Skip to content

E
edx-platform
Commit 0e4b1142 by Vik Paruchuri
Options

Merge pull request #633 from edx/fix/vik/oe-state 

Fix/vik/oe state
parents 7d9607f0 3c55a44b
Showing with 238 additions and 16 deletions
common/lib/xmodule/xmodule/combined_open_ended_module.py
......@@ -20,7 +20,7 @@ V1_SETTINGS_ATTRIBUTES = [
]
V1_STUDENT_ATTRIBUTES = ["current_task_number", "task_states", "state",
"student_attempts", "ready_to_reset"]
"student_attempts", "ready_to_reset", "old_task_states"]
V1_ATTRIBUTES = V1_SETTINGS_ATTRIBUTES + V1_STUDENT_ATTRIBUTES
......@@ -183,6 +183,13 @@ class CombinedOpenEndedFields(object):
default=0,
scope=Scope.user_state
)
old_task_states = List(
help=("A list of lists of state dictionaries for student states that are saved."
"This field is only populated if the instructor changes tasks after"
"the module is created and students have attempted it (for example changes a self assessed problem to "
"self and peer assessed."),
scope = Scope.user_state
)
task_states = List(
help="List of state dictionaries of each task within this module.",
scope=Scope.user_state
......@@ -380,6 +387,9 @@ class CombinedOpenEndedModule(CombinedOpenEndedFields, XModule):
if self.task_states is None:
self.task_states = []
if self.old_task_states is None:
self.old_task_states = []
version_tuple = VERSION_TUPLES[self.version]
self.student_attributes = version_tuple.student_attributes
......
common/lib/xmodule/xmodule/js/src/combinedopenended/edit.coffee
......@@ -63,6 +63,8 @@ Write a persuasive essay to a newspaper reflecting your vies on censorship in li
else
@createXMLEditor()
@alertTaskRubricModification()
###
Creates the XML Editor and sets it as the current editor. If text is passed in,
it will replace the text present in the HTML template.
......@@ -93,6 +95,8 @@ Write a persuasive essay to a newspaper reflecting your vies on censorship in li
# Hide markdown-specific toolbar buttons
$(@element.find('.editor-bar')).hide()
alertTaskRubricModification: ->
return alert("Before you edit, please note that if you alter the tasks block or the rubric block of this question after students have submitted responses, it may result in their responses and grades being deleted! Use caution when altering problems that have already been released to students.")
###
Have the user confirm the one-way conversion to XML.
Returns true if the user clicked OK, else false.
......
common/lib/xmodule/xmodule/open_ended_grading_classes/combined_open_ended_modulev1.py
......@@ -35,8 +35,8 @@ TRUE_DICT = ["True", True, "TRUE", "true"]
HUMAN_TASK_TYPE = {
'selfassessment': "Self",
'openended': "edX",
'ml_grading.conf' : "AI",
'peer_grading.conf' : "Peer",
'ml_grading.conf': "AI",
'peer_grading.conf': "Peer",
}
HUMAN_STATES = {
......@@ -103,6 +103,8 @@ class CombinedOpenEndedV1Module():
self.current_task_number = instance_state.get('current_task_number', 0)
# This loads the states of the individual children
self.task_states = instance_state.get('task_states', [])
#This gets any old task states that have been persisted after the instructor changed the tasks.
self.old_task_states = instance_state.get('old_task_states', [])
# Overall state of the combined open ended module
self.state = instance_state.get('state', self.INITIAL)
......@@ -161,8 +163,77 @@ class CombinedOpenEndedV1Module():
self.task_xml = definition['task_xml']
self.location = location
self.fix_invalid_state()
self.setup_next_task()
def fix_invalid_state(self):
"""
Sometimes a teacher will change the xml definition of a problem in Studio.
This means that the state passed to the module is invalid.
If that is the case, moved it to old_task_states and delete task_states.
"""
# If we are on a task that is greater than the number of available tasks,
# it is an invalid state. If the current task number is greater than the number of tasks
# we have in the definition, our state is invalid.
if self.current_task_number > len(self.task_states) or self.current_task_number > len(self.task_xml):
self.current_task_number = max(min(len(self.task_states), len(self.task_xml)) - 1, 0)
#If the length of the task xml is less than the length of the task states, state is invalid
if len(self.task_xml) < len(self.task_states):
self.current_task_number = len(self.task_xml) - 1
self.task_states = self.task_states[:len(self.task_xml)]
#Loop through each task state and make sure it matches the xml definition
for (i, t) in enumerate(self.task_states):
tag_name = self.get_tag_name(self.task_xml[i])
children = self.child_modules()
task_xml = self.task_xml[i]
task_descriptor = children['descriptors'][tag_name](self.system)
task_parsed_xml = task_descriptor.definition_from_xml(etree.fromstring(task_xml), self.system)
try:
task = children['modules'][tag_name](
self.system,
self.location,
task_parsed_xml,
task_descriptor,
self.static_data,
instance_state=t,
)
#Loop through each attempt of the task and see if it is valid.
for att in task.child_history:
if "post_assessment" not in att:
continue
pa = att['post_assessment']
try:
pa = json.loads(pa)
except ValueError:
#This is okay, the value may or may not be json encoded.
pass
if tag_name == "openended" and isinstance(pa, list):
self.reset_task_state("Type is open ended and post assessment is a list.")
break
elif tag_name == "selfassessment" and not isinstance(pa, list):
self.reset_task_state("Type is self assessment and post assessment is not a list.")
break
#See if we can properly render the task. Will go into the exception clause below if not.
task.get_html(self.system)
except Exception as err:
#If one task doesn't match, the state is invalid.
self.reset_task_state("Could not parse task. {0}".format(err))
break
def reset_task_state(self, message=""):
"""
Resets the task states. Moves current task state to an old_state variable, and then makes the task number 0.
:param message: A message to put in the log.
:return: None
"""
info_message = "Combined open ended user state for user {0} in location {1} was invalid. It has been reset, and you now have a new attempt. {2}".format(self.system.anonymous_student_id, self.location.url(), message)
self.current_task_number = 0
self.student_attempts = 0
self.old_task_states.append(self.task_states)
self.task_states = []
log.info(info_message)
def get_tag_name(self, xml):
"""
Gets the tag name of a given xml block.
......@@ -315,7 +386,7 @@ class CombinedOpenEndedV1Module():
'accept_file_upload': self.accept_file_upload,
'location': self.location,
'legend_list': LEGEND_LIST,
'human_state': HUMAN_STATES.get(self.state,"Not started.")
'human_state': HUMAN_STATES.get(self.state, "Not started.")
}
return context
......@@ -471,14 +542,14 @@ class CombinedOpenEndedV1Module():
'feedback_dicts': feedback_dicts,
'grader_ids': grader_ids,
'submission_ids': submission_ids,
'success' : True
'success': True
}
return last_response_dict
def extract_human_name_from_task(self, task_xml):
tree = etree.fromstring(task_xml)
payload = tree.xpath("/openended/openendedparam/grader_payload")
if len(payload)==0:
if len(payload) == 0:
task_name = "selfassessment"
else:
inner_payload = json.loads(payload[0].text)
......@@ -775,7 +846,6 @@ class CombinedOpenEndedV1Module():
for i in xrange(0, len(self.task_states)):
# For each task, extract all student scores on that task (each attempt for each task)
last_response = self.get_last_response(i)
max_score = last_response.get('max_score', None)
score = last_response.get('all_scores', None)
if score is not None:
# Convert none scores and weight scores properly
......@@ -794,9 +864,9 @@ class CombinedOpenEndedV1Module():
else:
score = 0
if max_score is not None:
if self._max_score is not None:
# Weight the max score if it is not None
max_score *= float(weight)
max_score = self._max_score * float(weight)
else:
# Without a max_score, we cannot have a score!
score = None
......@@ -816,8 +886,7 @@ class CombinedOpenEndedV1Module():
'''
max_score = None
if self.check_if_done_and_scored():
last_response = self.get_last_response(self.current_task_number)
max_score = last_response['max_score']
max_score = self._max_score
return max_score
def get_progress(self):
......
