An automated Exploratory Data Analysis (EDA) project built with Python and Jupyter/Google Colab.
This project analyzes the Nepal weather and river dataset and demonstrates how different Python EDA tools can be used to inspect, clean, visualize, and generate automated reports from a dataset.
The project performs automated exploratory data analysis on the nepal.csv dataset.
The notebook includes:
- Dataset requirement validation
- Dataset loading and inspection
- Column name cleaning
- Numerical and categorical column identification
- Basic statistical analysis
- Data visualization
- Automated EDA reports
- Interactive data exploration
- DataPrep report generation
- D-Tale interactive analysis
Automated-Exploratory-Data-Analysis-/
│
├── Main.ipynb
├── nepal.csv
├── dataprep_report.html
└── README.md
| File | Description |
|---|---|
Main.ipynb |
Main Jupyter/Google Colab notebook containing the complete EDA workflow |
nepal.csv |
Nepal weather and river dataset used for analysis |
dataprep_report.html |
Generated automated DataPrep EDA report |
README.md |
Project documentation |
The project uses nepal.csv.
The dataset contains:
- 13,390 records
- 19 columns
- Numerical attributes
- Categorical attributes
- Weather-related measurements
- Geographic information
- River and hydrological measurements
Some of the available attributes include:
- Date
- Location
- River
- Basin
- Latitude
- Longitude
- Elevation
- Precipitation
- Soil Moisture
- Rainfall
- Temperature
- Dew Point
- Relative Humidity
- Wind Speed
- Wind Gusts
- Wind Direction
- River Discharge
The notebook first checks whether the dataset satisfies the required conditions.
Records > 10,000 : PASS
Numerical Attributes : PASS
Categorical Attributes : PASS
The dataset contains 13,390 records and 19 columns, making it suitable for the project's EDA workflow.
The notebook performs basic preprocessing before analysis.
This includes:
- Loading the CSV file with Pandas
- Cleaning column names
- Converting column names into a consistent format
- Removing unnecessary characters from column names
- Handling duplicate column names
- Checking dataset dimensions
- Inspecting the first rows of the dataset
For example, column names are converted into a cleaner format such as:
temperature_mean_c
river_discharge_m3s
relative_humidity_mean_pct
wind_speed_max_kmh
The project uses several Python libraries and EDA tools to explore the dataset.
Used for:
- Loading the dataset
- Data inspection
- Data cleaning
- Statistical analysis
- Data manipulation
Used for numerical operations and data processing.
Used for interactive visualizations and charts.
Used for automatically generating exploratory visualizations and identifying patterns in the dataset.
Used to generate an automated HTML-based EDA report.
Used for interactive exploration and analysis of the Pandas DataFrame.
The project generates an HTML report using DataPrep.
The generated report is available in:
dataprep_report.html
The report provides automated analysis of the dataset, including distributions, statistics, and relationships between variables.
The notebook also demonstrates how to launch D-Tale for interactive dataset exploration.
D-Tale provides a browser-based interface for exploring the Pandas DataFrame without manually writing every analysis command.
- Python
- Jupyter Notebook
- Google Colab
- Pandas
- NumPy
- Plotly
- AutoViz
- DataPrep
- D-Tale
Clone the repository:
git clone https://github.com/Zohaibcode740/Automated-Exploratory-Data-Analysis-.gitMove into the project directory:
cd Automated-Exploratory-Data-Analysis-Install the main Python dependencies:
pip install pandas numpy plotly autoviz dtaleNote: DataPrep can have compatibility requirements depending on the Python version. The notebook includes a separate Python 3.10 virtual environment setup for generating the DataPrep report.
The easiest way to run the project is through Google Colab.
- Open
Main.ipynb. - Upload/open the notebook in Google Colab.
- Make sure
nepal.csvis available in the notebook environment. - Run the notebook cells in order.
- Generate the EDA reports and visualizations.
You can also run the notebook locally:
jupyter notebook Main.ipynbLoad Dataset
↓
Validate Dataset Requirements
↓
Inspect Dataset
↓
Clean Column Names
↓
Identify Data Types
↓
Explore Numerical & Categorical Data
↓
Generate Visualizations
↓
Automated EDA
↓
Generate DataPrep Report
↓
Explore Data with D-Tale
The main goals of this project are to:
- Practice exploratory data analysis with Python
- Learn automated EDA techniques
- Work with real-world datasets
- Understand numerical and categorical data
- Generate automated data reports
- Explore multiple Python EDA libraries
- Learn interactive data analysis workflows
By working with this project, you can learn how to:
- Load and inspect large CSV datasets
- Clean and standardize column names
- Identify numerical and categorical variables
- Perform basic dataset validation
- Use Pandas for data analysis
- Create interactive visualizations with Plotly
- Generate automated EDA reports
- Explore datasets using D-Tale
- Work with Jupyter Notebook and Google Colab
Contributions are welcome.
If you find a bug or have an idea for improving the project:
- Fork the repository.
- Create a new branch.
- Make your changes.
- Commit your changes.
- Open a Pull Request.
Example:
git checkout -b improve-eda
git add .
git commit -m "improve EDA workflow"
git push origin improve-edaThen open a Pull Request on GitHub.
This project currently does not specify a license.
If you plan to allow others to freely use, modify, and distribute the project, consider adding an appropriate open-source license.
Zohaibcode740
GitHub: https://github.com/Zohaibcode740
⭐ If you find this project useful, consider giving the repository a star.