week2_Asmt_Abhiram
library(readr)
library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(psych)# Example with full path
data <- read_delim("C:\\Users\\abhir\\OneDrive\\Documents\\luddy\\H510-Stats,R\\adult.csv", delim = ",")## Rows: 32561 Columns: 15
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (9): Work-Class, Education, Marital Status, Occupation, Relationship, Ra...
## dbl (6): Age, Fnl_Wgt, Education_Level, Capital_Gain, Capital_Loss, hrs_week
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.Use spec() with your data object
spec(data)
summary(data)
```r
# dimensions of your data
dim(data)## [1] 32561 15# data types of your columns
sapply(data, class)## Age Work-Class Fnl_Wgt Education Education_Level
## "numeric" "character" "numeric" "character" "numeric"
## Marital Status Occupation Relationship Race Sex
## "character" "character" "character" "character" "character"
## Capital_Gain Capital_Loss hrs_week Country Annual_pay
## "numeric" "numeric" "numeric" "character" "character"head(data)## # A tibble: 6 × 15
## Age `Work-Class` Fnl_Wgt Education Education_Level `Marital Status`
## <dbl> <chr> <dbl> <chr> <dbl> <chr>
## 1 39 " State-gov" 77516 " Bachelor… 13 " Never-married"
## 2 50 " Self-emp-not-inc" 83311 " Bachelor… 13 " Married-civ-s…
## 3 38 " Private" 215646 " HS-grad" 9 " Divorced"
## 4 53 " Private" 234721 " 11th" 7 " Married-civ-s…
## 5 28 " Private" 338409 " Bachelor… 13 " Married-civ-s…
## 6 37 " Private" 284582 " Masters" 14 " Married-civ-s…
## # ℹ 9 more variables: Occupation <chr>, Relationship <chr>, Race <chr>,
## # Sex <chr>, Capital_Gain <dbl>, Capital_Loss <dbl>, hrs_week <dbl>,
## # Country <chr>, Annual_pay <chr>table(data$Education)##
## 10th 11th 12th 1st-4th 5th-6th
## 933 1175 433 168 333
## 7th-8th 9th Assoc-acdm Assoc-voc Bachelors
## 646 514 1067 1382 5355
## Doctorate HS-grad Masters Preschool Prof-school
## 413 10501 1723 51 576
## Some-college
## 7291table(data$Occupation)##
## ? Adm-clerical Armed-Forces Craft-repair
## 1843 3770 9 4099
## Exec-managerial Farming-fishing Handlers-cleaners Machine-op-inspct
## 4066 994 1370 2002
## Other-service Priv-house-serv Prof-specialty Protective-serv
## 3295 149 4140 649
## Sales Tech-support Transport-moving
## 3650 928 1597# Get summary statistics using describe() function
describe(data)## vars n mean sd median trimmed mad min
## Age 1 32561 38.58 13.64 37 37.69 14.83 17
## Work-Class* 2 32561 4.87 1.46 5 4.96 0.00 1
## Fnl_Wgt 3 32561 189778.37 105549.98 178356 180802.36 88798.84 12285
## Education* 4 32561 11.30 3.87 12 11.81 2.97 1
## Education_Level 5 32561 10.08 2.57 10 10.19 1.48 1
## Marital Status* 6 32561 3.61 1.51 3 3.65 2.97 1
## Occupation* 7 32561 7.57 4.23 8 7.50 5.93 1
## Relationship* 8 32561 2.45 1.61 2 2.25 1.48 1
## Race* 9 32561 4.67 0.85 5 4.90 0.00 1
## Sex* 10 32561 1.67 0.47 2 1.71 0.00 1
## Capital_Gain 11 32561 1077.65 7385.29 0 0.00 0.00 0
## Capital_Loss 12 32561 87.30 402.96 0 0.00 0.00 0
## hrs_week 13 32561 40.44 12.35 40 40.55 4.45 1
## Country* 14 32561 37.72 7.82 40 40.00 0.00 1
## Annual_pay* 15 32561 1.24 0.43 1 1.18 0.00 1
## max range skew kurtosis se
## Age 90 73 0.56 -0.17 0.08
## Work-Class* 9 8 -0.75 1.68 0.01
## Fnl_Wgt 1484705 1472420 1.45 6.22 584.94
## Education* 16 15 -0.93 0.68 0.02
## Education_Level 16 15 -0.31 0.62 0.01
## Marital Status* 7 6 -0.01 -0.54 0.01
## Occupation* 15 14 0.11 -1.23 0.02
## Relationship* 6 5 0.79 -0.77 0.01
## Race* 5 4 -2.44 4.87 0.00
## Sex* 2 1 -0.72 -1.48 0.00
## Capital_Gain 99999 99999 11.95 154.77 40.93
## Capital_Loss 4356 4356 4.59 20.37 2.23
## hrs_week 99 98 0.23 2.92 0.07
## Country* 42 41 -3.66 12.53 0.04
## Annual_pay* 2 1 1.21 -0.53 0.00colnames(data)## [1] "Age" "Work-Class" "Fnl_Wgt" "Education"
## [5] "Education_Level" "Marital Status" "Occupation" "Relationship"
## [9] "Race" "Sex" "Capital_Gain" "Capital_Loss"
## [13] "hrs_week" "Country" "Annual_pay"str(data)## spc_tbl_ [32,561 × 15] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
