alu/tra-analysis
1
0
Fork 0
mirror of https://github.com/titanscouting/tra-analysis.git synced 2024-12-27 09:59:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

analysis.py v 1.1.7.000

Browse Source
This commit is contained in:
art 2019-11-05 13:14:08 -06:00
parent 3c21512a46
commit 5ecd01279f
1 changed files with 19 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
data analysis/analysis/analysis.py
View File

@ -7,10 +7,13 @@
# current benchmark of optimization: 1.33 times faster # current benchmark of optimization: 1.33 times faster
# setup: # setup:
__version__ = "1.1.6.002" __version__ = "1.1.7.000"
# changelog should be viewed using print(analysis.__changelog__) # changelog should be viewed using print(analysis.__changelog__)
__changelog__ = """changelog: __changelog__ = """changelog:
1.1.7.000:
- added knn()
- added confusion matrix to decisiontree()
1.1.6.002: 1.1.6.002:
- changed layout of __changelog to be vscode friendly - changed layout of __changelog to be vscode friendly
1.1.6.001: 1.1.6.001:
@ -395,14 +398,27 @@ def pca(data, kernel = sklearn.decomposition.PCA(n_components=2)):
return kernel.fit_transform(data) return kernel.fit_transform(data)
def decisiontree(data, labels, test_size = 0.3, criterion = "gini", splitter = "default", max_depth = None): #expects 2d data and 1d labels def decisiontree(data, labels, test_size = 0.3, criterion = "gini", splitter = "default", max_depth = None): #expects *2d data and 1d labels
data_train, data_test, labels_train, labels_test = sklearn.model_selection.train_test_split(data, labels, test_size=test_size, random_state=1) data_train, data_test, labels_train, labels_test = sklearn.model_selection.train_test_split(data, labels, test_size=test_size, random_state=1)
model = sklearn.tree.DecisionTreeClassifier(criterion = criterion, splitter = splitter, max_depth = max_depth) model = sklearn.tree.DecisionTreeClassifier(criterion = criterion, splitter = splitter, max_depth = max_depth)
model = model.fit(data_train,labels_train) model = model.fit(data_train,labels_train)
predictions = model.predict(data_test) predictions = model.predict(data_test)
cm = sklearn.metrics.confusion_matrix(labels_test, predictions)
accuracy = sklearn.metrics.accuracy_score(labels_test, predictions) accuracy = sklearn.metrics.accuracy_score(labels_test, predictions)
return model, accuracy
return model, cm, accuracy
def knn(data, labels, test_size = 0.3, algorithm='auto', leaf_size=30, metric='minkowski', metric_params=None, n_jobs=None, n_neighbors=5, p=2, weights='uniform'): #expects *2d data and 1d labels post-scaling
data_train, data_test, labels_train, labels_test = sklearn.model_selection.train_test_split(data, labels, test_size=test_size, random_state=1)
model = sklearn.neighbors.KNeighborsClassifier()
model.fit(data_train, labels_train)
predictions = model.predict(data_test)
cm = sklearn.metrics.confusion_matrix(labels_test, predictions)
cr = sklearn.metrics.classification_report(labels_test, predictions)
return model, cm, cr
class Regression: class Regression: