hgboost

hgboost_classification_import_titanic.py

#######################################################
# Import Titanic dataset, and preprocessing
#######################################################
# Import the Titanic dataset
df = hgb.import_example(data='titanic')

print(df)
#      PassengerId  Survived  Pclass  ...     Fare Cabin  Embarked
# 0              1         0       3  ...   7.2500   NaN         S
# 1              2         1       1  ...  71.2833   C85         C
# 2              3         1       3  ...   7.9250   NaN         S
# 3              4         1       1  ...  53.1000  C123         S
# 4              5         0       3  ...   8.0500   NaN         S
# ..           ...       ...     ...  ...      ...   ...       ...
# 886          887         0       2  ...  13.0000   NaN         S
# 887          888         1       1  ...  30.0000   B42         S
# 888          889         0       3  ...  23.4500   NaN         S
# 889          890         1       1  ...  30.0000  C148         C
# 890          891         0       3  ...   7.7500   NaN         Q

# [891 rows x 12 columns]
#######################################################
# Set target value
y = df['Survived'].values
print(y)
# array([0, 1, 1, 1, 0, 0, 0, ..., 0, 1, 1, 1, 1, 0, 0])
#######################################################
# Remove features
df.drop(['Survived', 'PassengerId', 'Name'], axis=1, inplace=True)
#######################################################
# One-hot encoding
X = hgb.preprocessing(df)
#######################################################
# Remove missing values
import numpy as np
I = ~np.isnan(y)
X = X.loc[I, :]
y = y[I]

#######################################################
print(X)

#      Pclass_1.0  Pclass_2.0  Pclass_3.0  ...  Embarked_None  Embarked_Q  Embarked_S
# 0         False       False        True  ...          False       False        True
# 1          True       False       False  ...          False       False       False
# 2         False       False        True  ...          False       False        True
# 3          True       False       False  ...          False       False        True
# 4         False       False        True  ...          False       False        True
# ..          ...         ...         ...  ...            ...         ...         ...
# 886       False        True       False  ...          False       False        True
# 887        True       False       False  ...          False       False        True
# 888       False       False        True  ...          False       False        True
# 889        True       False       False  ...          False       False       False
# 890       False       False        True  ...          False        True       False

# [891 rows x 203 columns]