ahurriyetoglu

#!/usr/bin/python
#
# K-means clustering using Lloyd's algorithm in pure Python.
# Written by Lars Buitinck. This code is in the public domain.
#
# The main program runs the clustering algorithm on a bunch of text documents
# specified as command-line arguments. These documents are first converted to
# sparse vectors, represented as lists of (index, value) pairs.

from collections import defaultdict

ahurriyetoglu

>>> from pandas import DataFrame
>>> from sklearn.feature_extraction.text import CountVectorizer
>>> docs = ["You can catch more flies with honey than you can with vinegar.",
...         "You can lead a horse to water, but you can't make him drink."]
>>> vect = CountVectorizer(min_df=0., max_df=1.0)
>>> X = vect.fit_transform(docs)
>>> print(DataFrame(X.A, columns=vect.get_feature_names()).to_string())
   but  can  catch  drink  flies  him  honey  horse  lead  make  more  than  to  vinegar  water  with  you
0    0    2      1      0      1    0      1      0     0     0     1     1   0        1      0     2    2
1    1    2      0      1      0    1      0      1     1     1     0     0   1        0      1     0    2

ahurriyetoglu

1. General Background and Overview

• Probabilistic Data Structures for Web Analytics and Data Mining : A great overview of the space of probabilistic data structures and how they are used in approximation algorithm implementation.
• Models and Issues in Data Stream Systems
• Philippe Flajolet’s contribution to streaming algorithms : A presentation by Jérémie Lumbroso that visits some of the hostorical perspectives and how it all began with Flajolet
• Approximate Frequency Counts over Data Streams by Gurmeet Singh Manku & Rajeev Motwani : One of the early papers on the subject.
• [Methods for Finding Frequent Items in Data Streams](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.187.9800&rep

ahurriyetoglu

#!/usr/bin/env python

import numpy as np


def medfilt (x, k):
    """Apply a length-k median filter to a 1D array x.
    Boundaries are extended by repeating endpoints.
    """
    assert k % 2 == 1, "Median filter length must be odd."

ahurriyetoglu

# code to connect to twiqs.nl API
# Current IP address of twiqs.nl is: http://145.100.57.182
import requests

urlto_twiqsNL = "http://145.100.57.222/cgi-bin/twitter"

s = requests.Session()
r = s.post(urlto_twiqsNL, data={"NAME":user_name, "PASSWD":passwd})
print('Cookie Created')

ahurriyetoglu

import numpy as np
from math import pi, log
import pylab
from scipy import fft, ifft
from scipy.optimize import curve_fit

i = 10000
x = np.linspace(0, 3.5 * pi, i)
y = (0.3*np.sin(x) + np.sin(1.3 * x) + 0.9 * np.sin(4.2 * x) + 0.06 *
    np.random.randn(i))

ahurriyetoglu

def plot_correlogram(df,figsize=(20,20)):
    ''' Creat an n x n matrix of scatter plots for every
    combination of numeric columns in a dataframe'''

    cols = list(df.columns[df.dtypes=='float64'])
    n = len(cols)
    fig, ax = plt.subplots(n,n,figsize=figsize)
    for i,y in enumerate(cols):
        for j,x in enumerate(cols):
            if i != n-1:

ahurriyetoglu

#!flask/bin/python
from flask import Flask, jsonify, abort, request, make_response, url_for
from flask.ext.httpauth import HTTPBasicAuth

app = Flask(__name__, static_url_path = "")
auth = HTTPBasicAuth()

@auth.get_password
def get_password(username):
    if username == 'miguel':

ahurriyetoglu

import requests as r
import json
import datetime

# Docs: http://developer.nytimes.com/docs
# Try at: http://developer.nytimes.com/io-docs

srch_api_key = "Your key <check docs>"
keyphrase = 'anything_you_want'
srch_api_result = r.get("http://api.nytimes.com/svc/search/v2/articlesearch.json?q="+keyphrase+"&api-key="+srch_api_key)

ahurriyetoglu

# Docs: http://open-platform.theguardian.com/documentation/
import requests as r
import json

g_api_key = "Your API key" # limit is 12 calls per second.

keyterm = "Your Keyterm"

#from-date=1920-
g_articles_strt = r.get("http://content.guardianapis.com/search?q="+keyterm+"/politics&show-blocks=all&from-date=2015-01-01&api-key="+g_api_key)