Compulsory Task $1$

Follow these steps:

Open Kmeans$\_$task.ipynb

Load the Country$-$data.csv dataset.

Drop any non$-$numeric columns from the dataset.

Create a heatmap of correlation of features to explore relationships between features.

Create scatter plots to explore the continuous independent features against gdpp$.$

Normalise the dataset using MinMaxScaler from sklearn.

Find the optimal number of clusters using the elbow and silhouette score

method.

Fit the scaled dataset to the optimal number of clusters. Report back on

the silhouette score of the model.

Plot elbow curve using scaled dataset

Visualise the clusters for the following two groups:

Child mortality vs GDPP

Inflation vs GDPP

Label the groups of countries in the plots you created based on child

mortality, GDPP$,$ and inflation. You may use terms such as: least

developed, developing and developed, or low, low$-$middle, upper$-$middle

and high income. Alternatively, simply rank them from highest to lowest.

Justify the labels you assign to each group.