def buscaCorreo2(x):
documents = []
documap = {}
for archivo in os.listdir("Correos"):
if archivo.endswith(".txt"):
f = open("Correos/" + archivo, "r")
f.readline()
f.readline()
f.readline()
f.readline()
mailbody = f.read()
f.close()
docu = Document(mailbody, name=archivo)
documents.append(docu)
docukey = int(archivo[0:-4])
documap[docukey] = docu
model = Model(documents=documents, weight=TFIDF)
docu = documap[int(var.get())]
tupla = model.neighbors(docu, top=1)[0]
tkMessageBox.showinfo("Tk", "El documento que mas se parece es el " + tupla[1].name[0:-4] + ", con un " + str(tupla[0]) + " de similitud")
# For text, a better metric than Euclidean distance
# is called cosine similarity. This is what a Model uses:
d1 = m.document(name="lion")
d2 = m.document(name="tiger")
d3 = m.document(name="dolphin")
d4 = m.document(name="shark")
d5 = m.document(name="parakeet")
print "lion-tiger:", m.similarity(d1, d2)
print "lion-dolphin:", m.similarity(d1, d3)
print "dolphin-shark:", m.similarity(d3, d4)
print "dolphin-parakeet:", m.similarity(d3, d5)
print
print "Related to tiger:"
print m.neighbors(d2, top=3) # Top three most similar.
print
print "Related to a search query ('water'):"
print m.search("water", top=10)
# In summary:
# A Document:
# - takes a string of text,
# - counts the words in the text,
# - constructs a vector of words (features) and normalized word count (weight).
# A Model:
# - groups multiple vectors in a matrix,
# - tweaks the weight with TF-IDF to find "unique" words in each document,
# For text, a better metric than Euclidean distance
# is called cosine similarity. This is what a Model uses:
d1 = m.document(name="lion")
d2 = m.document(name="tiger")
d3 = m.document(name="dolphin")
d4 = m.document(name="shark")
d5 = m.document(name="parakeet")
print("lion-tiger:", m.similarity(d1, d2))
print("lion-dolphin:", m.similarity(d1, d3))
print("dolphin-shark:", m.similarity(d3, d4))
print("dolphin-parakeet:", m.similarity(d3, d5))
print()
print("Related to tiger:")
print(m.neighbors(d2, top=3)) # Top three most similar.
print()
print("Related to a search query ('water'):")
print(m.search("water", top=10))
# In summary:
# A Document:
# - takes a string of text,
# - counts the words in the text,
# - constructs a vector of words (features) and normalized word count (weight).
# A Model:
# - groups multiple vectors in a matrix,
# - tweaks the weight with TF-IDF to find "unique" words in each document,
from pattern.vector import Document, Model, IG, TF, TFIDF, BINARY
import sys
import os
print "Reading sample code and instantiating documents..."
documents = []
exampleDir = "examples/"
for file in os.listdir(exampleDir):
if os.path.isdir(exampleDir + file):
for subfile in os.listdir(exampleDir + file):
if (os.path.isfile(exampleDir + file + "/" + subfile)):
with open (exampleDir + file + "/" + subfile, "r") as langDoc:
text = langDoc.read()
doc = Document(text, type=file)
documents.append(doc)
print "Creating statistical model..."
m = Model(documents=documents, weight=IG)
# Test with sample Java doc
print "Comparing test document..."
with open ("coffee.txt", "r") as myfile:
testFile = myfile.read()
testDoc = Document(testFile, type='Java')
testSimilarities = m.neighbors(testDoc, top=10)
prediction = testSimilarities[0][1].type #neighbors() returns (similarity, document) list
confidence = testSimilarities[0][0]
print "LanguageLearn has predicted " + testSimilarities[0][1].type + " with a " + str(round(confidence * 100, 2)) + "% confidence"
def recommend_game(this_game):
games = recommendable_games(this_game)
total_recommendable = games.count()
print 'Total recommendable games based on ' + this_game.title + ": " + total_recommendable.__str__()
document_title = Document(this_game.title)
document_publisher = Document(this_game.publisher)
document_summary = Document(this_game.summary,
top=None,
threshold=0,
stemmer=None,
exclude=[],
stopwords=False,
language='en')
document_keywords = Document(', '.join([x['name'] for x in this_game.keywords.all().values("name")]))
document_genres = Document(', '.join([x['name'] for x in this_game.genres.all().values("name")]))
# format: {"id":id, socre:"SUM(dist*pond)"}
game_similarities = []
summary_documents = []
for game in games:
score = 0
game = Game.objects.filter(title=game['title'], platform=game['platform'])[0]
title_similarity = 1 - distance(document_title.vector, Document(game.title).vector)
publisher_similarity = 1 - distance(document_publisher.vector, Document(game.publisher).vector)
genre_similarity = 1 - distance(document_genres.vector, Document(
', '.join([x['name'] for x in game.genres.all().values("name")])
).vector)
keywords_similarity = 1 - distance(document_keywords.vector, Document(
', '.join([x['name'] for x in game.keywords.all().values("name")])
).vector)
score = (0.15 * title_similarity) + (0.2 * genre_similarity) + (0.2 * publisher_similarity) + (
0.20 * keywords_similarity)
summary_documents.append(Document(game.summary,
top=None,
threshold=0,
stemmer=None,
exclude=[],
stopwords=False,
language='en',
name=game.id))
game_similarities.append({"id": game.id, "score": score})
to_compare = Document(document_summary)
model = Model(documents=summary_documents, weight=TFIDF)
neighbours = model.neighbors(to_compare, top=total_recommendable)
for neighbour in neighbours:
for rec_game in game_similarities:
if rec_game['id'] == neighbour[1].name:
rec_game['score'] = rec_game['score'] + 0.25 * neighbour[0]
recommended = sorted(game_similarities, key=lambda k: -k['score'])[0:total_recommendable]
if len(recommended) >= 40:
random_selection = random.sample(recommended[0:40], 25)
else:
random_selection = random.sample(recommended, 25)
recommended_ids = [g['id'] for g in random_selection]
return recommended_ids
