def test_with_stride_and_lag(self):
reader = CSVReader(self.filename1)
for s in [2, 3, 7, 10]:
for t in [1, 23, 7, 59]:
chunks = []
chunks_lag = []
it = reader.iterator(stride=s, lag=t)
with it:
for _, X, Y in it:
chunks.append(X)
chunks_lag.append(Y)
chunks = np.vstack(chunks)
chunks_lag = np.vstack(chunks_lag)
actual_lagged = self.data[t::s]
np.testing.assert_almost_equal(
chunks,
self.data[::s][0:len(actual_lagged)],
err_msg="output is not equal for"
" lag %i and stride %i" % (t, s))
np.testing.assert_almost_equal(
chunks_lag,
self.data[t::s],
err_msg="output is not equal for"
" lag %i and stride %i" % (t, s))
def test_reset(self):
reader = CSVReader((self.filename1, self.filename2))
it = reader.iterator()
data = [chunk for chunk in it]
it.reset()
data2 = [chunk for chunk in it]
np.testing.assert_equal(data, data2)
def test_with_lag(self):
reader = CSVReader(self.filename1)
for t in [23, 7, 59]:
chunks = []
for _, _, Y in reader.iterator(stride=1, lag=t):
chunks.append(Y)
chunks = np.vstack(chunks)
np.testing.assert_almost_equal(chunks, self.data[t:])
def test_with_lag(self):
reader = CSVReader(self.filename1)
for t in [23, 7, 59]:
chunks = []
for _, _, Y in reader.iterator(stride=1, lag=t):
chunks.append(Y)
chunks = np.vstack(chunks)
np.testing.assert_almost_equal(chunks, self.data[t:])
def test_read_lagged_small_chunks(self):
lag = 200
reader = CSVReader(self.filename1, chunksize=30)
lagged_data = self.data[lag:]
lagged_chunks = []
for _, _, Y in reader.iterator(lag=lag):
# kick out empty chunks
if Y.shape[0] > 0:
lagged_chunks.append(Y)
lagged_chunks = np.vstack(lagged_chunks)
np.testing.assert_almost_equal(lagged_chunks, lagged_data)
def test_read_lagged_small_chunks(self):
lag = 200
reader = CSVReader(self.filename1, chunksize=30)
lagged_data = self.data[lag:]
lagged_chunks = []
for _, _, Y in reader.iterator(lag=lag):
# kick out empty chunks
if Y.shape[0] > 0:
lagged_chunks.append(Y)
lagged_chunks = np.vstack(lagged_chunks)
np.testing.assert_almost_equal(lagged_chunks, lagged_data)
def test_read_lagged_small_chunks(self):
lag = 200
reader = CSVReader(self.filename1, chunksize=30)
lagged_data = self.data[lag:]
lagged_chunks = []
it = reader.iterator(lag=lag)
with it:
for _, _, Y in it:
assert len(Y) > 0
lagged_chunks.append(Y)
lagged_chunks = np.vstack(lagged_chunks)
np.testing.assert_almost_equal(lagged_chunks, lagged_data)
def test_with_stride_and_lag_with_header(self):
reader = CSVReader(self.file_with_header)
for s in [2, 3, 7, 10]:
for t in [1, 23, 7, 59]:
chunks = []
chunks_lag = []
for _, X, Y in reader.iterator(stride=s, lag=t):
chunks.append(X)
chunks_lag.append(Y)
chunks = np.vstack(chunks)
chunks_lag = np.vstack(chunks_lag)
np.testing.assert_almost_equal(chunks, self.data[::s])
np.testing.assert_almost_equal(chunks_lag, self.data[t::s],
err_msg="output is not equal for"
" lag %i and stride %i" % (t, s))
def test_with_stride_and_lag_with_header(self):
reader = CSVReader(self.file_with_header)
for s in [2, 3, 7, 10]:
for t in [1, 23, 7, 59]:
chunks = []
chunks_lag = []
for _, X, Y in reader.iterator(stride=s, lag=t):
chunks.append(X)
chunks_lag.append(Y)
chunks = np.vstack(chunks)
chunks_lag = np.vstack(chunks_lag)
np.testing.assert_almost_equal(chunks, self.data[::s])
np.testing.assert_almost_equal(
chunks_lag,
self.data[t::s],
err_msg="output is not equal for"
" lag %i and stride %i" % (t, s))
def test_use_cols(self):
reader = CSVReader(self.filename1)
cols = (0, 2)
with reader.iterator(chunk=0, cols=cols, return_trajindex=False) as it:
for x in it:
np.testing.assert_equal(x, self.data[:, cols])
