import pandas as pd
import statsmodels.api as sm
import pylab as pl
import numpy as np
from sklearn.metrics import roc_curve, auc
# read the data in
df = pd.read_csv("http://www.ats.ucla.edu/stat/data/binary.csv")
# rename the 'rank' column because there is also a DataFrame method called 'rank'
df.columns = ["admit", "gre", "gpa", "prestige"]
# dummify rank
dummy_ranks = pd.get_dummies(df['prestige'], prefix='prestige')
# create a clean data frame for the regression
cols_to_keep = ['admit', 'gre', 'gpa']
data = df[cols_to_keep].join(dummy_ranks.ix[:, 'prestige_2':])
# manually add the intercept
data['intercept'] = 1.0
train_cols = data.columns[1:]
# fit the model
result = sm.Logit(data['admit'], data[train_cols]).fit()
print result.summary()
# Add prediction to dataframe
data['pred'] = result.predict(data[train_cols])
fpr, tpr, thresholds =roc_curve(data['admit'], data['pred'])
roc_auc = auc(fpr, tpr)
print("Area under the ROC curve : %f" % roc_auc)
####################################
# The optimal cut off would be where tpr is high and fpr is low
# tpr - (1-fpr) is zero or near to zero is the optimal cut off point
####################################
i = np.arange(len(tpr)) # index for df
roc = pd.DataFrame({'fpr' : pd.Series(fpr, index=i),'tpr' : pd.Series(tpr, index = i), '1-fpr' : pd.Series(1-fpr, index = i), 'tf' : pd.Series(tpr - (1-fpr), index = i), 'thresholds' : pd.Series(thresholds, index = i)})
roc.ix[(roc.tf-0).abs().argsort()[:1]]
# Plot tpr vs 1-fpr
fig, ax = pl.subplots()
pl.plot(roc['tpr'])
pl.plot(roc['1-fpr'], color = 'red')
pl.xlabel('1-False Positive Rate')
pl.ylabel('True Positive Rate')
pl.title('Receiver operating characteristic')
ax.set_xticklabels([])
def Find_Optimal_Cutoff(target, predicted):
""" Find the optimal probability cutoff point for a classification model related to event rate
Parameters
----------
target : Matrix with dependent or target data, where rows are observations
predicted : Matrix with predicted data, where rows are observations
Returns
-------
list type, with optimal cutoff value
"""
fpr, tpr, threshold = roc_curve(target, predicted)
i = np.arange(len(tpr))
roc = pd.DataFrame({'tf' : pd.Series(tpr-(1-fpr), index=i), 'threshold' : pd.Series(threshold, index=i)})
roc_t = roc.ix[(roc.tf-0).abs().argsort()[:1]]
return list(roc_t['threshold'])
# Add prediction probability to dataframe
data['pred_proba'] = result.predict(data[train_cols])
# Find optimal probability threshold
threshold = Find_Optimal_Cutoff(data['admit'], data['pred_proba'])
print threshold
# [0.31762762459360921]
# Find prediction to the dataframe applying threshold
data['pred'] = data['pred_proba'].map(lambda x: 1 if x > threshold else 0)
# Print confusion Matrix
from sklearn.metrics import confusion_matrix
confusion_matrix(data['admit'], data['pred'])
# array([[175, 98],
# [ 46, 81]])
给定tpr、fpr、问题的阈值,最佳阈值的答案是:
虽然现在回答得晚,但思考可能会有帮助。您可以使用R(here!)中的
epi
包来完成此操作,但是我在python中找不到类似的包或示例。最佳截止点是
true positive rate
为高和false positive rate
为低的地方。基于这个逻辑,我在下面画了一个例子来寻找最佳阈值。Python代码:
最佳截止点是0.317628,因此高于此值的任何值都可以标记为1或0。从输出/图表可以看出,在当前示例中,当tpr与1-fpr交叉时,tpr为63%,fpr为36%,tpr-(1-fpr)最接近于零。
输出:
希望这对你有帮助。
编辑
为了简化和引入可重用性,我做了一个函数来寻找最佳的概率临界点。
Python代码:
Youden的J-Score的普通Python实现
相关问题 更多 >
编程相关推荐