Spaces:
Running
Running
| from os import O_ACCMODE | |
| import gradio as gr | |
| import joblib | |
| from transformers import pipeline | |
| import requests.exceptions | |
| from huggingface_hub import HfApi, hf_hub_download | |
| from huggingface_hub.repocard import metadata_load | |
| # work around for error, not happy really | |
| # import os | |
| # os.environ['KMP_DUPLICATE_LIB_OK']='True' | |
| app = gr.Blocks() | |
| model_1 = "juliensimon/distilbert-amazon-shoe-reviews" | |
| model_2 = "juliensimon/distilbert-amazon-shoe-reviews" | |
| def load_agent(model_id_1, model_id_2): | |
| """ | |
| This function load the agent's results | |
| """ | |
| # Load the metrics | |
| metadata_1 = get_metadata(model_id_1) | |
| # get predictions | |
| predictions_1 = predict(model_id_1) | |
| # Get the accuracy | |
| # results_1 = parse_metrics_accuracy(metadata_1) | |
| # Load the metrics | |
| metadata_2 = get_metadata(model_id_2) | |
| # get predictions | |
| predictions_2 = predict(model_id_2) | |
| # Get the accuracy | |
| # results_2 = parse_metrics_accuracy(metadata_2) | |
| return model_id_1, predictions_1, model_id_2, predictions_2 | |
| # def parse_metrics_accuracy(meta): | |
| # if "model-index" not in meta: | |
| # return None | |
| # result = meta["model-index"][0]["results"] | |
| # metrics = result[0]["metrics"] | |
| # accuracy = metrics[0]["value"] | |
| # return accuracy | |
| def get_metadata(model_id): | |
| """ | |
| Get the metadata of the model repo | |
| :param model_id: | |
| :return: metadata | |
| """ | |
| try: | |
| readme_path = hf_hub_download(model_id, filename="README.md") | |
| metadata = metadata_load(readme_path) | |
| print(metadata) | |
| return metadata | |
| except requests.exceptions.HTTPError: | |
| return None | |
| # classifier = pipeline("text-classification", model="juliensimon/distilbert-amazon-shoe-reviews") | |
| def predict(review, model_id): | |
| classifier = pipeline("text-classification", model=model_id) | |
| prediction = classifier(review) | |
| print(prediction) | |
| stars = prediction[0]['label'] | |
| stars = (int)(stars.split('_')[1])+1 | |
| score = 100*prediction[0]['score'] | |
| return "{} {:.0f}%".format("\U00002B50"*stars, score) | |
| with app: | |
| gr.Markdown( | |
| """ | |
| # Compare Sentiment Analysis Models | |
| Type text to predict sentiment. | |
| """) | |
| with gr.Row(): | |
| inp_1= gr.Textbox(label="Type text here.",placeholder="The customer service was satisfactory.") | |
| out_2 = gr.Textbox(label="Prediction") | |
| # gr.Markdown( | |
| # """ | |
| # Model Predictions | |
| # """) | |
| with gr.Row(): | |
| model1_input = gr.Textbox(label="Model 1") | |
| with gr.Row(): | |
| btn = gr.Button("Prediction for Model 1") | |
| btn.click(fn=predict(model_1), inputs=inp_1, outputs=out_2) | |
| with gr.Row(): | |
| model2_input = gr.Textbox(label="Model 2") | |
| with gr.Row(): | |
| btn = gr.Button("Prediction for Model 2") | |
| btn.click(fn=predict(model_2), inputs=inp_1, outputs=out_2) | |
| app_button.click(load_agent, inputs=[model1_input, model2_input], outputs=[model1_name, model1_score_output, model2_name, model2_score_output]) | |
| # examples = gr.Examples(examples=[["juliensimon/distilbert-amazon-shoe-reviews","juliensimon/distilbert-amazon-shoe-reviews"]], | |
| # inputs=[model1_input, model2_input]) | |
| app.launch() |