X_train[var + '_na'] = pf.add_missing_indicator(X_train, var)
X_train[var] = pf.impute_na(X_train, var, config.IMPUTATION_DICT[var])
X_test[var + '_na'] = pf.add_missing_indicator(X_test, var)
X_test[var] = pf.impute_na(X_test, var, config.IMPUTATION_DICT[var])
# Group rare labels
for var in config.CATEGORICAL_VARS:
X_train[var] = pf.remove_rare_labels(X_train, var,
config.FREQUENT_LABELS[var])
X_test[var] = pf.remove_rare_labels(X_test, var,
config.FREQUENT_LABELS[var])
# encode categorical variables
for var in config.CATEGORICAL_VARS:
X_train = pf.encode_categorical(X_train, var)
X_test = pf.encode_categorical(X_test, var)
# check all dummies were added
X_train = pf.check_dummy_variables(X_train, config.DUMMY_VARIABLES)
X_test = pf.check_dummy_variables(X_test, config.DUMMY_VARIABLES)
# train scaler and save
scaler = pf.train_scaler(X_train, config.OUTPUT_SCALER_PATH)
# scale train set
X_train = pf.scale_features(X_train, config.OUTPUT_SCALER_PATH)
# train model and save
pf.train_model(X_train, y_train, config.OUTPUT_MODEL_PATH)
print('Finished training')
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
X_train = scaler.transform(X_train[config.FEATURES])
# entrenar y guardar el modelo
pf.train_model(X_train, np.log(y_train), config.OUTPUT_MODEL_PATH)
print('Enterenamiento terminado')
y_train_aux = X_train[config.AUX_TARGET]
# Add time-based features and the speed columns
X_train = pf.add_features(X_train)
# Add the region column
X_train = pf.add_region(X_train, config.REGION_BOUNDS)
# Apply cube-root transformation
for var in config.CBRT_TRANSFORM:
X_train[var] = pf.cbrt_transform(X_train, var)
y_train = pf.cbrt_transform(y_train)
# Train standard scaler on numerical variables only
scaled = X_train[config.NUM_VARS].copy()
scaler = pf.train_scaler(scaled, config.SCALER_PATH)
# Scale the numerical data
scaled.iloc[:,:] = pf.scale_features(scaled, config.SCALER_PATH)
# One-hot encode all the categorical variables
categoricals = []
for var in config.CAT_VARS:
categoricals.append(pf.encode_categorical(X_train, var))
# Final design matrix for training
X_train = pf.concat_dfs(scaled, categoricals)
# Assert we have the desired features
assert X_train.columns.tolist() == config.FEATURES
# impute numerical variables
medians = config_file[1]['Parameters'].get('imputation_dict')
for var in num_vars:
X_train = pf.add_missing_indicator(X_train, var)
X_train[var] = pf.impute_na(X_train, var, medians.get(var))
## Group rare labels
frequent_list = config_file[1]['Parameters'].get('frequent_labels')
for var in cat_vars:
X_train[var] = pf.remove_rare_labels(X_train, var, frequent_list)
# encode categorical variables
dummies = config_file[1]['Parameters'].get('dummy_variables')
for var in cat_vars:
X_train = pf.encode_categorical(X_train, var)
# check all dummies were added
X_train = pf.check_dummy_variables(X_train, dummies)
# train scaler and save
output_path = config_file[0]['Paths'].get('output_scaler_path')
output_model_path = config_file[0]['Paths'].get('output_model_path')
scaler = pf.train_scaler(X_train, output_path)
# scale train set
X_train = scaler.transform(X_train)
y_train = y_train.astype(int)
# train model and save
pf.train_model(X_train, y_train, output_model_path)
print('Finished training')
# add missing indicator #Note that I added this to conform train.py with notebook.
for var in ['age', 'fare']:
X_train = pf.add_missing_indicator(X_train, var)
# Group rare labels
for var in config.CATEGORICAL_VARS:
X_train = pf.remove_rare_labels(X_train, config.FREQUENT_LABELS, var)
# encode categorical variables
for var in config.CATEGORICAL_VARS:
X_train = pf.encode_categorical(X_train, var)
# check all dummies were added
X_train = pf.check_dummy_variables(X_train, config.DUMMY_VARIABLES)
# train scaler and save
pf.train_scaler(X_train, config.ORDERED_COLUMNS, config.OUTPUT_SCALER_PATH)
# scale train set
X_train = pf.scale_features(X_train, config.ORDERED_COLUMNS, config.OUTPUT_SCALER_PATH)
# train model and save
pf.train_model(X_train, config.ORDERED_COLUMNS, y_train, config.OUTPUT_MODEL_PATH)
print('Finished training')
