为 DecisionTreeClassifier 绘制 multi-class ROC 曲线
Plot multi-class ROC curve for DecisionTreeClassifier
我试图用文档中提供的 svm.SVC 以外的分类器绘制 ROC 曲线。我的代码适用于 svm.SVC；但是，在我切换到 KNeighborsClassifier、MultinomialNB 和 DecisionTreeClassifier 之后，系统一直告诉我 check_consistent_length(y_true, y_score)andFound input variables with inconsistent numbers of samples: [26632, 53264] My CSV file looks like this
这是我的代码
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from itertools import cycle
import sys
from sklearn import svm, datasets
from sklearn.metrics import roc_curve, auc
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import label_binarize
from sklearn.multiclass import OneVsRestClassifier
from scipy import interp
from sklearn.neighbors import KNeighborsClassifier
from sklearn.naive_bayes import MultinomialNB
from sklearn.tree import DecisionTreeClassifier
# Import some data to play with
df = pd.read_csv("E:\autodesk\Hourly and weather categorized2.csv")
X =df[['TTI','Max TemperatureF','Mean TemperatureF','Min TemperatureF',' Min Humidity']].values
y = df['TTI_Category'].as_matrix()
y=y.reshape(-1,1)
# Binarize the output
y = label_binarize(y, classes=['Good','Bad'])
n_classes = y.shape[1]
# shuffle and split training and test sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.5,
random_state=0)
# Learn to predict each class against the other
classifier = OneVsRestClassifier(DecisionTreeClassifier(random_state=0))
y_score = classifier.fit(X_train, y_train).predict_proba(X_test)
# Compute ROC curve and ROC area for each class
fpr = dict()
tpr = dict()
roc_auc = dict()
for i in range(n_classes):
fpr[i], tpr[i], _ = roc_curve(y_test[:, i], y_score[:, i])
roc_auc[i] = auc(fpr[i], tpr[i])
# Compute micro-average ROC curve and ROC area
fpr["micro"], tpr["micro"], _ = roc_curve(y_test.ravel(), y_score.ravel())
roc_auc["micro"] = auc(fpr["micro"], tpr["micro"])
plt.figure()
lw = 1
plt.plot(fpr[0], tpr[0], color='darkorange', lw=lw, label='ROC curve (area = %0.2f)' % roc_auc[0])
plt.plot([0, 1], [0, 1], color='navy', lw=lw, linestyle='--')
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('Receiver operating characteristic example')
plt.legend(loc="lower right")
plt.show()
我怀疑错误发生在这一行 fpr["micro"], tpr["micro"], _ = roc_curve(y_test.ravel(), y_score.ravel())
roc_auc["micro"] = auc(fpr["micro"], tpr["micro"])，但我是这条 ROC 曲线的初学者，所以有人可以指导我完成这个回溯。非常感谢您的时间和帮助。
顺便说一句，这里是整个追溯。希望我的解释足够清楚。 `
Traceback (most recent call last):
File "<ipython-input-1-16eb0db9d4d9>", line 1, in <module>
runfile('C:/Users/Think/Desktop/Python Practice/ROC with decision tree.py', wdir='C:/Users/Think/Desktop/Python Practice')
File "C:\Users\Think\Anaconda2\lib\site-packages\spyder\utils\site\sitecustomize.py", line 880, in runfile
execfile(filename, namespace)
File "C:\Users\Think\Anaconda2\lib\site-packages\spyder\utils\site\sitecustomize.py", line 87, in execfile
exec(compile(scripttext, filename, 'exec'), glob, loc)
File "C:/Users/Think/Desktop/Python Practice/ROC with decision tree.py", line 47, in <module>
fpr["micro"], tpr["micro"], _ = roc_curve(y_test.ravel(), y_score.ravel())
File "C:\Users\Think\Anaconda2\lib\site-packages\sklearn\metrics\ranking.py", line 510, in roc_curve
y_true, y_score, pos_label=pos_label, sample_weight=sample_weight)
File "C:\Users\Think\Anaconda2\lib\site-packages\sklearn\metrics\ranking.py", line 302, in _binary_clf_curve
check_consistent_length(y_true, y_score)
File "C:\Users\Think\Anaconda2\lib\site-packages\sklearn\utils\validation.py", line 173, in check_consistent_length
" samples: %r" % [int(l) for l in lengths])
ValueError: Found input variables with inconsistent numbers of samples: [26632, 53264]
您需要使用DecisionTreeClassifier的predict_proba函数:
示例：
import matplotlib.pyplot as plt
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import label_binarize
from sklearn.metrics import roc_curve, auc
from sklearn.multiclass import OneVsRestClassifier
from sklearn.tree import DecisionTreeClassifier
iris = datasets.load_iris()
X = iris.data
y = iris.target
# Binarize the output
y = label_binarize(y, classes=[0, 1, 2])
n_classes = y.shape[1]
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.5, random_state=0)
classifier = OneVsRestClassifier(DecisionTreeClassifier(random_state=0))
y_score = classifier.fit(X_train, y_train).predict_proba(X_test)
fpr = dict()
tpr = dict()
roc_auc = dict()
for i in range(n_classes):
fpr[i], tpr[i], _ = roc_curve(y_test[:, i], y_score[:, i])
roc_auc[i] = auc(fpr[i], tpr[i])
colors = cycle(['blue', 'red', 'green'])
for i, color in zip(range(n_classes), colors):
plt.plot(fpr[i], tpr[i], color=color, lw=lw,
label='ROC curve of class {0} (area = {1:0.2f})'
''.format(i, roc_auc[i]))
plt.plot([0, 1], [0, 1], 'k--', lw=lw)
plt.xlim([-0.05, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('Receiver operating characteristic for multi-class data')
plt.legend(loc="lower right")
plt.show()
在原来的代码中加入这一行问题得到解决y_resampled = label_binarize(y_resampled, classes=['Good','Bad','Ok'])
所有这些被忽略的实现都有一个关键的区别。 sklearn 中固有的基于树的算法将 one-hot 编码（二值化）目标标签解释为 multi-label 问题。要获得 multi-class 问题的 AUC 和 ROC 曲线，必须仅对 ROC 计算的输出进行二值化。默认情况下，不需要将 OneVsRestClassifier 与 inherently multi class 下规定的任何 algorithm 一起使用。对于本质上不是 multi class 的算法，使用 OVR classifier 或在 SVM 的情况下避免复杂的决策函数是有意义的。请参考下面的代码片段，第一个与上面示例中使用的代码相同。第二个是正确的实现，它考虑了训练多 class classifier 的位置，然后计算个人 class 的 ROC。检查图中的差异。
import matplotlib.pyplot as plt
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import label_binarize
from sklearn.metrics import roc_curve, auc
from sklearn.multiclass import OneVsRestClassifier
from sklearn.tree import DecisionTreeClassifier
iris = datasets.load_iris()
X = iris.data
y = iris.target
# Binarize the output
y = label_binarize(y, classes=[0, 1, 2])
n_classes = y.shape[1]
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.5, random_state=0)
classifier = OneVsRestClassifier(DecisionTreeClassifier(random_state=0))
y_score = classifier.fit(X_train, y_train).predict_proba(X_test)
fpr = dict()
tpr = dict()
roc_auc = dict()
for i in range(n_classes):
fpr[i], tpr[i], _ = roc_curve(y_test[:, i], y_score[:, i])
roc_auc[i] = auc(fpr[i], tpr[i])
colors = cycle(['blue', 'red', 'green'])
for i, color in zip(range(n_classes), colors):
plt.plot(fpr[i], tpr[i], color=color, lw=lw,
label='ROC curve of class {0} (area = {1:0.2f})'
''.format(i, roc_auc[i]))
plt.plot([0, 1], [0, 1], 'k--', lw=lw)
plt.xlim([-0.05, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('Receiver operating characteristic for multi-class data')
plt.legend(loc="lower right")
plt.show()
import matplotlib.pyplot as plt
from sklearn import datasets
from itertools import cycle
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import label_binarize
from sklearn.metrics import roc_curve, auc
from sklearn.multiclass import OneVsRestClassifier
from sklearn.tree import DecisionTreeClassifier
iris = datasets.load_iris()
X = iris.data
y = iris.target
# Binarize the output
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.5, random_state=0)
classifier = DecisionTreeClassifier(random_state=0)
y_score = classifier.fit(X_train, y_train).predict_proba(X_test)
y_test_bin = label_binarize(y_test, classes=[0, 1, 2])
n_classes = y_test_bin.shape[1]
fpr = dict()
tpr = dict()
roc_auc = dict()
for i in range(n_classes):
fpr[i], tpr[i], _ = roc_curve(y_test_bin[:, i], y_score[:, i])
roc_auc[i] = auc(fpr[i], tpr[i])
colors = cycle(['blue', 'red', 'green'])
for i, color in zip(range(n_classes), colors):
plt.plot(fpr[i], tpr[i], color=color,
label='ROC curve of class {0} (area = {1:0.2f})'
''.format(i, roc_auc[i]))
plt.plot([0, 1], [0, 1], 'k--')
plt.xlim([-0.05, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('Receiver operating characteristic for multi-class data')
