test_data = dc.convertPandasDataFrameToNumpyArray(test_frame)
dc.describeDataframe(test_frame)
decision_tree = tree.DecisionTreeClassifier(max_depth=4)
train_x = train_data[:, 1:]
train_y = train_data[:, 0]
decision_tree.fit(train_x, train_y)
cv_score = metrics.crossValidationScore(decision_tree, train_x, train_y, cvCount=5)
xTrain, xTest, yTrain, yTest = metrics.traintestSplit(train_x, train_y, randomState=1)
cv_tree = tree.DecisionTreeClassifier(max_depth=4)
cv_tree.fit(xTrain,yTrain)
y_predict = cv_tree.predict(xTest)
ta = metrics.trainingAccuracy(yTest, y_predict)
rmse = metrics.rmse(yTest, y_predict)
nrmse = metrics.nrmse(yTest, y_predict)
predictors = dc.getColNames(train_frame)[1:]
kfoldAccuracy = metrics.measureKFoldAccuracy(train_frame, decision_tree, predictors, outputClass="Survived", outputClause="Survived", kFolds=10)
print("Max Cross Validation Score : ", cv_score.max(), "\nAverage Cross Validation Score : ", cv_score.mean(),
"\nExtraTreeCLassifier Score : ", decision_tree.score(xTrain, yTrain),
"\nTraining Accuracy : ", ta,
"\nRoot Mean Squared Error : ", rmse, "\nNormalized RMSE : ", nrmse,
"\nKFold Accuracy : ", kfoldAccuracy)
featureNames = dc.getColNames(train_frame)[1:]
helper.printFeatureImportances(featureNames, decision_tree.feature_importances_)
final_y_pred = decision_tree.predict(test_data[:, 1:])
if __name__ == "__main__":
params = {"max_depth" : [3,4,5,6,7,8], "n_estimators" : [100, 200, 300, 400], "learning_rate" : [0.01, 0.05, 0.1, 0.2, 0.5, 1]}
clf = GridSearchCV(crossvalidationTree, params, verbose=1, n_jobs=2, cv=10)
clf.fit(trainX, trainY)
print("GridSearch : \n", "Best Estimator : ", clf.best_estimator_,
"\nBest Params : ", clf.best_params_, "\nBest Score", clf.best_score_)
"""
crossvalidationTree.fit(xTrain, yTrain)
yPredict = crossvalidationTree.predict(xTest)
#trainingAccuracy = metrics.trainingAccuracy(yTest, yPredict)
rmse = Metrics.rmse(yTest, yPredict)
nrmse = Metrics.nrmse(yTest, yPredict)
for i, x in enumerate(yPredict):
if yPredict[i] < 0:
#print("Yactucal : ", yTest[i], " Ypredict : ", yPredict[i])
yPredict[i] = -yPredict[i]
logloss = Metrics.rmsle(yTest, yPredict)
print(
"Max Cross Validation Score : ",
crossvalidation.max(),
"\nAverage Cross Validation Score : ",
crossvalidation.mean(),
#"\nGradient Boosting Forest Score : ", crossvalidationTree.score(xTrain, yTrain),
if __name__ == "__main__":
params = {"max_depth" : [3,4,5,6,7,8], "n_estimators" : [50, 100, 150, 200, 250, 300, 350, 400], "learning_rate" : [0.01, 0.02, 0.05, 0.1, 0.15, 0.2, 0.5, 1], "gamma" : [0.1, 0.2, 0.5, 1]}
clf = GridSearchCV(crossvalidationTree, params, verbose=1, n_jobs=4, cv=10)
clf.fit(xTrain, yTrain)
print("GridSearch : \n", "Best Estimator : ", clf.best_estimator_,
"\nBest Params : ", clf.best_params_, "\nBest Score", clf.best_score_)
"""
evalSet = [(xTrain, yTrain), (xTest, yTest)]
crossvalidationTree.fit(xTrain, yTrain, eval_set=evalSet, eval_metric="auc")
predictedY = crossvalidationTree.predict(xTest)
trainingAccuracy = metric.trainingAccuracy(yTest, predictedY)
rmse = metric.rmse(yTest, predictedY)
nrmse = metric.nrmse(yTest, predictedY)
predictors = dataclean.getFeatureNames()[2:]
kfoldAccuracy = metric.measureKFoldAccuracy(trainFrame,
crossvalidationTree,
predictors,
outputClass="Survived",
outputClause="Survived",
kFolds=10)
print("Max Cross Validation Score : ",
crossvalidation.max(), "\nAverage Cross Validation Score : ",
crossvalidation.mean(), "\nTraining Accuracy : ", trainingAccuracy,
"\nRoot Mean Squared Error : ", rmse, "\nNormalized RMSE : ", nrmse,
"\nKFold Accuracy : ", kfoldAccuracy)
if __name__ == "__main__":
params = {"max_depth" : [2, 3, 4, 5, 6, 7, 8], "max_features" : [None, 2, 3, 4, 5, 6, 7, 8, 9, "auto", "log2", ], "presort" : [True, False]}
clf = GridSearchCV(decisionTree, params, verbose=1, n_jobs=4, cv=10)
clf.fit(xTrain, yTrain)
print("GridSearch : \n", "Best Estimator : ", clf.best_estimator_,
"\nBest Params : ", clf.best_params_, "\nBest Score", clf.best_score_)
"""
decisionTree.fit(xTrain, yTrain)
predictedY = decisionTree.predict(xTest)
trainingAccuracy = Metrics.trainingAccuracy(yTest, predictedY)
rmse = Metrics.rmse(yTest, predictedY)
nrmse = Metrics.nrmse(yTest, predictedY)
predictors = dataclean.getFeatureNames()[2:]
kfoldAccuracy = Metrics.measureKFoldAccuracy(trainFrame,
decisionTree,
predictors,
outputClass="Survived",
outputClause="Survived",
kFolds=10)
print("Max Cross Validation Score : ",
crossvalidation.max(), "\nAverage Cross Validation Score : ",
crossvalidation.mean(), "\nExtraTreeCLassifier Score : ",
decisionTree.score(xTrain, yTrain), "\nTraining Accuracy : ",
trainingAccuracy, "\nRoot Mean Squared Error : ", rmse,