Ejecutando: enriquecimiento de los datos

df['DIA'] = df['FECHA'].dt.day
df['MES'] = df['FECHA'].dt.month
df['YEAR'] = df['FECHA'].dt.year

Pueden utilizar herramientas como Featuretools para automatizar el proceso de enriquecimiento de datos

En mi proyecto yo aplique feature engineering:

Crearemos una nueva categoria, para denotar el objetivo del ejercicio (por ejemplo, perder peso, aumentar masa muscular, mejorar la resistencia, etc.).

Posible clasificación de los tipos de ejercicios y sus objetivos principales correspondientes realizada por CHATGPT:

• burning: Strength, Hypertrophy, Power, Functional training.
• Stretching: Flexibility, Mobility, Rehabilitation, Stress reduction.
• Plyometrics: Power, Agility, Explosive Strength, Functional Training.
• Powerlifting: Strength, Hypertrophy, Power, Functional Training.
• Cardio: Cardiovascular resistance, Fat burning, Functional training.
• Olympic Weightlifting: Strength, Hypertrophy, Power, Functional Training.
• Strongman: Strength, Hypertrophy, Power, Functional Training.

# Creamos las nuevas columnas "TrainingGoal" en el DataFrame
df_data_processing["TrainingGoal_Strength"] = ""
df_data_processing["TrainingGoal_Hypertrophy"] = ""
df_data_processing["TrainingGoal_Power"] = ""
df_data_processing["TrainingGoal_Functional Training"] = ""
df_data_processing["TrainingGoal_Flexibility"] = ""
df_data_processing["TrainingGoal_Mobility"] = ""
df_data_processing["TrainingGoal_Rehabilitation"] = ""
df_data_processing["TrainingGoal_Stress Reduction"] = ""
df_data_processing["TrainingGoal_Agility"] = ""
df_data_processing["TrainingGoal_Explosive Strength"] = ""
df_data_processing["TrainingGoal_Cardiovascular Endurance"] = ""
df_data_processing["TrainingGoal_FatBurning"] = ""

# Asignamos un valor correspondiente a cada columna "TrainingGoal" para cada valor de la columna "Type"
for idx, value in df_data["Type"].iteritems():
    if value in ["Strength", 'Powerlifting', 'Olympic Weightlifting', 'Strongman']:
        df_data_processing.loc[idx, "TrainingGoal_Strength"] = 1.0
    else:
        df_data_processing.loc[idx, "TrainingGoal_Strength"] = 0.0


    if value in ["Strength", 'Powerlifting', 'Olympic Weightlifting', 'Strongman']:
        df_data_processing.loc[idx, "TrainingGoal_Hypertrophy"] = 1.0
    else:
        df_data_processing.loc[idx, "TrainingGoal_Hypertrophy"] = 0.0


    if value in ["Strength", 'Powerlifting', 'Olympic Weightlifting', 'Strongman', 'Plyometrics']:
        df_data_processing.loc[idx, "TrainingGoal_Power"] = 1.0
    else:
        df_data_processing.loc[idx, "TrainingGoal_Power"] = 0.0
        

    if value in ["Plyometrics", 'Powerlifting', 'Olympic Weightlifting', 'Strongman']:
        df_data_processing.loc[idx, "TrainingGoal_Functional Training"] = 1.0
    else:
        df_data_processing.loc[idx, "TrainingGoal_Functional Training"] = 0.0


    if value in ["Stretching"]:
        df_data_processing.loc[idx, "TrainingGoal_Flexibility"] = 1.0
    else:
        df_data_processing.loc[idx, "TrainingGoal_Flexibility"] = 0.0


    if value in ["Stretching"]:
        df_data_processing.loc[idx, "TrainingGoal_Mobility"] = 1.0
    else:
        df_data_processing.loc[idx, "TrainingGoal_Mobility"] = 0.0


    if value in ["Stretching"]:
        df_data_processing.loc[idx, "TrainingGoal_Rehabilitation"] = 1.0
    else:
        df_data_processing.loc[idx, "TrainingGoal_Rehabilitation"] = 0.0


    if value in ["Stretching"]:
        df_data_processing.loc[idx, "TrainingGoal_Stress Reduction"] = 1.0
    else:
        df_data_processing.loc[idx, "TrainingGoal_Stress Reduction"] = 0.0


    if value in ["Plyometrics"]:
        df_data_processing.loc[idx, "TrainingGoal_Agility"] = 1.0
    else:
        df_data_processing.loc[idx, "TrainingGoal_Agility"] = 0.0


    if value in ["Plyometrics"]:
        df_data_processing.loc[idx, "TrainingGoal_Explosive Strength"] = 1.0
    else:
        df_data_processing.loc[idx, "TrainingGoal_Explosive Strength"] = 0.0


    if value in ["Cardio"]:
        df_data_processing.loc[idx, "TrainingGoal_Cardiovascular Endurance"] = 1.0
    else:
        df_data_processing.loc[idx, "TrainingGoal_Cardiovascular Endurance"] = 0.0


    if value in ["Cardio"]:
        df_data_processing.loc[idx, "TrainingGoal_FatBurning"] = 1.0
    else:
        df_data_processing.loc[idx, "TrainingGoal_FatBurning"] = 0.0

Ya antes había planificado enriquecer los datos sin saber como se le llama a ese proceso 😅.

hay forma de que al momento de cargar el dataset, pandas te ponga la columna FECHA en formato datetime64.

compras_df = pd.read_csv(’/mnt/e/RICARDO/Documents/curso_crear_proyectos_ciencia_datos/notebooks/data/clean_compras.csv’,parse_dates=[‘FECHA’])