time series from Italy and first used in the paper "Intelligent
Icons: Integrating Lite-Weight Data Mining and Visualization into
GUI Operating Systems". The classification task is to distinguish
days from Oct to March (inclusive) from April to September.
""",
fold="_transform",
)
# load data back from the ts file
result = f"{tmp_path}/{dataset}/{dataset}_transform.ts"
res_X, res_y = load_from_tsfile_to_dataframe(result)
# check if the dataframes are the same
assert_frame_equal(res_X, test_X)
def read_ts(
filepath: str, **kwargs
) -> Tuple[Union[DenseFunctionalData, IrregularFunctionalData], np.ndarray]:
"""Read a ts file into Functional Data.
Build a DenseFunctionalData or IrregularFunctionalData object upon a ts
file passed as parameter.
Notes
-----
We assumed that the data are unidimensional and is not checked.
Parameters
----------
filepath: str
Any valid string path is acceptable.
**kwargs:
Keywords arguments to passed to the load_from_tsfile_to_dataframe
function.
Returns
-------
obj: DenseFunctionalData or IrregularFunctionalData
The loaded csv file.
labels: np.ndarray
Labels
"""
data, labels = load_from_tsfile_to_dataframe(filepath, **kwargs)
len_argavals = data.applymap(len)['dim_0'].unique()
if len(len_argavals) == 1:
obj = read_ts_dense(data)
else:
obj = read_ts_irregular(data)
return obj, labels
def test_load_from_tsfile_to_dataframe():
"""Test the load_from_tsfile_to_dataframe() function."""
# Test that an empty file is classed an invalid
fd, path = tempfile.mkstemp()
try:
with os.fdopen(fd, "w") as tmp_file:
# Write the contents of the file
file_contents = ""
tmp_file.write(file_contents)
tmp_file.flush()
# Parse the file and assert that it is invalid
np.testing.assert_raises(IOError, load_from_tsfile_to_dataframe,
path)
finally:
os.remove(path)
# Test that a file with an incomplete set of metadata is invalid
fd, path = tempfile.mkstemp()
try:
with os.fdopen(fd, "w") as tmp_file:
# Write the contents of the file
file_contents = ("@problemName Test Problem\n@timeStamps "
"true\n@univariate true\n")
tmp_file.write(file_contents)
tmp_file.flush()
# Parse the file and assert that it is invalid
np.testing.assert_raises(IOError, load_from_tsfile_to_dataframe,
path)
finally:
os.remove(path)
# Test that a file with a complete set of metadata but no data is invalid
fd, path = tempfile.mkstemp()
try:
with os.fdopen(fd, "w") as tmp_file:
# Write the contents of the file
file_contents = (
"@problemName Test Problem\n@timeStamps "
"true\n@univariate true\n@classLabel false\n@data")
tmp_file.write(file_contents)
tmp_file.flush()
# Parse the file and assert that it is invalid
np.testing.assert_raises(IOError, load_from_tsfile_to_dataframe,
path)
finally:
os.remove(path)
# Test that a file with a complete set of metadata and no data but
# invalid metadata values is invalid
fd, path = tempfile.mkstemp()
try:
with os.fdopen(fd, "w") as tmp_file:
# Write the contents of the file
file_contents = ("@problemName\n@timeStamps\n@univariate "
"true\n@classLabel false\n@data")
tmp_file.write(file_contents)
tmp_file.flush()
# Parse the file and assert that it is invalid
np.testing.assert_raises(IOError, load_from_tsfile_to_dataframe,
path)
finally:
os.remove(path)
# Test that a file with a complete set of metadata and a single
# case/dimension parses correctly
fd, path = tempfile.mkstemp()
try:
with os.fdopen(fd, "w") as tmp_file:
# Write the contents of the file
file_contents = ("@problemName Test Problem\n@timeStamps "
"true\n@univariate true\n@classLabel "
"false\n@data\n")
file_contents += "(0, 1), (1, 2)"
tmp_file.write(file_contents)
tmp_file.flush()
# Parse the file
df = load_from_tsfile_to_dataframe(path)
# Test the DataFrame returned accurately reflects the data in
# the file
np.testing.assert_equal(len(df), 1)
np.testing.assert_equal(len(df.columns), 1)
series = df["dim_0"]
