Updated 3 years ago
Vectorize Text Using Different Techniques for Data Mining the Mahābhārata
import sklearn
print(sklearn.__version__)
0.20.3
with open('/content/drive/MyDrive/beproject/rawdata/maha01.txt') as f:
maha01 = f.read()
with open('/content/drive/MyDrive/beproject/rawdata/maha02.txt') as f:
maha02 = f.read()
with open('/content/drive/MyDrive/beproject/rawdata/maha03.txt') as f:
maha03 = f.read()
with open('/content/drive/MyDrive/beproject/rawdata/maha04.txt') as f:
maha04 = f.read()
with open('/content/drive/MyDrive/beproject/rawdata/maha05.txt') as f:
maha05 = f.read()
with open('/content/drive/MyDrive/beproject/rawdata/maha06.txt') as f:
maha06 = f.read()
with open('/content/drive/MyDrive/beproject/rawdata/maha07.txt') as f:
maha07 = f.read()
with open('/content/drive/MyDrive/beproject/rawdata/maha08.txt') as f:
maha08 = f.read()
with open('/content/drive/MyDrive/beproject/rawdata/maha09.txt') as f:
maha09 = f.read()
with open('/content/drive/MyDrive/beproject/rawdata/maha10.txt') as f:
maha10 = f.read()
with open('/content/drive/MyDrive/beproject/rawdata/maha11.txt') as f:
maha11 = f.read()
with open('/content/drive/MyDrive/beproject/rawdata/maha12.txt') as f:
maha12 = f.read()
with open('/content/drive/MyDrive/beproject/rawdata/maha13.txt') as f:
maha13 = f.read()
with open('/content/drive/MyDrive/beproject/rawdata/maha14.txt') as f:
maha14 = f.read()
with open('/content/drive/MyDrive/beproject/rawdata/maha15.txt') as f:
maha15 = f.read()
with open('/content/drive/MyDrive/beproject/rawdata/maha16.txt') as f:
maha16 = f.read()
with open('/content/drive/MyDrive/beproject/rawdata/maha17.txt') as f:
maha17 = f.read()
with open('/content/drive/MyDrive/beproject/rawdata/maha18.txt') as f:
maha18 = f.read()
CountVectorizer
from google.colab import drive
drive.mount('/content/drive')
Mounted at /content/drive