def CCP_cross_validation(TreeSets, alpha_list, X_test, y_test, feature_names,
class_names, sklearn_model):
precision_list = []
progress_length = len(TreeSets)
# print"------------------------------检查下这里------------------------------"
# print"X_test,y_test=",X_test
# print y_test
for index, item in enumerate(TreeSets):
Ti_precision = precision_compute(item, X_test, y_test, feature_names,
class_names)
print "T%d_precision=%f" % (index, Ti_precision)
precision_list.append(Ti_precision)
print "the T" + str(index) + " has been validated, " + str(
progress_length - index - 1) + " Trees left, wait please....."
pruned_precision = max(precision_list)
index = precision_list.index(pruned_precision)
print "index=", index
best_alpha = alpha_list[index]
Best_tree = TreeSets[index]
dot_file = "./visualization/Best_tree.dot"
svg_file = "./visualization/Best_tree.svg"
#画一画树
best_sklearn_model = copy.deepcopy(sklearn_model)
prune_sklearn_model(best_sklearn_model.tree_, 0, Best_tree)
draw_file(best_sklearn_model, dot_file, svg_file, feature_names)
return Best_tree, best_alpha, pruned_precision
def CCP_validation(TreeSets,alpha_list,X_test,y_test,feature_names,class_names,sklearn_model,b_SE):
precision_list=[]
progress_length=len(TreeSets)
# print"------------------------------检查下这里------------------------------"
# print"X_test,y_test=",X_test
# print y_test
for index,item in enumerate(TreeSets):
Ti_precision=precision_compute(item,X_test,y_test,feature_names,class_names)
print"T%d_precision=%f"%(index,Ti_precision)
precision_list.append(Ti_precision)
print"the T"+str(index)+" has been validated, "+str(progress_length-index-1)+" Trees left, wait please....."
if b_SE==False:
pruned_precision=max(precision_list)
index=precision_list.index(pruned_precision)
print"index=",index
best_alpha=alpha_list[index]
Best_tree=TreeSets[index]
dot_file="./visualization/Best_tree_0SE.dot"
svg_file="./visualization/Best_tree_0SE.svg"
#画一画树
best_sklearn_model=copy.deepcopy(sklearn_model)
prune_sklearn_model(best_sklearn_model.tree_,0,Best_tree)
draw_file(best_sklearn_model,dot_file,svg_file,feature_names)
return Best_tree,best_alpha,pruned_precision,precision_list[0]
else:#使用１-SE rule
error_rate_list=[1-item for item in precision_list]
lowest_error_rate=min(error_rate_list)
print"error_rate_list=",error_rate_list
SE=sqrt(lowest_error_rate*(1-lowest_error_rate)/len(y_test))
print"SE=",SE
criterion_1_SE=lowest_error_rate+SE
index_error_rate=0
for index,item in enumerate(error_rate_list):#search from from the end ,because the error_rate_list is not monotory.
if error_rate_list[len(error_rate_list)-1-index]<criterion_1_SE:
index_error_rate=len(error_rate_list)-1-index
break
# if index_error_rate-1>=0:
# index_error_rate=index_error_rate-1
# else:
# pass#becasuse the list may only have one item.
pruned_precision=precision_list[index_error_rate]#here's right,because the precision list is corresponding to the error_rate_list.
best_alpha=alpha_list[index_error_rate]
Best_tree=TreeSets[index_error_rate]
dot_file="./visualization/Best_tree_1SE.dot"
svg_file="./visualization/Best_tree_1SE.svg"
#画一画树
best_sklearn_model=copy.deepcopy(sklearn_model)
prune_sklearn_model(best_sklearn_model.tree_,0,Best_tree)
draw_file(best_sklearn_model,dot_file,svg_file,feature_names)
return Best_tree,best_alpha,pruned_precision,precision_list[0]
def ECP_1SE_validation(TreeSets, alpha_list, X_test, y_test, feature_names,
sklearn_model, b_SE):
mse_list = []
progress_length = len(TreeSets)
# print"------------------------------检查下这里------------------------------"
# print"X_test,y_test=",X_test
# print y_test
for index, item in enumerate(TreeSets):
Ti_mse = mse_compute(item, X_test, y_test, feature_names)
print "T%d_mse=%f" % (index, Ti_mse)
mse_list.append(Ti_mse)
print "the T" + str(index) + " has been validated, " + str(
progress_length - index - 1) + " Trees left, wait please....."
