def save_characteristics_in_db(file_path, author_name, xml_file_path):
text = open(file_path, 'r').readlines()
# xml_tree = XmlParser(xml_file_path)
author_position_characteristics = {
"name": author_name,
"average_word_length": average_word_length(text),
"type_token_ratio": type_token_ratio(text),
"hapax_legomana_ratio": hapax_legomana_ratio(text),
"average_sentence_length": average_sentence_length(text),
"average_sentence_complexity": avg_sentence_complexity(text),
# "base_words": xml_tree.get_base_form_words(),
# "parts_of_speech_frequencies": xml_tree.get_parts_of_speech_frequency(),
# "words_count": xml_tree.get_number_of_words()
}
author_data = collection.find_one({"name": author_name})
if author_data:
print author_position_characteristics["words_count"]
old_positions_impact = author_data["words_count"] / float(
author_position_characteristics["words_count"] +
author_data["words_count"])
print old_positions_impact
new_position_impact = 1 - old_positions_impact
characteristics_to_recalculate = [
"average_word_length", "type_token_ratio", "hapax_legomana_ratio",
"average_sentence_length", "average_sentence_complexity"
]
recalculate_simple_characteristics_keeping_impact(
author_data, old_positions_impact, author_position_characteristics,
new_position_impact, characteristics_to_recalculate)
recalculate_morphological_characteristics_keeping_impact(
author_data, old_positions_impact, author_position_characteristics,
new_position_impact, "parts_of_speech_frequencies")
collection.find_one_and_replace({"name": author_name}, author_data)
else:
collection.insert_one(author_position_characteristics)
def save_characteristics_in_db(file_path, author_name, xml_file_path):
text = open(file_path, 'r').readlines()
# xml_tree = XmlParser(xml_file_path)
author_position_characteristics = {"name": author_name,
"average_word_length": average_word_length(text),
"type_token_ratio": type_token_ratio(text),
"hapax_legomana_ratio": hapax_legomana_ratio(text),
"average_sentence_length": average_sentence_length(text),
"average_sentence_complexity": avg_sentence_complexity(text),
# "base_words": xml_tree.get_base_form_words(),
# "parts_of_speech_frequencies": xml_tree.get_parts_of_speech_frequency(),
# "words_count": xml_tree.get_number_of_words()
}
author_data = collection.find_one({"name": author_name})
if author_data:
print author_position_characteristics["words_count"]
old_positions_impact = author_data["words_count"] / float(author_position_characteristics["words_count"] + author_data["words_count"])
print old_positions_impact
new_position_impact = 1 - old_positions_impact
characteristics_to_recalculate = ["average_word_length",
"type_token_ratio",
"hapax_legomana_ratio",
"average_sentence_length",
"average_sentence_complexity"]
recalculate_simple_characteristics_keeping_impact(author_data, old_positions_impact,
author_position_characteristics, new_position_impact,
characteristics_to_recalculate)
recalculate_morphological_characteristics_keeping_impact(author_data, old_positions_impact,
author_position_characteristics, new_position_impact,
"parts_of_speech_frequencies")
collection.find_one_and_replace({"name": author_name}, author_data)
else:
collection.insert_one(author_position_characteristics)
avg_sentence_complexity
def print_results_in_file(path, content):
print "Writing results to file results"
with open(path, "w") as result_file:
for result in content:
result_file.write("%s\n" % result)
def save_text_as_file(name, text):
file = open(name, "w")
file.write(text)
file.write("\n")
file.close()
if __name__ == '__main__':
text = open('./texts/toDetectFile', 'r').readlines()
resultFileContent = [
'average word length: ',
average_word_length(text), 'type token ratio: ',
type_token_ratio(text), 'hapax legomana ratio: ',
hapax_legomana_ratio(text), 'average sentence length: ',
average_sentence_length(text), 'average sentence complexity: ',
avg_sentence_complexity(text)
]
XmlParser.produce_xml_with_morphological_data('./numericalResults',
'./xmlResults/toDetect.xml')
xml_tree = XmlParser('./xmlResults/toDetect.xml')
from XmlParser import XmlParser
from textCharacteristics import average_word_length, type_token_ratio, hapax_legomana_ratio, average_sentence_length, \
avg_sentence_complexity
def print_results_in_file(path, content):
print "Writing results to file results"
with open(path, "w") as result_file:
for result in content:
result_file.write("%s\n" % result)
def save_text_as_file(name, text):
file = open(name, "w")
file.write(text)
file.write("\n")
file.close()
if __name__ == '__main__':
text = open('./texts/toDetectFile', 'r').readlines()
resultFileContent = ['average word length: ', average_word_length(text),
'type token ratio: ', type_token_ratio(text),
'hapax legomana ratio: ', hapax_legomana_ratio(text),
'average sentence length: ', average_sentence_length(text),
'average sentence complexity: ', avg_sentence_complexity(text)]
XmlParser.produce_xml_with_morphological_data('./numericalResults', './xmlResults/toDetect.xml')
xml_tree = XmlParser('./xmlResults/toDetect.xml')