o ni@s~ddlmZddlZddlmZmZddlZddlmZddlm Z ddl m Z m Z er2ddlm Z      ddddZdS)) annotationsN) TYPE_CHECKINGSequence)util) plot_table) test_missing test_types) CustomChart ROC CurveFy_trueSequence[numbers.Number]y_probas Sequence[Sequence[float]] | Nonelabelslist[str] | Noneclasses_to_plotlist[numbers.Number] | Nonetitlestr split_tableboolreturnr c Cstjddd}tjddd}tdd}tdd} ||}||}t||d s,d St||d s4d S||} |d ur?| }i} i} ||| |d } | D]5}|d urlt| |t set| d |j rl|| |}n| |}|j ||d |f| |d \| |<| |<}qP| | dd| D| t| | t| dd}t|tjjkrtdtjjd| j|dtjjd|ddgd}ttj|dddddd|ddd |d!S)"a Constructs Receiver Operating Characteristic (ROC) curve chart. Args: y_true (Sequence[numbers.Number]): The true class labels (ground truth) for the target variable. Shape should be (num_samples,). y_probas (Sequence[Sequence[float]]): The predicted probabilities or decision scores for each class. Shape should be (num_samples, num_classes). labels (list[str]): Human-readable labels corresponding to the class indices in `y_true`. For example, if `labels=['dog', 'cat']`, class 0 will be displayed as 'dog' and class 1 as 'cat' in the plot. If None, the raw class indices from `y_true` will be used. Default is None. classes_to_plot (list[numbers.Number]): A subset of unique class labels to include in the ROC curve. If None, all classes in `y_true` will be plotted. Default is None. title (str): Title of the ROC curve plot. Default is "ROC Curve". split_table (bool): Whether the table should be split into a separate section in the W&B UI. If `True`, the table will be displayed in a section named "Custom Chart Tables". Default is `False`. Returns: CustomChart: A custom chart object that can be logged to W&B. To log the chart, pass it to `wandb.log()`. Raises: wandb.Error: If numpy, pandas, or scikit-learn are not found. Example: ``` import numpy as np import wandb # Simulate a medical diagnosis classification problem with three diseases n_samples = 200 n_classes = 3 # True labels: assign "Diabetes", "Hypertension", or "Heart Disease" to # each sample disease_labels = ["Diabetes", "Hypertension", "Heart Disease"] # 0: Diabetes, 1: Hypertension, 2: Heart Disease y_true = np.random.choice([0, 1, 2], size=n_samples) # Predicted probabilities: simulate predictions, ensuring they sum to 1 # for each sample y_probas = np.random.dirichlet(np.ones(n_classes), size=n_samples) # Specify classes to plot (plotting all three diseases) classes_to_plot = [0, 1, 2] # Initialize a W&B run and log a ROC curve plot for disease classification with wandb.init(project="medical_diagnosis") as run: roc_plot = wandb.plot.roc_curve( y_true=y_true, y_probas=y_probas, labels=disease_labels, classes_to_plot=classes_to_plot, title="ROC Curve for Disease Classification", ) run.log({"roc-curve": roc_plot}) ``` numpyz@roc requires the numpy library, install with `pip install numpy`)requiredpandaszBroc requires the pandas library, install with `pip install pandas`zsklearn.metricszHroc requires the scikit library, install with `pip install scikit-learn`z sklearn.utils)r r Nr.) pos_labelcSsg|] \}}|gt|qS)len).0kvrrR/home/ubuntu/SoloSpeech/.venv/lib/python3.10/site-packages/wandb/plot/roc_curve.py szroc_curve..)classfprtprzwandb uses only z! data points to create the plots.F*r#)replace n_samples random_statestratify)r$r%r#) dataframezwandb/area-under-curve/v0r$r%)xyr#zFalse positive ratezTrue positive rate)rz x-axis-titlez y-axis-title) data_tablevega_spec_namefields string_fieldsr)r get_modulearrayrruniquewhereisin isinstanceintinteger roc_curve DataFramehstackitemslistvaluesroundrwandbTableMAX_ROWStermwarnresample sort_valuesr)r r rrrrnppdsklearn_metrics sklearn_utilsclassesr$r%indices_to_ploti class_label_dfrrr!r;sE        r;)NNNr F)r r r rrrrrrrrrrr ) __future__rnumberstypingrrrBrwandb.plot.custom_chartrwandb.plot.utilsrrr r;rrrr!s