g4_fe_tenure.py

#function to order cluster numbers
def order_cluster(cluster_field_name, target_field_name,df,ascending):
    new_cluster_field_name = 'new_' + cluster_field_name
    df_new = df.groupby(cluster_field_name)[target_field_name].mean().reset_index()
    df_new = df_new.sort_values(by=target_field_name,ascending=ascending).reset_index(drop=True)
    df_new['index'] = df_new.index
    df_final = pd.merge(df,df_new[[cluster_field_name,'index']], on=cluster_field_name)
    df_final = df_final.drop([cluster_field_name],axis=1)
    df_final = df_final.rename(columns={"index":cluster_field_name})
    return df_final


#Elbow Method to identify the appropriate number of clusters 
sse={}
df_cluster = df_data[['tenure']]
for k in range(1, 10):
    kmeans = KMeans(n_clusters=k, max_iter=1000).fit(df_cluster)
    df_cluster["clusters"] = kmeans.labels_
    sse[k] = kmeans.inertia_ 
plt.figure()
plt.plot(list(sse.keys()), list(sse.values()))
plt.xlabel("Number of cluster")
plt.show()


#K-means logic to the selected column and change the naming
kmeans = KMeans(n_clusters=3)
kmeans.fit(df_data[['tenure']])
df_data['TenureCluster'] = kmeans.predict(df_data[['tenure']])

#order cluster numbers
df_data = order_cluster('TenureCluster', 'tenure',df_data,True)

#observe the characteristics
df_data.groupby('TenureCluster').tenure.describe()

#change the naming
df_data['TenureCluster'] = df_data["TenureCluster"].replace({0:'Low',1:'Mid',2:'High'})

#plot Churn Rate vs new clusters
df_plot = df_data.groupby('TenureCluster').Churn.mean().reset_index()
plot_data = [
    go.Bar(
        x=df_plot['TenureCluster'],
        y=df_plot['Churn'],
        width = [0.5, 0.5, 0.5,0.5],
        marker=dict(
        color=['green', 'blue', 'orange','red'])
    )
]

plot_layout = go.Layout(
        xaxis={"type": "category","categoryarray":['Low','Mid','High']},
        title='Tenure Cluster vs Churn Rate',
        plot_bgcolor  = "rgb(243,243,243)",
        paper_bgcolor  = "rgb(243,243,243)",
    )
fig = go.Figure(data=plot_data, layout=plot_layout)
pyoff.iplot(fig)