np.testing.assert_equal(len(series), 1)
series = df["dim_0"][0]
np.testing.assert_equal(series[0], 1.0)
np.testing.assert_equal(series[1], 2.0)
finally:
os.remove(path)
# Test that a file with a complete set of metadata and 2 cases with 3
# dimensions parses correctly
fd, path = tempfile.mkstemp()
try:
with os.fdopen(fd, "w") as tmp_file:
# Write the contents of the file
file_contents = ("@problemName Test Problem\n@timeStamps "
"true\n@univariate true\n@classLabel "
"false\n@data\n")
file_contents += "(0, 1), (1, 2):(0, 3), (1, 4):(0, 5), (1, 6)\n"
file_contents += "(0, 11), (1, 12):(0, 13), (1,14):(0, 15), (1, 16) \n"
tmp_file.write(file_contents)
tmp_file.flush()
# Parse the file
df = load_from_tsfile_to_dataframe(path)
# Test the DataFrame returned accurately reflects the data in
# the file
np.testing.assert_equal(len(df), 2)
np.testing.assert_equal(len(df.columns), 3)
series = df["dim_0"]
np.testing.assert_equal(len(series), 2)
series = df["dim_0"][0]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 1.0)
np.testing.assert_equal(series[1], 2.0)
series = df["dim_0"][1]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 11.0)
np.testing.assert_equal(series[1], 12.0)
series = df["dim_1"]
np.testing.assert_equal(len(series), 2)
series = df["dim_1"][0]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 3.0)
np.testing.assert_equal(series[1], 4.0)
series = df["dim_1"][1]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 13.0)
np.testing.assert_equal(series[1], 14.0)
series = df["dim_2"]
np.testing.assert_equal(len(series), 2)
series = df["dim_2"][0]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 5.0)
np.testing.assert_equal(series[1], 6.0)
series = df["dim_2"][1]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 15.0)
np.testing.assert_equal(series[1], 16.0)
finally:
os.remove(path)
# Test that a file with a complete set of metadata and time-series of
# different length parses correctly
fd, path = tempfile.mkstemp()
try:
with os.fdopen(fd, "w") as tmp_file:
# Write the contents of the file
file_contents = ("@problemName Test Problem\n@timeStamps "
"true\n@univariate true\n@classLabel "
"false\n@data\n")
file_contents += "(0, 1), (1, 2):(0, 3):(0, 5), (1, 6)\n"
file_contents += "(0, 11), (1, 12):(0, 13), (1,14):(0, 15)\n"
tmp_file.write(file_contents)
tmp_file.flush()
# Parse the file
df = load_from_tsfile_to_dataframe(path)
# Test the DataFrame returned accurately reflects the data in
# the file
np.testing.assert_equal(len(df), 2)
np.testing.assert_equal(len(df.columns), 3)
series = df["dim_0"]
np.testing.assert_equal(len(series), 2)
series = df["dim_0"][0]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 1.0)
np.testing.assert_equal(series[1], 2.0)
series = df["dim_0"][1]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 11.0)
np.testing.assert_equal(series[1], 12.0)
series = df["dim_1"]
np.testing.assert_equal(len(series), 2)
series = df["dim_1"][0]
np.testing.assert_equal(len(series), 1)
np.testing.assert_equal(series[0], 3.0)
series = df["dim_1"][1]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 13.0)
np.testing.assert_equal(series[1], 14.0)
series = df["dim_2"]
np.testing.assert_equal(len(series), 2)
series = df["dim_2"][0]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 5.0)
np.testing.assert_equal(series[1], 6.0)
series = df["dim_2"][1]
np.testing.assert_equal(len(series), 1)
np.testing.assert_equal(series[0], 15.0)
finally:
os.remove(path)
# Test that a file with a complete set of metadata and data but an
# inconsistent number of dimensions across cases is classed as invalid
fd, path = tempfile.mkstemp()
try:
with os.fdopen(fd, "w") as tmp_file:
# Write the contents of the file
file_contents = ("@problemName Test Problem\n@timeStamps "
"true\n@univariate true\n@classLabel "
"false\n@data\n")
