A Repo of various End-to-End analysis in statistical approach, exploratory data analysis (EDA) , feature engineering and modelling. Along with just Analysis of various data, visualization of data.
I will keep updating this repo once i add explanations to other notebooks and for reference in the future, also as i work on new datasets.
- Python 3.6+
- IPython
- Jupyter notebook
- Usual Data Science Packages as they appear in the code.
Use pip to install the packages or get the wheel format of the packages from python package repository here-> or to make life easier go with Anaconda
as there might be some version clash between different libraries.
Also, take note what architecture (32bit or 64bit) python is and install lib's accordingly :) Especially tensorflow and tensorflow-gpu which needs to be 64bit.
I use pycharm with dark theme and layout so some of my visualization setting might not be pleasing in some jupyter notebooks so please change them to your liking.
Free to use the notebooks, ideas and code as you see fit for your own work.