On 02/22/2015 01:21 PM, shalu jhanwar wrote:
Hi guys,
thanks a lot for all your interesting replies.
i) How can I get threshold value which the classifier has decided to
take the decision for a particular sample to be in 0 or 1 class in
binary classification using scikit? The whole purpose of my previous
questions were to know about that threshold value (either by
visualising it or just get values)?
That is always 0 for decision_function.
ii) Also can I know the threshold values in each iteration which
scikit used to generate each point on ROC curve using these below lines:
fpr = dict()
tpr = dict()
roc_auc = dict()
for i in range(n_classes):
fpr[i], tpr[i], _ = roc_curve
<http://scikit-learn.org/stable/modules/generated/sklearn.metrics.roc_curve.html#sklearn.metrics.roc_curve>(y_test[:,
i], y_score[:, i])
roc_auc[i] = auc
<http://scikit-learn.org/stable/modules/generated/sklearn.metrics.auc.html#sklearn.metrics.auc>(fpr[i],
tpr[i])
# Compute micro-average ROC curve and ROC area
fpr["micro"], tpr["micro"], _ = roc_curve
<http://scikit-learn.org/stable/modules/generated/sklearn.metrics.roc_curve.html#sklearn.metrics.roc_curve>(y_test.ravel(),
y_score.ravel())
roc_auc["micro"] = auc
<http://scikit-learn.org/stable/modules/generated/sklearn.metrics.auc.html#sklearn.metrics.auc>(fpr["micro"],
tpr["micro"])
I'm just using this default code, but I would like to know about the
threshold it uses to generate each point of ROC
The threshold is the third returned value of roc_curve, which you assign
to _
------------------------------------------------------------------------------
Download BIRT iHub F-Type - The Free Enterprise-Grade BIRT Server
from Actuate! Instantly Supercharge Your Business Reports and Dashboards
with Interactivity, Sharing, Native Excel Exports, App Integration & more
Get technology previously reserved for billion-dollar corporations, FREE
http://pubads.g.doubleclick.net/gampad/clk?id=190641631&iu=/4140/ostg.clktrk
_______________________________________________
Scikit-learn-general mailing list
Scikit-learn-general@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
