alu/tra-analysis
1
0
Fork 0
mirror of https://github.com/titanscouting/tra-analysis.git synced 2024-12-26 17:49:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

analysis.py v 1.1.11.001

Browse Source
This commit is contained in:
ltcptgeneral 2019-11-10 01:38:39 -06:00
parent 234f54ef5d
commit 08ff6aec8e
1 changed files with 18 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
data analysis/analysis/analysis.py
View File

@ -7,10 +7,12 @@
# current benchmark of optimization: 1.33 times faster # current benchmark of optimization: 1.33 times faster
# setup: # setup:
__version__ = "1.1.11.000" __version__ = "1.1.11.001"
# changelog should be viewed using print(analysis.__changelog__) # changelog should be viewed using print(analysis.__changelog__)
__changelog__ = """changelog: __changelog__ = """changelog:
1.1.11.001:
- added test/train split to RandomForestClassifier and RandomForestRegressor
1.1.11.000: 1.1.11.000:
- added RandomForestClassifier and RandomForestRegressor - added RandomForestClassifier and RandomForestRegressor
- note: untested - note: untested
@ -554,17 +556,26 @@ class SVM:
return r_2, _mse, _rms return r_2, _mse, _rms
def RandomForestClassifier(data, labels, n_estimators="warn", 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 RandomForestClassifier(data, labels, test_size, n_estimators="warn", 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 = 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, labels) kernel.fit(data_train, labels_train)
return kernel predictions = kernel.predict(data_test)
cm = sklearn.metrics.confusion_matrix(predictions, predictions)
cr = sklearn.metrics.classification_report(predictions, predictions)
return kernel, cm, cr
def RandomForestRegressor(inputs, outputs, n_estimators="warn", 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 RandomForestRegressor(data, outputs, test_size, n_estimators="warn", 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(inputs, 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, 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(inputs, outputs) kernel.fit(data_train, outputs_train)
return kernel predictions = kernel.predict(data_test)
r_2 = r_squared(predictions, outputs_test)
_mse = mse(predictions, outputs_test)
_rms = rms(predictions, outputs_test)
return kernel, r_2, _mse, _rms
class Regression: class Regression: