作业：
自行学习参考如何使用kaggle平台，写下使用注意点，并对下述比赛提交代码
python
import warnings
warnings.filterwarnings("ignore") #忽略警告信息
# 数据处理清洗包
import pandas as pd
import numpy as np
import random as rnd
# 可视化包
import seaborn as sns
import matplotlib.pyplot as plt
# 机器学习算法相关包
from sklearn.linear_model import LogisticRegression, Perceptron, SGDClassifier
# 设置中文字体（解决中文显示问题）
plt.rcParams['font.sans-serif'] = ['SimHei'] # Windows系统常用黑体字体
plt.rcParams['axes.unicode_minus'] = False # 正常显示负号
data_train = pd.read_csv(r'train.csv') #读取训练集数据
data_test = pd.read_csv(r'test.csv') #读取测试集数据
combine = [data_train, data_test] # 合并数据
#这只是放到一个列表，以便后续合并，现在还没合并
print(data_train.isnull().sum())
print(data_test.isnull().sum())
#删除无用特征 Ticket
print("Before", data_train.shape, data_test.shape, combine[0].shape, combine[1].shape)
data_train = data_train.drop(['Ticket'], axis=1)
data_test = data_test.drop(['Ticket'], axis=1)
combine = [data_train, data_test]
print("After", data_train.shape, data_test.shape, combine[0].shape, combine[1].shape)
# 转换分类特征Sex
for dataset in combine:
dataset['Sex'] = dataset['Sex'].map( {'female': 1, 'male': 0} ).astype(int) #男性赋值为0，女性赋值为1，并转换为整型数据
data_test.head()
# 创建空数组
guess_ages = np.zeros((2,3))
guess_ages
# 遍历 Sex (0 或 1) 和 Pclass (1, 2, 3) 来计算六种组合的 Age 猜测值
for dataset in combine:
# 第一个for循环计算每一个分组的Age预测值
for i in range(0, 2):
for j in range(0, 3):
guess_df = dataset[(dataset['Sex'] == i) & \
(dataset['Pclass'] == j+1)]['Age'].dropna()
age_guess = guess_df.median()
# 将随机年龄浮点数转换为最接近的 0.5 年龄（四舍五入）
guess_ages[i,j] = int( age_guess/0.5 + 0.5 ) * 0.5
# 第二个for循环对空值进行赋值
for i in range(0, 2):
for j in range(0, 3):
dataset.loc[ (dataset.Age.isnull()) & (dataset.Sex == i) & (dataset.Pclass == j+1),\
'Age'] = guess_ages[i,j]
dataset['Age'] = dataset['Age'].astype(int)
data_train.head()
# Embarked: 仅2个缺失，用众数填充
data_train['Embarked'].fillna(data_train['Embarked'].mode()[0], inplace=True)
data_test['Embarked'].fillna(data_test['Embarked'].mode()[0], inplace=True)
print(data_train.isnull().sum())
# Fare: 极少数缺失，用中位数填充
data_test['Fare'].fillna(data_test['Fare'].median(), inplace=True)
# 姓名对预测生存率的影响较小，除非从中提取出有用的信息（如头衔、家庭关系等）
data_train['Title'] = data_train['Name'].str.extract(' ([A-Za-z]+)\.', expand=False)
data_train['Title'] = data_train['Title'].replace(['Lady', 'Countess', 'Dr', 'Rev', 'Sir', 'Jonkheer', 'Dona'], 'Rare')
data_train['Title'] = data_train['Title'].replace('Mlle', 'Miss').replace('Ms', 'Miss').replace('Mme', 'Mrs')
data_test['Title'] = data_test['Name'].str.extract(' ([A-Za-z]+)\.', expand=False)
data_test['Title'] = data_test['Title'].replace(['Lady', 'Countess', 'Dr', 'Rev', 'Sir', 'Jonkheer', 'Dona'], 'Rare')
data_test['Title'] = data_test['Title'].replace('Mlle', 'Miss').replace('Ms', 'Miss').replace('Mme', 'Mrs')
# 计算家庭成员数量，家庭规模可能影响生存率
data_train['FamilySize'] = data_train['SibSp'] + data_train['Parch'] + 1
data_test['FamilySize'] = data_test['SibSp'] + data_test['Parch'] + 1
# 结合 FamilySize 创建新特征（如是否独自乘船）：
data_train['IsAlone'] = (data_train['FamilySize'] == 1).astype(int)
data_test['IsAlone'] = (data_test['FamilySize'] == 1).astype(int)
# 客舱甲板
# 提取客舱首字母（如果有的话）
data_train['Deck'] = data_train['Cabin'].str[0]
data_train['Deck'] = data_train['Deck'].fillna('Unknown') # 填充缺失值
data_test['Deck'] = data_test['Cabin'].str[0]
data_test['Deck'] = data_test['Deck'].fillna('Unknown') # 填充缺失值
# 删除冗余特征
data_train.drop([ 'Name', 'Cabin'], axis=1, inplace=True)
data_test.drop(['Name', 'Cabin'], axis=1, inplace=True)
# 先筛选字符串变量
discrete_features = data_train.select_dtypes(include=['object']).columns.tolist()
print("离散变量:", discrete_features) # 打印离散变量列名
data_train.rename(columns={'Sex': 'isFemale'}, inplace=True) # 重命名列名 -> 是否女性
data_test.rename(columns={'Sex': 'isFemale'}, inplace=True) # 重命名列名
print(data_train['isFemale'].value_counts()) # 打印Sex列的取值分布
# 对embarked和deck进行独热编码（无序）
data_train = pd.get_dummies(data_train, columns=['Embarked', 'Deck'], dtype=int, drop_first=True)
data_test = pd.get_dummies(data_test, columns=['Embarked', 'Deck'], dtype=int, drop_first=True)
# 确保训练集和测试集的列顺序一致
# 排除标签列'Survived'，仅比较特征列
feature_columns = [col for col in data_train.columns if col != 'Survived']
missing_cols = set(feature_columns) - set(data_test.columns)
for col in missing_cols:
data_test[col] = 0
# 按照训练集特征列的顺序排序测试集列
data_test = data_test[feature_columns]
print(data_train.head())
title_mapping = {
'Mr': 0,
'Rare': 1,
'Master': 2,
'Miss': 3,
'Mrs': 4
}
data_train['Title'] = data_train['Title'].map(title_mapping)
data_test['Title'] = data_test['Title'].map(title_mapping)
print(data_train['Title'].value_counts()) # 打印Title列的取值分布
# 对Age, Fare 进行标准化（均值为0，方差为1）
from sklearn.preprocessing import StandardScaler, MinMaxScaler
scaler = StandardScaler()
data_train[['Age', 'Fare']] = scaler.fit_transform(data_train[['Age', 'Fare']])
print(data_train.head()) # 打印前几行数据
print(data_train.info())
# 划分一下测试集
from sklearn.model_selection import train_test_split
X = data_train.drop(['Survived'], axis=1) # 特征，axis=1表示按列删除
y = data_train['Survived'] # 标签
# 按照8:2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) # 80%训练集，20%测试集
# --- 1. 默认参数的随机森林 ---
from sklearn.ensemble import RandomForestClassifier #随机森林分类器
from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score # 用于评估分类器性能的指标
from sklearn.metrics import classification_report, confusion_matrix #用于生成分类报告和混淆矩阵
import warnings #用于忽略警告信息
warnings.filterwarnings("ignore") # 忽略所有警告信息
import time
print("--- 1. 默认参数随机森林 (训练集 -> 测试集) ---")
start_time = time.time() # 记录开始时间
rf_model = RandomForestClassifier(random_state=42)
rf_model.fit(X_train, y_train) # 在训练集上训练
rf_pred = rf_model.predict(X_test) # 在测试集上预测
end_time = time.time() # 记录结束时间
print(f"训练与预测耗时: {end_time - start_time:.4f} 秒")
print("\n默认随机森林 在测试集上的分类报告：")
print(classification_report(y_test, rf_pred))
print("默认随机森林 在测试集上的混淆矩阵：")
print(confusion_matrix(y_test, rf_pred))