python实现数据挖掘——分类

决策树分类

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn import datasets

iris = datasets.load_iris()

#将数据集按7：3切分为训练集和测试集（特征变量和目标变量）
data_train, data_test, target_train, target_test = train_test_split(
        iris.data,  #特征数据
        iris.target,  #目标数据
        test_size=0.3)  #测试集占比

from sklearn import tree
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier

ID3算法

# ID3算法信息增益entropy
id3 = tree.DecisionTreeClassifier(criterion="entropy")
# 建立模型
id3 = id3.fit(data_train,target_train)
# 预测的准确度accuracy
id3_ac = id3.score(data_test,target_test)
# 可视化
tree.plot_tree(id3)

 CART算法

# CART算法基尼系数
cart = tree.DecisionTreeClassifier(criterion="gini")
# 建立模型
cart = cart.fit(data_train,target_train)
# 预测的准确度accuracy
cart_ac = cart.score(data_test,target_test)
# 可视化
tree.plot_tree(cart)

---

贝叶斯分类

# 贝叶斯
from sklearn.naive_bayes import GaussianNB

gnb = GaussianNB().fit(data_train,target_train)
target_pred = gnb.predict(data_test)

混淆矩阵

 

 

 

ROC曲线 

---

神经网络分类

---

逻辑回归

---

 随机森林

---

KNN最近邻

 

交叉验证

参数调优