plentas / app.py
xiomarablanco's picture
Nuevo formato de archivos sakai
97b0243
raw
history blame
12.8 kB
import gradio as gr
import json
from flask import jsonify
from sentence_transformers import SentenceTransformer, InputExample, util
from codeScripts.utils import save_json, load_json, create_file_path, remove
from plentas import Plentas
import pandas as pd
import zipfile
import os
import shutil
from datetime import datetime
import tablib
from pathlib import Path
def Main(uploadedFile, txtFileInput, orthographyPercentage, syntaxPercentage, semanticPercentage, studentsRange):
error = ""
excelPath = ""
copySpanishDictionaries()
try:
if not txtFileInput:
error="Por favor seleccione un archivo con las preguntas y respuestas"
return [error, excelPath]
else:
txtFileInput = txtFileInput.name
configuration = readQATextFile(txtFileInput)
configuration["ortographyPercentage"] = float(orthographyPercentage)
configuration["syntaxPercentage"] = float(syntaxPercentage)
configuration["semanticPercentage"] = float(semanticPercentage)
if studentsRange == "":
studentsRange = "All"
configuration["students"] = studentsRange
if not uploadedFile:
error="Por favor seleccione el .zip con las respuestas de los alumnos"
return [error, excelPath]
else:
uploadedFilePath = uploadedFile.name
config_json = load_json("configV2.json")
# #configuring plentas methodology
response = Plentas(config_json[0], [answersTodict(uploadedFilePath), createTeacherJson(configuration)])
# # #overwriting the custom settings for the settings from the api
response.setApiSettings(configuration)
try:
print("Processing!")
modelResult = response.processApiData()
except Exception as ex:
print("Error processing: " + str(ex))
# modelJson = json.dumps(modelResult)
excelPath = exportResultToExcelFile(modelResult)
except Exception as e:
error = "Oops: " + str(e)
return [error, excelPath]
def exportResultToExcelFile(modelResult):
excelData = []
studentsArray = modelResult[0]
index = 0
for item in studentsArray:
#print("ITEM - " + str(item))
studentData = item[index]
excelData.append(studentData)
index+= 1
#tableResults = tablib.Dataset(headers=('ID', 'SimilitudSpacy', 'SimilitudBert', 'NotaSemanticaSpacy', 'NotaSemanticaBert', 'NotaSintaxis', 'NotaOrtografia','NotaTotalSpacy','NotaTotalBert','Feedback'))
tableResults = tablib.Dataset(headers=('ID', 'SumaTotalSpacy', 'SumaTotaldBert', 'NotaSemanticaSpacy', 'NotaSemanticaBert', 'NotaSintaxis', 'NotaOrtografia','NotaTotalSpacy','NotaTotalBert','Feedback'))
tableResults.json=json.dumps(excelData)
tableExport=tableResults.export('xlsx')
outputFilePath = './output/' + str(datetime.now().microsecond) + '_plentas_output.xlsx'
# outputFilePath = './output/plentas_output.xlsx'
with open(outputFilePath, 'wb') as f: # open the xlsx file
f.write(tableExport) # write the dataset to the xlsx file
f.close()
return outputFilePath
def copySpanishDictionaries():
try:
shutil.copy("./assets/hunspell_dictionaries/es_ES/es_ES.aff", "/home/user/.local/lib/python3.8/site-packages/hunspell/dictionaries/es_ES.aff")
shutil.copy("./assets/hunspell_dictionaries/es_ES/es_ES.dic", "/home/user/.local/lib/python3.8/site-packages/hunspell/dictionaries/es_ES.dic")
except Exception as ex:
print("Error copying dictionaries" + str(ex))
def readQATextFile(qaTextFilePath):
configuration = {}
f = open(qaTextFilePath, 'r')
lines = f.readlines()
count = 0
qCount=1
q = ""
a = ""
while count < len(lines):
if q == "" or q == "\n":
q = lines[count]
count += 1
continue
if a == "" or a == "\n":
a = lines[count]
count += 1
if q != "" and a != "":
configuration["minip" + str(qCount)] = q
configuration["minir" + str(qCount)] = a
qCount += 1
q = ""
a = ""
return configuration
def createTeacherJson(configuration):
"""
This function extracts the information about the subquestions and subanswers and puts them in the correct format.
Inputs:
config: The configured info from the api.
Outputs:
teachersJson: The generated dictionary with the subquestions.
"""
teachersJson = {"enunciado": "", "minipreguntas":[], "keywords":""}
#5 is the maximum number of permitted subquestions in the configuration2 page
for i in range(5):
try:
teachersJson["minipreguntas"].append({
"minipregunta": configuration["minip" + str(i+1)],
"minirespuesta": configuration["minir" + str(i+1)]
})
except:
break
return teachersJson
def extractZipData(ruta_zip):
"""
This function extracts the students's answers from the zip file (the one the teacher has in the task section).
Inputs:
ruta_zip: The path inherited from answersTodict
"""
#defining the path where the extracted info is to be stored
ruta_extraccion = create_file_path("StudentAnswers/", doctype= 1)
#extracting the info
archivo_zip = zipfile.ZipFile(ruta_zip, "r")
try:
archivo_zip.extractall(pwd=None, path=ruta_extraccion)
#archivo_zip.extract(pwd=None, path=ruta_extraccion)
except:
pass
archivo_zip.close()
def removeHtmlFromString(string):
"""
This function removes the html tags from the student's response.
