def Test(inp):
print("Entered Test")
wordcount = 0
#inp = raw_input("Enter the name of the test file : ") # test
#inp = raw_input("Enter the name of the test file (filename.txt) : ")
#path = ('./dataset/Test/input/raghuram.txt')
import os
script_dir = os.path.dirname(__file__) #<-- absolute dir the script is in
rel_path = "/dataset/Test/input/" + str(inp)
#abs_file_path = os.path.join(script_dir, rel_path)
#abs_file_path = os.path.abspath(os.path.dirname(__file__))
path = os.getcwd()
print path
abs_file_path = str(path) + str(rel_path)
#parentdir = os.path.dirname(path)
#os.chdir(parentdir)
#path = os.getcwd()
print "\n\n\npath="
print abs_file_path
print "\n\n\n\n"
#paths = os.path.abspath('dataset/Test/input/'+str(inp))
paths = abs_file_path
#path = ('./dataset/Test/input/'+inp)
#f = open(paths,'r')
arra = []
with open(paths, 'r+') as f:
tweets = [x.strip() for x in f]
preprocessed = preproc.tweet_mains(tweets)
wordcount = w.generatetestset(preprocessed, str(inp))
svm.create_trainfile(2, str(inp))
arra = svm.testSVM(str(inp))
print("Leaving Test")
return arra
def Test():
print("Entered Test")
wordcount = 0
path = ('./dataset/Test/input/bse.txt')
with open(path) as f:
tweets = [x.strip() for x in f]
preprocessed = preproc.tweet_mains(tweets)
wordcount = w.generatetestset(preprocessed)
print("Leaving Test")
def Test():
print("Entered Test")
wordcount = 0
#inp = raw_input("Enter the name of the test file : ") # test
inp = raw_input("Enter the name of the test file (filename.txt) : ")
#path = ('./dataset/Test/input/raghuram.txt')
path = ('./dataset/Test/input/' + str(inp))
#path = ('./dataset/Test/input/raghuram.txt')
with open(path) as f:
tweets = [x.strip() for x in f]
preprocessed = preproc.tweet_mains(tweets)
wordcount = w.generatetestset(preprocessed)
print("Leaving Test")
def Train():
print("EnteredTrain")
preprocessed = []
wordcount = 0
categoryId = 0
path = ('./dataset/input/')
#string =[ "Hello this is it;","Hi How are you","This is Congratulations:"]
for filename in glob.glob(os.path.join(path, '*.txt')):
categoryId += 1
with open(filename) as f:
tweets = [x.strip() for x in f]
preprocessed = preproc.tweet_mains(tweets)
wordcount = w.generatewordset(preprocessed, categoryId)
#svm.create_trainfile() "not complete"
'''for pre in preprocessed:
print pre'''
print("Leaving Train")
def Train():
print("EnteredTrain")
preprocessed = []
wordcount = 0
categoryId =0
#string =[ "Hello this is it;","Hi How are you","This is Congratulations:"]
path = ('./dataset/input/')
#string =[ "Hello this is it;","Hi How are you","This is Congratulations:"]
for filename in glob.glob(os.path.join(path, '*.txt')):
with open('./dataset/test.txt','r+') as f:
tweets = [x.strip() for x in f]
preprocessed = preproc.tweet_mains(tweets)
m = Word2Vec(preprocessed)
print m.vocab
m.most_similar('SunRisers', topn=5)
'''for tweet in preprocessed:
def Train():
print("EnteredTrain")
preprocessed = []
wordcount = 0
categoryId = 0
#string =[ "Hello this is it;","Hi How are you","This is Congratulations:"]
path = ('./dataset/input/')
#string =[ "Hello this is it;","Hi How are you","This is Congratulations:"]
for filename in glob.glob(os.path.join(path, '*.txt')):
print categoryId
categoryId += 1
with open(filename, 'r+') as f:
tweets = [x.strip() for x in f]
preprocessed.append(preproc.tweet_mains(tweets))
for tweet in preprocessed:
for word in tweet:
print word
print '\n'
'''m = Word2Vec(preprocessed)
def Train():
print("EnteredTrain")
preprocessed = []
wordcount = 0
categoryId = 0
files = [
'./dataset/input/sports.txt', './dataset/input/finance.txt',
'./dataset/input/politics.txt', './dataset/input/technology.txt',
'./dataset/input/entertainment.txt'
]
#string =[ "Hello this is it;","Hi How are you","This is Congratulations:"]
for filename in files:
categoryId += 1
with open(filename) as f:
tweets = [x.strip() for x in f]
preprocessed = preproc.tweet_mains(tweets)
wordcount = w.generatewordset(preprocessed, categoryId)
#svm.create_trainfile() "not complete"
'''for pre in preprocessed:
print pre'''
print("Leaving Train")