def test_generate_d3_object(self):
assert generate_d3_object(
{'a': 1, 'b': 2, 'c': 3, 'd': 4},
"object", "word", "count") == {
'name': 'object', 'children': [{'word': 'a', 'count': 1},
{'word': 'b', 'count': 2},
{'word': 'c', 'count': 3},
{'word': 'd', 'count': 4}]}
def test_generate_d3_object(self):
assert generate_d3_object(
{'a': 1, 'b': 2, 'c': 3, 'd': 4},
"object", "word", "count") == {
'name': 'object', 'children': [{'word': 'a', 'count': 1},
{'word': 'b', 'count': 2},
{'word': 'c', 'count': 3},
{'word': 'd', 'count': 4}]}
def generate_d3_json_object(self, word_label: str,
count_label: str) -> object:
"""Generate a JSON object for d3 from the word counts of the file.
:param word_label: label to use for identifying words in the
sub-objects.
:param count_label: label to use for identifying counts in the
sub-objects.
:return: the resultant JSON object, formatted for d3.
"""
word_counts = self.get_word_counts()
return general_functions.generate_d3_object(word_counts, self.label,
word_label, count_label)
def generate_d3_json_object(self, word_label: str,
count_label: str) -> object:
""" Generates a JSON object for d3 from the word counts of the file.
:param word_label: label to use for identifying words in the
sub-objects.
:param count_label: label to use for identifying counts in the
sub-objects.
:return: the resultant JSON object, formatted for d3.
"""
word_counts = self.get_word_counts()
return general_functions.generate_d3_object(
word_counts, self.label, word_label, count_label)
def generate_json_for_d3(file_manager: FileManager, merged_set):
"""
Generates the data formatted nicely for the d3 visualization library.
Args:
merged_set: Boolean saying whether to merge all files into one data set
or, if false, create a list of datasets.
Returns:
An object, formatted in the JSON that d3 needs, either a list or a
dictionary.
"""
active_files = []
for l_file in list(file_manager.files.values()):
if l_file.active:
active_files.append(l_file)
if merged_set: # Create one JSON Object across all the chunks
minimum_length = int(request.form['minlength']) \
if 'minlength' in request.form else 0
master_word_counts = {}
for l_file in active_files:
word_counts = l_file.get_word_counts()
for key in word_counts:
if len(key) <= minimum_length:
continue
if key in master_word_counts:
master_word_counts[key] += word_counts[key]
else:
master_word_counts[key] = word_counts[key]
if 'maxwords' in request.form:
# Make sure there is a number in the input form
check_for_value = request.form['maxwords']
if check_for_value == "":
max_num_words = 100
else:
max_num_words = int(request.form['maxwords'])
sorted_word_counts = sorted(master_word_counts,
key=master_word_counts.__getitem__)
j = len(sorted_word_counts) - max_num_words
for i in range(len(sorted_word_counts) - 1, -1, -1):
if i < j:
del master_word_counts[sorted_word_counts[i]]
return_obj = general_functions.generate_d3_object(
master_word_counts,
object_label="tokens",
word_label="name",
count_label="size")
else: # Create a JSON object for each chunk
return_obj = []
for l_file in active_files:
return_obj.append(
l_file.generate_d3_json_object(word_label="text",
count_label="size"))
# NOTE: Objects in JSON are dictionaries in Python, but Lists are Arrays
# are Objects as well.
return return_obj