karimkhanp

import nltk
from nltk.corpus import stopwords

class PhraseExtractor(object):
    
    def __init__(self):
        self.sentence_re = r'(?:(?:[A-Z])(?:.[A-Z])+.?)|(?:\w+(?:-\w+)*)|(?:\$?\d+(?:.\d+)?%?)|(?:...|)(?:[][.,;"\'?():-_`])'
        self.lemmatizer = nltk.WordNetLemmatizer()
        self.stemmer = nltk.stem.porter.PorterStemmer()
        self.grammar = r"""

karimkhanp

#Function to read xlsx files

    def readExcel(self):
        from xlrd import open_workbook
        wb = open_workbook('Shortlisted Rumours Jan to June 2016.xlsx')
        for s in wb.sheets():
            for row in range(1, s.nrows):
                # pdb.set_trace()
                col_names = s.row(0)
                col_value = []

karimkhanp

import nltk
from nltk.corpus import stopwords

text = raw_input("Enter the text please ...")
print text

sentence_re = r'(?:(?:[A-Z])(?:.[A-Z])+.?)|(?:\w+(?:-\w+)*)|(?:\$?\d+(?:.\d+)?%?)|(?:...|)(?:[][.,;"\'?():-_`])'
lemmatizer = nltk.WordNetLemmatizer()
stemmer = nltk.stem.porter.PorterStemmer()
grammar = r"""

karimkhanp

sudo apt-get install build-essential

wget https://www.python.org/ftp/python/2.7.6/Python-2.7.6.tar.xz
tar -xf Python-2.7.6.tar.xz
cd Python-2.7.6
./configure
make 
make install

sudo apt-get install build-essential python-dev python-setuptools python-numpy python-scipy 

karimkhanp

Read basics about Python - http://www.tutorialspoint.com/python/python_overview.htm

Tutorials

http://www.tutorialspoint.com/python/index.htm
http://askpython.com/

More resources 

https://wiki.python.org/moin/BeginnersGuide/Programmers

karimkhanp

import sys

"""
NltkSentTokenize Class for all nltk sent tokenize
"""
class NltkSentTokenize(object):
    """
    Initialization function of NltkSentTokenize Class
    """
    def __init__(self):

karimkhanp

"""
Using the words as features removing stopwords
"""
from sklearn.utils import check_random_state
from sklearn.datasets import load_files
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.feature_extraction.text import HashingVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.metrics import accuracy_score, average_precision_score, f1_score, precision_score, recall_score

karimkhanp

Libraries:
    https://www.tensorflow.org/
    
Articles:
    https://www.kaggle.com/c/titanic/details/getting-started-with-python
    https://www.kaggle.com/c/titanic/details/getting-started-with-python-ii

karimkhanp

from __future__ import division
from math import log, exp
from operator import mul
from collections import Counter
import os
import pylab
import cPickle


class MyDict(dict):

karimkhanp

13 15 15 0 0 0 14 0 0 0 14 16 14 16 0 0 13 15 0 0 14 16 14 15 0 13 16 13 0 16 13 16 14 0 15 0 0 16 0 16 13 15 15 15 13 0 13 15 13 14 0 0 14 14 16 0 14 0 0 0 0 13 0 0 0 0 0 13 14 0 0 15 13 0 14 0 16 13 13 14 15 0 14 13 0 16 16 13 15 16 0 15 16 14 0 0 0 0 16 14 0 14 0 0 13 16 14 13 13 15 16 0 0 14 15 0 0 15 0 15 13 16 0 0 13 15 16 0 0 14 16 13 13 15 0 0 15 0 0 0 14 0 15 14 16 16 0 0 0 13 0 14 13 0 15 15 14 0 15 0 0 0 14 0 0 0 16 0 16 13 14 0 0 14 0 16 13 16 14 13 15 0 14 14 14 0 13 13 15 16 0 0 0 13 14 13 13 0 0 15 0 14 14 13 13 0 15 14 0 0 14 0 0 13 0 0 14 0 13 0 15 14 0 0 15 0 15 16 14 0 0 16 15 0 0 0 16 0 0 15 13 15 15 13 0 14 14 0 14 15 15 15 14 14 16 15 0 0 16 0 0 0 0 13 13 15 15 15 0 0 15 13 0 0 0 14 0 14 0 15 16 16 14 13 14 15 0 13 0 13 15 0 14 16 16 14 14 0 15 0 15 0 0 0 14 13 0 13 0 0 0 0 16 14 13 14 0 13 0 16 15 0 14 16 16 13 15 0 13 14 14 13 0 0 14 0 14 16 16 15 13 13 14 13 0 13 0 0 13 16 13 0 0 16 14 0 0 15 15 13 0 16 0 15 16 13 0 13 0 15 16 16 14 0 16 0 15 15 0 0 0 13 15 14 14 0 0 14 0 15 14 16 0 1