## $ Age : num [1:32561] 39 50 38 53 28 37 49 52 31 42 ...
## $ Work-Class : chr [1:32561] " State-gov" " Self-emp-not-inc" " Private" " Private" ...
## $ Fnl_Wgt : num [1:32561] 77516 83311 215646 234721 338409 ...
## $ Education : chr [1:32561] " Bachelors" " Bachelors" " HS-grad" " 11th" ...
## $ Education_Level: num [1:32561] 13 13 9 7 13 14 5 9 14 13 ...
## $ Marital Status : chr [1:32561] " Never-married" " Married-civ-spouse" " Divorced" " Married-civ-spouse" ...
## $ Occupation : chr [1:32561] " Adm-clerical" " Exec-managerial" " Handlers-cleaners" " Handlers-cleaners" ...
## $ Relationship : chr [1:32561] " Not-in-family" " Husband" " Not-in-family" " Husband" ...
## $ Race : chr [1:32561] " White" " White" " White" " Black" ...
## $ Sex : chr [1:32561] " Male" " Male" " Male" " Male" ...
## $ Capital_Gain : num [1:32561] 2174 0 0 0 0 ...
## $ Capital_Loss : num [1:32561] 0 0 0 0 0 0 0 0 0 0 ...
## $ hrs_week : num [1:32561] 40 13 40 40 40 40 16 45 50 40 ...
## $ Country : chr [1:32561] " United-States" " United-States" " United-States" " United-States" ...
## $ Annual_pay : chr [1:32561] " <=50K" " <=50K" " <=50K" " <=50K" ...
## - attr(*, "spec")=
## .. cols(
## .. Age = col_double(),
## .. `Work-Class` = col_character(),
## .. Fnl_Wgt = col_double(),
## .. Education = col_character(),
## .. Education_Level = col_double(),
## .. `Marital Status` = col_character(),
## .. Occupation = col_character(),
## .. Relationship = col_character(),
## .. Race = col_character(),
## .. Sex = col_character(),
## .. Capital_Gain = col_double(),
## .. Capital_Loss = col_double(),
## .. hrs_week = col_double(),
## .. Country = col_character(),
## .. Annual_pay = col_character()
## .. )
## - attr(*, "problems")=<externalptr># Assuming 'data' is your data frame
# Example for a numeric column 'Age'
data$Age <- as.numeric(data$Age)
hist(data$Age, main = "Histogram of Age", xlab = "Age", col = "lightblue")
```r
# Install and load the ggplot2 package if not already installed
install.packages("ggplot2")## Installing package into 'C:/Users/abhir/AppData/Local/R/win-library/4.3'
## (as 'lib' is unspecified)## package 'ggplot2' successfully unpacked and MD5 sums checked
##
## The downloaded binary packages are in
## C:\Users\abhir\AppData\Local\Temp\RtmpwVSoIN\downloaded_packageslibrary(ggplot2)##
## Attaching package: 'ggplot2'## The following objects are masked from 'package:psych':
##
## %+%, alphaggplot(data, aes(x = Age)) +
geom_histogram(fill = "lightblue", color = "black", bins = 30) +
labs(title = "Histogram of Age", x = "Age")
# plot with 'Age' and 'Education_Level'
plot(data$Age, data$hrs_week, type = "l", col = "blue", xlab = "Age", ylab = "hrs_week")
ggplot(data, aes(x = Age)) +
geom_histogram(fill = "lightblue", color = "black", bins = 30) +
labs(title = "Histogram of Age", x = "Age")