sudevschiz

#!/usr/bin/env python
# encoding: utf-8

import tweepy #https://github.com/tweepy/tweepy
import unicodecsv as csv

#Twitter API credentials
consumer_key = "ADD KEY BEFORE USE"
consumer_secret = "ADD SECRET BEFORE USE"
access_key = "ADD KEY BEFORE USE"

sudevschiz

library(streamR)
library(ROAuth)


setwd("~/tweet_miner_boy/")
# The following four lines assign the right values to the variables that
# are needed for the API call.
requestURL <- "https://api.twitter.com/oauth/request_token"
accessURL <- "https://api.twitter.com/oauth/access_token"
authURL <- "https://api.twitter.com/oauth/authorize"

sudevschiz

Create a new VM instance in Google Cloud Console Note that gcloud will already be installed in the system

gcloud init

Choose the service account of the VM Choose project

sudevschiz

sudo apt-get install python3-dev
virtualenv -p python3 venv
source venv/bin/activate
pip install SpeechRecognition
sudo apt-get install -qq python python-dev python-pip build-essential swig git libpulse-dev
pip install --upgrade pocketsphinx
git clone https://github.com/Uberi/speech_recognition.git
cd speech_recognition/
ls

sudevschiz

#install r-base
sudo apt-get -y install r-base

#install rstudio server 64-bit
sudo apt-get -y install gdebi-core
wget https://download2.rstudio.org/rstudio-server-1.0.44-amd64.deb
sudo gdebi rstudio-server*

sudevschiz

from collections import defaultdict

#words = "apple banana apple strawberry banana lemon"
file = open("input.txt")
words = file.read()
words = words.split()
result = defaultdict(int)
for word in words:
    result[word] += 1

sudevschiz

#!/usr/bin/env python
# coding=utf-8

# Calculating Protein Mass
# ========================
# 
# In a weighted alphabet, every symbol is assigned a positive real number called
# a weight. A string formed from a weighted alphabet is called a weighted
# string, and its weight is equal to the sum of the weights of its symbols.
# 

sudevschiz

import smtplib
from os.path import basename
from email.mime.application import MIMEApplication
from email.mime.multipart import MIMEMultipart
from email.mime.text import MIMEText
from email.utils import COMMASPACE, formatdate
import sys
import datetime
import json

sudevschiz

## Supposed you want to apply an operation to every element in a vector. Efficient way to do it in R is to use sapply / lapply

## Sample vector of 100 observation
x_vec <- rnorm(100)

## Need to find the absolute value of each element

x_abs <- sapply(x_vec,abs)

## The above implementation equivalent to doing x_abs <- abs(x_vec)

sudevschiz

## Function to split the dataframe
## 143 is just a default seed

splitdf <- function(dataframe, seed=143,splitper) {
  if (!is.null(seed)) set.seed(seed)
  index <- 1:nrow(dataframe)
  trainindex <- sample(index, (splitper/100)*trunc(length(index)))
  trainset <- dataframe[trainindex, ]
  testset <- dataframe[-trainindex, ]
  list(trainset=trainset,testset=testset)