mirror of
https://github.com/titanscouting/tra-analysis.git
synced 2024-09-20 08:57:56 +00:00
f72d8457a7
* feat: created kivy gui boilerplate * migrated docker base image to debian Signed-off-by: ltcptgeneral <learthurgo@gmail.com> * migrated to ubuntu Signed-off-by: ltcptgeneral <learthurgo@gmail.com> * fixed issues Signed-off-by: ltcptgeneral <learthurgo@gmail.com> * fix: docker build? * fix: use ubuntu bionic * fix: get kivy installed * @ltcptgeneral can't spell * optim dockerfile for not installing unused packages * install basic stuff while building the container * use prebuilt image for development * install pylint on base image * rename and use new kivy * tests: added tests for Array and CorrelationTest Both are not working due to errors * fix: Array no longer has *args and CorrelationTest functions no longer have self in the arguments * use new thing * use 20.04 base * symlink pip3 to pip * use pip instead of pip3 * tra_analysis v 2.1.0-alpha.2 SVM v 1.0.1 added unvalidated SVM unit tests Signed-off-by: ltcptgeneral <learthurgo@gmail.com> * fixed version number Signed-off-by: ltcptgeneral <learthurgo@gmail.com> * tests: added tests for ClassificationMetric * partially fixed and commented out svm unit tests * fixed some SVM unit tests * added installing pytest to devcontainer.json * fix: small fixes to KNN Namely, removing self from parameters and passing correct arguments to KNeighborsClassifier constructor * fix, test: Added tests for KNN and NaiveBayes. Also made some small fixes in KNN, NaiveBayes, and RegressionMetric * test: finished unit tests except for StatisticalTest Also made various small fixes and style changes * StatisticalTest v 1.0.1 * fixed RegressionMetric unit test temporarily disabled CorrelationTest unit tests * tra_analysis v 2.1.0-alpha.3 * readded __all__ * fix: floating point issues in unit tests for CorrelationTest Co-authored-by: AGawde05 <agawde05@gmail.com> Co-authored-by: ltcptgeneral <learthurgo@gmail.com> Co-authored-by: Dev Singh <dev@devksingh.com> Co-authored-by: jzpan1 <panzhenyu2014@gmail.com>
42 lines
2.8 KiB
Python
42 lines
2.8 KiB
Python
# Titan Robotics Team 2022: RandomForest submodule
|
|
# Written by Arthur Lu
|
|
# Notes:
|
|
# this should be imported as a python module using 'from tra_analysis import RandomForest'
|
|
# setup:
|
|
|
|
__version__ = "1.0.0"
|
|
|
|
__changelog__ = """changelog:
|
|
1.0.0:
|
|
- ported analysis.RandomFores() here
|
|
- removed classness
|
|
"""
|
|
|
|
__author__ = (
|
|
"Arthur Lu <learthurgo@gmail.com>",
|
|
)
|
|
|
|
__all__ = [
|
|
]
|
|
|
|
import sklearn
|
|
from sklearn import ensemble, model_selection
|
|
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):
|
|
|
|
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.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):
|
|
|
|
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.fit(data_train, outputs_train)
|
|
predictions = kernel.predict(data_test)
|
|
|
|
return kernel, RegressionMetric.RegressionMetric(predictions, outputs_test) |