From dc9b3d227ffc251fb6ae5dd4dc6e4d2d9b86f6d3 Mon Sep 17 00:00:00 2001
From: rileyh Header name: Description: Specifies the training data set as well as a myriad of attributes related to training a model including the dependent variable within that dataset, the independent variables created from the Required: False Type: Object Attributes:Advanced Config Filedecision = "drop_duplicate_with_threshold_ratio"
n_training_iterations = 2
-param_grid = true
+model_parameter_search = {strategy = "grid"}
model_parameters = [
{ type = "random_forest", maxDepth = [7], numTrees = [100], threshold = [0.05, 0.005], threshold_ratio = [1.2, 1.3] },
{ type = "logistic_regression", threshold = [0.50, 0.65, 0.80], threshold_ratio = [1.0, 1.1] }
@@ -393,7 +393,7 @@
Advanced Config Filedecision = "drop_duplicate_with_threshold_ratio"
n_training_iterations = 10
-param_grid = false
+model_parameter_search = {strategy = "explicit"}
model_parameters = [
{ type = "random_forest", maxDepth = 6, numTrees = 50, threshold = 0.5, threshold_ratio = 1.0 },
{ type = "probit", threshold = 0.5, threshold_ratio = 1.0 }
@@ -798,13 +798,13 @@
Training and models¶
-
+
training
comparison_features
section, and the different models you want to use for either model exploration or scoring.
+
dataset
– Type: string
. Location of the training dataset. Must be a csv file.dependent_var
– Type: string
. Name of dependent variable in training dataset.independent_vars
– Type: list
. List of independent variables to use in the model. These must be either part of pipeline_features
or comparison_features
.Training and decision – Type:
string
. Optional. Specifies which decision function to use to create the final prediction. The first option is drop_duplicate_a
, which drops any links for which a record in the a
data set has a predicted match more than one time. The second option is drop_duplicate_with_threshold_ratio
which only takes links for which the a
record has the highest probability out of any other potential links, and the second best link for the a
record is less than the threshold_ratio
.
threshold_ratio
– Type: float
. Optional. For use when decision
is drop_duplicate_with_threshold_ratio
. Specifies the smallest possible ratio to accept between a best and second best link for a given record. Can be used to specify a threshold ratio (beta threshold) to use for all models. Alternatively, unique threshold ratios can be specified in each individual chosen_model
and model_parameters
specification.
model_parameters
– Type: list
. Specifies models to test out in the model_exploration
task. See the models section for more information on model specifications.
param_grid
– Type: boolean
. Optional. If you would like to evaluate multiple hyper-parameters for a single model type in your model_parameters
specification, you can give hyper-parameter inputs as arrays of length >= 1 instead of integers to allow one model per row specification with multiple model eval outputs.
score_with_model
– Type: boolean
. If set to false, will skip the apply_model
step of the matching task. Use this if you want to use the run_all_steps
command and are just trying to generate potential links, such as for the creation of training data.
n_training_iterations
– Type: integer
. Optional; default value is 10. The number of training iterations to use during the model_exploration
task.
scale_data
– Type: boolean
. Optional. Whether to scale the data as part of the machine learning pipeline.
boolean
. Optional.
+param_grid
has been deprecated and will eventually be removed. Please use
+the more flexible model_parameter_search
option by replacing param_grid = false
+with
+model_parameter_search = {strategy = "explicit"}
+
and replacing param_grid = true
with
+model_parameter_search = {strategy = "grid"}
+
[training]
independent_vars = ["race", "srace", "race_interacted_srace", "hits", "hits2", "exact_mult", "ncount", "ncount2", "region", "namefrst_jw","namelast_jw","namefrst_std_jw","byrdiff", "f_interacted_jw_f", "jw_f", "f_caution", "f_pres", "fbplmatch", "m_interacted_jw_m", "jw_m", "m_caution", "m_pres", "mbplmatch", "sp_interacted_jw_sp", "jw_sp", "sp_caution", "sp_pres", "mi", "fsoundex", "lsoundex", "rel", "oth", "sgen", "nbors", "county_distance", "county_distance_squared", "street_jw", "imm_interacted_immyear_caution", "immyear_diff", "imm"]
@@ -839,7 +855,7 @@ Training and decision = "drop_duplicate_with_threshold_ratio"
n_training_iterations = 10
-param_grid = false
+model_parameter_search = {strategy = "explicit"}
model_parameters = [
{ type = "random_forest", maxDepth = 6, numTrees = 50 },
{ type = "probit", threshold = 0.5}
@@ -879,7 +895,7 @@ Household training and modelsfeature_importances = true
decision = "drop_duplicate_with_threshold_ratio"
-param_grid = true
+model_parameter_search = {strategy = "grid"}
n_training_iterations = 10
model_parameters = [
{ type = "logistic_regression", threshold = [0.5], threshold_ratio = [1.1]},
diff --git a/docs/feature_selection_transforms.html b/docs/feature_selection_transforms.html
index 158bf1a..a0dd972 100644
--- a/docs/feature_selection_transforms.html
+++ b/docs/feature_selection_transforms.html
@@ -5,11 +5,11 @@
- Feature Selection Transforms — hlink 3.8.0 documentation
+ Feature Selection Transforms — hlink 4.0.0a1 documentation
-
+
diff --git a/docs/genindex.html b/docs/genindex.html
index ca78f6e..9a7d0a6 100644
--- a/docs/genindex.html
+++ b/docs/genindex.html
@@ -4,11 +4,11 @@
- Index — hlink 3.8.0 documentation
+ Index — hlink 4.0.0a1 documentation
-
+
diff --git a/docs/index.html b/docs/index.html
index 8072c8d..3268a2c 100644
--- a/docs/index.html
+++ b/docs/index.html
@@ -5,11 +5,11 @@
- Welcome to hlink’s documentation! — hlink 3.8.0 documentation
+ Welcome to hlink’s documentation! — hlink 4.0.0a1 documentation
-
+
diff --git a/docs/installation.html b/docs/installation.html
index dcf8303..9a9b728 100644
--- a/docs/installation.html
+++ b/docs/installation.html
@@ -5,11 +5,11 @@
- Installation — hlink 3.8.0 documentation
+ Installation — hlink 4.0.0a1 documentation
-
+
diff --git a/docs/introduction.html b/docs/introduction.html
index c3b8d00..ef882a8 100644
--- a/docs/introduction.html
+++ b/docs/introduction.html
@@ -5,11 +5,11 @@
- Introduction — hlink 3.8.0 documentation
+ Introduction — hlink 4.0.0a1 documentation
-
+
diff --git a/docs/link_tasks.html b/docs/link_tasks.html
index 4bc83c5..4036197 100644
--- a/docs/link_tasks.html
+++ b/docs/link_tasks.html
@@ -5,11 +5,11 @@
- Link Tasks — hlink 3.8.0 documentation
+ Link Tasks — hlink 4.0.0a1 documentation
-
+
diff --git a/docs/models.html b/docs/models.html
index 288d9f3..911dfa9 100644
--- a/docs/models.html
+++ b/docs/models.html
@@ -5,11 +5,11 @@
- Models — hlink 3.8.0 documentation
+ Models — hlink 4.0.0a1 documentation
-
+
diff --git a/docs/objects.inv b/docs/objects.inv
index 1c309079b81852fd5f4d837db9912320e8b17591..6a555eb4567ca2fd5368bf068fdabdb8ba3fd036 100644
GIT binary patch
delta 18
Zcmey${GEA%CA*29fu2F4;YPddi~u~<1?&I-
delta 16
Xcmey){FQlvC9AQXg`UAihwY32GFb&-
diff --git a/docs/pipeline_features.html b/docs/pipeline_features.html
index 8073569..6bb8c0c 100644
--- a/docs/pipeline_features.html
+++ b/docs/pipeline_features.html
@@ -5,11 +5,11 @@
- Pipeline generated features — hlink 3.8.0 documentation
+ Pipeline generated features — hlink 4.0.0a1 documentation
-
+
diff --git a/docs/running_the_program.html b/docs/running_the_program.html
index 7cf2e39..c285b76 100644
--- a/docs/running_the_program.html
+++ b/docs/running_the_program.html
@@ -5,11 +5,11 @@
- Running hlink — hlink 3.8.0 documentation
+ Running hlink — hlink 4.0.0a1 documentation
-
+
diff --git a/docs/search.html b/docs/search.html
index 5d4f15f..a016028 100644
--- a/docs/search.html
+++ b/docs/search.html
@@ -4,12 +4,12 @@
- Search — hlink 3.8.0 documentation
+ Search — hlink 4.0.0a1 documentation
-
+
diff --git a/docs/searchindex.js b/docs/searchindex.js
index 7c7bb5e..cdd15a4 100644
--- a/docs/searchindex.js
+++ b/docs/searchindex.js
@@ -1 +1 @@
-Search.setIndex({"alltitles": {"1:1 substitution by data table": [[12, "substitution-by-data-table"]], "Advanced Config File": [[3, "advanced-config-file"]], "Advanced Usage": [[0, "advanced-usage"]], "Advanced Workflow Examples": [[13, null]], "Aggregate Features": [[1, "aggregate-features"]], "An Example Model Exploration Workflow": [[13, "an-example-model-exploration-workflow"]], "Basic Config File": [[3, "basic-config-file"]], "Basic Usage": [[0, "basic-usage"]], "Blocking": [[3, "blocking"]], "Column Mappings": [[0, null], [3, "column-mappings"]], "Comparison Features": [[1, null], [3, "comparison-features"]], "Comparison Types": [[1, "comparison-types"], [2, "comparison-types"]], "Comparisons": [[2, null], [3, "comparisons"]], "Configuration": [[3, null]], "Configuration API": [[5, "configuration-api"], [5, null]], "Data sources": [[3, "data-sources"]], "Defining Multiple Comparisons": [[2, "defining-multiple-comparisons"]], "Example interactive mode workflow": [[11, "example-interactive-mode-workflow"]], "Example training data export with generated ML features": [[13, "example-training-data-export-with-generated-ml-features"]], "Export training data after generating features to reuse in different linking years": [[13, "export-training-data-after-generating-features-to-reuse-in-different-linking-years"]], "Feature Selection Transforms": [[4, null]], "Feature Selections": [[3, "feature-selections"]], "Feature add-ons": [[1, "feature-add-ons"]], "Filter": [[3, "filter"]], "Household Aggregate Features": [[1, "household-aggregate-features"]], "Household Comparisons": [[3, "household-comparisons"]], "Household Matching": [[8, "household-matching"]], "Household training and models": [[3, "household-training-and-models"]], "Installation": [[6, null]], "Installing from PyPI": [[6, "installing-from-pypi"]], "Installing from source": [[6, "installing-from-source"]], "Interactive Mode": [[11, "interactive-mode"]], "Introduction": [[7, null]], "Link Tasks": [[8, null]], "Matching": [[8, "matching"]], "Model Exploration and Household Model Exploration": [[8, "model-exploration-and-household-model-exploration"]], "Models": [[9, null]], "Multiple Comparisons": [[3, "multiple-comparisons"]], "Overview": [[2, "overview"], [7, "overview"], [8, "overview"], [8, "id1"], [8, "id4"], [8, "id7"], [8, "id10"], [8, "id13"]], "Pipeline generated features": [[10, null]], "Pipeline-generated Features": [[3, "pipeline-generated-features"]], "Potential Matches Universe": [[3, "potential-matches-universe"]], "Preprocessing": [[8, "preprocessing"]], "Related Configuration Sections": [[8, "related-configuration-sections"], [8, "id3"], [8, "id6"], [8, "id9"], [8, "id12"], [8, "id15"]], "Reporting": [[8, "reporting"]], "Requirements": [[6, "requirements"]], "Running Linking Tasks and Steps": [[11, "running-linking-tasks-and-steps"]], "Running hlink": [[11, null]], "Single Comparison": [[3, "single-comparison"]], "Starting the program": [[11, "starting-the-program"]], "Substitution Columns": [[3, "substitution-columns"]], "Substitution by regex word replace": [[12, "substitution-by-regex-word-replace"]], "Substitutions": [[12, null]], "Task steps": [[8, "task-steps"], [8, "id2"], [8, "id5"], [8, "id8"], [8, "id11"], [8, "id14"]], "Top level configs": [[3, "top-level-configs"]], "Training