我正在尝试使用逻辑回归软件包在Python中开发的预测模型来绘制ROC曲线以评估模型的准确性。我已经计算出真正例率和假正例率,但是我无法弄清如何使用matplotlib
正确绘制这些并计算AUC值。我该怎么做?
我正在尝试使用逻辑回归软件包在Python中开发的预测模型来绘制ROC曲线以评估模型的准确性。我已经计算出真正例率和假正例率,但是我无法弄清如何使用matplotlib
正确绘制这些并计算AUC值。我该怎么做?
以下是两种尝试的方法,假设您的model
是一个sklearn预测器:
import sklearn.metrics as metrics
# calculate the fpr and tpr for all thresholds of the classification
probs = model.predict_proba(X_test)
preds = probs[:,1]
fpr, tpr, threshold = metrics.roc_curve(y_test, preds)
roc_auc = metrics.auc(fpr, tpr)
# method I: plt
import matplotlib.pyplot as plt
plt.title('Receiver Operating Characteristic')
plt.plot(fpr, tpr, 'b', label = 'AUC = %0.2f' % roc_auc)
plt.legend(loc = 'lower right')
plt.plot([0, 1], [0, 1],'r--')
plt.xlim([0, 1])
plt.ylim([0, 1])
plt.ylabel('True Positive Rate')
plt.xlabel('False Positive Rate')
plt.show()
# method II: ggplot
from ggplot import *
df = pd.DataFrame(dict(fpr = fpr, tpr = tpr))
ggplot(df, aes(x = 'fpr', y = 'tpr')) + geom_line() + geom_abline(linetype = 'dashed')
或者尝试一下
ggplot(df, aes(x = 'fpr', ymin = 0, ymax = 'tpr')) + geom_line(aes(y = 'tpr')) + geom_area(alpha = 0.2) + ggtitle("ROC Curve w/ AUC = %s" % str(roc_auc))
import scikitplot as skplt
import matplotlib.pyplot as plt
y_true = # ground truth labels
y_probas = # predicted probabilities generated by sklearn classifier
skplt.metrics.plot_roc_curve(y_true, y_probas)
plt.show()
y_true
和 y_probas
? - Md. Rezwanul Haqueskplt.metrics.plot_roc_curve(y_true, y_probas)
吗?非常感谢你。 - salvufrom sklearn import svm, datasets
from sklearn import metrics
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
from sklearn.datasets import load_breast_cancer
import matplotlib.pyplot as plt
breast_cancer = load_breast_cancer()
X = breast_cancer.data
y = breast_cancer.target
X_train, X_test, y_train, y_test = train_test_split(X,y,test_size=0.33, random_state=44)
clf = LogisticRegression(penalty='l2', C=0.1)
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
print("Accuracy", metrics.accuracy_score(y_test, y_pred))
y_pred_proba = clf.predict_proba(X_test)[::,1]
fpr, tpr, _ = metrics.roc_curve(y_test, y_pred_proba)
auc = metrics.roc_auc_score(y_test, y_pred_proba)
plt.plot(fpr,tpr,label="data 1, auc="+str(auc))
plt.legend(loc=4)
plt.show()
目前还不清楚这里的问题所在,但如果你有一个数组true_positive_rate
和一个数组false_positive_rate
,那么绘制ROC曲线并获取AUC就像这样简单:
import matplotlib.pyplot as plt
import numpy as np
x = # false_positive_rate
y = # true_positive_rate
# This is the ROC curve
plt.plot(x,y)
plt.show()
# This is the AUC
auc = np.trapz(y,x)
以下是计算ROC曲线(散点图)的Python代码:
import matplotlib.pyplot as plt
import numpy as np
score = np.array([0.9, 0.8, 0.7, 0.6, 0.55, 0.54, 0.53, 0.52, 0.51, 0.505, 0.4, 0.39, 0.38, 0.37, 0.36, 0.35, 0.34, 0.33, 0.30, 0.1])
y = np.array([1,1,0, 1, 1, 1, 0, 0, 1, 0, 1,0, 1, 0, 0, 0, 1 , 0, 1, 0])
# false positive rate
fpr = []
# true positive rate
tpr = []
# Iterate thresholds from 0.0, 0.01, ... 1.0
thresholds = np.arange(0.0, 1.01, .01)
# get number of positive and negative examples in the dataset
P = sum(y)
N = len(y) - P
# iterate through all thresholds and determine fraction of true positives
# and false positives found at this threshold
for thresh in thresholds:
FP=0
TP=0
for i in range(len(score)):
if (score[i] > thresh):
if y[i] == 1:
TP = TP + 1
if y[i] == 0:
FP = FP + 1
fpr.append(FP/float(N))
tpr.append(TP/float(P))
plt.scatter(fpr, tpr)
plt.show()
from sklearn import metrics
import numpy as np
import matplotlib.pyplot as plt
y_true = # true labels
y_probas = # predicted results
fpr, tpr, thresholds = metrics.roc_curve(y_true, y_probas, pos_label=0)
# Print ROC curve
plt.plot(fpr,tpr)
plt.show()
# Print AUC
auc = np.trapz(tpr,fpr)
print('AUC:', auc)
y_true = #真实标签, y_probas = #预测结果
? - Md. Rezwanul Haque根据stackoverflow、scikit-learn文档和其他来源的多个评论,我制作了一个Python包,可以以非常简单的方式绘制ROC曲线(和其他指标)。
安装包:pip install plot-metric
(更多信息请见本文末尾)
绘制ROC曲线(下面的示例来自文档):
我们加载一个简单的数据集并创建训练集和测试集:
from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split
X, y = make_classification(n_samples=1000, n_classes=2, weights=[1,1], random_state=1)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5, random_state=2)
训练分类器并对测试集进行预测:
from sklearn.ensemble import RandomForestClassifier
clf = RandomForestClassifier(n_estimators=50, random_state=23)
model = clf.fit(X_train, y_train)
# Use predict_proba to predict probability of the class
y_pred = clf.predict_proba(X_test)[:,1]
您现在可以使用plot_metric来绘制ROC曲线:
from plot_metric.functions import BinaryClassification
# Visualisation with plot_metric
bc = BinaryClassification(y_test, y_pred, labels=["Class 1", "Class 2"])
# Figures
plt.figure(figsize=(5,5))
bc.plot_roc_curve()
plt.show()
您可以在该软件包的Github和文档中找到更多示例:
有一个叫做metriculous的库可以为您完成这个任务:
$ pip install metriculous
首先让我们模拟一些数据,通常这些数据来自测试数据集和模型:
import numpy as np
def normalize(array2d: np.ndarray) -> np.ndarray:
return array2d / array2d.sum(axis=1, keepdims=True)
class_names = ["Cat", "Dog", "Pig"]
num_classes = len(class_names)
num_samples = 500
# Mock ground truth
ground_truth = np.random.choice(range(num_classes), size=num_samples, p=[0.5, 0.4, 0.1])
# Mock model predictions
perfect_model = np.eye(num_classes)[ground_truth]
noisy_model = normalize(
perfect_model + 2 * np.random.random((num_samples, num_classes))
)
random_model = normalize(np.random.random((num_samples, num_classes)))
import metriculous
metriculous.compare_classifiers(
ground_truth=ground_truth,
model_predictions=[perfect_model, noisy_model, random_model],
model_names=["Perfect Model", "Noisy Model", "Random Model"],
class_names=class_names,
one_vs_all_figures=True, # This line is important to include ROC curves in the output
).save_html("model_comparison.html").display()
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])
all thresholds
是什么,它们是如何计算的? - mrgloom