frequent_itemsets_eclat = fp.eclat(frequent_itemsets_apriori,min) print(frequent_itemsets_eclat.sort_values(by=['support'],ascending=False)) list_of_datasets = [frequent_itemsets_apriori, frequent_itemsets_fpgrowth, frequent_itemsets_eclat] min_supports = [0.100, 0.150, 0.200] def get_all_graphs(list_of_datasets,min_supports): for dataset in list_of_datasets: gr.get_single_graph(dataset) for support in min_supports: gr.get_single_graph(dataset,support) gr.get_multiple_graph(list_of_datasets[0], list_of_datasets[1], list_of_datasets[2]) for support in min_supports: gr.get_multiple_graph(list_of_datasets[0], list_of_datasets[1], list_of_datasets[2],filter_support=support) get_all_graphs(list_of_datasets,min_supports) df = pd.read_csv("data.csv") df.drop(['Channel', 'Region'], axis=1) colors = ['red', 'green', 'blue', 'orange'] pca = PCA(n_components=2, random_state=1) pca_result = pca.fit_transform(df) # Determine the number of clusters for KMeans and AGNES algorithms n_clusters_kmeans = clustering.elbow_chart(df, model_type='Kmeans') n_clusters_agnes = clustering.elbow_chart(df, model_type='AGNES') clustering.kmeans_clustering(df, pca_result, colors, n_clusters_kmeans) clustering.agnes_clustering(df, pca_result, colors, n_clusters_agnes) # Selecting epsilon for DBSCAN by running an NearestNeighbours algorihm # The optimal eps value is 0.3 as can be shown from the plot clustering.eps_selection(pca_result) clustering.dbscan_clustering(df, pca_result, eps=0.3, min_samples=15)