| { | |
| "metadata": { | |
| "name": "unpivoting-csv-pandas" | |
| }, | |
| "nbformat": 3, | |
| "nbformat_minor": 0, | |
| "worksheets": [ | |
| { | |
| "cells": [ | |
| { |
| import numpy as np | |
| import scipy | |
| import time | |
| import matplotlib.pyplot as plt | |
| print np.__file__ | |
| ax = plt.subplot(111) |
| import pandas as pd | |
| # http://blog.yhathq.com/static/misc/data/WineKMC.xlsx | |
| df_offers = pd.read_excel("./WineKMC.xlsx", sheetname=0) | |
| df_offers.columns = ["offer_id", "campaign", "varietal", "min_qty", "discount", "origin", "past_peak"] | |
| df_offers.head() | |
| df_transactions = pd.read_excel("./WineKMC.xlsx", sheetname=1) | |
| df_transactions.columns = ["customer_name", "offer_id"] | |
| df_transactions['n'] = 1 | |
| df_transactions.head() |
| import pymc, pymc.graph | |
| import matplotlib.pyplot as plt | |
| import numpy as np | |
| import sys | |
| channels = [ | |
| ('A', 2292.04, 9), | |
| ('B', 1276.85, 2), | |
| ('C', 139.59, 3), | |
| ('D', 954.98, 5) |
First, make sure you have command line tools installed:
xcode-select --installThen open Terminal.app and type:
curl https://gist.githubusercontent.com/DirtyF/5d2bde5c682101b7b5d90708ad333bf3/raw/fbc736fa1b50bd637929a315e6803df306c8bc8e/setup-rbenv.sh | bash
| """ | |
| Implementation of the beta-geometric/NBD (BG/NBD) model from '"Counting Your Customers" the Easy Way: An Alternative to | |
| the Pareto/NBD Model' (Fader, Hardie and Lee 2005) http://brucehardie.com/papers/018/fader_et_al_mksc_05.pdf and | |
| accompanying technical note http://www.brucehardie.com/notes/004/ | |
| Apache 2 License | |
| """ | |
| from math import log, exp | |
| import numpy as np |
| { | |
| "lines.linewidth": 2.0, | |
| "examples.download": true, | |
| "patch.linewidth": 0.5, | |
| "legend.fancybox": true, | |
| "axes.color_cycle": [ | |
| "#30a2da", | |
| "#fc4f30", | |
| "#e5ae38", | |
| "#6d904f", |
| # ============= | |
| # Introduction | |
| # ============= | |
| # I've been doing some data mining lately and specially looking into `Gradient | |
| # Boosting Trees <http://en.wikipedia.org/wiki/Gradient_boosting>`_ since it is | |
| # claimed that this is one of the techniques with best performance out of the | |
| # box. In order to have a better understanding of the technique I've reproduced | |
| # the example of section *10.14.1 California Housing* in the book `The Elements of Statistical Learning <http://www-stat.stanford.edu/~tibs/ElemStatLearn/>`_. | |
| # Each point of this dataset represents the house value of a property with some | |
| # attributes of that house. You can get the data and the description of those |
| <?php | |
| require 'tmhOAuth.php'; // Get it from: https://github.com/themattharris/tmhOAuth | |
| // Use the data from http://dev.twitter.com/apps to fill out this info | |
| // notice the slight name difference in the last two items) | |
| $connection = new tmhOAuth(array( | |
| 'consumer_key' => '', | |
| 'consumer_secret' => '', | |
| 'user_token' => '', //access token |
| from matplotlib import use | |
| from pylab import * | |
| from scipy.stats import beta, norm, uniform | |
| from random import random | |
| from numpy import * | |
| import numpy as np | |
| import os | |
| # Input data |