def find_clusters(self, method, n_clusters = NUM_OF_CLUSTERS):
self.method = method
if len(self.snippets) == 0:
print("Sorry. There is nothing to cluster. Firstly, search for something.")
return
if method.lower() == "stc":
self.clustering = SuffixTreeClustering(self.snippets)
elif method.lower() == "fca":
self.clustering = FCAClustering(self.snippets)
elif method.lower() == "ward":
self.clustering = HierarchicalClustering(self.snippets)
elif method.lower() == "k-means" or method.lower() == "kmeans":
self.clustering = kMeansClustering(self.snippets)
else:
print("Sorry, unknown clustering algorithm.")
return {}
self.clustering.find_clusters(n_clusters)
return self.get_clusters()
def find_clusters(self, method, n_clusters=NUM_OF_CLUSTERS):
self.method = method
if len(self.snippets) == 0:
print(
"Sorry. There is nothing to cluster. Firstly, search for something."
)
return
if method.lower() == "stc":
self.clustering = SuffixTreeClustering(self.snippets)
elif method.lower() == "fca":
self.clustering = FCAClustering(self.snippets)
elif method.lower() == "ward":
self.clustering = HierarchicalClustering(self.snippets)
elif method.lower() == "k-means" or method.lower() == "kmeans":
self.clustering = kMeansClustering(self.snippets)
else:
print("Sorry, unknown clustering algorithm.")
return {}
self.clustering.find_clusters(n_clusters)
return self.get_clusters()
class Newster:
def __init__(self, api_urls, api_keys, query = ''):
self.API_URLs = api_urls
self.API_KEYs = api_keys
self.snippets = []
self.sources = []
self.links = []
self.titles = []
if len(query) > 0:
result = search_articles(self.API_URLs, self.API_KEYs, query)
self.snippets = result['snippets']
self.sources = result['sources']
self.links = result['links']
self.titles = result['titles']
self.clustering = None # stores clustering object
def search(self, query):
if len(query) > 0:
self.snippets = search_articles(self.API_URLs, self.API_KEYs, query)
return self.snippets
def find_clusters(self, method, n_clusters = NUM_OF_CLUSTERS):
self.method = method
if len(self.snippets) == 0:
print("Sorry. There is nothing to cluster. Firstly, search for something.")
return
if method.lower() == "stc":
self.clustering = SuffixTreeClustering(self.snippets)
elif method.lower() == "fca":
self.clustering = FCAClustering(self.snippets)
elif method.lower() == "ward":
self.clustering = HierarchicalClustering(self.snippets)
elif method.lower() == "k-means" or method.lower() == "kmeans":
self.clustering = kMeansClustering(self.snippets)
else:
print("Sorry, unknown clustering algorithm.")
return {}
self.clustering.find_clusters(n_clusters)
return self.get_clusters()
def get_snippets(self):
return self.snippets
def get_links(self):
return self.links
def get_sources(self):
return self.sources
def get_titles(self):
return self.titles
def print_snippets(self):
for num, snippet in enumerate(self.snippets):
print("Snippet #%i: " % num, end = ' ')
print(snippet)
print("--------------------------------")
def print_links(self):
for num, link in enumerate(self.links):
print("URL for #%i: " % num, end = ' ')
print(link)
print("--------------------------------")
def print_sources(self):
for num, source in enumerate(self.sources):
print("Source for #%i: " % num, end = ' ')
print(source)
print("--------------------------------")
def print_titles(self):
for num, title in enumerate(self.titles):
print("Title for #%i: " % num, end = ' ')
print(title)
print("--------------------------------")
def print_search_results(self):
for item in range(len(self.snippets)):
print("Search result #%i" % item)
print("Title: ", end = '')
print(self.titles[item])
print("Snippet: ", end = '')
print(self.snippets[item])
print("URL: ", end = '')
print(self.links[item])
print("Source: ", end = '')
print(self.sources[item])
print('-------------------------------')
def get_clusters(self):
if self.clustering:
return self.clustering.get_clusters()
else:
return {}
def get_common_tags(self, num = 2):
return self.clustering.get_common_phrases(num)
def get_number_of_good_clusters(self):
if self.method == 'stc':
return self.clustering.get_number_of_good_clusters()
def print_clusters(self):
if self.clustering:
return self.clustering.print_clusters()
class Newster:
def __init__(self, api_urls, api_keys, query=''):
self.API_URLs = api_urls
self.API_KEYs = api_keys
self.snippets = []
self.sources = []
self.links = []
self.titles = []
if len(query) > 0:
result = search_articles(self.API_URLs, self.API_KEYs, query)
self.snippets = result['snippets']
self.sources = result['sources']
self.links = result['links']
self.titles = result['titles']
self.clustering = None # stores clustering object
def search(self, query):
if len(query) > 0:
self.snippets = search_articles(self.API_URLs, self.API_KEYs,
query)
return self.snippets
def find_clusters(self, method, n_clusters=NUM_OF_CLUSTERS):
self.method = method
if len(self.snippets) == 0:
print(
"Sorry. There is nothing to cluster. Firstly, search for something."
)
return
if method.lower() == "stc":
self.clustering = SuffixTreeClustering(self.snippets)
elif method.lower() == "fca":
self.clustering = FCAClustering(self.snippets)
elif method.lower() == "ward":
self.clustering = HierarchicalClustering(self.snippets)
elif method.lower() == "k-means" or method.lower() == "kmeans":
self.clustering = kMeansClustering(self.snippets)
else:
print("Sorry, unknown clustering algorithm.")
return {}
self.clustering.find_clusters(n_clusters)
return self.get_clusters()
def get_snippets(self):
return self.snippets
def get_links(self):
return self.links
def get_sources(self):
return self.sources
def get_titles(self):
return self.titles
def print_snippets(self):
for num, snippet in enumerate(self.snippets):
print("Snippet #%i: " % num, end=' ')
print(snippet)
print("--------------------------------")
def print_links(self):
for num, link in enumerate(self.links):
print("URL for #%i: " % num, end=' ')
print(link)
print("--------------------------------")
def print_sources(self):
for num, source in enumerate(self.sources):
print("Source for #%i: " % num, end=' ')
print(source)
print("--------------------------------")
def print_titles(self):
for num, title in enumerate(self.titles):
print("Title for #%i: " % num, end=' ')
print(title)
print("--------------------------------")
def print_search_results(self):
for item in range(len(self.snippets)):
print("Search result #%i" % item)
print("Title: ", end='')
print(self.titles[item])
print("Snippet: ", end='')
print(self.snippets[item])
print("URL: ", end='')
print(self.links[item])
print("Source: ", end='')
print(self.sources[item])
print('-------------------------------')
def get_clusters(self):
if self.clustering:
return self.clustering.get_clusters()
else:
return {}
def get_common_tags(self, num=2):
return self.clustering.get_common_phrases(num)
def get_number_of_good_clusters(self):
if self.method == 'stc':
return self.clustering.get_number_of_good_clusters()
def print_clusters(self):
if self.clustering:
return self.clustering.print_clusters()
