Scribd
Upload
122 views4 pages

Data Wrangling (Data Preprocessing)

The document discusses data wrangling and preprocessing. It generates three synthetic datasets - a sales dataset with 150 rows, a customer dataset with 200 rows, and an inventory dataset with 200 rows. Each dataset contains randomly generated data along with missing values and outliers introduced. The datasets are exported to CSV files. Next steps mentioned are merging the datasets, checking the structure of the combined data, generating summary statistics, and scanning for missing values. However, the code blocks provided are empty and explanations for each step are missing.

Uploaded by

Siddharth Raul
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
122 views4 pages

Data Wrangling (Data Preprocessing)

The document discusses data wrangling and preprocessing. It generates three synthetic datasets - a sales dataset with 150 rows, a customer dataset with 200 rows, and an inventory dataset with 200 rows. Each dataset contains randomly generated data along with missing values and outliers introduced. The datasets are exported to CSV files. Next steps mentioned are merging the datasets, checking the structure of the combined data, generating summary statistics, and scanning for missing values. However, the code blocks provided are empty and explanations for each step are missing.

Uploaded by

Siddharth Raul
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 4

9/18/23, 7:29 PM Data Wrangling (Data Preprocessing)

Data Wrangling (Data Preprocessing) Code

Mid-term assessment
Siddharth Dinkar Raul (s4015125)
18-09-2023

Setup
Hide

# Load the necessary packages required to reproduce the report.


library(tibble)
library(dplyr)
library(lubridate)

Data generation
Hide

file:///C:/Users/SIDDHARTH/Downloads/Data Wrangling 2/Mid-term-Assessment-Rmarkdown-Template.nb.html 1/4


9/18/23, 7:29 PM Data Wrangling (Data Preprocessing)

# Data generation, provide your R codes

# Generating date range


start_date <- as.Date("2023-01-01")
end_date <- as.Date("2023-12-31")
date_range <- seq(start_date, end_date, by = "days")

# Setting the seed


set.seed(285)

# Creating the first dataset ( Sales dataset)


sales_data <- tibble(
date = sample(date_range, 150, replace = TRUE),
product_id = sample(1:200, 150, replace = TRUE),
product_name = as.character(replicate(150, paste(sample(words, 2), collapse = " "))),
quantity_sold = as.numeric(sample(1:20, 150, replace = TRUE)),
price = as.numeric(runif(150, min = 50, max = 500)),
customer_id = as.factor(sample(1:500, 150, replace = TRUE)),
store_id = as.factor(sample(1:5, 150, replace = TRUE)) # Common variable "store_id"
)

# Introducing the missing values in the "price" column (approximately 5%)

sales_data[sample(1:150, 5), "price"] <- NA

# Introducing outliers

sales_data[sample(1:150, 5), "quantity_sold"] <- sales_data[sample(1:150, 5), "quantity_sol


d"] * 10
sales_data[sample(1:150, 5), "price"] <- sales_data[sample(1:150, 5), "price"] * 2

# Exporting to CSV
write.csv(sales_data, "sales_data.csv", row.names = FALSE)

# Creating second dataset ( Customer Dataset)

set.seed(286)

customer_data <- tibble(


customer_id = as.factor(1:200),
customer_name = as.character(replicate(200, paste(sample(LETTERS, 5), collapse = ""))),
email = as.character(paste0(replicate(200, paste(sample(letters, 5), collapse = "")), "@exa
mple.com")),
total_purchases = as.numeric(sample(100:1000, 200, replace = TRUE)),
is_member = as.logical(sample(c(TRUE, FALSE), 200, replace = TRUE, prob = c(0.6, 0.4))),
store_id = as.factor(sample(1:5, 200, replace = TRUE)) # Common variable "store_id"
)

# Introduce missing values in the "email" column (approximately 5%)


customer_data[sample(1:200, 10), "email"] <- NA

# Export to CSV
write.csv(customer_data, "customer_data.csv", row.names = FALSE)

file:///C:/Users/SIDDHARTH/Downloads/Data Wrangling 2/Mid-term-Assessment-Rmarkdown-Template.nb.html 2/4


9/18/23, 7:29 PM Data Wrangling (Data Preprocessing)

# Creating second dataset ( Customer Dataset)

# Create an inventory dataset


set.seed(789)
inventory_data <- tibble(
product_id = as.factor(1:200),
product_name = as.character(replicate(200, paste(sample(words, 2), collapse = " "))),
stock_level = as.numeric(sample(1:100, 200, replace = TRUE)),
supplier = as.character(replicate(200, paste(sample(LETTERS, 3), collapse = ""))),
cost_price = as.numeric(runif(200, min = 50, max = 200)),
selling_price = as.numeric(runif(200, min = 100, max = 500)),
store_id = as.factor(sample(1:5, 200, replace = TRUE)) # Common variable "store_id"
)

# Introduce missing values in the "stock_level" column (approximately 5%)


inventory_data[sample(1:200, 10), "stock_level"] <- NA

# Introduce outliers
inventory_data[sample(1:200, 5), "cost_price"] <- inventory_data[sample(1:200, 5), "cost_pric
e"] * 0.5
inventory_data[sample(1:200, 5), "selling_price"] <- inventory_data[sample(1:200, 5), "sellin
g_price"] * 2

# Export to CSV
write.csv(inventory_data, "inventory_data.csv", row.names = FALSE)

Provide explanations here.

Merging data sets


Hide

# Merge your synthetic data sets, provide R codes here.

Provide explanations here.

Checking structure of combined data


Hide

# Check structure of combined data and perform all necessary data type conversions, provide R
codes here.

Provide explanations here.

Generate summary statistics


Hide

# Generate summary statistics, provide R codes here.

file:///C:/Users/SIDDHARTH/Downloads/Data Wrangling 2/Mid-term-Assessment-Rmarkdown-Template.nb.html 3/4


9/18/23, 7:29 PM Data Wrangling (Data Preprocessing)

Provide explanations here.

Scanning data
Hide

# Scan variables for missing values, provide R codes here.

Provide explanations here.

file:///C:/Users/SIDDHARTH/Downloads/Data Wrangling 2/Mid-term-Assessment-Rmarkdown-Template.nb.html 4/4

You might also like