common/lib/xmodule/xmodule/tests/test_combined_open_ended.py
......@@ -22,7 +22,9 @@ from xmodule.open_ended_grading_classes.grading_service_module import GradingSer
from xmodule.combined_open_ended_module import CombinedOpenEndedModule
from xmodule.modulestore import Location
from xmodule.tests import get_test_system, test_util_open_ended
from xmodule.tests.test_util_open_ended import MockQueryDict, DummyModulestore
from xmodule.tests.test_util_open_ended import (MockQueryDict, DummyModulestore, TEST_STATE_SA_IN,
MOCK_INSTANCE_STATE, TEST_STATE_SA, TEST_STATE_AI, TEST_STATE_AI2, TEST_STATE_AI2_INVALID,
TEST_STATE_SINGLE, TEST_STATE_PE_SINGLE)
import capa.xqueue_interface as xqueue_interface
......@@ -423,8 +425,6 @@ class CombinedOpenEndedModuleTest(unittest.TestCase):
)
def setUp(self):
# TODO: this constructor call is definitely wrong, but neither branch
# of the merge matches the module constructor. Someone (Vik?) should fix this.
self.combinedoe = CombinedOpenEndedV1Module(self.test_system,
self.location,
self.definition,
......@@ -434,16 +434,25 @@ class CombinedOpenEndedModuleTest(unittest.TestCase):
instance_state=self.static_data)
def test_get_tag_name(self):
"""
Test to see if the xml tag name is correct
"""
name = self.combinedoe.get_tag_name("<t>Tag</t>")
self.assertEqual(name, "t")
def test_get_last_response(self):
"""
See if we can parse the last response
"""
response_dict = self.combinedoe.get_last_response(0)
self.assertEqual(response_dict['type'], "selfassessment")
self.assertEqual(response_dict['max_score'], self.max_score)
self.assertEqual(response_dict['state'], CombinedOpenEndedV1Module.INITIAL)
def test_update_task_states(self):
"""
See if we can update the task states properly
"""
changed = self.combinedoe.update_task_states()
self.assertFalse(changed)
......@@ -454,6 +463,9 @@ class CombinedOpenEndedModuleTest(unittest.TestCase):
self.assertTrue(changed)
def test_get_max_score(self):
"""
Try to get the max score of the problem
"""
self.combinedoe.update_task_states()
self.combinedoe.state = "done"
self.combinedoe.is_scored = True
......@@ -461,24 +473,39 @@ class CombinedOpenEndedModuleTest(unittest.TestCase):
self.assertEqual(max_score, 1)
def test_container_get_max_score(self):
"""
See if we can get the max score from the actual xmodule
"""
#The progress view requires that this function be exposed
max_score = self.combinedoe_container.max_score()
self.assertEqual(max_score, None)
def test_container_weight(self):
"""
Check the problem weight in the container
"""
weight = self.combinedoe_container.weight
self.assertEqual(weight, 1)
def test_container_child_weight(self):
"""
Test the class to see if it picks up the right weight
"""
weight = self.combinedoe_container.child_module.weight
self.assertEqual(weight, 1)
def test_get_score(self):
"""
See if scoring works
"""
score_dict = self.combinedoe.get_score()
self.assertEqual(score_dict['score'], 0)
self.assertEqual(score_dict['total'], 1)
def test_alternate_orderings(self):
"""
Try multiple ordering of definitions to see if the problem renders different steps correctly.
"""
t1 = self.task_xml1
t2 = self.task_xml2
xml_to_test = [[t1], [t2], [t1, t1], [t1, t2], [t2, t2], [t2, t1], [t1, t2, t1]]
......@@ -496,9 +523,28 @@ class CombinedOpenEndedModuleTest(unittest.TestCase):
changed = combinedoe.update_task_states()
self.assertFalse(changed)
combinedoe = CombinedOpenEndedV1Module(self.test_system,
self.location,
definition,
descriptor,
static_data=self.static_data,
metadata=self.metadata,
instance_state={'task_states' : TEST_STATE_SA})
combinedoe = CombinedOpenEndedV1Module(self.test_system,
self.location,
definition,
descriptor,
static_data=self.static_data,
metadata=self.metadata,
instance_state={'task_states' : TEST_STATE_SA_IN})
def test_get_score_realistic(self):
instance_state = r"""{"ready_to_reset": false, "skip_spelling_checks": true, "current_task_number": 1, "weight": 5.0, "graceperiod": "1 day 12 hours 59 minutes 59 seconds", "graded": "True", "task_states": ["{\"child_created\": false, \"child_attempts\": 4, \"version\": 1, \"child_history\": [{\"answer\": \"The students\\u2019 data are recorded in the table below.\\r\\n\\r\\nStarting Mass (g)\\tEnding Mass (g)\\tDifference in Mass (g)\\r\\nMarble\\t 9.8\\t 9.4\\t\\u20130.4\\r\\nLimestone\\t10.4\\t 9.1\\t\\u20131.3\\r\\nWood\\t11.2\\t11.2\\t 0.0\\r\\nPlastic\\t 7.2\\t 7.1\\t\\u20130.1\\r\\nAfter reading the group\\u2019s procedure, describe what additional information you would need in order to replicate the expe\", \"post_assessment\": \"{\\\"submission_id\\\": 3097, \\\"score\\\": 0, \\\"feedback\\\": \\\"{\\\\\\\"spelling\\\\\\\": \\\\\\\"Spelling: Ok.\\\\\\\", \\\\\\\"grammar\\\\\\\": \\\\\\\"Grammar: More grammar errors than average.\\\\\\\", \\\\\\\"markup-text\\\\\\\": \\\\\\\"the students data are recorded in the <bg>table below . starting mass</bg> g ending mass g difference in mass g marble . . . limestone . . . wood . . . plastic . . . after reading the groups <bg>procedure , describe what additional</bg> information you would need in order to replicate the <bs>expe</bs>\\\\\\\"}\\\", \\\"success\\\": true, \\\"grader_id\\\": 3233, \\\"grader_type\\\": \\\"ML\\\", \\\"rubric_scores_complete\\\": true, \\\"rubric_xml\\\": \\\"<rubric><category><description>Response Quality</description><score>0</score><option points='0'>The response is not a satisfactory answer to the question. It either fails to address the question or does so in a limited way, with no evidence of higher-order thinking.</option><option points='1'>The response is a marginal answer to the question. It may contain some elements of a proficient response, but it is inaccurate or incomplete.</option><option points='2'>The response is a proficient answer to the question. It is generally correct, although it may contain minor inaccuracies. There is limited evidence of higher-order thinking.</option><option points='3'>The response is correct, complete, and contains evidence of higher-order thinking.</option></category></rubric>\\\"}\", \"score\": 0}, {\"answer\": \"After 24 hours, remove the samples from the containers and rinse each sample with distilled water.\\r\\nAllow the samples to sit and dry for 30 minutes.\\r\\nDetermine the mass of each sample.\\r\\nThe students\\u2019 data are recorded in the table below.\\r\\n\\r\\nStarting Mass (g)\\tEnding Mass (g)\\tDifference in Mass (g)\\r\\nMarble\\t 9.8\\t 9.4\\t\\u20130.4\\r\\nLimestone\\t10.4\\t 9.1\\t\\u20131.3\\r\\nWood\\t11.2\\t11.2\\t 0.0\\r\\nPlastic\\t 7.2\\t 7.1\\t\\u20130.1\\r\\nAfter reading the\", \"post_assessment\": \"[3]\", \"score\": 3}, {\"answer\": \"To replicate the experiment, the procedure would require more detail. One piece of information that is omitted is the amount of vinegar used in the experiment. It is also important to know what temperature the experiment was kept at during the 24 hours. Finally, the procedure needs to include details about the experiment, for example if the whole sample must be submerged.\", \"post_assessment\": \"[3]\", \"score\": 3}, {\"answer\": \"e the mass of four different samples.\\r\\nPour vinegar in each of four separate, but identical, containers.\\r\\nPlace a sample of one material into one container and label. Repeat with remaining samples, placing a single sample into a single container.\\r\\nAfter 24 hours, remove the samples from the containers and rinse each sample with distilled water.\\r\\nAllow the samples to sit and dry for 30 minutes.\\r\\nDetermine the mass of each sample.\\r\\nThe students\\u2019 data are recorded in the table below.\\r\\n\", \"post_assessment\": \"[3]\", \"score\": 3}, {\"answer\": \"\", \"post_assessment\": \"[3]\", \"score\": 3}], \"max_score\": 3, \"child_state\": \"done\"}", "{\"child_created\": false, \"child_attempts\": 0, \"version\": 1, \"child_history\": [{\"answer\": \"The students\\u2019 data are recorded in the table below.\\r\\n\\r\\nStarting Mass (g)\\tEnding Mass (g)\\tDifference in Mass (g)\\r\\nMarble\\t 9.8\\t 9.4\\t\\u20130.4\\r\\nLimestone\\t10.4\\t 9.1\\t\\u20131.3\\r\\nWood\\t11.2\\t11.2\\t 0.0\\r\\nPlastic\\t 7.2\\t 7.1\\t\\u20130.1\\r\\nAfter reading the group\\u2019s procedure, describe what additional information you would need in order to replicate the expe\", \"post_assessment\": \"{\\\"submission_id\\\": 3097, \\\"score\\\": 0, \\\"feedback\\\": \\\"{\\\\\\\"spelling\\\\\\\": \\\\\\\"Spelling: Ok.\\\\\\\", \\\\\\\"grammar\\\\\\\": \\\\\\\"Grammar: More grammar errors than average.\\\\\\\", \\\\\\\"markup-text\\\\\\\": \\\\\\\"the students data are recorded in the <bg>table below . starting mass</bg> g ending mass g difference in mass g marble . . . limestone . . . wood . . . plastic . . . after reading the groups <bg>procedure , describe what additional</bg> information you would need in order to replicate the <bs>expe</bs>\\\\\\\"}\\\", \\\"success\\\": true, \\\"grader_id\\\": 3233, \\\"grader_type\\\": \\\"ML\\\", \\\"rubric_scores_complete\\\": true, \\\"rubric_xml\\\": \\\"<rubric><category><description>Response Quality</description><score>0</score><option points='0'>The response is not a satisfactory answer to the question. It either fails to address the question or does so in a limited way, with no evidence of higher-order thinking.</option><option points='1'>The response is a marginal answer to the question. It may contain some elements of a proficient response, but it is inaccurate or incomplete.</option><option points='2'>The response is a proficient answer to the question. It is generally correct, although it may contain minor inaccuracies. There is limited evidence of higher-order thinking.</option><option points='3'>The response is correct, complete, and contains evidence of higher-order thinking.</option></category></rubric>\\\"}\", \"score\": 0}, {\"answer\": \"After 24 hours, remove the samples from the containers and rinse each sample with distilled water.\\r\\nAllow the samples to sit and dry for 30 minutes.\\r\\nDetermine the mass of each sample.\\r\\nThe students\\u2019 data are recorded in the table below.\\r\\n\\r\\nStarting Mass (g)\\tEnding Mass (g)\\tDifference in Mass (g)\\r\\nMarble\\t 9.8\\t 9.4\\t\\u20130.4\\r\\nLimestone\\t10.4\\t 9.1\\t\\u20131.3\\r\\nWood\\t11.2\\t11.2\\t 0.0\\r\\nPlastic\\t 7.2\\t 7.1\\t\\u20130.1\\r\\nAfter reading the\", \"post_assessment\": \"{\\\"submission_id\\\": 3098, \\\"score\\\": 0, \\\"feedback\\\": \\\"{\\\\\\\"spelling\\\\\\\": \\\\\\\"Spelling: Ok.\\\\\\\", \\\\\\\"grammar\\\\\\\": \\\\\\\"Grammar: Ok.\\\\\\\", \\\\\\\"markup-text\\\\\\\": \\\\\\\"after hours , remove the samples from the containers and rinse each sample with distilled water . allow the samples to sit and dry for minutes . determine the mass of each sample . the students data are recorded in the <bg>table below . starting mass</bg> g ending mass g difference in mass g marble . . . limestone . . . wood . . . plastic . . . after reading the\\\\\\\"}\\\", \\\"success\\\": true, \\\"grader_id\\\": 3235, \\\"grader_type\\\": \\\"ML\\\", \\\"rubric_scores_complete\\\": true, \\\"rubric_xml\\\": \\\"<rubric><category><description>Response Quality</description><score>0</score><option points='0'>The response is not a satisfactory answer to the question. It either fails to address the question or does so in a limited way, with no evidence of higher-order thinking.</option><option points='1'>The response is a marginal answer to the question. It may contain some elements of a proficient response, but it is inaccurate or incomplete.</option><option points='2'>The response is a proficient answer to the question. It is generally correct, although it may contain minor inaccuracies. There is limited evidence of higher-order thinking.</option><option points='3'>The response is correct, complete, and contains evidence of higher-order thinking.</option></category></rubric>\\\"}\", \"score\": 0}, {\"answer\": \"To replicate the experiment, the procedure would require more detail. One piece of information that is omitted is the amount of vinegar used in the experiment. It is also important to know what temperature the experiment was kept at during the 24 hours. Finally, the procedure needs to include details about the experiment, for example if the whole sample must be submerged.\", \"post_assessment\": \"{\\\"submission_id\\\": 3099, \\\"score\\\": 3, \\\"feedback\\\": \\\"{\\\\\\\"spelling\\\\\\\": \\\\\\\"Spelling: Ok.\\\\\\\", \\\\\\\"grammar\\\\\\\": \\\\\\\"Grammar: Ok.\\\\\\\", \\\\\\\"markup-text\\\\\\\": \\\\\\\"to replicate the experiment , the procedure would require <bg>more detail . one</bg> piece of information <bg>that is omitted is the</bg> amount of vinegar used in the experiment . it is also important to know what temperature the experiment was kept at during the hours . finally , the procedure needs to include details about the experiment , for example if the whole sample must be submerged .\\\\\\\"}\\\", \\\"success\\\": true, \\\"grader_id\\\": 3237, \\\"grader_type\\\": \\\"ML\\\", \\\"rubric_scores_complete\\\": true, \\\"rubric_xml\\\": \\\"<rubric><category><description>Response Quality</description><score>3</score><option points='0'>The response is not a satisfactory answer to the question. It either fails to address the question or does so in a limited way, with no evidence of higher-order thinking.</option><option points='1'>The response is a marginal answer to the question. It may contain some elements of a proficient response, but it is inaccurate or incomplete.</option><option points='2'>The response is a proficient answer to the question. It is generally correct, although it may contain minor inaccuracies. There is limited evidence of higher-order thinking.</option><option points='3'>The response is correct, complete, and contains evidence of higher-order thinking.</option></category></rubric>\\\"}\", \"score\": 3}, {\"answer\": \"e the mass of four different samples.\\r\\nPour vinegar in each of four separate, but identical, containers.\\r\\nPlace a sample of one material into one container and label. Repeat with remaining samples, placing a single sample into a single container.\\r\\nAfter 24 hours, remove the samples from the containers and rinse each sample with distilled water.\\r\\nAllow the samples to sit and dry for 30 minutes.\\r\\nDetermine the mass of each sample.\\r\\nThe students\\u2019 data are recorded in the table below.\\r\\n\", \"post_assessment\": \"{\\\"submission_id\\\": 3100, \\\"score\\\": 0, \\\"feedback\\\": \\\"{\\\\\\\"spelling\\\\\\\": \\\\\\\"Spelling: Ok.\\\\\\\", \\\\\\\"grammar\\\\\\\": \\\\\\\"Grammar: Ok.\\\\\\\", \\\\\\\"markup-text\\\\\\\": \\\\\\\"e the mass of four different samples . pour vinegar in <bg>each of four separate</bg> , but identical , containers . place a sample of one material into one container and label . repeat with remaining samples , placing a single sample into a single container . after hours , remove the samples from the containers and rinse each sample with distilled water . allow the samples to sit and dry for minutes . determine the mass of each sample . the students data are recorded in the table below . \\\\\\\"}\\\", \\\"success\\\": true, \\\"grader_id\\\": 3239, \\\"grader_type\\\": \\\"ML\\\", \\\"rubric_scores_complete\\\": true, \\\"rubric_xml\\\": \\\"<rubric><category><description>Response Quality</description><score>0</score><option points='0'>The response is not a satisfactory answer to the question. It either fails to address the question or does so in a limited way, with no evidence of higher-order thinking.</option><option points='1'>The response is a marginal answer to the question. It may contain some elements of a proficient response, but it is inaccurate or incomplete.</option><option points='2'>The response is a proficient answer to the question. It is generally correct, although it may contain minor inaccuracies. There is limited evidence of higher-order thinking.</option><option points='3'>The response is correct, complete, and contains evidence of higher-order thinking.</option></category></rubric>\\\"}\", \"score\": 0}, {\"answer\": \"\", \"post_assessment\": \"{\\\"submission_id\\\": 3101, \\\"score\\\": 0, \\\"feedback\\\": \\\"{\\\\\\\"spelling\\\\\\\": \\\\\\\"Spelling: Ok.\\\\\\\", \\\\\\\"grammar\\\\\\\": \\\\\\\"Grammar: Ok.\\\\\\\", \\\\\\\"markup-text\\\\\\\": \\\\\\\"invalid essay .\\\\\\\"}\\\", \\\"success\\\": true, \\\"grader_id\\\": 3241, \\\"grader_type\\\": \\\"ML\\\", \\\"rubric_scores_complete\\\": true, \\\"rubric_xml\\\": \\\"<rubric><category><description>Response Quality</description><score>0</score><option points='0'>The response is not a satisfactory answer to the question. It either fails to address the question or does so in a limited way, with no evidence of higher-order thinking.</option><option points='1'>The response is a marginal answer to the question. It may contain some elements of a proficient response, but it is inaccurate or incomplete.</option><option points='2'>The response is a proficient answer to the question. It is generally correct, although it may contain minor inaccuracies. There is limited evidence of higher-order thinking.</option><option points='3'>The response is correct, complete, and contains evidence of higher-order thinking.</option></category></rubric>\\\"}\", \"score\": 0}], \"max_score\": 3, \"child_state\": \"done\"}"], "attempts": "10000", "student_attempts": 0, "due": null, "state": "done", "accept_file_upload": false, "display_name": "Science Question -- Machine Assessed"}"""
instance_state = json.loads(instance_state)
"""
Try to parse the correct score from a json instance state
"""
instance_state = json.loads(MOCK_INSTANCE_STATE)
rubric = """
<rubric>
<rubric>
......@@ -526,6 +572,74 @@ class CombinedOpenEndedModuleTest(unittest.TestCase):
self.assertEqual(score_dict['score'], 15.0)
self.assertEqual(score_dict['total'], 15.0)
def generate_oe_module(self, task_state, task_number, task_xml):
"""
Return a combined open ended module with the specified parameters
"""
definition = {'prompt': etree.XML(self.prompt), 'rubric': etree.XML(self.rubric),
'task_xml': task_xml}
descriptor = Mock(data=definition)
instance_state = {'task_states': task_state, 'graded': True}
if task_number is not None:
instance_state.update({'current_task_number' : task_number})
combinedoe = CombinedOpenEndedV1Module(self.test_system,
self.location,
definition,
descriptor,
static_data=self.static_data,
metadata=self.metadata,
instance_state=instance_state)
return combinedoe
def ai_state_reset(self, task_state, task_number=None):
"""
See if state is properly reset
"""
combinedoe = self.generate_oe_module(task_state, task_number, [self.task_xml2])
html = combinedoe.get_html()
self.assertIsInstance(html, basestring)
score = combinedoe.get_score()
if combinedoe.is_scored:
self.assertEqual(score['score'], 0)
else:
self.assertEqual(score['score'], None)
def ai_state_success(self, task_state, task_number=None, iscore=2, tasks=None):
"""
See if state stays the same
"""
if tasks is None:
tasks = [self.task_xml1, self.task_xml2]
combinedoe = self.generate_oe_module(task_state, task_number, tasks)
html = combinedoe.get_html()
self.assertIsInstance(html, basestring)
score = combinedoe.get_score()
self.assertEqual(int(score['score']), iscore)
def test_ai_state_reset(self):
self.ai_state_reset(TEST_STATE_AI)
def test_ai_state2_reset(self):
self.ai_state_reset(TEST_STATE_AI2)
def test_ai_invalid_state(self):
self.ai_state_reset(TEST_STATE_AI2_INVALID)
def test_ai_state_rest_task_number(self):
self.ai_state_reset(TEST_STATE_AI, task_number=2)
self.ai_state_reset(TEST_STATE_AI, task_number=5)
self.ai_state_reset(TEST_STATE_AI, task_number=1)
self.ai_state_reset(TEST_STATE_AI, task_number=0)
def test_ai_state_success(self):
self.ai_state_success(TEST_STATE_AI)
def test_state_single(self):
self.ai_state_success(TEST_STATE_SINGLE, iscore=12)
def test_state_pe_single(self):
self.ai_state_success(TEST_STATE_PE_SINGLE, iscore=0, tasks=[self.task_xml2])
class OpenEndedModuleXmlTest(unittest.TestCase, DummyModulestore):
"""
......
