Spaces:
Running
Running
| import gradio as gr | |
| import torch | |
| import numpy as np | |
| import pandas as pd | |
| from tqdm import tqdm | |
| import matplotlib.pyplot as plt | |
| from transformers import AutoTokenizer, AutoConfig, AutoModel, AutoModelForSequenceClassification | |
| description_sentence = "<h3>Demo EmotioNL</h3>\nThis demo allows you to analyse the emotion in a sentence." | |
| description_dataset = "<h3>Demo EmotioNL</h3>\nThis demo allows you to analyse the emotions in a dataset.\nThe data should be in tsv-format with two named columns: the first column (id) should contain the sentence IDs, and the second column (text) should contain the actual texts. Optionally, there is a third column named 'date', which specifies the date associated with the text (e.g., tweet date). This column is necessary when the options 'emotion distribution over time' and 'peaks' are selected." | |
| inference_modelpath = "model/checkpoint-128" | |
| def inference_sentence(text): | |
| tokenizer = AutoTokenizer.from_pretrained(inference_modelpath) | |
| model = AutoModelForSequenceClassification.from_pretrained(inference_modelpath) | |
| for text in tqdm([text]): | |
| inputs = tokenizer(text, return_tensors="pt") | |
| with torch.no_grad(): # run model | |
| logits = model(**inputs).logits | |
| predicted_class_id = logits.argmax().item() | |
| output = model.config.id2label[predicted_class_id] | |
| return output | |
| def frequencies(preds): | |
| preds_dict = {"neutral": 0, "anger": 0, "fear": 0, "joy": 0, "love": 0, "sadness": 0} | |
| for pred in preds: | |
| preds_dict[pred] = preds_dict[pred] + 1 | |
| bars = list(preds_dict.keys()) | |
| height = list(preds_dict.values()) | |
| x_pos = np.arange(len(bars)) | |
| plt.bar(x_pos, height, color=['lightgrey', 'firebrick', 'rebeccapurple', 'orange', 'palevioletred', 'cornflowerblue']) | |
| plt.xticks(x_pos, bars) | |
| return plt | |
| def inference_dataset(file_object, option_list): | |
| tokenizer = AutoTokenizer.from_pretrained(inference_modelpath) | |
| model = AutoModelForSequenceClassification.from_pretrained(inference_modelpath) | |
| data_path = open(file_object.name, 'r') | |
| df = pd.read_csv(data_path, delimiter='\t', header=0, names=['id', 'text']) | |
| ids = df["id"].tolist() | |
| texts = df["text"].tolist() | |
| preds = [] | |
| for text in tqdm(texts): # progressbar | |
| inputs = tokenizer(text, return_tensors="pt") | |
| with torch.no_grad(): # run model | |
| logits = model(**inputs).logits | |
| predicted_class_id = logits.argmax().item() | |
| prediction = model.config.id2label[predicted_class_id] | |
| preds.append(prediction) | |
| predictions_content = list(zip(ids, texts, preds)) | |
| # write predictions to file | |
| output = "output.txt" | |
| f = open(output, 'w') | |
| f.write("id\ttext\tprediction\n") | |
| for line in predictions_content: | |
| f.write(str(line[0]) + '\t' + str(line[1]) + '\t' + str(line[2]) + '\n') | |
| output1 = output | |
| output2 = output3 = output4 = output5 = "This option was not selected." | |
| if "emotion frequencies" in option_list: | |
| output2 = frequencies(preds) | |
| else: | |
| output2 = None | |
| if "emotion distribution over time" in option_list: | |
| output3 = "This option was selected." | |
| if "peaks" in option_list: | |
| output4 = "This option was selected." | |
| if "topics" in option_list: | |
| output5 = "This option was selected." | |
| return [output1, output2, output3, output4, output5] | |
| iface_sentence = gr.Interface( | |
| fn=inference_sentence, | |
| description = description_sentence, | |
| inputs = gr.Textbox( | |
| label="Enter a sentence", | |
| lines=1), | |
| outputs="text") | |
| inputs = [gr.File( | |
| label="Upload a dataset"), | |
| gr.CheckboxGroup( | |
| ["emotion frequencies", "emotion distribution over time", "peaks", "topics"], | |
| label = "Select options")] | |
| outputs = [gr.File(), | |
| gr.Plot(label="Emotion frequencies"), | |
| gr.Textbox(label="Emotion distribution over time"), | |
| gr.Textbox(label="Peaks"), | |
| gr.Textbox(label="Topics")] | |
| iface_dataset = gr.Interface( | |
| fn = inference_dataset, | |
| description = description_dataset, | |
| inputs=inputs, | |
| outputs = outputs) | |
| iface = gr.TabbedInterface([iface_sentence, iface_dataset], ["Sentence", "Dataset"]) | |
| iface.queue().launch() |