Replace the tweet emoticon with sentiment text

Hi Dears,
See the code
This code helps to replace a text using another one in Python.
This is applied in sentiments analysis. So that the emoticons can be replaced by its sentiments.
This is used in the data mining part of the sentiments analysis using Python.


--------------------------

from nltk import NaiveBayesClassifier as nbc

from nltk.tokenize import word_tokenize

from itertools import chain

import csv

sentence="it is #abcd1212 and #12341212"

with open('emoticon.csv','r') as csvinput:

    reader=csv.reader(csvinput,delimiter=",")

    rownum = 0 

    training_data = []

    for code,tag in reader:

        sentence=sentence.replace(code,tag)

        

print(sentence)

------------------------------------

Output : it is positive and negativve

------------------------------------

emoticon.csv

#abcd1212,positive #12341212,negative #121212aa,positive

Parse a textfile and generate tokens to a file in Python

Hi All

find the program.

------------------------------------

import re

def ngram_gen(s, n):

    s = s.lower()

    s = re.sub(r'[^a-zA-Z0-9\s]', ' ', s)

    tokens = [token for token in s.split(" ") if token != ""]

    ngrams = zip(*[tokens[i:] for i in range(n)])

    return [" ".join(ngram) for ngram in ngrams]

fil=open("aaa.php", "r")

cou=fil.read()

am= ngram_gen(cou, n=1)

am

str1=''

for i in am:

  print (i)

  i=i.replace("\n","")

  i=i.replace("\t","")

  str1=str1+" "+i

print(str1)

f = open("hup.csv", "w")

f.write(str1)

f.close()

Canny Edge Detection in Python

Hi All,

See the code.
------------------------------------

import cv2
import numpy as np
from matplotlib import pyplot as plt
img = cv2.imread('tkm1.jpg',0)
edges = cv2.Canny(img,100,200)
plt.subplot(121),plt.imshow(img,cmap = 'gray')
plt.title('Original Image'), plt.xticks([]), plt.yticks([])
plt.subplot(122),plt.imshow(edges,cmap = 'gray')
plt.title('Edge Image'), plt.xticks([]), plt.yticks([])
plt.show()

n-gram implementation in Python using PDF file Operations

Hi All,
See the codes...
---------------------------------------------------------------------------------------------------------------------
# code to generte ngrams

import re
def ngram_gen(s, n):
    s = s.lower()
    s = re.sub(r'[^a-zA-Z0-9\s]', ' ', s)
    tokens = [token for token in s.split(" ") if token != ""]
    ngrams = zip(*[tokens[i:] for i in range(n)])
    return [" ".join(ngram) for ngram in ngrams]


------------------------------------------------------------------------------------------

# code to read from text file and generating ngrams

fil=open("hup.txt", "r")
cou=fil.read()
am= generate_ngrams(cou, n=3)
am


-------------------------------------------------------------------------------------------

# code to read from pdf file and generating ngrams

pip install PyPDF2
pip install textract
pip install nltk
import PyPDF2
pdfFileObj = open('new.pdf', 'rb')
pdfReader = PyPDF2.PdfFileReader(pdfFileObj)
print(pdfReader.numPages)
pageObj = pdfReader.getPage(0)
z=pageObj.extractText()
bm= generate_ngrams(z, n=5)
bm


--------------------------------------------------------------------------------------------

# code to count plagiarism and store in array

j=0
cnt=[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0]
for i in am:
  c=bm.count(i)
  c=c+bm1.count(i)
  print(i,c)
  cnt[j]=c
  j=j+1
print(cnt)
print(cnt)
a=cnt[0:34].count(0)
p=((j-a)/j*100)
if p>25:
  print("\nplagiarism detected!!\n plagiarism level:",round(p),"%")


---------------------------------------------------------------------------------------------

# code to combine all files and count plagiarism

import os, fnmatch
c1=""
listOfFiles = os.listdir('.')
pattern = "*.pdf"
for entry in listOfFiles:
    if fnmatch.fnmatch(entry, pattern):
            pdfFileObj = open(entry, 'rb')
            pdfReader = PyPDF2.PdfFileReader(pdfFileObj)
            print(pdfReader.numPages) 
            pageObj = pdfReader.getPage(0) 
            z1=pageObj.extractText()
            c1=c1+z1;
bm1= generate_ngrams(c1, n=5)
j=0
cnt=[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0]
for i in am:
  c=bm1.count(i)
  print(i,c)
  cnt[j]=c
  j=j+1
print(cnt)
a=cnt[0:34].count(0)
p=((j-a)/j*100)
if p>25:
  print("\nplagiarism detected!!\n plagiarism level:",round(p),"%")
           

--------------------------------------------------------------------------------------

Steps in Machine Learning

Hi All
Find the different steps in Machine Learning

---------------------------------
Train data

you are great,positive
its bad,negative
ok fine,neutral
-----------------------------------------------
Step1: Create Vocabulary

create a vocabulary=you are great its bad ok fine
--------------------------------------------------
Step 2; Training

1. create feature set

you:true are:true great:true its:false bad:false ok:false fine:false,positive

you:false are:false great:false its:true bad:true ok:false fine:false,negative

2. using feature set train the classifier(Naive bayes)

------------------------------------------------
Step3 :Testing
1. read the test data from console/csv/cloud/google drive
  it was fine
2. create featureset of test data

 you:false are:false great:false its:false bad:false ok:false fine:true



Testing

Remove stopwords in Python

Hi All,
See the code using set difference operation

--------------------------------
stopwords="is and it when which where to in have has "
testdata="it is bad and worst"
stoplist=stopwords.split()
testlist=testdata.split()
newtestlist=list(set(testlist)-set(stoplist))
print(newtestlist)
----------------------------------------

Classification in Python without Machine Learning

HI All,
See the code...

The input is trainingdata.csv  with the following content

high-temparature headache cough,fever
chest-pain high-pressure breathing-issue,heartattack
very-high-esr faint high-beta-count,cancer

-------------------------------------
import csv
list1=[]
class1=[]
stopwords="i am you we an in on where is are what which here"
slist=stopwords.split()
csvinput=open("trainingdata.csv","r")
reader=csv.reader(csvinput,delimiter=",")
for sym,label in reader:
  list1.append(sym)
  class1.append(label)
print(list1)
print(class1)
in1=input("Enter your symptoms")
inlist=in1.split()
newlist=list(set(inlist)-set(slist))
print(newlist)
j=0
for i in list1:
  #print(i)
  templist=i.split()
  commonlist=list(set(templist)&set(newlist))
  l1=len(commonlist)
  percentage=l1/len(templist)*100
  #print(templist)
  print(class1[j],percentage)
  j=j+1