drorata

import re
from pyspark import SparkContext
print "-----------------===========================-----------------"
print "-----------------==========Staring==========-----------------"
print "-----------------===========================-----------------"
sc = SparkContext(appName = "simple app")

print "-----------------===========================-----------------"
print "-----------------==========Loaded file======-----------------"
print "-----------------===========================-----------------"

drorata

Cat,Country,Count
A,DE,0.4596065657
B,DE,0
C,US,0.3224789091
A,UK,0.4740651803
B,US,5
C,UK,0.6467712916
A,UK,0.4206986968
B,DE,0.647481787
C,UK,0.7009353881

drorata

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Assume you have events log with two event types `foo` and `bar`. The goal is to obtain a frequency bar plot of the events per some predescribed time interval."
   ]
  },
  {

drorata

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Toree on Mac\n",
    "\n",
    "## Installing\n",
    "\n",

drorata

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Assume you have events log with two event types `foo` and `bar`. The goal is to obtain a frequency bar plot of the events per some predescribed time interval."
   ]
  },
  {

drorata

{
  "basics": {
    "name": "Dr. Foo Bar",
    "label": "Programmer",
    "picture": "",
    "email": "drorata@gmail.com",
    "phone": "(912) 555-4321",
    "website": "http://richardhendricks.com",
    "summary": "Richard hails from Tulsa. He has earned degrees from the University of Oklahoma and Stanford. (Go Sooners and Cardinals!) Before starting Pied Piper, he worked for Hooli as a part time software developer. While his work focuses on applied information theory, mostly optimizing lossless compression schema of both the length-limited and adaptive variants, his non-work interests range widely, everything from quantum computing to chaos theory. He could tell you about it, but THAT would NOT be a “length-limited” conversation!",
    "location": {

drorata

import pandas as pd
import numpy as np
from sklearn import preprocessing

X = pd.DataFrame(np.random.normal(size=(50,4), scale=1, loc=3))
print(X.describe())
scalar = preprocessing.StandardScaler().fit(X)
print(pd.DataFrame(scalar.transform(X)).describe())

drorata

In [1]: import numpy as np

In [2]: def myfunc(a,b):
   ...:     if a > b:
   ...:         return a+b
   ...:     else:
   ...:         return float(a) / float(b)
   ...:

In [3]: vfunc = np.vectorize(myfunc)

drorata

drorata