eda-datapilot 0.2.3

DataPilot - A powerful, automated Exploratory Data Analysis (EDA) library in Python

🚀 DataPilot — Automated EDA Library

DataPilot is a Python library for automated Exploratory Data Analysis (EDA).
Give it a pandas DataFrame — it gives you a beautiful, interactive HTML report with statistics, visualizations, outlier detection, data quality alerts, and ML insights.

---

✨ Features

• 📊 Dataset shape, memory usage, and data-type summaries
• ❓ Missing values analysis per column
• 🔢 Numerical & categorical statistics
• 🔗 Pearson, Spearman, and Kendall correlations
• 🚨 IQR and Z-score outlier detection
• ⚠️ Data-quality alerts and preprocessing recommendations
• 🤖 ML task detection, feature importance, and PCA insights
• 📄 Standalone interactive HTML reports with Plotly + Seaborn charts

---

📦 Installation

Install directly from PyPI:

pip install eda-datapilot

Upgrade to the latest version:

pip install --upgrade eda-datapilot

Requirements: Python 3.10 or newer

---

🖥️ Usage in Jupyter Notebook

Step 1 — Install

!pip install --upgrade eda-datapilot

Step 2 — Run EDA on your CSV

import pandas as pd
import datapilot
from IPython.display import IFrame

# Verify version
print("DataPilot version:", datapilot.__version__)

# Change to your CSV file path
df = pd.read_csv("your_file.csv")

print(f"Loaded: {df.shape[0]} rows × {df.shape[1]} columns")
print(f"Columns: {list(df.columns)}")

# Set your target column or keep None
TARGET = None   # e.g. TARGET = "Price" or TARGET = "diagnosis"

# Run full EDA
report = datapilot.analyze(df, target=TARGET)

# Save & display inline in Jupyter
report.to_html("My_EDA_Report.html")
IFrame("My_EDA_Report.html", width="100%", height=850)

Open report in browser tab instead

report.show("My_EDA_Report.html")   # saves + auto-opens in browser

---

☁️ Usage in Google Colab

Step 1 — Install & Upload CSV

!pip install eda-datapilot

import pandas as pd
import datapilot
from google.colab import files

# Upload your CSV file
uploaded = files.upload()
filename = list(uploaded.keys())[0]
df = pd.read_csv(filename)
print(f"Loaded: {df.shape[0]} rows × {df.shape[1]} columns")

Step 2 — Run EDA & Download Report

TARGET = None   # e.g. TARGET = "Price"

report = datapilot.analyze(df, target=TARGET)
report.to_html("My_EDA_Report.html")
files.download("My_EDA_Report.html")
print("Report downloaded!")

Step 3 — View Inline in Colab

from IPython.display import IFrame
IFrame("My_EDA_Report.html", width="100%", height=850)

---

⚡ Quick Start (Python Script)

import pandas as pd
import datapilot

df = pd.read_csv("data/dataset.csv")

# Set target=None if no target column
report = datapilot.analyze(df, target="target_column")

report.to_html("DataPilot_Report.html")
print("Report saved!")

---

🔬 Step-by-Step Analysis

Use EDA when you need individual results as Python dictionaries:

import pandas as pd
from datapilot import EDA

df = pd.read_csv("data/dataset.csv")
eda = EDA(df, target="target_column")

summary         = eda.summary()          # Dataset overview
missing         = eda.missing()          # Missing values per column
numeric         = eda.numeric()          # Numeric statistics
categorical     = eda.categorical()      # Categorical statistics
duplicates      = eda.duplicates()       # Duplicate rows & columns
correlation     = eda.correlation()      # Pearson / Spearman / Kendall
outliers        = eda.outliers()         # IQR & Z-score outliers
problems        = eda.problems()         # Data quality alerts
recommendations = eda.recommendations()  # Preprocessing suggestions
ml_insights     = eda.ml_insights()     # Feature importance & task type

print(summary)
print(problems)
print(recommendations)

# Generate full HTML report
report = eda.report()
report.to_html("detailed_report.html")

---

⚙️ Configuration

Customize thresholds, outlier detection, sampling, and report settings:

import pandas as pd
from datapilot import EDA, EDAConfig

df = pd.read_csv("data/dataset.csv")

config = EDAConfig(sample_size=10_000)
config.thresholds.high_correlation = 0.9
config.outliers.iqr_multiplier = 1.5
config.outliers.z_score_threshold = 3.0
config.report.title = "My EDA Report"
config.report.theme = "light"

eda = EDA(df, target="target_column", config=config)
eda.report().to_html("configured_report.html")

---

📋 Public API Reference

Object / Method	Description
datapilot.analyze(df, target=None)	One-liner full EDA → returns Report
EDA(df, target=None, config=None)	Step-by-step analysis class
EDAConfig()	Configuration for thresholds, outliers, reports
eda.summary()	Dataset overview (shape, dtypes, memory)
eda.missing()	Missing values per column
eda.numeric()	Numeric column statistics
eda.categorical()	Categorical column statistics
eda.duplicates()	Duplicate row & column detection
eda.correlation()	Correlation matrices
eda.outliers()	Outlier detection (IQR & Z-score)
eda.problems()	Data quality audit alerts
eda.recommendations()	Preprocessing recommendations
eda.ml_insights()	ML task type & feature importance
report.to_html("file.html")	Save report to HTML file
report.show("file.html")	Save + open in browser

---

🗂️ Project Layout

datapilot/
├── datapilot/              # Library source code
│   ├── analyzer.py         # EDA and analyze() APIs
│   ├── config.py           # EDAConfig and report settings
│   ├── report.py           # HTML report generation
│   ├── visualization.py    # Plotly & Seaborn chart generators
│   └── templates/          # Jinja2 HTML report template
├── examples/demo.py        # Runnable demo with synthetic data
├── tests/                  # Automated tests
├── pyproject.toml          # Package metadata and dependencies
└── requirements.txt        # Runtime dependencies

---

🧪 Run the Demo

python examples/demo.py

This creates a synthetic dataset with missing values, outliers, and duplicates, then generates DataPilot_Demo_Report.html.

---

🧪 Run Tests

python -m pytest

---

📄 License

MIT License — see LICENSE for details.

---

👩‍💻 Author

Sakshi Nagare — [e-mail]

⭐ If you find DataPilot useful, please star the repo and share it with others! eda.report().to_html("reports/configured_report.html")

## Run the Included Demo

The included demo creates a synthetic dataset with missing values, outliers,
duplicates, categorical columns, and a target column. It writes
`DataPilot_Demo_Report.html` to the project directory.

```powershell
python examples\demo.py

Run Tests

python -m pytest

Public API

The package exports the following public objects:

from datapilot import EDA, EDAConfig, analyze

• analyze(df, target=None) runs a complete analysis.
• EDA(df, target=None, config=None) provides step-by-step analysis.
• EDAConfig configures thresholds, outliers, reports, and sampling.

Project Layout

datapilot/
├── datapilot/              # Library source code
│   ├── analyzer.py         # EDA and analyze APIs
│   ├── config.py           # EDAConfig and report settings
│   ├── report.py           # HTML report generation
│   └── templates/          # Report template
├── examples/demo.py        # Runnable library example
├── tests/                  # Automated tests and sample data
├── pyproject.toml          # Package metadata and dependencies
└── requirements.txt        # Runtime and test dependencies