def test_rulebased_matcher_rule_wi_no_auto_gen_feature(self):
feature_string = "jaccard(qgm_3(ltuple['name']), qgm_3(rtuple['name']))"
f_dict = get_feature_fn(feature_string, get_tokenizers_for_blocking(),
get_sim_funs_for_blocking())
add_feature(self.feature_table, 'test', f_dict)
test_rule = ['test(ltuple, rtuple) > 0.4'] # same as rule_1
self.brm.add_rule(test_rule, self.feature_table)
predictions = self.brm.predict(table=self.C)
assert_equal(expected_labels_1, predictions)
def test_rb_block_tables_rule_wi_no_auto_gen_feature(self):
feature_string = "jaccard(qgm_3(ltuple['name']), qgm_3(rtuple['name']))"
f_dict = get_feature_fn(feature_string, get_tokenizers_for_blocking(),
get_sim_funs_for_blocking())
add_feature(self.feature_table, 'test', f_dict)
test_rule = ['test(ltuple, rtuple) < 0.3'] # same as rule_1
self.rb.add_rule(test_rule, self.feature_table)
C = self.rb.block_tables(self.A, self.B, show_progress=False)
validate_metadata(C)
validate_data(C, expected_ids_1)
def test_rulebased_matcher_rule_wi_overlap_coeff_sim_fn(self):
feature_string = "overlap_coeff(dlm_dc0(ltuple['name']), dlm_dc0(rtuple['name']))"
f_dict = get_feature_fn(feature_string, get_tokenizers_for_blocking(),
get_sim_funs_for_blocking())
f_dict['is_auto_generated'] = True
add_feature(self.feature_table, 'test', f_dict)
test_rule = ['test(ltuple, rtuple) > 1'] # should return an empty set
self.brm.add_rule(test_rule, self.feature_table)
predictions = self.brm.predict(table=self.C)
assert_equal(expected_labels_all_zeroes, predictions)
def test_rb_block_tables_rule_wi_overlap_coeff_sim_fn(self):
feature_string = "overlap_coeff(dlm_dc0(ltuple['name']), dlm_dc0(rtuple['name']))"
f_dict = get_feature_fn(feature_string, get_tokenizers_for_blocking(),
get_sim_funs_for_blocking())
f_dict['is_auto_generated'] = True
add_feature(self.feature_table, 'test', f_dict)
test_rule = ['test(ltuple, rtuple) <= 1'] # should return an empty set
self.rb.add_rule(test_rule, self.feature_table)
C = self.rb.block_tables(self.A, self.B, show_progress=False)
validate_metadata(C)
validate_data(C)
def test_trigger_rule_wi_no_auto_gen_feature(self):
feature_string = "jaccard(qgm_3(ltuple['name']), qgm_3(rtuple['name']))"
f_dict = get_feature_fn(feature_string, get_tokenizers_for_blocking(),
get_sim_funs_for_blocking())
add_feature(self.feature_table, 'test', f_dict)
test_rule = ['test(ltuple, rtuple) > 0.4'] # same as rule_1
self.mt.add_cond_rule(test_rule, self.feature_table)
self.mt.add_cond_status(False)
self.mt.add_action(0)
preds = self.mt.execute(self.C, 'neg_trig_labels', inplace=False)
predictions = preds['neg_trig_labels'].tolist()
assert_equal(expected_labels_1, predictions)
def test_trigger_rule_wi_no_auto_gen_feature(self):
feature_string = "jaccard(qgm_3(ltuple['name']), qgm_3(rtuple['name']))"
f_dict = get_feature_fn(feature_string, get_tokenizers_for_blocking(),
get_sim_funs_for_blocking())
add_feature(self.feature_table, 'test', f_dict)
test_rule = ['test(ltuple, rtuple) > 0.4'] # same as rule_1
self.mt.add_cond_rule(test_rule, self.feature_table)
self.mt.add_cond_status(False)
self.mt.add_action(0)
preds = self.mt.execute(self.C, 'neg_trig_labels', inplace=False)
predictions = preds['neg_trig_labels'].tolist()
assert_equal(expected_labels_1, predictions)
def test_trigger_rule_wi_diff_tokenizers(self):
feature_string = "jaccard(qgm_3(ltuple['address']), dlm_dc0(rtuple['address']))"
f_dict = get_feature_fn(feature_string, get_tokenizers_for_blocking(),
get_sim_funs_for_blocking())
f_dict['is_auto_generated'] = True
add_feature(self.feature_table, 'test', f_dict)
test_rule = ['test(ltuple, rtuple) > 1'] # should return an empty set
self.mt.add_cond_rule(test_rule, self.feature_table)
self.mt.add_cond_status(False)
self.mt.add_action(0)
preds = self.mt.execute(self.C, 'neg_trig_labels', inplace=False)
predictions = preds['neg_trig_labels'].tolist()
assert_equal(expected_labels_zeros, predictions)
def test_trigger_rule_wi_diff_tokenizers(self):
feature_string = "jaccard(qgm_3(ltuple['address']), dlm_dc0(rtuple['address']))"
f_dict = get_feature_fn(feature_string, get_tokenizers_for_blocking(),
get_sim_funs_for_blocking())
f_dict['is_auto_generated'] = True
add_feature(self.feature_table, 'test', f_dict)
test_rule = ['test(ltuple, rtuple) > 1'] # should return an empty set
self.mt.add_cond_rule(test_rule, self.feature_table)
self.mt.add_cond_status(False)
self.mt.add_action(0)
preds = self.mt.execute(self.C, 'neg_trig_labels', inplace=False)
predictions = preds['neg_trig_labels'].tolist()
assert_equal(expected_labels_zeros, predictions)
def test_valid_tok_sim_valid(self):
sim = simfuncs.get_sim_funs_for_blocking()
tok = toks.get_tokenizers_for_blocking()
status = afg.check_valid_tok_sim(('lev1', 'tok', 'tok'), sim, tok)
self.assertEqual(status, None)
def test_valid_tok_sim_valid(self):
sim = simfuncs.get_sim_funs_for_blocking()
tok = toks.get_tokenizers_for_blocking()
status = afg.check_valid_tok_sim(('lev1', 'tok', 'tok'), sim, tok)
self.assertEqual(status, None)
def test_get_tokenizers_for_blocking_invalid(self):
tok.get_tokenizers_for_blocking(None, None)
def test_get_tokenizers_for_blocking(self):
x = tok.get_tokenizers_for_blocking()
self.assertEqual(isinstance(x, dict), True)
input = 'data science'
for name, value in six.iteritems(x):
self.assertEqual(isinstance(value(input), list), True)
def get_features_for_blocking(ltable, rtable):
"""
This function automatically generates features that can be used for
blocking purposes.
Args:
ltable,rtable (DataFrame): The pandas DataFrames for which the
features are to be generated.
Returns:
A pandas DataFrame containing automatically generated features.
Specifically, the DataFrame contains the following attributes:
'feature_name', 'left_attribute', 'right_attribute',
'left_attr_tokenizer', 'right_attr_tokenizer', 'simfunction',
'function', 'function_source', and 'is_auto_generated'.
Further, this function also sets the following global variables:
_block_t, _block_s, _atypes1, _atypes2, and _block_c.
The variable _block_t contains the tokenizers used and _block_s
contains the similarity functions used for creating features.
The variables _atypes1, and _atypes2 contain the attribute types for
ltable and rtable respectively. The variable _block_c contains the
attribute correspondences between the two input tables.
Raises:
AssertionError: If `ltable` is not of type pandas
DataFrame.
AssertionError: If `rtable` is not of type pandas
DataFrame.
Note:
In the output DataFrame, two
attributes demand some explanation: (1) function, and (2)
is_auto_generated. The function, points to the actual Python function
that implements the feature. Specifically, the function takes in two
tuples (one from each input table) and returns a numeric value. The
attribute is_auto_generated contains either True or False. The flag
is True only if the feature is automatically generated by py_entitymatching.
This is important because this flag is used to make some assumptions
about the semantics of the similarity function used and use that
information for scaling purposes.
See Also:
:meth:`py_entitymatching.get_attr_corres`, :meth:`py_entitymatching.get_attr_types`,
:meth:`py_entitymatching.get_sim_funs_for_blocking`
:meth:`py_entitymatching.get_tokenizers_for_blocking`
"""
# Validate input parameters
# # We expect the ltable to be of type pandas DataFrame
if not isinstance(ltable, pd.DataFrame):
logger.error('Input table A is not of type pandas DataFrame')
raise AssertionError('Input table A is not of type pandas DataFrame')
# # We expect the rtable to be of type pandas DataFrame
if not isinstance(rtable, pd.DataFrame):
logger.error('Input table B is not of type pandas dataframe')
raise AssertionError('Input table B is not of type pandas dataframe')
# Get the similarity functions to be used for blocking
sim_funcs = sim.get_sim_funs_for_blocking()
# Get the tokenizers to be used for blocking
tok_funcs = tok.get_tokenizers_for_blocking()
# Get the attr. types for ltable and rtable
attr_types_ltable = au.get_attr_types(ltable)
attr_types_rtable = au.get_attr_types(rtable)
# Get the attr. correspondences between ltable and rtable
attr_corres = au.get_attr_corres(ltable, rtable)
# Get features based on attr types, attr correspondences, sim functions
# and tok. functions
feature_table = get_features(ltable, rtable, attr_types_ltable,
attr_types_rtable, attr_corres, tok_funcs,
sim_funcs)
# Export important variables to global name space
em._match_t = tok_funcs
em._block_s = sim_funcs
em._atypes1 = attr_types_ltable
em._atypes2 = attr_types_rtable
em._block_c = attr_corres
# Return the feature table
return feature_table
def get_features_for_blocking(ltable, rtable, validate_inferred_attr_types=True):
"""
This function automatically generates features that can be used for
blocking purposes.
Args:
ltable,rtable (DataFrame): The pandas DataFrames for which the
features are to be generated.
validate_inferred_attr_types (boolean): A flag to indicate whether to
show the user the inferred attribute types and the features
chosen for those types.
Returns:
A pandas DataFrame containing automatically generated features.
Specifically, the DataFrame contains the following attributes:
'feature_name', 'left_attribute', 'right_attribute',
'left_attr_tokenizer', 'right_attr_tokenizer', 'simfunction',
'function', 'function_source', and 'is_auto_generated'.
Further, this function also sets the following global variables:
_block_t, _block_s, _atypes1, _atypes2, and _block_c.
The variable _block_t contains the tokenizers used and _block_s
contains the similarity functions used for creating features.
The variables _atypes1, and _atypes2 contain the attribute types for
ltable and rtable respectively. The variable _block_c contains the
attribute correspondences between the two input tables.
Raises:
AssertionError: If `ltable` is not of type pandas
DataFrame.
AssertionError: If `rtable` is not of type pandas
DataFrame.
AssertionError: If `validate_inferred_attr_types` is not of type
pandas DataFrame.
Examples:
>>> import py_entitymatching as em
>>> A = em.read_csv_metadata('path_to_csv_dir/table_A.csv', key='ID')
>>> B = em.read_csv_metadata('path_to_csv_dir/table_B.csv', key='ID')
>>> block_f = em.get_features_for_blocking(A, B)
Note:
In the output DataFrame, two
attributes demand some explanation: (1) function, and (2)
is_auto_generated. The function, points to the actual Python function
that implements the feature. Specifically, the function takes in two
tuples (one from each input table) and returns a numeric value. The
attribute is_auto_generated contains either True or False. The flag
is True only if the feature is automatically generated by py_entitymatching.
This is important because this flag is used to make some assumptions
about the semantics of the similarity function used and use that
information for scaling purposes.
See Also:
:meth:`py_entitymatching.get_attr_corres`, :meth:`py_entitymatching.get_attr_types`,
:meth:`py_entitymatching.get_sim_funs_for_blocking`
:meth:`py_entitymatching.get_tokenizers_for_blocking`
"""
# Validate input parameters
# # We expect the ltable to be of type pandas DataFrame
validate_object_type(ltable, pd.DataFrame, 'Input table A')
# # We expect the rtable to be of type pandas DataFrame
validate_object_type(rtable, pd.DataFrame, 'Input table B')
# # We expect the validate_inferred_attr_types to be of type boolean
validate_object_type(validate_inferred_attr_types, bool, 'Validate inferred attribute type')
# Get the similarity functions to be used for blocking
sim_funcs = sim.get_sim_funs_for_blocking()
# Get the tokenizers to be used for blocking
tok_funcs = tok.get_tokenizers_for_blocking()
# Get the attr. types for ltable and rtable
attr_types_ltable = au.get_attr_types(ltable)
attr_types_rtable = au.get_attr_types(rtable)
# Get the attr. correspondences between ltable and rtable
attr_corres = au.get_attr_corres(ltable, rtable)
# Show the user inferred attribute types and features and request
# user permission to proceed
if validate_inferred_attr_types:
# if the user does not want to proceed, then exit the function
if validate_attr_types(attr_types_ltable, attr_types_rtable, attr_corres) is None:
return
# Get features based on attr types, attr correspondences, sim functions
# and tok. functions
feature_table = get_features(ltable, rtable, attr_types_ltable,
attr_types_rtable, attr_corres,
tok_funcs, sim_funcs)
# Export important variables to global name space
em._block_t = tok_funcs
em._block_s = sim_funcs
em._atypes1 = attr_types_ltable
em._atypes2 = attr_types_rtable
em._block_c = attr_corres
# Return the feature table
return feature_table
