def prototype_test(self, text, expected):
call = 'author_functions.avg_word_length({})'.format(text)
returned = af.avg_word_length(text)
msg = TestAverageWordLength.failure_message.format(call, expected,
returned)
#self.assertEqual(returned, expected, msg)
#Use next line if we want to allow some error margin
self.assertTrue(self.approx(returned, expected), msg)
# We assume there is a minimum of one file.
files = os.listdir(dir_name)
# ####################################################################
# The following code parses the mystery file and calculates its
# linguistic signature.
# ####################################################################
mystery_file = open(mystery_filename, 'r')
# readlines() gives us a list of strings, one for each line of the file
text = mystery_file.readlines()
mystery_file.close()
# Calculate the signature for the mystery file
mystery_signature = [mystery_filename]
mystery_signature.append(author_functions.avg_word_length(text))
mystery_signature.append(author_functions.type_token_ratio(text))
mystery_signature.append(author_functions.hapax_legomena_ratio(text))
mystery_signature.append(author_functions.avg_sentence_length(text))
mystery_signature.append(author_functions.avg_sentence_complexity(text))
# ####################################################
# The following code reads the linguistic signatures,
# compares them with the mystery_signature,
# and reports the author that was the best match.
# ####################################################
# Weights of linguistic features.
weights = [0, 11, 33, 50, 0.4, 4]
# We assume there is at least one signature in the dir_name directory
""" (float, float) -> bool
Return True iff v1 and v2 are approximately equal.
"""
return v1-0.0001 < v2 < v1+0.0001
# Test avg_word_length.
text = [
"James Fennimore Cooper\n",
"Peter, Paul, and Mary\n",
]
error_message = "average_word_length on the text:\n\n" + repr(text) + \
"\n\n should return 5.142857142857143"
assert approx(author_functions.avg_word_length(text), 5.142857142857143),\
error_message
# Test type_token_ratio.
text = [
"James Fennimore Cooper\n",
"Peter, Paul, and Mary\n",
"James Gosling\n"
]
error_message = "type_token_ratio on the text:\n\n" + repr(text) + \
"\n\n should return 0.8888888888888888"
assert approx(author_functions.type_token_ratio(text), 0.8888888888888888),\
error_message
# We assume there is a minimum of one file.
files = os.listdir(dir_name)
# ####################################################################
# The following code parses the mystery file and calculates its
# linguistic signature.
# ####################################################################
mystery_file = open(mystery_filename, 'r')
# readlines() gives us a list of strings, one for each line of the file
text = mystery_file.readlines()
mystery_file.close()
# Calculate the signature for the mystery file
mystery_signature = [mystery_filename]
mystery_signature.append(author_functions.avg_word_length(text))
mystery_signature.append(author_functions.type_token_ratio(text))
mystery_signature.append(author_functions.hapax_legomena_ratio(text))
mystery_signature.append(author_functions.avg_sentence_length(text))
mystery_signature.append(author_functions.avg_sentence_complexity(text))
# ####################################################
# The following code reads the linguistic signatures,
# compares them with the mystery_signature,
# and reports the author that was the best match.
# ####################################################
# Weights of linguistic features.
weights = [0, 11, 33, 50, 0.4, 4]
# We assume there is at least one signature in the dir_name directory
