Uncovering the Cost of Living in the Galactic Empire - Interview challenge solution

This challenge belongs to a series of programming challenges published by AltScore. You can see the complete list here. This is the tenth challenge.

• Problem Statement
  • Uncovering the Cost of Living in the Galactic Empire
• Why I Didn't Complete This Challenge
• What I Would Have Done
• Lessons Learned
• Final Thoughts

Problem Statement

Uncovering the Cost of Living in the Galactic Empire

This challenge was a Kaggle-style data science competition. The goal was to analyze data about the cost of living across different planets in the Galactic Empire.

Points: 500 (the highest point value for a single challenge before the Final Boss)

The challenge likely involved:

• Downloading a dataset from Kaggle or a provided source
• Performing exploratory data analysis (EDA)
• Building a predictive model or deriving insights
• Submitting predictions or analysis results

Why I Didn't Complete This Challenge

I decided not to attempt this challenge for several reasons:

1. Kaggle expertise gap: I don't have extensive experience with Kaggle competitions and the typical workflows involved (feature engineering, model tuning, submission formats)

2. Time constraints: At 500 points, this was a significant investment of time that I couldn't justify given my unfamiliarity with the platform

3. Different skill set: The previous challenges focused on API integration, web scraping, and backend development - areas where I'm more comfortable. This challenge pivoted to data science and machine learning

4. Diminishing returns: I had already accumulated enough points from the other challenges to feel satisfied with my participation

What I Would Have Done

If I had attempted this challenge, my approach would have been:

1. Setup Kaggle environment

   • Create/login to Kaggle account
   • Download the dataset
   • Set up a Jupyter notebook

2. Exploratory Data Analysis

   import pandas as pd
   import matplotlib.pyplot as plt
   import seaborn as sns
   
   df = pd.read_csv('galactic_cost_data.csv')
   df.describe()
   df.info()
   

3. Feature Engineering

   • Identify correlations between features
   • Handle missing values
   • Create new derived features

4. Model Building

   • Train/test split
   • Try multiple models (Linear Regression, Random Forest, XGBoost)
   • Cross-validation

5. Submit Results

   • Format predictions according to Kaggle requirements
   • Submit to the competition

Lessons Learned

Sometimes it's okay to skip a challenge if it's outside your comfort zone or doesn't align with your learning goals. The AltScore Makers Challenge was a great experience overall, and I learned a lot from the challenges I did complete.

If you're interested in data science challenges, I'd recommend:

• Kaggle Learn - Free courses on data science
• Kaggle Competitions - Practice with real competitions
• Start with "Getting Started" competitions before tackling more complex ones

Final Thoughts

This challenge reminded me that there's always more to learn. Data science and machine learning are vast fields, and it's okay to acknowledge gaps in your knowledge.

Maybe next time I'll be ready for a Kaggle challenge! 📊

Note: This article documents a challenge I chose not to complete. If you solved it, I'd love to hear about your approach!