if document.shape[0]>0:
document = document.transpose()
document.reset_index(inplace=True, drop=True)
document['PetID'] = (i.split('.')[0]).split('/')[2]
language = a[a.index.str.match('language')]
if language.shape[0]>0:
language = language.transpose()
language.reset_index(inplace=True, drop=True)
final = pd.concat([language, document, sentences, entities], axis=1)
return(final)
TrainSentiment = Parallel(n_jobs=-1)(delayed(SentFunct)(SentDir + '/' + i) for i in files)
TrainSentiment = pd.concat(TrainSentiment, sort=False)
TrainSentiment = TrainSentiment.filter(regex= 'Mention*|PetID*|document*|lang*|sentences*')
TrainSentiment.to_csv('Results/TestSentiment.csv')
####### Section 2: MetaDataJson to CSV
MetaDir = "Data/test_metadata"
files = os.listdir(MetaDir)
files = [x for x in files if 'json' in x]
def MetaFunct(i):
df = readJson(i)
df = flatten_json(df)
a = pd.DataFrame.from_dict(df, orient='index')
a.columns = ['Values']
