Skip to main content

How parse XML file Dataset using python

Parse XML file and Store data in CSV file for machine learning Algorithms.

import xml.etree.ElementTree as ET
import os
import csv
path = 'G:\salman'
with open('names.csv', 'a') as csvfile:
    fieldnames = ['pair_id', 'e1', 'e2', 'Sentance']
    writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
    for filename in os.listdir(path):
        if not filename.endswith('.xml'): continue
        fullname = os.path.join(path, filename)
        tree = ET.parse(fullname)
        lst = tree.findall('sentence')
        for i in lst:
            i_ = i.findall('pair')
            for elem in i_:
                if elem.attrib['ddi'] == 'true':
                    writer.writerow({'pair_id': elem.attrib['id'], 'e1': elem.attrib['e1'], 'e2': elem.attrib['e2'], 'Sentance': i.attrib["text"]})

Comments

Popular posts from this blog

IP camera access through python

In this tutorial we access IP camera using python. from urllib.request import Request, urlopen import base64 import cv2 import urllib import numpy as np url = 'http://192.168.0.104:8080/shot.jpg' username = '' password = '' while True:     proxy_handler = urllib.request.ProxyHandler({})     opener = urllib.request.build_opener(proxy_handler)     imgResp = Request(url, headers={"User-Agent": "Mozilla/5.0"})     base64string = base64.b64encode(('%s:%s' % (username, password)).encode("utf-8")).decode("utf-8")     imgResp.add_header("Authorization", "Basic %s" % base64string)     r = opener.open(imgResp)     imgNp = np.array(bytearray(r.read()), dtype=np.uint8)     img = cv2.imdecode(imgNp, -1)     cv2.imshow('test', img)     if ord('q') == cv2.waitKey(10):         exit(0)     # all the opencv processing is done here     cv2.imshow...