and Household Training": [[8, "training-and-household-training"]], "Training and models": [[3, "training-and-models"]], "Transformer types": [[10, "transformer-types"]], "Transforms": [[0, "transforms"]], "Using hlink as a Library": [[11, "using-hlink-as-a-library"]], "Welcome to hlink\u2019s documentation!": [[5, null]], "abs_diff": [[1, "abs-diff"]], "add_to_a": [[0, "add-to-a"]], "alias": [[1, "alias"]], "all_equals": [[1, "all-equals"]], "and": [[1, "and"]], "any_equals": [[1, "any-equals"]], "array": [[4, "array"]], "array_index": [[0, "array-index"]], "b_minus_a": [[1, "b-minus-a"]], "bigrams": [[4, "bigrams"]], "btwn_threshold": [[1, "btwn-threshold"]], "bucketizer": [[10, "bucketizer"]], "caution_comp_3": [[1, "caution-comp-3"]], "caution_comp_3_012": [[1, "caution-comp-3-012"]], "caution_comp_4": [[1, "caution-comp-4"]], "caution_comp_4_012": [[1, "caution-comp-4-012"]], "concat_to_a": [[0, "concat-to-a"]], "concat_to_b": [[0, "concat-to-b"]], "concat_two_cols": [[0, "concat-two-cols"]], "condense_strip_whitespace": [[0, "condense-strip-whitespace"]], "decision_tree": [[9, "decision-tree"]], "divide_by_int": [[0, "divide-by-int"]], "either_are_0": [[1, "either-are-0"]], "either_are_1": [[1, "either-are-1"]], "equals": [[1, "equals"]], "equals_as_int": [[1, "equals-as-int"]], "exact_mult": [[1, "exact-mult"]], "extra_children": [[1, "extra-children"]], "f1_match": [[1, "f1-match"]], "f2_match": [[1, "f2-match"]], "fetch_a": [[1, "fetch-a"]], "fetch_b": [[1, "fetch-b"]], "geo_distance": [[1, "geo-distance"]], "get_floor": [[0, "get-floor"]], "gradient_boosted_trees": [[9, "gradient-boosted-trees"]], "gt_threshold": [[1, "gt-threshold"]], "hits": [[1, "hits"]], "hits2": [[1, "hits2"]], "interaction": [[10, "interaction"]], "jaro_winkler": [[1, "jaro-winkler"]], "jaro_winkler_rate": [[1, "jaro-winkler-rate"]], "jaro_winkler_street": [[1, "jaro-winkler-street"]], "jw_max_a": [[1, "jw-max-a"]], "jw_max_b": [[1, "jw-max-b"]], "length_b": [[1, "length-b"]], "lightgbm": [[9, "lightgbm"]], "logistic_regression": [[9, "logistic-regression"]], "look_at_addl_var": [[1, "look-at-addl-var"]], "lower_threshold": [[1, "lower-threshold"]], "lowercase_strip": [[0, "lowercase-strip"]], "mapping": [[0, "mapping"]], "max_jaro_winkler": [[1, "max-jaro-winkler"]], "maximum_jaro_winkler": [[1, "maximum-jaro-winkler"]], "multi_jaro_winkler_search": [[1, "multi-jaro-winkler-search"]], "neither_are_null": [[1, "neither-are-null"]], "not_equals": [[1, "not-equals"]], "not_zero_and_not_equals": [[1, "not-zero-and-not-equals"]], "or": [[1, "or"]], "power": [[1, "power"], [4, "power"]], "present_and_equal_categorical_in_universe": [[1, "present-and-equal-categorical-in-universe"]], "present_and_matching_categorical": [[1, "present-and-matching-categorical"]], "present_and_not_equal": [[1, "present-and-not-equal"]], "present_both_years": [[1, "present-both-years"]], "probit": [[9, "probit"]], "random_forest": [[9, "random-forest"]], "rationalize_name_words": [[0, "rationalize-name-words"]], "rel_jaro_winkler": [[1, "rel-jaro-winkler"]], "remove_alternate_names": [[0, "remove-alternate-names"]], "remove_one_letter_names": [[0, "remove-one-letter-names"]], "remove_prefixes": [[0, "remove-prefixes"]], "remove_punctuation": [[0, "remove-punctuation"]], "remove_qmark_hyphen": [[0, "remove-qmark-hyphen"]], "remove_stop_words": [[0, "remove-stop-words"]], "remove_suffixes": [[0, "remove-suffixes"]], "replace_apostrophe": [[0, "replace-apostrophe"]], "second_gen_imm": [[1, "second-gen-imm"]], "soundex": [[4, "soundex"]], "split": [[0, "split"]], "sql_condition": [[1, "sql-condition"], [4, "sql-condition"]], "substring": [[0, "substring"]], "sum": [[1, "sum"]], "threshold": [[1, "threshold"]], "times": [[1, "times"]], "union": [[4, "union"]], "upper_threshold": [[1, "upper-threshold"]], "when_value": [[0, "when-value"]], "xgboost": [[9, "xgboost"]]}, "docnames": ["column_mappings", "comparison_features", "comparisons", "config", "feature_selection_transforms", "index", "installation", "introduction", "link_tasks", "models", "pipeline_features", "running_the_program", "substitutions", "use_examples"], "envversion": {"sphinx": 64, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2}, "filenames": ["column_mappings.md", "comparison_features.md", "comparisons.md", "config.md", "feature_selection_transforms.md", "index.rst", "installation.md", "introduction.md", "link_tasks.md", "models.md", "pipeline_features.md", "running_the_program.md", "substitutions.md", "use_examples.md"], "indexentries": {}, "objects": {}, "objnames": {}, "objtypes": {}, "terms": {"": [0, 1, 3, 7, 8, 9, 11, 12], "0": [0, 1, 2, 3, 8, 9, 10, 11, 13], "005": 3, "012": 1, "05": [1, 3, 9], "1": [0, 1, 2, 3, 5, 8, 9, 10, 11, 13], "10": [0, 3, 6, 13], "100": [0, 3, 13], "11": [0, 3, 6, 10], "12": [0, 6], "14": 1, "15": 9, "1867": 3, "1868": 3, "1869": 3, "1870": 3, "1871": 3, "1872": 3, "1873": 3, "1900": [3, 13], "1900_1910_potential_fn": [], "1900_1910_potential_fp": [], "1900_1910_training_data_20191023": 3, "1900_1910_training_result": 13, "1910": [1, 3, 13], "1920": 13, "1930": [3, 13], "1940": [3, 13], "1999": [0, 3], "2": [0, 1, 2, 3, 4, 8, 9, 12, 13], "20": 9, "25": 1, "3": [0, 1, 2, 3, 6, 8, 9, 10, 13], "300": 0, "301": 0, "302": 0, "303": 0, "4": [0, 1, 9], "5": [0, 1, 2, 3, 9, 10, 11, 13], "50": [3, 13], "50g": 13, "53": 3, "5g": 11, "6": [0, 3, 9, 10, 13], "65": 3, "7": [0, 1, 3, 9, 13], "75": [3, 9, 13], "79": [2, 3], "7th": 12, "8": [1, 3, 6, 9, 11], "80": 3, "84": [2, 3], "85": [9, 11], "9": 1, "95": 1, "99": [1, 3], "9998": 0, "9999": [0, 3, 10], "A": [0, 1, 2, 3, 4, 10, 11], "AND": [1, 2, 3], "As": [0, 2], "At": [7, 8], "But": [3, 6], "By": [0, 3, 11], "For": [0, 1, 2, 3, 8, 9, 11, 13], "If": [0, 1, 3, 4, 8, 9, 11, 12], "In": [0, 1, 2, 7, 9, 11, 13], "It": [0, 1, 2, 3, 7, 9, 11, 13], "NOT": 1, "OR": [1, 2, 3], "THEN": 1, "The": [0, 1, 2, 3, 4, 6, 8, 9, 10, 11, 13], "Then": [0, 6], "There": [1, 3, 8, 9], "These": [0, 1, 2, 3, 7, 8, 9, 10], "To": [0, 1, 6, 8, 9, 11], "Will": 3, "With": [0, 10], "_": [0, 1, 2, 3, 4, 5, 9, 10, 11], "_a": 1, "_bpl": 1, "_namefrst": 1, "_sex": 1, "a304bt": 3, "ab": 1, "abbrevi": [8, 12], "abl": 3, "about": [3, 11, 13], "abov": [1, 2, 6], "absolut": 1, "accept": [1, 3, 13], "access": [11, 13], "accord": 1, "across": 1, "ad": [0, 1, 2, 3, 9], "add": [0, 2, 5], "add_to_a": 3, "addit": [0, 1, 3, 6, 7, 9, 11], "addl": 1, "addl_var": 1, "adjust": 11, "adopt": 0, "advanc": 5, "affect": [4, 12], "after": [1, 2, 3, 5, 9, 11], "ag": [0, 1, 3, 4], "against": [1, 3, 12], "age_2": 3, "age_at_dataset_b": 0, "age_threshold": 1, "aggreg": 5, "ah": 0, "ahead": 8, "akin": 1, "algorithm": [1, 2, 7, 8], "alia": [0, 3, 8], "all": [0, 1, 3, 4, 8, 9, 10, 11], "allow": [1, 3, 8], "along": 1, "alpha": 9, "alphabet": 0, "alphanumer": 3, "also": [0, 1, 2, 3, 6, 7, 8, 9, 10, 11, 13], "altern": [0, 3, 9], "although": 3, "alwai": 2, "among": 1, "amount": 3, "an": [0, 1, 2, 3, 5, 7, 9, 11], "analysi": 13, "analyz": [11, 13], "ani": [1, 3, 4, 6, 9], "anoth": [0, 1, 3, 4, 8, 9], "anyon": 8, "anywher": 12, "apach": 6, "apart": 0, "api": [3, 7, 10], "apostroph": 0, "appear": [0, 1], "appli": [0, 2, 3, 4, 8, 9, 13], "apply_model": 3, "appropri": 3, "ar": [0, 1, 2, 3, 4, 6, 7, 8, 9, 10, 11, 13], "arbitrari": 0, "area": [], "aren": 1, "arg": 13, "argument": [1, 11, 13], "around": 3, "arrai": [0, 3, 5, 10], "array_index": 3, "ask": 13, "aspect": [8, 11], "assert": [1, 11], "assum": 3, "attach_vari": 3, "attempt": 3, "attribut": [0, 1, 2, 3, 4, 8, 9, 10, 11, 12], "auto": 9, "automat": [0, 3, 6, 8], "av": 12, "avail": [0, 1, 3, 4, 6, 8, 9, 10, 13], "avenu": [0, 12], "b": [0, 1, 2, 3, 4, 11], "b200": 3, "back": 1, "backup": 1, "base": [1, 3, 8], "basic": 5, "becaus": 2, "been": 7, "befor": [0, 1, 3, 4, 6, 8], "begin": 11, "behind": 0, "being": [1, 8], "belong": 3, "below": [0, 1, 3, 4, 9, 10, 11], "best": [3, 8], "beta": [3, 9], "better": [0, 7], "between": [0, 1, 2, 3, 7, 8, 9, 11, 13], "beyond": 1, "bigint": 3, "bigram": [3, 5], "bin": 9, "binomi": 9, "birth": 1, "birthplac": [0, 3], "birthyr": [0, 3], "birthyr_3": 3, "birthyr_col": 1, "block": [2, 5, 8], "blvd": 0, "boolean": [1, 3, 4, 12, 13], "boost": [5, 9], "born": 1, "borrow_t": 11, "both": [0, 1, 2, 3, 8, 13], "boundari": 1, "bpl": [0, 1, 3], "bpl1": 3, "bpl2": 3, "bpl2_str": 3, "bpl3": 3, "bpl_clean": 3, "bpl_orig": 3, "bpl_root": 0, "bpl_str": 3, "bplmatch": 3, "broken": 7, "btwn": 1, "bucket": [3, 8], "built": 6, "builtin": 1, "byrdifcat": 3, "byrdiff": [1, 3, 13], "c": [1, 9], "c201": 3, "calcul": 1, "call": [0, 9], "can": [0, 1, 2, 3, 4, 6, 7, 8, 9, 11, 13], "cannot": 3, "care": 2, "cartesian": 1, "case": [0, 1, 2, 3, 4, 7], "cast": 1, "categor": [1, 3, 9, 10], "categori": [0, 9], "caus": 9, "caution": [1, 10], "censu": [0, 8, 13], "census": 7, "chang": [0, 1, 3, 6, 11, 13], "charact": 0, "characterist": [7, 8], "check": [1, 11], "check_val_expr": 1, "checkpoint": 4, "child": [0, 9], "children": 1, "chines": 0, "choic": 11, "chosen": 8, "chosen_model": [3, 9, 13], "circl": 0, "circumst": 1, "class": [9, 11], "classif": [8, 9], "classifi": 9, "claus": [0, 1], "clean": [0, 7], "clean_birthyr": [0, 3, 4], "clone": 6, "code": [0, 1, 3, 6], "coeffici": [3, 8], "col": [0, 1], "col_to_add": 3, "col_to_join_on": 3, "col_typ": 3, "column": [1, 4, 5, 8, 10, 11, 12, 13], "column_map": [0, 3, 8], "column_nam": [0, 1, 3, 12], "column_to_append": 0, "combin": [1, 2, 3, 4, 8], "come": 1, "command": [3, 7, 11, 13], "comment": 4, "common": [7, 8, 12, 13], "comp": 1, "comp_a": [1, 2, 3], "comp_b": [1, 2, 3], "comp_c": 1, "comp_d": 1, "compar": [0, 1, 3, 7, 8], "comparis": 3, "comparison": [5, 8], "comparison_featur": [1, 2, 3, 8], "comparison_typ": [1, 2, 3], "complet": 11, "complex": [3, 4], "comput": [1, 4, 8], "concat": 0, "concaten": [0, 1], "condens": 0, "condense_strip_whitespac": 3, "condit": [0, 1, 2, 3, 4, 5, 8], "conf": [11, 13], "config": [1, 4, 5, 8, 11, 13], "configur": [0, 1, 2, 7, 9, 11, 13], "conjuct": 3, "conjunct": 3, "connect": [2, 3], "consid": [1, 2, 9], "consider": 1, "consol": 11, "constraint": [1, 2], "construct": 8, "contain": [0, 1, 3, 12], "context": 10, "continu": [9, 10, 13], "conveni": 11, "convert": [0, 1, 3], "convert_ints_to_long": 3, "copi": [4, 13], "core": [1, 8, 11, 13], "correspond": [7, 8], "could": [0, 2, 3], "count": [1, 11, 13], "counterpart": 9, "counti": [0, 1], "county_1900_1910_distances_km": 1, "county_a": 1, "county_b": 1, "county_dist": [1, 3, 13], "county_distance_lookup": 1, "county_distance_squar": [1, 3, 13], "county_state_dist": 1, "court": 0, "cover": 10, "coverag": [], "cpu": 11, "creat": [0, 3, 7, 8, 10, 11, 12, 13], "creation": 3, "crosswalk": 8, "csv": [1, 3, 8, 11, 12, 13], "current": [1, 2, 3, 9, 11], "d": 1, "d425": 3, "data": [0, 1, 5, 7, 8, 11], "databas": 11, "datafram": [8, 11, 13], "dataset": [0, 1, 3, 4, 7, 8, 11, 13], "datasourc": [1, 3, 11], "datasource_a": [3, 8], "datasource_b": [3, 8], "de": 9, "decis": [3, 5, 9, 13], "decisiontreeclassifi": 9, "default": [0, 1, 2, 3, 8, 9, 11], "defin": [1, 3, 5, 8, 10, 11], "definit": [3, 8], "demograph": 8, "depend": [1, 2, 3, 6, 9, 13], "dependent_var": [3, 13], "depth": 9, "deriv": 13, "derived_from": 3, "desc": 11, "describ": [0, 1, 2, 3, 11], "descript": [3, 11], "detail": [0, 3, 11], "detect": 9, "determin": [1, 8], "determinist": [7, 8], "dev": 6, "develop": [6, 7], "df": [3, 11], "dictionari": 11, "diff": 1, "differ": [0, 1, 3, 5, 7, 8], "digit": 0, "dir": 12, "directli": [2, 9], "directori": [6, 11, 13], "disabl": 9, "discard": 9, "discret": 9, "discuss": 3, "dist": 1, "dist_tabl": 1, "distanc": [1, 9], "distance_col": 1, "distance_km": 1, "distances_fil": 1, "distinct": 1, "divid": 0, "divide_by_int": 3, "do": [0, 1, 2, 4, 9, 11, 13], "doc": [9, 10], "document": [1, 3, 9, 11, 13], "doe": [1, 4, 8, 9, 13], "don": [3, 4], "doubl": 10, "down": [0, 7, 13], "drastic": 8, "drop": [0, 3, 11], "drop_al": 11, "drop_all_prc": 11, "drop_all_temp": 11, "drop_data_from_scored_match": 3, "drop_duplicate_a": 3, "drop_duplicate_with_threshold_ratio": [3, 9, 13], "duplic": [3, 9], "durat": 1, "dure": [1, 2, 3, 8], "durmarr": [1, 3], "e": 6, "each": [0, 1, 2, 3, 4, 6, 7, 8, 9, 10, 11], "easiest": [6, 11], "easili": 11, "edit": 6, "effect": [2, 4], "either": [0, 1, 2, 3, 7, 12], "either_0": 1, "either_1": 1, "element": 0, "elig": 8, "els": [1, 3, 4], "else_v": 1, "else_valu": 0, "empti": 1, "enabl": [3, 8, 9, 11], "encod": [3, 4], "encount": 9, "end": [0, 1, 3, 4, 12], "enorm": 9, "ensur": 3, "enter": 11, "entir": [0, 3], "enum_dist": 1, "enumer": 11, "equal": [2, 3, 12], "equal_and_not_null_templ": 1, "equival": 3, "error": [3, 9, 10], "especi": 3, "eta": 9, "etc": 13, "eval": 3, "evalu": [1, 3, 7, 8, 9], "even": 1, "everi": [1, 4], "ex": 1, "exact": [1, 3], "exact_mult": [3, 13], "exampl": [0, 1, 2, 3, 5, 9], "except": [3, 10], "exclud": 1, "excute_command": 11, "execut": 11, "execute_command": 11, "execute_task": 11, "executor": 11, "executor_memori": [11, 13], "exist": [1, 3, 11], "exit": 11, "expand": 3, "expand_length": 3, "expect": 1, "experi": 7, "experiment": [8, 11], "explicitli": [1, 10], "explod": [2, 3, 8], "exploded_df_a": 11, "exploded_df_b": 11, "explor": [3, 5, 7, 11], "expon": 4, "exponenti": 1, "export": [5, 8, 11], "express": [0, 1, 3], "extend": 1, "extens": 8, "extra": [1, 9], "extract": 3, "f": [1, 11], "f1": 1, "f1_match": 3, "f2": 1, "f2_match": 3, "f_caution": [3, 13], "f_interacted_jw_f": [3, 13], "f_pre": [3, 13], "factori": 11, "fail": 3, "fallback": 1, "fals": [1, 3, 4, 7, 11, 13], "famili": 9, "father_namefrst": 1, "favor": 1, "fbpl": 1, "fbpl_nomatch": 1, "fbplmatch": [3, 13], "featur": [2, 5, 7, 8, 9, 11], "feature_import": [3, 8, 13], "feature_nam": [2, 3], "feature_select": [2, 3, 4, 8], "featuresubsetstrategi": 9, "fed": [3, 8], "femal": [3, 12], "fetch": 1, "fetch_a": 3, "few": [4, 9], "fewer": [1, 9], "fi": 1, "file": [1, 4, 5, 7, 8, 11, 12, 13], "filepath": 11, "fill": 1, "filter": [1, 2, 5, 8, 12], "final": [1, 3, 13], "find": [1, 8, 13], "finish": 11, "first": [0, 1, 3, 6, 8, 11, 12], "first_init_col": 1, "first_nam": 0, "five": 11, "fix": 8, "flag": [1, 2, 3, 10, 11, 13], "flexibl": [1, 2], "float": [1, 3, 9], "floor": 0, "focus": [2, 8], "follow": [0, 1, 2, 7, 11, 12, 13], "force_row_wis": 9, "foreign": 1, "forest": [5, 9], "form": [1, 3, 8, 12], "format": 0, "four": 1, "framework": 13, "from": [0, 1, 3, 5, 7, 8, 10, 11, 13], "from_icpsrctyi": 1, "from_statefip": 1, "fsoundex": [3, 13], "full": [3, 8, 9, 13], "full_count_1870_1880": 11, "full_count_1900_1910": 13, "fullcount_1870_1880": 11, "function": [0, 1, 3, 7, 11], "further": [7, 13], "gamma": 9, "gbtclassifi": 9, "gen": 1, "gener": [0, 1, 5, 7, 8, 11], "generalizedlinearregress": 9, "geo": 1, "geograph": 1, "get": [0, 1, 2, 3, 11], "get_floor": 3, "get_set": 11, "get_step": 11, "get_tabl": 11, "get_task": 11, "github": 6, "give": [0, 3], "given": [0, 1, 2, 3, 4, 13], "go": [3, 11], "good": 1, "gradient": [5, 9], "greater": [1, 2, 6], "greatest": 1, "group": [3, 8], "gt": 1, "h": 11, "ha": [0, 1, 2, 3, 4, 7, 9, 11, 13], "handl": 11, "harmon": 0, "have": [0, 1, 2, 3, 4, 6, 7, 8, 9, 11, 13], "haven": 3, "head": 0, "header": [3, 10, 12], "help": [8, 9, 11], "here": [2, 3, 8, 9, 11, 13], "hh": [1, 2], "hh_blocked_match": 11, "hh_col": 3, "hh_comparison": [2, 3, 8], "hh_match": [3, 11], "hh_model_eval_repeat_fn": 11, "hh_model_eval_repeat_fp": 11, "hh_model_eval_training_data": 11, "hh_model_eval_training_featur": 11, "hh_model_eval_training_result": 11, "hh_model_eval_training_vector": 11, "hh_model_explor": 11, "hh_potential_match": [2, 11], "hh_potential_matchs_prep": 11, "hh_predicted_match": 11, "hh_repeat_fn": [], "hh_repeat_fp": [], "hh_scored_potential_match": 11, "hh_train": [1, 3, 8, 11, 13], "hh_training_data": 11, "hh_training_data_1900_1910": 3, "hh_training_featur": [11, 13], "hh_training_result": 13, "hidden": 11, "hierarch": [7, 11], "hierarchi": 11, "high": [9, 11], "highest": [1, 3, 9], "highli": [7, 8], "histid": [1, 3, 13], "histid_col": 1, "hit": [3, 11, 13], "hits2": [3, 13], "hlink": [0, 1, 2, 3, 4, 6, 7, 8, 9, 13], "hold": 10, "hot": 3, "household": [0, 2, 5, 7, 9, 11, 13], "how": [1, 3, 8], "howev": [4, 7, 13], "hundr": 0, "hyper": [3, 7, 13], "hyperparamet": 13, "hyphen": 0, "i": [0, 1, 2, 3, 4, 6, 7, 8, 9, 11, 12, 13], "id": [1, 3], "id_column": [1, 3], "ident": 13, "identifi": [3, 7, 13], "if_valu": 0, "ignor": 7, "ii": [0, 3], "iii": [0, 3], "imm": [1, 3, 13], "imm_interacted_bplmatch": 3, "imm_interacted_immyear_caut": [3, 13], "immigr": 1, "immyear_caut": [3, 10], "immyear_diff": [1, 3, 10, 13], "implement": [9, 13], "implicitli": 2, "import": [3, 8, 11], "improv": 8, "includ": [1, 3, 8, 9, 10, 11], "incompar": 1, "increas": 10, "independ": [0, 3], "independent_var": [1, 3, 13], "index": [0, 6], "indic": [1, 13], "individu": [1, 3, 8, 13], "inf": 10, "inform": [0, 1, 3, 11], "ingest": 8, "initi": [0, 1, 11], "input": [0, 1, 3, 4, 7, 8, 11, 12], "input_col": 4, "input_column": [3, 4, 10], "input_table_nam": 11, "inspect": 8, "instal": [5, 9], "instanc": [0, 9], "instead": [1, 3, 4, 6, 8], "instruct": [6, 11], "int": [0, 1, 3, 4, 9], "integ": [0, 1, 3, 10], "integr": [6, 9], "interact": [3, 5, 8, 13], "interfac": 11, "intermedi": 11, "introduct": 5, "introspect": 8, "invalid": [1, 9], "ipum": [0, 7], "ipython": 11, "isn": 13, "istemporari": 11, "item": 0, "iter": 3, "its": [0, 1, 7, 9, 11], "itself": [1, 2], "iv": 3, "jaro": [1, 10], "jaro_winkl": 3, "java": 6, "job": 11, "join": [1, 3, 12], "join_column": [3, 12], "join_valu": [3, 12], "jr": [0, 3], "json": [3, 11], "just": [1, 3, 11, 13], "jw": 1, "jw_col_templ": 1, "jw_f": [1, 3, 13], "jw_m": [3, 10, 13], "jw_max_a": 3, "jw_max_b": 3, "jw_sp": [3, 13], "jw_street": 1, "jw_threshold": 1, "kei": [1, 8, 11], "key_count": 1, "kind": 1, "know": 3, "known": 0, "label": 9, "languag": 7, "larger": 9, "last": [0, 1, 8, 10], "latest": 6, "launch": [11, 13], "law": 0, "lead": 0, "learn": [1, 2, 3, 7, 8, 9, 11, 13], "learningr": 9, "least": [0, 1, 9], "leav": 0, "left": 9, "length": [1, 3, 10], "less": [1, 3], "let": 11, "letter": 0, "level": [1, 5, 11], "leverag": 3, "libomp": 9, "librari": [5, 7, 9], "lightgbm": 5, "lightgbmclassifi": 9, "like": [0, 2, 3, 8, 11, 12], "limit": 3, "line": [7, 11], "link": [0, 1, 3, 5, 7, 9], "link_run": 11, "linkrun": [7, 11], "list": [0, 1, 3, 4, 9, 11, 12], "liter": 3, "ll": 11, "load": 11, "load_conf_fil": 11, "load_config": 11, "loc_a": 1, "loc_a_0": 1, "loc_a_1": 1, "loc_b": 1, "loc_b_0": 1, "loc_b_1": 1, "locat": [1, 3, 11], "log2": 9, "logic": [0, 2, 3], "logist": [5, 9], "logistic_regress": [3, 13], "logisticregress": 9, "long": [3, 12], "longest": 8, "look": [1, 2, 11, 12], "lookup": 1, "lower": [0, 1], "lowercas": 0, "lowercase_strip": 3, "lowest": 0, "lr": 11, "lsoundex": [3, 13], "m": [0, 1], "m_caution": [1, 3, 10, 13], "m_interacted_jw_m": [3, 10, 13], "m_namefrst": 1, "m_pre": [3, 10, 13], "machin": [1, 2, 3, 7, 8, 9, 11, 13], "made": 6, "mai": [0, 2, 3, 7, 8, 9, 11, 12], "main": 11, "mainli": 1, "major": [1, 11], "make": [0, 1, 2, 3, 6, 13], "male": [3, 12], "mani": [2, 8, 9, 11], "manual": 13, "map": [5, 8, 10], "mardurmatch": [1, 3], "mark": 2, "marriag": 1, "match": [0, 1, 2, 5, 7, 9, 11, 12, 13], "matches_df": 11, "matrix": 13, "max": [1, 9, 11], "max_depth": 9, "maxbin": 9, "maxdepth": [3, 9, 13], "maximum": [1, 9], "maximum_jw": 1, "mbpl": 1, "mbplmatch": [3, 13], "mean": [0, 2, 3], "meant": 3, "meet": 1, "member": [1, 8], "memori": 11, "men": 3, "messag": 11, "metadata": 8, "method": [11, 13], "mfbplmatch": 1, "mi": [3, 13], "mi0": 1, "mi1": 1, "mid_init_col": 1, "mid_init_match": 1, "middl": [0, 1], "might": 13, "minimum": [1, 9], "mininstancespernod": 9, "minu": [1, 3], "mismatch": 1, "miss": [1, 11], "ml": [3, 9, 10], "mode": [5, 6, 13], "model": [5, 7, 11], "model_eval_repeat_fn": 11, "model_eval_repeat_fp": 11, "model_eval_training_data": 11, "model_eval_training_featur": 11, "model_eval_training_result": 11, "model_eval_training_vector": 11, "model_explor": [3, 9, 11, 13], "model_paramet": [3, 8, 13], "modifi": 3, "modul": 11, "moment": 8, "momloc": 1, "more": [0, 1, 2, 3, 9, 10, 11, 13], "most": [0, 1, 8, 11], "mother": 10, "mother_birthyr": 1, "mpre": 1, "mr": 0, "much": [1, 8], "mult": 1, "multi": 1, "multipl": [0, 1, 5, 9, 11], "multipli": 1, "must": [0, 1, 2, 3, 4, 9, 10, 12], "my": [11, 13], "my_conf": 11, "my_fil": 3, "myriad": 3, "n": [1, 9, 10], "n_training_iter": [3, 8, 13], "name": [0, 1, 3, 4, 9, 11, 12], "name_col": 1, "name_std": [3, 12], "namefrst": [0, 1, 3], "namefrst_clean": [0, 3], "namefrst_init": 1, "namefrst_jw": [1, 2, 3, 13], "namefrst_mid_init": [0, 1], "namefrst_mid_init_2": 1, "namefrst_rel": 1, "namefrst_related_row": 1, "namefrst_split": [0, 3], "namefrst_std": [3, 12], "namefrst_std_jw": [3, 13], "namefrst_unstd": [1, 3], "namefrst_unstd_bigram": 4, "namelast": [1, 3], "namelast1": 1, "namelast2": 1, "namelast3": 1, "namelast_bigram": 3, "namelast_clean": [1, 3, 4], "namelast_clean_bigram": [3, 4], "namelast_clean_soundex": 4, "namelast_equal_as_int": 1, "namelast_frst_bigram": 4, "namelast_jw": [2, 3, 13], "namelast_jw_max": 1, "namelast_neighbor": 1, "namelast_popular": 1, "namelast_popularity_sum": 1, "nativ": 1, "nbor": [1, 3, 13], "ncount": [3, 4, 13], "ncount2": [3, 4, 13], "nearest": 0, "necessari": [4, 13], "need": [0, 1, 2, 3, 8, 9, 11, 13], "neg": 7, "neighbor": 1, "neighborhood": 1, "neither": 1, "nest": [2, 3, 7], "new": [0, 3, 13], "new_marr": [1, 3], "newli": 3, "niu": 1, "no_first_pad": 4, "node": 9, "non": 0, "nonzero": 1, "nor": 1, "normal": [8, 9], "note": [2, 3], "now": [2, 11], "null": [1, 3, 4], "null_fil": 3, "num": 11, "num_col": 1, "number": [0, 1, 3, 4, 8, 9, 11], "numer": [0, 1], "numtre": [3, 9, 13], "nvl": 1, "object": [1, 3, 7, 11], "often": [2, 4, 11], "onc": [1, 11], "one": [0, 1, 3, 8], "onethird": 9, "onli": [0, 1, 2, 3, 8, 9, 13], "ons": 5, "oper": [0, 1, 2, 3, 9], "option": [0, 1, 3, 4, 7, 8, 9, 11, 13], "or_group": 3, "order": [0, 3, 8], "org": 6, "organ": 11, "original_valu": 3, "oth": [3, 13], "other": [1, 3, 9, 13], "otherwis": [0, 1, 10, 13], "our": 11, "out": [3, 4, 8, 13], "output": [0, 1, 2, 3, 4, 7, 8, 11, 13], "output_col": 4, "output_column": [3, 4, 10], "output_suspicious_td": [], "output_table_nam": 11, "output_typ": 3, "outsid": 10, "overrid": [0, 3], "override_column_a": [0, 3, 4], "override_column_b": [0, 3, 4], "override_transform": [0, 3], "overview": 5, "own": [1, 3], "p": 3, "packag": [6, 9], "page": [1, 2, 3, 11], "pair": [1, 2, 3, 13], "param": 13, "param_grid": [3, 13], "paramet": [3, 7, 8, 9, 11, 13], "parent": [0, 1, 12], "parent_step_chang": 1, "parenthes": 3, "parquet": [3, 8], "part": [3, 8], "particular": [1, 2, 3], "particularli": 1, "partit": 13, "pass": [1, 8, 9], "passthrougharg": 9, "path": [1, 3, 11, 12, 13], "pattern": 11, "peopl": [0, 1, 7, 11], "per": [1, 3, 9, 10, 11], "percent": 8, "percentag": 1, "perform": [1, 3, 7, 8, 9, 12], "persist": 11, "person": [0, 1, 7], "pip": [6, 9], "pipelin": 5, "pipeline_featur": [3, 8, 10], "piplin": 3, "placehold": 1, "pleas": [3, 9, 11], "plu": 3, "point": [10, 13], "popul": 8, "posit": [0, 1, 7], "possibl": 3, "post": [3, 8], "potenti": [1, 2, 5, 8, 9], "potential_match": [1, 2, 8, 11], "potential_matches_prep": 11, "potential_matches_univers": [3, 8], "power": 5, "predefin": 1, "predict": [3, 13], "predicted_match": 11, "prediction_col": 3, "preexist": 11, "prefer": 13, "prefix": 0, "prep": 3, "prep_step": 11, "prepar": [7, 8, 11], "prepend": 4, "prepped_df_a": 11, "prepped_df_b": 11, "preprocess": [5, 7, 11, 13], "present": [1, 3, 10], "pretti": 2, "primari": [1, 7], "primarili": [1, 8], "print": 11, "probabilist": [3, 7], "probabl": [0, 3, 9], "probit": [3, 5], "proceed": 12, "process": [2, 3, 7, 11], "produc": [0, 11], "product": [1, 7, 13], "program": [1, 3, 8, 13], "project": 6, "prompt": 11, "provid": [0, 3, 4, 7, 8, 9, 10, 11], "pull": 8, "punctuat": 0, "put": [11, 13], "py": [1, 3], "pypi": 5, "pyspark": [6, 9, 10, 11], "python": [6, 7, 9, 11], "q": [11, 13], "qmark": 0, "qualifi": 3, "queri": [1, 3], "race": [0, 1, 3, 10, 13], "race_interacted_srac": [3, 10, 13], "racematch": 3, "rais": [1, 4, 9], "random": [5, 9], "random_forest": [3, 13], "randomforestclassifi": 9, "rang": [3, 10], "rate": 1, "ratio": [3, 9], "ration": 0, "rationalize_name_word": 3, "raw": [0, 3, 8, 11], "raw_df_a": 11, "raw_df_b": 11, "read": [0, 1, 3, 8, 11], "readm": 3, "real": 7, "reason": 1, "recod": 0, "record": [0, 1, 2, 3, 7, 8, 9], "recurs": [2, 3], "reduc": [4, 8], "refer": 3, "regex": 5, "regex_word_replac": 12, "region": [3, 13], "region_dict": 3, "regionf": 3, "regist": [8, 11], "regress": [5, 9], "regular": [], "rel": [1, 3, 13], "relat": [0, 1, 3], "relate_a": [3, 10], "relate_col": 1, "relate_div_100": [0, 1, 3], "related_individual_max_jw": 1, "related_individual_row": 1, "relatematch": [1, 3], "relatetyp": [3, 10], "relatetype_interacted_relatematch": 3, "relationship": 7, "relev": 13, "reload": 11, "remain": 8, "remov": 0, "remove_alternate_nam": 3, "remove_qmark_hyphen": 3, "remove_suffix": 3, "repeat_fn": [], "repeat_fp": [], "repeatedli": [], "replac": [0, 1, 2, 5], "replace_apostroph": 3, "replaced_birthyr": [1, 3, 4], "report": [1, 5, 7, 11], "repositori": 6, "repres": [0, 1, 3, 10, 11], "represent": 8, "reproduc": 11, "request": 8, "requir": [0, 1, 2, 3, 4, 5, 8, 9, 10, 11, 12], "research": 7, "reshap": 8, "resourc": 4, "respect": [1, 8], "restrict": 2, "result": [0, 1, 7, 10, 11, 13], "return": [1, 4, 11], "reus": 5, "right": [9, 11], "risk": 1, "road": 0, "robust": 3, "root": 6, "round": [0, 3], "row": [0, 3, 4], "rule": [2, 7, 8], "run": [5, 6, 7, 8, 13], "run_all_step": [3, 11, 13], "run_step": 11, "runtim": 8, "sai": 11, "same": [0, 1, 2, 3, 4, 7, 8, 11], "sampl": 1, "satisfi": [2, 3, 8], "save": [3, 8, 13], "scala": [1, 9], "scale": 3, "scale_data": [3, 13], "scenario": 13, "schema": 3, "score": [1, 3, 8, 9, 10], "score_with_model": [3, 13], "scored_potential_match": 11, "scratch": 3, "script": [3, 7, 11], "search": 1, "second": [0, 1, 3, 9, 12], "secondari": 1, "secondary_distance_col": 1, "secondary_distances_fil": 1, "secondary_key_count": 1, "secondary_loc_a": 1, "secondary_loc_b": 1, "secondary_source_column": 1, "secondary_table_nam": 1, "section": [0, 1, 2, 3, 9, 13], "see": [1, 3, 6, 9, 11, 13], "seen": 1, "select": [0, 1, 5, 7, 11, 13], "send": 9, "separ": 8, "sequenc": 7, "seri": 11, "serialp": 3, "serv": 1, "set": [0, 1, 2, 3, 4, 7, 8, 9, 11, 13], "set_executor_memori": 11, "set_link_task": 11, "set_loc": 11, "set_num_cor": 11, "set_preexisting_t": 11, "set_print_sql": 11, "set_value_column_a": [3, 4], "set_value_column_b": [3, 4], "sever": [1, 7], "sex": [1, 3, 12], "sex_equ": 3, "sex_region_interact": 3, "sex_regionf_interact": 3, "sexmatch": 3, "sgen": [1, 3, 13], "share": 7, "short": 3, "should": [1, 3, 4, 9, 10, 11], "show": 11, "showf": 11, "shut": 13, "sibl": 0, "sign": 1, "signific": 0, "similar": [1, 3], "simpli": [0, 3], "simplifi": 1, "sinc": [0, 3, 9], "singl": [0, 4, 11, 13], "size": 1, "skip": [3, 4, 8], "sm_bpl": 1, "sm_namefrst": 1, "sm_sex": 1, "small": 3, "smaller": 7, "smallest": 3, "sn_bpl": 1, "sn_namefrst": 1, "sn_sex": 1, "so": [0, 1, 2, 3, 6, 9, 13], "some": [0, 1, 2, 3, 4, 7, 8, 9, 11], "someth": 11, "sometim": [3, 9], "somewhat": 2, "soundex": 5, "sourc": [1, 5, 8, 11, 13], "source_column_a": 1, "source_column_b": 1, "sp": 1, "sp_caution": [1, 3, 13], "sp_interacted_jw_sp": [3, 13], "sp_pre": [3, 13], "space": [0, 3, 4, 12], "span": 13, "spark": [1, 3, 4, 6, 9, 10, 11, 13], "sparkfactori": 11, "sparksess": 11, "sparkxgbclassifi": 9, "special": [1, 9], "specif": [1, 3, 9, 11], "specifi": [0, 1, 3, 7, 8, 10, 11, 12], "split": [3, 4, 8, 9, 10, 13], "split_by_id_a": [3, 13], "sploc": 1, "spous": 0, "spouse_birthyr": 1, "spouse_bpl": 1, "sql": [0, 1, 2, 3, 4, 5, 8, 11], "sql_condit": 3, "sqrt": 9, "squar": 1, "sr": [0, 3], "srace": [3, 10, 13], "stage": 3, "standard": [0, 1, 12], "start": [0, 12], "state": [1, 7], "state_1900_1910_distances_km": 1, "state_dist": 1, "state_distance_lookup": 1, "statecode1": 1, "statecode2": 1, "statefip": [0, 1, 3], "statefip_h": 3, "step": [0, 1, 3, 7], "stepmom": 1, "still": 12, "stop": [0, 9], "street": [0, 1], "street_jw": [1, 3, 13], "street_unstd": 12, "strictli": 10, "string": [0, 1, 3, 4, 8, 9, 11, 12], "strip": [0, 8], "structur": [2, 3, 7], "sub": [1, 2, 3], "subhead": 12, "subset": [3, 12], "substitut": [5, 8], "substitution_column": [3, 8, 12], "substitution_fil": [3, 12], "substitutions_street_abbrev": 12, "subtract": 1, "suffix": 0, "suppli": 12, "support": [0, 2, 3, 8, 9], "suppos": [0, 2, 3], "sure": [2, 3, 6, 11], "surnam": 1, "surround": 0, "suspect": [1, 7], "swap": 12, "synaps": 9, "syntax": 2, "system": [6, 9], "t": [0, 1, 3, 4, 13], "tabl": [1, 2, 3, 5, 8, 11, 13], "table_nam": 1, "tablenam": 11, "tailor": 7, "take": [0, 1, 2, 3, 4, 8, 11], "taken": [0, 1], "task": [2, 3, 5, 7, 9, 13], "task_nam": 11, "tell": [1, 3, 4], "templat": 1, "ten": 1, "term": 3, "test": [3, 8, 13], "text": 11, "than": [0, 1, 2, 3, 9], "thei": [0, 1, 2, 3, 8, 11], "them": [0, 1, 3, 8], "thi": [0, 1, 2, 3, 4, 6, 7, 8, 9, 10, 11, 13], "thing": 3, "those": [1, 3], "though": 1, "thought": 8, "three": [2, 3, 8], "threshold": [2, 3, 9, 13], "threshold_expr": [2, 3], "threshold_ratio": [3, 9, 13], "through": [6, 8, 9, 10, 11], "thu": 1, "time": [0, 3, 8, 9, 11], "to_icpsrctyi": 1, "to_statefip": 1, "togeth": [0, 1, 3], "toml": [3, 7, 11], "tool": [6, 7], "top": [1, 5], "topic": 11, "total": 8, "train": [1, 5, 7, 9, 11], "training_data": [3, 11], "training_data_1900_1910": 13, "training_data_1900_1910_hlink_featur": 13, "training_data_subset": 3, "training_featur": [11, 13], "training_result": 13, "transform": [1, 3, 5, 7, 8], "transformer_typ": [3, 10], "treat": [3, 10], "tree": [5, 9], "true": [1, 3, 4, 8, 9, 10, 12, 13], "try": [3, 9], "tune": [7, 13], "tutori": [3, 11], "two": [0, 1, 2, 3, 4, 7, 8, 10, 11, 13], "type": [0, 3, 4, 5, 8, 9, 11, 12, 13], "typic": [3, 8], "u": 0, "ugli": 2, "under": [1, 3], "underli": 9, "understand": 7, "union": 5, "uniqu": 3, "unit": 7, "univers": [1, 5, 8], "unknown": 1, "unlik": 2, "unrel": 1, "unstabl": [9, 11], "up": [1, 3, 11, 12], "updat": 13, "upper": 1, "upper_threshold": 3, "uppercas": 0, "us": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 12, 13], "us1900": 3, "us1900m_usa": 3, "us1910": 3, "us1910m_usa": 3, "usag": [3, 4, 5, 11], "use_potential_matches_featur": 13, "use_training_data_featur": [3, 8, 13], "user": [1, 11], "usual": [0, 8, 9, 13], "util": 4, "v": 3, "valu": [0, 1, 2, 3, 4, 9, 10, 11, 12], "var": [1, 3], "vari": [0, 3, 4], "variabl": [0, 1, 3, 13], "variant": 12, "varieti": 8, "variou": 9, "ve": 13, "vector": [3, 10], "verbos": 2, "veri": [4, 8], "version": [0, 6, 9, 13], "vi": 3, "via": [6, 7, 9], "view": 9, "vii": 3, "viii": 3, "volumn": 1, "wa": [1, 13], "wai": [1, 2, 3, 6, 11], "want": [0, 1, 3, 11, 13], "washington": 3, "we": [0, 1, 9, 11, 13], "well": 3, "were": 3, "weren": 13, "what": [1, 3, 11, 13], "when": [0, 1, 2, 3, 4, 8, 9, 13], "where": [1, 8, 11, 13], "whether": [1, 3, 12], "which": [0, 1, 2, 3, 4, 7, 8, 9, 10, 11, 12, 13], "white": 0, "whitespac": [0, 8], "who": 1, "whole": [0, 7], "whose": [1, 9], "width": 8, "winkler": [1, 10], "within": [1, 3, 7, 11, 12], "without": 9, "word": [0, 5], "work": [0, 1, 3, 6, 8, 11, 13], "workflow": [4, 5], "world": 7, "would": [1, 2, 3, 13], "write": [1, 11, 13], "written": [3, 7], "x": [3, 10, 11], "x_crosswalk": 11, "x_hh_tfam": 11, "x_hh_tfam_2a": 11, "x_hh_tfam_2b": 11, "x_load": 11, "x_parquet_from_csv": 11, "x_persist": 11, "x_sql": 11, "x_sqlf": 11, "x_summari": 11, "x_tab": 11, "x_tfam": 11, "x_tfam_raw": 11, "x_union": 11, "xgboost": 5, "y": 10, "year": [0, 1, 3, 4, 5], "year_b": 1, "yet": 11, "you": [0, 1, 2, 3, 6, 9, 11, 12, 13], "your": [2, 3, 4, 6, 8, 9, 11, 13], "yrimmig": 1, "zero": 1}, "titles": ["Column Mappings", "Comparison Features", "Comparisons", "Configuration", "Feature Selection Transforms", "Welcome to hlink\u2019s documentation!", "Installation", "Introduction", "Link Tasks", "Models", "Pipeline generated features", "Running hlink", "Substitutions", "Advanced Workflow Examples"], "titleterms": {"": 5, "1": 12, "abs_diff": 1, "add": 1, "add_to_a": 0, "advanc": [0, 3, 13], "after": 13, "aggreg": 1, "alia": 1, "all_equ": 1, "an": 13, "any_equ": 1, "api": 5, "arrai": 4, "array_index": 0, "b_minus_a": 1, "basic": [0, 3], "bigram": 4, "block": 3, "btwn_threshold": 1, "bucket": 10, "caution_comp_3": 1, "caution_comp_3_012": 1, "caution_comp_4": 1, "caution_comp_4_012": 1, "column": [0, 3], "comparison": [1, 2, 3], "concat_to_a": 0, "concat_to_b": 0, "concat_two_col": 0, "condense_strip_whitespac": 0, "config": 3, "configur": [3, 5, 8], "data": [3, 12, 13], "decision_tre": 9, "defin": 2, "differ": 13, "divide_by_int": 0, "document": 5, "either_are_0": 1, "either_are_1": 1, "equal": 1, "equals_as_int": 1, "exact_mult": 1, "exampl": [11, 13], "explor": [8, 13], "export": 13, "extra_children": 1, "f1_match": 1, "f2_match": 1, "fals": [], "featur": [1, 3, 4, 10, 13], "fetch_a": 1, "fetch_b": 1, "file": 3, "filter": 3, "fn": [], "fp": [], "from": 6, "gener": [3, 10, 13], "geo_dist": 1, "get_floor": 0, "gradient_boosted_tre": 9, "gt_threshold": 1, "hit": 1, "hits2": 1, "hlink": [5, 11], "household": [1, 3, 8], "instal": 6, "interact": [10, 11], "introduct": 7, "jaro_winkl": 1, "jaro_winkler_r": 1, "jaro_winkler_street": 1, "jw_max_a": 1, "jw_max_b": 1, "length_b": 1, "level": 3, "librari": 11, "lightgbm": 9, "link": [8, 11, 13], "list": [], "logistic_regress": 9, "look_at_addl_var": 1, "lower_threshold": 1, "lowercase_strip": 0, "map": [0, 3], "match": [3, 8], "max_jaro_winkl": 1, "maximum_jaro_winkl": 1, "ml": 13, "mode": 11, "model": [3, 8, 9, 13], "multi_jaro_winkler_search": 1, "multipl": [2, 3], "neg": [], "neither_are_nul": 1, "not_equ": 1, "not_zero_and_not_equ": 1, "ons": 1, "overview": [2, 7, 8], "pipelin": [3, 10], "posit": [], "potenti": 3, "power": [1, 4], "preprocess": 8, "present_and_equal_categorical_in_univers": 1, "present_and_matching_categor": 1, "present_and_not_equ": 1, "present_both_year": 1, "probit": 9, "program": 11, "pypi": 6, "random_forest": 9, "rationalize_name_word": 0, "regex": 12, "rel_jaro_winkl": 1, "relat": 8, "remove_alternate_nam": 0, "remove_one_letter_nam": 0, "remove_prefix": 0, "remove_punctu": 0, "remove_qmark_hyphen": 0, "remove_stop_word": 0, "remove_suffix": 0, "replac": 12, "replace_apostroph": 0, "report": 8, "requir": 6, "reus": 13, "run": 11, "second_gen_imm": 1, "section": 8, "select": [3, 4], "singl": 3, "soundex": 4, "sourc": [3, 6], "split": 0, "sql_condit": [1, 4], "start": 11, "step": [8, 11], "substitut": [3, 12], "substr": 0, "sum": 1, "tabl": 12, "task": [8, 11], "threshold": 1, "time": 1, "top": 3, "train": [3, 8, 13], "transform": [0, 4, 10], "type": [1, 2, 10], "union": 4, "univers": 3, "upper_threshold": 1, "us": 11, "usag": 0, "welcom": 5, "when_valu": 0, "word": 12, "workflow": [11, 13], "xgboost": 9, "year": 13}})
