def predict(data):
# extract first letter from cabin
pf.extract_cabin_letter(data, 'cabin')
# impute NA categorical
for var in ['age', 'fare']:
pf.add_missing_indicator(data, var)
# impute NA numerical
for var in config.CATEGORICAL_VARS:
pf.impute_na(data, var)
# Group rare labels
for var in config.CATEGORICAL_VARS:
pf.remove_rare_labels(data, var, config.FREQUENT_LABELS)
# encode variables
data = pf.encode_categorical(df, config.CATEGORICAL_VARS)
# scale variables
data = pf.scale_features(data, config.OUTPUT_SCALER_PATH)
# make predictions
predictions, _ = pf.predict(data, config.OUTPUT_MODEL_PATH)
return predictions
def predict(data):
# extract first letter from cabin
pf.extract_cabin_letter(data, 'cabin')
# impute NA numerical
for var in config.NUMERICAL_TO_IMPUTE:
pf.add_missing_indicator(data, var)
pf.impute_na(data, var, config.IMPUTATION_DICT[var])
# impute NA categorical
for var in config.CATEGORICAL_VARS:
pf.impute_na(data, var)
# Group rare labels
for var, labels in config.FREQUENT_LABELS.items():
pf.remove_rare_labels(data, var, labels)
# encode variables
for var in config.CATEGORICAL_VARS:
data = pf.encode_categorical(data, var)
# check all dummies were added
pf.check_dummy_variables(data, config.DUMMY_VARIABLES)
data = data[config.ALL_VARS]
# scale variables
data = pf.scale_features(data, config.OUTPUT_SCALER_PATH)
# make predictions
predictions = pf.predict(data, config.OUTPUT_MODEL_PATH)
return predictions
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):
# extract first letter from cabin
data['cabin'] = pf.extract_cabin_letter(data, var='cabin')
# impute NA categorical
for var in config.CATEGORICAL_VARS:
data[var] = pf.impute_na(data, var, replacement='Missing')
# impute NA numerical
for var in config.NUMERICAL_TO_IMPUTE:
data[var] = pf.add_missing_indicator(data, var)
# Group rare labels
for var in config.CATEGORICAL_VARS:
data[var] = pf.remove_rare_labels(data, var, frequent_labels = config.FREQUENT_LABELS[var])
# encode variables
data = pf.encode_categorical(data, var=config.CATEGORICAL_VARS)
# check all dummies were added
data = pf.check_dummy_variables(data, dummy_list = config.DUMMY_VARIABLES)
# 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):
# extract first letter from cabin
data["cabin"] = pf.extract_cabin_letter(data, "cabin")
# impute NA categorical
for var in config.CATEGORICAL_VARS:
data[var] = pf.impute_na(data, var, replacement="Missing")
# impute NA numerical
for var in config.NUMERICAL_TO_IMPUTE:
median_val = data[var].median()
data[var] = pf.impute_na(data, var, replacement=median_val)
# Group rare labels
for var in config.CATEGORICAL_VARS:
data[var] = pf.remove_rare_labels(data, var, config.FREQUENT_LABELS[var])
# encode variables
for var in config.CATEGORICAL_VARS:
data = pf.encode_categorical(data, var)
# check all dummies were added
data = pf.check_dummy_variables(data, config.DUMMY_VARIABLES)
# scale variables
data = pf.scale_features(data, config.OUTPUT_SCALER_PATH)
# make predictions
predictions = pf.predict(data, config.OUTPUT_MODEL_PATH)
return predictions
def predict(data):
# extract first letter from cabin
X_test = pf.extract_cabin_letter(data, config.IMPUTATION_DICT['cabin_variable'])
# impute NA categorical
X_test = pf.add_missing_indicator(X_test, config.CATEGORICAL_VARS)
# impute NA numerical
for var in config.NUMERICAL_TO_IMPUTE:
X_test = pf.impute_na(X_test,var,replace_by=config.IMPUTATION_DICT[var], add_na_columns=True)
# Group rare labels
X_test = pf.remove_rare_labels(X_test, config.FREQUENT_LABELS)
# encode variables
for var in config.CATEGORICAL_VARS:
X_test = pf.encode_categorical(X_test, var)
X_test.drop(labels=config.CATEGORICAL_VARS, axis=1, inplace=True)
# check all dummies were added
X_test = pf.check_dummy_variables(X_test, config.DUMMY_VARIABLES)
# scale variables
X_test = pf.scale_features(X_test, config.OUTPUT_SCALER_PATH)
