21/08/2025
๐ ๐๐๐ฌ๐ค ๐ ๐๐จ๐ฆ๐ฉ๐ฅ๐๐ญ๐๐ โ ๐๐๐ญ๐ ๐๐ง๐๐ฅ๐ฒ๐ฌ๐ข๐ฌ ๐๐ง๐ญ๐๐ซ๐ง๐ฌ๐ก๐ข๐ฉ
As part of my internship, I worked on ๐๐ฑ๐ฉ๐ฅ๐จ๐ซ๐๐ญ๐จ๐ซ๐ฒ ๐๐๐ญ๐ ๐๐ง๐๐ฅ๐ฒ๐ฌ๐ข๐ฌ (๐๐๐) using the classic Titanic dataset from Kaggle. This task helped me practice the fundamentals of ๐๐๐ญ๐ ๐๐ฅ๐๐๐ง๐ข๐ง๐ ๐งน, ๐ญ๐ซ๐๐ง๐ฌ๐๐จ๐ซ๐ฆ๐๐ญ๐ข๐จ๐ง ๐, ๐๐ง๐ ๐ฏ๐ข๐ฌ๐ฎ๐๐ฅ๐ข๐ณ๐๐ญ๐ข๐จ๐ง ๐ in Python.
๐ ๐๐๐ฒ ๐๐ญ๐๐ฉ๐ฌ ๐ ๐๐๐ซ๐๐จ๐ซ๐ฆ๐๐
โจ Cleaned missing values (Age, Cabin, Embarked) and converted categorical types
๐ Generated descriptive statistics and group-based insights (e.g., survival by gender and passenger class)
๐ Visualized patterns and correlations using ๐๐๐๐๐จ๐ซ๐ง and ๐๐๐ญ๐ฉ๐ฅ๐จ๐ญ๐ฅ๐ข๐
๐ Bonus: Created bar plots and heatmaps to clearly show survival rates across different groups
โ๏ธ ๐๐จ๐จ๐ฅ๐ฌ & ๐๐ข๐๐ซ๐๐ซ๐ข๐๐ฌ
๐ Python
๐ Pandas
๐จ Seaborn / Matplotlib
๐ ๐๐๐ฒ ๐๐ง๐ฌ๐ข๐ ๐ก๐ญ๐ฌ
๐ฉโ๐ฆฐ Female passengers had a much higher survival rate than male passengers
๐๏ธ First-class passengers had significantly better survival chances compared to third-class
๐จโ๐ฉโ๐ง Family size and embarkation port also influenced survival probability
๐ ๐๐ข๐ญ๐๐ฎ๐ ๐๐๐ฉ๐จ๐ฌ๐ข๐ญ๐จ๐ซ๐ฒ
๐ https://github.com/iammarafzal/eda-titanic-dataset.git
This task not only improved my EDA skills but also gave me hands-on experience in presenting data-driven insights effectively.
๐ฅ Excited to move forward to the next tasks and continue growing in my ๐๐๐ญ๐ ๐๐ง๐๐ฅ๐ฒ๐ฌ๐ข๐ฌ ๐๐ง๐ญ๐๐ซ๐ง๐ฌ๐ก๐ข๐ฉ at Elevvo Pathways! ๐