def main(args):
# retrieve dataset
start = time.time()
feature_df = pd.read_csv(os.path.join('training_set_features.csv'))
label_df = pd.read_csv(os.path.join('training_set_labels.csv'))
data_df = feature_df.merge(label_df, on='respondent_id', how='left')
print('\ntime to read in data...{:.3f}s'.format(time.time() - start))
# split data into train and test
train_df, test_df = train_test_split(data_df,
test_size=args.test_size,
random_state=args.seed,
stratify=data_df['seasonal_vaccine'])
# get features
columns = list(train_df.columns)
# remove select columns
remove_cols = ['respondent_id']
if len(remove_cols) > 0:
train_df = train_df.drop(columns=remove_cols)
test_df = test_df.drop(columns=remove_cols)
columns = [x for x in columns if x not in remove_cols]
# categorize attributes
features = {}
features['label'] = ['seasonal_vaccine']
features['numeric'] = []
features['categorical'] = list(
set(columns) - set(features['numeric']) - set(features['label']))
util.preprocess(train_df, test_df, features, processing=args.processing)
def main(args):
# retrieve dataset
start = time.time()
data_df = pd.read_csv('Surgical-deepnet.csv')
print('\ntime to read in data...{:.3f}s'.format(time.time() - start))
# split data into train and test
train_df, test_df = train_test_split(data_df,
test_size=args.test_size,
random_state=args.seed,
stratify=data_df['complication'])
# get features
columns = list(train_df.columns)
# remove select columns
remove_cols = []
if len(remove_cols) > 0:
train_df = train_df.drop(columns=remove_cols)
test_df = test_df.drop(columns=remove_cols)
columns = [x for x in columns if x not in remove_cols]
# categorize attributes
features = {}
features['label'] = ['complication']
features['numeric'] = [
'bmi', 'Age', 'ccsComplicationRate', 'ccsMort30Rate',
'complication_rsi', 'hour', 'mortality_rsi'
]
features['categorical'] = list(
set(columns) - set(features['numeric']) - set(features['label']))
util.preprocess(train_df, test_df, features, processing=args.processing)
def main(args):
# retrieve dataset
start = time.time()
data_df = pd.read_csv('WA_Fn-UseC_-Telco-Customer-Churn.csv')
print('\ntime to read in data...{:.3f}s'.format(time.time() - start))
# fix numeric column containing empy strings
data_df['TotalCharges'] = pd.to_numeric(data_df['TotalCharges'],
errors='coerce')
# split data into train and test
train_df, test_df = train_test_split(data_df,
test_size=args.test_size,
random_state=args.seed,
stratify=data_df['Churn'])
# get features
columns = list(train_df.columns)
# remove select columns
remove_cols = ['customerID']
if len(remove_cols) > 0:
train_df = train_df.drop(columns=remove_cols)
test_df = test_df.drop(columns=remove_cols)
columns = [x for x in columns if x not in remove_cols]
# categorize attributes
features = {}
features['label'] = ['Churn']
features['numeric'] = ['tenure', 'MonthlyCharges', 'TotalCharges']
features['categorical'] = list(
set(columns) - set(features['numeric']) - set(features['label']))
util.preprocess(train_df, test_df, features, processing=args.processing)
def main(args):
# categorize attributes
columns = ['age', 'workclass', 'fnlwgt', 'education', 'education-num', 'marital-status',
'occupation', 'relationship', 'race', 'sex', 'capital-gain', 'capital-loss',
'hours-per-week', 'native-country', 'label']
# retrieve dataset
start = time.time()
train_df = pd.read_csv('adult.data', header=None, names=columns)
test_df = pd.read_csv('adult.test', header=None, names=columns, skiprows=1)
print('\ntime to read in data...{:.3f}s'.format(time.time() - start))
# remove first row and fix label columns
test_df['label'] = test_df['label'].apply(lambda x: x.replace('.', ''))
# remove select columns
remove_cols = []
if len(remove_cols) > 0:
