def randomForestTest(feature_len, all_lines, all_features, all_labels):
best_trees_num = 0
temp = 0
counts = {}
for i in range(10):
rate = 0
print("Test %d:" % (i + 1))
train_features = all_features[0:int(0.8 * len(all_features))]
train_labels = all_labels[0:int(0.8 * len(all_features))]
test_features = all_features[int(0.8 * len(all_features)):]
test_labels = all_labels[int(0.8 * len(all_features)):]
for trees_num in range(25, 36):
rate = 0
if trees_num not in counts:
counts[trees_num] = 0
print("trees_num:%d " % (trees_num), end=" ")
new_forest = RandomForest(trees_num)
new_forest.buildTrees(train_features, train_labels,
len(train_features[0]), 3, 6)
length = len(test_labels)
for j in range(0, length):
res = new_forest.predictForest(test_features[j])
if res == test_labels[j]:
rate += 1
print(rate / length)
counts[trees_num] += rate / length
if temp < counts[trees_num]:
temp = counts[trees_num]
best_trees_num = trees_num
all_features, all_labels = now_provider.getFeatureAndLabel(
all_lines, feature_len)
print("Best trees_num:%d %f" %
(best_trees_num, counts[best_trees_num] / 10))
for x in counts:
print(x, counts[x])
def compareTest(feature_len, all_lines, all_features, all_labels):
count = {}
for i in range(10):
print("\nTest %d" % (i + 1))
train_features = all_features[0:int(0.8 * len(all_features))]
train_labels = all_labels[0:int(0.8 * len(all_features))]
test_features = all_features[int(0.8 * len(all_features)):]
test_labels = all_labels[int(0.8 * len(all_features)):]
length = len(test_labels)
rate = 0
print("NaiveBayes : ", end="")
new_bayes = NaiveBayes(train_features, train_labels, feature_len)
new_bayes.train()
for j in range(0, length):
res = new_bayes.predict(test_features[j])
if res == test_labels[j]:
rate += 1
print(rate / length)
if "NaiveBayes" not in count:
count["NaiveBayes"] = rate / length
else:
count["NaiveBayes"] += rate / length
rate = 0
print("KNN : ", end="")
for j in range(0, length):
res = Knn(train_features, train_labels, test_features[j], 3)
if res == test_labels[j]:
rate += 1
print(rate / length)
if "KNN" not in count:
count["KNN"] = rate / length
else:
count["KNN"] += rate / length
rate = 0
print("Logistic : ", end="")
new_logistic = Logistic(train_features,
train_labels,
feature_len,
alpha=5,
tol=0.000001)
new_logistic.train()
for j in range(0, length):
res = new_logistic.predict(test_features[j])
if res == test_labels[j]:
rate += 1
print(rate / length)
if "Logistic" not in count:
count["Logistic"] = rate / length
else:
count["Logistic"] += rate / length
rate = 0
print("NeuralNetwork : ", end="")
new_NN = NeuralNetwork(train_features,
train_labels,
feature_len,
hidden_num=32,
learn_rate=100)
new_NN.train()
for j in range(0, length):
res = new_NN.predict(test_features[j])
if res == test_labels[j]:
rate += 1
print(rate / length)
if "NeuralNetwork" not in count:
count["NeuralNetwork"] = rate / length
else:
count["NeuralNetwork"] += rate / length
rate = 0
print("Tree : ", end="")
new_tree = Tree(train_features, train_labels, len(train_features[0]),
3, 8)
new_tree.train()
for j in range(0, length):
res = new_tree.predictTree(test_features[j])
if res == test_labels[j]:
rate += 1
print(rate / length)
if "Tree" not in count:
count["Tree"] = rate / length
else:
count["Tree"] += rate / length
rate = 0
print("AdaBoost : ", end="")
new_boost = AdaBoost(train_features,
train_labels,
len(train_features[0]),
28,
mode=2)
new_boost.train()
for j in range(0, length):
res = new_boost.predict(test_features[j])
if res == test_labels[j]:
rate += 1
print(rate / length)
if "AdaBoost" not in count:
count["AdaBoost"] = rate / length
else:
count["AdaBoost"] += rate / length
rate = 0
print("RandomForest : ", end="")
new_forest = RandomForest(30)
new_forest.buildTrees(train_features, train_labels,
len(train_features[0]), 3, 6)
for j in range(0, length):
res = new_forest.predictForest(test_features[j])
if res == test_labels[j]:
rate += 1
print(rate / length)
if "RandomForest" not in count:
count["RandomForest"] = rate / length
else:
count["RandomForest"] += rate / length
rate = 0
print("SVM : ", end="")
new_svm = SVM(train_features,
train_labels,
C=43,
function='RBF',
d=0.53)
new_svm.train()
for j in range(0, length):
res = new_svm.predict(test_features[j])
if res == test_labels[j]:
rate += 1
print(rate / length)
if "SVM" not in count:
count["SVM"] = rate / length
else:
count["SVM"] += rate / length
all_features, all_labels = now_provider.getFeatureAndLabel(
all_lines, feature_len)
print("\nAverage:")
for x in count:
print(x, end=": ")
print(count[x] / 10)
