Create app.py

app.py

@@ -0,0 +1,96 @@
+import gradio as gr
+import json
+from datasets import load_dataset
+from sentence_transformers import SentenceTransformer, InputExample, losses, util, evaluation
+import pandas as pd
+
+def Main(Modelo, Texto1, Texto2):
+  
+  error = ""
+  modelResult  = ""
+  
+  if File == None and Operacion == "Procesar Fichero":
+    error = "Debe seleccionar un fichero"
+  else:
+    try:
+      if Operacion == "Comparar Textos":
+        data_test = []
+        data_test.append(InputExample(guid= "", texts=[Texto1, Texto2], label=0))
+      else:
+        data_test = ConvertJsonToList(File.name)
+      
+      modelResult = TestModel('jfarray/Model_'+ Modelo +'_50_Epochs',data_test)
+    except Exception as e:
+      error = e
+  
+  return [error, modelResult]
+    
+def ConvertJsonToList(fileName):
+  subject_fileDataset = load_dataset("json", data_files=fileName)
+
+  samples = []
+
+  for i in range (0,len(subject_fileDataset["train"])): #len(subject1)
+    hashed_id = subject_fileDataset["train"][i]['hashed_id']
+    mark = subject_fileDataset["train"][i]['nota']
+    responseStudent = subject_fileDataset["train"][i]['respuesta']
+    responseTeacher = ""
+    for j in range(0,len(subject_fileDataset["train"][i]['metadata']['minipreguntas'])):
+      responseTeacher = responseTeacher + subject_fileDataset["train"][i]['metadata']['minipreguntas'][j]['minirespuesta']
+    
+    ie = InputExample(guid= hashed_id, texts=[responseTeacher, responseStudent], label=mark)
+
+    samples.append(ie)
+
+  return samples
+  
+def TestModel(checkpoint, data):
+  local_model_path = checkpoint
+  model = SentenceTransformer(local_model_path)
+  df = pd.DataFrame(columns=["Hashed_id", "Nota", "Similitud Semántica"])
+  
+  sentences1 = []
+  sentences2 = []
+  hashed_ids = []
+  marks = []
+  scores = []
+  for i in range (0,len(data)): #len(data)
+    sentences1.append(data[i].texts[0])
+    sentences2.append(data[i].texts[1])
+
+  #Compute embedding for both lists
+  embeddings1 = model.encode(sentences1, convert_to_tensor=True)
+  embeddings2 = model.encode(sentences2, convert_to_tensor=True)
+  
+  #Compute cosine-similarits
+  cosine_scores = util.cos_sim(embeddings1, embeddings2)
+  
+  for i in range(len(sentences1)):
+    hashed_ids.append(data[i].guid)
+    marks.append(data[i].label)
+    scores.append(round(cosine_scores[i][i].item(),3))
+
+  df['Similitud Semántica'] = scores
+  
+  return df
+
+Modelos = gr.inputs.Dropdown(["dccuchile_bert-base-spanish-wwm-uncased"
+  , "bert-base-multilingual-uncased"
+  , "all-distilroberta-v1"
+  , "paraphrase-multilingual-mpnet-base-v2"
+  , "paraphrase-multilingual-MiniLM-L12-v2"
+  , "distiluse-base-multilingual-cased-v1"])
+Opciones = gr.inputs.Radio(["Comparar Textos", "Procesar Fichero"])
+Text1Input = gr.inputs.Textbox(lines=10, placeholder="Escriba el texto aqui ...")
+Text2Input = gr.inputs.Textbox(lines=10, placeholder="Escriba el otro texto aqui ...")
+LabelOutput = gr.outputs.Label(num_top_classes=None, type="auto", label="")
+DataFrameOutput = gr.outputs.Dataframe(headers=["Similitud Semántica"]
+  , max_rows=20, max_cols=None, overflow_row_behaviour="paginate", type="auto", label="Resultado")
+
+iface = gr.Interface(fn=Main
+    , inputs=[ Modelos, Text1Input ,Text2Input]
+    , outputs=[LabelOutput, DataFrameOutput]
+    , title = "Similitud Semántica de textos en Español de tamaño medio (200-250 palabras)"
+)
+
+iface.launch(share = True,enable_queue=True, show_error =True)