if b_SE == False:
pruned_mse = min(mse_list)
index = mse_list.index(pruned_mse)
# print"index=",index
#－－－－－－－－－－－－－－－－－－代码①处（start）－－－－－－－－－－－－－－－－－－－
best_alpha = alpha_list[index]
Best_tree = TreeSets[index]
dot_file = "./visualization/Best_tree_0SE.dot"
svg_file = "./visualization/Best_tree_０SE.svg"
#画一画树
print "unpruned_mse=", mse_list[0]
best_sklearn_model = copy.deepcopy(sklearn_model)
prune_sklearn_model(best_sklearn_model.tree_, 0, Best_tree)
draw_file(best_sklearn_model, dot_file, svg_file, feature_names)
return Best_tree, best_alpha, pruned_mse, mse_list[0]
#－－－－－－－－－－－－－－－－－－代码①处(end)－－－－－－－－－－－－－－－－－－－
else:
min_mse = min(mse_list)
SE = sqrt(min_mse * (1 - min_mse) / len(y_test))
criterion_1_SE = min_mse + SE
index_mse = 0
for index, item in enumerate(mse_list):
if mse_list[
len(mse_list) - 1 -
index] < criterion_1_SE: #the mse_list is not Monotonous,so search from the end.
index_mse = len(mse_list) - 1 - index
break
pruned_mse = mse_list[index_mse]
#－－－－－－－－－－－－－－－－－－下面代码与上面①一致(start)－－－－－－－－－－－－－－－－－－－
best_alpha = alpha_list[index_mse]
Best_tree = TreeSets[index_mse]
dot_file = "./visualization/Best_tree_1SE.dot"
svg_file = "./visualization/Best_tree_1SE.svg"
#画一画树
print "unpruned_mse=", mse_list[0]
best_sklearn_model = copy.deepcopy(sklearn_model)
prune_sklearn_model(best_sklearn_model.tree_, 0, Best_tree)
draw_file(best_sklearn_model, dot_file, svg_file, feature_names)
return Best_tree, best_alpha, pruned_mse, mse_list[0]
def model_json(data_path, name_path, cart_max_depth):
##########################################################
feature_names = get_Attribute(name_path)
print "data_path=", data_path
#------------------------------------------
x_list, y_list = read_data_for_split(data_path, n=0,
label=1) #把数据和类别标签列分开。
print "x_list=", x_list
print "y_list=", y_list
#------------------------------------------
X_train, X_test, y_train, y_test = train_test_split(x_list,
y_list,
test_size=0.25,
random_state=0)
print "X_train=", X_train
#分别初始化对特征值和目标值的标准化器
ss_X = StandardScaler()
ss_y = StandardScaler()
#训练数据都是数值型，所以要标准化处理
X_train = np.array(X_train)
print "X_train=", X_train
X_train = ss_X.fit_transform(np.array(X_train))
X_test = np.array(X_test)
X_test = ss_X.transform(np.array(X_test))
y_train = np.array(y_train)
y_test = np.array(y_test)
#目标数据（房价预测值）也是数值型，所以也要标准化处理
#说明一下：fit_transform与transform都要求操作2D数据，而此时的y_train与y_test都是1D的，因此需要调用reshape(-1,1)，例如：[1,2,3]变成[[1],[2],[3]]
y_train = ss_y.fit_transform(y_train.reshape(-1, 1))
y_test = ss_y.transform(y_test.reshape(-1, 1))
# print X_train
feature_list = get_Attribute(name_path)
dtr = DecisionTreeRegressor(max_depth=cart_max_depth,
criterion='mse',
random_state=0)
print "now training,wait please.........."
dtr.fit(X_train, y_train)
print "train finished"
class_names = '' #因为是回归，所以不需要分类名
result = rules(dtr, feature_list, class_names)
print "result=", result
with open('structure.json', 'w') as f:
f.write(json.dumps(result))
print "The json-style model has been stored in structure.json"
print "now I'm drawing the CART Regression tree,wait please............"
