CleanDataAgent

CleanDataAgent 📊

CleanDataAgent is an intelligent, automated data cleaning tool for structured datasets.
Built in R, it simplifies preprocessing by handling messy columns, formatting, missing data, outliers, scaling, and generating summary reports — all with built-in logging.

🚀 Features

• ✅ Cleans column names using janitor
• ✅ Flattens list/matrix columns to atomic vectors
• ✅ Trims and standardizes string formatting
• ✅ Parses and combines date parts (e.g., day/month/year)
• ✅ Handles missing values & outliers
• ✅ Creates useful engineered features (like total_guests, lead_time_category)
• ✅ Scales numeric columns for modeling
• ✅ Saves cleaned CSV, summary stats, and visualization plot
• ✅ Logs all steps for transparency

📦 Installation

```r # Install from GitHub (after publishing) devtools::install_github(“DanieG777/CleanDataAgent”) Or load locally:

r devtools::load_all(“path/to/CleanDataAgent”) 🧪 Usage

r library(CleanDataAgent)

clean_data_agent_v13_2( file_path = “hotel_bookings.csv”, output_prefix = “v13_cleaned”, log_file = “logfile.txt” ) 📂 Output Example v13_cleaned_data.csv → Cleaned + scaled data

v13_cleaned_summary.csv → Summary from summary()

v13_cleaned_plot.png → Lead time histogram by hotel

logfile.txt → Detailed log of processing

🔧 Requirements tidyverse

janitor

readr

lubridate

skimr

ggplot2

stringr

👤 Author Daniel Dawit – Junior Data Analyst Connect with me on LinkedIn

🧠 License MIT License – free for personal and commercial use.

yaml