mydata <- read.csv('CigarettesB.csv')

#1 Use the summary function to gain an overview of the data set. Then display the mean and median for at least two attributes.

summary(mydata)
##       X                 packs           price             income     
##  Length:46          Min.   :4.409   Min.   :-0.0326   Min.   :4.529  
##  Class :character   1st Qu.:4.712   1st Qu.: 0.1405   1st Qu.:4.679  
##  Mode  :character   Median :4.815   Median : 0.2002   Median :4.759  
##                     Mean   :4.848   Mean   : 0.2055   Mean   :4.775  
##                     3rd Qu.:4.984   3rd Qu.: 0.2735   3rd Qu.:4.853  
##                     Max.   :5.379   Max.   : 0.3640   Max.   :5.103
mean(mydata$price)
## [1] 0.2055087
median(mydata$price)
## [1] 0.200205
mean(mydata$income)
## [1] 4.775455
median(mydata$income)
## [1] 4.758505

#2 Create a new data frame with a subset of the columns and rows. Make sure to rename it.

df.mydata <- data.frame(mydata)
submydata <- subset(df.mydata, subset = price < 0.1)
submydata
##     X   packs    price  income
## 12 IN 5.11129  0.08992 4.72916
## 15 KY 5.37906 -0.03260 4.64937
## 23 MO 5.06430  0.08731 4.78189
## 36 SC 5.07801  0.07944 4.62549

#3 Create new column names for the new data frame.

submydata$age = c("18", "19", "45", "61")
submydata
##     X   packs    price  income age
## 12 IN 5.11129  0.08992 4.72916  18
## 15 KY 5.37906 -0.03260 4.64937  19
## 23 MO 5.06430  0.08731 4.78189  45
## 36 SC 5.07801  0.07944 4.62549  61

#4 Use the summary function to create an overview of your new data frame. The print the mean and median for the same two attributes. Please compare.

summary(submydata)
##       X                 packs           price              income     
##  Length:4           Min.   :5.064   Min.   :-0.03260   Min.   :4.625  
##  Class :character   1st Qu.:5.075   1st Qu.: 0.05143   1st Qu.:4.643  
##  Mode  :character   Median :5.095   Median : 0.08338   Median :4.689  
##                     Mean   :5.158   Mean   : 0.05602   Mean   :4.696  
##                     3rd Qu.:5.178   3rd Qu.: 0.08796   3rd Qu.:4.742  
##                     Max.   :5.379   Max.   : 0.08992   Max.   :4.782  
##      age           
##  Length:4          
##  Class :character  
##  Mode  :character  
##                    
##                    
## 
mean(submydata$price) #seeing an increase in the mean 
## [1] 0.0560175
median(submydata$price) #seeing an increase in the median
## [1] 0.083375
mean(submydata$income) #seeing a decrease in the mean
## [1] 4.696478
median(submydata$income) #seeing a decrease in the median
## [1] 4.689265

#5 For at least 3 values in a column please rename so that every value in that column is renamed.For example, suppose I have 20 values of the letter “e” in one column. Rename those values so that all 20 would show as “excellent”.

submydata[submydata == "IN"] <- "Indiana"
submydata[submydata == "KY"] <- "Kentucky"
submydata[submydata == "MO"] <- "Missouri"
submydata[submydata == "SC"] <- "South Carolina"
print(submydata)
##                 X   packs    price  income age
## 12        Indiana 5.11129  0.08992 4.72916  18
## 15       Kentucky 5.37906 -0.03260 4.64937  19
## 23       Missouri 5.06430  0.08731 4.78189  45
## 36 South Carolina 5.07801  0.07944 4.62549  61

#6 Display enough rows to see examples of all of steps 1-5 above.}

print(mydata)
##     X   packs    price  income
## 1  AL 4.96213  0.20487 4.64039
## 2  AZ 4.66312  0.16640 4.68389
## 3  AR 5.10709  0.23406 4.59435
## 4  CA 4.50449  0.36399 4.88147
## 5  CT 4.66983  0.32149 5.09472
## 6  DE 5.04705  0.21929 4.87087
## 7  DC 4.65637  0.28946 5.05960
## 8  FL 4.80081  0.28733 4.81155
## 9  GA 4.97974  0.12826 4.73299
## 10 ID 4.74902  0.17541 4.64307
## 11 IL 4.81445  0.24806 4.90387
## 12 IN 5.11129  0.08992 4.72916
## 13 IA 4.80857  0.24081 4.74211
## 14 KS 4.79263  0.21642 4.79613
## 15 KY 5.37906 -0.03260 4.64937
## 16 LA 4.98602  0.23856 4.61461
## 17 ME 4.98722  0.29106 4.75501
## 18 MD 4.77751  0.12575 4.94692
## 19 MA 4.73877  0.22613 4.99998
## 20 MI 4.94744  0.23067 4.80620
## 21 MN 4.69589  0.34297 4.81207
## 22 MS 4.93990  0.13638 4.52938
## 23 MO 5.06430  0.08731 4.78189
## 24 MT 4.73313  0.15303 4.70417
## 25 NE 4.77558  0.18907 4.79671
## 26 NV 4.96642  0.32304 4.83816
## 27 NH 5.10990  0.15852 5.00319
## 28 NJ 4.70633  0.30901 5.10268
## 29 NM 4.58107  0.16458 4.58202
## 30 NY 4.66496  0.34701 4.96075
## 31 ND 4.58237  0.18197 4.69163
## 32 OH 4.97952  0.12889 4.75875
## 33 OK 4.72720  0.19554 4.62730
## 34 PA 4.80363  0.22784 4.83516
## 35 RI 4.84693  0.30324 4.84670
## 36 SC 5.07801  0.07944 4.62549
## 37 SD 4.81545  0.13139 4.67747
## 38 TN 5.04939  0.15547 4.72525
## 39 TX 4.65398  0.28196 4.73437
## 40 UT 4.40859  0.19260 4.55586
## 41 VT 5.08799  0.18018 4.77578
## 42 VA 4.93065  0.11818 4.85490
## 43 WA 4.66134  0.35053 4.85645
## 44 WV 4.82454  0.12008 4.56859
## 45 WI 4.83026  0.22954 4.75826
## 46 WY 5.00087  0.10029 4.71169
print(submydata)
##                 X   packs    price  income age
## 12        Indiana 5.11129  0.08992 4.72916  18
## 15       Kentucky 5.37906 -0.03260 4.64937  19
## 23       Missouri 5.06430  0.08731 4.78189  45
## 36 South Carolina 5.07801  0.07944 4.62549  61

#7BONUS – place the original .csv in a github file and have R read from the link. This will be a very useful skill as you progress in your data science education and career.

gitHubData <- read.csv("https://raw.githubusercontent.com/arinolan/Nolan_Week-2-Assignment/main/CigarettesB.csv")