check frequency of the pronunciation variants of each word.

This commit is contained in:
yemaozi88 2019-01-12 23:29:56 +01:00
parent 1622655542
commit 6edde06a4f
2 changed files with 26 additions and 18 deletions

View File

@ -21,8 +21,11 @@ from forced_alignment import pyhtk, convert_phone_set
import novoapi
import novoapi_functions
## ======================= novo phoneset ======================
phoneset_ipa, phoneset_novo70, translation_key = novoapi_functions.load_phonset()
## ===== load novo phoneset =====
phoneset_ipa, phoneset_novo70, translation_key_ipa2novo70, translation_key_novo702ipa = novoapi_functions.load_phonset()
## ===== extract pronunciations written in novo70 only (not_in_novo70) =====
# As per Nederlandse phoneset_aki.xlsx recieved from David
# [ɔː] oh / ohr
@ -33,10 +36,7 @@ phoneset_ipa, phoneset_novo70, translation_key = novoapi_functions.load_phonset(
# [w] wv in IPA written as ʋ.
david_suggestion = ['ɔː', 'ɪː', 'iː', 'œː', 'ɛː', 'w']
## ======================= extract words which is written only with novo70 ======================
mapping = convert_xsampa2ipa.load_converter('xsampa', 'ipa', default.ipa_xsampa_converter_dir)
## read pronunciation variants.
stimmen_transcription_ = pd.ExcelFile(default.stimmen_transcription_xlsx)
df = pd.read_excel(stimmen_transcription_, 'frequency')
#for xsampa, ipa in zip(df['X-SAMPA'], df['IPA']):
@ -68,7 +68,8 @@ for ipa in transcription_ipa:
not_in_novo70.extend(not_in_novo70_)
not_in_novo70_list = list(set(not_in_novo70))
## check which phone is used in stimmen but not in novo70
## check which phones used in stimmen but not in novo70
# 'ʀ', 'ʁ',
# 'ɒ', 'ɐ',
# 'o', 'a' (o:, a:?)
@ -92,10 +93,12 @@ def search_phone_ipa(x, phone_list):
#search_phone_ipa('ø', transcription_ipa)
## ===== load all transcriptions (df) =====
df = pd.read_excel(stimmen_transcription_, 'original')
# mapping from ipa to xsampa
mapping = convert_xsampa2ipa.load_converter('xsampa', 'ipa', default.ipa_xsampa_converter_dir)
ipas = []
famehtks = []
for xsampa in df['Self Xsampa']:
@ -117,15 +120,11 @@ df = pd.DataFrame({'filename': df['Filename'],
'xsampa': df['Self Xsampa'],
'ipa': pd.Series(ipas)})
# find options which all phones are in novo70.
#word_list = list(set(df['word']))
#word_list = [word for word in word_list if not pd.isnull(word)]
#word = word_list[1]
word_list = [i for i in list(set(df['word'])) if not pd.isnull(i)]
word_list = sorted(word_list)
## pronunciation variants of 'word'
#df_ = df[df['word'] == word]['xsampa']
##pronunciation_variant = list(set(df_))
## check frequency of each pronunciation variants
cols = ['word', 'ipa', 'frequency']
df_samples = pd.DataFrame(index=[], columns=cols)
for ipa in all_in_novo70:
@ -134,3 +133,12 @@ for ipa in all_in_novo70:
word = list(set(samples['word']))[0]
samples_Series = pd.Series([word, ipa, len(samples)], index=df_samples.columns)
df_samples = df_samples.append(samples_Series, ignore_index=True)
# each word
df_per_word = pd.DataFrame(index=[], columns=df_samples.keys())
for word in word_list:
df_samples_ = df_samples[df_samples['word']==word]
df_samples_ = df_samples_[df_samples_['frequency']>1]
df_per_word = df_per_word.append(df_samples_, ignore_index=True)
df_per_word.to_excel(os.path.join(default.stimmen_dir, 'pronunciation_variants_novo70.xlsx'), encoding="utf-8")

View File

@ -39,7 +39,7 @@ def load_phonset():
phoneset_ipa = np.unique(phoneset_ipa)
phoneset_novo70 = np.unique(phoneset_novo70)
return phoneset_ipa, phoneset_novo70, translation_key_ipa2novo70, translation_key_novo702ipa
return
def multi_character_tokenize(line, multi_character_tokens):