机器学习（day2下）

朴素贝叶斯分类方法

贝叶斯公式

计算案例

 

 

 

 

 拉普拉斯平滑系数

 API

 

 朴素贝叶斯算法总结

 总结

决策树

 

 

 

 决策树API

3.5.4案例：泰坦尼克号乘客生存预测

 

import pandas as pd

# 1、获取数据
path = "http://biostat.mc.vanderbilt.edu/wiki/pub/Main/DataSets/titanic.txt"
titanic = pd.read_csv(path)

titanic.head()

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

x.head()

y.head()

# 2、数据处理
# 1）缺失值处理
x["age"].fillna(x["age"].mean(), inplace=True)

# 2) 转换成字典
x = x.to_dict(orient="records")

from sklearn.model_selection import train_test_split
# 3、数据集划分
x_train, x_test, y_train, y_test = train_test_split(x, y, random_state=22)

# 4、字典特征抽取
from sklearn.feature_extraction import DictVectorizer
from sklearn.tree import DecisionTreeClassifier, export_graphviz

transfer = DictVectorizer()
x_train = transfer.fit_transform(x_train)
x_test = transfer.transform(x_test)

# 3）决策树预估器
estimator = DecisionTreeClassifier(criterion="entropy", max_depth=8)
estimator.fit(x_train, y_train)

# 4）模型评估
# 方法1：直接比对真实值和预测值
y_predict = estimator.predict(x_test)
print("y_predict:\n", y_predict)
print("直接比对真实值和预测值:\n", y_test == y_predict)

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

# 可视化决策树
export_graphviz(estimator, out_file="titanic_tree.dot", feature_names=transfer.get_feature_names())


### 随机森林对泰坦尼克号乘客的生存进行预测

from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import GridSearchCV

estimator = RandomForestClassifier()
# 加入网格搜索与交叉验证
# 参数准备
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1：直接比对真实值和预测值
y_predict = estimator.predict(x_test)
print("y_predict:\n", y_predict)
print("直接比对真实值和预测值:\n", y_test == y_predict)

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

# 最佳参数：best_params_
print("最佳参数：\n", estimator.best_params_)
# 最佳结果：best_score_
print("最佳结果：\n", estimator.best_score_)
# 最佳估计器：best_estimator_
print("最佳估计器:\n", estimator.best_estimator_)
# 交叉验证结果：cv_results_
print("交叉验证结果:\n", estimator.cv_results_)