# Load necessary libraries
library(tidyverse)
#;-) ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
#;-) ✔ dplyr 1.1.4 ✔ readr 2.1.5
#;-) ✔ forcats 1.0.0 ✔ stringr 1.5.1
#;-) ✔ ggplot2 3.5.0 ✔ tibble 3.2.1
#;-) ✔ lubridate 1.9.3 ✔ tidyr 1.3.1
#;-) ✔ purrr 1.0.2
#;-) ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
#;-) ✖ dplyr::filter() masks stats::filter()
#;-) ✖ dplyr::lag() masks stats::lag()
#;-) ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(dlookr)
#;-) Registered S3 methods overwritten by 'dlookr':
#;-) method from
#;-) plot.transform scales
#;-) print.transform scales
#;-)
#;-) Attaching package: 'dlookr'
#;-)
#;-) The following object is masked from 'package:tidyr':
#;-)
#;-) extract
#;-)
#;-) The following object is masked from 'package:base':
#;-)
#;-) transform
library(ggplot2)
library(rrcov)
#;-) Loading required package: robustbase
#;-) Scalable Robust Estimators with High Breakdown Point (version 1.7-5)
# Set seed for reproducibility
set.seed(10)
# Generate sample data
n <- 1000 # Number of observations
# Age between 18 and 90
age <- sample(18:90, n, replace = TRUE)
# Introduce errors in age column
age[sample(1:n, 50)] <- "InvalidAge"
# Workclass: Private, Self-emp-not-inc, Self-emp-inc, Federal-gov, Local-gov, State-gov, Without-pay, Never-worked
workclass <- sample(c("Private", "Self-emp-not-inc", "Self-emp-inc", "Federal-gov", "Local-gov", "State-gov", "Without-pay", "Never-worked"), n, replace = TRUE)
# Introduce missing values in workclass column
workclass[sample(1:n, 50)] <- NA
# Education: Bachelors, Some-college, 11th, HS-grad, Prof-school, Assoc-acdm, Assoc-voc, 9th, 7th-8th, 12th, Masters, 1st-4th, 10th, Doctorate, 5th-6th, Preschool
education <- sample(c("Bachelors", "Some-college", "11th", "HS-grad", "Prof-school", "Assoc-acdm", "Assoc-voc", "9th", "7th-8th", "12th", "Masters", "1st-4th", "10th", "Doctorate", "5th-6th", "Preschool"), n, replace = TRUE)
# Introduce inconsistencies in education column
education[sample(1:n, 50)] <- "InvalidEducation"
# Education Number: 1-16
education_num <- sample(1:16, n, replace = TRUE)
# Marital Status: Married-civ-spouse, Divorced, Never-married, Separated, Widowed, Married-spouse-absent, Married-AF-spouse
marital_status <- sample(c("Married-civ-spouse", "Divorced", "Never-married", "Separated", "Widowed", "Married-spouse-absent", "Married-AF-spouse"), n, replace = TRUE)
# Introduce missing values in marital_status column
marital_status[sample(1:n, 50)] <- NA
# Occupation: Tech-support, Craft-repair, Other-service, Sales, Exec-managerial, Prof-specialty, Handlers-cleaners, Machine-op-inspct, Adm-clerical, Farming-fishing, Transport-moving, Priv-house-serv, Protective-serv, Armed-Forces
occupation <- sample(c("Tech-support", "Craft-repair", "Other-service", "Sales", "Exec-managerial", "Prof-specialty", "Handlers-cleaners", "Machine-op-inspct", "Adm-clerical", "Farming-fishing", "Transport-moving", "Priv-house-serv", "Protective-serv", "Armed-Forces"), n, replace = TRUE)
# Introduce errors in occupation column
occupation[sample(1:n, 50)] <- "InvalidOccupation"
# Relationship: Wife, Own-child, Husband, Not-in-family, Other-relative, Unmarried
relationship <- sample(c("Wife", "Own-child", "Husband", "Not-in-family", "Other-relative", "Unmarried"), n, replace = TRUE)
# Introduce missing values in relationship column
relationship[sample(1:n, 50)] <- NA
# Race: White, Asian-Pac-Islander, Amer-Indian-Eskimo, Other, Black
race <- sample(c("White", "Asian-Pac-Islander", "Amer-Indian-Eskimo", "Other", "Black"), n, replace = TRUE)
# Introduce inconsistencies in race column
race[sample(1:n, 50)] <- "InvalidRace"
# Sex: Female, Male
sex <- sample(c("Female", "Male"), n, replace = TRUE)
# Introduce missing values in sex column
sex[sample(1:n, 50)] <- NA
# Capital Gain: 0-99999
capital_gain <- sample(0:99999, n, replace = TRUE)
# Introduce errors in capital_gain column
capital_gain[sample(1:n, 50)] <- -999
# Capital Loss: 0-99999
capital_loss <- sample(0:99999, n, replace = TRUE)
# Introduce errors in capital_loss column
capital_loss[sample(1:n, 50)] <- -999
# Hours per week: 1-99
hours_per_week <- sample(1:99, n, replace = TRUE)
# Introduce missing values in hours_per_week column
hours_per_week[sample(1:n, 50)] <- NA
# Native country: United-States, Cambodia, England, ...
native_country <- sample(c("United-States", "Cambodia", "England", "Puerto-Rico", "Canada", "Germany", "Outlying-US(Guam-USVI-etc)", "India", "Japan", "Greece", "South", "China", "Cuba", "Iran", "Honduras", "Philippines", "Italy", "Poland", "Jamaica", "Vietnam", "Mexico", "Portugal", "Ireland", "France", "Dominican-Republic", "Laos", "Ecuador", "Taiwan", "Haiti", "Columbia", "Hungary", "Guatemala", "Nicaragua", "Scotland", "Thailand", "Yugoslavia", "El-Salvador", "Trinadad&Tobago", "Peru", "Hong", "Holand-Netherlands"), n, replace = TRUE)
# Introduce missing values in native_country column
native_country[sample(1:n, 50)] <- NA
# Income: <=50K, >50K
income <- sample(c("<=50K", ">50K"), n, replace = TRUE, prob = c(0.75, 0.25))
# Create dataframe
sample_dirty_dataset <- data.frame(age, workclass, education, education_num, marital_status, occupation, relationship, race, sex, capital_gain, capital_loss, hours_per_week, native_country, income)
# Print first few rows of the dataset
head(sample_dirty_dataset)
#;-) age workclass education education_num marital_status
#;-) 1 26 Federal-gov Assoc-acdm 2 Separated
#;-) 2 72 Private HS-grad 16 Married-civ-spouse
#;-) 3 89 Federal-gov HS-grad 14 Married-spouse-absent
#;-) 4 71 Without-pay 12th 7 <NA>
#;-) 5 56 Without-pay 5th-6th 5 Separated
#;-) 6 32 Self-emp-not-inc Assoc-acdm 4 Married-AF-spouse
#;-) occupation relationship race sex capital_gain
#;-) 1 Craft-repair Not-in-family Other Female 95729
#;-) 2 Machine-op-inspct Unmarried Asian-Pac-Islander Female 16548
#;-) 3 Armed-Forces Not-in-family Black Male 26865
#;-) 4 Machine-op-inspct Wife Asian-Pac-Islander Female 80193
#;-) 5 Priv-house-serv Other-relative Other Male 97828
#;-) 6 InvalidOccupation Husband Black Female 76074
#;-) capital_loss hours_per_week native_country income
#;-) 1 78233 71 Laos <=50K
#;-) 2 91089 81 Italy <=50K
#;-) 3 5355 51 Ecuador >50K
#;-) 4 32043 64 Taiwan >50K
#;-) 5 17804 47 Italy <=50K
#;-) 6 28165 31 China <=50K
summary(sample_dirty_dataset)
#;-) age workclass education education_num
#;-) Length:1000 Length:1000 Length:1000 Min. : 1.000
#;-) Class :character Class :character Class :character 1st Qu.: 5.000
#;-) Mode :character Mode :character Mode :character Median : 9.000
#;-) Mean : 8.697
#;-) 3rd Qu.:13.000
#;-) Max. :16.000
#;-)
#;-) marital_status occupation relationship race
#;-) Length:1000 Length:1000 Length:1000 Length:1000
#;-) Class :character Class :character Class :character Class :character
#;-) Mode :character Mode :character Mode :character Mode :character
#;-)
#;-)
#;-)
#;-)
#;-) sex capital_gain capital_loss hours_per_week
#;-) Length:1000 Min. : -999 Min. : -999 Min. : 1.00
#;-) Class :character 1st Qu.:21208 1st Qu.:21453 1st Qu.:23.25
#;-) Mode :character Median :45534 Median :46901 Median :49.00
#;-) Mean :47103 Mean :47848 Mean :49.75
#;-) 3rd Qu.:74322 3rd Qu.:74949 3rd Qu.:77.00
#;-) Max. :99692 Max. :99804 Max. :99.00
#;-) NA's :50
#;-) native_country income
#;-) Length:1000 Length:1000
#;-) Class :character Class :character
#;-) Mode :character Mode :character
#;-)
#;-)
#;-)
#;-)
Na_values_bool <- any(is.na(sample_dirty_dataset))#True
any(duplicated(sample_dirty_dataset))#No fully duplicated values
#;-) [1] FALSE
sum(is.na(sample_dirty_dataset))#300 missing values
#;-) [1] 300
nrow(sample_dirty_dataset)#1000
#;-) [1] 1000
sample_dirty_dataset <- na.omit(sample_dirty_dataset)
nrow(sample_dirty_dataset) #739
#;-) [1] 739
education_levels <- unique(sample_dirty_dataset$education)
#print(education_levels) #InvalidEducation
invalid_age_rows <- sample_dirty_dataset[sample_dirty_dataset$age == "InvalidAge", ]
print(invalid_age_rows)
#;-) age workclass education education_num
#;-) 9 InvalidAge Self-emp-inc Assoc-acdm 10
#;-) 21 InvalidAge Without-pay Doctorate 15
#;-) 68 InvalidAge Without-pay 5th-6th 6
#;-) 76 InvalidAge Never-worked 11th 16
#;-) 117 InvalidAge Never-worked 9th 6
#;-) 186 InvalidAge Never-worked 10th 15
#;-) 189 InvalidAge State-gov Masters 13
#;-) 230 InvalidAge Self-emp-not-inc Some-college 7
#;-) 232 InvalidAge Self-emp-inc Assoc-acdm 4
#;-) 288 InvalidAge State-gov HS-grad 14
#;-) 306 InvalidAge Local-gov Some-college 6
#;-) 321 InvalidAge Self-emp-not-inc 11th 10
#;-) 362 InvalidAge Private 10th 7
#;-) 380 InvalidAge Federal-gov 7th-8th 8
#;-) 406 InvalidAge Self-emp-inc Bachelors 1
#;-) 407 InvalidAge State-gov Bachelors 14
#;-) 449 InvalidAge Local-gov Assoc-voc 2
#;-) 450 InvalidAge Local-gov 9th 11
#;-) 480 InvalidAge Never-worked InvalidEducation 16
#;-) 503 InvalidAge Never-worked Doctorate 1
#;-) 573 InvalidAge Never-worked Doctorate 14
#;-) 575 InvalidAge Without-pay Doctorate 11
#;-) 589 InvalidAge State-gov 1st-4th 13
#;-) 594 InvalidAge Without-pay 12th 1
#;-) 609 InvalidAge Federal-gov 12th 3
#;-) 638 InvalidAge Private Preschool 13
#;-) 650 InvalidAge Self-emp-inc Bachelors 2
#;-) 661 InvalidAge Self-emp-inc InvalidEducation 6
#;-) 679 InvalidAge Private 9th 4
#;-) 760 InvalidAge Never-worked Preschool 13
#;-) 775 InvalidAge Private Some-college 14
#;-) 800 InvalidAge Self-emp-inc Assoc-acdm 11
#;-) 834 InvalidAge Local-gov Preschool 12
#;-) 842 InvalidAge Without-pay Doctorate 2
#;-) 876 InvalidAge Local-gov 11th 5
#;-) 888 InvalidAge Private HS-grad 14
#;-) 894 InvalidAge Local-gov 1st-4th 8
#;-) 960 InvalidAge Local-gov Preschool 12
#;-) marital_status occupation relationship race
#;-) 9 Married-civ-spouse Armed-Forces Husband Other
#;-) 21 Never-married Prof-specialty Unmarried White
#;-) 68 Separated Adm-clerical Not-in-family Asian-Pac-Islander
#;-) 76 Divorced Tech-support Not-in-family Black
#;-) 117 Married-AF-spouse Machine-op-inspct Not-in-family Amer-Indian-Eskimo
#;-) 186 Separated Farming-fishing Own-child Asian-Pac-Islander
#;-) 189 Never-married Protective-serv Husband Other
#;-) 230 Married-AF-spouse Handlers-cleaners Other-relative Asian-Pac-Islander
#;-) 232 Widowed Farming-fishing Not-in-family White
#;-) 288 Widowed Other-service Husband Asian-Pac-Islander
#;-) 306 Divorced InvalidOccupation Own-child White
#;-) 321 Married-AF-spouse Other-service Wife Other
#;-) 362 Married-civ-spouse Adm-clerical Unmarried Other
#;-) 380 Divorced Prof-specialty Unmarried Amer-Indian-Eskimo
#;-) 406 Divorced Adm-clerical Unmarried White
#;-) 407 Married-spouse-absent Exec-managerial Unmarried Black
#;-) 449 Married-civ-spouse Machine-op-inspct Husband Asian-Pac-Islander
#;-) 450 Separated Transport-moving Unmarried Asian-Pac-Islander
#;-) 480 Divorced Prof-specialty Wife White
#;-) 503 Never-married Protective-serv Own-child Other
#;-) 573 Married-civ-spouse Adm-clerical Own-child Other
#;-) 575 Married-spouse-absent Exec-managerial Not-in-family Black
#;-) 589 Married-spouse-absent Prof-specialty Wife Other
#;-) 594 Widowed Transport-moving Husband Asian-Pac-Islander
#;-) 609 Never-married Sales Other-relative Amer-Indian-Eskimo
#;-) 638 Separated Protective-serv Own-child Other
#;-) 650 Married-AF-spouse Tech-support Husband Amer-Indian-Eskimo
#;-) 661 Widowed Other-service Own-child Asian-Pac-Islander
#;-) 679 Separated Armed-Forces Husband Other
#;-) 760 Married-spouse-absent Protective-serv Own-child Other
#;-) 775 Widowed Craft-repair Wife Amer-Indian-Eskimo
#;-) 800 Married-AF-spouse Protective-serv Other-relative White
#;-) 834 Married-civ-spouse Armed-Forces Husband Other
#;-) 842 Married-spouse-absent Adm-clerical Wife Black
#;-) 876 Separated Priv-house-serv Other-relative Asian-Pac-Islander
#;-) 888 Married-civ-spouse Other-service Husband Asian-Pac-Islander
#;-) 894 Never-married Other-service Unmarried Amer-Indian-Eskimo
#;-) 960 Married-civ-spouse Protective-serv Own-child Amer-Indian-Eskimo
#;-) sex capital_gain capital_loss hours_per_week native_country
#;-) 9 Female 81715 79444 77 Canada
#;-) 21 Female 80917 65266 50 United-States
#;-) 68 Male 92339 72412 62 United-States
#;-) 76 Female 81398 78735 79 Mexico
#;-) 117 Female 72400 87507 91 Ecuador
#;-) 186 Female 15747 17284 3 Jamaica
#;-) 189 Female 65454 -999 96 Ireland
#;-) 230 Male 70358 16571 75 Iran
#;-) 232 Female 32326 84061 34 Hong
#;-) 288 Male 27253 27183 77 Hungary
#;-) 306 Male 77003 82147 24 Cambodia
#;-) 321 Female 62901 23094 92 Greece
#;-) 362 Female 87418 92143 27 Italy
#;-) 380 Male 86196 46053 74 Taiwan
#;-) 406 Female 91914 39157 57 Dominican-Republic
#;-) 407 Female 15968 66987 21 Honduras
#;-) 449 Male 90471 34417 49 Philippines
#;-) 450 Female -999 42299 15 Cambodia
#;-) 480 Male 97099 63859 18 England
#;-) 503 Male 81172 -999 86 Peru
#;-) 573 Female 84550 41330 43 Iran
#;-) 575 Male 34456 94416 56 Jamaica
#;-) 589 Male 92358 31468 79 Hong
#;-) 594 Female 44187 21023 12 Poland
#;-) 609 Female 62574 6803 93 Vietnam
#;-) 638 Male 49048 10309 85 Columbia
#;-) 650 Female 91992 68676 52 Ecuador
#;-) 661 Male -999 82727 71 Peru
#;-) 679 Male 52107 14519 45 Holand-Netherlands
#;-) 760 Female -999 48157 12 Puerto-Rico
#;-) 775 Male 43231 74697 36 United-States
#;-) 800 Male -999 23122 18 France
#;-) 834 Male 34425 76248 43 Nicaragua
#;-) 842 Male 11663 48569 86 Vietnam
#;-) 876 Male 826 11760 10 Columbia
#;-) 888 Female 44222 49219 43 Outlying-US(Guam-USVI-etc)
#;-) 894 Male 67234 18339 46 Italy
#;-) 960 Male 95340 56560 50 Germany
#;-) income
#;-) 9 <=50K
#;-) 21 <=50K
#;-) 68 >50K
#;-) 76 >50K
#;-) 117 <=50K
#;-) 186 <=50K
#;-) 189 <=50K
#;-) 230 <=50K
#;-) 232 <=50K
#;-) 288 >50K
#;-) 306 <=50K
#;-) 321 <=50K
#;-) 362 <=50K
#;-) 380 <=50K
#;-) 406 <=50K
#;-) 407 <=50K
#;-) 449 <=50K
#;-) 450 <=50K
#;-) 480 <=50K
#;-) 503 <=50K
#;-) 573 >50K
#;-) 575 >50K
#;-) 589 <=50K
#;-) 594 <=50K
#;-) 609 <=50K
#;-) 638 <=50K
#;-) 650 <=50K
#;-) 661 <=50K
#;-) 679 <=50K
#;-) 760 <=50K
#;-) 775 <=50K
#;-) 800 <=50K
#;-) 834 >50K
#;-) 842 >50K
#;-) 876 <=50K
#;-) 888 <=50K
#;-) 894 <=50K
#;-) 960 <=50K
median_age <- median(sample_dirty_dataset$age[sample_dirty_dataset$age != "InvalidAge"], na.rm = TRUE)
sample_dirty_dataset$age[sample_dirty_dataset$age == "InvalidAge"] <- median_age #imputing mean age values in InvalidAge place
sample_dirty_dataset$age <- as.integer(sample_dirty_dataset$age)
### HANDLING INVALID EDUCATION with bar plot and replacing it with most common education
invalid_education_counts <- table(sample_dirty_dataset$education == "InvalidEducation")
barplot(invalid_education_counts,
main = "Occurrences of InvalidEducation",
xlab = "InvalidEducation",
ylab = "Occurrences",
col = "blue",
ylim = c(0, max(invalid_education_counts)))
education_counts <- table(sample_dirty_dataset$education)
education_counts
#;-)
#;-) 10th 11th 12th 1st-4th
#;-) 42 50 46 39
#;-) 5th-6th 7th-8th 9th Assoc-acdm
#;-) 35 48 49 35
#;-) Assoc-voc Bachelors Doctorate HS-grad
#;-) 46 39 45 49
#;-) InvalidEducation Masters Preschool Prof-school
#;-) 36 57 42 34
#;-) Some-college
#;-) 47
sample_dirty_dataset$education[sample_dirty_dataset$education == "InvalidEducation"] <-
"11th"
### CALCULATING MEDIAN CAPITAL GAIN
median_gain_capital <- median(sample_dirty_dataset$capital_gain[sample_dirty_dataset$capital_gain != -999], na.rm = TRUE)
### REPLACING MEDIAN CAPITAL GAIN
sample_dirty_dataset$capital_gain[sample_dirty_dataset$capital_gain == -999] <-
median_gain_capital
### CALCULATING MEDIAN CAPITAL LOSS
median_loss_capital <- median(sample_dirty_dataset$capital_loss[sample_dirty_dataset$capital_loss != -999], na.rm = TRUE)
### REPLACING -999 CAPITAL LOSS with median capital loss
sample_dirty_dataset$capital_loss[sample_dirty_dataset$capital_loss == -999] <-
median_loss_capital
### HANDLING INVALID OCCUPATION
occupation_levels <- unique(sample_dirty_dataset$occupation)
#print(occupation_levels) #InvalidOccupation
occupation_count <- sum(sample_dirty_dataset$occupation == "InvalidOccupation", na.rm = TRUE)
#occupation_count #43
occupation_counts <- table(sample_dirty_dataset$occupation)
occupation_counts #most common Adm-clerical 66
#;-)
#;-) Adm-clerical Armed-Forces Craft-repair Exec-managerial
#;-) 66 47 54 54
#;-) Farming-fishing Handlers-cleaners InvalidOccupation Machine-op-inspct
#;-) 36 43 43 46
#;-) Other-service Priv-house-serv Prof-specialty Protective-serv
#;-) 54 53 62 53
#;-) Sales Tech-support Transport-moving
#;-) 44 40 44
### REPLACING INVALID OCCUPATION WITH MOST COMMON OCCUPATION
sample_dirty_dataset$occupation[sample_dirty_dataset$occupation == "InvalidOccupation"] <-
"Adm-clerical"
occupation_count <- sum(sample_dirty_dataset$occupation == "InvalidOccupation", na.rm = TRUE)
occupation_count #0
#;-) [1] 0
sample_dirty_dataset$capital_gain <- as.integer(sample_dirty_dataset$capital_gain)
### ZSCORE OUTLIERS
# Calculate z-scores
zscore <- abs(scale(sample_dirty_dataset$capital_gain))
# Create a data frame for plotting
zscore_df <- data.frame(Data_Point_Index = 1:length(zscore),
Z_Score = zscore)
# Plot z-scores as a scatter plot
plot(zscore_df$Data_Point_Index, zscore_df$Z_Score,
col = ifelse(zscore_df$Z_Score > 2, "darkgreen", "blue"),
pch = 19,
main = "Z-scores of Capital gain",
xlab = "Data Point Index", ylab = "Z-score",
ylim = c(0, max(zscore) + 1))
# Add horizontal line for threshold
abline(h = 2, col = "red", lty = 2)
# Add legend
legend("topright", legend = c("Z-score", "Threshold (2)", "Exceeding Threshold"),
col = c("blue", "red", "darkgreen"), lty = c(NA, 2, NA),
pch = c(19, NA, 19))
### BOX PLOT CAPITAL LOSS AND AGE
boxplot(sample_dirty_dataset$capital_loss)
boxplot(sample_dirty_dataset$capital_loss)$out
#;-) numeric(0)
boxplot(sample_dirty_dataset$age)
boxplot(sample_dirty_dataset$age)$out
#;-) numeric(0)
#NO OUTLIERS
### OUTLIERS hours_per_week
par(mfrow=c(2,2))
plot(covMcd(sample_dirty_dataset$hours_per_week))
### SUMMARY
summary(sample_dirty_dataset)
#;-) age workclass education education_num
#;-) Min. :18.00 Length:739 Length:739 Min. : 1.000
#;-) 1st Qu.:37.00 Class :character Class :character 1st Qu.: 5.000
#;-) Median :53.00 Mode :character Mode :character Median : 9.000
#;-) Mean :54.35 Mean : 8.829
#;-) 3rd Qu.:73.00 3rd Qu.:13.000
#;-) Max. :90.00 Max. :16.000
#;-) marital_status occupation relationship race
#;-) Length:739 Length:739 Length:739 Length:739
#;-) Class :character Class :character Class :character Class :character
#;-) Mode :character Mode :character Mode :character Mode :character
#;-)
#;-)
#;-)
#;-) sex capital_gain capital_loss hours_per_week
#;-) Length:739 Min. : 200 Min. : 70 Min. : 1.00
#;-) Class :character 1st Qu.:26138 1st Qu.:26396 1st Qu.:24.00
#;-) Mode :character Median :48885 Median :48779 Median :49.00
#;-) Mean :49756 Mean :50396 Mean :50.27
#;-) 3rd Qu.:74198 3rd Qu.:75590 3rd Qu.:77.00
#;-) Max. :99692 Max. :99727 Max. :99.00
#;-) native_country income
#;-) Length:739 Length:739
#;-) Class :character Class :character
#;-) Mode :character Mode :character
#;-)
#;-)
#;-)
head(sample_dirty_dataset)
#;-) age workclass education education_num marital_status
#;-) 1 26 Federal-gov Assoc-acdm 2 Separated
#;-) 2 72 Private HS-grad 16 Married-civ-spouse
#;-) 3 89 Federal-gov HS-grad 14 Married-spouse-absent
#;-) 5 56 Without-pay 5th-6th 5 Separated
#;-) 6 32 Self-emp-not-inc Assoc-acdm 4 Married-AF-spouse
#;-) 7 32 State-gov Some-college 16 Married-spouse-absent
#;-) occupation relationship race sex capital_gain
#;-) 1 Craft-repair Not-in-family Other Female 95729
#;-) 2 Machine-op-inspct Unmarried Asian-Pac-Islander Female 16548
#;-) 3 Armed-Forces Not-in-family Black Male 26865
#;-) 5 Priv-house-serv Other-relative Other Male 97828
#;-) 6 Adm-clerical Husband Black Female 76074
#;-) 7 Adm-clerical Husband Other Male 16495
#;-) capital_loss hours_per_week native_country income
#;-) 1 78233 71 Laos <=50K
#;-) 2 91089 81 Italy <=50K
#;-) 3 5355 51 Ecuador >50K
#;-) 5 17804 47 Italy <=50K
#;-) 6 28165 31 China <=50K
#;-) 7 63343 71 Iran >50K
#sample_dirty_dataset
### REPORTS
diagnose_web_report(sample_dirty_dataset)
#;-) processing file: diagnosis_temp.Rmd
#;-) output file: diagnosis_temp.knit.md
#;-) /Users/kacperpietka/Desktop/RStudio.app/Contents/Resources/app/quarto/bin/tools/pandoc +RTS -K512m -RTS diagnosis_temp.knit.md --to html4 --from markdown+autolink_bare_uris+tex_math_single_backslash --output /var/folders/g3/ldv1ypn57td1phswkr2h7yc80000gn/T//RtmpKRaIct/Diagnosis_Report.html --lua-filter /Library/Frameworks/R.framework/Versions/4.3-arm64/Resources/library/rmarkdown/rmarkdown/lua/pagebreak.lua --lua-filter /Library/Frameworks/R.framework/Versions/4.3-arm64/Resources/library/rmarkdown/rmarkdown/lua/latex-div.lua --embed-resources --standalone --variable bs3=TRUE --section-divs --template /Library/Frameworks/R.framework/Versions/4.3-arm64/Resources/library/rmarkdown/rmd/h/default.html --no-highlight --variable highlightjs=1 --variable theme=bootstrap --css /Library/Frameworks/R.framework/Versions/4.3-arm64/Resources/library/dlookr/resources/dlookr-bootstrap.css --mathjax --variable 'mathjax-url=https://mathjax.rstudio.com/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML' --include-in-header /var/folders/g3/ldv1ypn57td1phswkr2h7yc80000gn/T//RtmpKRaIct/rmarkdown-str66c17ed11537.html --variable code_folding=show --variable code_menu=1 --include-in-header header_temp.html --include-after-body /Library/Frameworks/R.framework/Versions/4.3-arm64/Resources/library/dlookr/resources/footer.html
#;-)
#;-) Output created: /var/folders/g3/ldv1ypn57td1phswkr2h7yc80000gn/T//RtmpKRaIct/Diagnosis_Report.html
eda_web_report(sample_dirty_dataset)
#;-) processing file: eda_temp.Rmd
#;-) Error in parse_block(g[-1], g[1], params.src, markdown_mode): Duplicate chunk label 'unnamed-chunk-1', which has been used for the chunk:
#;-) cat(sprintf("*Local `.Rprofile` detected at `%s`*", normalizePath(".Rprofile")))
transformation_paged_report(sample_dirty_dataset)
#;-) processing file: transformation_paged_temp.Rmd
#;-) Error in parse_block(g[-1], g[1], params.src, markdown_mode): Duplicate chunk label 'unnamed-chunk-1', which has been used for the chunk:
#;-) cat(sprintf("*Local `.Rprofile` detected at `%s`*", normalizePath(".Rprofile")))sessionInfo()
#;-) R version 4.3.3 (2024-02-29)
#;-) Platform: aarch64-apple-darwin20 (64-bit)
#;-) Running under: macOS Sonoma 14.4
#;-)
#;-) Matrix products: default
#;-) BLAS: /Library/Frameworks/R.framework/Versions/4.3-arm64/Resources/lib/libRblas.0.dylib
#;-) LAPACK: /Library/Frameworks/R.framework/Versions/4.3-arm64/Resources/lib/libRlapack.dylib; LAPACK version 3.11.0
#;-)
#;-) locale:
#;-) [1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8
#;-)
#;-) time zone: Europe/Warsaw
#;-) tzcode source: internal
#;-)
#;-) attached base packages:
#;-) [1] stats graphics grDevices utils datasets methods base
#;-)
#;-) other attached packages:
#;-) [1] htmltools_0.5.7 reactable_0.4.4 kableExtra_1.4.0 rrcov_1.7-5
#;-) [5] robustbase_0.99-2 dlookr_0.6.3 lubridate_1.9.3 forcats_1.0.0
#;-) [9] stringr_1.5.1 dplyr_1.1.4 purrr_1.0.2 readr_2.1.5
#;-) [13] tidyr_1.3.1 tibble_3.2.1 ggplot2_3.5.0 tidyverse_2.0.0
#;-)
#;-) loaded via a namespace (and not attached):
#;-) [1] tidyselect_1.2.0 viridisLite_0.4.2 farver_2.1.1
#;-) [4] fastmap_1.1.1 pagedown_0.20 fontquiver_0.2.1
#;-) [7] promises_1.2.1 reprex_2.1.0 digest_0.6.34
#;-) [10] timechange_0.3.0 mime_0.12 lifecycle_1.0.4
#;-) [13] ellipsis_0.3.2 gfonts_0.2.0 magrittr_2.0.3
#;-) [16] compiler_4.3.3 rlang_1.1.3 sass_0.4.8
#;-) [19] tools_4.3.3 utf8_1.2.4 yaml_2.3.8
#;-) [22] knitr_1.45 labeling_0.4.3 htmlwidgets_1.6.4
#;-) [25] curl_5.2.1 xml2_1.3.6 showtextdb_3.0
#;-) [28] httpcode_0.3.0 withr_3.0.0 grid_4.3.3
#;-) [31] pcaPP_2.0-4 stats4_4.3.3 fansi_1.0.6
#;-) [34] sysfonts_0.8.9 gdtools_0.3.7 xtable_1.8-4
#;-) [37] colorspace_2.1-0 extrafontdb_1.0 scales_1.3.0
#;-) [40] crul_1.4.0 cli_3.6.2 mvtnorm_1.2-4
#;-) [43] rmarkdown_2.26 crayon_1.5.2 generics_0.1.3
#;-) [46] rstudioapi_0.15.0 tzdb_0.4.0 cachem_1.0.8
#;-) [49] base64enc_0.1-3 vctrs_0.6.5 jsonlite_1.8.8
#;-) [52] fontBitstreamVera_0.1.1 bookdown_0.38 hms_1.1.3
#;-) [55] systemfonts_1.0.6 fontawesome_0.5.2 jquerylib_0.1.4
#;-) [58] glue_1.7.0 reactR_0.5.0 DEoptimR_1.1-3
#;-) [61] stringi_1.8.3 gtable_0.3.4 later_1.3.2
#;-) [64] extrafont_0.19 munsell_0.5.0 pillar_1.9.0
#;-) [67] showtext_0.9-7 R6_2.5.1 evaluate_0.23
#;-) [70] shiny_1.8.1 lattice_0.22-5 highr_0.10
#;-) [73] fontLiberation_0.1.0 httpuv_1.6.15 bslib_0.6.1
#;-) [76] hrbrthemes_0.8.7 Rcpp_1.0.12 svglite_2.1.3
#;-) [79] gridExtra_2.3 Rttf2pt1_1.3.12 xfun_0.42
#;-) [82] fs_1.6.3 pkgconfig_2.0.3