plt.legend(loc="lower right")
plt.show()
我试图用文档中提供的 svm.SVC 以外的分类器绘制 ROC 曲线。我的代码适用于 svm.SVC；但是，在我切换到 KNeighborsClassifier、MultinomialNB 和 DecisionTreeClassifier 之后，系统一直告诉我 check_consistent_length(y_true, y_score)andFound input variables with inconsistent numbers of samples: [26632, 53264] My CSV file looks like this
这是我的代码
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from itertools import cycle
import sys
from sklearn import svm, datasets
from sklearn.metrics import roc_curve, auc
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import label_binarize
from sklearn.multiclass import OneVsRestClassifier
from scipy import interp
from sklearn.neighbors import KNeighborsClassifier
from sklearn.naive_bayes import MultinomialNB
from sklearn.tree import DecisionTreeClassifier
# Import some data to play with
df = pd.read_csv("E:\autodesk\Hourly and weather categorized2.csv")
X =df[['TTI','Max TemperatureF','Mean TemperatureF','Min TemperatureF',' Min Humidity']].values
y = df['TTI_Category'].as_matrix()
y=y.reshape(-1,1)
# Binarize the output
y = label_binarize(y, classes=['Good','Bad'])
n_classes = y.shape[1]
# shuffle and split training and test sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.5,
random_state=0)
# Learn to predict each class against the other
classifier = OneVsRestClassifier(DecisionTreeClassifier(random_state=0))
y_score = classifier.fit(X_train, y_train).predict_proba(X_test)
# Compute ROC curve and ROC area for each class
fpr = dict()
tpr = dict()
roc_auc = dict()
for i in range(n_classes):
fpr[i], tpr[i], _ = roc_curve(y_test[:, i], y_score[:, i])
roc_auc[i] = auc(fpr[i], tpr[i])
# Compute micro-average ROC curve and ROC area
fpr["micro"], tpr["micro"], _ = roc_curve(y_test.ravel(), y_score.ravel())
roc_auc["micro"] = auc(fpr["micro"], tpr["micro"])
plt.figure()
lw = 1
plt.plot(fpr[0], tpr[0], color='darkorange', lw=lw, label='ROC curve (area = %0.2f)' % roc_auc[0])
plt.plot([0, 1], [0, 1], color='navy', lw=lw, linestyle='--')
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('Receiver operating characteristic example')
plt.legend(loc="lower right")
plt.show()
我怀疑错误发生在这一行 fpr["micro"], tpr["micro"], _ = roc_curve(y_test.ravel(), y_score.ravel())
roc_auc["micro"] = auc(fpr["micro"], tpr["micro"])，但我是这条 ROC 曲线的初学者，所以有人可以指导我完成这个回溯。非常感谢您的时间和帮助。
Traceback (most recent call last):
File "<ipython-input-1-16eb0db9d4d9>", line 1, in <module>
runfile('C:/Users/Think/Desktop/Python Practice/ROC with decision tree.py', wdir='C:/Users/Think/Desktop/Python Practice')
File "C:\Users\Think\Anaconda2\lib\site-packages\spyder\utils\site\sitecustomize.py", line 880, in runfile
execfile(filename, namespace)
File "C:\Users\Think\Anaconda2\lib\site-packages\spyder\utils\site\sitecustomize.py", line 87, in execfile
exec(compile(scripttext, filename, 'exec'), glob, loc)
File "C:/Users/Think/Desktop/Python Practice/ROC with decision tree.py", line 47, in <module>
fpr["micro"], tpr["micro"], _ = roc_curve(y_test.ravel(), y_score.ravel())
File "C:\Users\Think\Anaconda2\lib\site-packages\sklearn\metrics\ranking.py", line 510, in roc_curve
y_true, y_score, pos_label=pos_label, sample_weight=sample_weight)
File "C:\Users\Think\Anaconda2\lib\site-packages\sklearn\metrics\ranking.py", line 302, in _binary_clf_curve
check_consistent_length(y_true, y_score)
File "C:\Users\Think\Anaconda2\lib\site-packages\sklearn\utils\validation.py", line 173, in check_consistent_length
" samples: %r" % [int(l) for l in lengths])
ValueError: Found input variables with inconsistent numbers of samples: [26632, 53264]
您需要使用DecisionTreeClassifier的predict_proba函数:
示例：
import matplotlib.pyplot as plt
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import label_binarize
from sklearn.metrics import roc_curve, auc
from sklearn.multiclass import OneVsRestClassifier
