class TestAverageCountOne:
test_average_count = RWATestOptions(
file_id_content_map={
0: "ha ha \n ha ha \n la ta \n ha \n ta ta \n la la"},
rolling_windows_options=RWAFrontEndOptions(
ratio_token_options=None,
average_token_options=RWAAverageTokenOptions(
token_type=RWATokenType.string,
tokens=["ta", "ha"]),
passage_file_id=0,
window_options=RWAWindowOptions(
window_size=2,
window_unit=WindowUnitType.line
),
plot_options=RWAPlotOptions(
individual_points=False,
black_white=False
),
milestone=None
)
)
# Get the rolling window model and other testing components.
rw_average_model = RollingWindowsModel(test_option=test_average_count)
rw_average_windows = rw_average_model._get_windows()
rw_average_graph = rw_average_model._generate_rwa_graph()
rw_average_csv_frame = rw_average_model._get_rwa_csv_frame()
def test_get_windows(self):
np.testing.assert_array_equal(
self.rw_average_windows,
['ha ha \n ha ha \n', ' ha ha \n la ta \n', ' la ta \n ha \n',
' ha \n ta ta \n', ' ta ta \n la la']
)
def test_generate_rwa_graph(self):
assert self.rw_average_graph['data'][0]['type'] == 'scattergl'
np.testing.assert_array_equal(
self.rw_average_graph['data'][0]['x'],
[0., 1., 2., 3., 4.]
)
np.testing.assert_array_equal(
self.rw_average_graph['data'][0]['y'],
[0., 0.5, 0.5, 1., 1.]
)
assert self.rw_average_graph['data'][1]['mode'] == 'lines'
assert self.rw_average_graph['data'][1]['name'] == 'ha'
def test_csv_frame(self):
pd.testing.assert_frame_equal(
self.rw_average_csv_frame,
pd.DataFrame(
index=[0, 1, 2, 3, 4],
columns=["ta", "ha"],
data=[[0., 2.], [0.5, 1.], [0.5, 0.5], [1., 0.5], [1., 0.]]
)
)
class TestRatioCountTwo:
test_ratio_count = RWATestOptions(
file_id_content_map={0: "ha ha ha ha la ta ha \n ha ha \n ta ha",
1: "la la ta ta da da ha"},
rolling_windows_options=RWAFrontEndOptions(
ratio_token_options=RWARatioTokenOptions(
token_type=RWATokenType.word,
token_frame=pd.DataFrame(
data={
"numerator": ["ha"],
"denominator": ["la"]
}
)
),
average_token_options=None,
passage_file_id=0,
window_options=RWAWindowOptions(
window_size=2,
window_unit=WindowUnitType.word
),
plot_options=RWAPlotOptions(
individual_points=False,
black_white=False
),
milestone="ta"
)
)
# Get the rolling window model and other testing components.
rw_ratio_model = RollingWindowsModel(test_option=test_ratio_count)
rw_ratio_windows = rw_ratio_model._get_windows()
rw_ratio_graph = rw_ratio_model._generate_rwa_graph()
rw_ratio_milestone = \
rw_ratio_model._find_mile_stone_windows_indexes_in_all_windows(
windows=rw_ratio_windows
)
def test_get_windows(self):
np.testing.assert_array_equal(
self.rw_ratio_windows,
['ha ha ', 'ha ha ', 'ha ha ', 'ha la ', 'la ta ', 'ta ha \n ',
'ha \n ha ', 'ha ha \n ', 'ha \n ta ', 'ta ha'])
def test_generate_rwa_graph(self):
assert self.rw_ratio_graph['data'][0]['type'] == 'scattergl'
np.testing.assert_array_equal(
self.rw_ratio_graph['data'][0]['x'],
[0., 1., 2., 3., 4., 5., 6., 7., 8., 9.]
)
np.testing.assert_array_equal(
self.rw_ratio_graph['data'][0]['y'],
[1., 1., 1., 0.5, 0., 1., 1., 1., 1., 1.]
)
def test_find_milestone(self):
assert self.rw_ratio_milestone == {'t': [5, 9],
'a': []}
class TestRatioCountOne:
test_ratio_count = RWATestOptions(
file_id_content_map={
0: "ha ha ha ha la ta ha",
1: "la la ta ta da da ha"
},
rolling_windows_options=RWAFrontEndOptions(
ratio_token_options=RWARatioTokenOptions(
token_type=RWATokenType.string,
token_frame=pd.DataFrame(data={
"numerator": ["t"],
"denominator": ["a"]
})),
average_token_options=None,
passage_file_id=0,
window_options=RWAWindowOptions(window_size=3,
window_unit=WindowUnitType.letter),
plot_options=RWAPlotOptions(individual_points=False,
black_white=False),
milestone="ta"))
# Get the rolling window model and other test components
rw_ratio_model = RollingWindowsModel(test_option=test_ratio_count)
rw_ratio_windows = rw_ratio_model._get_windows()
rw_ratio_graph = rw_ratio_model._generate_rwa_graph()
rw_ratio_csv_frame = rw_ratio_model._get_rwa_csv_frame()
rw_ratio_milestone = \
rw_ratio_model._find_mile_stone_windows_indexes_in_all_windows(
windows=rw_ratio_windows
)
def test_get_windows(self):
np.testing.assert_array_equal(self.rw_ratio_windows, [
'ha ', 'a h', ' ha', 'ha ', 'a h', ' ha', 'ha ', 'a h', ' ha',
'ha ', 'a l', ' la', 'la ', 'a t', ' ta', 'ta ', 'a h', ' ha'
])
def test_token_ratio_windows(self):
pd.testing.assert_series_equal(
left=self.rw_ratio_model._find_token_ratio_in_windows(
numerator_token="t",
denominator_token="a",
windows=self.rw_ratio_windows),
right=pd.Series(data=[
0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0,
0.0, 0.5, 0.5, 0.5, 0.0, 0.0
], ),
check_names=False)
def test_generate_rwa_graph(self):
assert self.rw_ratio_graph['data'][0]['type'] == 'scattergl'
np.testing.assert_array_equal(
self.rw_ratio_graph['data'][0]['x'],
[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17])
np.testing.assert_array_equal(self.rw_ratio_graph['data'][0]['y'], [
0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0,
0.5, 0.5, 0.5, 0.0, 0.0
])
def test_find_milestone(self):
assert self.rw_ratio_milestone == {
't': [15],
'a': [1, 4, 7, 10, 13, 16]
}
def test_csv_frame(self):
pd.testing.assert_frame_equal(
self.rw_ratio_csv_frame,
pd.DataFrame(index=[
0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17
],
columns=["t / (t + a)"],
data=[[0.], [0.], [0.], [0.], [0.], [0.], [0.], [0.],
[0.], [0.], [0.], [0.], [0.], [0.5], [0.5],
[0.5], [0.], [0.]]))