Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/LauraSilRu/exoplanet-profiler/llms.txt

Use this file to discover all available pages before exploring further.

01_data_understanding.ipynb is the entry point of the ExoProfiler pipeline. It establishes the data contract by loading the raw CSV, auditing column types, inspecting null rates, and defining the 12 candidate features that all downstream notebooks will use.

​
Objectives

  • Load data/raw/exoplanets.csv and inspect shape (910 rows × 355 columns)
  • Verify pl_name is a unique, non-null identifier
  • Identify planetary and stellar feature candidates
  • Document data types and initial null rates
  • Establish FEATURE_COLUMNS contract for downstream use

​
Key Findings

910 Exoplanets

Total exoplanets in the raw NASA TESS dataset.

355 Total Columns

Full column count in the raw CSV before any feature selection.

12 Candidate Features

7 planetary + 5 stellar variables selected as the agreed feature set.

pl_name: Zero Nulls, Zero Duplicates

The planet name identifier is clean and unique across all 910 rows.

​
Candidate Feature Definition

The 12 features selected cover orbital mechanics, planetary size and mass, thermal properties, and stellar characteristics. Together they provide a multi-dimensional description of each exoplanet that enables meaningful clustering while avoiding redundant or unreliable columns. 
FEATURE_COLUMNS = [
    # Planetary features
    "pl_orbper",    # Orbital period (days)
    "pl_orbsmax",   # Orbital semi-major axis (AU)
    "pl_rade",      # Planetary radius (Earth radii)
    "pl_bmasse",    # Planetary mass (Earth masses)
    "pl_orbeccen",  # Orbital eccentricity [0, 1]
    "pl_insol",     # Insolation flux (relative to Earth)
    "pl_eqt",       # Equilibrium temperature (K)
    # Stellar features
    "st_teff",      # Stellar effective temperature (K)
    "st_rad",       # Stellar radius (solar radii)
    "st_mass",      # Stellar mass (solar masses)
    "st_met",       # Stellar metallicity
    "st_logg",      # Log stellar surface gravity
]

​
Running the Notebook

jupyter notebook notebooks/01_data_understanding.ipynb
Run this notebook before any other in the pipeline. All outputs are informational — no files are written to data/processed/. The primary deliverable is the agreed FEATURE_COLUMNS list that all subsequent notebooks depend on.

​
Prerequisites

data/raw/exoplanets.csv must exist before running this notebook. The file is downloaded from the NASA Exoplanet Archive (Planetary Systems table, TESS discoveries, default flag = 1). No other setup is required.

Build docs developers (and LLMs) love

Get started for freeTalk to us