In [1]:

    

import logging

from sklearn.datasets import fetch_rcv1
from sklearn.multiclass import OneVsRestClassifier
from sklearn.metrics import f1_score, precision_score, recall_score
from sklearn.pipeline import Pipeline
from sklearn import svm

logging.basicConfig()
rcv1 = fetch_rcv1()


    

In [2]:

    

training_samples = 23149

X_train = rcv1.data[:training_samples]
X_test = rcv1.data[training_samples:]

y_train = rcv1.target[:training_samples]
y_test = rcv1.target[training_samples:]


    

In [15]:

    

sample_ids = rcv1.sample_id[:training_samples]


    

In [23]:

    

sample_ids[-1]


    

    
Out[23]:





26150

In [ ]: