#🐍 #Python #EDA #NaN #ランキング #断捨離

nan_pick.py

# Looking at NaN % within the data

nan = pd.DataFrame(all_df.isna().sum(), columns=['NaN_sum'])
nan['feat'] = nan.index
nan['ratio(%)'] = (nan['NaN_sum']/all_df.shape[0])*100
nan = nan[nan['NaN_sum'] > 0]
nan = nan.sort_values(by = ['NaN_sum']) #option: ascending=False 昇順
nan['Usability'] = np.where(nan['ratio(%)'] > 20, 'Discard', 'Keep')
nan

# Plotting Nan

plt.figure(figsize=(15, 6))
sns.barplot(x=nan["name"], y=nan["ratio"])
plt.xticks(rotation=45)
plt.title('Features containing Nan')
plt.xlabel('Features')
plt.ylabel('% of Missing Data')
plt.show()