from sklearn.feature_extraction.text import CountVectorizer
from sklearn.feature_extraction.text import TfidfTransformer
from nltk.corpus import stopwords
import numpy as np
import numpy.linalg as LA

train_set = ["The sky is blue.", "The sun is bright."]  # Documents
test_set = ["The sun in the sky is bright."]  # Query
stopWords = stopwords.words('english')

vectorizer = CountVectorizer(stop_words = stopWords)
#print vectorizer
transformer = TfidfTransformer()
#print transformer

trainVectorizerArray = vectorizer.fit_transform(train_set).toarray()
testVectorizerArray = vectorizer.transform(test_set).toarray()
print 'Fit Vectorizer to train set', trainVectorizerArray
print 'Transform Vectorizer to test set', testVectorizerArray

transformer.fit(trainVectorizerArray)
print
print transformer.transform(trainVectorizerArray).toarray()

transformer.fit(testVectorizerArray)
print
tfidf = transformer.transform(testVectorizerArray)
print tfidf.todense()

Fit Vectorizer to train set [[1 0 1 0]
 [0 1 0 1]]
Transform Vectorizer to test set [[0 1 1 1]]

[[ 0.70710678  0.          0.70710678  0.        ]
 [ 0.          0.70710678  0.          0.70710678]]

[[ 0.          0.57735027  0.57735027  0.57735027]]

>>> from sklearn.feature_extraction.text import TfidfVectorizer
>>> from sklearn.datasets import fetch_20newsgroups
>>> twenty = fetch_20newsgroups()

>>> tfidf = TfidfVectorizer().fit_transform(twenty.data)
>>> tfidf
<11314x130088 sparse matrix of type '<type 'numpy.float64'>'
    with 1787553 stored elements in Compressed Sparse Row format>

>>> tfidf[0:1]
<1x130088 sparse matrix of type '<type 'numpy.float64'>'
    with 89 stored elements in Compressed Sparse Row format>

>>> from sklearn.metrics.pairwise import linear_kernel
>>> cosine_similarities = linear_kernel(tfidf[0:1], tfidf).flatten()
>>> cosine_similarities
array([ 1.        ,  0.04405952,  0.11016969, ...,  0.04433602,
    0.04457106,  0.03293218])

>>> related_docs_indices = cosine_similarities.argsort()[:-5:-1]
>>> related_docs_indices
array([    0,   958, 10576,  3277])
>>> cosine_similarities[related_docs_indices]
array([ 1.        ,  0.54967926,  0.32902194,  0.2825788 ])

>>> print twenty.data[0]
From: lerxst@wam.umd.edu (where's my thing)
Subject: WHAT car is this!?
Nntp-Posting-Host: rac3.wam.umd.edu
Organization: University of Maryland, College Park
Lines: 15

 I was wondering if anyone out there could enlighten me on this car I saw
the other day. It was a 2-door sports car, looked to be from the late 60s/
early 70s. It was called a Bricklin. The doors were really small. In addition,
the front bumper was separate from the rest of the body. This is
all I know. If anyone can tellme a model name, engine specs, years
of production, where this car is made, history, or whatever info you
have on this funky looking car, please e-mail.

Thanks,
- IL
   ---- brought to you by your neighborhood Lerxst ----

>>> print twenty.data[958]
From: rseymour@reed.edu (Robert Seymour)
Subject: Re: WHAT car is this!?
Article-I.D.: reed.1993Apr21.032905.29286
Reply-To: rseymour@reed.edu
Organization: Reed College, Portland, OR
Lines: 26

In article <1993Apr20.174246.14375@wam.umd.edu> lerxst@wam.umd.edu (where's my
thing) writes:
>
>  I was wondering if anyone out there could enlighten me on this car I saw
> the other day. It was a 2-door sports car, looked to be from the late 60s/
> early 70s. It was called a Bricklin. The doors were really small. In
addition,
> the front bumper was separate from the rest of the body. This is
> all I know. If anyone can tellme a model name, engine specs, years
> of production, where this car is made, history, or whatever info you
> have on this funky looking car, please e-mail.

Bricklins were manufactured in the 70s with engines from Ford. They are rather
odd looking with the encased front bumper. There aren't a lot of them around,
but Hemmings (Motor News) ususally has ten or so listed. Basically, they are a
performance Ford with new styling slapped on top.

>    ---- brought to you by your neighborhood Lerxst ----

Rush fan?