\ No newline at end of file
+Search.setIndex({"alltitles": {"1:1 substitution by data table": [[12, "substitution-by-data-table"]], "Advanced Config File": [[3, "advanced-config-file"]], "Advanced Usage": [[0, "advanced-usage"]], "Advanced Workflow Examples": [[13, null]], "Aggregate Features": [[1, "aggregate-features"]], "An Example Model Exploration Workflow": [[13, "an-example-model-exploration-workflow"]], "Basic Config File": [[3, "basic-config-file"]], "Basic Usage": [[0, "basic-usage"]], "Blocking": [[3, "blocking"]], "Column Mappings": [[0, null], [3, "column-mappings"]], "Comparison Features": [[1, null], [3, "comparison-features"]], "Comparison Types": [[1, "comparison-types"], [2, "comparison-types"]], "Comparisons": [[2, null], [3, "comparisons"]], "Configuration": [[3, null]], "Configuration API": [[5, "configuration-api"], [5, null]], "Data sources": [[3, "data-sources"]], "Defining Multiple Comparisons": [[2, "defining-multiple-comparisons"]], "Example interactive mode workflow": [[11, "example-interactive-mode-workflow"]], "Example training data export with generated ML features": [[13, "example-training-data-export-with-generated-ml-features"]], "Export training data after generating features to reuse in different linking years": [[13, "export-training-data-after-generating-features-to-reuse-in-different-linking-years"]], "Feature Selection Transforms": [[4, null]], "Feature Selections": [[3, "feature-selections"]], "Feature add-ons": [[1, "feature-add-ons"]], "Filter": [[3, "filter"]], "Household Aggregate Features": [[1, "household-aggregate-features"]], "Household Comparisons": [[3, "household-comparisons"]], "Household Matching": [[8, "household-matching"]], "Household training and models": [[3, "household-training-and-models"]], "Installation": [[6, null]], "Installing from PyPI": [[6, "installing-from-pypi"]], "Installing from source": [[6, "installing-from-source"]], "Interactive Mode": [[11, "interactive-mode"]], "Introduction": [[7, null]], "Link Tasks": [[8, null]], "Matching": [[8, "matching"]], "Model Exploration and Household Model Exploration": [[8, "model-exploration-and-household-model-exploration"]], "Models": [[9, null]], "Multiple Comparisons": [[3, "multiple-comparisons"]], "Overview": [[2, "overview"], [7, "overview"], [8, "overview"], [8, "id1"], [8, "id4"], [8, "id7"], [8, "id10"], [8, "id13"]], "Pipeline generated features": [[10, null]], "Pipeline-generated Features": [[3, "pipeline-generated-features"]], "Potential Matches Universe": [[3, "potential-matches-universe"]], "Preprocessing": [[8, "preprocessing"]], "Related Configuration Sections": [[8, "related-configuration-sections"], [8, "id3"], [8, "id6"], [8, "id9"], [8, "id12"], [8, "id15"]], "Reporting": [[8, "reporting"]], "Requirements": [[6, "requirements"]], "Running Linking Tasks and Steps": [[11, "running-linking-tasks-and-steps"]], "Running hlink": [[11, null]], "Single Comparison": [[3, "single-comparison"]], "Starting the program": [[11, "starting-the-program"]], "Substitution Columns": [[3, "substitution-columns"]], "Substitution by regex word replace": [[12, "substitution-by-regex-word-replace"]], "Substitutions": [[12, null]], "Task steps": [[8, "task-steps"], [8, "id2"], [8, "id5"], [8, "id8"], [8, "id11"], [8, "id14"]], "Top level configs": [[3, "top-level-configs"]], "Training and Household Training": [[8, "training-and-household-training"]], "Training and models": [[3, "training-and-models"]], "Transformer types": [[10, "transformer-types"]], "Transforms": [[0, "transforms"]], "Using hlink as a Library": [[11, "using-hlink-as-a-library"]], "Welcome to hlink\u2019s documentation!": [[5, null]], "abs_diff": [[1, "abs-diff"]], "add_to_a": [[0, "add-to-a"]], "alias": [[1, "alias"]], "all_equals": [[1, "all-equals"]], "and": [[1, "and"]], "any_equals": [[1, "any-equals"]], "array": [[4, "array"]], "array_index": [[0, "array-index"]], "b_minus_a": [[1, "b-minus-a"]], "bigrams": [[4, "bigrams"]], "btwn_threshold": [[1, "btwn-threshold"]], "bucketizer": [[10, "bucketizer"]], "caution_comp_3": [[1, "caution-comp-3"]], "caution_comp_3_012": [[1, "caution-comp-3-012"]], "caution_comp_4": [[1, "caution-comp-4"]], "caution_comp_4_012": [[1, "caution-comp-4-012"]], "concat_to_a": [[0, "concat-to-a"]], "concat_to_b": [[0, "concat-to-b"]], "concat_two_cols": [[0, "concat-two-cols"]], "condense_strip_whitespace": [[0, "condense-strip-whitespace"]], "decision_tree": [[9, "decision-tree"]], "divide_by_int": [[0, "divide-by-int"]], "either_are_0": [[1, "either-are-0"]], "either_are_1": [[1, "either-are-1"]], "equals": [[1, "equals"]], "equals_as_int": [[1, "equals-as-int"]], "exact_mult": [[1, "exact-mult"]], "extra_children": [[1, "extra-children"]], "f1_match": [[1, "f1-match"]], "f2_match": [[1, "f2-match"]], "fetch_a": [[1, "fetch-a"]], "fetch_b": [[1, "fetch-b"]], "geo_distance": [[1, "geo-distance"]], "get_floor": [[0, "get-floor"]], "gradient_boosted_trees": [[9, "gradient-boosted-trees"]], "gt_threshold": [[1, "gt-threshold"]], "hits": [[1, "hits"]], "hits2": [[1, "hits2"]], "interaction": [[10, "interaction"]], "jaro_winkler": [[1, "jaro-winkler"]], "jaro_winkler_rate": [[1, "jaro-winkler-rate"]], "jaro_winkler_street": [[1, "jaro-winkler-street"]], "jw_max_a": [[1, "jw-max-a"]], "jw_max_b": [[1, "jw-max-b"]], "length_b": [[1, "length-b"]], "lightgbm": [[9, "lightgbm"]], "logistic_regression": [[9, "logistic-regression"]], "look_at_addl_var": [[1, "look-at-addl-var"]], "lower_threshold": [[1, "lower-threshold"]], "lowercase_strip": [[0, "lowercase-strip"]], "mapping": [[0, "mapping"]], "max_jaro_winkler": [[1, "max-jaro-winkler"]], "maximum_jaro_winkler": [[1, "maximum-jaro-winkler"]], "multi_jaro_winkler_search": [[1, "multi-jaro-winkler-search"]], "neither_are_null": [[1, "neither-are-null"]], "not_equals": [[1, "not-equals"]], "not_zero_and_not_equals": [[1, "not-zero-and-not-equals"]], "or": [[1, "or"]], "power": [[1, "power"], [4, "power"]], "present_and_equal_categorical_in_universe": [[1, "present-and-equal-categorical-in-universe"]], "present_and_matching_categorical": [[1, "present-and-matching-categorical"]], "present_and_not_equal": [[1, "present-and-not-equal"]], "present_both_years": [[1, "present-both-years"]], "probit": [[9, "probit"]], "random_forest": [[9, "random-forest"]], "rationalize_name_words": [[0, "rationalize-name-words"]], "rel_jaro_winkler": [[1, "rel-jaro-winkler"]], "remove_alternate_names": [[0, "remove-alternate-names"]], "remove_one_letter_names": [[0, "remove-one-letter-names"]], "remove_prefixes": [[0, "remove-prefixes"]], "remove_punctuation": [[0, "remove-punctuation"]], "remove_qmark_hyphen": [[0, "remove-qmark-hyphen"]], "remove_stop_words": [[0, "remove-stop-words"]], "remove_suffixes": [[0, "remove-suffixes"]], "replace_apostrophe": [[0, "replace-apostrophe"]], "second_gen_imm": [[1, "second-gen-imm"]], "soundex": [[4, "soundex"]], "split": [[0, "split"]], "sql_condition": [[1, "sql-condition"], [4, "sql-condition"]], "substring": [[0, "substring"]], "sum": [[1, "sum"]], "threshold": [[1, "threshold"]], "times": [[1, "times"]], "union": [[4, "union"]], "upper_threshold": [[1, "upper-threshold"]], "when_value": [[0, "when-value"]], "xgboost": [[9, "xgboost"]]}, "docnames": ["column_mappings", "comparison_features", "comparisons", "config", "feature_selection_transforms", "index", "installation", "introduction", "link_tasks", "models", "pipeline_features", "running_the_program", "substitutions", "use_examples"], "envversion": {"sphinx": 64, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2}, "filenames": ["column_mappings.md", "comparison_features.md", "comparisons.md", "config.md", "feature_selection_transforms.md", "index.rst", "installation.md", "introduction.md", "link_tasks.md", "models.md", "pipeline_features.md", "running_the_program.md", "substitutions.md", "use_examples.md"], "indexentries": {}, "objects": {}, "objnames": {}, "objtypes": {}, "terms": {"": [0, 1, 3, 7, 8, 9, 11, 12], "0": [0, 1, 2, 3, 8, 9, 10, 11, 13], "005": 3, "012": 1, "05": [1, 3, 9], "1": [0, 1, 2, 3, 5, 8, 9, 10, 11, 13], "10": [0, 3, 6, 13], "100": [0, 3, 13], "11": [0, 3, 6, 10], "12": [0, 6], "14": 1, "15": 9, "1867": 3, "1868": 3, "1869": 3, "1870": 3, "1871": 3, "1872": 3, "1873": 3, "1900": [3, 13], "1900_1910_potential_fn": [], "1900_1910_potential_fp": [], "1900_1910_training_data_20191023": 3, "1900_1910_training_result": 13, "1910": [1, 3, 13], "1920": 13, "1930": [3, 13], "1940": [3, 13], "1999": [0, 3], "2": [0, 1, 2, 3, 4, 8, 9, 12, 13], "20": 9, "25": 1, "3": [0, 1, 2, 3, 6, 8, 9, 10, 13], "300": 0, "301": 0, "302": 0, "303": 0, "4": [0, 1, 3, 9], "5": [0, 1, 2, 3, 9, 10, 11, 13], "50": [3, 13], "50g": 13, "53": 3, "5g": 11, "6": [0, 3, 9, 10, 13], "65": 3, "7": [0, 1, 3, 9, 13], "75": [3, 9, 13], "79": [2, 3], "7th": 12, "8": [1, 3, 6, 9, 11], "80": 3, "84": [2, 3], "85": [9, 11], "9": 1, "95": 1, "99": [1, 3], "9998": 0, "9999": [0, 3, 10], "A": [0, 1, 2, 3, 4, 10, 11], "AND": [1, 2, 3], "As": [0, 2], "At": [7, 8], "But": [3, 6], "By": [0, 3, 11], "For": [0, 1, 2, 3, 8, 9, 11, 13], "If": [0, 1, 3, 4, 8, 9, 11, 12], "In": [0, 1, 2, 7, 9, 11, 13], "It": [0, 1, 2, 3, 7, 9, 11, 13], "NOT": 1, "OR": [1, 2, 3], "THEN": 1, "The": [0, 1, 2, 3, 4, 6, 8, 9, 10, 11, 13], "Then": [0, 6], "There": [1, 3, 8, 9], "These": [0, 1, 2, 3, 7, 8, 9, 10], "To": [0, 1, 6, 8, 9, 11], "Will": 3, "With": [0, 10], "_": [0, 1, 2, 3, 4, 5, 9, 10, 11], "_a": 1, "_bpl": 1, "_namefrst": 1, "_sex": 1, "a304bt": 3, "ab": 1, "abbrevi": [8, 12], "abl": 3, "about": [3, 11, 13], "abov": [1, 2, 6], "absolut": 1, "accept": [1, 3, 13], "access": [11, 13], "accord": 1, "across": 1, "ad": [0, 1, 2, 3, 9], "add": [0, 2, 5], "add_to_a": 3, "addit": [0, 1, 3, 6, 7, 9, 11], "addl": 1, "addl_var": 1, "adjust": 11, "adopt": 0, "advanc": 5, "affect": [4, 12], "after": [1, 2, 3, 5, 9, 11], "ag": [0, 1, 3, 4], "against": [1, 3, 12], "age_2": 3, "age_at_dataset_b": 0, "age_threshold": 1, "aggreg": 5, "ah": 0, "ahead": 8, "akin": 1, "algorithm": [1, 2, 7, 8], "alia": [0, 3, 8], "all": [0, 1, 3, 4, 8, 9, 10, 11], "allow": [1, 8], "along": 1, "alpha": 9, "alphabet": 0, "alphanumer": 3, "also": [0, 1, 2, 3, 6, 7, 8, 9, 10, 11, 13], "altern": [0, 3, 9], "although": 3, "alwai": 2, "among": 1, "amount": 3, "an": [0, 