def test_to_dict_without_categories(self):
tdm = get_term_doc_matrix_without_categories()
scatter_chart = ScatterChart(term_doc_matrix=tdm,
minimum_term_frequency=0)
with self.assertRaises(NeedToInjectCoordinatesException):
scatter_chart.to_dict_without_categories()
x_coords = tdm.get_term_doc_mat().sum(axis=0).A1
y_coords = tdm.get_term_doc_mat().astype(bool).astype(int).sum(
axis=0).A1
scatter_chart.inject_coordinates(original_x=x_coords,
original_y=y_coords,
x_coords=scale(x_coords),
y_coords=scale(y_coords))
j = scatter_chart.to_dict_without_categories()
self.assertIsInstance(j, dict)
self.assertEqual(set(j.keys()), set(['data']))
self.assertEqual(len(j['data']), tdm.get_num_terms())
self.assertEqual(
j['data'][-1], {
'cat': 4,
'cat25k': 735,
'ox': 4,
'oy': 3,
'term': 'speak',
'x': 1.0,
'y': 1.0
})
def test_inject_coordinates_original(self):
tdm = build_hamlet_jz_term_doc_mat()
freq_df = tdm.get_term_freq_df()
scatter_chart = ScatterChart(term_doc_matrix=tdm,
minimum_term_frequency=0)
x = freq_df[freq_df.columns[1]].astype(np.float)
y = freq_df[freq_df.columns[0]].astype(np.float)
scatter_chart.inject_coordinates(x / x.max(), y / y.max(), original_x=x, original_y=y)
j = scatter_chart.to_dict('hamlet')
self.assertEqual(j['data'][0].keys(),
{'x', 'os', 'y', 'ncat25k', 'neut', 'cat25k', 'ox', 'neut25k', 'extra25k', 'extra', 'oy',
'term',
's', 'bg'})
and_term = [t for t in j['data'] if t['term'] == 'and'][0]
self.assertEqual(and_term['ox'], 0)
self.assertEqual(and_term['oy'], 1)
def test_inject_coordinates_original(self):
tdm = build_hamlet_jz_term_doc_mat()
freq_df = tdm.get_term_freq_df()
scatter_chart = ScatterChart(term_doc_matrix=tdm,
minimum_term_frequency=0)
x = freq_df[freq_df.columns[1]].astype(np.float)
y = freq_df[freq_df.columns[0]].astype(np.float)
scatter_chart.inject_coordinates(x / x.max(), y / y.max(), original_x=x, original_y=y)
j = scatter_chart.to_dict('hamlet')
self.assertEqual(j['data'][0].keys(),
{'x', 'os', 'y', 'ncat25k', 'neut', 'cat25k', 'ox', 'neut25k', 'extra25k', 'extra', 'oy',
'term',
's', 'bg'})
and_term = [t for t in j['data'] if t['term'] == 'and'][0]
self.assertEqual(and_term['ox'], 0)
self.assertEqual(and_term['oy'], 1)
def test_to_dict_without_categories(self):
tdm = get_term_doc_matrix_without_categories()
scatter_chart = ScatterChart(term_doc_matrix=tdm, minimum_term_frequency=0)
with self.assertRaises(NeedToInjectCoordinatesException):
scatter_chart.to_dict_without_categories()
x_coords = tdm.get_term_doc_mat().sum(axis=0).A1
y_coords = tdm.get_term_doc_mat().astype(bool).astype(int).sum(axis=0).A1
scatter_chart.inject_coordinates(original_x=x_coords,
original_y=y_coords,
x_coords=scale(x_coords),
y_coords=scale(y_coords))
j = scatter_chart.to_dict_without_categories()
self.assertIsInstance(j, dict)
self.assertEqual(set(j.keys()), set(['data']))
self.assertEqual(len(j['data']), tdm.get_num_terms())
self.assertEqual(j['data'][-1],
{'cat': 4, 'cat25k': 735, 'ox': 4, 'oy': 3,
'term': 'speak', 'x': 1.0, 'y': 1.0})
def test_inject_coordinates(self):
tdm = build_hamlet_jz_term_doc_mat()
freq_df = tdm.get_term_freq_df()
scatter_chart = ScatterChart(term_doc_matrix=tdm,
minimum_term_frequency=0)
with self.assertRaises(CoordinatesNotRightException):
scatter_chart.inject_coordinates([], [])
with self.assertRaises(CoordinatesNotRightException):
scatter_chart.inject_coordinates(freq_df[freq_df.columns[0]], [])
with self.assertRaises(CoordinatesNotRightException):
scatter_chart.inject_coordinates([], freq_df[freq_df.columns[0]])
x = freq_df[freq_df.columns[1]].astype(np.float)
y = freq_df[freq_df.columns[0]].astype(np.float)
with self.assertRaises(CoordinatesNotRightException):
scatter_chart.inject_coordinates(x, y)
with self.assertRaises(CoordinatesNotRightException):
scatter_chart.inject_coordinates(x, y / y.max())
with self.assertRaises(CoordinatesNotRightException):
scatter_chart.inject_coordinates(x / x.max(), y)
with self.assertRaises(CoordinatesNotRightException):
scatter_chart.inject_coordinates(-x / x.max(), -y / y.max())
with self.assertRaises(CoordinatesNotRightException):
scatter_chart.inject_coordinates(-x / x.max(), y / y.max())
with self.assertRaises(CoordinatesNotRightException):
scatter_chart.inject_coordinates(x / x.max(), -y / y.max())
scatter_chart.inject_coordinates(x / x.max(), y / y.max())
def test_inject_coordinates(self):
tdm = build_hamlet_jz_term_doc_mat()
freq_df = tdm.get_term_freq_df()
scatter_chart = ScatterChart(term_doc_matrix=tdm,
minimum_term_frequency=0)
with self.assertRaises(CoordinatesNotRightException):
scatter_chart.inject_coordinates([], [])
with self.assertRaises(CoordinatesNotRightException):
scatter_chart.inject_coordinates(freq_df[freq_df.columns[0]], [])
with self.assertRaises(CoordinatesNotRightException):
scatter_chart.inject_coordinates([], freq_df[freq_df.columns[0]])
x = freq_df[freq_df.columns[1]].astype(np.float)
y = freq_df[freq_df.columns[0]].astype(np.float)
with self.assertRaises(CoordinatesNotRightException):
scatter_chart.inject_coordinates(x, y)
with self.assertRaises(CoordinatesNotRightException):
scatter_chart.inject_coordinates(x, y / y.max())
with self.assertRaises(CoordinatesNotRightException):
scatter_chart.inject_coordinates(x / x.max(), y)
with self.assertRaises(CoordinatesNotRightException):
scatter_chart.inject_coordinates(-x / x.max(), -y / y.max())
with self.assertRaises(CoordinatesNotRightException):
scatter_chart.inject_coordinates(-x / x.max(), y / y.max())
with self.assertRaises(CoordinatesNotRightException):
scatter_chart.inject_coordinates(x / x.max(), -y / y.max())
scatter_chart.inject_coordinates(x / x.max(), y / y.max())