sgd = SGD_SVM.SGDSVM(C=best_C,
ro=best_ro,
epochs=best_epoch,
W0=[0] * len(data[0]),
gamma0=best_g0)
sgd.fit(data, data_labels)
predictTrain = sgd.predict(data)
predictTest = sgd.predict(testset)
print("Accuracy for training set:")
print(Stat.Accuracy(predictTrain, data_labels))
print("F1 score for training set:")
print(Stat.F1_Score(predictTrain, data_labels))
print("Precision for training set:")
print(Stat.Precision(predictTrain, data_labels))
print("Recall for training set:")
print(Stat.Recall(predictTrain, data_labels))
print("Accuracy for test set")
print(Stat.Accuracy(predictTest, test_labels))
print("F1 score for test set")
print(Stat.F1_Score(predictTest, test_labels))
print("Precision for test set")
print(Stat.Precision(predictTest, test_labels))
###
predictTrains = []
predictTests = []
dataAccuracy = []
testAccuracy = []
for i in range(5):
sgd = SGD.SGD(r=best_r,epochs=best_epoch,W0=[0]*len(data[i][0]))
sgd.fit(data[i],data_labels)
predictTrains.append(sgd.predict(data[i]))
predictTests.append(sgd.predict(testset[i]))
dataAccuracy.append(Stat.F1_Score(sgd.predict(data[i]), data_labels))
testAccuracy.append(Stat.F1_Score(sgd.predict(testset[i]), test_labels))
trainT = np.asarray(predictTrains).T.tolist()
testT = np.asarray(predictTests).T.tolist()
predictTrain = []
for i in range(len(data[0])):
probPos = 0
probNeg = 0
for j in range(5):
if predictTrains[j][i] == 1:
probPos += dataAccuracy[j]
else:
probNeg += dataAccuracy[j]
if probPos > probNeg:
best_f1 = 0
for d in [10, 20, 30, 40, 50, float('inf')]:
tmp = []
dt = DecisionTree.DecisionTree(max_depth=d)
kfold = KFold.KFold(n_splits=5)
for kf in kfold.split(data):
train = [data[i] for i in kf[0]]
train_label = [data_labels[i] for i in kf[0]]
test = [data[i] for i in kf[1]]
test_label = [data_labels[i] for i in kf[1]]
dt.fit(train, train_label)
predict_tmp = dt.predict(test)
tmp.append(Stat.F1_Score(predict_tmp, test_label))
if np.mean(tmp) > best_f1:
best_f1 = np.mean(tmp)
best_depth = d
print("Best result so far >>", best_f1, d)
print("best depth:", best_depth)
###
dt = DecisionTree.DecisionTree(max_depth=best_depth)
dt.fit(data, data_labels)
predictTrain = dt.predict(data)
filename = 'ensembleResult/test' + '_ensemble_SVM_Perceptron'
predictTest = [
1 if s == 1 and p == 1 else -1
for p, s in zip(predict_labels_Perceptron, predict_labels_SVM)
]
predictEval = [
1 if s == 1 and p == 1 else -1
for p, s in zip(eval_labels_Perceptron, eval_labels_SVM)
]
print("Accuracy for test set")
print(Stat.Accuracy(predictTest, test_labels))
print("F1 score for test set")
print(Stat.F1_Score(predictTest, test_labels))
print("Precision for test set")
print(Stat.Precision(predictTest, test_labels))
print("Recall for test set")
print(Stat.Recall(predictTest, test_labels))
# filename = 'results/eval_Ensemble_SVM_Perceptron'
#
# with open(filename, 'wb') as thefile:
# for item in predictEval:
# thefile.write("%s\n" % item)
#
# print("eval is written!")