---
title: "Public Distributed system part-1"
output: 
  flexdashboard::flex_dashboard:
    orientation: columns
    vertical_layout: scroll
    theme: simplex
    social: menu
    source_code: embed
---

```{r setup, include=FALSE}
library(flexdashboard)
library(ggplot2)
library(lattice)
library(dplyr)
library(tidyverse)
library(cluster)
library(NbClust)
library(GGally)
library(rgl)
library(scatterplot3d)
library(useful)
```

Column {data-width=650}
-----------------------------------------------------------------------

### Objective :

```{r}
print("Predicting sugar corruption in public distribution system")
```

### Problem Statement :

```{r}
print("Predict the shop location which is performed sugar corruption.View the data in hierarchical view of location and clustering the people according to cards, district, office, shop and try to detect the corruption of sugar in ration shop.")

```

### Dataset Description :

```{r}
"Organization: Telangana State Civil Supplies Corporation Limited

The dataset about the FP Shop Distribution data in Telangana.

This dataset contains 16970 obs. of  13 variables:  
  
distCode : District Code

officeCode : Represents the office code

shopNo   : Representing Shop number

noOfRcs  : No.of Ration Cards

noOfTrans: No.of Transactions

riceAfsc : Rice to Anthtodaya Food Security Cards

riceFsc  : Rice to Food Security Card

riceAap  : Rice to Annapurna Card

sugar    : sugar quantity

totalAmount : total amount

otherShopTransCnt : Other shops transaction quantity"

```

Link to [Preprocessing the Data]

# Preprocessing the Data

Column {data-width=500}
-----------------------------------------------------------------------

### DataStructure

```{r}
data <- read.csv("/cloud/project/shop-wise-trans-detailsTelangana State Civil Supplies Distribution - FP Shop Wise Transactions Data_01-01-2021 to 31-01-2021.csv")
str(data)
```

### Dimension of dataset

```{r}
dim(data)

```

### Checking null values

```{r}
colSums(is.na(data)) 

```

### Summary of the data

```{r}
summary(data)
```


### Create new attribute using existing attribute
```{r}
distric_class = data.frame(
  distName=c("Adilabad","Bhadrdri Kothagudem","Hanumakonda","Hyderabad","Jagityal","Janagaon","Jayashankar Bhupalpalli","Jogulamba Gadwal","Kamareddy","Karimnagar","Khammam","Kumarambheem Asifabad","Mahabubabad","Mahbubnagar","Manchiryala","Medak","Medchal","Mulugu","Nagarkarnool","Nalgonda","Narayanpet","Nirmal","Nizamabad","Peddapalli","Rajanna Siricilla","Ranga Reddy","Sangareddy","Siddipet","Suryapet","Vikarabad","Wanaparthy","Warangal","Yadadri Bhuvanagiri" ),
  Classifi=c("Rural","Rural","Urban","Urban","Rural","Urban","Rural","Rural","Rural","Rural","Rural","Rural","Rural","Rural","Rural","Rural","Rural","Rural","Rural","Rural","Rural","Urban","Rural","Rural","Rural","Urban","Rural","Rural","Urban","Rural","Urban","Rural","Rural"))
factor(distric_class$distName)
#Merge the classification data with the main dataset based on district names
sub1=merge(data,distric_class,by='distName',,all.x=TRUE)
data=sub1
```

Link to [EDA]


# EDA
Column {data-width=500}
-----------------------------------------------------------------------
### Univariate Ananlysis


### Histogram of number of ration cards

```{r}
ggplot(data
       , aes(x = noOfRcs)) +
  
  geom_histogram(bins = 30) +
  labs(title = "Distribution of Number of Ration Cards", x = "Number of Ration Cards")
```
### Histogram of sub1.distCode

```{r}
ggplot(data, aes(x = distCode)) + 
  geom_histogram(binwidth = 50, fill = "skyblue", color = "black") +
  labs(title = "Histogram of distCode", x = "distCode", y = "Frequency")
```


### Histogram of noOfTrans

```{r}
ggplot(data, aes(x = noOfTrans)) + 
  geom_histogram(binwidth = 50, fill = "skyblue", color = "black") +
  labs(title = "Histogram of noOfTrans", x = "noOfTrans", y = "Frequency")
```


### Histogram of riceAfsc

```{r}
ggplot(data, aes(x = riceAfsc)) + 
  geom_histogram(binwidth = 50, fill = "skyblue", color = "black") +
  labs(title = "Histogram of riceAfsc", x = "riceAfsc", y = "Frequency")
```

Column {data-width=500}
-----------------------------------------------------------------------

### Histogram of riceFsc

```{r}
ggplot(data, aes(x = riceFsc)) + 
  geom_histogram(binwidth = 50, fill = "skyblue", color = "black") +
  labs(title = "Histogram of riceFsc", x = "riceFsc", y = "Frequency")
```


### Histogram of riceAap

```{r}
ggplot(data, aes(x = riceAap)) + 
  geom_histogram(binwidth = 50, fill = "skyblue", color = "black") +
  labs(title = "Histogram of riceAap", x = "riceAap", y = "Frequency")
```


### Histogram of sugar

```{r}
ggplot(data, aes(x = sugar)) + 
  geom_histogram(binwidth = 50, fill = "skyblue", color = "black") +
  labs(title = "Histogram of sugar", x = "sugar", y = "Frequency")
```


### Histogram of totalAmount

```{r}

ggplot(data, aes(x = totalAmount)) + 
  geom_histogram(binwidth = 50, fill = "skyblue", color = "black") +
  labs(title = "Histogram of totalAmount", x = "totalAmount", y = "Frequency")
```

### Histogram of otherShopTransCnt

```{r}
ggplot(data, aes(x = otherShopTransCnt)) + 
  geom_histogram(binwidth = 50, fill = "skyblue", color = "black") +
  labs(title = "Histogram of otherShopTransCnt", x = "otherShopTransCnt", y = "Frequency")
```

### Histogram of X

```{r}
histogram_10 <- ggplot(data, aes(x = X)) + 
  geom_histogram(binwidth = 50, fill = "skyblue", color = "black") +
  labs(title = "Histogram of X", x = "X", y = "Frequency")
```

```{r}
#bivariant analysis

# Bar plot of 'Classifi' vs. 'noOfTrans'
ggplot(data, aes(x = Classifi, fill = Classifi)) +
  geom_bar() +
  labs(x = "Classification", y = "Number of Transactions") +
  ggtitle("Number of Transactions by Classification")

# Bar plot of 'distCode' vs. 'riceAfsc'
ggplot(data, aes(x = distCode, y = riceAfsc)) +
  geom_bar(stat = "identity") +
  labs(x = "District Code", y = "Rice Amount") +
  ggtitle("Rice Amount by District Code")

# Bar plot of 'officeCode' vs. 'sugar'
ggplot(data, aes(x = officeCode, y = sugar)) +
  geom_bar(stat = "identity") +
  labs(x = "Office Code", y = "Sugar Amount") +
  ggtitle("Sugar Amount by Office Code")

# Example: Bar chart for 'officeCode' vs. 'totalAmount'
ggplot(data, aes(x = factor(officeCode), y = totalAmount)) +
  geom_bar(stat = "identity") +
  labs(x = "Office Code", y = "Total Amount") +
  ggtitle("Total Amount by Office Code")

# Example: Bar chart for 'distCode' vs. 'totalAmount'
ggplot(data, aes(x = factor(distCode), y = totalAmount)) +
  geom_bar(stat = "identity") +
  labs(x = "District Code", y = "Total Amount") +
  ggtitle("Total Amount by District Code")

# Example: Bar chart for 'Classifi' vs. 'totalAmount'
ggplot(data, aes(x = Classifi, y = totalAmount)) +
  geom_bar(stat = "identity") +
  labs(x = "Classification", y = "Total Amount") +
  ggtitle("Total Amount by Classification")

# Box plot of 'distCode' vs. 'totalAmount'
ggplot(data, aes(x = factor(distCode), y = totalAmount)) +
  geom_boxplot() +
  labs(x = "District Code", y = "Total Amount") +
  ggtitle("Box Plot of Total Amount by District Code")

# Box plot of 'officeCode' vs. 'totalAmount'
ggplot(data, aes(x = factor(officeCode), y = totalAmount)) +
  geom_boxplot() +
  labs(x = "Office Code", y = "Total Amount") +
  ggtitle("Box Plot of Total Amount by Office Code")

# Box plot of 'Classifi' vs. 'totalAmount'
ggplot(data, aes(x = factor(Classifi), y = totalAmount)) +
  geom_boxplot() +
  labs(x = "Classification", y = "Total Amount") +
  ggtitle("Box Plot of Total Amount by Classification")

#scatteplot
# Scatter plot of 'noOfRcs' vs. 'totalAmount'
ggplot(data, aes(x = noOfRcs, y = totalAmount)) +
  geom_point() +
  labs(x = "Number of Records", y = "Total Amount") +
  ggtitle("Scatter Plot: Number of Records vs. Total Amount")

# Scatter plot of 'noOfTrans' vs. 'totalAmount'
ggplot(data, aes(x = noOfTrans, y = totalAmount)) +
  geom_point() +
  labs(x = "Number of Transactions", y = "Total Amount") +
  ggtitle("Scatter Plot: Number of Transactions vs. Total Amount")

# Scatter plot of 'riceAfsc' vs. 'totalAmount'
ggplot(data, aes(x = riceAfsc, y = totalAmount)) +
  geom_point() +
  labs(x = "Rice AFSC", y = "Total Amount") +
  ggtitle("Scatter Plot: Rice AFSC vs. Total Amount")

# Scatter plot of 'riceFsc' vs. 'totalAmount'
ggplot(data, aes(x = riceFsc, y = totalAmount)) +
  geom_point() +
  labs(x = "Rice FSC", y = "Total Amount") +
  ggtitle("Scatter Plot: Rice FSC vs. Total Amount")

# Scatter plot of 'riceAap' vs. 'totalAmount'
ggplot(data, aes(x = riceAap, y = totalAmount)) +
  geom_point() +
  labs(x = "Rice AAP", y = "Total Amount") +
  ggtitle("Scatter Plot: Rice AAP vs. Total Amount")
```


```{r}
#correlation
# select specific columns for correlation analysis
selected_columns <- data[, c("sugar", "distCode", "noOfRcs", "noOfTrans", "riceAfsc", "totalAmount")]

# Calculate the correlation matrix
correlation_matrix <- cor(selected_columns)

# Print the correlation coefficients related to 'sub1.sugar'
print(correlation_matrix["sugar", ])

#testing
# Filter data for urban and rural areas

sugar_urban <- data[data$Classifi == "Urban", "sugar"]
sugar_rural <- data[data$Classifi == "Rural", "sugar"]

# Perform independent t-test
t_test_result <- t.test(sugar_urban, sugar_rural)

# Print the result
print(t_test_result)
```

Link to [EDA]