Inputs:
-string: The student's response
Outputs:
-new_string: The filtered response
"""
string = string.encode('utf-8', 'replace')
string = string.decode('utf-8', 'replace')
new_string = ""
skipChar = 0
for char in string:
if char == "<":
skipChar = 1
elif char == ">":
skipChar = 0
else:
if not skipChar:
new_string = new_string+char
new_string = new_string.encode('utf-8', 'replace')
new_string = new_string.decode('utf-8', 'replace')
return new_string
def answersTodict(zip_path):
"""
This function extracts the students's answers and stacks them in one specific format so that it can be processed next.
Inputs:
ruta_zip: The path where the zip file is stored
Outputs:
studentAnswersDict: The dictionary with all the responses
"""
# path
remove('api/StudentAnswers/')
#extracting the data
extractZipData(zip_path)
studentAnswersDict = []
indx2=0
#stacking the information of each extracted folder
for work_folder in os.listdir(create_file_path("StudentAnswers/", doctype= 1)):
#print("work_folder: " + work_folder)
for student, indx in zip(os.listdir(create_file_path("StudentAnswers/" + work_folder, doctype= 1)), range(len(os.listdir(create_file_path("StudentAnswers/" + work_folder, doctype= 1))))):
student_name = student.split("(")
student_name = student_name[0]
print("student: " + str(student) + " - index: " + str(indx))
try:
#opening the file
#fichero1 = create_file_path("StudentAnswers/" + work_folder + "/" + student+ "/" + 'Adjuntos del envio/', doctype= 1)
fichero1 = create_file_path("StudentAnswers/" + work_folder + "/" + student + "/" + student+'_submissionText.html', doctype= 1)
print("Fichero:"+str(fichero1))
#where the actual response is
if os.path.exists(fichero1):
#fichero = open(create_file_path("StudentAnswers/" + work_folder + "/" + student + "/" + 'Adjuntos del envio/Respuesta enviada', doctype= 1), encoding='utf-8')
#fichero = create_file_path("StudentAnswers/" + work_folder + "/" + student + "/" + 'Adjuntos del envio/Respuesta enviada', doctype= 1)
#if os.path.exists(fichero):
# fichero = open(create_file_path("StudentAnswers/" + work_folder + "/" + student + "/" + 'Adjuntos del envio/Respuesta enviada', doctype= 1), encoding='utf-8')
#else:
fichero = open(create_file_path("StudentAnswers/" + work_folder + "/" + student + "/" + student+'_submissionText.html', doctype= 1), encoding='utf-8')
#print("Entra por acá")
#reading it
lineas = fichero.readlines()
#removing html
lineas[0] = removeHtmlFromString(lineas[0])
#saving it
studentAnswersDict.append({"respuesta":lineas[0], "hashed_id":student_name, "TableIndex":indx})
elif os.path.exists(create_file_path("StudentAnswers/" + work_folder, doctype= 1)) :
#print("Entra por acá2")
student_name2 = work_folder.split("_")
student_name = student_name2[0]
student_id2=student_name2[1]
student_assingsubmission = student_name2[2]
student_response = student_name2[3]
#print("Sigue acá2")
#print("StudentResponse"+str(student_response))
if student_response=='onlinetext':
fichero = open(create_file_path("StudentAnswers/" + work_folder+"/onlinetext.html", doctype= 1), encoding='utf-8')
lineas = fichero.readlines()
#removing html
lineas[0] = removeHtmlFromString(lineas[0])
#saving it
indx2+=1
studentAnswersDict.append({"respuesta":lineas[0], "hashed_id":student_name, "TableIndex":indx2})
#break
elif student_response!='file' or None:
studentAnswersDict.append({"respuesta":"", "hashed_id":student_name, "TableIndex":indx})
except:
studentAnswersDict.append({"respuesta":"", "hashed_id":student_name, "TableIndex":indx})
#saving the final dictionary
save_json(create_file_path('ApiStudentsDict.json', doctype= 1),studentAnswersDict)
return studentAnswersDict
zipFileInput = gr.inputs.File(label="1. Selecciona el .ZIP con las respuestas de los alumnos")
txtFileInput = gr.inputs.File(label="2. Selecciona el .txt con las preguntas y respuestas correctas. Escriba una pregunta en una sola línea y debajo la respuesta en la línea siguiente.")
orthographyPercentage = gr.inputs.Textbox(label="Ortografía",lines=1, placeholder="0",default=0.1, numeric=1)
syntaxPercentage = gr.inputs.Textbox(label="Sintaxis",lines=1, placeholder="0",default=0.1,numeric=1)
semanticPercentage = gr.inputs.Textbox(label="Semántica",lines=1, placeholder="0",default=0.8, numeric=1)
studentsRange = gr.inputs.Textbox(label="Estudiantes a evaluar",lines=1, placeholder="Dejar vacío para evaluar todos")
#dataFrameOutput = gr.outputs.Dataframe(headers=["Resultados"], max_rows=20, max_cols=None, overflow_row_behaviour="paginate", type="pandas", label="Resultado")
labelOutput = gr.outputs.Label(num_top_classes=None, type="auto", label="Output")
labelError = gr.outputs.Label(num_top_classes=None, type="auto", label="Errores")
downloadExcelButton = gr.outputs.File('Resultados')
iface = gr.Interface(fn=Main
, inputs=[zipFileInput, txtFileInput, orthographyPercentage, syntaxPercentage, semanticPercentage, studentsRange]
, outputs=[labelError, downloadExcelButton]
, title = "PLENTAS"
)
iface.launch(share = False,enable_queue=True, show_error =True, server_port= 7861)
#iface.launch(share = False,enable_queue=True, show_error =True)