Skip to content

switch logistic classifier to random forest as default classifier #1031

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
fgregg wants to merge 4 commits into
base: main
Choose a base branch
from
Open

switch logistic classifier to random forest as default classifier #1031

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
6fab426
random forest
fgregg Jun 2, 2022
ff4587c
merge conflict
fgregg Jun 2, 2022
c84a0c8
Merge branch 'main' into rf
fgregg Jun 2, 2022
574aa84
fewer elements in grid search
fgregg Jun 2, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions dedupe/api.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@
import tempfile

import numpy
import sklearn.linear_model
import sklearn.ensemble
import sklearn.model_selection

import dedupe.core as core
Expand Down Expand Up @@ -1091,8 +1091,8 @@ def __init__(
]
]
self.classifier = sklearn.model_selection.GridSearchCV(
estimator=sklearn.linear_model.LogisticRegression(),
param_grid={"C": [0.00001, 0.0001, 0.001, 0.01, 0.1, 1, 10]},
estimator=sklearn.ensemble.RandomForestClassifier(),
param_grid={"n_estimators": [100, 200, 400, 800]},
scoring="f1",
n_jobs=-1,
)
Expand Down
10 changes: 5 additions & 5 deletions dedupe/labeler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
import numpy
from typing import List
from typing_extensions import Protocol
import sklearn.linear_model
import sklearn.ensemble

import dedupe.core as core
import dedupe.training as training
Expand Down Expand Up @@ -38,7 +38,7 @@ class HasDataModel(Protocol):
data_model: datamodel.DataModel


class RLRLearner(sklearn.linear_model.LogisticRegression, ActiveLearner):
class RFLearner(sklearn.ensemble.RandomForestClassifier, ActiveLearner):
def __init__(self, data_model):
super().__init__()
self.data_model = data_model
Expand Down Expand Up @@ -304,7 +304,7 @@ def _sample(self, data_1, data_2, sample_size):

class DisagreementLearner(ActiveLearner):

classifier: RLRLearner
classifier: RFLearner
blocker: BlockLearner
candidates: List[TrainingExample]

Expand Down Expand Up @@ -409,7 +409,7 @@ def __init__(

self.candidates = self.blocker.candidates

self.classifier = RLRLearner(self.data_model)
self.classifier = RFLearner(self.data_model)
self.classifier.candidates = self.candidates

self._common_init()
Expand Down Expand Up @@ -441,7 +441,7 @@ def __init__(
self.blocker = RecordLinkBlockLearner(data_model, data_1, data_2, index_include)
self.candidates = self.blocker.candidates

self.classifier = RLRLearner(self.data_model)
self.classifier = RFLearner(self.data_model)
self.classifier.candidates = self.candidates

self._common_init()
Expand Down
2 changes: 1 addition & 1 deletion tests/test_labeler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@ def setUp(self):
def test_AL(self):
random.seed(1111111111110)
original_N = len(SAMPLE)
active_learner = dedupe.labeler.RLRLearner(self.data_model)
active_learner = dedupe.labeler.RFLearner(self.data_model)
active_learner.candidates = SAMPLE
assert len(active_learner) == original_N

Expand Down