pandas 绘图
import numpy as np
import tflearn
from tflearn.layers.core import dropout
from tflearn.layers.normalization import batch_normalization
from tflearn.data_utils import to_categorical
from sklearn.model_selection import train_test_split
import sys
import pandas as pd
from pandas import Series,DataFrame
import matplotlib.pyplot as plt
data_train = pd.read_csv("feature_with_dnn_todo2.dat")
data_train.info()
import matplotlib.pyplot as plt
print(data_train.columns)
for col in data_train.columns[1:]:
fig = plt.figure()
fig.set(alpha=0.2)
plt.figure()
data_train[data_train.label == 0.0][col].plot()
data_train[data_train.label == 1.0][col].plot()
data_train[data_train.label == 2.0][col].plot()
data_train[data_train.label == 3.0][col].plot()
plt.xlabel(u"sample data id")
plt.ylabel(col)
plt.title(col)
plt.legend((u'white', u'cdn',u'tunnel', u"msad"),loc='best')
plt.show()结果：
Index(['label', 'flow_cnt', 'len(srcip_arr)', 'len(dstip_arr)',
'subdomain_num', 'uniq_subdomain_ratio',
'np.average(dns_request_len_arr)', 'np.average(dns_reply_len_arr)',
'np.average(subdomain_tag_num_arr)', 'np.average(subdomain_len_arr)',
'np.average(subdomain_weird_len_arr)',
'np.average(subdomain_entropy_arr)', 'A_rr_type_ratio',
'incommon_rr_type_rato', 'valid_ipv4_ratio', 'uniq_valid_ipv4_ratio',
'request_reply_ratio', 'np.max(dns_request_len_arr)',
'np.max(dns_reply_len_arr)', 'np.max(subdomain_tag_num_arr)',
'np.max(subdomain_len_arr)', 'np.max(subdomain_weird_len_arr)',
'np.max(subdomain_entropy_arr)', 'avg_distance', 'std_distance'],
dtype='object')
。。。。
输入数据样例：
label,flow_cnt,len(srcip_arr),len(dstip_arr),subdomain_num,uniq_subdomain_ratio,np.average(dns_request_len_arr),np.average(dns_reply_len_arr),np.average(subdomain_tag_num_arr),np.average(subdomain_len_arr),np.average(subdomain_weird_len_arr),np.average(subdomain_entropy_arr),A_rr_type_ratio,incommon_rr_type_rato,valid_ipv4_ratio,uniq_valid_ipv4_ratio,request_reply_ratio,np.max(dns_request_len_arr),np.max(dns_reply_len_arr),np.max(subdomain_tag_num_arr),np.max(subdomain_len_arr),np.max(subdomain_weird_len_arr),np.max(subdomain_entropy_arr),avg_distance,std_distance
0.0,1.0,1.0,1.0,1.0,1.0,35.0,148.0,1.0,3.0,0.0,0.0,1.0,0.0,1.0,1.0,0.142857142857,35.0,148.0,1.0,3.0,0.0,-0.0,0,0
0.0,10.0,1.0,3.0,6.0,0.6,42.7,143.5,1.83333333333,8.5,0.0,2.75986309274,0.6,0.0,0.2,0.2,0.0117096018735,44.0,287.0,2.0,10.0,0.0,2.94770277922,2.2,1.46969384567
0.0,100.0,1.0,2.0,50.0,0.5,49.63,62.96,1.0,7.7,0.0,2.41418035734,0.51,0.0,0.26,0.01,0.00100745516825,56.0,134.0,1.0,14.0,0.0,3.27761343682,7.14285714286,2.65729646253
0.0,100.0,1.0,3.0,17.0,0.17,46.11,70.53,1.0,4.47058823529,0.0,1.29411764706,0.4,0.0,0.13,0.05,0.00108436347864,54.0,631.0,1.0,12.0,0.0,3.0,5.1875,1.84454432042
0.0,100.0,1.0,4.0,50.0,0.5,45.8,59.59,1.0,5.8,0.0,2.06068705052,0.5,0.0,0.22,0.01,0.00109170305677,46.0,126.0,1.0,6.0,0.0,2.58496250072,4.14285714286,0.925820099773
0.0,100.0,11.0,7.0,26.0,0.26,42.64,58.51,1.0,4.80769230769,0.0,1.53846153846,0.84,0.0,0.7,0.25,0.00117260787992,47.0,201.0,1.0,5.0,0.0,2.0,1.28,0.825590697622 。。。