Импорт
import numpy as np
from sklearn.metrics import roc_curve, auc
import matplotlib.pyplot as plt
Генерация данных
# simulate first dataset with 364 obs
df1 = \
pd.DataFrame(i for i in range(364))
df1['predict_proba_1'] = np.random.normal(0,1,len(df1))
df1['epsilon'] = np.random.normal(0,1,len(df1))
df1['true'] = (0.7*df1['epsilon'] < df1['predict_proba_1']) * 1
df1 = df1.drop(columns=[0, 'epsilon'])
# simulate second dataset with 763 obs
df2 = \
pd.DataFrame(i for i in range(763))
df2['predict_proba_2'] = np.random.normal(0,1,len(df2))
df2['epsilon'] = np.random.normal(0,1,len(df2))
df2['true'] = (0.7*df2['epsilon'] < df2['predict_proba_2']) * 1
df2 = df2.drop(columns=[0, 'epsilon'])
Быстрый просмотр сгенерированных данных
df1
predict_proba_1 true
0 1.234549 1
1 -0.586544 0
2 -0.229539 1
3 0.132185 1
4 -0.411284 0
.. ... ...
359 -0.218775 0
360 -0.985565 0
361 0.542790 1
362 -0.463667 0
363 1.119244 1
[364 rows x 2 columns]
df2
predict_proba_2 true
0 0.278755 1
1 0.653663 0
2 -0.304216 1
3 0.955658 1
4 -1.341669 0
.. ... ...
758 1.359606 1
759 -0.605894 0
760 0.379738 0
761 1.571615 1
762 -1.102565 0
[763 rows x 2 columns]
Необходимые функции
def show_ROCs(scores_list: list, ys_list: list, labels_list:list = None):
"""
This function plots a couple of ROCs. Corresponding labels are optional.
Parameters
----------
scores_list : list of array-likes with scorings or predicted probabilities.
ys_list : list of array-likes with ground true labels.
labels_list : list of labels to be displayed in plotted graph.
Returns
----------
None
"""
if len(scores_list) != len(ys_list):
raise Exception('len(scores_list) != len(ys_list)')
fpr_dict = dict()
tpr_dict = dict()
for x in range(len(scores_list)):
fpr_dict[x], tpr_dict[x], _ = roc_curve(ys_list[x], scores_list[x])
for x in range(len(scores_list)):
try:
plot_ROC(fpr_dict[x], tpr_dict[x], str(labels_list[x]) + ' AUC:' + str(round(auc(fpr_dict[x], tpr_dict[x]),3)))
except:
plot_ROC(fpr_dict[x], tpr_dict[x], str(x) + ' ' + str(round(auc(fpr_dict[x], tpr_dict[x]),3)))
plt.show()
def plot_ROC(fpr, tpr, label):
"""
This function plots a single ROC. Corresponding label is optional.
Parameters
----------
fpr : array-likes with fpr.
tpr : array-likes with tpr.
label : label to be displayed in plotted graph.
Returns
----------
None
"""
plt.figure(1)
plt.plot([0, 1], [0, 1], 'k--')
plt.plot(fpr, tpr, label=label)
plt.xlabel('False positive rate')
plt.ylabel('True positive rate')
plt.title('ROC curve')
plt.legend(loc='best')
Печать
show_ROCs(
[df1['predict_proba_1'], df2['predict_proba_2']],
[df1['true'], df2['true']],
['df1 with {} obs'.format(len(df1)), 'df2 with {} obs'.format(len(df2))]
)