jobliz

from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.firefox.options import Options
from selenium.webdriver.firefox.firefox_binary import FirefoxBinary

# https://askubuntu.com/questions/870530/how-to-install-geckodriver-in-ubuntu
# https://stackoverflow.com/questions/25713824/setting-path-to-firefox-binary-on-windows-with-selenium-webdriver
# http://selenium-python.readthedocs.io/getting-started.html

binary = FirefoxBinary(PATH_TO_BINARY)

jobliz

# http://archive.ics.uci.edu/ml/datasets/online+retail

import csv
import sys
import time
import datetime
from sqlalchemy import *
from sqlalchemy import create_engine
from sqlalchemy import sql

jobliz

import xlrd
import xlwt
import numpy as np

def read_excel(filename, n=0):
    """Converts first sheet from an Excel file into an ndarray
    
    Parameters
    ----------
    filename : string

jobliz

# from http://funcall.blogspot.sg/2009/03/not-lisp-again.html

def deriv(f, dx=.0001):
    return lambda x: (f(x + dx) - f(x)) / dx

cube  = lambda x: x**3
d = deriv(cube)

for n in xrange(5):
    print n, d(n)

jobliz

import sys
import math
import numpy as np
from matplotlib import pyplot as plt

# https://en.wikipedia.org/wiki/Binomial_distribution
# k successes, n trials, p probability of success
def binomial_pmf(k, n, p):
    nk = math.factorial(n) / (math.factorial(k) * math.factorial(n-k))
    return nk * p**k * (1.0-p)**(n-k)

jobliz

import sys
import itertools
import numpy as np
from collections import Counter
from matplotlib import pyplot as plt

def dice_prob(n):
    sides = [(1,2,3,4,5,6) for x in xrange(n)]
    combined = itertools.product(*sides)
    sums = [sum(i) for i in combined]

jobliz

demand_dist = (0.30, 0.45, 0.25) # [0]high, [1]medium, [2]low
positions   = (  36,   48,   60,   72,   84,   96)
high_demand = (0.05, 0.10, 0.25, 0.30, 0.20, 0.10)
med_demand  = (0.10, 0.20, 0.30, 0.25, 0.10, 0.05)
low_demand  = (0.15, 0.25, 0.35, 0.15, 0.05, 0.05)

demand_type = position_generator(demand_dist)

# be careful with order!
demand_amount = [

jobliz

def profit(supply, demand, sale_price=0.40, production_cost=0.25, welfare_price=0.10, lost=0.15):
    operative_cost = production_cost * supply 
    if supply >= demand:    
        excedent = supply - demand
        sale_income = demand * sale_price
        welfare_gain = excedent * welfare_price
        result = sale_income + welfare_gain - operative_cost
    else:
        not_baked_loss = lost * (demand - supply) 
        sale_income = supply * sale_price

jobliz

heights   = ["high", "medium", "short"]
dist      = [0.2, 0.6, 0.2]
generator = position_generator(dist)

n = 10000
count = 0
high = 0
med = 0
low = 0

jobliz

import csv
import pylab as p

data = [r for r in csv.reader(open('piratebay.csv', 'rb'))]
def categoryratio(c):
    return sum([ int(r[3]) for r in data if r[1][0] == str(c) ])

# Adapted from # http://scienceoss.com/bar-plot-with-custom-axis-labels/

fig = p.figure()