def test_find_strength_diff(self):
bt = BradleyTerry()
bt.is_fitted = True
bt.target_col_name = 'result'
bt.lkp = {0: 'A', 1: 'B', 2: 'C', 3: 'D'}
bt.rplc_lkp = {'A': 0, 'B': 1, 'C': 2, 'D': 3}
bt._params = np.array([0.3, 0.2, -0.2, -0.4])
bt.params_ = np.array([0.3, 0.2, -0.2, -0.4])
calc_strength = bt.find_strength_diff(INDEXED_DATA_NORESCOL)
correct_strength = np.array([-0.4, -0.1, 0.2, -0.2])
np.testing.assert_array_almost_equal(calc_strength,
correct_strength,
decimal=10)
def test_unpack_data_for_choix(self):
bt = BradleyTerry()
bt.rplc_lkp, bt.lkp = generate_entity_lookup(
get_distinct_entities(INDEXED_DATA))
bt.target_col_name = 'result'
data, n_ents = bt.unpack_data_for_choix(INDEXED_DATA,
INDEXED_DATA.index.names)
correct_data = {'winner': [(2, 1), (0, 1), (3, 2), (3, 2)]}
corrrect_n_ents = 4
self.assertEqual(n_ents, corrrect_n_ents)
self.assertEqual(data.keys(), correct_data.keys())
for key in data:
for iteration, _tuple in enumerate(data[key]):
self.assertTupleEqual(_tuple, correct_data[key][iteration])
def test_check_for_no_new_entities(self):
bt = BradleyTerry()
bt.is_fitted = True
bt.target_col_name = 'result'
bt.lkp = {1: 'A', 2: 'B', 3: 'C', 4: 'D'}
wrong_data = pd.DataFrame({
'ent1': ['K', 'A'],
'ent2': ['A,', 'B'],
'result': [1, 0]
})
wrong_data = wrong_data.set_index(['ent1', 'ent2'])
with self.assertRaises(Exception):
bt.check_for_no_new_entities(wrong_data)
try:
bt.check_for_no_new_entities(TRANSITIVE_DATA_INDEXED)
except:
self.fail("check_for_no_new_entities failed unexpectedly")
def test_unpack_data_for_pylogit(self):
bt = BradleyTerry()
bt.rplc_lkp, bt.lkp = generate_entity_lookup(
get_distinct_entities(INDEXED_EVERYONE_WINS_ONCE_DATA))
bt.target_col_name = 'result'
long_format_pylogit = bt.unpack_data_for_pylogit(
INDEXED_EVERYONE_WINS_ONCE_DATA, ['ent1', 'ent2'])
correct_lf_output = pd.DataFrame({
'observation': [1, 1, 2, 2, 3, 3, 4, 4, 5, 5],
'entity': [1, 2, 0, 1, 2, 3, 2, 3, 1, 3],
'CHOICE': [0, 1, 1, 0, 0, 1, 0, 1, 1, 0]
})
assert_frame_equal(long_format_pylogit.astype('int32'),
correct_lf_output.astype('int32'))
def test_predict_proba(self):
bt = BradleyTerry()
bt.is_fitted = True
bt.target_col_name = 'result'
bt.lkp = {0: 'A', 1: 'B', 2: 'C', 3: 'D'}
bt.rplc_lkp = {'A': 0, 'B': 1, 'C': 2, 'D': 3}
bt._params = np.array([0.3, 0.2, -0.2, -0.4])
bt.params_ = np.array([0.3, 0.2, -0.2, -0.4])
bt.pylogit_fit = False
def exp_func(x):
return 1 / (1 + np.exp(-x))
pred_probs = bt.predict_proba(INDEXED_DATA_NORESCOL)
corect_probs = np.array(
[exp_func(-0.4),
exp_func(-0.1),
exp_func(0.2),
exp_func(-0.2)])
np.testing.assert_array_equal(pred_probs, corect_probs)
def test_join_up_dataframes(self):
bt = BradleyTerry()
# Testing case when only df_i is fed in but df_j is meant to be the same
bt.rplc_lkp, bt.lkp = generate_entity_lookup(
get_distinct_entities(INDEXED_EVERYONE_WINS_ONCE_DATA))
bt.target_col_name = 'result'
long_format_pylogit = bt.unpack_data_for_pylogit(
INDEXED_EVERYONE_WINS_ONCE_DATA, ['ent1', 'ent2'])
x_comb = bt.join_up_dataframes(long_format_pylogit,
df_i=INDEXED_ENT1_ATTRIBUTES)
correct_x_comb = pd.DataFrame({
'observation': [1, 1, 2, 2, 3, 3, 4, 4, 5, 5],
'entity': [1, 2, 0, 1, 2, 3, 2, 3, 1, 3],
'CHOICE': [0, 1, 1, 0, 0, 1, 0, 1, 1, 0],
'feat1': [11, 12, 1, 11, 12, 15, 12, 15, 11, 15]
})
assert_frame_equal(x_comb.astype('int32'),
correct_x_comb.astype('int32'))
# Testing the case when different df_i and df_j is fed in
# x_comb_1_2 = \
# bt.join_up_dataframes(INDEXED_EVERYONE_WINS_ONCE_DATA,
# INDEXED_ENT1_ATTRIBUTES,
# INDEXED_ENT2_ATTRIBUTES)
#
# correct_x_comb_1_2 = pd.DataFrame(
# {'observation': [1, 1, 2, 2, 3, 3, 4, 4, 5, 5],
# 'entity': [1, 2, 0, 1, 2, 3, 2, 3, 1, 3],
# 'CHOICE': [0, 1, 1, 0, 0, 1, 0, 1, 1, 0],
# 'feat1': [11, 12, 1, 11, 12, 15, 12, 15, 11, 15],
# 'feat2'}
# ).set_index(['ent1', 'ent2'])
#
# assert_frame_equal(x_comb_1_2, correct_x_comb_1_2)
#
# # Testing the case when df_j is fed in but df_i is meant to be the same
# x_comb_2_1, x_comb_entnames_2_1, run_choix_2_1 = \
# bt.join_up_dataframes(INDEXED_DATA, df_j=INDEXED_ENT2_ATTRIBUTES)
#
# correct_x_comb_2_1 = pd.DataFrame(
# {'ent1': ['C', 'B', 'C', 'D'],
# 'ent2': ['B', 'A', 'D', 'C'],
# 'result': [1, 0, 0, 1],
# 'feat1_ent2': [1, 1, 0, 1],
# 'feat1_ent1': [1, 1, 1, 0]}
# ).set_index(['ent1', 'ent2'])
#
# assert_frame_equal(x_comb_2_1, correct_x_comb_2_1)
# self.assertListEqual(x_comb_entnames_2_1, ['ent1', 'ent2'])
# self.assertFalse(run_choix_2_1)
#
# # Case when df_j is fed in but df_i is not meant to exist
# x_comb_2, x_comb_entnames_2, run_choix_2 = \
# bt.join_up_dataframes(INDEXED_DATA, df_j=INDEXED_ENT2_ATTRIBUTES,
# same_ent_data=False)
#
# correct_x_comb_2 = pd.DataFrame(
# {'ent1': ['C', 'B', 'C', 'D'],
# 'ent2': ['B', 'A', 'D', 'C'],
# 'result': [1, 0, 0, 1],
# 'feat1': [1, 1, 0, 1]}
# ).set_index(['ent1', 'ent2'])
#
# assert_frame_equal(x_comb_2, correct_x_comb_2)
# self.assertListEqual(x_comb_entnames_2, ['ent1', 'ent2'])
# self.assertFalse(run_choix_2)
#
# # Case when df_i is fed in but df_j does not exist
# x_comb_1, x_comb_entnames_1, run_choix_1 = \
# bt.join_up_dataframes(INDEXED_DATA, df_i=INDEXED_ENT1_ATTRIBUTES,
# same_ent_data=False)
#
# correct_x_comb_1 = pd.DataFrame(
# {'ent1': ['C', 'B', 'C', 'D'],
# 'ent2': ['B', 'A', 'D', 'C'],
# 'result': [1, 0, 0, 1],
# 'feat1': [12, 11, 12, 15]}
# ).set_index(['ent1', 'ent2'])
#
# assert_frame_equal(x_comb_1, correct_x_comb_1)
# self.assertListEqual(x_comb_entnames_1, ['ent1', 'ent2'])
# self.assertFalse(run_choix_1)
#
# # Case when simple Bradley Terry is fed in
# x_comb_na, x_comb_entnames_na, run_choix_na = \
# bt.join_up_dataframes(INDEXED_DATA)
#
# assert_frame_equal(x_comb_na, INDEXED_DATA)
# self.assertListEqual(x_comb_entnames_na, ['ent1', 'ent2'])
# self.assertTrue(run_choix_na)
#
# Case when df_i is fed in with a merge column and df_j is meant to be
# the same
long_format_pylogit = bt.unpack_data_for_pylogit(
EVERYONE_WINS_ONCE_DATA_MERGECOL_INDEXED, ['ent1', 'ent2'])
x_comb_m = bt.join_up_dataframes(long_format_pylogit,
df_i=INDEXED_ENT1_ATTRIBUTES_MERGECOL,
merge_columns=['mergecol'])
correct_x_comb_m = pd.DataFrame({
'observation': [1, 1, 2, 2, 3, 3, 4, 4, 5, 5],
'entity': [1, 2, 0, 1, 2, 3, 2, 3, 1, 3],
'CHOICE': [0, 1, 1, 0, 0, 1, 0, 1, 1, 0],
'feat1': [11, 12, 1, 11, 12, 15, 3, 4, 2, 4]
})
assert_frame_equal(x_comb_m.astype('int32'),
correct_x_comb_m.astype('int32'))