# 模型网络的入口和出口
d = Model(inputs=dnn_inp, outputs=d_out)
d.compile(optimizer=Adam(lr=0.00001),
loss="categorical_crossentropy",
metrics=["accuracy"])
# 以下输入数据进行wide and deep模型的训练
print(d.summary())
X_tr = X_train_dnn
Y_tr = y_train_dnn
# 测试集
X_te = X_test_dnn
Y_te = y_test_dnn
d.fit(X_tr, Y_tr, epochs=40000, batch_size=32)
results = d.evaluate(X_te, Y_te)
print("\n", results)
results = d.evaluate(X_te, Y_te)
predicts = d.predict(X_te)
y_pre = [np.argmax(i) for i in predicts]
y_ture = [np.argmax(i) for i in Y_te]
print("\n", results)
alphabet = [
"AIM", "email", "facebookchat", "gmailchat", "hangoutsaudio",
"hangoutschat", "icqchat", "netflix", "skypechat", "skypefile", "spotify",
"vimeo", "youtube", "youtubeHTML5"
]
figures.plot_confusion_matrix(y_ture, y_pre, alphabet, "./finetune_")
# print("recall_score_micro:",recall_score(y_true,predicts,average='micro'))
print("recall_score_macro:",recall_score(y_true,predicts,average='macro'))
# alphabet=["AIM","email","facebookchat","gmailchat","hangoutsaudio","hangoutschat","icqchat","netflix","skypechat","skypefile","spotify","vimeo","youtube","youtubeHTML5"]
alphabet=softwares=["Baidu Map",
"Baidu Post Bar",
"Netease cloud music",
"iQIYI",
"Jingdong",
"Jinritoutiao",
"Meituan",
"QQ",
"QQ music",
"QQ reader",
"Taobao",
"Weibo",
"CTRIP",
"Zhihu",
"Tik Tok",
"Ele.me",
"gtja",
"QQ mail",
"Tencent",
"Alipay"]
figures.plot_confusion_matrix(y_true, predicts,alphabet, "./%dx%d_"% (pkt_counts, pkt_size) + choose)
# 打印weight
weights=model.predict(input_fn=test_input_fn,predict_keys=["layer_rnn_weight"])
weights=[w['layer_rnn_weight'] for w in weights]
for weight in weights[:10]:
print(weight)
print("\n")
from sklearn.ensemble import RandomForestClassifier
train_data, train_labels, test_data, test_labels = input_w.inputs()
clf = RandomForestClassifier(n_estimators=100,
max_depth=12,
random_state=0,
verbose=1)
clf.fit(train_data, train_labels)
dump(clf, './randomForest.model')
clf = load('./randomForest.model')
predicts = clf.predict(test_data)
print(predicts)
print("predicts:", len(predicts))
print("accuracy_score:", accuracy_score(test_labels, predicts))
print("precision_score:",
precision_score(test_labels, predicts, average='macro'))
# print("f1_score_micro:",f1_score(y_true,predicts,average='micro'))
print("f1_score_macro:", f1_score(test_labels, predicts, average='macro'))
# print("recall_score_micro:",recall_score(y_true,predicts,average='micro'))
print("recall_score_macro:",
recall_score(test_labels, predicts, average='macro'))
# alphabet=["AIM","email","facebookchat","gmailchat","hangoutsaudio","hangoutschat","icqchat","netflix","skypechat","skypefile","spotify","vimeo","youtube","youtubeHTML5"]
alphabet = softwares = [
"Baidu Map", "Baidu Post Bar", "Netease cloud music", "iQIYI", "Jingdong",
"Jinritoutiao", "Meituan", "QQ", "QQ music", "QQ reader", "Taobao",
"Weibo", "CTRIP", "Zhihu", "Tik Tok", "Ele.me", "gtja", "QQ mail",
"Tencent", "Alipay"
]
figures.plot_confusion_matrix(test_labels, predicts, alphabet, "./rf")
cnn_x_name=["Seq_%d_y"%i for i in range(128)]
rnn_x_name=["Seq_%d_x"%i for i in range(128)]
filtered_val_data=pd.read_csv(config.HTTPS_CONFIG["all_val_path"])
y_test=filtered_val_data["label"]
# y_test=to_categorical(y_test)
X_test_cnn = filtered_val_data[cnn_x_name]
X_test_cnn=np.asarray(X_test_cnn).reshape((-1,128,1))
X_test_rnn = filtered_val_data[rnn_x_name]
X_test_rnn=np.asarray(X_test_rnn)
X_te = [X_test_cnn, X_test_rnn]
Y_te = y_test
outcomes=[]
models=os.listdir(config.HTTPS_CONFIG["models"])
for model in models:
clf=load_model(config.HTTPS_CONFIG["models"]+model)
outcome=clf.predict(X_te)
outcomes.append(np.asarray(outcome)[:,0])
#转置
tmp=np.asarray(outcomes).T
predicts=[np.argmax(i) for i in tmp]
choose=config.HTTPS_CONFIG[config.HTTPS_CONFIG["choose"]]
names=os.listdir(choose)
alphabet=[names[i][:-4] for i in range(len(names))]
#绘制混淆矩阵
figures.plot_confusion_matrix(Y_te, predicts,alphabet, "./")
def fit_and_save_result(x_train, y_train, x_test, y_ture, clf, path):
t1 = time()
clf.fit(x_train, y_train)
t2 = time()
test_one_hot = label_binarize(y_ture, np.arange(config.HTTPS_CONFIG["num_class"]))
y_score = clf.predict_proba(x_test)
t3 = time()
y_pre = clf.predict(x_test)
t4 = time()
