In [22]:

    

import numpy as np
import matplotlib.pyplot as plt

import pandas as pd
from sklearn.preprocessing import label_binarize
from sklearn.metrics import roc_curve, auc

%matplotlib inline

dir = '/Users/chanjinpark/GitHub/NRFAnalysis/'
df = pd.read_csv(dir + 'data/predlabel.txt')
df.columns = ['docid', 'prediction', 'label']
df.info

y = label_binarize(df['label'], classes = [x for x in range(27)])
nclasses = y.shape[1]
X = df['prediction']
X.shape[0]


    

    
Out[22]:





2399

In [10]:

    

verts = [x for x in range(10)]
verts


    

    
Out[10]:





[0, 1, 2, 3, 4, 5, 6, 7, 8, 9]

In [ ]: