shravan-kuchkula

# Takes a list of status/twitter objects, extracts the text,
# cleans the text, calculates word frequencies and generates 
# a word cloud.
generateWordCloud <- function(tweets){
  
  #Get the text from the status/twitter object
  tweets_list <- sapply(tweets, function(x) x$getText())
  
  #Remove any weird symbols from the text
  tweets_list <- str_replace_all(tweets_list, "[^[:graph:]]", " ")

shravan-kuchkula

# Install a package and load it.
installRequiredPackages <- function(pkg){
  new.pkg <- pkg[!(pkg %in% installed.packages()[,"Package"])]
  if (length(new.pkg))
    install.packages(new.pkg, dependencies = TRUE)
  sapply(pkg, require, character.only = TRUE)
}

libs <- c("readr", "dplyr", "tidyr", "ggplot2",
          "magrittr", "markdown", "knitr", "Hmisc",

shravan-kuchkula

df <- data.frame(
  a = rnorm(10),
  b = rnorm(10),
  c = rnorm(10),
  d = rnorm(10)
 )

# Replace the 1:ncol(df) sequence
for (i in seq_along(df)) {
  print(median(df[[i]]))

shravan-kuchkula

# Define lists2dict()
def lists2dict(list1, list2):
    """Return a dictionary where list1 provides
    the keys and list2 provides the values."""

    # Zip lists: zipped_lists
    zipped_lists = zip(list1, list2)

    # Create a dictionary: rs_dict
    rs_dict = dict(zipped_lists)

shravan-kuchkula

# Import the pandas package
import pandas as pd

# Turn list of lists into list of dicts: list_of_dicts
# https://gist.github.com/shravan-kuchkula/6ca3054d5ec0549e1759d739b3d47513
list_of_dicts = [lists2dict(feature_names, sublist) for sublist in row_lists]

# Turn list of dicts into a dataframe: df
df = pd.DataFrame(list_of_dicts)

shravan-kuchkula

<?xml version="1.0" encoding="UTF-8"?>
<TLSales xmlns="http://tlsales.com/namespace" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://tlsales.com/namespace /tmp/msds7330/customer.xsd">
	<Address>
		<Name>Addr1</Name>
		<Street>123 Main St.</Street>
		<City>Seattle</City>
	</Address>
	<Customer OneTime="true" Regular="false" Senior="false" Discount="5">
		<First>John Q.</First>
		<Last>Public</Last>

shravan-kuchkula

# To insert the data in the people collection use 'insertOne.py' that I have given earlier

# Display the contents of the people collection
> db.people.find()
{ "_id" : ObjectId("59a36310fc2b2b3d843af1b6"), "name" : "Smith", "age" : 30, "profession" : "hacker" }
{ "_id" : ObjectId("59a36310fc2b2b3d843af1b7"), "name" : "Jones", "age" : 35, "profession" : "baker" }
{ "_id" : ObjectId("59a36310fc2b2b3d843af1b8"), "name" : "Alice" }
{ "_id" : ObjectId("59a36310fc2b2b3d843af1b9"), "name" : "Bob" }
{ "_id" : ObjectId("59a36310fc2b2b3d843af1ba"), "name" : "Charlie" }
{ "_id" : ObjectId("59a36310fc2b2b3d843af1bb"), "name" : "Dave" }

shravan-kuchkula

import pymongo

connection = pymongo.MongoClient("mongodb://localhost")

db = connection.school
people = db.people
people.drop()


def insert(peopleList):

shravan-kuchkula

import os
files = os.listdir(os.getcwd())
[os.replace(file, file.replace(" ", "_")) for file in files]

shravan-kuchkula

Conda is a powerful package manager and environment manager that you use with command line commands at the Anaconda Prompt for Windows, or in a Terminal window for macOS or Linux.

Common Commands:
a. To see a list of all your environments, type:
conda info --envs

$conda info --envs
# conda environments:
#
base                  *  /Users/Shravan/anaconda3