def histogram(source_text):
word_list = word_frequency.get_words(source_text)
# count occurrence of strings:
word_data_struct = Linked_List()
for each_str in word_list:
# if each_str in word_dict:
each_node = word_data_struct.find_node_tuple(each_str)
if each_node is not None:
each_node.value = (each_node.value[0], each_node.value[1] + 1)
else:
# word_dict[each_str] = 1
new_value = (each_str, 1)
new_node = Node(new_value)
word_data_struct.unshift(new_node)
return word_data_struct
def histogram_tuples(source_text):
word_list = word_frequency.get_words(source_text)
word_list.sort()
tuple_arr = []
for idx, each_str in enumerate(word_list):
# search list for tuples with 0th element == each_str
existing_idx = None
for inner_idx, each_tuple in enumerate(tuple_arr):
if each_tuple[0] == each_str:
existing_idx = inner_idx
break
if existing_idx is not None:
old_tuple = tuple_arr[existing_idx]
new_tuple = (old_tuple[0], old_tuple[1] + 1)
tuple_arr[existing_idx] = new_tuple
else:
new_tuple = (each_str, 1)
tuple_arr.append(new_tuple)
return tuple_arr
def convert_histogram(): #text
# text_stuff = text.split()
# word_counts = word_frequency.histogram(text)
word_counts = word_frequency.histogram(word_frequency.get_words())
# print(word_counts)
return word_counts
