maria-aguilera

<?xml version="1.0" encoding="UTF-8"?>
<module type="PYTHON_MODULE" version="4">
  <component name="NewModuleRootManager">
    <content url="file://$MODULE_DIR$" />
    <orderEntry type="inheritedJdk" />
    <orderEntry type="sourceFolder" forTests="false" />
  </component>
  <component name="TestRunnerService">
    <option name="PROJECT_TEST_RUNNER" value="Unittests" />
  </component>

maria-aguilera

#!/usr/bin/env python3

import xml.etree.ElementTree as ET
from pprint import pprint
import code

tree = ET.parse('biosample_result.xml')

def expand_blob(blob, attributes={}):
    '''

maria-aguilera

import xml.etree.ElementTree as ET
import json

def parse_element(element, namespace, indent=""):
    result = {}

    if element.attrib:
        result['attributes'] = element.attrib

    if element.text and element.text.strip():

maria-aguilera

from xml import sax


class XMLParser(sax.handler.ContentHandler):

    def __init__(self, keys=[], lists=[], *args, **kwargs):
        """
        :param keys: list of data keys have to be available in data
        :param lists: list of nodes have be represented as list

maria-aguilera

// XPath CheatSheet
// To test XPath in your Chrome Debugger: $x('/html/body')
// http://www.jittuu.com/2012/2/14/Testing-XPath-In-Chrome/


// 0. XPath Examples.
// More: http://xpath.alephzarro.com/content/cheatsheet.html


'//hr[@class="edge" and position()=1]'                // every first hr of 'edge' class

maria-aguilera

from urllib.request import urlopen
from xml.etree.ElementTree import parse

# Download the RSS feed and parse it
u = urlopen('http://planet.python.org/rss20.xml')
doc = parse(u)

# Extract and output tags of interest
for item in doc.iterfind('channel/item'):
    title = item.findtext('title')

maria-aguilera

import os
import re
import sys
import glob
import nltk
import gensim
import numpy as np
import pandas as pd
from tqdm import tqdm
from uuid import uuid4

maria-aguilera

import matplotlib
import seaborn as sns
import pandas as pd
from scipy.stats import zscore
from sklearn.preprocessing import MinMaxScaler
from sklearn.cluster import DBSCAN
from matplotlib import cm
from datetime import datetime
from dateutil import parser
import json

maria-aguilera

from sklearn.datasets import load_wine
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
data = pd.DataFrame(load_wine()["data"],columns=load_wine()["feature_names"])
data.head()

maria-aguilera

import numpy
import pandas
import matplotlib.pyplot as plt
import seaborn as sns
from ggplot import *
plt.style.use('ggplot')


def get_histogram_xy(data, bins=10):
    """Returns x,y coordinates for Histogram data.