This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/python | |
import numpy as np | |
from sklearn import cross_validation | |
from sklearn import svm | |
import pandas as pd | |
import math as m | |
from sklearn import preprocessing |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/bin/bash | |
#script for preprocessing html files using bash | |
####BETTER PERFORMANCE THAN PYTHON/R######## | |
#Check for time | |
date | |
#loop through files | |
for file in `ls ./Train1/*.txt` | |
do | |
#Remove html tags |