Index

A

add_threshold_dict() (in module namematch.fit_model) add_uncovered_pairs() (namematch.block.Block method) all_tasks (namematch.namematcher.NameMatcher property)

apply_blocking_filter() (namematch.block.Block method) apply_link_priority (namematch.cluster.Constraints property) auto_is_valid_cluster() (namematch.cluster.Cluster method) auto_is_valid_edge() (namematch.cluster.Cluster method)

B

Block (class in namematch.block) block (namematch.namematcher.NameMatcher property) build() (namematch.data_structures.data_file.DataFileList class method) (namematch.data_structures.data_file.ExistingDataFile class method) (namematch.data_structures.data_file.NewDataFile class method) (namematch.data_structures.variable.Variable class method) (namematch.data_structures.variable.VariableList class method)

build_blockstring() (in module namematch.utils.utils) build_ml_var_df() (namematch.generate_must_links.GenerateMustLinks method)

C

camel_to_snake() (in module namematch.utils.utils) check_for_required_variables() (namematch.data_structures.parameters.Parameters method) check_integrity() (namematch.data_structures.parameters.Parameters static method) clean_nn_string() (in module namematch.utils.utils) Cluster (class in namematch.cluster) cluster (namematch.namematcher.NameMatcher property) cluster_potential_edges() (namematch.cluster.Cluster method) compute_cosine_sim() (namematch.block.Block method)

Constraints (class in namematch.cluster) convert_all_names_to_blockstring_info() (namematch.block.Block method) copy() (namematch.data_structures.data_file.DataFile method) (namematch.data_structures.data_file.DataFileList method) (namematch.data_structures.parameters.Parameters method) (namematch.data_structures.variable.Variable method) (namematch.data_structures.variable.VariableList method) create_allnames_clusterid_file() (namematch.generate_output.GenerateOutput method) create_nm_record_id() (in module namematch.utils.utils)

D

DataFile (class in namematch.data_structures.data_file) DataFileList (class in namematch.data_structures.data_file) define_necessary_models() (in module namematch.fit_model) determine_model_to_use() (in module namematch.utils.utils)

disallow_switched_pairs() (namematch.block.Block method) dr_file_list (namematch.fit_model.FitModel property) (namematch.predict.Predict property) dump_yaml() (in module namematch.utils.utils)

E

evaluate_blocking() (namematch.block.Block method)

evaluate_models() (namematch.fit_model.FitModel method) ExistingDataFile (class in namematch.data_structures.data_file)

F

filename_friendly_hash() (in module namematch.utils.utils) filter() (namematch.generate_report.IgnoreBlackWarning method) (namematch.utils.utils.StatLogFilter method) find_valid_training_records() (namematch.fit_model.FitModel method) (namematch.generate_data_rows.GenerateDataRows method)

fit_model (namematch.namematcher.NameMatcher property) fit_model() (namematch.fit_model.FitModel method) fit_models() (namematch.fit_model.FitModel method) FitModel (class in namematch.fit_model)

G

generate_actual_data_rows() (namematch.generate_data_rows.GenerateDataRows method) generate_candidate_pairs() (namematch.block.Block method) generate_data_row_files() (namematch.generate_data_rows.GenerateDataRows method) generate_data_rows (namematch.namematcher.NameMatcher property) generate_index() (namematch.block.Block method) generate_must_links (namematch.namematcher.NameMatcher property) generate_name_probabilities_object() (namematch.generate_data_rows.GenerateDataRows method) generate_output (namematch.namematcher.NameMatcher property) generate_report (namematch.namematcher.NameMatcher property) generate_shingles_matrix() (namematch.block.Block method) generate_true_pairs() (in module namematch.block) GenerateDataRows (class in namematch.generate_data_rows) GenerateMustLinks (class in namematch.generate_must_links) GenerateOutput (class in namematch.generate_output) GenerateReport (class in namematch.generate_report) get_actual_candidates() (namematch.block.Block method) get_all_data_files() (namematch.data_structures.data_file.DataFileList method) get_all_nicknames() (namematch.data_structures.data_file.DataFileList method) get_all_shingles() (in module namematch.block) get_an_column_names() (namematch.data_structures.variable.VariableList method) get_an_columns() (namematch.data_structures.variable.Variable method) get_blocking_columns() (in module namematch.block) get_blocking_variables() (namematch.data_structures.parameters.Parameters method) get_ci_ix_map() (namematch.cluster.Cluster method) get_cluster_logic() (namematch.cluster.Cluster method)

get_columns_to_read() (namematch.data_structures.variable.Variable method) (namematch.data_structures.variable.VariableList method) get_columns_used (namematch.cluster.Constraints property) get_common_name_penalties() (in module namematch.block) get_ed_string_from_blockstring() (in module namematch.utils.utils) get_endpoints() (in module namematch.utils.utils) get_exact_match_candidate_pairs() (namematch.block.Block method) get_feature_info() (in module namematch.fit_model) get_flipped0_potential_edges() (in module namematch.fit_model) get_indices() (namematch.block.Block method) get_initial_clusters() (namematch.cluster.Cluster method) get_match_train_eligible_flag() (in module namematch.fit_model) get_must_links() (namematch.generate_must_links.GenerateMustLinks method) get_names() (namematch.data_structures.variable.VariableList method) get_near_neighbors_df() (namematch.block.Block method) get_nn_string_counts() (in module namematch.block) get_nn_string_from_blockstring() (in module namematch.utils.utils) get_potential_edges() (namematch.cluster.Cluster method) (namematch.predict.Predict method) get_potential_edges_in_parallel() (namematch.predict.Predict method) get_query_strings() (namematch.block.Block method) get_second_index_nn_strings() (in module namematch.block) get_stage_params() (namematch.data_structures.parameters.Parameters method) get_train_eval_data() (namematch.fit_model.FitModel method) get_variables_where() (namematch.data_structures.variable.VariableList method)

I

IgnoreBlackWarning (class in namematch.generate_report) init() (namematch.data_structures.parameters.Parameters class method) (namematch.data_structures.schema.Schema class method)

is_valid_cluster (namematch.cluster.Constraints property) is_valid_link (namematch.cluster.Constraints property)

L

load() (namematch.data_structures.data_file.DataFile class method) (namematch.data_structures.data_file.DataFileList class method) (namematch.data_structures.parameters.Parameters class method) (namematch.data_structures.schema.Schema class method) (namematch.data_structures.variable.VariableList class method) load_and_save_trained_model() (in module namematch.fit_model) load_cluster_info() (namematch.cluster.Cluster method) load_csv_list() (in module namematch.utils.utils) load_from_dict() (namematch.data_structures.parameters.Parameters class method) (namematch.data_structures.schema.Schema class method) load_logging_params() (in module namematch.utils.utils)

load_main_index() (namematch.block.Block method) load_main_index_nn_strings() (in module namematch.block) load_models() (in module namematch.utils.utils) load_namematcher() (namematch.namematcher.NameMatcher class method) load_parquet() (in module namematch.utils.utils) load_parquet_list() (in module namematch.utils.utils) load_sample() (in module namematch.utils.utils) load_yaml() (in module namematch.utils.utils) log_runtime_and_memory() (in module namematch.utils.utils) log_stat() (in module namematch.utils.utils) luigi_dict_parameter_to_dict() (in module namematch.utils.utils)

M

main() (namematch.block.Block method) (namematch.cluster.Cluster method) (namematch.fit_model.FitModel method) (namematch.generate_data_rows.GenerateDataRows method) (namematch.generate_must_links.GenerateMustLinks method) (namematch.generate_output.GenerateOutput method) (namematch.generate_report.GenerateReport method) (namematch.predict.Predict method) (namematch.process_input_data.ProcessInputData method) module namematch.block namematch.cluster namematch.data_structures.data_file namematch.data_structures.parameters namematch.data_structures.schema namematch.data_structures.variable namematch.fit_model namematch.generate_data_rows namematch.generate_must_links namematch.generate_output namematch.generate_report namematch.namematcher namematch.predict namematch.process_input_data namematch.utils.utils

