機器學習算法之決策樹回歸模型可視化

一個程式員在海濱遊泳時溺水身亡。他死前拼命的呼救，當時海灘上有許多救生員，但是沒有人救他。因為他一直大喊“F1!”“F1!”，誰都不知道“F1”究竟是什麼意思。

分類樹和回歸樹的差別

import numpy as np
import matplotlib as mpl
import matplotlib.pyplot as plt
import pandas as pd
import warnings
import sklearn
from sklearn.linear_model import LinearRegression, LassoCV, RidgeCV
from sklearn.pipeline import Pipeline
from sklearn.model_selection  import train_test_split
from sklearn.model_selection import GridSearchCV
from sklearn.tree import DecisionTreeRegressor
from sklearn.pipeline import Pipeline
from sklearn.feature_selection import SelectKBest
from sklearn.feature_selection import chi2
from sklearn.preprocessing import MinMaxScaler
from sklearn.decomposition import PCA
from sklearn.pipeline import Pipeline
from sklearn.model_selection  import GridSearchCV
from sklearn.linear_model.coordinate_descent import ConvergenceWarning
           

def notEmpty(s):
    return s != ''
           

mpl.rcParams['font.sans-serif']=[u'simHei']
mpl.rcParams['axes.unicode_minus']=False
## 攔截異常
warnings.filterwarnings(action = 'ignore', category=ConvergenceWarning)
           

names = ['CRIM','ZN', 'INDUS','CHAS','NOX','RM','AGE','DIS','RAD','TAX','PTRATIO','B','LSTAT']
path = "datas/boston_housing.data"
## 由于資料檔案格式不統一，是以讀取的時候，先按照一行一個字段屬性讀取資料，然後再按照每行資料進行處理
fd = pd.read_csv(path, header=None)
data = np.empty((len(fd), 14))
for i, d in enumerate(fd.values):
    d = map(float, filter(notEmpty, d[0].split(' ')))
    data[i] = list(d)

x, y = np.split(data, (13,), axis=1)
y = y.ravel()

print ("樣本資料量:%d, 特征個數：%d" % x.shape)
print ("target樣本資料量:%d" % y.shape[0])
           

樣本資料量:506, 特征個數：13

target樣本資料量:506

#資料的分割，
x_train1, x_test1, y_train1, y_test1 = train_test_split(x, y, train_size=0.8, random_state=14)
x_train, x_test, y_train, y_test = x_train1, x_test1, y_train1, y_test1
print ("訓練資料集樣本數目：%d, 測試資料集樣本數目：%d" % (x_train.shape[0], x_test.shape[0]))
           

訓練資料集樣本數目：404, 測試資料集樣本數目：102

#标準化
ss = MinMaxScaler()

x_train = ss.fit_transform(x_train, y_train)
x_test = ss.transform(x_test)

print ("原始資料各個特征屬性的調整最小值:",ss.min_)
print ("原始資料各個特征屬性的縮放資料值:",ss.scale_)
           

原始資料各個特征屬性的調整最小值: [-7.10352762e-05 0.00000000e+00 -1.68621701e-02 0.00000000e+00

-7.92181070e-01 -6.82314620e-01 -2.98661174e-02 -1.02719857e-01

-4.34782609e-02 -3.56870229e-01 -1.34042553e+00 -6.38977636e-03

-4.90780142e-02]

原始資料各個特征屬性的縮放資料值: [1.12397589e-02 1.00000000e-02 3.66568915e-02 1.00000000e+00

2.05761317e+00 1.91607588e-01 1.02986612e-02 9.09347180e-02

4.34782609e-02 1.90839695e-03 1.06382979e-01 2.53562554e-03

2.83687943e-02]

#構模組化型（回歸）
model = DecisionTreeRegressor(criterion='mae',max_depth=5)
#模型訓練
model.fit(x_train, y_train)
#模型預測
y_test_hat = model.predict(x_test) 
           

#評估模型
score = model.score(x_test, y_test)
print ("Score：", score)
           

Score： 0.7900379894156064

# 方式三：直接生成圖檔
from sklearn import tree
from IPython.display import Image  
import pydotplus
dot_data = tree.export_graphviz(model, out_file=None,  
                         filled=True, rounded=True,  
                         special_characters=True)  
graph = pydotplus.graph_from_dot_data(dot_data)  
Image(graph.create_png())