alu/tra-analysis
1
0
Fork 0
mirror of https://github.com/titanscouting/tra-analysis.git synced 2024-12-25 00:59:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix minor bugs in RandomForest.py

Browse Source
This commit is contained in:
Arthur Lu 2022-02-04 08:50:56 +00:00
parent 30a2334d54
commit 237e69b732
1 changed files with 8 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
analysis-master/tra_analysis/RandomForest.py
View File

@ -4,9 +4,12 @@
# this should be imported as a python module using 'from tra_analysis import RandomForest'
# setup:
__version__ = "1.0.2"
__version__ = "1.0.3"
__changelog__ = """changelog:
1.0.3:
- updated RandomForestClassifier and RandomForestRegressor parameters to match sklearn v 1.0.2
- changed default values for kwargs to rely on sklearn
1.0.2:
- optimized imports
1.0.1:
@ -28,19 +31,19 @@ __all__ = [
import sklearn, sklearn.ensemble, sklearn.naive_bayes
from . import ClassificationMetric, RegressionMetric
def random_forest_classifier(data, labels, test_size, n_estimators, criterion="gini", max_depth=None, min_samples_split=2, min_samples_leaf=1, min_weight_fraction_leaf=0.0, max_features="auto", max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, bootstrap=True, oob_score=False, n_jobs=None, random_state=None, verbose=0, warm_start=False, class_weight=None):
def random_forest_classifier(data, labels, test_size, n_estimators, **kwargs):
data_train, data_test, labels_train, labels_test = sklearn.model_selection.train_test_split(data, labels, test_size=test_size, random_state=1)
kernel = sklearn.ensemble.RandomForestClassifier(n_estimators = n_estimators, criterion = criterion, max_depth = max_depth, min_samples_split = min_samples_split, min_samples_leaf = min_samples_leaf, min_weight_fraction_leaf = min_weight_fraction_leaf, max_leaf_nodes = max_leaf_nodes, min_impurity_decrease = min_impurity_decrease, bootstrap = bootstrap, oob_score = oob_score, n_jobs = n_jobs, random_state = random_state, verbose = verbose, warm_start = warm_start, class_weight = class_weight)
kernel = sklearn.ensemble.RandomForestClassifier(n_estimators = n_estimators, **kwargs)
kernel.fit(data_train, labels_train)
predictions = kernel.predict(data_test)
return kernel, ClassificationMetric(predictions, labels_test)
def random_forest_regressor(data, outputs, test_size, n_estimators, criterion="mse", max_depth=None, min_samples_split=2, min_samples_leaf=1, min_weight_fraction_leaf=0.0, max_features="auto", max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, bootstrap=True, oob_score=False, n_jobs=None, random_state=None, verbose=0, warm_start=False):
def random_forest_regressor(data, outputs, test_size, n_estimators, **kwargs):
data_train, data_test, outputs_train, outputs_test = sklearn.model_selection.train_test_split(data, outputs, test_size=test_size, random_state=1)
kernel = sklearn.ensemble.RandomForestRegressor(n_estimators = n_estimators, criterion = criterion, max_depth = max_depth, min_samples_split = min_samples_split, min_weight_fraction_leaf = min_weight_fraction_leaf, max_features = max_features, max_leaf_nodes = max_leaf_nodes, min_impurity_decrease = min_impurity_decrease, min_impurity_split = min_impurity_split, bootstrap = bootstrap, oob_score = oob_score, n_jobs = n_jobs, random_state = random_state, verbose = verbose, warm_start = warm_start)
kernel = sklearn.ensemble.RandomForestRegressor(n_estimators = n_estimators, **kwargs)
kernel.fit(data_train, outputs_train)
predictions = kernel.predict(data_test)