def keyword_neighbors(keyword):
keywords = iotools.load_keywords_dict()
keyword_weight = weighting_function(keyword)
related_datasets = set([x[0] for x in keywords['all'][keyword]])
ret = {}
for dataset in related_datasets:
dataset_keywords = iotools.load_dataset_keywords_dict(dataset)['all']
for keyword2 in dataset_keywords:
ret[keyword2] = ret.get(keyword2, 0) + 1
for keyword2, val in ret.items():
weight = 1.0 * weighting_function(keyword2) * mylog(val) / keyword_weight / mylog(len(related_datasets))
ret[keyword2] = weight
return sorted(ret.items(), key=lambda x: x[1], reverse=True)
def tag_cloud_text_new_keywords_simple():
ret = []
for dataset, keywords in iotools.load_dataset_keywords_dict().items():
ret += keywords['all'].keys()
return ret
def dataset_weighting_function(dataset):
keywords = iotools.load_dataset_keywords_dict(dataset['name'])['all']
keywords_weight = weight_keywords(keywords)
return sum([x[1] for x in keywords_weight])
def get_all_datasets_with_keywords():
categories = similarity.get_category_dict()
keywords = iotools.load_dataset_keywords_dict()
return render_template('datasets-with-keywords.html', dataset_dict=categories, keywords=keywords)
def df_new_keywords_list_weighted(dataset):
name = dataset['name']
keywords = iotools.load_dataset_keywords_dict(name)['all'].keys()
weights = [weighting_function(keyword) for keyword in keywords]
return dict(zip(keywords, weights))
def df_new_keywords_list(dataset):
name = dataset['name']
return iotools.load_dataset_keywords_dict(name)['all']
