In [1]:
print(__doc__)
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
from sklearn.preprocessing import label_binarize
from sklearn.metrics import confusion_matrix
%matplotlib inline
dir = '/Users/chanjinpark/GitHub/NRFAnalysis/'
df = pd.read_csv(dir + 'data/predlabel.txt')
df.columns = ['docid', 'prediction', 'label']
df.info
Out[1]:
<bound method DataFrame.info of docid prediction label
0 2013R1A1A1005147 22.0 22.0
1 2013R1A1A1005486 15.0 15.0
2 2013R1A1A1005731 23.0 23.0
3 2013R1A1A1006062 6.0 17.0
4 2013R1A1A1006606 3.0 4.0
5 2013R1A1A1006701 6.0 6.0
6 2013R1A1A1007068 6.0 6.0
7 2013R1A1A1007084 6.0 6.0
8 2013R1A1A1007475 10.0 17.0
9 2013R1A1A1007541 1.0 1.0
10 2013R1A1A1007615 5.0 15.0
11 2013R1A1A1007658 2.0 15.0
12 2013R1A1A1007706 5.0 15.0
13 2013R1A1A1008098 23.0 23.0
14 2013R1A1A1008154 12.0 15.0
15 2013R1A1A1008228 26.0 4.0
16 2013R1A1A1008431 15.0 24.0
17 2013R1A1A1008686 0.0 0.0
18 2013R1A1A1008910 3.0 4.0
19 2013R1A1A1009085 8.0 8.0
20 2013R1A1A1009259 17.0 17.0
21 2013R1A1A1009437 3.0 15.0
22 2013R1A1A1009571 7.0 7.0
23 2013R1A1A1009630 22.0 22.0
24 2013R1A1A1009816 2.0 9.0
25 2013R1A1A1009840 10.0 10.0
26 2013R1A1A1010004 1.0 1.0
27 2013R1A1A1010171 11.0 11.0
28 2013R1A1A1010185 8.0 8.0
29 2013R1A1A1010268 15.0 15.0
... ... ... ...
2369 2015R1D1A3A01020444 10.0 10.0
2370 2015R1D1A3A01020450 3.0 3.0
2371 2015R1D1A3A01020539 22.0 22.0
2372 2015R1D1A3A01020625 15.0 5.0
2373 2015R1D1A3A01020635 8.0 5.0
2374 2015R1D1A3A01020651 3.0 12.0
2375 2015R1D1A3A01020679 5.0 4.0
2376 2015R1D1A3A01020750 1.0 9.0
2377 2015R1D1A3A01020817 22.0 17.0
2378 2015R1D1A3A03015653 15.0 14.0
2379 2015R1D1A3A03020569 10.0 17.0
2380 2015R1D1A4A01016293 8.0 4.0
2381 2015R1D1A4A01016406 5.0 5.0
2382 2015R1D1A4A01016640 15.0 5.0
2383 2015R1D1A4A01016662 5.0 8.0
2384 2015R1D1A4A01017672 5.0 3.0
2385 2015R1D1A4A01018668 22.0 18.0
2386 2015R1D1A4A01019028 15.0 5.0
2387 2015R1D1A4A01019211 3.0 3.0
2388 2015R1D1A4A01019610 7.0 7.0
2389 2015R1D1A4A01019646 8.0 12.0
2390 2015R1D1A4A01019759 5.0 8.0
2391 2015R1D1A4A01019835 1.0 1.0
2392 2015R1D1A4A01019937 20.0 20.0
2393 2015R1D1A4A01019960 6.0 6.0
2394 2015R1D1A4A01020104 15.0 8.0
2395 2015R1D1A4A01020317 26.0 26.0
2396 2015R1D1A4A01020352 10.0 10.0
2397 2015R1D1A4A01020665 22.0 22.0
2398 2015R1D1A4A01020961 6.0 6.0
[2399 rows x 3 columns]>
In [ ]:
Content source: chanjin/NRFAnalysis
Similar notebooks: