Skip to content

2
2022-158
Commit f1d8742a authored by OnellaNatalie's avatar OnellaNatalie
Browse files
Options

plagiarism calculation

parent b8db5760
Expand all Hide whitespace changes
Inline Side-by-side
Showing with 38 additions and 2243 deletions
backend/models/attribute_model.py deleted 100644 → 0
View file @ b8db5760
from config.database import db
class Attribute(db.Model):
id = db.Column(db.Integer, primary_key=True)
data_type = db.Column(db.String(50), nullable=False)
name = db.Column(db.String(50), nullable=False)
access_spec = db.Column(db.String(50), nullable=False)
class_id = db.Column(db.Integer)
def __repr__(self) -> str:
return 'Attribute>>> {self.content}'
backend/models/component_model.py deleted 100644 → 0
View file @ b8db5760
from sqlalchemy.orm import relationship
from config.database import db
class Component(db.Model):
id = db.Column(db.Integer, primary_key=True)
class_answer = db.Column(db.Integer, nullable=False)
name = db.Column(db.String(50), nullable=False)
type = db.Column(db.String(50), nullable=False)
def __repr__(self) -> str:
return 'Class>>> {self.content}'
backend/models/method_model.py deleted 100644 → 0
View file @ b8db5760
from config.database import db
class Method(db.Model):
id = db.Column(db.Integer, primary_key=True)
return_type = db.Column(db.String(50))
name = db.Column(db.String(50), nullable=False)
access_spec = db.Column(db.String(50))
class_id = db.Column(db.Integer)
def __repr__(self) -> str:
return 'Method>>> {self.content}'
backend/ner_models/model-best/config.cfg deleted 100644 → 0
View file @ b8db5760
[paths]
train = "./training_data.spacy"
dev = "./training_data.spacy"
vectors = null
init_tok2vec = null
[system]
gpu_allocator = null
seed = 0
[nlp]
lang = "en"
pipeline = ["tok2vec","ner"]
batch_size = 1000
disabled = []
before_creation = null
after_creation = null
after_pipeline_creation = null
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
[components]
[components.ner]
factory = "ner"
incorrect_spans_key = null
moves = null
scorer = {"@scorers":"spacy.ner_scorer.v1"}
update_with_oracle_cut_size = 100
[components.ner.model]
@architectures = "spacy.TransitionBasedParser.v2"
state_type = "ner"
extra_state_tokens = false
hidden_width = 64
maxout_pieces = 2
use_upper = true
nO = null
[components.ner.model.tok2vec]
@architectures = "spacy.Tok2VecListener.v1"
width = ${components.tok2vec.model.encode.width}
upstream = "*"
[components.tok2vec]
factory = "tok2vec"
[components.tok2vec.model]
@architectures = "spacy.Tok2Vec.v2"
[components.tok2vec.model.embed]
@architectures = "spacy.MultiHashEmbed.v2"
width = ${components.tok2vec.model.encode.width}
attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
rows = [5000,2500,2500,2500]
include_static_vectors = false
[components.tok2vec.model.encode]
@architectures = "spacy.MaxoutWindowEncoder.v2"
width = 96
depth = 4
window_size = 1
maxout_pieces = 3
[corpora]
[corpora.dev]
@readers = "spacy.Corpus.v1"
path = ${paths.dev}
max_length = 0
gold_preproc = false
limit = 0
augmenter = null
[corpora.train]
@readers = "spacy.Corpus.v1"
path = ${paths.train}
max_length = 0
gold_preproc = false
limit = 0
augmenter = null
[training]
dev_corpus = "corpora.dev"
train_corpus = "corpora.train"
seed = ${system.seed}
gpu_allocator = ${system.gpu_allocator}
dropout = 0.1
accumulate_gradient = 1
patience = 1600
max_epochs = 0
max_steps = 20000
eval_frequency = 200
frozen_components = []
annotating_components = []
before_to_disk = null
[training.batcher]
@batchers = "spacy.batch_by_words.v1"
discard_oversize = false
tolerance = 0.2
get_length = null
[training.batcher.size]
@schedules = "compounding.v1"
start = 100
stop = 1000
compound = 1.001
t = 0.0
[training.logger]
@loggers = "spacy.ConsoleLogger.v1"
progress_bar = false
[training.optimizer]
@optimizers = "Adam.v1"
beta1 = 0.9
beta2 = 0.999
L2_is_weight_decay = true
L2 = 0.01
grad_clip = 1.0
use_averages = false
eps = 0.00000001
learn_rate = 0.001
[training.score_weights]
ents_f = 1.0
ents_p = 0.0
ents_r = 0.0
ents_per_type = null
[pretraining]
[initialize]
vectors = ${paths.vectors}
init_tok2vec = ${paths.init_tok2vec}
vocab_data = null
lookups = null
before_init = null
after_init = null
[initialize.components]
[initialize.tokenizer]
\ No newline at end of file
backend/ner_models/model-best/meta.json deleted 100644 → 0
View file @ b8db5760
{
"lang":"en",
"name":"pipeline",
"version":"0.0.0",
"spacy_version":">=3.4.1,<3.5.0",
"description":"",
"author":"",
"email":"",
"url":"",
"license":"",
"spacy_git_version":"Unknown",
"vectors":{
"width":0,
"vectors":0,
"keys":0,
"name":null,
"mode":"default"
},
"labels":{
"tok2vec":[
],
"ner":[
"ACCESS_SP",
"ATTRIBUTE_NAME",
"DATA_TYPE",
"METHOD_NAME",
"MULTIPLICITY",
"PARAMETERS"
]
},
"pipeline":[
"tok2vec",
"ner"
],
"components":[
"tok2vec",
"ner"
],
"disabled":[
],
"performance":{
"ents_f":0.9938850387,
"ents_p":0.9918633035,
"ents_r":0.9959150327,
"ents_per_type":{
"ACCESS_SP":{
"p":0.995157385,
"r":0.9927536232,
"f":0.9939540508
},
"ATTRIBUTE_NAME":{
"p":0.9959183673,
"r":0.9959183673,
"f":0.9959183673
},
"DATA_TYPE":{
"p":0.9856321839,
"r":1.0,
"f":0.99276411
},
"METHOD_NAME":{
"p":0.993902439,
"r":0.993902439,
"f":0.993902439
},
"MULTIPLICITY":{
"p":0.9756097561,
"r":1.0,
"f":0.987654321
},
"PARAMETERS":{
"p":1.0,
"r":1.0,
"f":1.0
}
},
"tok2vec_loss":78.7692795898,
"ner_loss":1014.2115147574
}
}
\ No newline at end of file
backend/ner_models/model-best/ner/cfg deleted 100644 → 0
View file @ b8db5760
{
"moves":null,
"update_with_oracle_cut_size":100,
"multitasks":[
],
"min_action_freq":1,
"learn_tokens":false,
"beam_width":1,
"beam_density":0.0,
"beam_update_prob":0.0,
"incorrect_spans_key":null
}
\ No newline at end of file
backend/ner_models/model-best/ner/moves deleted 100644 → 0
View file @ b8db5760
moves{"0":{},"1":{"ACCESS_SP":414,"DATA_TYPE":346,"ATTRIBUTE_NAME":256,"METHOD_NAME":166,"MULTIPLICITY":102,"PARAMETERS":26},"2":{"ACCESS_SP":414,"DATA_TYPE":346,"ATTRIBUTE_NAME":256,"METHOD_NAME":166,"MULTIPLICITY":102,"PARAMETERS":26},"3":{"ACCESS_SP":414,"DATA_TYPE":346,"ATTRIBUTE_NAME":256,"METHOD_NAME":166,"MULTIPLICITY":102,"PARAMETERS":26},"4":{"ACCESS_SP":414,"DATA_TYPE":346,"ATTRIBUTE_NAME":256,"METHOD_NAME":166,"MULTIPLICITY":102,"PARAMETERS":26,"":1},"5":{"":1}}cfgneg_key
\ No newline at end of file
backend/ner_models/model-best/tokenizer deleted 100644 → 0
View file @ b8db5760
This diff is collapsed.
