Question

我已经绘制了一些ROC曲线来计算AUC。我的ROC曲线实际上不像曲线那样绘制。我已附上图片，以便更好地理解。如果有人可以告诉我那里有什么问题。我有义务。 This is one kind of plot I am getting This is the another type However I am not getting a curve like this one. 这是我的数据集的链接 https://drive.google.com/open?id=1luj8d863_IOA36cQTo772GEWgUsrXlbJ 如果有人可以帮助我理解问题，或者曲线是否正确，我将不胜感激，为什么它实际上不在结构之类的曲线中

import numpy as np
import pandas as pd
from sklearn.pipeline import Pipeline
from sklearn.decomposition import PCA
from keras.layers import Dense, Input
from keras.wrappers.scikit_learn import KerasClassifier
from keras.models import Model,Sequential
from keras.utils import np_utils
from sklearn.model_selection import train_test_split, cross_val_score, KFold
import matplotlib.pyplot as plt
from sklearn.preprocessing import LabelEncoder, MinMaxScaler, StandardScaler
from itertools import cycle
from sklearn.metrics import roc_curve, auc
from imblearn.over_sampling import SMOTE
seed = 7
np.random.seed(seed)    
dataset = pd.read_csv('dataset/prostate.csv')
labels = dataset.values[:,-1]
features_set = dataset.iloc[:,0:12600]
oversampler = SMOTE(random_state=0)
oversampler_feature_set, oversampler_labels = oversampler.fit_sample(features_set,labels)
feature_df = pd.DataFrame(oversampler_feature_set)
labels_df = pd.DataFrame(oversampler_labels)
scalar = MinMaxScaler()
scaled_data = scalar.fit_transform(feature_df)
pca = PCA(n_components=30)
pca_data = pd.DataFrame(pca.fit_transform(scaled_data))
recreated_df = pd.concat([pca_data,labels_df], axis=1)
train, test = train_test_split(recreated_df,test_size=0.2)
X_train = train.values[:,0:30]
Y_train = train.values[:,-1]
X_test = test.values[:,0:30]
y_test = test.values[:,-1]
def my_model():
    model = Sequential()
    model.add(Dense(20, input_dim=30,activation='sigmoid'))
    model.add(Dense(10, activation='sigmoid'))
    model.add(Dense(1, activation='sigmoid'))
    model.compile(loss='binary_crossentropy', optimizer='adam',metrics=['accuracy'])
    return model
estimator = KerasClassifier(build_fn=my_model, epochs=1000, batch_size=10, shuffle=True,verbose=1)
kfold = KFold(n_splits=10, shuffle=True, random_state=seed)
results = cross_val_score(estimator,X_train,Y_train, cv=kfold)
results.mean()
estimator.fit(X_train,Y_train)
y_pred = estimator.predict(X_test).ravel()
sensitivity, specificity, thresholds_keras = roc_curve(y_test,y_pred,pos_label=2)
auc_keras = auc(sensitivity,specificity)
plt.figure(1)
plt.plot([0, 1], [0, 1], 'k--')
plt.plot(sensitivity, specificity, label='Keras (area =:.3f})'.format(auc_keras))
plt.xlabel('Specificity')
plt.ylabel('Sensitivity')
plt.title('Prostate')
plt.legend(loc='best')
plt.show()

ROC曲线不是曲线

0 个答案: