def predict(data):
# impute NA
for var in config.CATEGORICAL_TO_IMPUTE:
data[var] = pf.impute_na(data, var, replacement='Missing')
data[config.NUMERICAL_TO_IMPUTE] = pf.impute_na(
data, config.NUMERICAL_TO_IMPUTE, replacement=config.LOTFRONTAGE_MODE)
# capture elapsed time
data[config.YEAR_VARIABLE] = pf.elapsed_years(data,
config.YEAR_VARIABLE,
ref_var='YrSold')
# log transform numerical variables
for var in config.NUMERICAL_LOG:
data[var] = pf.log_transform(data, var)
# Group rare labels
for var in config.CATEGORICAL_ENCODE:
data[var] = pf.remove_rare_labels(data, var,
config.FREQUENT_LABELS[var])
# encode variables
for var in config.CATEGORICAL_ENCODE:
data[var] = pf.encode_categorical(data, var,
config.ENCODING_MAPPINGS[var])
# scale variables
data = pf.scale_features(data[config.FEATURES], config.OUTPUT_SCALER_PATH)
# make predictions
predictions = pf.predict(data, config.OUTPUT_MODEL_PATH)
return predictions
def predict(data):
# imputar datos faltantes
for var in config.CATEGORICAL_TO_IMPUTE:
data[var] = pf.impute_na(data, var, replacement='Missing')
data[config.NUMERICAL_TO_IMPUTE] = pf.impute_na(data,
config.NUMERICAL_TO_IMPUTE,
replacement=config.LOTFRONTAGE_MODE)
# intervalos de tiempo
data[config.YEAR_VARIABLE] = pf.elapsed_years(data,
config.YEAR_VARIABLE, ref_var='YrSold')
# transformación logarítmica
for var in config.NUMERICAL_LOG:
data[var] = pf.log_transform(data, var)
# agrupación de etiquetas poco frecuentes
for var in config.CATEGORICAL_ENCODE:
data[var] = pf.remove_rare_labels(data, var, config.FREQUENT_LABELS[var])
# codificación de var. categóricas
for var in config.CATEGORICAL_ENCODE:
data[var] = pf.encode_categorical(data, var,
config.ENCODING_MAPPINGS[var])
# escalar variables
data = pf.scale_features(data[config.FEATURES],
config.OUTPUT_SCALER_PATH)
# obtener predicciones
predictions = pf.predict(data, config.OUTPUT_MODEL_PATH)
return predictions
data = pf.load_data(config.PATH_TO_DATASET)
# dividir el set
X_train, X_test, y_train, y_test = pf.divide_train_test(data, config.TARGET)
# imputar variables categóricas
for var in config.CATEGORICAL_TO_IMPUTE:
X_train[var] = pf.impute_na(X_train, var, replacement='Missing')
# imputar variables numéricas
X_train[config.NUMERICAL_TO_IMPUTE] = pf.impute_na(
X_train, config.NUMERICAL_TO_IMPUTE, replacement=config.LOTFRONTAGE_MODE)
# intervalos de tiempo
X_train[config.YEAR_VARIABLE] = pf.elapsed_years(X_train,
config.YEAR_VARIABLE,
ref_var='YrSold')
# transformación logarítmica
for var in config.NUMERICAL_LOG:
X_train[var] = pf.log_transform(X_train, var)
# agrupación de categorías poco frecuentes
for var in config.CATEGORICAL_ENCODE:
X_train[var] = pf.remove_rare_labels(X_train, var,
config.FREQUENT_LABELS[var])
# codificación de variables categóricas
for var in config.CATEGORICAL_ENCODE:
X_train[var] = pf.encode_categorical(X_train, var,
config.ENCODING_MAPPINGS[var])