elyase

import time

def timeit(f):

    def timed(*args, **kwargs):
        start = time.clock()
        for _ in range(100):
            f(*args, **kwargs)
        end = time.clock()
        return end - start

elyase

{'INTEGER': 12, 'HTMLTAG': 10, 'int': 4, 'formattedsize': 4, 'sizeindex': 4, 'string': 3, 
'sizes': 3, 'decimals': 3, 'size': 2, 'code': 2, 'blockquote': 2, 'permitted': 2, 'specifiers': 2, 
'default': 2, 'parameter': 2, 'FUNCTIONCALL': 2, 'CODE': 1, 'private': 1, 'eb': 1, 'gt': 1, 
'gb': 1, 'error': 1, 'application': 1, 'format': 1, 'desktop': 1, 'pb': 1, 'formatsizebinary': 1, 
'lt': 1, 'tb': 1, 'math': 1, 'return': 1, 'kb': 1, 'yb': 1, 'tostring': 1, 'zb': 1, 'amp': 1, 
'mb': 1, 'bytes': 1, 'length': 1, 'double': 1}


['default',
 'parameter',

elyase

{
 "metadata": {
  "name": ""
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {

elyase

import csv

with open('companies.csv', 'wb') as csvfile:
    csv.writer(csvfile, delimiter=',').writerows(row_gen)

elyase

row_gen = ( [td.text(), td.next().text()]                # left, right element
          for table in d('.borderless').items()
          for td in table('td:nth-child(1)').items()   # left column
          if table('th:first').text() == 'NUANS Reports & Preliminary Searches' and 
             td.next().text() in ('Active', 'Inactive') )

10 loops, best of 3: 172 ms per loop

elyase

l = []
for th in d.items('.borderless td:nth-child(1)'):
    left = th.text()
    right = th.next().text()
    tr = th.parent()
    tbody = tr.parent()
    title = tbody('th:first').text()    # first element
    if title == 'NUANS Reports & Preliminary Searches' and right in ['Active', 'Inactive']:
        l.append([left, right])

elyase

from pyquery import PyQuery as pq

url = 'https://www.nuans.com/RTS2/en/jur_codes-codes_jur_en.cgi#Example_of_report_layouts'
d = pq(url)

elyase

from sklearn.feature_extraction.text import CountVectorizer
import numpy as np

def tokenizer(s):
    width = 7
    return [s[i:i+width] for i in range(len(s)-width+1)]

def count_chunks(sequence_list):
    vectorizer = CountVectorizer(tokenizer=tokenizer)
    X = vectorizer.fit_transform(sequence_list)

elyase

# Split the dataset in two equal parts
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.5, random_state=0)

# Set the parameters by cross-validation
tuned_parameters = [{'kernel': ['rbf'], 'gamma': [1e-3, 1e-4],
                     'C': [1, 10, 100, 1000]},
                    {'kernel': ['linear'], 'C': [1, 10, 100, 1000]}]
model = GridSearchCV(SVC(C=1), tuned_parameters, cv=5, scoring=score)
model.fit(X_train, y_train)

elyase

function svmStruct = best_svm_classifer_rbf(cdata,labels)


%Write a function called crossfun to calculate the predicted classification yfit from a test vector 
%xtest, when the SVM is trained on a sample xtrain that has classification ytrain.

function yfit = crossfun(xtrain,ytrain,xtest, rbf_sigma, boxconstraint) 

% Train the model on xtrain, ytrain, 
% and get predictions of class of xtest and output it as yfit