[数据结构与算法]决策树案例

注：本案例为黑马的课堂案例，上传仅为方便查看

# 1.获取数据
# 2.数据基本处理
# 2.1 确定特征值,目标值
# 2.2 缺失值处理
# 2.3 数据集划分
# 3.特征工程(字典特征抽取)
# 4.机器学习(决策树)
# 5.模型评估

import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction import DictVectorizer
from sklearn.tree import DecisionTreeClassifier, export_graphviz

# 1.获取数据,此数据连接已失效
data = pd.read_csv("http://biostat.mc.vanderbilt.edu/wiki/pub/Main/DataSets/titanic.txt")

data

1313 rows × 11 columns

data.describe()

# 2.数据基本处理
# 2.1 确定特征值,目标值
x = data[["pclass", "age", "sex"]]
x.head()

y = data["survived"]
y.head()

0    1
1    0
2    0
3    0
4    1
Name: survived, dtype: int64

# 2.2 缺失值处理
x["age"].fillna(value=data["age"].mean(), inplace=True)

x.head()

# 2.3 数据集划分，test_size是测试集所占的比例
x_train, x_test, y_train, y_test = train_test_split(x, y, random_state=22, test_size=0.2)

# 3.特征工程(字典特征抽取)
x.head()

x_train = x_train.to_dict(orient="records")
x_test = x_test.to_dict(orient="records")
x_train

[{'pclass': '3rd', 'age': 45.0, 'sex': 'female'},
 {'pclass': '3rd', 'age': 31.19418104265403, 'sex': 'male'},
 {'pclass': '1st', 'age': 31.19418104265403, 'sex': 'female'},
.....
 ...]

transfer = DictVectorizer()

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

x_train

<1050x6 sparse matrix of type '<class 'numpy.float64'>'
	with 3150 stored elements in Compressed Sparse Row format>

# 4.机器学习(决策树)
estimator = DecisionTreeClassifier(max_depth=5)

estimator.fit(x_train, y_train)

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=5,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')

# 5.模型评估
y_pre = estimator.predict(x_test)
print(y_pre)

[0 0 0 0 1 1 1 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 1 1 0 1 0 1 0 0 0
 0 0 0 0 0 0 0 0 0 1 1 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 1 0 0 0
 1 1 0 0 0 1 0 1 0 0 0 0 0 0 0 0 0 0 0 1 0 1 0 1 0 1 0 0 0 0 0 0 0 0 0 0 1
 0 1 0 0 0 0 0 0 0 0 0 1 0 0 1 1 0 1 0 0 1 0 0 0 0 0 0 0 0 1 1 0 0 0 0 1 1
 1 0 0 0 0 0 0 0 0 0 0 0 0 0 1 1 0 1 0 0 0 0 1 0 0 0 0 0 1 1 1 1 0 0 0 0 0
 0 0 0 1 1 1 0 0 0 0 1 1 1 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 1 1 0 0 0 0 0 1 0
 0 0 1 0 0 0 0 0 0 1 0 0 1 0 1 0 1 0 0 0 1 0 0 1 0 0 0 0 1 0 1 0 0 0 0 1 0
 0 1 0 1]

ret = estimator.score(x_test, y_test)
ret

0.7984790874524715

# 决策树可视化
export_graphviz(estimator, out_file="./data/tree.dot", feature_names=['age', 'pclass=1st', 'pclass=2nd', 'pclass=3rd', '女性', '男性'])