indexlist = []
for i in range(len(data_example)):
indexlist.append(i)
random.shuffle(indexlist)
size = len(indexlist)
for k in range(10):
train = []
test = []
for i in range(size):
if (i >= k * size / 10) and (i <= (k + 1) * size / 10):
test.append(indexlist[i])
else:
train.append(indexlist[i])
mynode = decision.makesubtree(data_example, ma, 'bot', train)
result = decision.judgeData(mynode, data_example, ma, 'bot', test)
tp = result[0]
fp = result[1]
fn = result[2]
tn = result[3]
accuracy += (tp + tn) / len(test)
precise = tp / (tp + fp)
recal = tp / (tp + fn)
precision += precise
recall += recal
f1score += 2 * (1 / ((1 / precise) + (1 / recal)))
print("accuracy:", accuracy / 50)
print("precision:", precision / 50)
print("recall:", recall / 50)
print("f1score:", f1score / 50)
for i in range(len(data_trai)):
row = []
for name in ma:
row.append(data_trai[name][i])
thedatatr.append(row)
targettr.append(data_trai['bot'][i])
for i in range(len(data_test)):
row = []
for name in ma:
row.append(data_test[name][i])
thedatate.append(row)
for k in range(1):
model = mybayes.buildmodel(data_trai, ma, 'bot', trainindexlist)
result1 = model.getResult(data_test, ma, 'bot', testindexlist)
mynode = decision.makesubtree(data_trai, ma, 'bot', trainindexlist)
result2 = decision.getResult(mynode, data_test, ma, 'bot', testindexlist)
logreg = LogisticRegression(C=1000).fit(thedatatr, targettr)
thetar = logreg.predict(thedatate)
result = []
for i in range(len(result1)):
t = result1[i] + result2[i] + thetar[i]
if t >= 2:
result.append(1)
else:
result.append(0)
accuracy = 0.0
precision = 0.0
recall = 0.0
f1score = 0.0
tp = 0