[python] xml parsing - xml 값 읽어오기

In [1]:

import pandas as pd

In [2]:

import numpy as np

In [3]:

import xml.etree.ElementTree as elemTree

In [4]:

xmlTree=elemTree.parse('C:/Users/folder')

In [5]:

# xml 파싱하기
root=xmlTree.getroot()
print(root)

<Element 'root' at 0x00000000081D5098>

In [6]:

week=root.find('data').text

In [7]:

MA_4=root.find('MA_4')

In [8]:

print(MA_4)

None

In [9]:

# 저장하는 변수 형태 지정 
results=[]
for data in root:
    week=int(data.find('week').text)
    sales=int(data.find('sales').text)
    if data.find('MA_4') is None:
        MA_4=""
    else:
        MA_4=np.float(data.find('MA_4').text)
    if data.find('y_hat_4') is None:
        y_hat_4=""
    else:
        y_hat_4=np.float(data.find('y_hat_4').text)

    if data.find('y_hat_5') is None:
        y_hat_5=""
    else:
        y_hat_5=np.float(data.find('y_hat_5').text)

    if data.find('MA_5') is None:
        MA_5=""
    else:
        MA_5=np.float(data.find('MA_5').text)

    results.append({"week":week,
                   "sales":sales,
                   "MA_4":MA_4,
                   "y_hat_4":y_hat_4,
                   "MA_5":MA_5,
                   "y_hat_5":y_hat_5})

In [10]:

results

Out[10]:

[{'week': 1,
  'sales': 60,
  'MA_4': '',
  'y_hat_4': '',
  'MA_5': '',
  'y_hat_5': ''},
 {'week': 2,
  'sales': 225,
  'MA_4': '',
  'y_hat_4': '',
  'MA_5': '',
  'y_hat_5': ''},
 {'week': 3,
  'sales': 168,
  'MA_4': '',
  'y_hat_4': '',
  'MA_5': '',
  'y_hat_5': ''},
 {'week': 4,
  'sales': 7,
  'MA_4': 115.0,
  'y_hat_4': '',
  'MA_5': '',
  'y_hat_5': ''},
 {'week': 5,
  'sales': 52,
  'MA_4': 113.0,
  'y_hat_4': 115.0,
  'MA_5': 102.4,
  'y_hat_5': ''},
 {'week': 6,
  'sales': 32,
  'MA_4': 64.75,
  'y_hat_4': 113.0,
  'MA_5': 96.8,
  'y_hat_5': 102.4},
 {'week': 7,
  'sales': 11,
  'MA_4': 25.5,
  'y_hat_4': 64.75,
  'MA_5': 54.0,
  'y_hat_5': 96.8},
 {'week': 8,
  'sales': 9,
  'MA_4': 26.0,
  'y_hat_4': 25.5,
  'MA_5': 22.2,
  'y_hat_5': 54.0},
 {'week': 9,
  'sales': 148,
  'MA_4': 50.0,
  'y_hat_4': 26.0,
  'MA_5': 50.4,
  'y_hat_5': 22.2},
 {'week': 10,
  'sales': 160,
  'MA_4': 82.0,
  'y_hat_4': 50.0,
  'MA_5': 72.0,
  'y_hat_5': 50.4},
 {'week': 11,
  'sales': 66,
  'MA_4': 95.75,
  'y_hat_4': 82.0,
  'MA_5': 78.8,
  'y_hat_5': 72.0},
 {'week': 12,
  'sales': 271,
  'MA_4': 161.25,
  'y_hat_4': 95.75,
  'MA_5': 130.8,
  'y_hat_5': 78.8},
 {'week': 13,
  'sales': 24,
  'MA_4': 130.25,
  'y_hat_4': 161.25,
  'MA_5': 133.8,
  'y_hat_5': 130.8},
 {'week': 14,
  'sales': 58,
  'MA_4': 104.75,
  'y_hat_4': 130.25,
  'MA_5': 115.8,
  'y_hat_5': 133.8},
 {'week': 15,
  'sales': 87,
  'MA_4': 110.0,
  'y_hat_4': 104.75,
  'MA_5': 101.2,
  'y_hat_5': 115.8},
 {'week': 16,
  'sales': 52,
  'MA_4': 55.25,
  'y_hat_4': 110.0,
  'MA_5': 98.4,
  'y_hat_5': 101.2},
 {'week': 17,
  'sales': 142,
  'MA_4': 84.75,
  'y_hat_4': 55.25,
  'MA_5': 72.6,
  'y_hat_5': 98.4},
 {'week': 18,
  'sales': 66,
  'MA_4': 86.75,
  'y_hat_4': 84.75,
  'MA_5': 81.0,
  'y_hat_5': 72.6},
 {'week': 19,
  'sales': 30,
  'MA_4': 72.5,
  'y_hat_4': 86.75,
  'MA_5': 75.4,
  'y_hat_5': 81.0},
 {'week': 20,
  'sales': 95,
  'MA_4': 83.25,
  'y_hat_4': 72.5,
  'MA_5': 77.0,
  'y_hat_5': 75.4}]

In [11]:

# 판다스를 이용하여 Data Frame으로 변경 
columns=["week","sales","MA_4","y_hat_4","MA_5","y_hat_5"]
xmlParsing=pd.DataFrame(results,columns=columns)

In [12]:

xmlParsing

Out[12]:

	week	sales	MA_4	y_hat_4	MA_5	y_hat_5
0	1	60
1	2	225
2	3	168
3	4	7	115
4	5	52	113	115	102.4
5	6	32	64.75	113	96.8	102.4
6	7	11	25.5	64.75	54	96.8
7	8	9	26	25.5	22.2	54
8	9	148	50	26	50.4	22.2
9	10	160	82	50	72	50.4
10	11	66	95.75	82	78.8	72
11	12	271	161.25	95.75	130.8	78.8
12	13	24	130.25	161.25	133.8	130.8
13	14	58	104.75	130.25	115.8	133.8
14	15	87	110	104.75	101.2	115.8
15	16	52	55.25	110	98.4	101.2
16	17	142	84.75	55.25	72.6	98.4
17	18	66	86.75	84.75	81	72.6
18	19	30	72.5	86.75	75.4	81
19	20	95	83.25	72.5	77	75.4

In [13]:

xdata=xmlParsing
df=xdata
df=xmlParsing

In [14]:

xdata.dtypes

Out[14]:

week        int64
sales       int64
MA_4       object
y_hat_4    object
MA_5       object
y_hat_5    object
dtype: object

In [15]:

xdata.shape

Out[15]:

(20, 6)

In [16]:

# index변경
xdata.set_index("week")

Out[16]:

	sales	MA_4	y_hat_4	MA_5	y_hat_5
week
1	60
2	225
3	168
4	7	115
5	52	113	115	102.4
6	32	64.75	113	96.8	102.4
7	11	25.5	64.75	54	96.8
8	9	26	25.5	22.2	54
9	148	50	26	50.4	22.2
10	160	82	50	72	50.4
11	66	95.75	82	78.8	72
12	271	161.25	95.75	130.8	78.8
13	24	130.25	161.25	133.8	130.8
14	58	104.75	130.25	115.8	133.8
15	87	110	104.75	101.2	115.8
16	52	55.25	110	98.4	101.2
17	142	84.75	55.25	72.6	98.4
18	66	86.75	84.75	81	72.6
19	30	72.5	86.75	75.4	81
20	95	83.25	72.5	77	75.4

In [17]:

xdata.dtypes
df=xdata

In [18]:

df.set_index("week")
df.dtypes

Out[18]:

week        int64
sales       int64
MA_4       object
y_hat_4    object
MA_5       object
y_hat_5    object
dtype: object

In [19]:

df['MA_5'].iloc[4]

Out[19]:

102.4

In [1]:

from IPython.core.display import display, HTML
display(HTML("<style>.container {width:90% !important;}</style>"))

In [ ]: