Python superconducting exploratory data analysis and feature selection for superconducting data frames

The goal of this article is to outline the EDA (Exploratory Data Analysis) steps for the superconductivity dataframe in the UCI ml dataset catalog (https://archive.ics.uci.edu/dataset/464/superconductivty+data).

This EDA is part of a larger project to predict the critical temperature and chemical composition of a material based on some user input. More information can be found here (https://burnt-layer-3b0.notion.site/Product-Specs-a7b5c13b376a415fa9a750d0b7b47f04?pvs=4).

First we load the data with pandas.

#importing pandas
import pandas as pd
import os
#loading dataset
superc_df= pd.read_csv("/content/drive/MyDrive/superconductivty+data (1)/train.csv")
superc_df.head()
number_of_elements mean_atomic_mass wtd_mean_atomic_mass gmean_atomic_mass wtd_gmean_atomic_mass entropy_atomic_mass wtd_entropy_atomic_mass range_atomic_mass wtd_range_atomic_mass std_atomic_mass ... wtd_mean_Valence gmean_Valence wtd_gmean_Valence entropy_Valence wtd_entropy_Valence range_Valence wtd_range_Valence st