# print dir(data)
dot_file = "./visualization/T0.dot"
png_file = "./visualization/T0.svg"
# draw_file(dtr,dot_file,png_file,X_train,feature_list)
draw_file(dtr, dot_file, png_file, feature_list)
print "CART tree has been drawn in " + png_file
return dtr, result, X_train, y_train, X_test, y_test, feature_list
def model_gtmin_Tt(clf,model,feature_names,class_names,Tt_name):#T0->T1
# print"model=",model
Tt=Tt_count(model,0)#|Tt|
# print"|Tt|=",Tt
Rt=Rt_compute(model)
# print"R(t)=",Rt
RTt=RTt_compute(model,0)
# print"R(Tt)=",RTt
# leaves=nodes_all_count(model,0)#no use now
# print"all nodes=",leaves
gt_list=[]
prune_parts=[]
gt_with_tree(model,gt_list,prune_parts)
# print gt_list
# print"---------------------------------------------------------"
# print len(gt_list)
# print_list(prune_parts)
# print"---------------------------------------------------------"
# print len(prune_parts)
alpha=min(gt_list)
prune_gt_index=gt_list.index(alpha)
# print"prune_gt_index=",prune_gt_index
prune_for_minimum_gt=prune_parts[prune_gt_index]#
# print"prune_for_minimum_gt=\n",prune_for_minimum_gt
#------------------------------
T0=copy.deepcopy(model)
T1=copy.deepcopy(model)#here T1 means Ti
gt_list=[]#这里必须复位清零
prune_parts=[]#这里必须复位清零
T1_create(T1,gt_list,prune_parts,prune_gt_index)
#这里不使用上面的prune_for_minimum的原因是，这个被裁掉的部分，你不知道处于哪个结点下面．
#也就是说，你虽然知道要裁掉的子树是什么，但是你无法知道在哪里裁，所以这里对prune_parts进行重新构建
#from T0(original model) to get T1
#print"\nT0=",model
#print "\nT1=",T1
index=0#never change this value！！！
sklearn_model=copy.deepcopy(clf)
prune_sklearn_model(sklearn_model.tree_,index,T1)
dot_file="./visualization/T"+Tt_name+".dot"
png_file="./visualization/T"+Tt_name+".svg"
# draw_file(sklearn_model,dot_file,png_file,X_train,feature_names)
draw_file(sklearn_model,dot_file,png_file,feature_names)
return sklearn_model,T1,alpha
def model_gtmin_Tt(dtr, model, feature_names, Tt_name): #还没修改完成
# print"model=",model
Tt = Tt_count(model, 0) #|Tt|
# print"|Tt|=",Tt
Rt = Rt_compute(model)
# print"R(t)=",Rt
RTt = RTt_compute(model, 0)
# print"R(Tt)=",RTt
# leaves=nodes_all_count(model,0)#no use now
# print"all nodes=",leaves
gt_list = []
prune_parts = []
gt_with_tree(model, gt_list, prune_parts)
print "gt_list=", gt_list
print "prune_parts=", prune_parts
print "len(prune_parts)=", len(prune_parts)
# print"---------------------------------------------------------"
# print len(gt_list)
# print_list(prune_parts)
# print"---------------------------------------------------------"
# print len(prune_parts)
print "model=", model
alpha = min(gt_list)
prune_gt_index = gt_list.index(alpha)
# print"prune_gt_index=",prune_gt_index
prune_for_minimum_gt = prune_parts[prune_gt_index]
# print"prune_for_minimum_gt=\n",prune_for_minimum_gt
#------------------------------
T0 = copy.deepcopy(model)
T1 = copy.deepcopy(model) #here T1 means Ti
gt_list = [] #这里必须复位清零
pruned_parts = [] #这里必须复位清零
T1_create(T1, gt_list, pruned_parts, prune_gt_index)
print "pruned_parts=", pruned_parts
index = 0 #never change this value！！！
sklearn_model = copy.deepcopy(dtr)
prune_sklearn_model(sklearn_model.tree_, index, T1)
dot_file = "./visualization/T" + Tt_name + ".dot"
png_file = "./visualization/T" + Tt_name + ".svg"
# draw_file(sklearn_model,dot_file,png_file,X_train,feature_names)
draw_file(sklearn_model, dot_file, png_file, feature_names)
return sklearn_model, T1, alpha