backend/ner_models/model-best/vocab/strings.json deleted 100644 → 0
View file @ b8db5760
This diff is collapsed.
backend/ner_models/model-best/vocab/vectors.cfg deleted 100644 → 0
View file @ b8db5760
{
"mode":"default"
}
\ No newline at end of file
backend/routes/assignment_routes.py
View file @ f1d8742a
......@@ -42,7 +42,7 @@ def create_assignment():
else:
assignment_obj = Assignment.query.filter_by(id=assignment_obj.id).first()
db.session.delete(assignment_obj)
db.commit()
db.session.commit()
return jsonify({'err': 'Something went wrong while generating model answers'}), HTTP_500_INTERNAL_SERVER_ERROR
......
backend/routes/plagiarism_routes.py
View file @ f1d8742a
......@@ -20,12 +20,15 @@ from models.use_case_answer import UseCaseAnswer
from models.actor_generalization_relationship import ActorGeneralizationRelationship
from services.similarity import similarity_components
use_case_diagram_plagiarism = Blueprint('use_case_diagram_plagiarism', __name__,
url_prefix='/api/v1/use_case_diagram_plagiarism')
@use_case_diagram_plagiarism.get('/filter')
@use_case_diagram_plagiarism.get('/similarities')
def get_use_case():
extent_component = None
include_component = None
user_case_association_component = None
......@@ -33,67 +36,58 @@ def get_use_case():
actor_generalization_component = None
actor_association_component = None
def similarity_components(use_case_answer, use_case_text):
user_cases = ActorANDUseCase.query.all()
for use_case1 in user_cases:
if use_case1.use_case_answer != use_case_answer and use_case1.text == use_case_text:
use_case1.plagiarism_count = 1
db.session.add(use_case1)
db.session.commit()
includes = IncludeRelationship.query.all()
extents = ExtendRelationship.query.all()
user_cases = ActorANDUseCase.query.all()
use_case_answers = UseCaseAnswer.query.all()
user_case_associations = UseCaseAssociationRelationship.query.all()
user_cases_generalizations = UseCaseGeneralizationRelationship.query.all()
actor_generalizations = ActorGeneralizationRelationship.query.all()
for user_case in user_cases:
if user_case.type == "use case":
for extent in extents:
if user_case.id == extent.connected_component_01:
extent_component = user_case
similarity_components(extent_component.use_case_answer, extent_component.text)
print("connected_component_01: : ", extent_component.text)
print("Extend component 1 : ", extent_component.text)
elif user_case.id == extent.connected_component_02:
extent_component = user_case
similarity_components(extent_component.use_case_answer, extent_component.text)
print("extent.connected_component_02: ", extent_component.text)
print("Extend component 2 : ", extent_component.text)
for include in includes:
if user_case.id == include.connected_component_01:
include_component = user_case
similarity_components(include_component.use_case_answer, include_component.text)
print("connected_component_01: ", include_component.text)
print("Include component 1 : ", include_component.text)
elif user_case.id == include.connected_component_02:
include_component = user_case
similarity_components(include_component.use_case_answer, include_component.text)
print("connected_component_02: ", include_component.text)
print("Include component 2 : ", include_component.text)
for user_case_association in user_case_associations:
if user_case.id == user_case_association.connected_component_01:
user_case_association_component = user_case
similarity_components(user_case_association_component.use_case_answer,
user_case_association_component.text)
print("connected_component_01: ", user_case_association_component.text)
print("User cases association component 1 : ", user_case_association_component.text)
elif user_case.id == user_case_association.connected_component_02:
user_case_association_component = user_case
similarity_components(user_case_association_component.use_case_answer,
user_case_association_component.text)
print("connected_component_02: ", user_case_association_component.text)
print("User cases association component 2 : ", user_case_association_component.text)
for user_cases_generalization in user_cases_generalizations:
if user_case.id == user_cases_generalization.connected_component_01:
user_cases_generalization_component = user_case
similarity_components(user_cases_generalization_component.use_case_answer,
user_cases_generalization_component.text)
print("connected_component_01: ", user_cases_generalization_component.text)
print("User cases generalization Component 1 : ", user_cases_generalization_component.text)
elif user_case.id == user_cases_generalization.connected_component_02:
user_cases_generalization_component = user_case
similarity_components(user_cases_generalization_component.use_case_answer,
user_cases_generalization_component.text)
print("connected_component_02: ", user_cases_generalization_component.text)
print("User cases generalization Component 2 : ", user_cases_generalization_component.text)
elif user_case.type == "actor":
for actor_generalization in actor_generalizations:
......@@ -101,30 +95,30 @@ def get_use_case():
actor_generalization_component = user_case
similarity_components(actor_generalization_component.use_case_answer,
actor_generalization_component.text)
print("connected_component_01: ", actor_generalization_component.text)
print("Actor generalization component 1 : ", actor_generalization_component.text)
elif user_case.id == actor_generalization.connected_component_02:
actor_generalization_component = user_case
similarity_components(actor_generalization_component.use_case_answer,
actor_generalization_component.text)
print("connected_component_02: ", actor_generalization_component.text)
print("actor")
print("Actor generalization component 2 : ", actor_generalization_component.text)
for actor_association in user_case_associations:
if user_case.id == actor_association.connected_component_01:
actor_association_component = user_case
similarity_components(actor_association_component.use_case_answer,
actor_association_component.text)
print("connected_component_01: ", user_case_association_component.text)
print("Actor association component 1 : ", actor_association_component.text)
elif user_case.id == actor_association.connected_component_02:
actor_association_component = user_case
similarity_components(actor_association_component.use_case_answer,
actor_association_component.text)
print("connected_component_02: ", actor_association_component.text)
print("Actor association component 2 : ", actor_association_component.text)
return jsonify({"Message": "Success"}), HTTP_200_OK
@use_case_diagram_plagiarism.get('/actors')
@use_case_diagram_plagiarism.get('/use_case_plagiarism_percentage')
def get_actor():
user_cases = ActorANDUseCase.query.all()
use_case_answers = UseCaseAnswer.query.all()
......@@ -142,17 +136,17 @@ def get_actor():
print(use_case_answer.id)
counter = 0
counter1 = 0
plagirism_count = 0
for user_case in user_cases:
if user_case.use_case_answer == use_case_answer.id:
counter += 1
if user_case.plagiarism_count == "1":
counter1 += 1
print("count :", counter)
print("All use cases and actors count :", counter)
print("similarity count :", counter1)
if counter != 0:
plagirism_count = counter1/counter * 100
print("plagirism_count :", plagirism_count)
print("Plagiarism Percentage :", plagirism_count)
......
backend/services/similarity.py 0 → 100644
View file @ f1d8742a
from models.actor_and_use_case import ActorANDUseCase
from config.database import db
def similarity_components(use_case_answer, use_case_text):
user_cases = ActorANDUseCase.query.all()
for use_case1 in user_cases:
if use_case1.use_case_answer != use_case_answer and use_case1.text == use_case_text:
use_case1.plagiarism_count = 1
db.session.add(use_case1)
db.session.commit()
backend/tensorflow_models/class/label/label_map.pbtxt
View file @ f1d8742a
item {
id: 1
name: 'association'
}
item {
id: 2
name: 'class'
}
item {
id: 3
name: 'composition'
}
item {
id: 4
name: 'indirect association'
}
item {
id: 5
name: 'inheritance'
}
item {
id: 6
name: 'interface'
}
item {
id: 7
name: 'realization'
id: 2
name: 'relationship'
}
\ 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