from sklearn.tree import DecisionTreeClassifier
iris = datasets.load_iris()
X = iris.data
y = iris.target
# Binarize the output
y = label_binarize(y, classes=[0, 1, 2])
n_classes = y.shape[1]
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.5, random_state=0)
classifier = OneVsRestClassifier(DecisionTreeClassifier(random_state=0))
y_score = classifier.fit(X_train, y_train).predict_proba(X_test)
fpr = dict()
tpr = dict()
roc_auc = dict()
for i in range(n_classes):
fpr[i], tpr[i], _ = roc_curve(y_test[:, i], y_score[:, i])
roc_auc[i] = auc(fpr[i], tpr[i])
colors = cycle(['blue', 'red', 'green'])
for i, color in zip(range(n_classes), colors):
plt.plot(fpr[i], tpr[i], color=color, lw=lw,
label='ROC curve of class {0} (area = {1:0.2f})'
''.format(i, roc_auc[i]))
plt.plot([0, 1], [0, 1], 'k--', lw=lw)
plt.xlim([-0.05, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('Receiver operating characteristic for multi-class data')
plt.legend(loc="lower right")
plt.show()
在原来的代码中加入这一行问题得到解决y_resampled = label_binarize(y_resampled, classes=['Good','Bad','Ok'])
所有这些被忽略的实现都有一个关键的区别。 sklearn 中固有的基于树的算法将 one-hot 编码（二值化）目标标签解释为 multi-label 问题。要获得 multi-class 问题的 AUC 和 ROC 曲线，必须仅对 ROC 计算的输出进行二值化。默认情况下，不需要将 OneVsRestClassifier 与 inherently multi class 下规定的任何 algorithm 一起使用。对于本质上不是 multi class 的算法，使用 OVR classifier 或在 SVM 的情况下避免复杂的决策函数是有意义的。请参考下面的代码片段，第一个与上面示例中使用的代码相同。第二个是正确的实现，它考虑了训练多 class classifier 的位置，然后计算个人 class 的 ROC。检查图中的差异。
import matplotlib.pyplot as plt
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import label_binarize
from sklearn.metrics import roc_curve, auc
from sklearn.multiclass import OneVsRestClassifier
from sklearn.tree import DecisionTreeClassifier
iris = datasets.load_iris()
X = iris.data
y = iris.target
# Binarize the output
y = label_binarize(y, classes=[0, 1, 2])
n_classes = y.shape[1]
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.5, random_state=0)
classifier = OneVsRestClassifier(DecisionTreeClassifier(random_state=0))
y_score = classifier.fit(X_train, y_train).predict_proba(X_test)
fpr = dict()
tpr = dict()
roc_auc = dict()
for i in range(n_classes):
fpr[i], tpr[i], _ = roc_curve(y_test[:, i], y_score[:, i])
roc_auc[i] = auc(fpr[i], tpr[i])
colors = cycle(['blue', 'red', 'green'])
for i, color in zip(range(n_classes), colors):
plt.plot(fpr[i], tpr[i], color=color, lw=lw,
label='ROC curve of class {0} (area = {1:0.2f})'
''.format(i, roc_auc[i]))
plt.plot([0, 1], [0, 1], 'k--', lw=lw)
plt.xlim([-0.05, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('Receiver operating characteristic for multi-class data')
plt.legend(loc="lower right")
plt.show()
import matplotlib.pyplot as plt
from sklearn import datasets
from itertools import cycle
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import label_binarize
from sklearn.metrics import roc_curve, auc
from sklearn.multiclass import OneVsRestClassifier
from sklearn.tree import DecisionTreeClassifier
iris = datasets.load_iris()
X = iris.data
y = iris.target
# Binarize the output
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.5, random_state=0)
classifier = DecisionTreeClassifier(random_state=0)
y_score = classifier.fit(X_train, y_train).predict_proba(X_test)
y_test_bin = label_binarize(y_test, classes=[0, 1, 2])
n_classes = y_test_bin.shape[1]
fpr = dict()
tpr = dict()
roc_auc = dict()
for i in range(n_classes):
fpr[i], tpr[i], _ = roc_curve(y_test_bin[:, i], y_score[:, i])
roc_auc[i] = auc(fpr[i], tpr[i])
colors = cycle(['blue', 'red', 'green'])
for i, color in zip(range(n_classes), colors):
plt.plot(fpr[i], tpr[i], color=color,
label='ROC curve of class {0} (area = {1:0.2f})'
''.format(i, roc_auc[i]))
plt.plot([0, 1], [0, 1], 'k--')
plt.xlim([-0.05, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('Receiver operating characteristic for multi-class data')
plt.legend(loc="lower right")
plt.show()