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
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)
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
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['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(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):
# 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
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 = 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):
# remove duplicate
data = pf.drop_duplicate(data)
# Engineer BMI column
data['bmi'] = pf.bmi_feature(data, 'weight', 'height')
# Remove extreme outliers for ap_hi
data['ap_hi'] = pf.remove_outlier(data, 'ap_hi')
# Remove extreme outliers for ap_lo
data['ap_lo'] = pf.remove_outlier(data, 'ap_lo')
# 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):
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):
# 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
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 = 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
# Train the default linear regression model
pf.train_linreg_model(X_train, y_train, config.LINEAR_REG_MODEL_PATH)
# 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')