--
Robert Seymour              rseymour@reed.edu
Physics and Philosophy, Reed College    (NeXTmail accepted)
Artificial Life Project         Reed College
Reed Solar Energy Project (SolTrain)    Portland, OR

from sklearn.feature_extraction.text import CountVectorizer
from sklearn.metrics.pairwise import cosine_similarity
from sklearn.feature_extraction.text import TfidfVectorizer

f = open("/root/Myfolder/scoringDocuments/doc1")
doc1 = str.decode(f.read(), "UTF-8", "ignore")
f = open("/root/Myfolder/scoringDocuments/doc2")
doc2 = str.decode(f.read(), "UTF-8", "ignore")
f = open("/root/Myfolder/scoringDocuments/doc3")
doc3 = str.decode(f.read(), "UTF-8", "ignore")

train_set = ["president of India",doc1, doc2, doc3]

tfidf_vectorizer = TfidfVectorizer()
tfidf_matrix_train = tfidf_vectorizer.fit_transform(train_set)  #finds the tfidf score with normalization
print "cosine scores ==> ",cosine_similarity(tfidf_matrix_train[0:1], tfidf_matrix_train)  #here the first element of tfidf_matrix_train is matched with other three elements

[[ 1.          0.07102631  0.02731343  0.06348799]]

cosine_function = lambda a, b : round(np.inner(a, b)/(LA.norm(a)*LA.norm(b)), 3)

from sklearn.feature_extraction.text import CountVectorizer
from sklearn.feature_extraction.text import TfidfTransformer
from nltk.corpus import stopwords
import numpy as np
import numpy.linalg as LA

train_set = ["The sky is blue.", "The sun is bright."] #Documents
test_set = ["The sun in the sky is bright."] #Query
stopWords = stopwords.words('english')

vectorizer = CountVectorizer(stop_words = stopWords)
#print vectorizer
transformer = TfidfTransformer()
#print transformer

trainVectorizerArray = vectorizer.fit_transform(train_set).toarray()
testVectorizerArray = vectorizer.transform(test_set).toarray()
print 'Fit Vectorizer to train set', trainVectorizerArray
print 'Transform Vectorizer to test set', testVectorizerArray
cx = lambda a, b : round(np.inner(a, b)/(LA.norm(a)*LA.norm(b)), 3)

for vector in trainVectorizerArray:
    print vector
    for testV in testVectorizerArray:
        print testV
        cosine = cx(vector, testV)
        print cosine

transformer.fit(trainVectorizerArray)
print
print transformer.transform(trainVectorizerArray).toarray()

transformer.fit(testVectorizerArray)
print
tfidf = transformer.transform(testVectorizerArray)
print tfidf.todense()

Fit Vectorizer to train set [[1 0 1 0]
 [0 1 0 1]]
Transform Vectorizer to test set [[0 1 1 1]]
[1 0 1 0]
[0 1 1 1]
0.408
[0 1 0 1]
[0 1 1 1]
0.816

[[ 0.70710678  0.          0.70710678  0.        ]
 [ 0.          0.70710678  0.          0.70710678]]

[[ 0.          0.57735027  0.57735027  0.57735027]]

from nltk.corpus import stopwords
import string
from nltk.tokenize import wordpunct_tokenize as tokenize
from nltk.stem.porter import PorterStemmer
from sklearn.feature_extraction.text import TfidfVectorizer
from scipy.spatial.distance import cosine

porter = PorterStemmer()
stop_words = set(stopwords.words('english'))

modified_arr = [[porter.stem(i.lower()) for i in tokenize(d.translate(None, string.punctuation)) if i.lower() not in stop_words] for d in documents]

modified_doc = [' '.join(i) for i in modified_arr] # this is only to convert our list of lists to list of strings that vectorizer uses.
tf_idf = TfidfVectorizer().fit_transform(modified_doc)

l = len(documents) - 1
for i in xrange(l):
    minimum = (1, None)
    minimum = min((cosine(tf_idf[i].todense(), tf_idf[l + 1].todense()), i), minimum)
print minimum

from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import cosine_similarity

tfidf_vectorizer = TfidfVectorizer()
tfidf_matrix = tfidf_vectorizer.fit_transform(train_set)
print tfidf_matrix
cosine = cosine_similarity(tfidf_matrix[length-1], tfidf_matrix)
print cosine

[[ 0.34949812  0.81649658  1.        ]]