file_contents += "(0, 1), (1, 2):(0, 3), (1, 4):(0, 5), (1, 6)\n"
file_contents += "(0, 11), (1, 12):(0, 13), (1,14) \n"
tmp_file.write(file_contents)
tmp_file.flush()
# Parse the file and assert that it is invalid
np.testing.assert_raises(IOError, load_from_tsfile_to_dataframe,
path)
finally:
os.remove(path)
# Test that a file with a complete set of metadata and data but missing
# values after a tuple is classed as invalid
fd, path = tempfile.mkstemp()
try:
with os.fdopen(fd, "w") as tmp_file:
# Write the contents of the file
file_contents = ("@problemName Test Problem\n@timeStamps "
"true\n@univariate true\n@classLabel "
"false\n@data\n")
file_contents += "(0, 1), (1, 2):(0, 3), (1, 4):(0, 5),\n"
tmp_file.write(file_contents)
tmp_file.flush()
# Parse the file and assert that it is invalid
np.testing.assert_raises(IOError, load_from_tsfile_to_dataframe,
path)
finally:
os.remove(path)
# Test that a file with a complete set of metadata and data and some
# empty dimensions is classed as valid
fd, path = tempfile.mkstemp()
try:
with os.fdopen(fd, "w") as tmp_file:
# Write the contents of the file
file_contents = ("@problemName Test Problem\n@timeStamps "
"true\n@univariate true\n@classLabel "
"false\n@data\n")
file_contents += "(0, 1), (1, 2): :(0, 5), (1, 6)\n"
file_contents += "(0, 11), (1, 12):(0, 13), (1,14) : \n"
file_contents += (
"(0, 21), (1, 22):(0, 23), (1,24) : (0,25), (1, 26) \n"
)
tmp_file.write(file_contents)
tmp_file.flush()
# Parse the file
df = load_from_tsfile_to_dataframe(path)
# Test the DataFrame returned accurately reflects the data in
# the file
np.testing.assert_equal(len(df), 3)
np.testing.assert_equal(len(df.columns), 3)
series = df["dim_0"]
np.testing.assert_equal(len(series), 3)
series = df["dim_0"][0]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 1.0)
np.testing.assert_equal(series[1], 2.0)
series = df["dim_0"][1]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 11.0)
np.testing.assert_equal(series[1], 12.0)
series = df["dim_0"][2]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 21.0)
np.testing.assert_equal(series[1], 22.0)
series = df["dim_1"]
np.testing.assert_equal(len(series), 3)
series = df["dim_1"][0]
np.testing.assert_equal(len(series), 0)
series = df["dim_1"][1]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 13.0)
np.testing.assert_equal(series[1], 14.0)
series = df["dim_1"][2]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 23.0)
np.testing.assert_equal(series[1], 24.0)
series = df["dim_2"]
np.testing.assert_equal(len(series), 3)
series = df["dim_2"][0]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 5.0)
np.testing.assert_equal(series[1], 6.0)
series = df["dim_2"][1]
np.testing.assert_equal(len(series), 0)
series = df["dim_2"][2]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 25.0)
np.testing.assert_equal(series[1], 26.0)
finally:
os.remove(path)
# Test that a file with a complete set of metadata and data that
# contains datetimes as timestamps and has some empty dimensions is
# classed as valid
fd, path = tempfile.mkstemp()
try:
with os.fdopen(fd, "w") as tmp_file:
# Write the contents of the file
file_contents = ("@problemName Test Problem\n@timeStamps "
"true\n@univariate true\n@classLabel "
"false\n@data\n")
file_contents += ("(01/01/2019 00:00:00, 1), (01/02/2019 "
"00:00:00, 2) : "
" : (01/05/2019 00:00:00, "
"5), (01/06/2019 00:00:00, 6)\n")
file_contents += ("(01/01/2020 00:00:00, 11), (01/02/2020 "
"00:00:00, 12) : (01/03/2020 00:00:00, 13), "
"(01/04/2020 00:00:00, 14) : \n")
file_contents += ("(01/01/2021 00:00:00, 21), (01/02/2021 "
"00:00:00, 22) : (01/03/2021 00:00:00, 23), "
"(01/04/2021 00:00:00, 24) : \n")
tmp_file.write(file_contents)
tmp_file.flush()
# Parse the file
df = load_from_tsfile_to_dataframe(path)
# Test the DataFrame returned accurately reflects the data in
# the file
np.testing.assert_equal(len(df), 3)
np.testing.assert_equal(len(df.columns), 3)
series = df["dim_0"]
np.testing.assert_equal(len(series), 3)
series = df["dim_0"][0]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series["01/01/2019"], 1.0)
np.testing.assert_equal(series["01/02/2019"], 2.0)
series = df["dim_0"][1]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series["01/01/2020"], 11.0)
np.testing.assert_equal(series["01/02/2020"], 12.0)
series = df["dim_0"][2]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series["01/01/2021"], 21.0)
np.testing.assert_equal(series["01/02/2021"], 22.0)
series = df["dim_1"]
np.testing.assert_equal(len(series), 3)
series = df["dim_1"][0]
np.testing.assert_equal(len(series), 0)
series = df["dim_1"][1]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series["01/03/2020"], 13.0)
np.testing.assert_equal(series["01/04/2020"], 14.0)
series = df["dim_1"][2]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series["01/03/2021"], 23.0)
np.testing.assert_equal(series["01/04/2021"], 24.0)
series = df["dim_2"]
np.testing.assert_equal(len(series), 3)
series = df["dim_2"][0]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series["01/05/2019"], 5.0)
np.testing.assert_equal(series["01/06/2019"], 6.0)
series = df["dim_2"][1]
np.testing.assert_equal(len(series), 0)
series = df["dim_2"][2]
np.testing.assert_equal(len(series), 0)
finally:
os.remove(path)
# Test that a file that mixes timestamp conventions is invalid
fd, path = tempfile.mkstemp()
try:
with os.fdopen(fd, "w") as tmp_file:
# Write the contents of the file
file_contents = ("@problemName Test Problem\n@timeStamps "
"true\n@univariate true\n@classLabel "
"false\n@data\n")
file_contents += ("(01/01/2019 00:00:00, 1), (01/02/2019 "
"00:00:00, 2) : "
" : (01/05/2019 00:00:00, "
"5), (01/06/2019 00:00:00, 6)\n")
file_contents += ("(00, 11), (1, 12) : (01/03/2020 00:00:00, 13), "
"(01/04/2020 00:00:00, 14) : \n")
file_contents += ("(01/01/2021 00:00:00, 21), (01/02/2021 "
"00:00:00, 22) : (01/03/2021 00:00:00, 23), "
"(01/04/2021 00:00:00, 24) : \n")
tmp_file.write(file_contents)
tmp_file.flush()
# Parse the file and assert that it is invalid
np.testing.assert_raises(IOError, load_from_tsfile_to_dataframe,
path)
finally:
os.remove(path)
# Test that a file with a complete set of metadata and data but missing
# classes is classed as invalid
fd, path = tempfile.mkstemp()
try:
with os.fdopen(fd, "w") as tmp_file:
# Write the contents of the file
file_contents = ("@problemName Test Problem\n@timeStamps "
"true\n@univariate true\n@classLabel true 0 1 "
"2\n@data\n")
file_contents += "(0, 1), (1, 2):(0, 3), (1, 4):(0, 5), (1, 6)\n"
file_contents += "(0, 11), (1, 12):(0, 13), (1,14):(0, 15), (1, 16) \n"
tmp_file.write(file_contents)
tmp_file.flush()
# Parse the file and assert that it is invalid
np.testing.assert_raises(IOError, load_from_tsfile_to_dataframe,
path)
finally:
os.remove(path)
# Test that a file with a complete set of metadata and data but invalid
# classes is classed as invalid
fd, path = tempfile.mkstemp()
try:
with os.fdopen(fd, "w") as tmp_file:
# Write the contents of the file
file_contents = ("@problemName Test Problem\n@timeStamps "
"true\n@univariate true\n@classLabel true 0 1 "
"2\n@data\n")
file_contents += "(0, 1), (1, 2):(0, 3), (1, 4):(0, 5), (1, 6) : 0 \n"
file_contents += (
"(0, 11), (1, 12):(0, 13), (1,14):(0, 15), (1, 16) : 3 \n")
tmp_file.write(file_contents)
tmp_file.flush()
# Parse the file and assert that it is invalid
np.testing.assert_raises(IOError, load_from_tsfile_to_dataframe,
path)
finally:
os.remove(path)
# Test that a file with a complete set of metadata and data with classes
# is classed as valid
fd, path = tempfile.mkstemp()
try:
with os.fdopen(fd, "w") as tmp_file:
# Write the contents of the file
file_contents = ("@problemName Test Problem\n@timeStamps "
