def __init__(self):
self.nlp = NLP()
self.txt_utils = TextUtils()
self.usr_words = {} # to temporary store users with tagged words
self.users = {}
self.result = None
class TweetAnalyser(BaseAnalyser):
def __init__(self):
self.nlp = NLP()
self.txt_utils = TextUtils()
self.usr_words = {} # to temporary store users with tagged words
self.users = {}
self.result = None
def add_users(self, users):
for u in users:
# store tagged tweets of the current user
if u.tweets:
self.users[u.id] = u.screen_name
self.usr_words[u.id] = self.get_tagged_words(u.tweets, ['N'])
def get_tagged_words(self, tweets, tags):
""" Return a list of all the tagged words of tweets
tweets: list of TwitterMessage objects
[TwitterMessage, TwitterMessage]
tags : list with tag that must be filtered on
['N', 'V']
"""
words = []
for tweet in tweets:
tagged_tweet = self.tag_tweet(tweet)
if tagged_tweet:
for tagged_word in tagged_tweet:
if tagged_word[1] in tags:
words.append(tagged_word)
return words
def tag_tweet(self, tweet):
if self.nlp.detect_language(tweet.text):
return self.nlp.tag(self.txt_utils.tokenize(tweet.text), self.nlp.detect_language(tweet.text))
return None
def analyse(self):
word_count = {}
word_users = {} # contains a list of tuples (usr, timesused)
data = {}
# Build word_count and word_users
data['message'] = "Building word_count and word_users"
self.notifyAll(data)
for u_id in self.usr_words:
word_fd = nltk.FreqDist(word for (word, tag) in self.usr_words[u_id])
for word in word_fd:
if word_count.has_key(word):
word_count[word] += word_fd[word]
word_users[word].append((u_id, word_fd[word]))
else:
word_count[word] = word_fd[word]
word_users[word] = [(u_id, word_fd[word])]
data['message'] = "Filtering word_count and word_users on the times a word is used by a user in comparison with the other users of this word."
self.notifyAll(data)
# Filter the users of a word on the times a word is used
for word in word_count:
avg_usg = word_count[word]/float(len(word_users[word]))
lower_limit = avg_usg - 0.25 * avg_usg
for i, user in enumerate(word_users[word]):
if user[1] < lower_limit:
word_count[word] -= user[1]
clusters = []
words = word_count.keys()
data['message'] = "Comparing word users and clusters words and users if the group of users of both word match enough with each other."
self.notifyAll(data)
# Compare word_users and if they are similar combine to a clusters
for i in range(len(words)):
cluster_words = [words[i]]
cluster_users = []
users_a = [user[0] for user in word_users[words[i]]]
cluster_users.extend(users_a)
# Now compare the users of word[i] with the users of all other words
for j in range((i+1), len(words)):
users_b = [user[0] for user in word_users[words[j]]]
intersect_len = len(set(users_a).intersection(set(users_b)))
# Check if user groups of two words are very similar
if intersect_len < 0.75 * len(users_a) or intersect_len < 0.75 * len(users_b):
continue
# They are very similar
cluster_words.append(words[j])
cluster_users = set(cluster_users).union(users_b)
# We don't want clusters with one word, and especially not clusters with one user.
if len(cluster_users) == 1 or len(cluster_words) == 1:
continue
# Check if the cluster is not a subcluster (of words) of a previous cluster. Then we can skip the subcluster
in_previous_cluster = False
for cluster in clusters:
if len(set(cluster_words)) == len(set(cluster[0]).intersection(set(cluster_words))):
in_previous_cluster = True
break
if in_previous_cluster:
continue
# Everything ok, so replace user ids with screennames in result
screennames = []
for user in cluster_users:
screennames.append("@" + self.users[user])
# Save found cluster
data['message'] = self.cluster_to_string((cluster_words, screennames))
self.notifyAll(data)
clusters.append((cluster_words, screennames))
# Sort by users per cluster
sorted_clusters = sorted(clusters, cmp=lambda x,y: cmp(len(x[1]), len(y[1])), reverse=True)
self.result = sorted_clusters
return sorted_clusters
def cluster_to_string(self, cluster):
r = ""
for word in cluster[0]:
r+= " " + word
r+="\n"
for username in cluster[1]:
r += " " + str(username)
r+="\n"
return r
def result_to_string(self):
"""Returns a printable version of the results"""
r = ""
for cluster in self.result:
r += self.cluster_to_string(cluster) + "\n"
return r
