siyuan_ye-thesis_intersection-attacks/v2/final.py

import numpy as np
import glob
from tslearn.clustering import KShape
from sklearn.cluster import KMeans
import tslearn.metrics as metrics
from sklearn.metrics import calinski_harabasz_score
from tslearn.preprocessing import TimeSeriesScalerMeanVariance
from tslearn.clustering import TimeSeriesKMeans
import matplotlib.pyplot as plt
#from tslearn.generators import random_walks
import tslearn.metrics as metrics
import pandas as pd
from sklearn.model_selection import train_test_split
import warnings
from tslearn.clustering import silhouette_score
import os
from sklearn import metrics
import random

seed = 0




def filter():
    GoodNameList = np.loadtxt('/home/it/middle_data/good_name_list.txt',dtype=int)
    X=np.array(pd.read_csv('/home/it/middle_data/value.csv',header=None))
    
    print("X=",X,type(X),np.shape(X))
    threshold_1=19
    threshold_2=20
    t1 = np.empty([len(X),len(X)], dtype = int)
    t2 = np.empty([len(X),len(X)], dtype = int)
    i=0
    while i<len(X):
        j=i
        while j<len(X):
            a=X[i]
            b=X[j]
            m1_num=np.sum(a==b)
            if m1_num>=threshold_1:#close
                t2[i][j]=t2[j][i]=1
            else:
                t2[i][j]=t2[j][i]=0#far
            t1[i][j]=t1[j][i]=m1_num
            j=j+1
        i=i+1
    outlier = np.empty([len(X)], dtype = int)
    k=0
    while k<len(X):
        if np.sum(t2[k])>=threshold_2:
            outlier[k]=0#NOT outlier
        else:
            outlier[k]=1#outlier
        k=k+1
    need_be_filtered=np.argwhere(outlier>=1).copy()
    filtered_index=np.concatenate(need_be_filtered)
    np.savetxt('/home/it/middle_data/filtered_good_name_list.txt',np.delete(GoodNameList,filtered_index),fmt="%i")
    pattern_middle=np.delete(GoodNameList,filtered_index).copy()
    df_result = pd.DataFrame(np.delete(X,filtered_index,axis=0).copy())
    df_result.to_csv('/home/it/middle_data/filtered_valus.csv',header=None,index=False)

    
    print("group")
    X=pd.read_csv('/home/it/middle_data/filtered_valus.csv',header=None)
    x_original=X.copy()
    x_pattern=np.copy(X)
    seed = 2
    num_cluster = 13
    X = TimeSeriesScalerMeanVariance(mu= 0.0 ,std= 1.0 ).fit_transform(X)
    ks = KShape(n_clusters= num_cluster ,n_init= 10 ,max_iter=200,tol=1e-8,verbose= True ,random_state=seed)
    y_pred = ks.fit_predict(X)
    y_pattern=y_pred.copy()
    final_y_pred=y_pred.copy()
    f4 = open("/home/it/middle_data/filtered_good_name_list.txt","a+") # open in `w` mode to write
    i=0
    while i<len(filtered_index):
        f4.write(str(GoodNameList[filtered_index[i]])) # concatenate the contents
        final_y_pred=np.append(final_y_pred,num_cluster)
        f4.write("\n")
        i=i+1
    f4.close()
    np.savetxt('/home/it/middle_data/groupingResult.txt',final_y_pred,fmt="%i")
    
    
    #score function
    score_result=metrics.calinski_harabasz_score(x_original, y_pred)
    score_result_path="/home/it/middle_data/score_result_kshape.txt"
    f = open(score_result_path,"a+") # open in `w` mode to write
    f.write("\n")
    f.write("k="+str(num_cluster))
    f.write("\n")
    f.write("CA="+str(score_result)) # concatenate the contents
    f.close()

    pattern=np.zeros([num_cluster,len(X[0])], dtype = int)
    count= np.zeros([1,num_cluster],dtype = int)#用于计相加数，每个group的数量，看跟实际分组数量是否对得上

    i=0
    while i<len(y_pattern):
        #print("final_test",pattern[y_pattern[i]],x_pattern[i])
        pattern[y_pattern[i]]=pattern[y_pattern[i]]+x_pattern[i]
        count[0][y_pattern[i]]=count[0][y_pattern[i]]+1
        i=i+1
    final_result=np.zeros([num_cluster,len(X[0])], dtype = float)
    i=0
    while i<num_cluster:
        final_result[i]=np.true_divide(pattern[i],float(count[0][i]))
        i=i+1
    print("final_result=",final_result)
    i=0
    while i<len(final_result):
        j=0
        while j<len(final_result[0]):
            if final_result[i][j]>=0.3:
                final_result[i][j]=1
            else:
                final_result[i][j]=0
            j=j+1
        i=i+1


    #repeat the fixed scheduler
    middle_final_result=np.copy(final_result) 
    k=0
    while k<13:
        middle_final_result=np.concatenate((middle_final_result,final_result),axis=1)
        k=k+1
    np.savetxt('/home/it/middle_data/pattern.txt',middle_final_result,fmt="%i")



warnings.filterwarnings("ignore", category=FutureWarning, module="sklearn", lineno=931)
filter()