"true\n@univariate true\n@classLabel true 0 1 "
"2\n@data\n")
file_contents += "(0, 1), (1, 2):(0, 3), (1, 4):(0, 5), (1, 6): 0\n"
file_contents += (
"(0, 11), (1, 12):(0, 13), (1,14):(0, 15), (1, 16): 2 \n")
tmp_file.write(file_contents)
tmp_file.flush()
# Parse the file
df, y = load_from_tsfile_to_dataframe(path)
# Test the DataFrame of X values returned accurately reflects
# the data in the file
np.testing.assert_equal(len(df), 2)
np.testing.assert_equal(len(df.columns), 3)
series = df["dim_0"]
np.testing.assert_equal(len(series), 2)
series = df["dim_0"][0]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 1.0)
np.testing.assert_equal(series[1], 2.0)
series = df["dim_0"][1]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 11.0)
np.testing.assert_equal(series[1], 12.0)
series = df["dim_1"]
np.testing.assert_equal(len(series), 2)
series = df["dim_1"][0]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 3.0)
np.testing.assert_equal(series[1], 4.0)
series = df["dim_1"][1]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 13.0)
np.testing.assert_equal(series[1], 14.0)
series = df["dim_2"]
np.testing.assert_equal(len(series), 2)
series = df["dim_2"][0]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 5.0)
np.testing.assert_equal(series[1], 6.0)
series = df["dim_2"][1]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 15.0)
np.testing.assert_equal(series[1], 16.0)
# Test that the class values are as expected
np.testing.assert_equal(len(y), 2)
np.testing.assert_equal(y[0], "0")
np.testing.assert_equal(y[1], "2")
finally:
os.remove(path)
# Test that a file with a complete set of metadata and data, with no
# timestamps, is classed as valid
fd, path = tempfile.mkstemp()
try:
with os.fdopen(fd, "w") as tmp_file:
# Write the contents of the file
file_contents = ("@problemName Test Problem\n@timeStamps "
"false\n@univariate true\n@classLabel "
"false\n@data\n")
file_contents += "1,2:3,4:5,6\n"
file_contents += "11,12:13,14:15,16\n"
file_contents += "21,22:23,24:25,26\n"
tmp_file.write(file_contents)
tmp_file.flush()
# Parse the file
df = load_from_tsfile_to_dataframe(path)
# Test the DataFrame returned accurately reflects the data in
# the file
np.testing.assert_equal(len(df), 3)
np.testing.assert_equal(len(df.columns), 3)
series = df["dim_0"]
np.testing.assert_equal(len(series), 3)
series = df["dim_0"][0]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 1.0)
np.testing.assert_equal(series[1], 2.0)
series = df["dim_0"][1]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 11.0)
np.testing.assert_equal(series[1], 12.0)
series = df["dim_0"][2]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 21.0)
np.testing.assert_equal(series[1], 22.0)
series = df["dim_1"]
np.testing.assert_equal(len(series), 3)
series = df["dim_1"][0]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 3.0)
np.testing.assert_equal(series[1], 4.0)
series = df["dim_1"][1]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 13.0)
np.testing.assert_equal(series[1], 14.0)
series = df["dim_1"][2]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 23.0)
np.testing.assert_equal(series[1], 24.0)
series = df["dim_2"]
np.testing.assert_equal(len(series), 3)
series = df["dim_2"][0]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 5.0)
np.testing.assert_equal(series[1], 6.0)
series = df["dim_2"][1]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 15.0)
np.testing.assert_equal(series[1], 16.0)
series = df["dim_2"][2]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 25.0)
np.testing.assert_equal(series[1], 26.0)
finally:
os.remove(path)
# Test that a file with a complete set of metadata and data, with no
# timestamps and some empty dimensions, is classed as valid
fd, path = tempfile.mkstemp()
try:
with os.fdopen(fd, "w") as tmp_file:
# Write the contents of the file
file_contents = ("@problemName Test Problem\n@timeStamps "
