优达机器学习：决策树练习题

12 练习：决策树准确性

这里优达的运行环境有个坑，就是他时而准确时而错误，所以测试的时候就一会儿是对的，一会儿是错的，同样的一个代码，感觉变量会混淆似的

import sys
from class_vis import prettyPicture
from prep_terrain_data import makeTerrainData

import matplotlib.pyplot as plt
import numpy as np
import pylab as pl

features_train, labels_train, features_test, labels_test = makeTerrainData()



########################## DECISION TREE #################################


### your code goes here--now create 2 decision tree classifiers,
### one with min_samples_split=2 and one with min_samples_split=50
### compute the accuracies on the testing data and store
### the accuracy numbers to acc_min_samples_split_2 and
### acc_min_samples_split_50, respectively

from sklearn import tree
from sklearn.metrics import accuracy_score
clf50 = tree.DecisionTreeClassifier(min_samples_split=50)
clf50.fit(features_train,labels_train)
result50 = clf50.predict(features_test)
acc_min_samples_split_50 = accuracy_score(labels_test,result50)

clf2 = tree.DecisionTreeClassifier(min_samples_split=2)
clf2.fit(features_train,labels_train)
result2 = clf2.predict(features_test)
acc_min_samples_split_2 = accuracy_score(labels_test,result2)


def submitAccuracies():
  return {"acc_min_samples_split_2":round(acc_min_samples_split_2,3),
          "acc_min_samples_split_50":round(acc_min_samples_split_50,3)}