train_df = train_df.drop(columns=remove_cols)
test_df = test_df.drop(columns=remove_cols)
columns = [x for x in columns if x not in remove_cols]
# categorize attributes
features = {}
features['label'] = ['label']
features['numeric'] = ['age', 'fnlwgt', 'education-num', 'capital-gain',
'capital-loss', 'hours-per-week']
features['categorical'] = list(set(columns) - set(features['numeric']) - set(features['label']))
util.preprocess(train_df, test_df, features, processing=args.processing)
def main(args):
# retrieve dataset
start = time.time()
df = pd.read_csv('bank-additional_bank-additional-full.csv', sep=';')
print('\ntime to read in data...{:.3f}s'.format(time.time() - start))
# split data into train and test
train_df, test_df = train_test_split(df,
test_size=args.test_size,
random_state=args.seed,
stratify=df['y'])
# get features
columns = list(train_df.columns)
# remove select columns
remove_cols = []
if len(remove_cols) > 0:
train_df = train_df.drop(columns=remove_cols)
test_df = test_df.drop(columns=remove_cols)
columns = [x for x in columns if x not in remove_cols]
# categorize attributes
features = {}
features['label'] = ['y']
features['numeric'] = [
'age', 'duration', 'campaign', 'pdays', 'previous', 'emp.var.rate',
'cons.price.idx', 'cons.conf.idx', 'euribor3m', 'nr.employed'
]
features['categorical'] = list(
set(columns) - set(features['numeric']) - set(features['label']))
util.preprocess(train_df, test_df, features, processing=args.processing)
def main(args):
# retrieve dataset
start = time.time()
train_df = pd.read_csv('train.csv')
test_df = pd.read_csv('test.csv')
print('\ntime to read in data...{:.3f}s'.format(time.time() - start))
# get features
columns = list(train_df.columns)
# remove select columns
remove_cols = []
if len(remove_cols) > 0:
train_df = train_df.drop(columns=remove_cols)
test_df = test_df.drop(columns=remove_cols)
columns = [x for x in columns if x not in remove_cols]
# categorize attributes
features = {}
features['label'] = ['ACTION']
features['numeric'] = []
features['categorical'] = list(
set(columns) - set(features['numeric']) - set(features['label']))
util.preprocess(train_df, test_df, features, processing=args.processing)
def main(args):
# categorize attributes
columns = [
'age', 'workclass', 'industry_code', 'occupation_code', 'education',
'wage_per_hour', 'enrolled_in_edu', 'marital_status',
'major_industry_code', 'major_occupation_code', 'race',
'hispanic_origin', 'sex', 'union_member', 'unemployment_reason',
'employment', 'capital_gain', 'capital_loss', 'dividends', 'tax_staus',
'prev_region', 'prev_state', 'household_stat', 'household_summary',
'weight', 'migration_msa', 'migration_reg', 'migration_reg_move',
'1year_house', 'prev_sunbelt', 'n_persons_employer', 'parents',
'father_birth', 'mother_birth', 'self_birth', 'citizenship', 'income',
'business', 'taxable_income', 'veterans_admin', 'veterans_benfits',
'label'
]
# retrieve dataset
start = time.time()
train_df = pd.read_csv('census-income.data', header=None, names=columns)
test_df = pd.read_csv('census-income.test', header=None, names=columns)
print('\ntime to read in data...{:.3f}s'.format(time.time() - start))
# remove select columns
remove_cols = []
if len(remove_cols) > 0:
train_df = train_df.drop(columns=remove_cols)
test_df = test_df.drop(columns=remove_cols)
columns = [x for x in columns if x not in remove_cols]
# categorize attributes
features = {}
features['label'] = ['label']
features['numeric'] = [
'age', 'wage_per_hour', 'capital_gain', 'capital_loss', 'dividends',
'weight', 'n_persons_employer'
]
features['categorical'] = list(
set(columns) - set(features['numeric']) - set(features['label']))
util.preprocess(train_df, test_df, features, processing=args.processing)