Dataset

Dataset: Loksabha 2019 Candidates General Information. (https://www.kaggle.com/datasets/themlphdstudent/lok-sabha-election-candidate-list-2004-to-2019)

# Importing required libraries
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.2     ✔ readr     2.1.4
## ✔ forcats   1.0.0     ✔ stringr   1.5.0
## ✔ ggplot2   3.4.3     ✔ tibble    3.2.1
## ✔ lubridate 1.9.2     ✔ tidyr     1.3.0
## ✔ 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(ggrepel)

Loading our Dataset

# Loading our dataset

data <-read.csv('C:\\Users\\bhush\\Downloads\\Coursework\\I 590 INTRO TO R\\datasets\\data_final\\LokSabha2019_xl.csv')
dim(data)
## [1] 7968   10

Creating different samples within our data

sub_samp <- 6

sub_samp_size <- nrow(data)/2

sub_samp_list <- list()

for (i in 1:sub_samp) {
  
  subsample_indices <- sample(1:nrow(data), sub_samp_size)
  subsample <- data[subsample_indices, ]
  

  sub_samp_list[[paste("df", i, sep = "_")]] <- subsample
}

We create 6 different sample having 50% data from our main data.

length(sub_samp_list)
## [1] 6
view(sub_samp_list[2])

Converting our samples to individual dataframes.

df_1 <- data.frame(sub_samp_list[1])
df_2 <- data.frame(sub_samp_list[2])
df_3 <- data.frame(sub_samp_list[3])
df_4 <- data.frame(sub_samp_list[4])
df_5 <- data.frame(sub_samp_list[5])
df_6 <- data.frame(sub_samp_list[6])

Selecting required columns.

df_1 <- df_1[,c("df_1.Candidate","df_1.Party","df_1.Criminal.Cases","df_1.Education","df_1.Age","df_1.Constituency","df_1.Total.Assets","df_1.Winner","df_1.Gender")]

df_2 <- df_2[,c("df_2.Candidate","df_2.Party","df_2.Criminal.Cases","df_2.Education","df_2.Age","df_2.Constituency","df_2.Total.Assets","df_2.Winner","df_2.Gender")]

df_3 <- df_3[,c("df_3.Candidate","df_3.Party","df_3.Criminal.Cases","df_3.Education","df_3.Age","df_3.Constituency","df_3.Total.Assets","df_3.Winner","df_3.Gender")]

df_4 <- df_4[,c("df_4.Candidate","df_4.Party","df_4.Criminal.Cases","df_4.Education","df_4.Age","df_4.Constituency","df_4.Total.Assets","df_4.Winner","df_4.Gender")]

df_5 <- df_5[,c("df_5.Candidate","df_5.Party","df_5.Criminal.Cases","df_5.Education","df_5.Age","df_5.Constituency","df_5.Total.Assets","df_5.Winner","df_5.Gender")]

df_6 <- df_6[,c("df_6.Candidate","df_6.Party","df_6.Criminal.Cases","df_6.Education","df_6.Age","df_6.Constituency","df_6.Total.Assets","df_6.Winner","df_6.Gender")]

Observing Age distribution in each of our sample.

ggplot(df_1, aes(x = df_1.Age)) +
  geom_histogram(binwidth = 5, fill = "blue") +
  labs(title = "Age Distribution", x = "Age", y = "Frequency")

ggplot(df_2, aes(x = df_2.Age)) +
  geom_histogram(binwidth = 5, fill = "blue") +
  labs(title = "Age Distribution", x = "Age", y = "Frequency")

ggplot(df_3, aes(x = df_3.Age)) +
  geom_histogram(binwidth = 5, fill = "blue") +
  labs(title = "Age Distribution", x = "Age", y = "Frequency")

ggplot(df_4, aes(x = df_4.Age)) +
  geom_histogram(binwidth = 5, fill = "blue") +
  labs(title = "Age Distribution", x = "Age", y = "Frequency")

ggplot(df_5, aes(x = df_5.Age)) +
  geom_histogram(binwidth = 5, fill = "blue") +
  labs(title = "Age Distribution", x = "Age", y = "Frequency")

ggplot(df_6, aes(x = df_6.Age)) +
  geom_histogram(binwidth = 5, fill = "blue") +
  labs(title = "Age Distribution", x = "Age", y = "Frequency")

Finding count of winners in each of our sample

Winner_count <- list()
m1 <- (sum(df_1$df_1.Winner == 1))
m2 <- (sum(df_2$df_2.Winner == 1))
m3 <- (sum(df_3$df_3.Winner == 1))
m4 <- (sum(df_4$df_4.Winner == 1))
m5 <- (sum(df_5$df_5.Winner == 1))
m6 <- (sum(df_6$df_6.Winner == 1))

Winner_count <- c(Winner_count,m1,m2,m3,m4,m5,m6)
print(Winner_count)
## [[1]]
## [1] 138
## 
## [[2]]
## [1] 149
## 
## [[3]]
## [1] 165
## 
## [[4]]
## [1] 161
## 
## [[5]]
## [1] 158
## 
## [[6]]
## [1] 177

Gender distribution in our samples

Gender <- df_1$df_1.Gender
ggplot(df_1, aes(x = df_1$df_1.Gender, fill = Gender)) +
  geom_bar() +
  geom_text(stat = "count", aes(label = after_stat(count)))+
  labs(title = "Gender Distribution", x = "Gender", y = "Frequency")

Gender2 <- df_2$df_2.Gender
ggplot(df_2, aes(x = df_2$df_2.Gender, fill = Gender2  )) +
  geom_bar() +
  geom_text(stat = "count", aes(label = after_stat(count)))+
  labs(title = "Gender Distribution", x = "Gender", y = "Frequency")

Gender3 <- df_3$df_3.Gender
ggplot(df_3, aes(x = df_3$df_3.Gender, fill = Gender3  )) +
  geom_bar() +
  geom_text(stat = "count", aes(label = after_stat(count)))+
  labs(title = "Gender Distribution", x = "Gender", y = "Frequency")

Gender4 <- df_4$df_4.Gender
ggplot(df_4, aes(x = df_4$df_4.Gender, fill = Gender4  )) +
  geom_bar() +
  geom_text(stat = "count", aes(label = after_stat(count)))+
  labs(title = "Gender Distribution", x = "Gender", y = "Frequency")

Gender5 <- df_5$df_5.Gender
ggplot(df_5, aes(x = df_5$df_5.Gender, fill = Gender5  )) +
  geom_bar() +
  geom_text(stat = "count", aes(label = after_stat(count)))+
  labs(title = "Gender Distribution", x = "Gender", y = "Frequency")

Gender6 <- df_6$df_6.Gender
ggplot(df_6, aes(x = df_6$df_6.Gender, fill = Gender6  )) +
  geom_bar() +
  geom_text(stat = "count", aes(label = after_stat(count)))+
  labs(title = "Gender Distribution", x = "Gender", y = "Frequency")

Finding candidates with no education.

ill6 <- df_6 |>
  group_by(df_6$Education) |>
  summarise(noOfCandidates = sum(df_6$df_6.Education == 'Illiterate'))

ill5 <- df_5 |>
  group_by(df_5$Education) |>
  summarise(noOfCandidates = sum(df_5$df_5.Education == 'Illiterate'))

ill4 <- df_4 |>
  group_by(df_4$Education) |>
  summarise(noOfCandidates = sum(df_4$df_4.Education == 'Illiterate'))

ill3 <- df_3 |>
  group_by(df_3$Education) |>
  summarise(noOfCandidates = sum(df_3$df_3.Education == 'Illiterate'))

ill2 <- df_2 |>
  group_by(df_2$Education) |>
  summarise(noOfCandidates = sum(df_2$df_2.Education == 'Illiterate'))

ill1 <- df_1 |>
  group_by(df_1$Education) |>
  summarise(noOfCandidates = sum(df_1$df_1.Education == 'Illiterate'))


edu_samples <- list(ill1,ill2,ill3,ill4,ill5,ill6)
count_ill <- data.frame(count_ = unlist(edu_samples))

ggplot(data = count_ill, aes(x = as.factor(count_))) +
  geom_bar(fill = "blue") +
  labs(title = "Candidates with having no formal education",
       x = "Sample number",
       y = "Count") +
  theme_minimal()