optiflow

# Calculate 1-year date range from latest data
end_date = df['Date'].max()

# Filter 1-year data range from original df
start_date = end_date - pd.to_timedelta(364, unit='d')
df_rfm = df[(df['Date'] >= start_date) & (df['Date'] <= end_date)]

# Create hypothetical snapshot date
snapshot_date = end_date + dt.timedelta(days=1)

optiflow

def kmeans(df, clusters_number):
    '''
    Implement k-means clustering on dataset
    
    INPUT:
        dataset : dataframe. Dataset for k-means to fit.
        clusters_number : int. Number of clusters to form.
        end : int. Ending range of kmeans to test.
    OUTPUT:
        Cluster results and t-SNE visualisation of clusters.

optiflow

def optimal_kmeans(dataset, start=2, end=11):
    '''
    Calculate the optimal number of kmeans
    
    INPUT:
        dataset : dataframe. Dataset for k-means to fit
        start : int. Starting range of kmeans to test
        end : int. Ending range of kmeans to test
    OUTPUT:
        Values and line plot of Silhouette Score.