-
-
Save RobinL/c99712c1fb0b6c80593b5028c0be553a to your computer and use it in GitHub Desktop.
Splink 3 vs 4
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import splink.duckdb.comparison_library as cl | |
from splink.datasets import splink_datasets | |
from splink.duckdb.blocking_rule_library import block_on | |
from splink.duckdb.linker import DuckDBLinker | |
df = splink_datasets.historical_50k | |
df = df.head(1000) | |
settings_dict = { | |
"link_type": "dedupe_only", | |
"blocking_rules_to_generate_predictions": [ | |
block_on(["postcode_fake", "first_name"]), | |
block_on(["first_name", "surname"]), | |
block_on(["dob", "substr(postcode_fake,1,2)"]), | |
block_on(["postcode_fake", "substr(dob,1,3)"]), | |
block_on(["postcode_fake", "substr(dob,4,5)"]), | |
], | |
"comparisons": [ | |
cl.exact_match( | |
"first_name", | |
term_frequency_adjustments=True, | |
), | |
cl.jaro_winkler_at_thresholds( | |
"surname", | |
distance_threshold_or_thresholds=[0.9, 0.8], | |
), | |
cl.levenshtein_at_thresholds( | |
"postcode_fake", distance_threshold_or_thresholds=[1, 2] | |
), | |
], | |
} | |
linker = DuckDBLinker(df, settings_dict) | |
linker.estimate_u_using_random_sampling(target_rows=1e6) | |
linker.estimate_parameters_using_expectation_maximisation( | |
block_on(["first_name", "surname"]) | |
) | |
linker.estimate_parameters_using_expectation_maximisation( | |
block_on(["dob", "substr(postcode_fake, 1,3)"]) | |
) | |
df_e = linker.predict() |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import splink.comparison_library as cl | |
from splink import DuckDBAPI, Linker, block_on, splink_datasets | |
df = splink_datasets.historical_50k | |
df = df.head(1000) | |
settings_dict = { | |
"link_type": "dedupe_only", | |
"blocking_rules_to_generate_predictions": [ | |
block_on("postcode_fake", "first_name"), | |
block_on("first_name", "surname"), | |
block_on("dob", "substr(postcode_fake,1,2)"), | |
block_on("postcode_fake", "substr(dob,1,3)"), | |
block_on("postcode_fake", "substr(dob,4,5)"), | |
], | |
"comparisons": [ | |
cl.ExactMatch("first_name").configure( | |
term_frequency_adjustments=True, | |
), | |
cl.JaroWinklerAtThresholds( | |
"surname", | |
score_threshold_or_thresholds=[0.9, 0.8], | |
), | |
cl.LevenshteinAtThresholds( | |
"postcode_fake", distance_threshold_or_thresholds=[1, 2] | |
), | |
], | |
} | |
linker = Linker(df, settings_dict, DuckDBAPI()) | |
linker.estimate_u_using_random_sampling(target_rows=1e6) | |
linker.estimate_parameters_using_expectation_maximisation( | |
block_on("first_name", "surname") | |
) | |
linker.estimate_parameters_using_expectation_maximisation( | |
block_on("dob", "substr(postcode_fake, 1,3)") | |
) | |
df_e = linker.predict() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment