Assignment1_Group6

library(readr)
mybabydata <- read_csv('~/Desktop/asgn1/temp/mybabydata.csv')

## Parsed with column specification:
## cols(
##   X1 = col_double(),
##   Name = col_character(),
##   Sex = col_character(),
##   Count = col_double(),
##   year = col_double()
## )

View(mybabydata)

Response to Question 1

##          name       x
## 9859     John 4600348
## 8990    James 4597517
## 16271  Robert 4420440
## 20105 William 3534717
## 13506 Michael 3450418
## 4447    David 3045297

##            name       x
## 22278      Mary 3980604
## 25859  Patricia 1535154
## 19869     Linda 1428668
## 2992    Barbara 1417994
## 9825  Elizabeth 1246461
## 14439  Jennifer 1241260

Our team interpreted this question to mean the following:

The most popular male baby name is [James] and the count is [5164280].

The most popular female baby name is [Mary] and the count is [4125675].

Response to Question 2

mybabydata_1950 = subset(mybabydata, mybabydata$year == 1950 & mybabydata$Sex == 'M')
head(mybabydata_1950)

## # A tibble: 6 x 5
##       X1 Name    Sex   Count  year
##    <dbl> <chr>   <chr> <dbl> <dbl>
## 1 468059 James   M     86224  1950
## 2 468060 Robert  M     83559  1950
## 3 468061 John    M     79424  1950
## 4 468062 Michael M     65144  1950
## 5 468063 David   M     60727  1950
## 6 468064 William M     60689  1950

mybabydata_1950_top5 = head(mybabydata_1950[order(mybabydata_1950$Count, decreasing = TRUE), ], 5)
mybabydata_1950_top5

## # A tibble: 5 x 5
##       X1 Name    Sex   Count  year
##    <dbl> <chr>   <chr> <dbl> <dbl>
## 1 468059 James   M     86224  1950
## 2 468060 Robert  M     83559  1950
## 3 468061 John    M     79424  1950
## 4 468062 Michael M     65144  1950
## 5 468063 David   M     60727  1950

barplot(mybabydata_1950_top5$Count, names = mybabydata_1950_top5$Name, main = 'Top Five Male Names in 1950', ylab = 'count')

barplot(mybabydata_1950_top5$Count, names = mybabydata_1950_top5$Name, main = 'Top Five Male Names in 1950', ylab = 'count', col = 'sky blue')

# The top five baby names for males for the year 1950 are shown in the plot.

Response to Question 3

mybabydata_1980 = subset(mybabydata, mybabydata$year == 1980 & mybabydata$Sex == 'F')
head(mybabydata_1980)

## # A tibble: 6 x 5
##       X1 Name     Sex   Count  year
##    <dbl> <chr>    <chr> <dbl> <dbl>
## 1 863845 Jennifer F     58375  1980
## 2 863846 Amanda   F     35821  1980
## 3 863847 Jessica  F     33921  1980
## 4 863848 Melissa  F     31636  1980
## 5 863849 Sarah    F     25755  1980
## 6 863850 Heather  F     19975  1980

mybabydata_1980_top5 = head(mybabydata_1980[order(mybabydata_1980$Count, decreasing = TRUE), ], 5)
mybabydata_1980_top5

## # A tibble: 5 x 5
##       X1 Name     Sex   Count  year
##    <dbl> <chr>    <chr> <dbl> <dbl>
## 1 863845 Jennifer F     58375  1980
## 2 863846 Amanda   F     35821  1980
## 3 863847 Jessica  F     33921  1980
## 4 863848 Melissa  F     31636  1980
## 5 863849 Sarah    F     25755  1980

barplot(mybabydata_1980_top5$Count, names = mybabydata_1980_top5$Name, main = 'Top Five Feale Names in 1980', ylab = 'count')

barplot(mybabydata_1980_top5$Count, names = mybabydata_1980_top5$Name, main = 'Top Five Feale Names in 1980', ylab = 'count', col = 'pink')

# The top five baby names for females for the year 1980 are shown in the plot.

Response to Question 4

mybabydata_top10 = head(mybabydata[order(mybabydata$Count, decreasing = TRUE), ], 10)
write.csv(mybabydata_top10, file = '~/Desktop/asgn1/temp/mybabydata_top10.csv')

The file with the top 10 baby names ever has been saved as a csv file named mostpop.csv in the current folder.