common/lib/xmodule/xmodule/tests/test_util_open_ended.py
......@@ -52,3 +52,27 @@ class DummyModulestore(object):
location = Location(location)
descriptor = self.modulestore.get_instance(course.id, location, depth=None)
return descriptor.xmodule(self.test_system)
# Task state for a module with self assessment then instructor assessment.
TEST_STATE_SA_IN = ["{\"child_created\": false, \"child_attempts\": 2, \"version\": 1, \"child_history\": [{\"answer\": \"However venture pursuit he am mr cordial. Forming musical am hearing studied be luckily. Ourselves for determine attending how led gentleman sincerity. Valley afford uneasy joy she thrown though bed set. In me forming general prudent on country carried. Behaved an or suppose justice. Seemed whence how son rather easily and change missed. Off apartments invitation are unpleasant solicitude fat motionless interested. Hardly suffer wisdom wishes valley as an. As friendship advantages resolution it alteration stimulated he or increasing. \\r<br><br>Now led tedious shy lasting females off. Dashwood marianne in of entrance be on wondered possible building. Wondered sociable he carriage in speedily margaret. Up devonshire of he thoroughly insensible alteration. An mr settling occasion insisted distance ladyship so. Not attention say frankness intention out dashwoods now curiosity. Stronger ecstatic as no judgment daughter speedily thoughts. Worse downs nor might she court did nay forth these. \", \"post_assessment\": \"[3, 3, 2, 2, 2]\", \"score\": 12}, {\"answer\": \"Delightful remarkably mr on announcing themselves entreaties favourable. About to in so terms voice at. Equal an would is found seems of. The particular friendship one sufficient terminated frequently themselves. It more shed went up is roof if loud case. Delay music in lived noise an. Beyond genius really enough passed is up. \\r<br><br>John draw real poor on call my from. May she mrs furnished discourse extremely. Ask doubt noisy shade guest did built her him. Ignorant repeated hastened it do. Consider bachelor he yourself expenses no. Her itself active giving for expect vulgar months. Discovery commanded fat mrs remaining son she principle middleton neglected. Be miss he in post sons held. No tried is defer do money scale rooms. \", \"post_assessment\": \"[3, 3, 2, 2, 2]\", \"score\": 12}], \"max_score\": 12, \"child_state\": \"done\"}", "{\"child_created\": false, \"child_attempts\": 0, \"version\": 1, \"child_history\": [{\"answer\": \"However venture pursuit he am mr cordial. Forming musical am hearing studied be luckily. Ourselves for determine attending how led gentleman sincerity. Valley afford uneasy joy she thrown though bed set. In me forming general prudent on country carried. Behaved an or suppose justice. Seemed whence how son rather easily and change missed. Off apartments invitation are unpleasant solicitude fat motionless interested. Hardly suffer wisdom wishes valley as an. As friendship advantages resolution it alteration stimulated he or increasing. \\r<br><br>Now led tedious shy lasting females off. Dashwood marianne in of entrance be on wondered possible building. Wondered sociable he carriage in speedily margaret. Up devonshire of he thoroughly insensible alteration. An mr settling occasion insisted distance ladyship so. Not attention say frankness intention out dashwoods now curiosity. Stronger ecstatic as no judgment daughter speedily thoughts. Worse downs nor might she court did nay forth these. \", \"post_assessment\": \"{\\\"submission_id\\\": 1460, \\\"score\\\": 12, \\\"feedback\\\": \\\"{\\\\\\\"feedback\\\\\\\": \\\\\\\"\\\\\\\"}\\\", \\\"success\\\": true, \\\"grader_id\\\": 5413, \\\"grader_type\\\": \\\"IN\\\", \\\"rubric_scores_complete\\\": true, \\\"rubric_xml\\\": \\\"<rubric><category><description>\\\\nIdeas\\\\n</description><score>3</score><option points='0'>\\\\nDifficult for the reader to discern the main idea. Too brief or too repetitive to establish or maintain a focus.\\\\n</option><option points='1'>\\\\nAttempts a main idea. Sometimes loses focus or ineffectively displays focus.\\\\n</option><option points='2'>\\\\nPresents a unifying theme or main idea, but may include minor tangents. Stays somewhat focused on topic and task.\\\\n</option><option points='3'>\\\\nPresents a unifying theme or main idea without going off on tangents. Stays completely focused on topic and task.\\\\n</option></category><category><description>\\\\nContent\\\\n</description><score>3</score><option points='0'>\\\\nIncludes little information with few or no details or unrelated details. Unsuccessful in attempts to explore any facets of the topic.\\\\n</option><option points='1'>\\\\nIncludes little information and few or no details. Explores only one or two facets of the topic.\\\\n</option><option points='2'>\\\\nIncludes sufficient information and supporting details. (Details may not be fully developed; ideas may be listed.) Explores some facets of the topic.\\\\n</option><option points='3'>\\\\nIncludes in-depth information and exceptional supporting details that are fully developed. Explores all facets of the topic.\\\\n</option></category><category><description>\\\\nOrganization\\\\n</description><score>2</score><option points='0'>\\\\nIdeas organized illogically, transitions weak, and response difficult to follow.\\\\n</option><option points='1'>\\\\nAttempts to logically organize ideas. Attempts to progress in an order that enhances meaning, and demonstrates use of transitions.\\\\n</option><option points='2'>\\\\nIdeas organized logically. Progresses in an order that enhances meaning. Includes smooth transitions.\\\\n</option></category><category><description>\\\\nStyle\\\\n</description><score>2</score><option points='0'>\\\\nContains limited vocabulary, with many words used incorrectly. Demonstrates problems with sentence patterns.\\\\n</option><option points='1'>\\\\nContains basic vocabulary, with words that are predictable and common. Contains mostly simple sentences (although there may be an attempt at more varied sentence patterns).\\\\n</option><option points='2'>\\\\nIncludes vocabulary to make explanations detailed and precise. Includes varied sentence patterns, including complex sentences.\\\\n</option></category><category><description>\\\\nVoice\\\\n</description><score>2</score><option points='0'>\\\\nDemonstrates language and tone that may be inappropriate to task and reader.\\\\n</option><option points='1'>\\\\nDemonstrates an attempt to adjust language and tone to task and reader.\\\\n</option><option points='2'>\\\\nDemonstrates effective adjustment of language and tone to task and reader.\\\\n</option></category></rubric>\\\"}\", \"score\": 12}, {\"answer\": \"Delightful remarkably mr on announcing themselves entreaties favourable. About to in so terms voice at. Equal an would is found seems of. The particular friendship one sufficient terminated frequently themselves. It more shed went up is roof if loud case. Delay music in lived noise an. Beyond genius really enough passed is up. \\r<br><br>John draw real poor on call my from. May she mrs furnished discourse extremely. Ask doubt noisy shade guest did built her him. Ignorant repeated hastened it do. Consider bachelor he yourself expenses no. Her itself active giving for expect vulgar months. Discovery commanded fat mrs remaining son she principle middleton neglected. Be miss he in post sons held. No tried is defer do money scale rooms. \", \"post_assessment\": \"{\\\"submission_id\\\": 1462, \\\"score\\\": 12, \\\"feedback\\\": \\\"{\\\\\\\"feedback\\\\\\\": \\\\\\\"\\\\\\\"}\\\", \\\"success\\\": true, \\\"grader_id\\\": 5418, \\\"grader_type\\\": \\\"IN\\\", \\\"rubric_scores_complete\\\": true, \\\"rubric_xml\\\": \\\"<rubric><category><description>\\\\nIdeas\\\\n</description><score>3</score><option points='0'>\\\\nDifficult for the reader to discern the main idea. Too brief or too repetitive to establish or maintain a focus.\\\\n</option><option points='1'>\\\\nAttempts a main idea. Sometimes loses focus or ineffectively displays focus.\\\\n</option><option points='2'>\\\\nPresents a unifying theme or main idea, but may include minor tangents. Stays somewhat focused on topic and task.\\\\n</option><option points='3'>\\\\nPresents a unifying theme or main idea without going off on tangents. Stays completely focused on topic and task.\\\\n</option></category><category><description>\\\\nContent\\\\n</description><score>3</score><option points='0'>\\\\nIncludes little information with few or no details or unrelated details. Unsuccessful in attempts to explore any facets of the topic.\\\\n</option><option points='1'>\\\\nIncludes little information and few or no details. Explores only one or two facets of the topic.\\\\n</option><option points='2'>\\\\nIncludes sufficient information and supporting details. (Details may not be fully developed; ideas may be listed.) Explores some facets of the topic.\\\\n</option><option points='3'>\\\\nIncludes in-depth information and exceptional supporting details that are fully developed. Explores all facets of the topic.\\\\n</option></category><category><description>\\\\nOrganization\\\\n</description><score>2</score><option points='0'>\\\\nIdeas organized illogically, transitions weak, and response difficult to follow.\\\\n</option><option points='1'>\\\\nAttempts to logically organize ideas. Attempts to progress in an order that enhances meaning, and demonstrates use of transitions.\\\\n</option><option points='2'>\\\\nIdeas organized logically. Progresses in an order that enhances meaning. Includes smooth transitions.\\\\n</option></category><category><description>\\\\nStyle\\\\n</description><score>2</score><option points='0'>\\\\nContains limited vocabulary, with many words used incorrectly. Demonstrates problems with sentence patterns.\\\\n</option><option points='1'>\\\\nContains basic vocabulary, with words that are predictable and common. Contains mostly simple sentences (although there may be an attempt at more varied sentence patterns).\\\\n</option><option points='2'>\\\\nIncludes vocabulary to make explanations detailed and precise. Includes varied sentence patterns, including complex sentences.\\\\n</option></category><category><description>\\\\nVoice\\\\n</description><score>2</score><option points='0'>\\\\nDemonstrates language and tone that may be inappropriate to task and reader.\\\\n</option><option points='1'>\\\\nDemonstrates an attempt to adjust language and tone to task and reader.\\\\n</option><option points='2'>\\\\nDemonstrates effective adjustment of language and tone to task and reader.\\\\n</option></category></rubric>\\\"}\", \"score\": 12}], \"max_score\": 12, \"child_state\": \"post_assessment\"}"]
# Mock instance state. Should receive a score of 15.
MOCK_INSTANCE_STATE = r"""{"ready_to_reset": false, "skip_spelling_checks": true, "current_task_number": 1, "weight": 5.0, "graceperiod": "1 day 12 hours 59 minutes 59 seconds", "graded": "True", "task_states": ["{\"child_created\": false, \"child_attempts\": 4, \"version\": 1, \"child_history\": [{\"answer\": \"After 24 hours, remove the samples from the containers and rinse each sample with distilled water.\\r\\nAllow the samples to sit and dry for 30 minutes.\\r\\nDetermine the mass of each sample.\\r\\nThe students\\u2019 data are recorded in the table below.\\r\\n\\r\\nStarting Mass (g)\\tEnding Mass (g)\\tDifference in Mass (g)\\r\\nMarble\\t 9.8\\t 9.4\\t\\u20130.4\\r\\nLimestone\\t10.4\\t 9.1\\t\\u20131.3\\r\\nWood\\t11.2\\t11.2\\t 0.0\\r\\nPlastic\\t 7.2\\t 7.1\\t\\u20130.1\\r\\nAfter reading the\", \"post_assessment\": \"[3]\", \"score\": 3}, {\"answer\": \"To replicate the experiment, the procedure would require more detail. One piece of information that is omitted is the amount of vinegar used in the experiment. It is also important to know what temperature the experiment was kept at during the 24 hours. Finally, the procedure needs to include details about the experiment, for example if the whole sample must be submerged.\", \"post_assessment\": \"[3]\", \"score\": 3}, {\"answer\": \"e the mass of four different samples.\\r\\nPour vinegar in each of four separate, but identical, containers.\\r\\nPlace a sample of one material into one container and label. Repeat with remaining samples, placing a single sample into a single container.\\r\\nAfter 24 hours, remove the samples from the containers and rinse each sample with distilled water.\\r\\nAllow the samples to sit and dry for 30 minutes.\\r\\nDetermine the mass of each sample.\\r\\nThe students\\u2019 data are recorded in the table below.\\r\\n\", \"post_assessment\": \"[3]\", \"score\": 3}, {\"answer\": \"\", \"post_assessment\": \"[3]\", \"score\": 3}], \"max_score\": 3, \"child_state\": \"done\"}", "{\"child_created\": false, \"child_attempts\": 0, \"version\": 1, \"child_history\": [{\"answer\": \"The students\\u2019 data are recorded in the table below.\\r\\n\\r\\nStarting Mass (g)\\tEnding Mass (g)\\tDifference in Mass (g)\\r\\nMarble\\t 9.8\\t 9.4\\t\\u20130.4\\r\\nLimestone\\t10.4\\t 9.1\\t\\u20131.3\\r\\nWood\\t11.2\\t11.2\\t 0.0\\r\\nPlastic\\t 7.2\\t 7.1\\t\\u20130.1\\r\\nAfter reading the group\\u2019s procedure, describe what additional information you would need in order to replicate the expe\", \"post_assessment\": \"{\\\"submission_id\\\": 3097, \\\"score\\\": 0, \\\"feedback\\\": \\\"{\\\\\\\"spelling\\\\\\\": \\\\\\\"Spelling: Ok.\\\\\\\", \\\\\\\"grammar\\\\\\\": \\\\\\\"Grammar: More grammar errors than average.\\\\\\\", \\\\\\\"markup-text\\\\\\\": \\\\\\\"the students data are recorded in the <bg>table below . starting mass</bg> g ending mass g difference in mass g marble . . . limestone . . . wood . . . plastic . . . after reading the groups <bg>procedure , describe what additional</bg> information you would need in order to replicate the <bs>expe</bs>\\\\\\\"}\\\", \\\"success\\\": true, \\\"grader_id\\\": 3233, \\\"grader_type\\\": \\\"ML\\\", \\\"rubric_scores_complete\\\": true, \\\"rubric_xml\\\": \\\"<rubric><category><description>Response Quality</description><score>0</score><option points='0'>The response is not a satisfactory answer to the question. It either fails to address the question or does so in a limited way, with no evidence of higher-order thinking.</option><option points='1'>The response is a marginal answer to the question. It may contain some elements of a proficient response, but it is inaccurate or incomplete.</option><option points='2'>The response is a proficient answer to the question. It is generally correct, although it may contain minor inaccuracies. There is limited evidence of higher-order thinking.</option><option points='3'>The response is correct, complete, and contains evidence of higher-order thinking.</option></category></rubric>\\\"}\", \"score\": 0}, {\"answer\": \"After 24 hours, remove the samples from the containers and rinse each sample with distilled water.\\r\\nAllow the samples to sit and dry for 30 minutes.\\r\\nDetermine the mass of each sample.