Skip to content

Fix correlation imputation report duplication #3

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Delpoo wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Fix correlation imputation report duplication #3

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
25 changes: 12 additions & 13 deletions ADRpy/analisis/Modulos/imputacion_correlacion/imputacion_correlacion.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -375,19 +375,18 @@ def imputacion_correlacion(df, path: str = "ADRpy/analisis/Data/Datos_aeronaves.
if not validos:
# registra advertencias y NO imputa
for m in descartados or [{"motivo": "Sin predictores válidos"}]:
for idx in faltantes:
reporte.append({
"Fila": idx,
"Parametro": objetivo,
"Valor imputado": np.nan,
"Confianza": 0.0,
"Corr": 0.0,
"k": 0,
"Tipo Modelo": m.get("tipo", "n/a"),
"Predictores": ",".join(m.get("predictores", [])),
"Penalizacion_k": 0.0,
"Advertencia": f"Modelo descartado: {m['motivo']}",
})
reporte.append({
"Fila": idx,
"Parametro": objetivo,
"Valor imputado": np.nan,
"Confianza": 0.0,
"Corr": 0.0,
"k": 0,
"Tipo Modelo": m.get("tipo", "n/a"),
"Predictores": ",".join(m.get("predictores", [])),
"Penalizacion_k": 0.0,
"Advertencia": f"Modelo descartado: {m['motivo']}",
})
continue

mejores = filtrar_mejores_modelos(validos)
Expand Down
35 changes: 21 additions & 14 deletions tests/test_imputacion_correlacion.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,19 +1,26 @@
import sys
import os

# Agregar la carpeta raíz al sistema de rutas
sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '../..')))

from ADRpy.analisis.Modulos.imputacion_correlacion.imputacion_correlacion import imputacion_correlacion
import tempfile
import pandas as pd
from ADRpy.analisis.Modulos.imputacion_correlacion import imputacion_correlacion

import numpy as np
from ADRpy.analisis.Modulos.imputacion_correlacion.imputacion_correlacion import imputacion_correlacion

def test_imputacion_correlacion_basica():
df, reporte = imputacion_correlacion('ADRpy/analisis/Data/Datos_aeronaves.xlsx')
assert not df.isna().any().any(), "Deberia imputar todos los valores faltantes"
# Verificamos que el valor imputado para Potencia en la fila 2 sea cercano al calculo esperado
valor = df.loc[2, 'Potencia']
assert round(valor, 3) == round(25.9691788448, 3)
assert 'Confianza' in reporte.columns
print("hola")
assert not df.isna().any().any()
assert 'Confianza_cv' in reporte.columns

def test_single_warning_per_missing_cell():
data = pd.DataFrame({
'Modelo': ['a', 'b', 'c'],
'Misión': [1, 1, 1],
'X': [1, 1, 1],
'Y': [np.nan, np.nan, 5],
})
tmp = tempfile.mktemp(suffix='.xlsx')
with pd.ExcelWriter(tmp, engine='openpyxl') as writer:
data.to_excel(writer, sheet_name='data_frame_prueba', index=False)
try:
_, reporte = imputacion_correlacion(None, path=tmp)
assert len(reporte) == data['Y'].isna().sum()
finally:
os.remove(tmp)