yogsp

library(pacman)
pacman::p_load(data.table, plyr, dplyr, ggpubr)
forbes <- fread("forbes_celebrity_100_w_title.csv")
wiki <- fread("wikipedia_edits_forbes_celebrity_100.csv")
View(head(forbes))
View(head(wiki))
unique(forbes$Title)
unique(forbes$Career)
#Who has ranked number 1 the most number of times
aggforbes <-

yogsp

#Calculating Frequencies for Categorical Variables
groups <- c(rep("blue", 3990),
            rep("red", 4140),
            rep("orange", 1890),
            rep("green", 3770),
            rep("purple", 855))
#Create frequency tables
groups.t1 <- table(groups) #as table
groups.t1
groupsdf <- as.data.frame(groups.t1) #as data frame

yogsp

#BAR CHARTS for categorical variables
data(chickwts)
head(chickwts)
plot(chickwts$feed)
barplot(chickwts$feed) #This doesn't work
#Create a summary table so R can make a barplot
feeds <- table(chickwts$feed)
feeds
barplot(feeds)
#Arrange in descending order

yogsp

#Working with Colors
x <- c(12,4,21,17,13,9)
barplot(x) #all gray and basic
browseURL("http://www.stat.columbia.edu/~tzheng/files/Rcolor.pdf")
colors() #list of colors
barplot(x, col="moccasin")
barplot(x, col= colors()[633]) #index number of tomato3 from colors()
#RGB Hexcodes
#Can also use shortcut hexcodes (base 16), which are equivalent to
#RGB on the 0-255 scale, as FF in hex equals 255 in decimal

yogsp

> df           <- mtcars
> dimnames(mtcars)
[[1]]
 [1] "Mazda RX4"           "Mazda RX4 Wag"       "Datsun 710"          "Hornet 4 Drive"     
 [5] "Hornet Sportabout"   "Valiant"             "Duster 360"          "Merc 240D"          
 [9] "Merc 230"            "Merc 280"            "Merc 280C"           "Merc 450SE"         
[13] "Merc 450SL"          "Merc 450SLC"         "Cadillac Fleetwood"  "Lincoln Continental"
[17] "Chrysler Imperial"   "Fiat 128"            "Honda Civic"         "Toyota Corolla"     
[21] "Toyota Corona"       "Dodge Challenger"    "AMC Javelin"         "Camaro Z28"         
[25] "Pontiac Firebird"    "Fiat X1-9"           "Porsche 914-2"       "Lotus Europa"       

yogsp

> #RESHAPING DATA
> #similar to creating a contingency table which enables the user to aggregate data
> library(reshape)
> library(reshape2)
> #use "dcast" function to transform data from long to wide
> #Using dcast, we specify that we want the data to transform as salaries in the forst parameter
> wide_salaries <-
+   dcast(salaries, emp_no ~ year(ymd(from_date)), 
+         value.var = "salary")
> wide_salaries[1:3, 1:7]

yogsp

#use random package to create random numbers
import random
print ("Hello! What's your name?")
#let the user type in name and store it
name = input()
print ("Hello " +name+", can you guess the number i'm thinking of? It's between 1-20")
#Generate the random integer inside a range
secret = random.randint(1,20)
print ("It's between 1-20.")
#We only want to give a specific number (6) of tries to guess the number so use for loop

yogsp

class <- read.csv(file.choose())
attach(class)
head(class)
mean(Final)
#Calculate mean by ignoring NA values
mean(Final, na.rm = TRUE)
#Check which columns have NAs
summary(class)
#TakeHome and Final have NAs
list(Final)

yogsp

SELECT * FROM cd.bookings LIMIT 5;
SELECT * FROM cd.facilities LIMIT 5;
SELECT * FROM cd.members LIMIT 5;
SELECT facid, SUM(slots) AS total_slots
FROM cd.bookings
WHERE starttime >= '2012-09-01' and starttime <= '2012-10-01'
GROUP BY facid
ORDER BY SUM(slots);
SELECT facid, SUM(slots) AS "total_slots"
FROM cd.bookings

yogsp

> library(ggplot2)
> summary(diamonds)
     carat               cut        color        clarity          depth           table           price      
 Min.   :0.2000   Fair     : 1610   D: 6775   SI1    :13065   Min.   :43.00   Min.   :43.00   Min.   :  326  
 1st Qu.:0.4000   Good     : 4906   E: 9797   VS2    :12258   1st Qu.:61.00   1st Qu.:56.00   1st Qu.:  950  
 Median :0.7000   Very Good:12082   F: 9542   SI2    : 9194   Median :61.80   Median :57.00   Median : 2401  
 Mean   :0.7979   Premium  :13791   G:11292   VS1    : 8171   Mean   :61.75   Mean   :57.46   Mean   : 3933  
 3rd Qu.:1.0400   Ideal    :21551   H: 8304   VVS2   : 5066   3rd Qu.:62.50   3rd Qu.:59.00   3rd Qu.: 5324  
 Max.   :5.0100                     I: 5422   VVS1   : 3655   Max.   :79.00   Max.   :95.00   Max.   :18823  
                                    J: 2808   (Other): 2531