# make predictions
predictions = pf.predict(X_test,config.OUTPUT_MODEL_PATH)
return predictions
def predict(data):
# extract first letter from cabin
data['cabin'] = pf.extract_cabin_letter(data, 'cabin')
# impute NA categorical
data[config.CATEGORICAL_VARS] = pf.impute_na(data[config.CATEGORICAL_VARS],
'Missing')
# impute NA numerical
data[config.NUMERICAL_TO_IMPUTE] = pf.impute_na(
data[config.NUMERICAL_TO_IMPUTE], 'Numerical')
# Group rare labels
for var in config.CATEGORICAL_VARS:
data[var] = pf.remove_rare_labels(data, var,
config.FREQUENT_LABELS[var])
# encode variables
data = pf.encode_categorical(data, config.CATEGORICAL_VARS)
print(data.shape)
# check all dummies were added
data = pf.check_dummy_variables(data, config.DUMMY_VARIABLES)
print(data.shape)
# scale variables
data = pf.scale_features(data, config.OUTPUT_SCALER_PATH)
# make predictions
predictions = pf.predict(data, config.OUTPUT_MODEL_PATH)
return predictions
def predict(data):
# impute categorical variables
for var in config.CATEGORICAL_VARS:
data[var] = pf.impute_na(data, var, replacement='Missing')
# impute numerical variables
for var in config.NUMERICAL_TO_IMPUTE:
# add missing indicator first
data[var + '_na'] = pf.add_missing_indicator(data, var)
# impute NA
data[var] = pf.impute_na(data, var,
replacement=config.IMPUTATION_DICT[var])
# Group rare labels
for var in config.CATEGORICAL_VARS:
data[var] = pf.remove_rare_labels(data, var,
config.FREQUENT_LABELS[var])
# encode categorical variables
for var in config.CATEGORICAL_VARS:
data = pf.encode_categorical(data, var)
# check all dummies were added
data = pf.check_dummy_variables(data, config.DUMMY_VARIABLES)
# scale variables
scaler = pf.scale_features(data,
config.OUTPUT_SCALER_PATH)
# make predictions
predictions = pf.predict(data, config.OUTPUT_MODEL_PATH)
return predictions
def predict(data):
# extract first letter from cabin
data["cabin"] = pf.extract_cabin_letter(data, "cabin")
# impute NA categorical
for var in config.CATEGORICAL_VARS:
data[var] = pf.impute_na(data, var, replacement='Missing')
# impute NA numerical
for var in config.NUMERICAL_TO_IMPUTE:
data[var + "_na"] = pf.add_missing_indicator(data, var)
median_train_var = config.IMPUTATION_DICT[var]
data[var] = pf.impute_na(data, var, replacement=median_train_var)
# Group rare labels
for var in config.CATEGORICAL_VARS:
freq_labels = config.FREQUENT_LABELS[var]
# Remove rare labels from both train and test set
data[var] = pf.remove_rare_labels(data, var, freq_labels)
# encode variables
for var in config.CATEGORICAL_VARS:
data = pf.encode_categorical(data, var)
# check all dummies were added
data = pf.check_dummy_variables(data, config.DUMMY_VARIABLES)
# scale variables
data = pf.scale_features(data, config.OUTPUT_SCALER_PATH)
# make predictions
predictions = pf.predict(data, config.OUTPUT_MODEL_PATH)
return predictions
def predict(data):
# extract first letter from cabin
data[config.EXTRACT_VARIABLE] = pf.extract_cabin_letter(
data, config.EXTRACT_VARIABLE)
# impute NA categorical
for var in config.CATEGORICAL_TO_ENCODE:
data[var] = pf.impute_na(data, var, replacement='Missing')
# impute NA numerical
for var in config.NUMERICAL_TO_IMPUTE:
if (var == 'age'):
data[var] = pf.add_missing_indicator(data, var, config.AGE_MEDIAN)
else:
data[var] = pf.add_missing_indicator(data, var, config.FARE_MEDIAN)
# Group rare labels
for var in config.CATEGORICAL_TO_ENCODE:
data[var] = pf.remove_rare_labels(data, var, config.RARE_VALUE)
# encode variables
for var in config.CATEGORICAL_TO_ENCODE:
data = pf.encode_categorical(data, var)
# check all dummies were added
pf.check_dummy_variables(data, config.DUMMY_VARIABLE)
# 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):
# extract first letter from cabin
data = pf.extract_cabin_letter(data, 'cabin')
# impute NA categorical
for var in config.CATEGORICAL_VARS:
data = pf.impute_na(data, var, config.IMPUTATION_DICT)
# impute NA numerical
for var in ['age', 'fare']:
