'@Tags': {
'$each': tags
}
}})
def tags_list_to_dict(user):
if '@Id' not in user or '@Tags' not in user:
return
tag_dict = {}
for tag in user['@Tags']:
if tag not in tag_dict:
tag_dict[tag] = 1
else:
tag_dict[tag] += 1
upd_handler.db.users.update({'@Id': user['@Id']},
{'$set': {
'@Tags': tag_dict
}})
# Iterate overall posts; append the post-tags to the owner user's prof
# for post in tqdm(db.get_post()):
# if '@OwnerUserId' in post and '@Tags' in post:
# append_tags(post['@OwnerUserId'], post['@Tags'])
# Iterate overall users; convert their list of tags to a freq-dist
for user in tqdm(list(db.get_user({'@Tags.1': {'$exists': True}}))):
tags_list_to_dict(user)
import matplotlib.pyplot as plt
from wordcloud import WordCloud
from dbm import DBM
dbm = DBM()
#Get all tags from all users
all_users = dbm.get_user(flt={'tags': {'$exists': 1}})
all_tags = ""
norm_tags = {}
for user in all_users:
for tag in user['tags']:
all_tags += tag['name'] + " "
if tag['name'] in norm_tags:
norm_tags[tag['name']] += tag['count']
else:
norm_tags[tag['name']] = tag['count']
print("Number of distinct tags:", len(norm_tags))
# Generate a non-normalized tag cloud image
wordcloud = WordCloud(width=700,
height=500,
stopwords=['n'],
normalize_plurals=False,
max_words=1000).generate(all_tags)
plt.imshow(wordcloud, interpolation='bilinear')
plt.axis("off")
plt.title("Non Normalized Tag-Cloud")
# Generate a Normalized tag cloud image