[机器学习]贝叶斯算法 对泰坦尼克号生存人群 分类预测 [简单示例]

1.代码

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @File  : 泰坦尼克号.py
# @Author: 赵路仓
# @Date  : 2020/4/4
# @Desc  :
# @Contact : 398333404@qq.com 

import pandas as pd
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.tree import DecisionTreeClassifier, export_graphviz
from sklearn.feature_extraction import DictVectorizer
from sklearn.ensemble import RandomForestClassifier



def titanic():
    # 导入数据
    titanic = pd.read_csv("titanic.txt")
    # print(titanic)

    # 筛选特征值和目标值
    x = titanic[["pclass", "age", "sex"]]
    y = titanic["survived"]
    # print(x)
    # print(y)

    # 数据处理
    # 1.缺失值处理
    x["age"].fillna(x["age"].mean(), inplace=True)
    # print(x["age"])
    # 2.转换成字典
    x = x.to_dict(orient="records")
    # 3.数据集划分
    x_train, x_test, y_train, y_test = train_test_split(x, y, random_state=21)

    # 4.字典特征抽取
    transfer = DictVectorizer()
    x_train = transfer.fit_transform(x_train)
    x_test = transfer.transform(x_test)
    print(x_train.toarray())
    print(transfer.get_feature_names())
    # 5.决策树预估器
    estimator = DecisionTreeClassifier(criterion="entropy")
    estimator.fit(x_train, y_train)

    # 6.模型评估
    # 方法一：直接对比真实数据和预测值
    y_predit = estimator.predict(x_test)

    print("y_predit:
", y_predit)
    print("对比真实值和预测值:
", y_test == y_predit)

    # 方法2：计算准确率
    score = estimator.score(x_test, y_test)
    print("准确率为：
", score)

    # 预测
    pre=transfer.transform([{'pclass': '1st', 'age': 48.0, 'sex': 'male'}])
    prediction=estimator.predict(pre)
    print(prediction)
    # 可视化决策树
    # 生成文件
    dot_data = export_graphviz(estimator, out_file="titanic.dot")


def titanic_forest():
    # 导入数据
    titanic = pd.read_csv("titanic.txt")
    # print(titanic)

    # 筛选特征值和目标值
    x = titanic[["pclass", "age", "sex"]]
    y = titanic["survived"]

    # 数据处理
    # 1.缺失值处理
    x["age"].fillna(x["age"].mean(), inplace=True)
    # print(x["age"])
    # 2.转换成字典
    x = x.to_dict(orient="records")
    # 3.数据集划分
    x_train, x_test, y_train, y_test = train_test_split(x, y, random_state=21)

    # 4.字典特征抽取
    transfer = DictVectorizer()
    x_train = transfer.fit_transform(x_train)
    x_test = transfer.transform(x_test)

    estimator=RandomForestClassifier()
    # 加入网格搜索与交叉验证
    param_dict = {
        "n_estimators": [120,200,300,500,800,1200],"max_depth":[5,8,15,25,30]
    }
    estimator = GridSearchCV(estimator, param_grid=param_dict, cv=3)
    estimator.fit(x_train, y_train)

    # 5.模型评估
    # 方法一：直接对比真实数据和预测值
    y_predit = estimator.predict(x_test)
    print("y_predit:
", y_predit)
    print("对比真实值和预测值:
", y_test == y_predit)

    # 方法2：计算准确率
    score = estimator.score(x_test, y_test)
    print("准确率为：
", score)

    """
       最佳参数：best_params_
       最佳结果：best_score_
       最佳估计器：best_estimator_
       交叉验证结果：cv_results_
    """
    print("最佳参数:
", estimator.best_params_)
    print("最佳结果:
", estimator.best_score_)
    print("最佳估计器:
", estimator.best_estimator_)
    print("交叉验证结果:
", estimator.cv_results_)
    return None


if __name__ == "__main__":
    titanic()
    titanic_forest()

2.解释

第一个函数 titanic() 根据游客数据

1.筛选有效数据

2.缺失值处理

3.转换为字典

5.划分数据集

6.转换为特征值

7.训练模型

8.模型评估

9.预测

形成模型并评估，可以进行简单的预测分类

第二个函数 titanic_forest() 

随机森林找到最优方案/模型，确定最优参数等等