N

namematch.block module namematch.cluster module namematch.data_structures.data_file module namematch.data_structures.parameters module namematch.data_structures.schema module namematch.data_structures.variable module namematch.fit_model module namematch.generate_data_rows module

namematch.generate_must_links module namematch.generate_output module namematch.generate_report module namematch.namematcher module namematch.predict module namematch.process_input_data module namematch.utils.utils module NameMatcher (class in namematch.namematcher) NewDataFile (class in namematch.data_structures.data_file) nm_metadata (namematch.namematcher.NameMatcher property)

O

output_clusterid_files() (namematch.generate_output.GenerateOutput method) output_files (namematch.block.Block property) (namematch.cluster.Cluster property) (namematch.fit_model.FitModel property) (namematch.generate_data_rows.GenerateDataRows property) (namematch.generate_must_links.GenerateMustLinks property) (namematch.generate_output.GenerateOutput property) (namematch.generate_report.GenerateReport property) (namematch.predict.Predict property) (namematch.process_input_data.ProcessInputData property)

P

Parameters (class in namematch.data_structures.parameters) parse_address() (namematch.process_input_data.ProcessInputData method) Predict (class in namematch.predict) predict (namematch.namematcher.NameMatcher property) predict() (namematch.predict.Predict class method) prep_index() (in module namematch.block) process_address_column() (namematch.process_input_data.ProcessInputData method)

process_auto_drops() (in module namematch.process_input_data) process_check() (namematch.process_input_data.ProcessInputData method) process_data() (namematch.process_input_data.ProcessInputData method) process_drop() (in module namematch.process_input_data) process_geo_column() (namematch.process_input_data.ProcessInputData method) process_input_data (namematch.namematcher.NameMatcher property) process_set_missing() (in module namematch.process_input_data) ProcessInputData (class in namematch.process_input_data)

R

read_an() (in module namematch.block) recursively_convert_tuple_to_list() (in module namematch.utils.utils)

reformat_dict() (in module namematch.utils.utils) run() (namematch.namematcher.NameMatcher method)

S

save_df_to_disk() (namematch.cluster.Cluster method) save_main_index() (in module namematch.block) save_models() (in module namematch.fit_model) Schema (class in namematch.data_structures.schema)

setup_logging() (in module namematch.utils.utils) split_last_names() (namematch.block.Block method) stage_params_lookup() (namematch.data_structures.parameters.Parameters method) StatLogFilter (class in namematch.utils.utils)

T

to_dict() (in module namematch.utils.utils)

V

validate() (namematch.data_structures.data_file.DataFileList method) (namematch.data_structures.parameters.Parameters method) (namematch.data_structures.variable.VariableList method) validate_blocking_scheme() (namematch.data_structures.parameters.Parameters method) validate_col_parameters() (namematch.data_structures.variable.Variable method) (namematch.data_structures.variable.VariableList method) validate_exactmatch_variables() (namematch.data_structures.parameters.Parameters method)

validate_existance() (namematch.data_structures.data_file.DataFile method) validate_names() (namematch.data_structures.data_file.DataFileList method) validate_record_id_col() (namematch.data_structures.data_file.DataFile method) validate_type_counts() (namematch.data_structures.variable.VariableList method) validate_variable_names() (namematch.data_structures.variable.VariableList method) Variable (class in namematch.data_structures.variable) VariableList (class in namematch.data_structures.variable)

W

write() (namematch.data_structures.data_file.DataFileList method) (namematch.data_structures.parameters.Parameters method) (namematch.data_structures.schema.Schema method) (namematch.data_structures.variable.VariableList method)

write_some_cps() (in module namematch.block)