simulatev1.3.py 文件源码

def init(l_sys, l_namenode, l_FS, l_RPC, sleeptime=15, cont=0.01,limit = 300):
    # ?????
    ilf_sys = IsolationForest(n_estimators=100, contamination=cont)
    ilf_namenode = IsolationForest(n_estimators=100, contamination=cont)
    ilf_FS = IsolationForest(n_estimators=50, contamination=cont)
    ilf_RPC = IsolationForest(n_estimators=100, contamination=cont)
    #??????????
    client = DataFrameClient(host='127.0.0.1', port=8086, username='root', password='root', database='testdb')

    data_sys = sampleWithDecay(client, limit, 'select * from ganglia where w_system >0 ORDER BY time DESC')
    d_sys = data_sys[l_sys]

    data_fs = sampleWithDecay(client, limit, 'select * from ganglia where w_fs >0 ORDER BY time DESC')
    d_FS = data_fs[l_FS]

    data_namenode = sampleWithDecay(client, limit, 'select * from ganglia where w_namenode >0 ORDER BY time DESC')
    d_namenode = data_namenode[l_namenode]

    data_rpc = sampleWithDecay(client, limit, 'select * from ganglia where w_rpc >0 ORDER BY time DESC')
    d_RPC = data_rpc[l_RPC]


    print len(d_sys)
    print len(d_FS)
    print len(d_namenode)
    print len(d_RPC)
    # ??fit
    ilf_sys.fit(d_sys)
    ilf_namenode.fit(d_namenode)
    ilf_FS.fit(d_FS)
    ilf_RPC.fit(d_RPC)

    print ilf_FS.predict(d_FS)

    return ilf_sys, ilf_namenode, ilf_FS, ilf_RPC