Kaggle Titanic Dataset [on Medium]

Fill_up_ages.py

# Now to fill up the NA values for Ages
mean_age=df_train_filt2['Age'].mean()
listofAgeind_=list(df_train_filt2[df_train_filt2['Age'].isna()==True].index)
list_of_ages=np.random.normal(mean_age, 10, len(listofAgeind_))

plt.plot(list_of_ages, linewidth=2, color='g', label='Age')
plt.show()
for (idx,age) in zip(listofAgeind_,list_of_ages):df_train_filt2.loc[idx, 'Age']=age
print(df_train_filt2.count())