fonnesbeck

TomAugspurger

hsurreal

with
    dau as (
        -- This part of the query can be pretty much anything.
        -- The only requirement is that it have three columns:
        --   dt, user_id, inc_amt
        -- Where dt is a date and user_id is some unique identifier for a user.
        -- Each dt-user_id pair should be unique in this table.
        -- inc_amt represents the amount of value that this user created on dt.
        -- The most common case is
        --   inc_amt = incremental revenue from the user on dt

AustinRochford

0asa

from pyspark import SparkConf, SparkContext
from sklearn.datasets import make_classification
from sklearn.ensemble import ExtraTreesClassifier
import pandas as pd
import numpy as np

conf = (SparkConf()
         .setMaster("local[*]")
         .setAppName("My app")
         .set("spark.executor.memory", "1g"))

GaelVaroquaux

'''
Non-parametric computation of entropy and mutual-information

Adapted by G Varoquaux for code created by R Brette, itself
from several papers (see in the code).

This code is maintained at https://github.com/mutualinfo/mutual_info 
Please download the latest code there, to have improvements and 
bug fixes.