\\r\\nThe students\\u2019 data are recorded in the table below.\\r\\n\\r\\nStarting Mass (g)\\tEnding Mass (g)\\tDifference in Mass (g)\\r\\nMarble\\t 9.8\\t 9.4\\t\\u20130.4\\r\\nLimestone\\t10.4\\t 9.1\\t\\u20131.3\\r\\nWood\\t11.2\\t11.2\\t 0.0\\r\\nPlastic\\t 7.2\\t 7.1\\t\\u20130.1\\r\\nAfter reading the\", \"post_assessment\": \"{\\\"submission_id\\\": 3098, \\\"score\\\": 0, \\\"feedback\\\": \\\"{\\\\\\\"spelling\\\\\\\": \\\\\\\"Spelling: Ok.\\\\\\\", \\\\\\\"grammar\\\\\\\": \\\\\\\"Grammar: Ok.\\\\\\\", \\\\\\\"markup-text\\\\\\\": \\\\\\\"after hours , remove the samples from the containers and rinse each sample with distilled water . allow the samples to sit and dry for minutes . determine the mass of each sample . the students data are recorded in the <bg>table below . starting mass</bg> g ending mass g difference in mass g marble . . . limestone . . . wood . . . plastic . . . after reading the\\\\\\\"}\\\", \\\"success\\\": true, \\\"grader_id\\\": 3235, \\\"grader_type\\\": \\\"ML\\\", \\\"rubric_scores_complete\\\": true, \\\"rubric_xml\\\": \\\"<rubric><category><description>Response Quality</description><score>0</score><option points='0'>The response is not a satisfactory answer to the question. It either fails to address the question or does so in a limited way, with no evidence of higher-order thinking.</option><option points='1'>The response is a marginal answer to the question. It may contain some elements of a proficient response, but it is inaccurate or incomplete.</option><option points='2'>The response is a proficient answer to the question. It is generally correct, although it may contain minor inaccuracies. There is limited evidence of higher-order thinking.</option><option points='3'>The response is correct, complete, and contains evidence of higher-order thinking.</option></category></rubric>\\\"}\", \"score\": 0}, {\"answer\": \"To replicate the experiment, the procedure would require more detail. One piece of information that is omitted is the amount of vinegar used in the experiment. It is also important to know what temperature the experiment was kept at during the 24 hours. Finally, the procedure needs to include details about the experiment, for example if the whole sample must be submerged.\", \"post_assessment\": \"{\\\"submission_id\\\": 3099, \\\"score\\\": 3, \\\"feedback\\\": \\\"{\\\\\\\"spelling\\\\\\\": \\\\\\\"Spelling: Ok.\\\\\\\", \\\\\\\"grammar\\\\\\\": \\\\\\\"Grammar: Ok.\\\\\\\", \\\\\\\"markup-text\\\\\\\": \\\\\\\"to replicate the experiment , the procedure would require <bg>more detail . one</bg> piece of information <bg>that is omitted is the</bg> amount of vinegar used in the experiment . it is also important to know what temperature the experiment was kept at during the hours . finally , the procedure needs to include details about the experiment , for example if the whole sample must be submerged .\\\\\\\"}\\\", \\\"success\\\": true, \\\"grader_id\\\": 3237, \\\"grader_type\\\": \\\"ML\\\", \\\"rubric_scores_complete\\\": true, \\\"rubric_xml\\\": \\\"<rubric><category><description>Response Quality</description><score>3</score><option points='0'>The response is not a satisfactory answer to the question. It either fails to address the question or does so in a limited way, with no evidence of higher-order thinking.</option><option points='1'>The response is a marginal answer to the question. It may contain some elements of a proficient response, but it is inaccurate or incomplete.</option><option points='2'>The response is a proficient answer to the question. It is generally correct, although it may contain minor inaccuracies. There is limited evidence of higher-order thinking.</option><option points='3'>The response is correct, complete, and contains evidence of higher-order thinking.</option></category></rubric>\\\"}\", \"score\": 3}, {\"answer\": \"e the mass of four different samples.\\r\\nPour vinegar in each of four separate, but identical, containers.\\r\\nPlace a sample of one material into one container and label. Repeat with remaining samples, placing a single sample into a single container.\\r\\nAfter 24 hours, remove the samples from the containers and rinse each sample with distilled water.\\r\\nAllow the samples to sit and dry for 30 minutes.\\r\\nDetermine the mass of each sample.\\r\\nThe students\\u2019 data are recorded in the table below.\\r\\n\", \"post_assessment\": \"{\\\"submission_id\\\": 3100, \\\"score\\\": 0, \\\"feedback\\\": \\\"{\\\\\\\"spelling\\\\\\\": \\\\\\\"Spelling: Ok.\\\\\\\", \\\\\\\"grammar\\\\\\\": \\\\\\\"Grammar: Ok.\\\\\\\", \\\\\\\"markup-text\\\\\\\": \\\\\\\"e the mass of four different samples . pour vinegar in <bg>each of four separate</bg> , but identical , containers . place a sample of one material into one container and label . repeat with remaining samples , placing a single sample into a single container . after hours , remove the samples from the containers and rinse each sample with distilled water . allow the samples to sit and dry for minutes . determine the mass of each sample . the students data are recorded in the table below . \\\\\\\"}\\\", \\\"success\\\": true, \\\"grader_id\\\": 3239, \\\"grader_type\\\": \\\"ML\\\", \\\"rubric_scores_complete\\\": true, \\\"rubric_xml\\\": \\\"<rubric><category><description>Response Quality</description><score>0</score><option points='0'>The response is not a satisfactory answer to the question. It either fails to address the question or does so in a limited way, with no evidence of higher-order thinking.</option><option points='1'>The response is a marginal answer to the question. It may contain some elements of a proficient response, but it is inaccurate or incomplete.</option><option points='2'>The response is a proficient answer to the question. It is generally correct, although it may contain minor inaccuracies. There is limited evidence of higher-order thinking.</option><option points='3'>The response is correct, complete, and contains evidence of higher-order thinking.</option></category></rubric>\\\"}\", \"score\": 0}, {\"answer\": \"\", \"post_assessment\": \"{\\\"submission_id\\\": 3101, \\\"score\\\": 0, \\\"feedback\\\": \\\"{\\\\\\\"spelling\\\\\\\": \\\\\\\"Spelling: Ok.\\\\\\\", \\\\\\\"grammar\\\\\\\": \\\\\\\"Grammar: Ok.\\\\\\\", \\\\\\\"markup-text\\\\\\\": \\\\\\\"invalid essay .\\\\\\\"}\\\", \\\"success\\\": true, \\\"grader_id\\\": 3241, \\\"grader_type\\\": \\\"ML\\\", \\\"rubric_scores_complete\\\": true, \\\"rubric_xml\\\": \\\"<rubric><category><description>Response Quality</description><score>0</score><option points='0'>The response is not a satisfactory answer to the question. It either fails to address the question or does so in a limited way, with no evidence of higher-order thinking.</option><option points='1'>The response is a marginal answer to the question. It may contain some elements of a proficient response, but it is inaccurate or incomplete.</option><option points='2'>The response is a proficient answer to the question. It is generally correct, although it may contain minor inaccuracies. There is limited evidence of higher-order thinking.</option><option points='3'>The response is correct, complete, and contains evidence of higher-order thinking.</option></category></rubric>\\\"}\", \"score\": 0}], \"max_score\": 3, \"child_state\": \"done\"}"], "attempts": "10000", "student_attempts": 0, "due": null, "state": "done", "accept_file_upload": false, "display_name": "Science Question -- Machine Assessed"}"""