# conf_arr = confusion_matrix(y_true=y_ture, y_pred=y_pre)
accuracy = metrics.accuracy_score(y_true=y_ture, y_pred=y_pre)
f1 = metrics.f1_score(y_true=y_ture, y_pred=y_pre, average='macro')
precision = metrics.precision_score(y_true=y_ture, y_pred=y_pre, average='macro')
recall = metrics.recall_score(y_true=y_ture, y_pred=y_pre, average='macro')
auc = metrics.roc_auc_score(y_true=test_one_hot, y_score=y_score, average='macro')
auc_all, f1_all, recall_all, precision_all, acc_all = [], [], [], [], []
for label in range(config.HTTPS_CONFIG["num_class"]):
def convert(x):
if x == label:
return 1
else:
return 0
label = int(label)
ture = y_ture
pre = y_pre
score = y_score[:, label]
ture = [convert(x) for x in ture]
pre = [convert(x) for x in pre]
auc_each = metrics.roc_auc_score(ture, score)
f1_each = metrics.f1_score(y_true=ture, y_pred=pre, average='binary')
recall_each = metrics.recall_score(ture, pre)
precision_each = metrics.precision_score(ture, pre)
accuracy_each = metrics.accuracy_score(ture, pre)
auc_all.append(auc_each)
f1_all.append(f1_each)
recall_all.append(recall_each)
precision_all.append(precision_each)
acc_all.append(accuracy_each)
each_class_pd = pd.DataFrame({
'auc':auc_all,
'f1':f1_all,
'recall':recall_all,
'precision_all':precision_all,
'acc':acc_all
})
each_class_pd.to_csv(path + 'each_class_metrics.csv', index=False)
df_score = pd.DataFrame(y_score)
df_score.to_csv(path + 'predict_proba.csv', index=False)
df_result = pd.DataFrame({'y_ture' : y_ture, 'y_pred' : y_pre})
df_result.to_csv(path + 'predict_data.csv', index=False)
with open(path + 'metrics', 'w') as w:
w.write('train_time: %s' % str(t2 - t1) + '\n')
w.write('predict_time: %s' % str(t4 - t3) + '\n')
w.write('accuracy: %s' % str(accuracy) + '\n')
w.write('f1: %s' % str(f1) + '\n')
w.write('precision: %s' % str(precision) + '\n')
w.write('recall: %s' % str(recall) + '\n')
w.write('auc: %s' % str(auc) + '\n')
# 保存最优超参数
with open(path + 'best_params', 'w') as w:
w.write('\n'.join(['%s %s' % (key, str(value)) for key, value in clf.best_params_.items()]))
# 画出混淆矩阵并保存
figures.plot_confusion_matrix(y_ture, y_pre,alphabet, path)
"learning_rate": 0.1,
"lambda_l1": 0.1,
"lambda_l2": 0.2,
"max_depth": 5,
"objective": "multiclass",
"num_class": config.HTTPS_CONFIG["num_class"],
"silent": True,
"verbosity": -1
}
train_data = lgb.Dataset(train_data, label=train_labels)
validation_data = lgb.Dataset(eval_data, label=eval_labels)
clf = lgb.train(params,
train_data,
num_boost_round=100000,
valid_sets=[validation_data],
early_stopping_rounds=500,
feval=f1_score_vali,
verbose_eval=1)
names = os.listdir(choose)
labels = [names[i][:-4] for i in range(len(names))]
y_pred = clf.predict(eval_data)
y_pred = [np.argmax(i) for i in y_pred]
eval_labels = [i for i in eval_labels]
figures.plot_confusion_matrix(
eval_labels, y_pred, labels,
config.HTTPS_CONFIG["outcome"] + 'lgb_confusion_matrix.png')
xgb_train = xgb.DMatrix(train_data[500:], label=train_labels[500:])
xgb_val = xgb.DMatrix(train_data[:500], train_labels[:500])
xgb_test = xgb.DMatrix(test_data)
watchlist = [(xgb_val, 'val')]
model = xgb.train(plst,
xgb_train,
num_rounds,
watchlist,
early_stopping_rounds=100)
model.save_model("./xgb.model")
bst = xgb.Booster({'nthread': 4})
bst.load_model('./xgb.model')
preds = bst.predict(xgb_test)
print(preds.tolist())
print("accuracy_score:", accuracy_score(test_labels, preds))
print("precision_score:", precision_score(test_labels, preds, average='macro'))
# print("f1_score_micro:",f1_score(y_true,predicts,average='micro'))
print("f1_score_macro:", f1_score(test_labels, preds, average='macro'))
# print("recall_score_micro:",recall_score(y_true,predicts,average='micro'))
print("recall_score_macro:", recall_score(test_labels, preds, average='macro'))
# alphabet=["AIM","email","facebookchat","gmailchat","hangoutsaudio","hangoutschat","icqchat","netflix","skypechat","skypefile","spotify","vimeo","youtube","youtubeHTML5"]
alphabet = softwares = [
"Baidu Map", "Baidu Post Bar", "Netease cloud music", "iQIYI", "Jingdong",
"Jinritoutiao", "Meituan", "QQ", "QQ music", "QQ reader", "Taobao",
"Weibo", "CTRIP", "Zhihu", "Tik Tok", "Ele.me", "gtja", "QQ mail",
"Tencent", "Alipay"
]
figures.plot_confusion_matrix(test_labels, preds, alphabet, "./xgb_finetune_")