import numpy as np
import pandas as pd
import multiprocessing
from functools import partial
from sklearn.preprocessing import LabelEncoder
from kairbnb.preprocessing import process_user_actions
from kairbnb.preprocessing import process_user_secs_elapsed
from kairbnb.io import load_users
NROWS = None
VERSION = '5'
if __name__ == '__main__':
# Load raw data
train_users, test_users = load_users(nrows=NROWS, na_values='-unknown-')
sessions = pd.read_csv('../data/sessions.csv',
nrows=NROWS, na_values='-unknown-')
# Join users
users = pd.concat((train_users, test_users), axis=0, ignore_index=True)
users = users.set_index('id')
# Drop date_first_booking column (empty since competition's restart)
users = users.drop('date_first_booking', axis=1)
# Remove weird age values
users.loc[users['age'] > 100, 'age'] = np.nan
users.loc[users['age'] < 13, 'age'] = np.nan
# Change type to date
import numpy as np
import pandas as pd
import multiprocessing
from functools import partial
from sklearn.preprocessing import LabelEncoder
from kairbnb.preprocessing import process_user_actions
from kairbnb.preprocessing import process_user_secs_elapsed
from kairbnb.io import load_users
NROWS = None
VERSION = '5'
if __name__ == '__main__':
# Load raw data
train_users, test_users = load_users(nrows=NROWS, na_values='-unknown-')
sessions = pd.read_csv('../data/sessions.csv',
nrows=NROWS,
na_values='-unknown-')
# Join users
users = pd.concat((train_users, test_users), axis=0, ignore_index=True)
users = users.set_index('id')
# Drop date_first_booking column (empty since competition's restart)
users = users.drop('date_first_booking', axis=1)
# Remove weird age values
users.loc[users['age'] > 100, 'age'] = np.nan
users.loc[users['age'] < 13, 'age'] = np.nan
#!/usr/bin/env python
from sklearn.preprocessing import LabelEncoder
from xgboost.sklearn import XGBClassifier
from kairbnb.io import generate_submission, load_users
VERSION = '5'
NAME = 'gb_' + VERSION
if __name__ == '__main__':
train_users, test_users = load_users(version=VERSION)
y_train = train_users['country_destination']
train_users.drop(['country_destination', 'id'], axis=1, inplace=True)
train_users = train_users.fillna(-1)
x_train = train_users.values
label_encoder = LabelEncoder()
encoded_y_train = label_encoder.fit_transform(y_train)
test_users_ids = test_users['id']
test_users.drop('id', axis=1, inplace=True)
test_users = test_users.fillna(-1)
x_test = test_users.values
clf = XGBClassifier(max_depth=7,
learning_rate=0.18,
n_estimators=80,
objective="rank:pairwise",
gamma=0,
min_child_weight=1,
import pandas as pd
from kairbnb.preprocessing import one_hot_encoding
from kairbnb.io import load_users
VERSION = '5'
if __name__ == '__main__':
# Load raw data
train_users, test_users = load_users(version=VERSION)
# Join users
users = pd.concat((train_users, test_users), axis=0, ignore_index=True)
# Set ID as index
users = users.set_index('id')
train_users = train_users.set_index('id')
test_users = test_users.set_index('id')
# Drop columns
drop_list = [
'date_account_created',
'date_first_active',
'timestamp_first_active'
]
users.drop(drop_list, axis=1, inplace=True)
# IDEA: Add interaction features
from kairbnb.io import load_users
VERSION = '1'
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('-d', '--max_depth', default=7, type=int)
parser.add_argument('-lr', '--learning_rate', default=0.18, type=float)
parser.add_argument('-n', '--n_estimators', default=80, type=int)
parser.add_argument('-ct', '--colsample_bytree', default=1, type=float)
parser.add_argument('-cl', '--colsample_bylevel', default=1, type=float)
parser.add_argument('-sub', '--subsample', default=1, type=float)
parser.add_argument('-md', '--max_delta', default=0, type=float)
args = parser.parse_args()
train_users, _ = load_users(version=VERSION)
train_users.fillna(-1, inplace=True)
y_train = train_users['country_destination']
train_users.drop(['country_destination', 'id'], axis=1, inplace=True)
x_train = train_users.values
label_encoder = LabelEncoder()
encoded_y_train = label_encoder.fit_transform(y_train)
xgb = XGBClassifier(
max_depth=args.max_depth,
learning_rate=args.learning_rate,
n_estimators=args.n_estimators,
objective="multi:softprob",
gamma=0,
min_child_weight=1,
from kairbnb.io import load_users
VERSION = '1'
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('-d', '--max_depth', default=7, type=int)
parser.add_argument('-lr', '--learning_rate', default=0.18, type=float)
parser.add_argument('-n', '--n_estimators', default=80, type=int)
parser.add_argument('-ct', '--colsample_bytree', default=1, type=float)
parser.add_argument('-cl', '--colsample_bylevel', default=1, type=float)
parser.add_argument('-sub', '--subsample', default=1, type=float)
parser.add_argument('-md', '--max_delta', default=0, type=float)
args = parser.parse_args()
train_users, _ = load_users(version=VERSION)
train_users.fillna(-1, inplace=True)
y_train = train_users['country_destination']
train_users.drop(['country_destination', 'id'], axis=1, inplace=True)
x_train = train_users.values
label_encoder = LabelEncoder()
encoded_y_train = label_encoder.fit_transform(y_train)
xgb = XGBClassifier(max_depth=args.max_depth,
learning_rate=args.learning_rate,
n_estimators=args.n_estimators,
objective="multi:softprob",
gamma=0,
min_child_weight=1,
max_delta_step=0,