data = pf.impute_na(data, var, config.IMPUTATION_DICT)
# add indicator variables
for var in ['age', 'fare']:
data = pf.add_missing_indicator(data, var)
# Group rare labels
for var in config.CATEGORICAL_VARS:
data = pf.remove_rare_labels(data, config.FREQUENT_LABELS, var)
# encode variables
for var in config.CATEGORICAL_VARS:
data = pf.encode_categorical(data, var)
# check all dummies were added
data = pf.check_dummy_variables(data, config.DUMMY_VARIABLES)
# scale variables
data = pf.scale_features(data, config.ORDERED_COLUMNS, config.OUTPUT_SCALER_PATH)
# make predictions
predictions = pf.predict(data, config.ORDERED_COLUMNS, 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
def predict(data):
data = pf.load_data(config.PATH_TO_DATASET)
X_train, X_test, y_train, y_test = pf.divide_train_test(data, config.TARGET)
data = X_test.copy()
# impute categorical variables
data = pf.add_missing_indicator(data, config.CATEGORICAL_VARS)
# extract first letter from cabin
data = pf.extract_cabin_letter(data, 'cabin')
# impute NA categorical
data = pf.impute_na(data, config.CATEGORICAL_VARS)
# impute NA numerical
data = pf.add_missing_indicator(data, config.NUMERICAL_TO_IMPUTE)
data = pf.impute_num(data, config.NUMERICAL_TO_IMPUTE)
# Group rare labels
data = pf.remove_rare_labels(data, config.CATEGORICAL_VARS)
# encode variables
data, data_features = pf.encode_categorical(data, config.CATEGORICAL_VARS)
print(data.head(1))
# check all dummies were added
data = pf.check_dummy_variables(data, config.DUMMY_VARIABLES)
# scale variables
data = pf.scale_features(data, config.OUTPUT_SCALER_PATH)
# make predictions
class_, pred = pf.predict(data, config.OUTPUT_MODEL_PATH)
return class_
def predict(data):
# extract first letter from cabin
data['cabin'] = pf.extract_cabin_letter(data, 'cabin')
# impute NA categorical
for el in config.CATEGORICAL_VARS:
data[el] = pf.impute_na(data, el, replacement='Missing')
# impute NA numerical
for el in config.NUMERICAL_TO_IMPUTE:
# add missing indicator first
data[el + '_NA'] = pf.add_missing_indicator(data, el)
# impute NA
data[el] = pf.impute_na(data,
el,
replacement=config.IMPUTATION_DICT[el])
# Group rare labels
for el in config.CATEGORICAL_VARS:
data[el] = pf.remove_rare_labels(data, el, config.FREQUENT_LABELS[el])
# encode variables
for el in config.CATEGORICAL_VARS:
data = pf.encode_categorical(data, el)
# check all dummies were added
data = pf.check_dummy_variables(data, config.DUMMY_VARIABLES)
# scale variables
data = pf.scale_features(data, config.OUTPUT_SCALER_PATH)
# make predictions
predictions = pf.predict(data, config.OUTPUT_MODEL_PATH)
return predictions
def predict(data):
# extract first letter from cabin
data = pf.extract_cabin_letter(data, 'cabin')
# impute NA categorical
for var in config.CATEGORICAL_VARS:
data[var] = pf.impute_na(data, var, replacement='Missing')
# impute NA numerical
for var in config.NUMERICAL_TO_IMPUTE:
data[var] = pf.impute_na(data,
var,
replacement=config.IMPUTATION_DICT[var])
# Group rare labels
for var in config.CATEGORICAL_VARS:
data[var] = pf.remove_rare_labels(data, var,
config.FREQUENT_LABELS[var])
# encode variables
for var in config.CATEGORICAL_VARS:
data = pf.encode_categorical(data, var)
# check all dummies were added
for var in config.DUMMY_VARIABLES:
if (var not in X_train.columns):
data[var] = 0
# scale variables
data = pf.scale_features(data, config.OUTPUT_SCALER_PATH)
# make predictions
predictions = pf.predict(data, config.OUTPUT_MODEL_PATH)
return predictions
X_train = pf.add_missing_indicator(X_train, config.CATEGORICAL_VARS)
X_test = pf.add_missing_indicator(X_test, config.CATEGORICAL_VARS)
# impute numerical variable
for var in config.NUMERICAL_TO_IMPUTE:
X_train = pf.impute_na(X_train,
var,
replace_by=config.IMPUTATION_DICT[var],
add_na_columns=True)
X_test = pf.impute_na(X_test,
var,
replace_by=config.IMPUTATION_DICT[var],
add_na_columns=True)
# Group rare labels
X_train = pf.remove_rare_labels(X_train, config.FREQUENT_LABELS)
X_test = pf.remove_rare_labels(X_test, config.FREQUENT_LABELS)
# 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)
X_train.drop(labels=config.CATEGORICAL_VARS, axis=1, inplace=True)
X_test.drop(labels=config.CATEGORICAL_VARS, axis=1, inplace=True)
# 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
pf.train_scaler(X_train, config.OUTPUT_SCALER_PATH)
X_train[var + '_na'] = pf.add_missing_indicator(X_train, var)
X_train[var] = pf.impute_na(X_train, var)
X_test[var + '_na'] = pf.add_missing_indicator(X_test, var)
X_test[var] = pf.impute_na(X_test, var)
# impute numerical variable
for var in config.NUMERICAL_TO_IMPUTE:
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)
# impute categorical variables
for var in config.CATEGORICAL_TO_ENCODE:
X_train[var] = pf.impute_na(X_train, var, replacement='Missing')
# impute numerical variable
for var in config.NUMERICAL_TO_IMPUTE:
if (var == 'age'):
X_train[var] = pf.add_missing_indicator(X_train, var, config.AGE_MEDIAN)
else:
X_train[var] = pf.add_missing_indicator(X_train, var, config.FARE_MEDIAN)
# Group rare labels
for var in config.CATEGORICAL_TO_ENCODE:
X_train[var] = pf.remove_rare_labels(X_train, var, config.RARE_VALUE)
# encode categorical variables
for var in config.CATEGORICAL_TO_ENCODE:
X_train = pf.encode_categorical(X_train, var)
# check all dummies were added
pf.check_dummy_variables(X_train, config.DUMMY_VARIABLE)
# train scaler and save
scaler = pf.train_scaler(X_train[config.FEATURES],
config.OUTPUT_SCALER_PATH)
# impute categorical variables
cat_vars = config_file[2]['Feature_Groups'].get('categorical_vars')
num_vars = config_file[2]['Feature_Groups'].get('numerical_to_impute')
for var in cat_vars:
X_train[var] = pf.impute_na(X_train, var, 'Missing')
# 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
for var in config.CATEGORICAL_VARS:
X_train[var] = pf.impute_na(X_train, var)
# impute numerical variable
for var in config.NUMERICAL_TO_IMPUTE:
X_train = pf.add_missing_indicator(X_train, var)
X_train[var] = pf.impute_na(X_train,
var,
value=config.IMPUTATION_DICT[var])
# Group rare labels
for col in config.CATEGORICAL_VARS:
X_train[col] = pf.remove_rare_labels(
X_train, col, freq_labels=config.FREQUENT_LABELS[col])
# encode categorical variables
oh = pf.train_encoder(X_train, config.CATEGORICAL_VARS,
config.OUTPUT_ENCODER_PATH)
X_train = pf.encode_categorical(X_train, config.CATEGORICAL_VARS,
config.OUTPUT_ENCODER_PATH)
print(X_train.shape)
print(X_train.head())
# check all dummies were added
X_train = pf.check_dummy_variables(X_train, config.DUMMY_VARIABLES)
# train scaler and save
# divide data set
X_train, X_test, y_train, y_test = pf.divide_train_test(df, config.TARGET)
# get first letter from cabin variable
X_train = pf.extract_cabin_letter(X_train, 'cabin')
# impute categorical variables
X_train = pf.add_missing_indicator(X_train, config.CATEGORICAL_VARS)
X_train = pf.impute_na(X_train, config.CATEGORICAL_VARS)
# impute numerical variable
X_train = pf.add_missing_indicator(X_train, config.NUMERICAL_TO_IMPUTE)
X_train = pf.impute_num(X_train, config.NUMERICAL_TO_IMPUTE)
# Group rare labels
X_train = pf.remove_rare_labels(X_train, config.CATEGORICAL_VARS)
# encode categorical variables
X_train, X_train_features = pf.encode_categorical(X_train,
config.CATEGORICAL_VARS)
# check dummy variables
X_check
# train scaler and save
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
xtrain, xtest, ytrain, ytest = pf.divide_train_test(df, config.TARGET)
# # get first letter from cabin variable
xtrain['cabin'] = pf.extract_cabin_letter(xtrain, 'cabin')
# # impute categorical variables
xtrain[config.CATEGORICAL_VARS] = pf.impute_na(xtrain[config.CATEGORICAL_VARS],
'Missing')
# # impute numerical variable
xtrain[config.NUMERICAL_TO_IMPUTE] = pf.impute_na(
xtrain[config.NUMERICAL_TO_IMPUTE], 'Numerical')
# # Group rare labels
for var in config.CATEGORICAL_VARS:
xtrain[var] = pf.remove_rare_labels(xtrain, var,
config.FREQUENT_LABELS[var])
# # encode categorical variables
xtrain = pf.encode_categorical(xtrain, config.CATEGORICAL_VARS)
# # check all dummies were added
xtrain = pf.check_dummy_variables(xtrain, config.DUMMY_VARIABLES)
# # train scaler and save
scaler = pf.train_scaler(xtrain, config.OUTPUT_SCALER_PATH)
# # scale train set
xtrain = pf.scale_features(xtrain, config.OUTPUT_SCALER_PATH)
# train model and save
pf.train_model(xtrain, ytrain, config.OUTPUT_MODEL_PATH)
# get first letter from cabin variable
pf.extract_cabin_letter(X_train, 'cabin')
# impute NA categorical
for var in ['age', 'fare']:
pf.add_missing_indicator(X_train, var)
# impute NA numerical
for var in config.CATEGORICAL_VARS:
pf.impute_na(X_train, var)
# Group rare labels
for var in config.CATEGORICAL_VARS:
pf.remove_rare_labels(X_train, var, config.FREQUENT_LABELS)
# encode variables
X_train = pf.encode_categorical(X_train, config.CATEGORICAL_VARS)
# scale variables
pf.train_scaler(X_train, config.OUTPUT_SCALER_PATH)
pf.scale_features(X_train, config.OUTPUT_SCALER_PATH)
pf.train_model(X_train, y_train, config.OUTPUT_MODEL_PATH)
# train scaler and save
# scale train set
# train model and save
# get first letter from cabin variable
X_train.loc[:, "cabin"] = pf.extract_cabin_letter(X_train, "cabin")
# impute categorical variables
for var in config.CATEGORICAL_VARS:
X_train.loc[:, var] = pf.impute_na(X_train, var, replacement="Missing")
# impute numerical variable
for var in config.NUMERICAL_TO_IMPUTE:
median_val = X_train[var].median()
X_train.loc[:, var] = pf.impute_na(X_train, var, replacement=median_val)
# Group rare labels
for var in config.CATEGORICAL_VARS:
X_train.loc[:, var] = pf.remove_rare_labels(X_train, var,
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
scaler = pf.train_scaler(X_train, config.OUTPUT_SCALER_PATH)
# scale train set
X_train = scaler.transform(X_train)
# train model and save
# impute categorical variables
for var in config.CATEGORICAL_VARS:
X_train[var] = pf.impute_na(X_train, var, replacement='Missing')
# impute numerical variable with median
for var in config.NUMERICAL_TO_IMPUTE:
X_train[var + "_na"] = pf.add_missing_indicator(X_train, var)
median_train_var = config.IMPUTATION_DICT[var]
X_train[var] = pf.impute_na(X_train, var, replacement=median_train_var)
# Group rare labels
for var in config.CATEGORICAL_VARS:
# Frequent labels found in Train set
freq_labels = config.FREQUENT_LABELS[var]
# Remove rare labels from both train and test set
X_train[var] = pf.remove_rare_labels(X_train, var, freq_labels)
# 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
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
# get first letter from cabin variable
pf.extract_cabin_letter(X_train, 'cabin')
# impute numerical variable
for var in config.NUMERICAL_TO_IMPUTE:
pf.add_missing_indicator(X_train, var)
pf.impute_na(X_train, var, config.IMPUTATION_DICT[var])
# impute categorical variables
for var in config.CATEGORICAL_VARS:
pf.impute_na(X_train, var)
# Group rare labels
for var, labels in config.FREQUENT_LABELS.items():
pf.remove_rare_labels(X_train, var, labels)
# encode categorical variables
for var in config.CATEGORICAL_VARS:
X_train = pf.encode_categorical(X_train, var)
# check all dummies were added
pf.check_dummy_variables(X_train, config.DUMMY_VARIABLES)
X_train = X_train[config.ALL_VARS]
# train scaler and save
pf.train_scaler(X_train, config.OUTPUT_SCALER_PATH)
# scale train set
X_train = pf.scale_features(X_train, config.OUTPUT_SCALER_PATH)
# impute numerical variable
# since the notebook just uses age and fare, we will ignore the "NUMERICAL TO IMPUTE"
for var in ['age', 'fare']:
X_train = pf.impute_na(X_train, var, config.IMPUTATION_DICT)
# 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