o xi5@s|dZddlmZddlZddlZddlZddlmZm Z ede dddd Z    dd d Z      dddZ dS)z;Define plots for clustering models built with scikit-learn.) simplefilterN) calculateutilsignore)actioncategory ClusterercCsftd|dt|tjjr$t||tdt||||ddnt|||ddtdd S) aXGenerates all sklearn clusterer plots supported by W&B. The following plots are generated: elbow curve, silhouette plot. Should only be called with a fitted clusterer (otherwise an error is thrown). Args: model: (clusterer) Takes in a fitted clusterer. X_train: (arr) Training set features. cluster_labels: (list) Names for cluster labels. Makes plots easier to read by replacing cluster indexes with corresponding names. labels: (list) Named labels for target variable (y). Makes plots easier to read by replacing target values with corresponding index. For example if `labels=['dog', 'cat', 'owl']` all 0s are replaced by dog, 1s by cat. model_name: (str) Model name. Defaults to 'Clusterer' Returns: None: To see plots, go to your W&B run page then expand the 'media' tab under 'auto visualizations'. Example: ```python wandb.sklearn.plot_clusterer(kmeans, X, cluster_labels, labels, "KMeans") ``` z Plotting .zLogged elbow curve.T)labelskmeansF)r zLogged silhouette plot.N)wandbtermlog isinstancesklearnclusterKMeans elbow_curve silhouette)modelX_traincluster_labelsr model_namer\/home/ubuntu/.local/lib/python3.10/site-packages/wandb/integration/sklearn/plot/clusterer.py clusterers  rTc Cspt|ds tddStj|d}tj}t|}|r2|r4|r6t|||||}t d|idSdSdSdS)awMeasures and plots variance explained as a function of the number of clusters. Useful in picking the optimal number of clusters. Should only be called with a fitted clusterer (otherwise an error is thrown). Please note this function fits the model on the training set when called. Args: model: (clusterer) Takes in a fitted clusterer. X: (arr) Training set features. Returns: None: To see plots, go to your W&B run page then expand the 'media' tab under 'auto visualizations'. Example: ```python wandb.sklearn.plot_elbow_curve(model, X_train) ``` n_clusterszAn_clusters attribute not in classifier. Cannot plot elbow method.Nrr) hasattrr r r test_missing test_types test_fittedrrlog) rXcluster_rangesn_jobsshow_cluster_time not_missing correct_types is_fittedelbow_curve_chartrrrr8s      r euclideanc Csrtj|d}tj|d}t|}|r3|r5|r7t|tjr |j}t ||||||} t d| idSdSdSdS)a#Measures & plots silhouette coefficients. Silhouette coefficients near +1 indicate that the sample is far away from the neighboring clusters. A value near 0 indicates that the sample is on or very close to the decision boundary between two neighboring clusters and negative values indicate that the samples might have been assigned to the wrong cluster. Should only be called with a fitted clusterer (otherwise an error is thrown). Please note this function fits the model on the training set when called. Args: model: (clusterer) Takes in a fitted clusterer. X: (arr) Training set features. cluster_labels: (list) Names for cluster labels. Makes plots easier to read by replacing cluster indexes with corresponding names. Returns: None: To see plots, go to your W&B run page then expand the 'media' tab under 'auto visualizations'. Example: ```python wandb.sklearn.plot_silhouette(model, X_train, ["spam", "not spam"]) ``` rsilhouette_plotN) rrr r!rpd DataFramevaluesrrr r") rr#rr metricr r'r(r)silhouette_chartrrrrfs "      r)Nr)NNNrT)NNNNr+T)__doc__warningsrpandasr-rr wandb.integration.sklearnrr FutureWarningrrrrrrrs*   * /