# %% from jinja2 import Environment, FileSystemLoader import pandas as pd import gradio as gr df = pd.read_csv("./data.csv") def parse_into_jinja_markdown(model_name, performance,accuracy,Precision, Recall, Robustness, Fairness, Failure_Clusters ): env = Environment(loader=FileSystemLoader('.'), autoescape=True) temp = env.get_template('mc_template.md') return( temp.render(model_id =model_name, accuracy=accuracy,Precision=Precision,Recall=Recall,Robustness=Robustness,Fairness=Fairness,Performance =performance, Failure_Cluster=Failure_Clusters)) def md_builder(model, dataset, displayed_metrics): row = df[df["friendly_name"] == model] str = "" ## f"# Model Card for {model}\n" ##f"On dataset `{dataset}`\n" ## ) if "Performance" in displayed_metrics: perform_val = f"\nPerformance: `{row['performance'].values[0]}`" if "Accuracy" in displayed_metrics: accuracy_val= f"\nAccuracy: `{row['accuracy'].values[0]}`" if "Precision" in displayed_metrics: precision_val= f"\nPrecision: `{row['precision_weighted'].values[0]}`" if "Recall" in displayed_metrics: recall_val= f"\nRecall: `{row['recall_weighted'].values[0]}`" if "Robustness" in displayed_metrics: robustness_val = f"\nRobustness: `{100-row['robustness'].values[0]}`" if "Fairness" in displayed_metrics: fairness_val = f"\nFairness: `{0}`" if "Failure Clusters" in displayed_metrics: cl_count = row['cluster_count'].values[0] fail_cluster = f"\nTop failures: {row['top_failure_cluster'].values[0]}(+{cl_count - 1} others)(details for all {cl_count} clusters)" str += "\n
⛶ Expand safety card
" str = parse_into_jinja_markdown(model,perform_val,accuracy_val,precision_val,recall_val,robustness_val,fairness_val,fail_cluster) return str iface = gr.Interface( md_builder, [ gr.Dropdown( list(df["friendly_name"]), label="Model", value="ViT", info="Select a model to use for testing.", ), gr.Dropdown( ["marmal88/skin_cancer"], value="marmal88/skin_cancer", label="Dataset", info="Select the sampling dataset to use for testing.", ), gr.CheckboxGroup( [ "Performance", "Accuracy", "Precision", "Recall", "Robustness", "Fairness", "Failure Clusters", ], value=["Accuracy", "Robustness", "Fairness", "Failure Clusters"], label="Metrics", info="Select displayed metrics.", ), # gr.Radio(["park", "zoo", "road"], label="Location", info="Where did they go?"), # gr.Dropdown( # ["ran", "swam", "ate", "slept"], value=["swam", "slept"], multiselect=True, label="Activity", info="Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed auctor, nisl eget ultricies aliquam, nunc nisl aliquet nunc, eget aliquam nisl nunc vel nisl." # ), # gr.Checkbox(label="Morning", info="Did they do it in the morning?"), ], "markdown", examples=[ [ "ViT", "marmal88/skin_cancer", ["Accuracy", "Robustness", "Fairness", "Failure Clusters"], ], ], ) iface.launch() # %%