1, 2, 3, 5, 7, 9, 11], "analysi": 13, "analyz": [11, 13], "ani": [1, 3, 4, 6, 9], "anoth": [0, 1, 3, 4, 8, 9], "anyon": 8, "anywher": 12, "apach": 6, "apart": 0, "api": [3, 7, 10], "apostroph": 0, "appear": [0, 1], "appli": [0, 2, 3, 4, 8, 9, 13], "apply_model": 3, "appropri": 3, "ar": [0, 1, 2, 3, 4, 6, 7, 8, 9, 10, 11, 13], "arbitrari": 0, "area": [], "aren": 1, "arg": 13, "argument": [1, 11, 13], "around": 3, "arrai": [0, 3, 5, 10], "array_index": 3, "ask": 13, "aspect": [8, 11], "assert": [1, 11], "assum": 3, "attach_vari": 3, "attempt": 3, "attribut": [0, 1, 2, 3, 4, 8, 9, 10, 11, 12], "auto": 9, "automat": [0, 3, 6, 8], "av": 12, "avail": [0, 1, 3, 4, 6, 8, 9, 10, 13], "avenu": [0, 12], "b": [0, 1, 2, 3, 4, 11], "b200": 3, "back": 1, "backup": 1, "base": [1, 3, 8], "basic": 5, "becaus": 2, "been": [3, 7], "befor": [0, 1, 3, 4, 6, 8], "begin": 11, "behind": 0, "being": [1, 8], "belong": 3, "below": [0, 1, 3, 4, 9, 10, 11], "best": [3, 8], "beta": [3, 9], "better": [0, 7], "between": [0, 1, 2, 3, 7, 8, 9, 11, 13], "beyond": 1, "bigint": 3, "bigram": [3, 5], "bin": 9, "binomi": 9, "birth": 1, "birthplac": [0, 3], "birthyr": [0, 3], "birthyr_3": 3, "birthyr_col": 1, "block": [2, 5, 8], "blvd": 0, "boolean": [1, 3, 4, 12, 13], "boost": [5, 9], "born": 1, "borrow_t": 11, "both": [0, 1, 2, 3, 8, 13], "boundari": 1, "bpl": [0, 1, 3], "bpl1": 3, "bpl2": 3, "bpl2_str": 3, "bpl3": 3, "bpl_clean": 3, "bpl_orig": 3, "bpl_root": 0, "bpl_str": 3, "bplmatch": 3, "broken": 7, "btwn": 1, "bucket": [3, 8], "built": 6, "builtin": 1, "byrdifcat": 3, "byrdiff": [1, 3, 13], "c": [1, 9], "c201": 3, "calcul": 1, "call": [0, 9], "can": [0, 1, 2, 3, 4, 6, 7, 8, 9, 11, 13], "cannot": 3, "care": 2, "cartesian": 1, "case": [0, 1, 2, 3, 4, 7], "cast": 1, "categor": [1, 3, 9, 10], "categori": [0, 9], "caus": 9, "caution": [1, 10], "censu": [0, 8, 13], "census": 7, "chang": [0, 1, 3, 6, 11, 13], "charact": 0, "characterist": [7, 8], "check": [1, 11], "check_val_expr": 1, "checkpoint": 4, "child": [0, 9], "children": 1, "chines": 0, "choic": 11, "chosen": 8, "chosen_model": [3, 9, 13], "circl": 0, "circumst": 1, "class": [9, 11], "classif": [8, 9], "classifi": 9, "claus": [0, 1], "clean": [0, 7], "clean_birthyr": [0, 3, 4], "clone": 6, "code": [0, 1, 3, 6], "coeffici": [3, 8], "col": [0, 1], "col_to_add": 3, "col_to_join_on": 3, "col_typ": 3, "column": [1, 4, 5, 8, 10, 11, 12, 13], "column_map": [0, 3, 8], "column_nam": [0, 1, 3, 12], "column_to_append": 0, "combin": [1, 2, 3, 4, 8], "come": 1, "command": [3, 7, 11, 13], "comment": 4, "common": [7, 8, 12, 13], "comp": 1, "comp_a": [1, 2, 3], "comp_b": [1, 2, 3], "comp_c": 1, "comp_d": 1, "compar": [0, 1, 3, 7, 8], "comparis": 3, "comparison": [5, 8], "comparison_featur": [1, 2, 3, 8], "comparison_typ": [1, 2, 3], "complet": 11, "complex": [3, 4], "comput": [1, 4, 8], "concat": 0, "concaten": [0, 1], "condens": 0, "condense_strip_whitespac": 3, "condit": [0, 1, 2, 3, 4, 5, 8], "conf": [11, 13], "config": [1, 4, 5, 8, 11, 13], "configur": [0, 1, 2, 7, 9, 11, 13], "conjuct": 3, "conjunct": 3, "connect": [2, 3], "consid": [1, 2, 9], "consider": 1, "consol": 11, "constraint": [1, 2], "construct": 8, "contain": [0, 1, 3, 12], "context": 10, "continu": [9, 10, 13], "conveni": 11, "convert": [0, 1, 3], "convert_ints_to_long": 3, "copi": [4, 13], "core": [1, 8, 11, 13], "correspond": [7, 8], "could": [0, 2, 3], "count": [1, 11, 13], "counterpart": 9, "counti": [0, 1], "county_1900_1910_distances_km": 1, "county_a": 1, "county_b": 1, "county_dist": [1, 3, 13], "county_distance_lookup": 1, "county_distance_squar": [1, 3, 13], "county_state_dist": 1, "court": 0, "cover": 10, "coverag": [], "cpu": 11, "creat": [0, 3, 7, 8, 10, 11, 12, 13], "creation": 3, "crosswalk": 8, "csv": [1, 3, 8, 11, 12, 13], "current": [1, 2, 3, 9, 11], "d": 1, "d425": 3, "data": [0, 1, 5, 7, 8, 11], "databas": 11, "datafram": [8, 11, 13], "dataset": [0, 1, 3, 4, 7, 8, 11, 13], "datasourc": [1, 3, 11], "datasource_a": [3, 8], "datasource_b": [3, 8], "de": 9, "decis": [3, 5, 9, 13], "decisiontreeclassifi": 9, "default": [0, 1, 2, 3, 8, 9, 11], "defin": [1, 3, 5, 8, 10, 11], "definit": [3, 8], "demograph": 8, "depend": [1, 2, 3, 6, 9, 13], "dependent_var": [3, 13], "deprec": 3, "depth": 9, "deriv": 13, "derived_from": 3, "desc": 11, "describ": [0, 1, 2, 3, 11], "descript": [3, 11], "detail": [0, 3, 11], "detect": 9, "determin": [1, 8], "determinist": [7, 8], "dev": 6, "develop": [6, 7], "df": [3, 11], "dictionari": 11, "diff": 1, "differ": [0, 1, 3, 5, 7, 8], "digit": 0, "dir": 12, "directli": [2, 9], "directori": [6, 11, 13], "disabl": 9, "discard": 9, "discret": 9, "discuss": 3, "dist": 1, "dist_tabl": 1, "distanc": [1, 9], "distance_col": 1, "distance_km": 1, "distances_fil": 1, "distinct": 1, "divid": 0, "divide_by_int": 3, "do": [0, 1, 2, 4, 9, 11, 13], "doc": [9, 10], "document": [1, 3, 9, 11, 13], "doe": [1, 4, 8, 9, 13], "don": [3, 4], "doubl": 10, "down": [0, 7, 13], "drastic": 8, "drop": [0, 3, 11], "drop_al": 11, "drop_all_prc": 11, "drop_all_temp": 11, "drop_data_from_scored_match": 3, "drop_duplicate_a": 3, "drop_duplicate_with_threshold_ratio": [3, 9, 13], "duplic": [3, 9], "durat": 1, "dure": [1, 2, 3, 8], "durmarr": [1, 3], "e": 6, "each": [0, 1, 2, 3, 4, 6, 7, 8, 9, 10, 11], "easiest": [6, 11], "easili": 11, "edit": 6, "effect": [2, 4], "either": [0, 1, 2, 3, 7, 12], "either_0": 1, "either_1": 1, "element": 0, "elig": 8, "els": [1, 3, 4], "else_v": 1, "else_valu": 0, "empti": 1, "enabl": [3, 8, 9, 11], "encod": [3, 4], "encount": 9, "end": [0, 1, 3, 4, 12], "enorm": 9, "ensur": 3, "enter": 11, "entir": [0, 3], "enum_dist": 1, "enumer": 11, "equal": [2, 3, 12], "equal_and_not_null_templ": 1, "equival": 3, "error": [3, 9, 10], "especi": 3, "eta": 9, "etc": 13, "eval": [], "evalu": [1, 3, 7, 8, 9], "even": 1, "eventu": 3, "everi": [1, 4], "ex": 1, "exact": [1, 3], "exact_mult": [3, 13], "exampl": [0, 1, 2, 3, 5, 9], "except": [3, 10], "exclud": 1, "excute_command": 11, "execut": 11, "execute_command": 11, "execute_task": 11, "executor": 11, "executor_memori": [11, 13], "exist": [1, 3, 11], "exit": 11, "expand": 3, "expand_length": 3, "expect": 1, "experi": 7, "experiment": [8, 11], "explicit": 3, "explicitli": [1, 10], "explod": [2, 3, 8], "exploded_df_a": 11, "exploded_df_b": 11, "explor": [3, 5, 7, 11], "expon": 4, "exponenti": 1, "export": [5, 8, 11], "express": [0, 1, 3], "extend": 1, "extens": 8, "extra": [1, 9], "extract": 3, "f": [1, 11], "f1": 1, "f1_match": 3, "f2": 1, "f2_match": 3, "f_caution": [3, 13], "f_interacted_jw_f": [3, 13], "f_pre": [3, 13], "factori": 11, "fail": 3, "fallback": 1, "fals": [1, 3, 4, 7, 11, 13], "famili": 9, "father_namefrst": 1, "favor": 1, "fbpl": 1, "fbpl_nomatch": 1, "fbplmatch": [3, 13], "featur": [2, 5, 7, 8, 9, 11], "feature_import": [3, 8, 13], "feature_nam": [2, 3], "feature_select": [2, 3, 4, 8], "featuresubsetstrategi": 9, "fed": [3, 8], "femal": [3, 12], "fetch": 1, "fetch_a": 3, "few": [4, 9], "fewer": [1, 9], "fi": 1, "file": [1, 4, 5, 7, 8, 11, 12, 13], "filepath": 11, "fill": 1, "filter": [1, 2, 5, 8, 12], "final": [1, 3, 13], "find": [1, 8, 13], "finish": 11, "first": [0, 1, 3, 6, 8, 11, 12], "first_init_col": 1, "first_nam": 0, "five": 11, "fix": 8, "flag": [1, 2, 3, 10, 11, 13], "flexibl": [1, 2, 3], "float": [1, 3, 9], "floor": 0, "focus": [2, 8], "follow": [0, 1, 2, 7, 11, 12, 13], "force_row_wis": 9, "foreign": 1, "forest": [5, 9], "form": [1, 3, 8, 12], "format": 0, "four": 1, "framework": 13, "from": [0, 1, 3, 5, 7, 8, 10, 11, 13], "from_icpsrctyi": 1, "from_statefip": 1, "fsoundex": [3, 13], "full": [3, 8, 9, 13], "full_count_1870_1880": 11, "full_count_1900_1910": 13, "fullcount_1870_1880": 11, "function": [0, 1, 3, 7, 11], "further": [7, 13], "gamma": 9, "gbtclassifi": 9, "gen": 1, "gener": [0, 1, 5, 7, 8, 11], "generalizedlinearregress": 9, "geo": 1, "geograph": 1, "get": [0, 1, 2, 3, 11], "get_floor": 3, "get_set": 11, "get_step": 11, "get_tabl": 11, "get_task": 11, "github": 6, "give": [0, 3], "given": [0, 1, 2, 3, 4, 13], "go": [3, 11], "good": 1, "gradient": [5, 9], "greater": [1, 2, 6], "greatest": 1, "grid": [3, 13], "group": [3, 8], "gt": 1, "h": 11, "ha": [0, 1, 2, 3, 4, 7, 9, 11, 13], "handl": 11, "harmon": 0, "have": [0, 1, 2, 3, 4, 6, 7, 8, 9, 11, 13], "haven": 3, "head": 0, "header": [3, 10, 12], "help": [8, 9, 11], "here": [2, 3, 8, 9, 11, 13], "hh": [1, 2], "hh_blocked_match": 11, "hh_col": 3, "hh_comparison": [2, 3, 8], "hh_match": [3, 11], "hh_model_eval_repeat_fn": 11, "hh_model_eval_repeat_fp": 11, "hh_model_eval_training_data": 11, "hh_model_eval_training_featur": 11, "hh_model_eval_training_result": 11, "hh_model_eval_training_vector": 11, "hh_model_explor": 11, "hh_potential_match": [2, 11], "hh_potential_matchs_prep": 11, "hh_predicted_match": 11, "hh_repeat_fn": [], "hh_repeat_fp": [], "hh_scored_potential_match": 11, "hh_train": [1, 3, 8, 11, 13], "hh_training_data": 11, "hh_training_data_1900_1910": 3, "hh_training_featur": [11, 13], "hh_training_result": 13, "hidden": 11, "hierarch": [7, 11], "hierarchi": 11, "high": [9, 11], "highest": [1, 3, 9], "highli": [7, 8], "histid": [1, 3, 13], "histid_col": 1, "hit": [3, 11, 13], "hits2": [3, 13], "hlink": [0, 1, 2, 3, 4, 6, 7, 8, 9, 13], "hold": 10, "hot": 3, "household": [0, 2, 5, 7, 9, 11, 13], "how": [1, 3, 8], "howev": [4, 7, 13], "hundr": 0, "hyper": [7, 13], "hyperparamet": 13, "hyphen": 0, "i": [0, 1, 2, 3, 4, 6, 7, 8, 9, 11, 12, 13], "id": [1, 3], "id_column": [1, 3], "ident": 13, "identifi": [3, 7, 13], "if_valu": 0, "ignor": 7, "ii": [0, 3], "iii": [0, 3], "imm": [1, 3, 13], "imm_interacted_bplmatch": 3, "imm_interacted_immyear_caut": [3, 13], "immigr": 1, "immyear_caut": [3, 10], "immyear_diff": [1, 3, 10, 13], "implement": [9, 13], "implicitli": 2, "import": [3, 8, 11], "improv": 8, "includ": [1, 3, 8, 9, 10, 11], "incompar": 1, "increas": 10, "independ": [0, 3], "independent_var": [1, 3, 13], "index": [0, 6], "indic": [1, 13], "individu": [1, 3, 8, 13], "inf": 10, "inform": [0, 1, 3, 11], "ingest": 8, "initi": [0, 1, 11], "input": [0, 1, 3, 4, 7, 8, 11, 12], "input_col": 4, "input_column": [3, 4, 10], "input_table_nam": 11, "inspect": 8, "instal": [5, 9], "instanc": [0, 9], "instead": [1, 3, 4, 6, 8], "instruct": [6, 11], "int": [0, 1, 3, 4, 9], "integ": [0, 1, 3, 10], "integr": [6, 9], "interact": [3, 5, 8, 13], "interfac": 11, "intermedi": 11, "introduct": 5, "introspect": 8, "invalid": [1, 9], "ipum": [0, 7], "ipython": 11, "isn": 13, "istemporari": 11, "item": 0, "iter": 3, "its": [0, 1, 7, 9, 11], "itself": [1, 2], "iv": 3, "jaro": [1, 10], "jaro_winkl": 3, "java": 6, "job": 11, "join": [1, 3, 12], "join_column": [3, 12], "join_valu": [3, 12], "jr": [0, 3], "json": [3, 11], "just": [1, 3, 11, 13], "jw": 1, "jw_col_templ": 1, "jw_f": [1, 3, 13], "jw_m": [3, 10, 13], "jw_max_a": 3, "jw_max_b": 3, "jw_sp": [3, 13], "jw_street": 1, "jw_threshold": 1, "kei": [1, 8, 11], "key_count": 1, "kind": 1, "know": 3, "known": 0, "label": 9, "languag": 7, "larger": 9, "last": [0, 1, 8, 10], "latest": 6, "launch": [11, 13], "law": 0, "lead": 0, "learn": [1, 2, 3, 7, 8, 9, 11, 13], "learningr": 9, "least": [0, 1, 9], "leav": 0, "left": 9, "length": [1, 3, 10], "less": [1, 3], "let": 11, "letter": 0, "level": [1, 5, 11], "leverag": 3, "libomp": 9, "librari": [5, 7, 9], "lightgbm": 5, "lightgbmclassifi": 9, "like": [0, 2, 3, 8, 11, 12], "limit": 3, "line": [7, 11], "link": [0, 1, 3, 5, 7, 9], "link_run": 11, "linkrun": [7, 11], "list": [0, 1, 3, 4, 9, 11, 12], "liter": 3, "ll": 11, "load": 11, "load_conf_fil": 11, "load_config": 11, "loc_a": 1, "loc_a_0": 1, "loc_a_1": 1, "loc_b": 1, "loc_b_0": 1, "loc_b_1": 1, "locat": [1, 3, 11], "log2": 9, "logic": [0, 2, 3], "logist": [5, 9], "logistic_regress": [3, 13], "logisticregress": 9, "long": [3, 12], "longest": 8, "look": [1, 2, 11, 12], "lookup": 1, "lower": [0, 1], "lowercas": 0, "lowercase_strip": 3, "lowest": 0, "lr": 11, "lsoundex": [3, 13], "m": [0, 1], "m_caution": [1, 3, 10, 13], "m_interacted_jw_m": [3, 10, 13], "m_namefrst": 1, "m_pre": [3, 10, 13], "machin": [1, 2, 3, 7, 8, 9, 11, 13], "made": 6, "mai": [0, 2, 3, 7, 8, 9, 11, 12], "main": 11, "mainli": 1, "major": [1, 11], "make": [0, 1, 2, 3, 6, 13], "male": [3, 12], "mani": [2, 8, 9, 11], "manual": 13, "map": [5, 8, 10], "mardurmatch": [1, 3], "mark": 2, "marriag": 1, "match": [0, 1, 2, 5, 7, 9, 11, 12, 13], "matches_df": 11, "matrix": 13, "max": [1, 9, 11], "max_depth": 9, "maxbin": 9, "maxdepth": [3, 9, 13], "maximum": [1, 9], "maximum_jw": 1, "mbpl": 1, "mbplmatch": [3, 13], "mean": [0, 2, 3], "meant": 3, "meet": 1, "member": [1, 8], "memori": 11, "men": 3, "messag": 11, "metadata": 8, "method": [11, 13], "mfbplmatch": 1, "mi": [3, 13], "mi0": 1, "mi1": 1, "mid_init_col": 1, "mid_init_match": 1, "middl": [0, 1], "might": 13, "minimum": [1, 9], "mininstancespernod": 9, "minu": [1, 3], "mismatch": 1, "miss": [1, 11], "ml": [3, 9, 10], "mode": [5, 6, 13], "model": [5, 7, 11], "model_eval_repeat_fn": 11, "model_eval_repeat_fp": 11, "model_eval_training_data": 11, "model_eval_training_featur": 11, "model_eval_training_result": 11, "model_eval_training_vector": 11, "model_explor": [3, 9, 11, 13], "model_paramet": [3, 8, 13], "model_parameter_search": [3, 13], "modifi": 3, "modul": 11, "moment": 8, "momloc": 1, "more": [0, 1, 2, 3, 9, 10, 11, 13], "most": [0, 1, 8, 11], "mother": 10, "mother_birthyr": 1, "mpre": 1, "mr": 0, "much": [1, 8], "mult": 1, "multi": 1, "multipl": [0, 1, 5, 9, 11], "multipli": 1, "must": [0, 1, 2, 3, 4, 9, 10, 12], "my": [11, 13], "my_conf": 11, "my_fil": 3, "myriad": 3, "n": [1, 9, 10], "n_training_iter": [3, 8, 13], "name": [0, 1, 3, 4, 9, 11, 12], "name_col": 1, "name_std": [3, 12], "namefrst": [0, 1, 3], "namefrst_clean": [0, 3], "namefrst_init": 1, "namefrst_jw": [1, 2, 3, 13], "namefrst_mid_init": [0, 1], "namefrst_mid_init_2": 1, "namefrst_rel": 1, "namefrst_related_row": 1, "namefrst_split": [0, 3], "namefrst_std": [3, 12], "namefrst_std_jw": [3, 13], "namefrst_unstd": [1, 3], "namefrst_unstd_bigram": 4, "namelast": [1, 3], "namelast1": 1, "namelast2": 1, "namelast3": 1, "namelast_bigram": 3, "namelast_clean": [1, 3, 4], "namelast_clean_bigram": [3, 4], "namelast_clean_soundex": 4, "namelast_equal_as_int": 1, "namelast_frst_bigram": 4, "namelast_jw": [2, 3, 13], "namelast_jw_max": 1, "namelast_neighbor": 1, "namelast_popular": 1, "namelast_popularity_sum": 1, "nativ": 1, "nbor": [1, 3, 13], "ncount": [3, 4, 13], "ncount2": [3, 4, 13], "nearest": 0, "necessari": [4, 13], "need": [0, 1, 2, 3, 8, 9, 11, 13], "neg": 7, "neighbor": 1, "neighborhood": 1, "neither": 1, "nest": [2, 3, 7], "new": [0, 3, 13], "new_marr": [1, 3], "newli": 3, "niu": 1, "no_first_pad": 4, "node": 9, "non": 0, "nonzero": 1, "nor": 1, "normal": [8, 9], "note": [2, 3], "now": [2, 11], "null": [1, 3, 4], "null_fil": 3, "num": 11, "num_col": 1, "number": [0, 1, 3, 4, 8, 9, 11], "numer": [0, 1], "numtre": [3, 9, 13], "nvl": 1, "object": [1, 3, 7, 11], "often": [2, 4, 11], "onc": [1, 11], "one": [0, 1, 3, 8], "onethird": 9, "onli": [0, 1, 2, 3, 8, 9, 13], "ons": 5, "oper": [0, 1, 2, 3, 9], "option": [0, 1, 3, 4, 7, 8, 9, 11, 13], "or_group": 3, "order": [0, 3, 8], "org": 6, "organ": 11, "original_valu": 3, "oth": [3, 13], "other": [1, 3, 9, 13], "otherwis": [0, 1, 10, 13], "our": 11, "out": [3, 4, 8, 13], "output": [0, 1, 2, 3, 4, 7, 8, 11, 13], "output_col": 4, "output_column": [3, 4, 10], "output_suspicious_td": [], "output_table_nam": 11, "output_typ": 3, "outsid": 10, "overrid": [0, 3], "override_column_a": [0, 3, 4], "override_column_b": [0, 3, 4], "override_transform": [0, 3], "overview": 5, "own": [1, 3], "p": 3, "packag": [6, 9], "page": [1, 2, 3, 11], "pair": [1, 2, 3, 13], "param": 13, "param_grid": 3, "paramet": [7, 8, 9, 11, 13], "parent": [0, 1, 12], "parent_step_chang": 1, "parenthes": 3, "parquet": [3, 8], "part": [3, 8], "particular": [1, 2, 3], "particularli": 1, "partit": 13, "pass": [1, 8, 9], "passthrougharg": 9, "path": [1, 3, 11, 12, 13], "pattern": 11, "peopl": [0, 1, 7, 11], "per": [1, 9, 10, 11], "percent": 8, "percentag": 1, "perform": [1, 3, 7, 8, 9, 12], "persist": 11, "person": [0, 1, 7], "pip": [6, 9], "pipelin": 5, "pipeline_featur": [3, 8, 10], "piplin": 3, "placehold": 1, "pleas": [3, 9, 11], "plu": 3, "point": [10, 13], "popul": 8, "posit": [0, 1, 7], "possibl": 3, "post": [3, 8], "potenti": [1, 2, 5, 8, 9], "potential_match": [1, 2, 8, 11], "potential_matches_prep": 11, "potential_matches_univers": [3, 8], "power": 5, "predefin": 1, "predict": [3, 13], "predicted_match": 11, "prediction_col": 3, "preexist": 11, "prefer": 13, "prefix": 0, "prep": 3, "prep_step": 11, "prepar": [7, 8, 11], "prepend": 4, "prepped_df_a": 11, "prepped_df_b": 11, "preprocess": [5, 7, 11, 13], "present": [1, 3, 10], "pretti": 2, "primari": [1, 7], "primarili": [1, 8], "print": 11, "probabilist": [3, 7], "probabl": [0, 3, 9], "probit": [3, 5], "proceed": 12, "process": [2, 3, 7, 11], "produc": [0, 11], "product": [1, 7, 13], "program": [1, 3, 8, 13], "project": 6, "prompt": 11, "provid": [0, 3, 4, 7, 8, 9, 10, 11], "pull": 8, "punctuat": 0, "put": [11, 13], "py": [1, 3], "pypi": 5, "pyspark": [6, 9, 10, 11], "python": [6, 7, 9, 11], "q": [11, 13], "qmark": 0, "qualifi": 3, "queri": [1, 3], "race": [0, 1, 3, 10, 13], "race_interacted_srac": [3, 10, 13], "racematch": 3, "rais": [1, 4, 9], "random": [5, 9], "random_forest": [3, 13], "randomforestclassifi": 9, "rang": [3, 10], "rate": 1, "ratio": [3, 9], "ration": 0, "rationalize_name_word": 3, "raw": [0, 3, 8, 11], "raw_df_a": 11, "raw_df_b": 11, "read": [0, 1, 3, 8, 11], "readm": 3, "real": 7, "reason": 1, "recod": 0, "record": [0, 1, 2, 3, 7, 8, 9], "recurs": [2, 3], "reduc": [4, 8], "refer": 3, "regex": 5, "regex_word_replac": 12, "region": [3, 13], "region_dict": 3, "regionf": 3, "regist": [8, 11], "regress": [5, 9], "regular": [], "rel": [1, 3, 13], "relat": [0, 1, 3], "relate_a": [3, 10], "relate_col": 1, "relate_div_100": [0, 1, 3], "related_individual_max_jw": 1, "related_individual_row": 1, "relatematch": [1, 3], "relatetyp": [3, 10], "relatetype_interacted_relatematch": 3, "relationship": 7, "relev": 13, "reload": 11, "remain": 8, "remov": [0, 3], "remove_alternate_nam": 3, "remove_qmark_hyphen": 3, "remove_suffix": 3, "repeat_fn": [], "repeat_fp": [], "repeatedli": [], "replac": [0, 1, 2, 3, 5], "replace_apostroph": 3, "replaced_birthyr": [1, 3, 4], "report": [1, 5, 7, 11], "repositori": 6, "repres": [0, 1, 3, 10, 11], "represent": 8, "reproduc": 11, "request": 8, "requir": [0, 1, 2, 3, 4, 5, 8, 9, 10, 11, 12], "research": 7, "reshap": 8, "resourc": 4, "respect": [1, 8], "restrict": 2, "result": [0, 1, 7, 10, 11, 13], "return": [1, 4, 11], "reus": 5, "right": [9, 11], "risk": 1, "road": 0, "robust": 3, "root": 6, "round": [0, 3], "row": [0, 3, 4], "rule": [2, 7, 8], "run": [5, 6, 7, 8, 13], "run_all_step": [3, 11, 13], "run_step": 11, "runtim": 8, "sai": 11, "same": [0, 1, 2, 3, 4, 7, 8, 11], "sampl": 1, "satisfi": [2, 3, 8], "save": [3, 8, 13], "scala": [1, 9], "scale": 3, "scale_data": [3, 13], "scenario": 13, "schema": 3, "score": [1, 3, 8, 9, 10], "score_with_model": [3, 13], "scored_potential_match": 11, "scratch": 3, "script": [3, 7, 11], "search": 1, "second": [0, 1, 3, 9, 12], "secondari": 1, "secondary_distance_col": 1, "secondary_distances_fil": 1, "secondary_key_count": 1, "secondary_loc_a": 1, "secondary_loc_b": 1, "secondary_source_column": 1, "secondary_table_nam": 1, "section": [0, 1, 2, 3, 9, 13], "see": [1, 3, 6, 9, 11, 13], "seen": 1, "select": [0, 1, 5, 7, 11, 13], "send": 9, "separ": 8, "sequenc": 7, "seri": 11, "serialp": 3, "serv": 1, "set": [0, 1, 2, 3, 4, 7, 8, 9, 11, 13], "set_executor_memori": 11, "set_link_task": 11, "set_loc": 11, "set_num_cor": 11, "set_preexisting_t": 11, "set_print_sql": 11, "set_value_column_a": [3, 4], "set_value_column_b": [3, 4], "sever": [1, 7], "sex": [1, 3, 12], "sex_equ": 3, "sex_region_interact": 3, "sex_regionf_interact": 3, "sexmatch": 3, "sgen": [1, 3, 13], "share": 7, "short": 3, "should": [1, 3, 4, 9, 10, 11], "show": 11, "showf": 11, "shut": 13, "sibl": 0, "sign": 1, "signific": 0, "similar": [1, 3], "simpli": [0, 3], "simplifi": 1, "sinc": [0, 3, 9], "singl": [0, 4, 11, 13], "size": 1, "skip": [3, 4, 8], "sm_bpl": 1, "sm_namefrst": 1, "sm_sex": 1, "small": 3, "smaller": 7, "smallest": 3, "sn_bpl": 1, "sn_namefrst": 1, "sn_sex": 1, "so": [0, 1, 2, 3, 6, 9, 13], "some": [0, 1, 2, 3, 4, 7, 8, 9, 11], "someth": 11, "sometim": [3, 9], "somewhat": 2, "soundex": 5, "sourc": [1, 5, 8, 11, 13], "source_column_a": 1, "source_column_b": 1, "sp": 1, "sp_caution": [1, 3, 13], "sp_interacted_jw_sp": [3, 13], "sp_pre": [3, 13], "space": [0, 3, 4, 12], "span": 13, "spark": [1, 3, 4, 6, 9, 10, 11, 13], "sparkfactori": 11, "sparksess": 11, "sparkxgbclassifi": 9, "special": [1, 9], "specif": [1, 3, 9, 11], "specifi": [0, 1, 3, 7, 8, 10, 11, 12], "split": [3, 4, 8, 9, 10, 13], "split_by_id_a": [3, 13], "sploc": 1, "spous": 0, "spouse_birthyr": 1, "spouse_bpl": 1, "sql": [0, 1, 2, 3, 4, 5, 8, 11], "sql_condit": 3, "sqrt": 9, "squar": 1, "sr": [0, 3], "srace": [3, 10, 13], "stage": 3, "standard": [0, 1, 12], "start": [0, 12], "state": [1, 7], "state_1900_1910_distances_km": 1, "state_dist": 1, "state_distance_lookup": 1, "statecode1": 1, "statecode2": 1, "statefip": [0, 1, 3], "statefip_h": 3, "step": [0, 1, 3, 7], "stepmom": 1, "still": 12, "stop": [0, 9], "strategi": [3, 13], "street": [0, 1], "street_jw": [1, 3, 13], "street_unstd": 12, "strictli": 10, "string": [0, 1, 3, 4, 8, 9, 11, 12], "strip": [0, 8], "structur": [2, 3, 7], "sub": [1, 2, 3], "subhead": 12, "subset": [3, 12], "substitut": [5, 8], "substitution_column": [3, 8, 12], "substitution_fil": [3, 12], "substitutions_street_abbrev": 12, "subtract": 1, "suffix": 0, "suppli": 12, "support": [0, 2, 3, 8, 9], "suppos": [0, 2, 3], "sure": [2, 3, 6, 11], "surnam": 1, "surround": 0, "suspect": [1, 7], "swap": 12, "synaps": 9, "syntax": 2, "system": [6, 9], "t": [0, 1, 3, 4, 13], "tabl": [1, 2, 3, 5, 8, 11, 13], "table_nam": 1, "tablenam": 11, "tailor": 7, "take": [0, 1, 2, 3, 4, 8, 11], "taken": [0, 1], "task": [2, 3, 5, 7, 9, 13], "task_nam": 11, "tell": [1, 3, 4], "templat": 1, "ten": 1, "term": 3, "test": [3, 8, 13], "text": 11, "than": [0, 1, 2, 3, 9], "thei": [0, 1, 2, 3, 8, 11], "them": [0, 1, 3, 8], "thi": [0, 1, 2, 3, 4, 6, 7, 8, 9, 10, 11, 13], "thing": 3, "those": [1, 3], "though": 1, "thought": 8, "three": [2, 3, 8], "threshold": [2, 3, 9, 13], "threshold_expr": [2, 3], "threshold_ratio": [3, 9, 13], "through": [6, 8, 9, 10, 11], "thu": 1, "time": [0, 3, 8, 9, 11], "to_icpsrctyi": 1, "to_statefip": 1, "togeth": [0, 1, 3], "toml": [3, 7, 11], "tool": [6, 