【机器学习实战】基于python对泰坦尼克幸存者进行数据分析与预测

import pandas as pd
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction import DictVectorizer
from sklearn.preprocessing import OneHotEncoder
from sklearn.compose import ColumnTransformer
from sklearn.pipeline import make_pipeline
from sklearn.metrics import accuracy_score
 
# 读取数据
titanic_data = pd.read_csv('titanic_data.csv')
 
# 分离特征和目标
X = titanic_data[titanic_data.select_dtypes(exclude=['object']).columns]
y = titanic_data['survived']
 
# 特征工程：对类别变量进行one-hot编码
categorical_features = ['sex', 'n_siblings_spouses', 'parch', 'class', 'deck', 'embark_town', 'alone']
 
preprocessor = ColumnTransformer(
    transformers=[
        ('one_hot_encoder', OneHotEncoder(handle_unknown='ignore'), categorical_features)
    ])
 
# 初始化随机森林分类器
rf_classifier = make_pipeline(preprocessor, RandomForestClassifier())
 
# 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
 
# 训练模型
rf_classifier.fit(X_train, y_train)
 
# 进行预测
y_pred = rf_classifier.predict(X_test)
 
# 评估模型性能
accuracy = accuracy_score(y_test, y_pred)
print(f"Model Accuracy: {accuracy*100:.2f}%")

这段代码使用了sklearn库中的随机森林分类器来解决分类问题。首先，我们读取了泰坦尼克的数据集，并将其分为特征X和目标y。然后，我们使用ColumnTransformer对类别特征进行one-hot编码，并初始化随机森林分类器。接着，我们使用train_test_split划分数据集为训练集和测试集，并训练模型。最后，我们使用测试集来评估模型性能，并打印出准确率。