用Titanic数据实现autosklearn

autosklearn实现Titanic分类

import autosklearn.classification as autoskcl
import pandas as pd
import numpy as np
import sklearn as sk
import seaborn as sns
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split


data = pd.read_csv('data/titanic_train.csv')
data['Sex'] = data['Sex'].astype('category')
data['Embarked'] = data['Embarked'].astype('category')
data['Sex'] = data['Sex'].cat.codes
data['Embarked'] = data['Embarked'].cat.codes
data_c = data.drop(['PassengerId','Name','Ticket','Cabin'], axis=1)
data_c['Age'] = data_c['Age'].fillna(data_c['Age'].mean())
cols = data_c.columns
features = cols[1:]
labels = cols[0]
for feature in features:
    data_c[feature] = (data_c[feature] - data_c[feature].mean())/data_c[feature].std()
X = data_c[features]
y = data_c[labels]
X_train, X_test, y_train, y_test = train_test_split(X,y, test_size=.3)
cls = autoskcl.AutoSklearnClassifier()
cls.fit(X_train, y_train)
predictions = cls.predict(X_test)
print(predictions)
print(sk.metrics.accuracy_score(y_test, predictions))