# Task state with self assessment only.
TEST_STATE_SA = ["{\"child_created\": false, \"child_attempts\": 1, \"version\": 1, \"child_history\": [{\"answer\": \"Censorship in the Libraries\\r<br>'All of us can think of a book that we hope none of our children or any other children have taken off the shelf. But if I have the right to remove that book from the shelf -- that work I abhor -- then you also have exactly the same right and so does everyone else. And then we have no books left on the shelf for any of us.' --Katherine Paterson, Author\\r<br><br>Write a persuasive essay to a newspaper reflecting your vies on censorship in libraries. Do you believe that certain materials, such as books, music, movies, magazines, etc., should be removed from the shelves if they are found offensive? Support your position with convincing arguments from your own experience, observations, and/or reading.\", \"post_assessment\": \"[3, 3, 2, 2, 2]\", \"score\": 12}], \"max_score\": 12, \"child_state\": \"done\"}", "{\"child_created\": false, \"child_attempts\": 0, \"version\": 1, \"child_history\": [{\"answer\": \"Censorship in the Libraries\\r<br>'All of us can think of a book that we hope none of our children or any other children have taken off the shelf. But if I have the right to remove that book from the shelf -- that work I abhor -- then you also have exactly the same right and so does everyone else. And then we have no books left on the shelf for any of us.' --Katherine Paterson, Author\\r<br><br>Write a persuasive essay to a newspaper reflecting your vies on censorship in libraries. Do you believe that certain materials, such as books, music, movies, magazines, etc., should be removed from the shelves if they are found offensive? Support your position with convincing arguments from your own experience, observations, and/or reading.\", \"post_assessment\": \"{\\\"submission_id\\\": 1461, \\\"score\\\": 12, \\\"feedback\\\": \\\"{\\\\\\\"feedback\\\\\\\": \\\\\\\"\\\\\\\"}\\\", \\\"success\\\": true, \\\"grader_id\\\": 5414, \\\"grader_type\\\": \\\"IN\\\", \\\"rubric_scores_complete\\\": true, \\\"rubric_xml\\\": \\\"<rubric><category><description>\\\\nIdeas\\\\n</description><score>3</score><option points='0'>\\\\nDifficult for the reader to discern the main idea. Too brief or too repetitive to establish or maintain a focus.\\\\n</option><option points='1'>\\\\nAttempts a main idea. Sometimes loses focus or ineffectively displays focus.\\\\n</option><option points='2'>\\\\nPresents a unifying theme or main idea, but may include minor tangents. Stays somewhat focused on topic and task.\\\\n</option><option points='3'>\\\\nPresents a unifying theme or main idea without going off on tangents. Stays completely focused on topic and task.\\\\n</option></category><category><description>\\\\nContent\\\\n</description><score>3</score><option points='0'>\\\\nIncludes little information with few or no details or unrelated details. Unsuccessful in attempts to explore any facets of the topic.\\\\n</option><option points='1'>\\\\nIncludes little information and few or no details. Explores only one or two facets of the topic.\\\\n</option><option points='2'>\\\\nIncludes sufficient information and supporting details. (Details may not be fully developed; ideas may be listed.) Explores some facets of the topic.\\\\n</option><option points='3'>\\\\nIncludes in-depth information and exceptional supporting details that are fully developed. Explores all facets of the topic.\\\\n</option></category><category><description>\\\\nOrganization\\\\n</description><score>2</score><option points='0'>\\\\nIdeas organized illogically, transitions weak, and response difficult to follow.\\\\n</option><option points='1'>\\\\nAttempts to logically organize ideas. Attempts to progress in an order that enhances meaning, and demonstrates use of transitions.\\\\n</option><option points='2'>\\\\nIdeas organized logically. Progresses in an order that enhances meaning. Includes smooth transitions.\\\\n</option></category><category><description>\\\\nStyle\\\\n</description><score>2</score><option points='0'>\\\\nContains limited vocabulary, with many words used incorrectly. Demonstrates problems with sentence patterns.\\\\n</option><option points='1'>\\\\nContains basic vocabulary, with words that are predictable and common. Contains mostly simple sentences (although there may be an attempt at more varied sentence patterns).\\\\n</option><option points='2'>\\\\nIncludes vocabulary to make explanations detailed and precise. Includes varied sentence patterns, including complex sentences.\\\\n</option></category><category><description>\\\\nVoice\\\\n</description><score>2</score><option points='0'>\\\\nDemonstrates language and tone that may be inappropriate to task and reader.\\\\n</option><option points='1'>\\\\nDemonstrates an attempt to adjust language and tone to task and reader.\\\\n</option><option points='2'>\\\\nDemonstrates effective adjustment of language and tone to task and reader.\\\\n</option></category></rubric>\\\"}\", \"score\": 12}], \"max_score\": 12, \"child_state\": \"post_assessment\"}"]
# Task state with self and then ai assessment.
TEST_STATE_AI = ["{\"child_created\": false, \"child_attempts\": 2, \"version\": 1, \"child_history\": [{\"answer\": \"In libraries, there should not be censorship on materials considering that it's an individual's decision to read what they prefer. There is no appropriate standard on what makes a book offensive to a group, so it should be undetermined as to what makes a book offensive. In a public library, many children, who the books are censored for, are with their parents. Parents should make an independent choice on what they can allow their children to read. Letting society ban a book simply for the use of inappropriate materials is ridiculous. If an author spent time creating a story, it should be appreciated, and should not put on a list of no-nos. If a certain person doesn't like a book's reputation, all they have to do is not read it. Even in school systems, librarians are there to guide kids to read good books. If a child wants to read an inappropriate book, the librarian will most likely discourage him or her not to read it. In my experience, I wanted to read a book that my mother suggested to me, but as I went to the school library it turned out to be a censored book. Some parents believe children should be ignorant about offensive things written in books, but honestly many of the same ideas are exploited to them everyday on television and internet. So trying to shield your child from the bad things may be a great thing, but the efforts are usually failed attempts. It also never occurs to the people censoring the books, that some people can't afford to buy the books they want to read. The libraries, for some, are the main means for getting books. To conclude there is very little reason to ban a book from the shelves. Many of the books banned have important lessons that can be obtained through reading it. If a person doesn't like a book, the simplest thing to do is not to pick it up.\", \"post_assessment\": \"[1, 1]\", \"score\": 2}, {\"answer\": \"This is another response\", \"post_assessment\": \"[1, 1]\", \"score\": 2}], \"max_score\": 2, \"child_state\": \"done\"}", "{\"child_created\": false, \"child_attempts\": 0, \"version\": 1, \"child_history\": [{\"answer\": \"In libraries, there should not be censorship on materials considering that it's an individual's decision to read what they prefer. There is no appropriate standard on what makes a book offensive to a group, so it should be undetermined as to what makes a book offensive. In a public library, many children, who the books are censored for, are with their parents. Parents should make an independent choice on what they can allow their children to read. Letting society ban a book simply for the use of inappropriate materials is ridiculous. If an author spent time creating a story, it should be appreciated, and should not put on a list of no-nos. If a certain person doesn't like a book's reputation, all they have to do is not read it. Even in school systems, librarians are there to guide kids to read good books. If a child wants to read an inappropriate book, the librarian will most likely discourage him or her not to read it. In my experience, I wanted to read a book that my mother suggested to me, but as I went to the school library it turned out to be a censored book. Some parents believe children should be ignorant about offensive things written in books, but honestly many of the same ideas are exploited to them everyday on television and internet. So trying to shield your child from the bad things may be a great thing, but the efforts are usually failed attempts. It also never occurs to the people censoring the books, that some people can't afford to buy the books they want to read. The libraries, for some, are the main means for getting books. To conclude there is very little reason to ban a book from the shelves. Many of the books banned have important lessons that can be obtained through reading it. If a person doesn't like a book, the simplest thing to do is not to pick it up.\", \"post_assessment\": \"{\\\"submission_id\\\": 6107, \\\"score\\\": 2, \\\"feedback\\\": \\\"{\\\\\\\"feedback\\\\\\\": \\\\\\\"\\\\\\\"}\\\", \\\"success\\\": true, \\\"grader_id\\\": 1898718, \\\"grader_type\\\": \\\"IN\\\", \\\"rubric_scores_complete\\\": true, \\\"rubric_xml\\\": \\\"<rubric><category><description>Writing Applications</description><score>1</score><option points='0'> The essay loses focus, has little information or supporting details, and the organization makes it difficult to follow.</option><option points='1'> The essay presents a mostly unified theme, includes sufficient information to convey the theme, and is generally organized well.</option></category><category><description> Language Conventions </description><score>1</score><option points='0'> The essay demonstrates a reasonable command of proper spelling and grammar. </option><option points='1'> The essay demonstrates superior command of proper spelling and grammar.</option></category></rubric>\\\"}\", \"score\": 2}, {\"answer\": \"This is another response\"}], \"max_score\": 2, \"child_state\": \"assessing\"}"]
# Task state with ai assessment only.
TEST_STATE_AI2 = ["{\"child_created\": false, \"child_attempts\": 0, \"version\": 1, \"child_history\": [{\"answer\": \"This isn't a real essay, and you should give me a zero on it. \", \"post_assessment\": \"{\\\"submission_id\\\": 18446, \\\"score\\\": [0, 1, 0], \\\"feedback\\\": [\\\"{\\\\\\\"feedback\\\\\\\": \\\\\\\"\\\\\\\"}\\\", \\\"{\\\\\\\"feedback\\\\\\\": \\\\\\\"\\\\\\\"}\\\", \\\"{\\\\\\\"feedback\\\\\\\": \\\\\\\"Zero it is! \\\\\\\"}\\\"], \\\"success\\\": true, \\\"grader_id\\\": [1944146, 1943188, 1940991], \\\"grader_type\\\": \\\"PE\\\", \\\"rubric_scores_complete\\\": [true, true, true], \\\"rubric_xml\\\": [\\\"<rubric><category><description>Writing Applications</description><score>0</score><option points='0'> The essay loses focus, has little information or supporting details, and the organization makes it difficult to follow.</option><option points='1'> The essay presents a mostly unified theme, includes sufficient information to convey the theme, and is generally organized well.</option></category><category><description> Language Conventions </description><score>0</score><option points='0'> The essay demonstrates a reasonable command of proper spelling and grammar. </option><option points='1'> The essay demonstrates superior command of proper spelling and grammar.</option></category></rubric>\\\", \\\"<rubric><category><description>Writing Applications</description><score>0</score><option points='0'> The essay loses focus, has little information or supporting details, and the organization makes it difficult to follow.</option><option points='1'> The essay presents a mostly unified theme, includes sufficient information to convey the theme, and is generally organized well.</option></category><category><description> Language Conventions </description><score>1</score><option points='0'> The essay demonstrates a reasonable command of proper spelling and grammar. </option><option points='1'> The essay demonstrates superior command of proper spelling and grammar.</option></category></rubric>\\\", \\\"<rubric><category><description>Writing Applications</description><score>0</score><option points='0'> The essay loses focus, has little information or supporting details, and the organization makes it difficult to follow.</option><option points='1'> The essay presents a mostly unified theme, includes sufficient information to convey the theme, and is generally organized well.</option></category><category><description> Language Conventions </description><score>0</score><option points='0'> The essay demonstrates a reasonable command of proper spelling and grammar. </option><option points='1'> The essay demonstrates superior command of proper spelling and grammar.</option></category></rubric>\\\"]}\", \"score\": 0}], \"max_score\": 2, \"child_state\": \"post_assessment\"}"]
