def VV(self):
"""
VVI: number of verb lemmas/number of verb tokens
VVII: number of verb lemmas/number of lexical tokens
"""
verb_lemmas = set(self.verb_lemmas)
verb_tokens = self.verb_lemmas
lex_tokens = self.open_class_lemmas
VVI = division(verb_lemmas, verb_tokens)
SVVI = squared_division(verb_lemmas, verb_tokens)
CVVI = corrected_division(verb_lemmas, verb_tokens)
VVII = division(verb_lemmas, lex_tokens)
return VVI, SVVI, CVVI, VVII
def derivational_suffixation(self):
"""
number of suffixes on n's level/number of suffixes
"""
suffixes = self.get_suffixes()
level3_suffixes = [i for i in suffixes if i in SUFFIXES["level3"]]
level4_suffixes = [i for i in suffixes if i in SUFFIXES["level4"]]
level5_suffixes = [i for i in suffixes if i in SUFFIXES["level5"]]
level6_suffixes = [i for i in suffixes if i in SUFFIXES["level6"]]
der_suff3 = division(level3_suffixes, suffixes)
der_suff4 = division(level4_suffixes, suffixes)
der_suff5 = division(level5_suffixes, suffixes)
der_suff6 = division(level6_suffixes, suffixes)
return der_suff3, der_suff4, der_suff5, der_suff6
def AdvV(self):
"""
number of adverb lemmas/number of lexical tokens
"""
adv_lemmas = set(self.adv_lemmas)
lex_tokens = self.open_class_lemmas
return division(adv_lemmas, lex_tokens)
def AdjV(self):
"""
number of adjective lemmas/number of lexical tokens
"""
adj_lemmas = set(self.adj_lemmas)
lex_tokens = self.open_class_lemmas
return division(adj_lemmas, lex_tokens)
def NV(self):
"""
number of noun lemmas/number of lexical tokens
"""
noun_lemmas = set(self.noun_lemmas)
lex_tokens = self.tokens
return division(noun_lemmas, lex_tokens)
def LFP(self):
"""
Lexical Frequency Profile is the proportion of tokens:
first - 1000 most frequent words
second list - the second 1000
third - University Word List (Xue & Nation 1989)
none - list of those that are not in these lists
"""
first = [i for i in self.lemmas if i in FIVE_T_FREQ_COCA[0:1000]]
second = [i for i in self.lemmas if i in FIVE_T_FREQ_COCA[1000:2000]]
third = [i for i in self.lemmas if i in UWL]
first_procent = division(first, self.lemmas)
second_procent = division(second, self.lemmas)
third_procent = division(third, self.lemmas)
none = 1 - (first_procent + second_procent + third_procent)
return first_procent, second_procent, third_procent, none
def VS(self):
"""
number of sophisticated verb lemmas/number of verb tokens
"""
soph_verbs = [i for i in self.verb_lemmas if i not in FREQ_VERBS_COCA_FROM_FIVE_T]
VSI = division(soph_verbs, self.verb_lemmas)
VSII = corrected_division(soph_verbs, self.verb_lemmas)
VSIII = squared_division(soph_verbs, self.verb_lemmas)
return VSI, VSII, VSIII
def TTR(self):
"""
number of lemmas/number of tokens
"""
lemmas = set(self.lemmas)
tokens = self.tokens
TTR = division(lemmas, tokens)
CTTR = corrected_division(lemmas, tokens)
RTTR = root_division(lemmas, tokens)
LogTTR = log_division(lemmas, tokens)
Uber = uber(lemmas, tokens)
return TTR, CTTR, RTTR, LogTTR, Uber
def LS(self):
"""
number of sophisticated lexical tokens/number of lexical tokens
"""
soph_lex_lemmas = [i for i in self.open_class_lemmas if i not in FIVE_T_FREQ_COCA]
return division(soph_lex_lemmas, self.open_class_lemmas)
def density(self):
"""
number of lexical tokens/number of tokens
"""
return division(self.open_class_lemmas, self.lemmas)
def freq_aux(self):
"""
frequency of modals(auxilaries)
"""
return division(self.aux_forms, self.verb_tokens)
def freq_finite_forms(self):
"""
frequency of tensed(finite) forms
"""
return division(self.finite_tokens, self.verb_tokens)