def subject_vs_object_pronoun_freqs(corp):
'''
Takes in a Corpus of novels
Returns a tuple of two dictionaries, one male and female
Each dictionary maps each Novel in the corpus to the proportion of the pronouns
of the specified gender in that novel that are subject pronouns
#TODO: add doctests
:param corp: Corpus
:return: tuple of two dictionaries (male, female)
>>> subject_vs_object_pronoun_freqs(Corpus('test_corpus'))
({<Novel (aanrud_longfrock)>: 0.793233082706767, <Novel (abbott_flatlandromance)>: 0.6741573033707865, <Novel (abbott_indiscreetletter)>: 0.7906976744186047, <Novel (adams_fighting)>: 0.7184527584020292, <Novel (alcott_josboys)>: 0.6330049261083744, <Novel (alcott_littlemen)>: 0.6451612903225807, <Novel (alcott_littlewomen)>: 0.6577563540753725, <Novel (alden_chautauqua)>: 0.7577030812324931, <Novel (austen_emma)>: 0.7086120401337792, <Novel (austen_persuasion)>: 0.6739130434782609}, {<Novel (aanrud_longfrock)>: 0.5376532399299474, <Novel (abbott_flatlandromance)>: 0.17543859649122806, <Novel (abbott_indiscreetletter)>: 0.4424242424242424, <Novel (adams_fighting)>: 0.43485915492957744, <Novel (alcott_josboys)>: 0.3862487360970678, <Novel (alcott_littlemen)>: 0.4343501326259947, <Novel (alcott_littlewomen)>: 0.4124569980083288, <Novel (alden_chautauqua)>: 0.5461432506887053, <Novel (austen_emma)>: 0.4836730221345606, <Novel (austen_persuasion)>: 0.4872013651877133})
'''
try:
if (not corp.load_test_corpus):
relative_freq_male_sub_v_ob = common.load_pickle(
f'{corp.corpus_name}_sub_v_ob_pronoun_freq_male')
relative_freq_female_sub_v_ob = common.load_pickle(
f'{corp.corpus_name}_sub_v_ob_pronoun_freq_female')
return (relative_freq_male_sub_v_ob, relative_freq_female_sub_v_ob)
except IOError:
pass
relative_freq_male_subject = {}
relative_freq_female_subject = {}
relative_freq_male_object = {}
relative_freq_female_object = {}
for book in corp.novels:
he = book.get_word_freq('he')
him = book.get_word_freq('him')
she = book.get_word_freq('she')
her = book.get_word_freq('her')
temp_dict_male = {'subject': he, 'object': him}
temp_dict_female = {'subject': she, 'object': her}
temp_dict_male = get_comparative_word_freq(temp_dict_male)
temp_dict_female = get_comparative_word_freq(temp_dict_female)
relative_freq_male_subject[book] = temp_dict_male['subject']
relative_freq_female_subject[book] = temp_dict_female['subject']
relative_freq_male_object[book] = temp_dict_male['object']
relative_freq_female_object[book] = temp_dict_female['object']
book.text = ''
book._word_counts_counter = None
if (not corp.load_test_corpus):
common.store_pickle(relative_freq_male_subject,
f'{corp.corpus_name}_sub_v_ob_pronoun_freq_male')
common.store_pickle(relative_freq_female_subject,
f'{corp.corpus_name}_sub_v_ob_pronoun_freq_female')
result_tuple = (relative_freq_male_subject, relative_freq_female_subject)
return result_tuple
def books_pronoun_freq(corp):
#TODO: add doctests
'''
Counts male and female pronouns for every book and finds their relative frequencies per book
Outputs dictionary mapping novel object to the relative frequency
of female pronouns in that book
:param: Corpus object
:return: dictionary with data organized by groups
'''
relative_freq_male = {}
relative_freq_female = {}
for book in corp.novels:
he = book.get_word_freq('he')
him = book.get_word_freq('him')
his = book.get_word_freq('his')
male = he + him + his
she = book.get_word_freq('she')
her = book.get_word_freq('her')
hers = book.get_word_freq('hers')
female = she + her + hers
temp_dict = {'male': male, 'female': female}
temp_dict = get_comparative_word_freq(temp_dict)
relative_freq_male[book] = temp_dict['male']
relative_freq_female[book] = temp_dict['female']
return (relative_freq_female)
def subject_vs_object_pronoun_freqs(corp):
'''
Takes in a Corpus of novels
Returns a tuple of two dictionaries, one male and female
Each dictionary maps each Novel in the corpus to the proportion of the pronouns
of the specified gender in that novel that are subject pronouns
#TODO: add doctests
:param corp: Corpus
:return: tuple of two dictionaries (male, female)
'''
relative_freq_male_subject = {}
relative_freq_female_subject = {}
relative_freq_male_object = {}
relative_freq_female_object = {}
for book in corp.novels:
he = book.get_word_freq('he')
him = book.get_word_freq('him')
she = book.get_word_freq('she')
her = book.get_word_freq('her')
temp_dict_male = {'subject': he, 'object': him}
temp_dict_female = {'subject': she, 'object': her}
temp_dict_male = get_comparative_word_freq(temp_dict_male)
temp_dict_female = get_comparative_word_freq(temp_dict_female)
relative_freq_male_subject[book] = temp_dict_male['subject']
relative_freq_female_subject[book] = temp_dict_female['subject']
relative_freq_male_object[book] = temp_dict_male['object']
relative_freq_female_object[book] = temp_dict_female['object']
result_tuple = (relative_freq_male_subject,
relative_freq_female_subject)
return result_tuple
def books_pronoun_freq(corp):
'''
Counts male and female pronouns for every book and finds their relative frequencies per book
Outputs dictionary mapping novel object to the relative frequency
of female pronouns in that book
:param: Corpus object
:return: dictionary with data organized by groups
>>> books_pronoun_freq(Corpus('test_corpus'))
{<Novel (aanrud_longfrock)>: 0.7623169107856191, <Novel (abbott_flatlandromance)>: 0.14321608040201003, <Novel (abbott_indiscreetletter)>: 0.4166666666666667, <Novel (adams_fighting)>: 0.1898395721925134, <Novel (alcott_josboys)>: 0.42152086422368146, <Novel (alcott_littlemen)>: 0.3111248200699157, <Novel (alcott_littlewomen)>: 0.6196978175713487, <Novel (alden_chautauqua)>: 0.7518623169791935, <Novel (austen_emma)>: 0.5662100456621004, <Novel (austen_persuasion)>: 0.5305111461382571}
'''
try:
if (not corp.load_test_corpus):
relative_freq_male = common.load_pickle(f'{corp.corpus_name}_pronoun_freq_male')
relative_freq_female = common.load_pickle(f'{corp.corpus_name}_pronoun_freq_female')
return relative_freq_female
except IOError:
pass
relative_freq_male = {}
relative_freq_female = {}
for book in corp.novels:
he = book.get_word_freq('he')
him = book.get_word_freq('him')
his = book.get_word_freq('his')
male = he + him + his
she = book.get_word_freq('she')
her = book.get_word_freq('her')
hers = book.get_word_freq('hers')
female = she + her + hers
temp_dict = {'male': male, 'female': female}
temp_dict = get_comparative_word_freq(temp_dict)
relative_freq_male[book] = temp_dict['male']
relative_freq_female[book] = temp_dict['female']
book.text = ''
book._word_counts_counter = None
if (not corp.load_test_corpus):
common.store_pickle(relative_freq_male, f'{corp.corpus_name}_pronoun_freq_male')
common.store_pickle(relative_freq_female, f'{corp.corpus_name}_pronoun_freq_female')
return (relative_freq_female)