"false\n@univariate true\n@classLabel "
"false\n@data\n")
file_contents += "1,2::5,6\n"
file_contents += "11,12:13,14:15,16\n"
file_contents += "21,22:23,24:\n"
tmp_file.write(file_contents)
tmp_file.flush()
# Parse the file
df = load_from_tsfile_to_dataframe(path)
# Test the DataFrame returned accurately reflects the data in
# the file
np.testing.assert_equal(len(df), 3)
np.testing.assert_equal(len(df.columns), 3)
series = df["dim_0"]
np.testing.assert_equal(len(series), 3)
series = df["dim_0"][0]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 1.0)
np.testing.assert_equal(series[1], 2.0)
series = df["dim_0"][1]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 11.0)
np.testing.assert_equal(series[1], 12.0)
series = df["dim_0"][2]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 21.0)
np.testing.assert_equal(series[1], 22.0)
series = df["dim_1"]
np.testing.assert_equal(len(series), 3)
series = df["dim_1"][0]
np.testing.assert_equal(len(series), 0)
series = df["dim_1"][1]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 13.0)
np.testing.assert_equal(series[1], 14.0)
series = df["dim_1"][2]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 23.0)
np.testing.assert_equal(series[1], 24.0)
series = df["dim_2"]
np.testing.assert_equal(len(series), 3)
series = df["dim_2"][0]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 5.0)
np.testing.assert_equal(series[1], 6.0)
series = df["dim_2"][1]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 15.0)
np.testing.assert_equal(series[1], 16.0)
series = df["dim_2"][2]
np.testing.assert_equal(len(series), 0)
finally:
os.remove(path)
# Test that a file with a complete set of metadata and data, with no
# timestamps and some empty dimensions and classes, is classed as valid
fd, path = tempfile.mkstemp()
try:
with os.fdopen(fd, "w") as tmp_file:
# Write the contents of the file
file_contents = ("@problemName Test Problem\n@timeStamps "
"false\n@univariate true\n@classLabel true cat "
"bear dog\n@data\n")
file_contents += "1,2::5,6:cat \n"
file_contents += "11,12:13,14:15,16: dog\n"
file_contents += "21,22:23,24:: bear \n"
tmp_file.write(file_contents)
tmp_file.flush()
# Parse the file
df, y = load_from_tsfile_to_dataframe(path)
# Test the DataFrame of X values returned accurately reflects
# the data in the file
np.testing.assert_equal(len(df), 3)
np.testing.assert_equal(len(df.columns), 3)
series = df["dim_0"]
np.testing.assert_equal(len(series), 3)
series = df["dim_0"][0]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 1.0)
np.testing.assert_equal(series[1], 2.0)
series = df["dim_0"][1]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 11.0)
np.testing.assert_equal(series[1], 12.0)
series = df["dim_0"][2]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 21.0)
np.testing.assert_equal(series[1], 22.0)
series = df["dim_1"]
np.testing.assert_equal(len(series), 3)
series = df["dim_1"][0]
np.testing.assert_equal(len(series), 0)
series = df["dim_1"][1]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 13.0)
np.testing.assert_equal(series[1], 14.0)
series = df["dim_1"][2]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 23.0)
np.testing.assert_equal(series[1], 24.0)
series = df["dim_2"]
np.testing.assert_equal(len(series), 3)
series = df["dim_2"][0]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 5.0)
np.testing.assert_equal(series[1], 6.0)
series = df["dim_2"][1]
np.testing.assert_equal(len(series), 2)
np.testing.assert_equal(series[0], 15.0)
np.testing.assert_equal(series[1], 16.0)
series = df["dim_2"][2]
np.testing.assert_equal(len(series), 0)
# Test that the class values are as expected
np.testing.assert_equal(len(y), 3)
np.testing.assert_equal(y[0], "cat")
np.testing.assert_equal(y[1], "dog")
np.testing.assert_equal(y[2], "bear")
finally:
os.remove(path)