amir-rahnama

import numpy as np

np.random.seed(0)

def cross_validation(X, y, cv_size=0.1):
    """Run cross validation on a numpy ndarray and return corresponding indices as well

        @param: X data in the form of numpy ndarray
        @param: y labels in the form of numpy ndarray
        @param: cv_size size of the test set

amir-rahnama

amir-rahnama

FROM python:3
MAINTAINER Amir Rahnama "[email protected]"

COPY . /app
WORKDIR /app

RUN pip install -r requirement.txt
RUN pip install --editable .

ENV FLASK_APP mini/app.py

amir-rahnama

"""A generic module to read data."""
import numpy
import collections
from tensorflow.python.framework import dtypes


class DataSet(object):
    """Dataset class object."""

    def __init__(self,

amir-rahnama

osrm:
  command: './start.sh Sweden http://download.geofabrik.de/europe/sweden-latest.osm.pbf'
  image: 'irony/osrm5:latest'
  ports:
    - '5000:5000'
  volumes_from:
    - osrm-data
osrm-data:
  image: 'irony/osrm5:latest'
  volumes:

amir-rahnama

es-master:
  image: 'elasticsearch:latest'
  command: 'elasticsearch --network.host=0.0.0.0 --node.master=true --cluster.name=escluster'
  restart: always
es-develop:
  image: 'elasticsearch:latest'
  command: 'elasticsearch --network.host=0.0.0.0 --cluster.name=escluster --discovery.zen.ping.unicast.hosts=es-master'
  deployment_strategy: high_availability
  links:
    - es-master

amir-rahnama

library(text2vec)
library(SnowballC)
library(doParallel)
library(microbenchmark)
library(tm)

con <- file("/Users/ara/dev/personal/r/final/en_US/en_US.blogs.txt", "r") 
blogs <- readLines(con, encoding = 'UTF-8')
close(con)

amir-rahnama

source("fast-ngrams.R")
con <- file("path_to_file", "r") 
data <- readLines(con, encoding = 'UTF-8')
close(con)

data <- clean(data)
onegram <- text_to_ngrams(decode(data), 1)
bigram <- text_to_ngrams(decode(data), 2)
trigram <- text_to_ngrams(decode(data, 3))

amir-rahnama

---
title: "Capstone First Milestone Report: Feature Engineering"
author: "Amir Hossein Rahnama"
date: "11 June 2016"
output: html_document
---
####Introduction
In this report, we are analyzing I have tried to start by showing a summary of all three data source from SwiftKey in terms of size. You can obtain the data with following code:

```{r eval=FALSE}

amir-rahnama

# pip install websocket-client
from pyspark import SparkContext
from pyspark.streaming import StreamingContext
from websocket import create_connection

def take_rdd_send_to_socket(time, rdd, num=1000):
    result = []
    taken = rdd.take(num + 1)
    print("-------------------------------------------")
    print("Time: %s" % time)