PoliBa-DeepLearning/NanoSocrates
2
0
Fork 0
Code Issues 3 Pull Requests 1 Actions Packages Projects Releases Wiki Activity

update cleaning pipeline with a new method to filter also by number of films,

Browse Source 
also updated the signature of the pipeline
This commit is contained in:
GassiGiuseppe 2025-10-04 19:00:05 +02:00
parent c2f9344c82
commit bbadd4c521
2 changed files with 20 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
Scripts/DataCleaning/filter.py
View File

@ -73,6 +73,10 @@ class PipelineApplier():
return RDF return RDF
def reduce_movie_list(self, starting_offset:int , ending_offset:int):
end = min(len(self.MOVIE_FILTER), ending_offset)
self.MOVIE_FILTER = self.MOVIE_FILTER.iloc[starting_offset:end].copy()
def drop_na_from_dataset(self, RDF: pd.DataFrame) -> pd.DataFrame: def drop_na_from_dataset(self, RDF: pd.DataFrame) -> pd.DataFrame:
# dataset has SubjectURI RelationshipURI ObjectURI # dataset has SubjectURI RelationshipURI ObjectURI
# want to drop the '' in them # want to drop the '' in them

23
Scripts/DataCleaning/pipeline.py
View File

@ -10,13 +10,19 @@ from Scripts.DataCleaning.data_output_models.rdf_completation_task import RDF_co
import pandas as pd import pandas as pd
class Pipeline(): class Pipeline():
def __init__(self): def __init__(self,
mask_task_dataset_path:str = "./Assets/Dataset/Tmp/rdf_mask.csv",
bpe_corpus_path:str = "./Assets/Dataset/Tmp/corpus.txt",
text_to_rdf_task_dataset_path:str = "./Assets/Dataset/Tmp/rdf_text.csv",
completation_rdf_task_dataset_path:str = "./Assets/Dataset/Tmp/rdf_completation.csv",
):
self.sql_endpoint = SqlEndpoint() self.sql_endpoint = SqlEndpoint()
# classes to manage taskes' datasets # classes to manage taskes' datasets
self.task_rdf_mask = RDF_mask_task_dataset("./Assets/Dataset/Tmp/rdf_mask.csv") self.task_rdf_mask = RDF_mask_task_dataset(mask_task_dataset_path)
self.task_bpe_corpus = BPE_corpus("./Assets/Dataset/Tmp/corpus.txt") self.task_bpe_corpus = BPE_corpus(bpe_corpus_path)
self.task_rdf_text = RDF_text_task_dataset("./Assets/Dataset/Tmp/rdf_text.csv") self.task_rdf_text = RDF_text_task_dataset(text_to_rdf_task_dataset_path)
self.task_rdf_completation = RDF_completation_task_dataset("./Assets/Dataset/Tmp/rdf_completation.csv") self.task_rdf_completation = RDF_completation_task_dataset(completation_rdf_task_dataset_path)
# prepare the filter # prepare the filter
# the filter applier needs to know the frequence of Movies and Relationship among all the Dataset # the filter applier needs to know the frequence of Movies and Relationship among all the Dataset
@ -113,6 +119,9 @@ class Pipeline():
movie_list = [117248, 147074, 113621, 1123, 117586, 90177, 71587, 138952, 144137, 148025] movie_list = [117248, 147074, 113621, 1123, 117586, 90177, 71587, 138952, 144137, 148025]
self.sql_endpoint.movie_ids = movie_list self.sql_endpoint.movie_ids = movie_list
def reduce_movie_list(self, starting_offset:int , ending_offset:int):
self.filter_applier.reduce_movie_list(starting_offset,ending_offset)
# there are a lot of settings to manage # there are a lot of settings to manage
@ -121,11 +130,11 @@ class Pipeline():
# in the use_toy_dataset , to change the toy dataset # in the use_toy_dataset , to change the toy dataset
# in _get_cleaned_movie_rows: to change how the pipeline behave # in _get_cleaned_movie_rows: to change how the pipeline behave
pipeline = Pipeline() #pipeline = Pipeline()
# pipeline.use_toy_dataset() # pipeline.use_toy_dataset()
# pipeline.execute_task_bpe_corpus() # pipeline.execute_task_bpe_corpus()
# pipeline.execute_task_rdf_mask() # pipeline.execute_task_rdf_mask()
# pipeline.execute_tasks_rdf_text() # pipeline.execute_tasks_rdf_text()
# pipeline.execute_task_rdf_completation() # pipeline.execute_task_rdf_completation()
pipeline.execute_all_task() # pipeline.execute_all_task()