Skip to content

rohan8594/Logistic-Regression-on-Titanic-Dataset

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

17 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Logistic Regression on Titanic Dataset

Content

In this project I'm attempting to do data analysis on the Titanic Dataset. In the first step I'm doing a very quick data exploration and preprocessing on a visual level, plotting some simple plots to understand the data better. Then I've done some data cleaning and built a Classifier that can predict whether a passenger survived or not.

Tools and Packages

In this project I've used the following tools and Python packages:

  • Jupyter Notebooks: This is the software that lets us run Python code in the browser and intermix markdown with cells containing code.
  • Numpy: This is pythons main scientific computing library. Its important for Data Science as all libraries in PyData Ecosystem rely on NumPy as one of their main building blocks
  • Pandas: This is the data analysis tool of choice in Python. It allows fast analysis and data cleaning and preparation using powerful data structures like dataframes and series.
  • Matplotlib: The data visualisation package of Python. Has a very similar feel to MalLab's graphical plotting and works well with numpy and pandas.
  • Seaborn: Statistical plotting library built on top of Matplotlib. It is also designed to work very well with pandas dataframes objects.
  • Scikit-learn: The machine learning package of Python. Makes implementing ML Algorithms extremely simple.

Results

The classifier built here has a prediction score of 0.81, i.e., we get an average accuracy of 80+%. This is a pretty good accuracy for starters and could be improved upon by coming up with newer, better features by using some feature engineering. This is something I could work on in the future.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published