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(df):
print('predict function b4 anything', df.shape)
print('predict function', df.shape)
df = pf.extract_time(df)
df = pf.log_transform(df, config.LOG_VARS)
df = pf.to_str(df, config.VAR_TO_STR)
df = pf.reduce_cardinality(df, df)
df = pf.cat_to_str(df)
encoder = ce.OneHotEncoder(use_cat_names=True)
df = encoder.fit_transform(df)
# scale variables
df = pf.scale_features(df[config.FEATURES], config.OUTPUT_SCALER_PATH)
# make predictions
predictions = pf.predict(df, 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
# 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])
# entrenear y guardar el escalador
scaler = pf.train_scaler(X_train[config.FEATURES], config.OUTPUT_SCALER_PATH)
# escalar variables
train = pf.trip_length(train, 'tpep_pickup_datetime', 'tpep_dropoff_datetime')
train = pf.remove_zero_or_neg_time(train, 'trip_seconds')
# divide data into train, val, test
train = df[df.tpep_dropoff_datetime <= pd.to_datetime('2017-06-30')]
test = df[df.tpep_dropoff_datetime >= pd.to_datetime('2017-11-01')]
val = train[train.tpep_dropoff_datetime >= pd.to_datetime('2017-06-01')]
train = train[train.tpep_dropoff_datetime < pd.to_datetime('2017-06-01')]
# continue preprocessing
train = pf.extract_time(train)
train = pf.log_transform(train, config.LOG_VARS)
train = pf.to_str(train, config.VAR_TO_STR)
train = pf.reduce_cardinality(train, train)
train = pf.cat_to_str(train)
encoder = ce.OneHotEncoder(use_cat_names=True)
X_train = encoder.fit_transform(train)
# y_train
y_train = train[config.TARGET]
# train scaler and save
scaler = pf.train_scaler(X_train[config.FEATURES], config.OUTPUT_SCALER_PATH)