Getting Started

Quick Start

Get up and running with the SDK and CLI in under 5 minutes

Featuresmith is designed to serve identical results whether you are running scripted pipelines in Python or triggering quick inspections in the terminal.

Python SDK Quick Start

Analyze a dataset and print quality findings:

python

1import featuresmith as fs
2
3# 1. Load a tabular dataset (CSV, Parquet, Excel, or DataFrames)
4dataset = fs.load("customers.csv")
5print(f"Loaded {dataset.row_count} rows.")
6
7# 2. Extract deterministic statistical profiles
8profile = fs.profile("customers.csv")
9
10# 3. Perform rule-based data quality & target leakage checks
11result = fs.analyze("customers.csv", target_column="churn")
12
13for finding in result.findings:
14    print(f"[{finding.severity.upper()}] {finding.title} in column '{finding.column_name}'")
15    print(f"  Reason: {finding.description}")

CLI Quick Start

Verify dataset issues inside your shell:

bash

1# Analyze a local CSV dataset
2featuresmith analyze customers.csv
3
4# Run leakage checks targeting the 'churn' column
5featuresmith analyze customers.csv --target churn
6
7# Export findings to report.json in machine-readable format
8featuresmith analyze customers.csv --format json --output report.json

CLI Exit Codes

The CLI uses precise exit codes to facilitate pipeline integration and gating:

Exit Code	Description
0	Clean — no rule violations detected at or above the threshold.
1	Findings detected — one or more rules triggered at or above threshold.
2	Invalid input — bad flags, missing arguments, or columns not in schema.
3	File load failure — file does not exist, or parser error.
4	Unexpected internal error (use `--verbose` for traceback).