Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Sign up
Appearance settings

update forks #51

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
bruce1408 wants to merge 7 commits into ddbourgin:master
base: master
Choose a base branch
Loading
from bruce1408:master
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion .gitignore
View file Open in desktop
Original file line number Diff line number Diff line change
@@ -1,9 +1,11 @@
### OSX ###
# General
.DS_Store
.gitignore
.AppleDouble
.LSOverride

*.xml
*.iml
# Icon must end with two \r
Icon

Expand Down
96 changes: 96 additions & 0 deletions numpy_ml/trees/cart_tree_imp.py
View file Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,96 @@
from numpy import *


# 载入数据
def loadDataSet(fileName):
dataMat = []
fr = open(fileName)
for line in fr.readlines():
curLine = line.strip().split('\t')
# python3不适用:fltLine = map(float,curLine) 修改为:
fltLine = list(map(float, curLine)) # 将每行映射成浮点数,python3返回值改变,所以需要
dataMat.append(fltLine)
return dataMat


# 切分数据集为两个子集
def binSplitDataSet(dataSet, feature, value): # 数据集 待切分特征 特征值
mat0 = dataSet[nonzero(dataSet[:, feature] > value)[0], :]
mat1 = dataSet[nonzero(dataSet[:, feature] <= value)[0], :]
# 下面原书代码报错 index 0 is out of bounds,使用上面两行代码
# mat0 = dataSet[nonzero(dataSet[:, feature] > value)[0], :][0]
# mat1 = dataSet[nonzero(dataSet[:, feature] <= value)[0], :][0]
return mat0, mat1


# Tree结点类型:回归树
def regLeaf(dataSet): # 生成叶结点,在回归树中是目标变量特征的均值
return mean(dataSet[:, -1])


# 误差计算函数:回归误差
def regErr(dataSet): # 计算目标的平方误差(均方误差*总样本数)
return var(dataSet[:, -1]) * shape(dataSet)[0]


# 二元切分
def chooseBestSplit(dataSet, leafType=regLeaf, errType=regErr, ops=(0, 1)):
# 切分特征的参数阈值,用户初始设置好
tolS = ops[0] # 允许的误差下降值
tolN = ops[1] # 切分的最小样本数
# 若所有特征值都相同,停止切分
featureNum = len(set(dataSet[:, -1].T.tolist()[0]))
if len(set(dataSet[:, -1].T.tolist()[0])) == 1: # 倒数第一列转化成list 不重复
return None, leafType(dataSet) # 如果剩余特征数为1,停止切分1。
# 找不到好的切分特征,调用regLeaf直接生成叶结点
m, n = shape(dataSet)
S = errType(dataSet) # 最好的特征通过计算平均误差
bestS = inf
bestIndex = 0
bestValue = 0
for featIndex in range(n - 1): # 遍历数据的每个属性特征
# for splitVal in set(dataSet[:,featIndex]): python3报错修改为下面
for splitVal in set((dataSet[:, featIndex].T.A.tolist())[0]): # 遍历每个特征里不同的特征值
mat0, mat1 = binSplitDataSet(dataSet, featIndex, splitVal) # 对每个特征进行二元分类
if (shape(mat0)[0] < tolN) or (shape(mat1)[0] < tolN): continue
newS = errType(mat0) + errType(mat1)
if newS < bestS: # 更新为误差最小的特征
bestIndex = featIndex
bestValue = splitVal
bestS = newS
# 如果切分后误差效果下降不大,则取消切分,直接创建叶结点
if (S - bestS) < tolS:
return None, leafType(dataSet) # 停止切分2
mat0, mat1 = binSplitDataSet(dataSet, bestIndex, bestValue)
# 判断切分后子集大小,小于最小允许样本数停止切分3
if (shape(mat0)[0] < tolN) or (shape(mat1)[0] < tolN):
return None, leafType(dataSet)
return bestIndex, bestValue # 返回特征编号和用于切分的特征值


# 构建tree
def createTree(dataSet, leafType=regLeaf, errType=regErr, ops=(0, 1)):
# 数据集默认NumPy Mat 其他可选参数【结点类型:回归树,误差计算函数,ops包含树构建所需的其他元组】
feat, val = chooseBestSplit(dataSet, leafType, errType, ops)
if feat == None: return val # 满足停止条件时返回叶结点值
# 切分后赋值
retTree = {}
retTree['spInd'] = feat
retTree['spVal'] = val
# 切分后的左右子树
lSet, rSet = binSplitDataSet(dataSet, feat, val)
retTree['left'] = createTree(lSet, leafType, errType, ops)
retTree['right'] = createTree(rSet, leafType, errType, ops)
return retTree


if __name__ == "__main__":
myDat = mat(loadDataSet('train_data'))
print(createTree(myDat))

# 绘制数据点图
import matplotlib.pyplot as plt

plt.plot(myDat[:, 0], myDat[:, 1], 'ro')
plt.show()

40 changes: 40 additions & 0 deletions numpy_ml/trees/scikit_learn_tree.py
View file Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,40 @@
import numpy as np
import matplotlib.pyplot as plt
from sklearn.tree import DecisionTreeRegressor
from sklearn import linear_model

# Data set,skl官方代码给出样例
x = np.array(list(range(1, 11))).reshape(-1, 1)
y = np.array([5.56, 5.70, 5.91, 6.40, 6.80, 7.05, 8.90, 8.70, 9.00, 9.05]).ravel()

# Fit regression model 和手工计算的一样,是个三段函数
# x≤3.5 5.72
# 3.5⩽x≤6.5 6.75
# 6.5 < x 8.91

model1 = DecisionTreeRegressor(max_depth=1)
model2 = DecisionTreeRegressor(max_depth=3, max_leaf_nodes=4, min_samples_leaf=3)
model3 = linear_model.LinearRegression()
model1.fit(x, y)
model2.fit(x, y)
model3.fit(x, y)

# Predict
X_test = np.arange(0.0, 10.0, 0.01)[:, np.newaxis]
y_1 = model1.predict(X_test)
y_2 = model2.predict(X_test)
y_3 = model3.predict(X_test)

# Plot the results
plt.figure()
plt.scatter(x, y, s=20, edgecolor="black",
c="darkorange", label="data")
plt.plot(X_test, y_1, color="cornflowerblue",
label="max_depth=1", linewidth=2)
plt.plot(X_test, y_2, color="yellowgreen", label="max_depth=3", linewidth=2)
plt.plot(X_test, y_3, color='red', label='liner regression', linewidth=2)
plt.xlabel("data")
plt.ylabel("target")
plt.title("Decision Tree Regression")
plt.legend()
plt.show()
10 changes: 10 additions & 0 deletions numpy_ml/trees/train_data
View file Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,10 @@
1 4.50
2 4.75
3 4.91
4 5.34
5 5.80
6 7.05
7 7.90
8 8.23
9 8.70
10 9.00

AltStyle によって変換されたページ (->オリジナル) /