# Invalid task state with ai assessment.
TEST_STATE_AI2_INVALID = ["{\"child_created\": false, \"child_attempts\": 0, \"version\": 1, \"child_history\": [{\"answer\": \"This isn't a real essay, and you should give me a zero on it. \", \"post_assessment\": \"{\\\"submission_id\\\": 18446, \\\"score\\\": [0, 1, 0], \\\"feedback\\\": [\\\"{\\\\\\\"feedback\\\\\\\": \\\\\\\"\\\\\\\"}\\\", \\\"{\\\\\\\"feedback\\\\\\\": \\\\\\\"\\\\\\\"}\\\", \\\"{\\\\\\\"feedback\\\\\\\": \\\\\\\"Zero it is! \\\\\\\"}\\\"], \\\"success\\\": true, \\\"grader_id\\\": [1943188, 1940991], \\\"grader_type\\\": \\\"PE\\\", \\\"rubric_scores_complete\\\": [true, true, true], \\\"rubric_xml\\\": [\\\"<rubric><category><description>Writing Applications</description><score>0</score><option points='0'> The essay loses focus, has little information or supporting details, and the organization makes it difficult to follow.</option><option points='1'> The essay presents a mostly unified theme, includes sufficient information to convey the theme, and is generally organized well.</option></category><category><description> Language Conventions </description><score>0</score><option points='0'> The essay demonstrates a reasonable command of proper spelling and grammar. </option><option points='1'> The essay demonstrates superior command of proper spelling and grammar.</option></category></rubric>\\\", \\\"<rubric><category><description>Writing Applications</description><score>0</score><option points='0'> The essay loses focus, has little information or supporting details, and the organization makes it difficult to follow.</option><option points='1'> The essay presents a mostly unified theme, includes sufficient information to convey the theme, and is generally organized well.</option></category><category><description> Language Conventions </description><score>1</score><option points='0'> The essay demonstrates a reasonable command of proper spelling and grammar. </option><option points='1'> The essay demonstrates superior command of proper spelling and grammar.</option></category></rubric>\\\", \\\"<rubric><category><description>Writing Applications</description><score>0</score><option points='0'> The essay loses focus, has little information or supporting details, and the organization makes it difficult to follow.</option><option points='1'> The essay presents a mostly unified theme, includes sufficient information to convey the theme, and is generally organized well.</option></category><category><description> Language Conventions </description><score>0</score><option points='0'> The essay demonstrates a reasonable command of proper spelling and grammar. </option><option points='1'> The essay demonstrates superior command of proper spelling and grammar.</option></category></rubric>\\\"]}\", \"score\": 0}], \"max_score\": 2, \"child_state\": \"post_assessment\"}"]
# Self assessment state.
TEST_STATE_SINGLE = ["{\"child_created\": false, \"child_attempts\": 1, \"version\": 1, \"child_history\": [{\"answer\": \"'All of us can think of a book that we hope none of our children or any other children have taken off the shelf. But if I have the right to remove that book from the shelf -- that work I abhor -- then you also have exactly the same right and so does everyone else. And then we have no books left on the shelf for any of us.' --Katherine Paterson, Author\\r<br><br>Write a persuasive essay to a newspaper reflecting your vies on censorship in libraries. Do you believe that certain materials, such as books, music, movies, magazines, etc., should be removed from the shelves if they are found offensive? Support your position with convincing arguments from your own experience, observations, and/or reading. \", \"post_assessment\": \"[3, 3, 2, 2, 2]\", \"score\": 12}], \"max_score\": 12, \"child_state\": \"done\"}"]
# Peer grading state.
TEST_STATE_PE_SINGLE = ["{\"child_created\": false, \"child_attempts\": 0, \"version\": 1, \"child_history\": [{\"answer\": \"Passage its ten led hearted removal cordial. Preference any astonished unreserved mrs. Prosperous understood middletons in conviction an uncommonly do. Supposing so be resolving breakfast am or perfectly. Is drew am hill from mr. Valley by oh twenty direct me so. Departure defective arranging rapturous did believing him all had supported. Family months lasted simple set nature vulgar him. Picture for attempt joy excited ten carried manners talking how. Suspicion neglected he resolving agreement perceived at an. \\r<br><br>Ye on properly handsome returned throwing am no whatever. In without wishing he of picture no exposed talking minutes. Curiosity continual belonging offending so explained it exquisite. Do remember to followed yourself material mr recurred carriage. High drew west we no or at john. About or given on witty event. Or sociable up material bachelor bringing landlord confined. Busy so many in hung easy find well up. So of exquisite my an explained remainder. Dashwood denoting securing be on perceive my laughing so. \\r<br><br>Ought these are balls place mrs their times add she. Taken no great widow spoke of it small. Genius use except son esteem merely her limits. Sons park by do make on. It do oh cottage offered cottage in written. Especially of dissimilar up attachment themselves by interested boisterous. Linen mrs seems men table. Jennings dashwood to quitting marriage bachelor in. On as conviction in of appearance apartments boisterous. \", \"post_assessment\": \"{\\\"submission_id\\\": 1439, \\\"score\\\": [0], \\\"feedback\\\": [\\\"{\\\\\\\"feedback\\\\\\\": \\\\\\\"\\\\\\\"}\\\"], \\\"success\\\": true, \\\"grader_id\\\": [5337], \\\"grader_type\\\": \\\"PE\\\", \\\"rubric_scores_complete\\\": [true], \\\"rubric_xml\\\": [\\\"<rubric><category><description>\\\\nIdeas\\\\n</description><score>0</score><option points='0'>\\\\nDifficult for the reader to discern the main idea. Too brief or too repetitive to establish or maintain a focus.\\\\n</option><option points='1'>\\\\nAttempts a main idea. Sometimes loses focus or ineffectively displays focus.\\\\n</option><option points='2'>\\\\nPresents a unifying theme or main idea, but may include minor tangents. Stays somewhat focused on topic and task.\\\\n</option><option points='3'>\\\\nPresents a unifying theme or main idea without going off on tangents. Stays completely focused on topic and task.\\\\n</option></category><category><description>\\\\nContent\\\\n</description><score>0</score><option points='0'>\\\\nIncludes little information with few or no details or unrelated details. Unsuccessful in attempts to explore any facets of the topic.\\\\n</option><option points='1'>\\\\nIncludes little information and few or no details. Explores only one or two facets of the topic.\\\\n</option><option points='2'>\\\\nIncludes sufficient information and supporting details. (Details may not be fully developed; ideas may be listed.) Explores some facets of the topic.\\\\n</option><option points='3'>\\\\nIncludes in-depth information and exceptional supporting details that are fully developed. Explores all facets of the topic.\\\\n</option></category><category><description>\\\\nOrganization\\\\n</description><score>0</score><option points='0'>\\\\nIdeas organized illogically, transitions weak, and response difficult to follow.\\\\n</option><option points='1'>\\\\nAttempts to logically organize ideas. Attempts to progress in an order that enhances meaning, and demonstrates use of transitions.\\\\n</option><option points='2'>\\\\nIdeas organized logically. Progresses in an order that enhances meaning. Includes smooth transitions.\\\\n</option></category><category><description>\\\\nStyle\\\\n</description><score>0</score><option points='0'>\\\\nContains limited vocabulary, with many words used incorrectly. Demonstrates problems with sentence patterns.\\\\n</option><option points='1'>\\\\nContains basic vocabulary, with words that are predictable and common. Contains mostly simple sentences (although there may be an attempt at more varied sentence patterns).\\\\n</option><option points='2'>\\\\nIncludes vocabulary to make explanations detailed and precise. Includes varied sentence patterns, including complex sentences.\\\\n</option></category><category><description>\\\\nVoice\\\\n</description><score>0</score><option points='0'>\\\\nDemonstrates language and tone that may be inappropriate to task and reader.\\\\n</option><option points='1'>\\\\nDemonstrates an attempt to adjust language and tone to task and reader.\\\\n</option><option points='2'>\\\\nDemonstrates effective adjustment of language and tone to task and reader.\\\\n</option></category></rubric>\\\"]}\", \"score\": 0}], \"max_score\": 12, \"child_state\": \"done\"}"]
\ No newline at end of file
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment