def find_top_k_entities(tweets, entity_key, k):
'''
Find the K most frequently occuring entitites.
Inputs:
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_top_k(entity_list, k)
def find_top_k_ngrams_by_month(tweets, n, stop_words, stop_prefixes, k):
'''
Find the top k ngrams for each month.
Inputs:
tweets: list of tweet dictionaries
n: integer
stop_words: a set of strings to ignore
stop_prefixes: a set of strings. Words w/ a prefix that
appears in this list should be ignored.
k: integer
Returns: sorted list of pairs. Each pair has the form:
((year, month), (sorted top-k n-grams for that month with their counts))
'''
time_dict = {}
ltuple = []
for td in tweets:
year_month = grab_year_month(td['created_at'])
if year_month in time_dict:
time_dict[year_month].append(td)
else:
time_dict[year_month] = []
time_dict[year_month].append(td)
for date, t_list in time_dict.items():
b = ngram_helper(t_list, n, stop_words, stop_prefixes)
ltuple.append((date, find_top_k(b, k)))
list.sort(ltuple)
return ltuple
def find_top_k_entities(tweets, entity_key, value_key, k):
'''
Find the K most frequently occuring entitites
Inputs:
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_top_k(l, k)
def find_top_k_ngrams(tweets, n, k):
'''
Find k most frequently occurring n-grams
Inputs:
tweets: a list of tweets
n: integer
k: integer
Returns: list of ngram/value pairs
'''
final_list = pre_process_tweets(tweets, n)
return find_top_k(final_list, k)
def find_top_k_ngrams(tweets, n, k):
'''
Find k most frequently occurring n-grams.
Inputs:
tweets: a list of tweets
n: integer
k: integer
Returns: list of key/value pairs
'''
"""
Your code goes here
"""
return find_top_k(make_n_grams(tweets, n), k)
def find_top_k_ngrams(tweets, n, k):
'''
Find k most 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_top_k(big_ngram_array, k)
def find_top_k_ngrams(tweets, n, k):
'''
Find k most frequently occurring n-grams.
Inputs:
tweets: a list of tweets
n: integer
k: integer
Returns: list of key/value pairs
'''
#Your code goes here
top_k = find_ngrams(tweets, n)
a = find_top_k(top_k, k)
return a
def find_top_k_entities(tweets, entity_key, k):
'''
Find the K most frequently occuring entitites
Inputs:
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_top_k(entity_array, k)
def find_top_k_ngrams(tweets, n, stop_words, stop_prefixes, k):
'''
Find k most frequently occuring n-grams or if k < 0,
count occurrences of all 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: list of key/value pairs sorted in non-increasing order by
value.
'''
b = ngram_helper(tweets, n, stop_words, stop_prefixes)
return find_top_k(b, k)
def find_top_k_entities(tweets, entity_key, k):
'''
Find the K most frequently occurring entities.
Inputs:
tweets: a 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
"""
top_hashtags = hashtager(tweets, entity_key)
a = find_top_k(top_hashtags, k)
return a
def find_top_k_entities(tweets, entity_key, k):
'''
Find the K most frequently occurring entities.
Inputs:
tweets: a 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
input_entities_list = extract_entities_list(tweets, entity_key)
# (I put an an extra list assignment so it's easier for
# The grader to understand the logic. I could have just
# put that in return. Will do that in later tasks)
return find_top_k(input_entities_list, k)
>>>>>>> 772604324d9e6fbf8e76ecb03659b77d09955de0
def find_top_k_entities(tweets, entity_key, k):
'''
Find the K most frequently occuring entitites
Inputs:
tweets: a list of tweets
entity_key: a pair ("hashtags", "text"),
("user_mentions", "screen_name"), etc
k: integer
Returns: list of entity, count pairs
'''
<<<<<<< HEAD
good_tweets = clean_tweets(tweets, entity_key)
top_k = find_top_k(good_tweets,k)
return top_k
=======
# Your code for Task 2.1 goes here
# Replace None with appropriate value
return None
>>>>>>> 772604324d9e6fbf8e76ecb03659b77d09955de0
def find_min_count_entities(tweets, entity_key, min_count):
'''
<<<<<<< HEAD
Find the entitites that occur at least min_count times.
Inputs: