def test_eval_matches_valid_2(self):
A = read_csv_metadata(path_a)
B = read_csv_metadata(path_b, key='ID')
C = read_csv_metadata(path_c, ltable=A, rtable=B)
C1 = C[['_id', 'ltable_ID', 'rtable_ID']]
num_ones = 1
num_zeros = len(C1) - num_ones
gold = [0] * num_ones
gold.extend([1] * num_zeros)
predicted = [1] * (num_zeros + num_ones)
ln = len(C1.columns)
C1.insert(ln, 'gold', gold)
C1.insert(ln + 1, 'predicted', predicted)
cm.copy_properties(C, C1)
result = eval_matches(C1, 'predicted', 'gold')
self.assertEqual(isinstance(result, dict), True)
self.assertEqual(result['prec_numerator'], 14)
self.assertEqual(result['prec_denominator'], 14)
self.assertAlmostEqual(result['precision'], 1)
self.assertEqual(result['recall_numerator'], 14)
self.assertEqual(result['recall_denominator'], 15)
self.assertEqual(result['recall'], 0.9333333333333333)
self.assertEqual(result['f1'], 0.9655172413793104)
self.assertEqual(result['pred_pos_num'], 14)
self.assertEqual(result['false_pos_num'], 0.0)
self.assertEqual(len(result['false_pos_ls']), 0)
self.assertEqual(result['pred_neg_num'], 1)
self.assertEqual(result['false_neg_num'], 1.0)
self.assertEqual(len(result['false_neg_ls']), 1)
t = result['false_neg_ls'][0]
self.assertEqual(t[0], 'a1')
self.assertEqual(t[1], 'b1')
def test_eval_matches_valid_3(self):
A = read_csv_metadata(path_a)
B = read_csv_metadata(path_b, key='ID')
C = read_csv_metadata(path_c, ltable=A, rtable=B)
C1 = C[['_id', 'ltable_ID', 'rtable_ID']]
num_ones = len(C1)
num_zeros = len(C1) - num_ones
gold = [0] * num_ones
# gold.extend([1]*num_zeros)
predicted = [1] * (num_zeros + num_ones)
ln = len(C1.columns)
C1.insert(ln, 'gold', gold)
C1.insert(ln + 1, 'predicted', predicted)
D = pd.DataFrame(columns=C1.columns)
cm.copy_properties(C, D)
result = eval_matches(D, 'gold', 'predicted')
self.assertEqual(isinstance(result, dict), True)
self.assertEqual(result['prec_numerator'], 0)
self.assertEqual(result['prec_denominator'], 0)
self.assertAlmostEqual(result['precision'], 0)
self.assertEqual(result['recall_numerator'], 0)
self.assertEqual(result['recall_denominator'], 0)
self.assertEqual(result['recall'], 0)
self.assertEqual(result['f1'], 0)
self.assertEqual(result['pred_pos_num'], 0)
self.assertEqual(result['false_pos_num'], 0.0)
self.assertEqual(len(result['false_pos_ls']), 0)
self.assertEqual(result['pred_neg_num'], 0)
self.assertEqual(result['false_neg_num'], 0.0)
self.assertEqual(len(result['false_neg_ls']), 0)
def test_eval_matches_valid_2(self):
A = read_csv_metadata(path_a)
B = read_csv_metadata(path_b, key='ID')
C = read_csv_metadata(path_c, ltable=A, rtable=B)
C1 = C[['_id', 'ltable_ID', 'rtable_ID']]
num_ones = 1
num_zeros = len(C1) - num_ones
gold = [0] * num_ones
gold.extend([1] * num_zeros)
predicted = [1] * (num_zeros + num_ones)
ln = len(C1.columns)
C1.insert(ln, 'gold', gold)
C1.insert(ln + 1, 'predicted', predicted)
cm.copy_properties(C, C1)
result = eval_matches(C1, 'predicted', 'gold')
self.assertEqual(isinstance(result, dict), True)
self.assertEqual(result['prec_numerator'], 14)
self.assertEqual(result['prec_denominator'], 14)
self.assertAlmostEqual(result['precision'], 1)
self.assertEqual(result['recall_numerator'], 14)
self.assertEqual(result['recall_denominator'], 15)
self.assertEqual(result['recall'], 0.9333333333333333)
self.assertEqual(result['f1'], 0.9655172413793104)
self.assertEqual(result['pred_pos_num'], 14)
self.assertEqual(result['false_pos_num'], 0.0)
self.assertEqual(len(result['false_pos_ls']), 0)
self.assertEqual(result['pred_neg_num'], 1)
self.assertEqual(result['false_neg_num'], 1.0)
self.assertEqual(len(result['false_neg_ls']), 1)
t = result['false_neg_ls'][0]
self.assertEqual(t[0], 'a1')
self.assertEqual(t[1], 'b1')
def test_eval_matches_valid_3(self):
A = read_csv_metadata(path_a)
B = read_csv_metadata(path_b, key='ID')
C = read_csv_metadata(path_c, ltable=A, rtable=B)
C1 = C[['_id', 'ltable_ID', 'rtable_ID']]
num_ones = len(C1)
num_zeros = len(C1) - num_ones
gold = [0]*num_ones
# gold.extend([1]*num_zeros)
predicted = [1]* (num_zeros + num_ones)
ln = len(C1.columns)
C1.insert(ln, 'gold', gold)
C1.insert(ln+1, 'predicted', predicted)
D = pd.DataFrame(columns=C1.columns)
cm.copy_properties(C, D)
result = eval_matches(D, 'gold', 'predicted')
self.assertEqual(isinstance(result, dict), True)
self.assertEqual(result['prec_numerator'], 0)
self.assertEqual(result['prec_denominator'], 0)
self.assertAlmostEqual(result['precision'], 0)
self.assertEqual(result['recall_numerator'], 0)
self.assertEqual(result['recall_denominator'], 0)
self.assertEqual(result['recall'], 0)
self.assertEqual(result['f1'], 0)
self.assertEqual(result['pred_pos_num'], 0)
self.assertEqual(result['false_pos_num'], 0.0)
self.assertEqual(len(result['false_pos_ls']), 0)
self.assertEqual(result['pred_neg_num'], 0)
self.assertEqual(result['false_neg_num'], 0.0)
self.assertEqual(len(result['false_neg_ls']), 0)
def test_eval_matches_predicted_attr_not_in_df(self):
A = read_csv_metadata(path_a)
B = read_csv_metadata(path_b, key='ID')
C = read_csv_metadata(path_c, ltable=A, rtable=B)
C1 = C[['_id', 'ltable_ID', 'rtable_ID']]
num_ones = 1
num_zeros = len(C1) - num_ones
gold = [0] * num_ones
gold.extend([1] * num_zeros)
predicted = [1] * (num_zeros + num_ones)
ln = len(C1.columns)
C1.insert(ln, 'gold', gold)
C1.insert(ln + 1, 'predicted', predicted)
cm.copy_properties(C, C1)
result = eval_matches(C1, 'gold', 'predicted1')
def test_eval_matches_predicted_attr_not_in_df(self):
A = read_csv_metadata(path_a)
B = read_csv_metadata(path_b, key='ID')
C = read_csv_metadata(path_c, ltable=A, rtable=B)
C1 = C[['_id', 'ltable_ID', 'rtable_ID']]
num_ones = 1
num_zeros = len(C1) - num_ones
gold = [0] * num_ones
gold.extend([1] * num_zeros)
predicted = [1] * (num_zeros + num_ones)
ln = len(C1.columns)
C1.insert(ln, 'gold', gold)
C1.insert(ln + 1, 'predicted', predicted)
cm.copy_properties(C, C1)
result = eval_matches(C1, 'gold', 'predicted1')
def _vis_debug_dt(matcher,
train,
test,
exclude_attrs,
target_attr,
show_window=True):
"""
Wrapper function for debugging the Random Forest matcher visually.
"""
try:
from PyQt5 import QtWidgets
from py_entitymatching.gui.debug_gui_base import MainWindowManager
except ImportError:
raise ImportError(
'PyQt5 is not installed. Please install PyQt5 to use '
'GUI related functions in py_entitymatching.')
# Validate the input parameters
# # We expect the matcher to be of type DTMatcher
if not isinstance(matcher, DTMatcher):
logger.error('Input matcher is not of type Decision Tree matcher')
raise AssertionError('Input matcher is not of type '
'Decision Tree matcher')
# # We expect the target attribute to be of type string.
validate_object_type(target_attr,
six.string_types,
error_prefix='Target attribute')
# # Check whether the exclude attributes are indeed present in the train
# DataFrame.
if not ch.check_attrs_present(train, exclude_attrs):
logger.error('The exclude attrs are not in train table columns')
raise AssertionError('The exclude attrs are not in the '
'train table columns')
# # Check whether the target attribute is indeed present in the train
# DataFrame.
if not ch.check_attrs_present(train, target_attr):
logger.error('The target attr is not in train table columns')
raise AssertionError('The target attr is not in the '
'train table columns')
# # Check whether the exclude attributes are indeed present in the test
# DataFrame.
if not ch.check_attrs_present(test, exclude_attrs):
logger.error('The exclude attrs are not in test table columns')
raise AssertionError('The exclude attrs are not in the '
'test table columns')
# The exclude attributes is expected to be of type list, if not
# explicitly convert this into a list.
if not isinstance(exclude_attrs, list):
exclude_attrs = [exclude_attrs]
# Drop the duplicates from the exclude attributes
exclude_attrs = gh.list_drop_duplicates(exclude_attrs)
# If the target attribute is not present in the exclude attributes,
# then explicitly add it to the exclude attributes.
if target_attr not in exclude_attrs:
exclude_attrs.append(target_attr)
# Now, fit using training data
matcher.fit(table=train,
exclude_attrs=exclude_attrs,
target_attr=target_attr)
# Get a column name to store the predictions.
predict_attr_name = get_name_for_predict_column(test.columns)
# Predict using the test data
predicted = matcher.predict(table=test,
exclude_attrs=exclude_attrs,
target_attr=predict_attr_name,
append=True,
inplace=False)
# Get the evaluation summary.
eval_summary = eval_matches(predicted, target_attr, predict_attr_name)
# Get metric in a form that can be displayed from the evaluation summary
metric = _get_metric(eval_summary)
# Get false negatives and false positives as a DataFrame
fp_dataframe = _get_dataframe(predicted, eval_summary['false_pos_ls'])
fn_dataframe = _get_dataframe(predicted, eval_summary['false_neg_ls'])
em._viewapp = QtWidgets.QApplication.instance()
if em._viewapp is None:
em._viewapp = QtWidgets.QApplication([])
app = em._viewapp
# Get the main window application
app = em._viewapp
m = MainWindowManager(matcher, "dt", exclude_attrs, metric, predicted,
fp_dataframe, fn_dataframe)
# If the show window is true, then display the window.
if show_window:
m.show()
app.exec_()
def test_eval_matches_invalid_predicted_attr(self):
eval_matches(pd.DataFrame(), "", None)
def test_eval_matches_invalid_gold_attr(self):
eval_matches(pd.DataFrame(), None, "")
def test_eval_matches_invalid_df(self):
eval_matches(None, "", "")
def test_eval_matches_invalid_predicted_attr(self):
eval_matches(pd.DataFrame(), "", None)
def test_eval_matches_invalid_gold_attr(self):
eval_matches(pd.DataFrame(), None, "")
def test_eval_matches_invalid_df(self):
eval_matches(None, "", "")
def _vis_debug_dt(matcher, train, test, exclude_attrs, target_attr,
show_window=True):
"""
Wrapper function for debugging the Random Forest matcher visually.
"""
try:
from PyQt5 import QtWidgets
from py_entitymatching.gui.debug_gui_base import MainWindowManager
except ImportError:
raise ImportError('PyQt5 is not installed. Please install PyQt5 to use '
'GUI related functions in py_entitymatching.')
# Validate the input parameters
# # We expect the matcher to be of type DTMatcher
if not isinstance(matcher, DTMatcher):
logger.error('Input matcher is not of type Decision Tree matcher')
raise AssertionError('Input matcher is not of type '
'Decision Tree matcher')
# # We expect the target attribute to be of type string.
validate_object_type(target_attr, six.string_types, error_prefix='Target attribute')
# # Check whether the exclude attributes are indeed present in the train
# DataFrame.
if not ch.check_attrs_present(train, exclude_attrs):
logger.error('The exclude attrs are not in train table columns')
raise AssertionError('The exclude attrs are not in the '
'train table columns')
# # Check whether the target attribute is indeed present in the train
# DataFrame.
if not ch.check_attrs_present(train, target_attr):
logger.error('The target attr is not in train table columns')
raise AssertionError('The target attr is not in the '
'train table columns')
# # Check whether the exclude attributes are indeed present in the test
# DataFrame.
if not ch.check_attrs_present(test, exclude_attrs):
logger.error('The exclude attrs are not in test table columns')
raise AssertionError('The exclude attrs are not in the '
'test table columns')
# The exclude attributes is expected to be of type list, if not
# explicitly convert this into a list.
if not isinstance(exclude_attrs, list):
exclude_attrs = [exclude_attrs]
# Drop the duplicates from the exclude attributes
exclude_attrs = gh.list_drop_duplicates(exclude_attrs)
# If the target attribute is not present in the exclude attributes,
# then explicitly add it to the exclude attributes.
if target_attr not in exclude_attrs:
exclude_attrs.append(target_attr)
# Now, fit using training data
matcher.fit(table=train, exclude_attrs=exclude_attrs,
target_attr=target_attr)
# Get a column name to store the predictions.
predict_attr_name = get_name_for_predict_column(test.columns)
# Predict using the test data
predicted = matcher.predict(table=test, exclude_attrs=exclude_attrs,
target_attr=predict_attr_name, append=True,
inplace=False)
# Get the evaluation summary.
eval_summary = eval_matches(predicted, target_attr, predict_attr_name)
# Get metric in a form that can be displayed from the evaluation summary
metric = _get_metric(eval_summary)
# Get false negatives and false positives as a DataFrame
fp_dataframe = _get_dataframe(predicted, eval_summary['false_pos_ls'])
fn_dataframe = _get_dataframe(predicted, eval_summary['false_neg_ls'])
em._viewapp = QtWidgets.QApplication.instance()
if em._viewapp is None:
em._viewapp = QtWidgets.QApplication([])
app = em._viewapp
# Get the main window application
app = em._viewapp
m = MainWindowManager(matcher, "dt", exclude_attrs, metric, predicted,
fp_dataframe,
fn_dataframe)
# If the show window is true, then display the window.
if show_window:
m.show()
app.exec_()