7], "top": [1, 5], "topic": 11, "total": 8, "train": [1, 5, 7, 9, 11], "training_data": [3, 11], "training_data_1900_1910": 13, "training_data_1900_1910_hlink_featur": 13, "training_data_subset": 3, "training_featur": [11, 13], "training_result": 13, "transform": [1, 3, 5, 7, 8], "transformer_typ": [3, 10], "treat": [3, 10], "tree": [5, 9], "true": [1, 3, 4, 8, 9, 10, 12, 13], "try": [3, 9], "tune": [7, 13], "tutori": [3, 11], "two": [0, 1, 2, 3, 4, 7, 8, 10, 11, 13], "type": [0, 3, 4, 5, 8, 9, 11, 12, 13], "typic": [3, 8], "u": 0, "ugli": 2, "under": [1, 3], "underli": 9, "understand": 7, "union": 5, "uniqu": 3, "unit": 7, "univers": [1, 5, 8], "unknown": 1, "unlik": 2, "unrel": 1, "unstabl": [9, 11], "up": [1, 3, 11, 12], "updat": 13, "upper": 1, "upper_threshold": 3, "uppercas": 0, "us": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 12, 13], "us1900": 3, "us1900m_usa": 3, "us1910": 3, "us1910m_usa": 3, "usag": [3, 4, 5, 11], "use_potential_matches_featur": 13, "use_training_data_featur": [3, 8, 13], "user": [1, 11], "usual": [0, 8, 9, 13], "util": 4, "v": 3, "valu": [0, 1, 2, 3, 4, 9, 10, 11, 12], "var": [1, 3], "vari": [0, 3, 4], "variabl": [0, 1, 3, 13], "variant": 12, "varieti": 8, "variou": 9, "ve": 13, "vector": [3, 10], "verbos": 2, "veri": [4, 8], "version": [0, 3, 6, 9, 13], "vi": 3, "via": [6, 7, 9], "view": 9, "vii": 3, "viii": 3, "volumn": 1, "wa": [1, 13], "wai": [1, 2, 3, 6, 11], "want": [0, 1, 3, 11, 13], "washington": 3, "we": [0, 1, 9, 11, 13], "well": 3, "were": 3, "weren": 13, "what": [1, 3, 11, 13], "when": [0, 1, 2, 3, 4, 8, 9, 13], "where": [1, 8, 11, 13], "whether": [1, 3, 12], "which": [0, 1, 2, 3, 4, 7, 8, 9, 10, 11, 12, 13], "white": 0, "whitespac": [0, 8], "who": 1, "whole": [0, 7], "whose": [1, 9], "width": 8, "winkler": [1, 10], "within": [1, 3, 7, 11, 12], "without": 9, "word": [0, 5], "work": [0, 1, 3, 6, 8, 11, 13], "workflow": [4, 5], "world": 7, "would": [1, 2, 3, 13], "write": [1, 11, 13], "written": [3, 7], "x": [3, 10, 11], "x_crosswalk": 11, "x_hh_tfam": 11, "x_hh_tfam_2a": 11, "x_hh_tfam_2b": 11, "x_load": 11, "x_parquet_from_csv": 11, "x_persist": 11, "x_sql": 11, "x_sqlf": 11, "x_summari": 11, "x_tab": 11, "x_tfam": 11, "x_tfam_raw": 11, "x_union": 11, "xgboost": 5, "y": 10, "year": [0, 1, 3, 4, 5], "year_b": 1, "yet": 11, "you": [0, 1, 2, 3, 6, 9, 11, 12, 13], "your": [2, 3, 4, 6, 8, 9, 11, 13], "yrimmig": 1, "zero": 1}, "titles": ["Column Mappings", "Comparison Features", "Comparisons", "Configuration", "Feature Selection Transforms", "Welcome to hlink\u2019s documentation!", "Installation", "Introduction", "Link Tasks", "Models", "Pipeline generated features", "Running hlink", "Substitutions", "Advanced Workflow Examples"], "titleterms": {"": 5, "1": 12, "abs_diff": 1, "add": 1, "add_to_a": 0, "advanc": [0, 3, 13], "after": 13, "aggreg": 1, "alia": 1, "all_equ": 1, "an": 13, "any_equ": 1, "api": 5, "arrai": 4, "array_index": 0, "b_minus_a": 1, "basic": [0, 3], "bigram": 4, "block": 3, "btwn_threshold": 1, "bucket": 10, "caution_comp_3": 1, "caution_comp_3_012": 1, "caution_comp_4": 1, "caution_comp_4_012": 1, "column": [0, 3], "comparison": [1, 2, 3], "concat_to_a": 0, "concat_to_b": 0, "concat_two_col": 0, "condense_strip_whitespac": 0, "config": 3, "configur": [3, 5, 8], "data": [3, 12, 13], "decision_tre": 9, "defin": 2, "differ": 13, "divide_by_int": 0, "document": 5, "either_are_0": 1, "either_are_1": 1, "equal": 1, "equals_as_int": 1, "exact_mult": 1, "exampl": [11, 13], "explor": [8, 13], "export": 13, "extra_children": 1, "f1_match": 1, "f2_match": 1, "fals": [], "featur": [1, 3, 4, 10, 13], "fetch_a": 1, "fetch_b": 1, "file": 3, "filter": 3, "fn": [], "fp": [], "from": 6, "gener": [3, 10, 13], "geo_dist": 1, "get_floor": 0, "gradient_boosted_tre": 9, "gt_threshold": 1, "hit": 1, "hits2": 1, "hlink": [5, 11], "household": [1, 3, 8], "instal": 6, "interact": [10, 11], "introduct": 7, "jaro_winkl": 1, "jaro_winkler_r": 1, "jaro_winkler_street": 1, "jw_max_a": 1, "jw_max_b": 1, "length_b": 1, "level": 3, "librari": 11, "lightgbm": 9, "link": [8, 11, 13], "list": [], "logistic_regress": 9, "look_at_addl_var": 1, "lower_threshold": 1, "lowercase_strip": 0, "map": [0, 3], "match": [3, 8], "max_jaro_winkl": 1, "maximum_jaro_winkl": 1, "ml": 13, "mode": 11, "model": [3, 8, 9, 13], "multi_jaro_winkler_search": 1, "multipl": [2, 3], "neg": [], "neither_are_nul": 1, "not_equ": 1, "not_zero_and_not_equ": 1, "ons": 1, "overview": [2, 7, 8], "pipelin": [3, 10], "posit": [], "potenti": 3, "power": [1, 4], "preprocess": 8, "present_and_equal_categorical_in_univers": 1, "present_and_matching_categor": 1, "present_and_not_equ": 1, "present_both_year": 1, "probit": 9, "program": 11, "pypi": 6, "random_forest": 9, "rationalize_name_word": 0, "regex": 12, "rel_jaro_winkl": 1, "relat": 8, "remove_alternate_nam": 0, "remove_one_letter_nam": 0, "remove_prefix": 0, "remove_punctu": 0, "remove_qmark_hyphen": 0, "remove_stop_word": 0, "remove_suffix": 0, "replac": 12, "replace_apostroph": 0, "report": 8, "requir": 6, "reus": 13, "run": 11, "second_gen_imm": 1, "section": 8, "select": [3, 4], "singl": 3, "soundex": 4, "sourc": [3, 6], "split": 0, "sql_condit": [1, 4], "start": 11, "step": [8, 11], "substitut": [3, 12], "substr": 0, "sum": 1, "tabl": 12, "task": [8, 11], "threshold": 1, "time": 1, "top": 3, "train": [3, 8, 13], "transform": [0, 4, 10], "type": [1, 2, 10], "union": 4, "univers": 3, "upper_threshold": 1, "us": 11, "usag": 0, "welcom": 5, "when_valu": 0, "word": 12, "workflow": [11, 13], "xgboost": 9, "year": 13}})
\ No newline at end of file
diff --git a/docs/substitutions.html b/docs/substitutions.html
index e5bc008..7f8c365 100644
--- a/docs/substitutions.html
+++ b/docs/substitutions.html
@@ -5,11 +5,11 @@
- Substitutions — hlink 3.8.0 documentation
+ Substitutions — hlink 4.0.0a1 documentation
-
+
diff --git a/docs/use_examples.html b/docs/use_examples.html
index e2419ae..9c5797d 100644
--- a/docs/use_examples.html
+++ b/docs/use_examples.html
@@ -5,11 +5,11 @@
- Advanced Workflow Examples — hlink 3.8.0 documentation
+ Advanced Workflow Examples — hlink 4.0.0a1 documentation
-
+
@@ -114,7 +114,7 @@ An Example Model Exploration Workflowscore_with_model = true
feature_importances = false
decision = "drop_duplicate_with_threshold_ratio"
-param_grid = true
+model_parameter_search = {strategy = "grid"}
n_training_iterations = 10
model_parameters = [
{ type = "logistic_regression", threshold = [0.5], threshold_ratio = [1.0, 1.1]},
diff --git a/sphinx-docs/config.md b/sphinx-docs/config.md
index b5ec9f7..21562ee 100644
--- a/sphinx-docs/config.md
+++ b/sphinx-docs/config.md
@@ -334,7 +334,7 @@ split_by_id_a = true
decision = "drop_duplicate_with_threshold_ratio"
n_training_iterations = 2
-param_grid = true
+model_parameter_search = {strategy = "grid"}
model_parameters = [
{ type = "random_forest", maxDepth = [7], numTrees = [100], threshold = [0.05, 0.005], threshold_ratio = [1.2, 1.3] },
{ type = "logistic_regression", threshold = [0.50, 0.65, 0.80], threshold_ratio = [1.0, 1.1] }
@@ -360,7 +360,7 @@ split_by_id_a = true
decision = "drop_duplicate_with_threshold_ratio"
n_training_iterations = 10
-param_grid = false
+model_parameter_search = {strategy = "explicit"}
model_parameters = [
{ type = "random_forest", maxDepth = 6, numTrees = 50, threshold = 0.5, threshold_ratio = 1.0 },
{ type = "probit", threshold = 0.5, threshold_ratio = 1.0 }
@@ -743,7 +743,6 @@ splits = [-1,0,6,11,9999]
* `decision` -- Type: `string`. Optional. Specifies which decision function to use to create the final prediction. The first option is `drop_duplicate_a`, which drops any links for which a record in the `a` data set has a predicted match more than one time. The second option is `drop_duplicate_with_threshold_ratio` which only takes links for which the `a` record has the highest probability out of any other potential links, and the second best link for the `a` record is less than the `threshold_ratio`.
* `threshold_ratio` -- Type: `float`. Optional. For use when `decision` is `drop_duplicate_with_threshold_ratio` . Specifies the smallest possible ratio to accept between a best and second best link for a given record. Can be used to specify a threshold ratio (beta threshold) to use for all models. Alternatively, unique threshold ratios can be specified in each individual `chosen_model` and `model_parameters` specification.
* `model_parameters` -- Type: `list`. Specifies models to test out in the `model_exploration` task. See the [models](models) section for more information on model specifications.
- * `param_grid` -- Type: `boolean`. Optional. If you would like to evaluate multiple hyper-parameters for a single model type in your `model_parameters` specification, you can give hyper-parameter inputs as arrays of length >= 1 instead of integers to allow one model per row specification with multiple model eval outputs.
* `score_with_model` -- Type: `boolean`. If set to false, will skip the `apply_model` step of the matching task. Use this if you want to use the `run_all_steps` command and are just trying to generate potential links, such as for the creation of training data.
* `n_training_iterations` -- Type: `integer`. Optional; default value is 10. The number of training iterations to use during the `model_exploration` task.
* `scale_data` -- Type: `boolean`. Optional. Whether to scale the data as part of the machine learning pipeline.
@@ -752,6 +751,25 @@ splits = [-1,0,6,11,9999]
* `feature_importances` -- Type: `boolean`. Optional. Whether to record
feature importances or coefficients for the training features when training
the ML model. Set this to true to enable training step 3.
+* Deprecated Attributes:
+ * `param_grid` (*Deprecated in version 4.0.0*) -- Type: `boolean`. Optional.
+ `param_grid` has been deprecated and will eventually be removed. Please use
+ the more flexible `model_parameter_search` option by replacing `param_grid
+ = false`
+
+ with
+
+ ```toml
+ model_parameter_search = {strategy = "explicit"}
+ ```
+
+ and replacing `param_grid = true`
+
+ with
+
+ ```toml
+ model_parameter_search = {strategy = "grid"}
+ ```
```
@@ -769,7 +787,7 @@ feature_importances = true
decision = "drop_duplicate_with_threshold_ratio"
n_training_iterations = 10
-param_grid = false
+model_parameter_search = {strategy = "explicit"}
model_parameters = [
{ type = "random_forest", maxDepth = 6, numTrees = 50 },
{ type = "probit", threshold = 0.5}
@@ -805,7 +823,7 @@ score_with_model = true
feature_importances = true
decision = "drop_duplicate_with_threshold_ratio"
-param_grid = true
+model_parameter_search = {strategy = "grid"}
n_training_iterations = 10
model_parameters = [
{ type = "logistic_regression", threshold = [0.5], threshold_ratio = [1.1]},
diff --git a/sphinx-docs/use_examples.md b/sphinx-docs/use_examples.md
index 4d41811..bd1c2be 100644
--- a/sphinx-docs/use_examples.md
+++ b/sphinx-docs/use_examples.md
@@ -88,7 +88,7 @@ However, when this training data set is used for other years, the program does n
score_with_model = true
feature_importances = false
decision = "drop_duplicate_with_threshold_ratio"
- param_grid = true
+ model_parameter_search = {strategy = "grid"}
n_training_iterations = 10
model_parameters = [
{ type = "logistic_regression", threshold = [0.5], threshold_ratio = [1.0, 1.1]},