def find_frequent_entities(tweets, entity_key, k):
'''
Find entities where the number of times the specific entity occurs
is at least fraction * the number of entities in across the tweets.
Input:
tweets: a list of tweets
entity_key: a pair ("hashtags", "text"),
("user_mentions", "screen_name"), etc
k: integer
Returns: list of entity, count pairs
'''
z1, z2 = entity_key
c = []
l = range(len(tweets))
for i in l:
a = tweets[i]['entities'][z1]
range_a = range(len(a))
for j in range_a:
b = a[j]
c.append(b[z2])
entity_list = [d.lower() for d in c]
return find_frequent(entity_list, k)
def find_frequent_entities(tweets, entity_key, value_key, k):
'''
Find entities where the number of times the specific entity occurs
is at least fraction * the number of entities in across the tweets.
Input:
tweets: a list of tweets
entity_key: a string ("hashtags", "user_mentions", etc)
value_key: string (appropriate value depends on the entity type)
k: integer
Returns: list of entity, count pairs sorted in non-decreasing order by count.
'''
l = helper_1_to_3(tweets, entity_key, value_key)
return find_frequent(l, k)
def find_frequent_ngrams(tweets, n, k):
'''
Find the most frequently-occurring n-grams.
Inputs:
tweets: a list of tweets
n: integer
k: integer
Returns: list of ngram/value pairs
'''
"""
Your code goes here
"""
return find_frequent(make_n_grams(tweets, n), k)
def find_frequent_ngrams(tweets, n, k):
'''
Find frequently occurring n-grams
Inputs:
tweets: a list of tweets
n: integer
k: integer
Variables:
big_ngram_array: list of tuples called ngrams
Returns: list of ngram/value pairs
'''
big_ngram_array = make_big_ngram_array(tweets, n)
return find_frequent(big_ngram_array, k)
def find_frequent_ngrams(tweets, n, stop_words, stop_prefixes, k):
'''
Find frequently occuring n-grams
Inputs:
tweets: a list of tweets
n: integer
k: integer
stop_words: a set of strigns to ignore
stop_prefixes: a set of strings. Words w/a prefix that appears
in this list should be ignored.
Returns: sorted list of pairs. Each pair has the form:
((year, month)), (sorted top-k n-grams for that month with their counts))
'''
b = ngram_helper(tweets, n, stop_words, stop_prefixes)
return find_frequent(b, k)
def find_frequent_entities(tweets, entity_key, k):
'''
Find entities where the number of times the specific entity occurs
is at least fraction * the number of entities in across the tweets.
Input:
tweets: a list of tweets
entity_key: a pair ("hashtags", "text"),
("user_mentions", "screen_name"), etc
k: integer
Variables:
entity_array = holds all the hastags or screen_names
Returns: list of entity, count pairs
'''
entity_array = make_entity_array(tweets, entity_key)
return find_frequent(entity_array, k)
def find_frequent_entities(tweets, entity_key, k):
'''
Find entities where the number of times the specific entity occurs
is at least 1/k * the number of entities in across the tweets.
Input:
tweets: list of tweets
entity_key: a pair ("hashtags", "text"),
("user_mentions", "screen_name"), etc.
k: integer
Returns: list of entity, count pairs
'''
"""
Your code goes here
"""
# Extract the list of desired entities/ key and subkey
return find_frequent(extract_entities_list(tweets, entity_key), k)
def find_frequent_entities(tweets, entity_key, k):
'''
Find entities where the number of times the specific entity occurs
is at least 1/k * the number of entities in across the tweets.
Input:
tweets: list of tweets
entity_key: a pair ("hashtags", "text"),
("user_mentions", "screen_name"), etc.
k: integer
Returns: list of entity, count pairs
'''
"""
Your code goes here
"""
lst = hashtager(tweets, entity_key)
a = find_frequent(lst, k)
return a