andrewbtran

View this code at http://livecoding.io/11153443

andrewbtran

from __future__ import unicode_literals

import requests
import json
import time
import codecs
import sys
UTF8Writer = codecs.getwriter('utf8')
sys.stdout = UTF8Writer(sys.stdout)

andrewbtran

library(dplyr)

ctmeet <- read.csv("meetup_groups.csv", quote = "", 
                   row.names = NULL, 
                   stringsAsFactors = FALSE)

# Adding column names
colnames(ctmeet) <- c("Area","Group","Created","Neighborhood","State","Category","Members","Who")

# Converting the Date group was created into a recognized format

andrewbtran

teams <- c(“Patriots”,”Red Sox”,”Celtics”)
losses <- c(5,13,21)
away <- c(TRUE,FALSE,TRUE)

sports <- data.frame(teams,losses,away)

andrewbtran

# Example for a Mac
setwd(“~/Downloads”)
# Example for a PC
setwd(“C:/User/Downloads”)

andrewbtran

# read in CSV file, assign it to a variable

earnings <- read.csv("Employee_Earnings_Report_2014.csv", stringsAsFactors=FALSE)

# Why the stringsAsFactors=FALSE? Because you're telling to interpret the text in the spreadsheet as a String, not a Factor
# Why is R obsessed with Factors? Blame statisticians. 

andrewbtran

# How many rows? 
nrow(earnings)

andrewbtran

# Look at the first five rows in the Console
head(earnings)

# Alternatively, to look at the last five rows
foot(earnings

andrewbtran

# Investigate the structure of the dataframe
str(earnings)

andrewbtran

#Change column to number format (first you have to strip out the $)
#The $ is a special character
earnings$TOTAL.EARNINGS <- gsub("\\$", "", earnings$TOTAL.EARNINGS)

#Function to change the format to numeric
earnings$TOTAL.EARNINGS <- as.numeric(earnings$TOTAL.EARNINGS)