Question

我正在尝试在Use Python & Pandas to Create a D3 Force Directed Network Diagram

中执行此示例

但是在下面这行我得到一个错误'KeyError :('count'，'发生在索引0'）'

 temp_links_list = list(grouped_src_dst.apply(lambda row: {"source": row['source'], "target": row['target'], "value": row['count']}, axis=1))

我是python的新手。这是什么问题？

已编辑的代码

import pandas as pd
import json
import re

pcap_data = pd.read_csv('C:\packet_metadata.csv', index_col='No.')
dataframe = pcap_data
src_dst = dataframe[["Source","Destination"]]
src_dst.rename(columns={"Source":"source","Destination":"target"}, inplace=True)
grouped_src_dst = src_dst.groupby(["source","target"]).size().reset_index()
grouped_src_dst.rename(columns={'count':'value'}).to_dict(orient='records')
unique_ips = pd.Index(grouped_src_dst['source']
                  .append(grouped_src_dst['target'])
                  .reset_index(drop=True).unique())

但是

print(grouped_src_dst.columns.tolist())
['source', 'target', 0]

最终代码

import pandas as pd
import json
import re

pcap_data = pd.read_csv('C:\packet_metadata.csv', index_col='No.')
dataframe = pcap_data
src_dst = dataframe[["Source","Destination"]]
src_dst.sample(10)
grouped_src_dst = src_dst.groupby(["Source","Destination"]).size().reset_index()
d={0:'value',"Source":"source","Destination":"target"}
L = grouped_src_dst.rename(columns=d)
unique_ips = pd.Index(L['source']
                  .append(L['target'])
                  .reset_index(drop=True).unique())
group_dict = {}
counter = 0
for ip in unique_ips:
breakout_ip = re.match("^(\d{1,3})\.(\d{1,3})\.(\d{1,3})\.(\d{1,3})$", ip)
if breakout_ip:
    net_id = '.'.join(breakout_ip.group(1,2,3))
    if net_id not in group_dict:
        counter += 1
        group_dict[net_id] = counter
    else:
        pass


temp_links_list = list(L.apply(lambda row: {"source": row['source'], "target": row['target'], "value": row['value']}, axis=1))

Answer 1

我认为列名count存在问题 - 缺少或' count'之类的空间。

#check columns names
print (grouped_src_dst.columns.tolist())
['count', 'source', 'target']

样品：

grouped_src_dst = pd.DataFrame({'source':['a','s','f'], 
                                'target':['b','n','m'], 
                                'count':[0,8,4]})
print (grouped_src_dst)
   count source target
0      0      a      b
1      8      s      n
2      4      f      m

f = lambda row: {"source": row['source'], "target": row['target'], "value": row['count']}
temp_links_list = list(grouped_src_dst.apply(f, axis=1))
print (temp_links_list)
[{'value': 0, 'source': 'a', 'target': 'b'}, 
 {'value': 8, 'source': 's', 'target': 'n'}, 
 {'value': 4, 'source': 'f', 'target': 'm'}]

更简单的解决方案是重命名列count并使用DataFrame.to_dict：

print (grouped_src_dst.rename(columns={'count':'value'}).to_dict(orient='records'))


[{'value': 0, 'source': 'a', 'target': 'b'}, 
 {'value': 8, 'source': 's', 'target': 'n'}, 
 {'value': 4, 'source': 'f', 'target': 'm'}]

EDIT1：

pcap_data = pd.read_csv('C:\packet_metadata.csv', index_col='No.')

grouped_src_dst = pcap_data.groupby(["Source","Destination"]).size().reset_index()
d = {0:'value', "Source":"source","Destination":"target"}
L = grouped_src_dst.rename(columns=d).to_dict(orient='records')

样品：

pcap_data = pd.DataFrame({'Source':list('aabbccdd'), 
                          'Destination':list('eertffff')})
print (pcap_data)
  Destination Source
0           e      a
1           e      a
2           r      b
3           t      b
4           f      c
5           f      c
6           f      d
7           f      d

grouped_src_dst = pcap_data.groupby(["Source","Destination"]).size().reset_index()
print (grouped_src_dst)
  Source Destination  0
0      a           e  2
1      b           r  1
2      b           t  1
3      c           f  2
4      d           f  2

d = {0:'value', "Source":"source","Destination":"target"}
L = grouped_src_dst.rename(columns=d).to_dict(orient='records')
print (L)
[{'value': 2, 'source': 'a', 'target': 'e'}, 
 {'value': 1, 'source': 'b', 'target': 'r'}, 
 {'value': 1, 'source': 'b', 'target': 't'}, 
 {'value': 2, 'source': 'c', 'target': 'f'}, 
 {'value': 2, 'source': 'd', 'target': 'f'}]

unique_ips = pd.Index(grouped_src_dst['Source']
                  .append(grouped_src_dst['Destination'])
                  .reset_index(drop=True).unique())

print (unique_ips)
Index(['a', 'b', 'c', 'd', 'e', 'r', 't', 'f'], dtype='object')


import numpy as np

unique_ips = np.unique(grouped_src_dst[['Source','Destination']].values.ravel()).tolist()
print (unique_ips)
['a', 'b', 'c', 'd', 'e', 'f', 'r', 't']

KeyError :('count'，'发生在索引0'）

1 个答案: