def load_sianipar16():
sianipar16=pd.read_excel(cs.sianipar16)
sianipar16=sianipar16[['Words (Indonesian)', 'ALL_Valence_Mean', 'ALL_Arousal_Mean', 'ALL_Dominance_Mean']]
sianipar16.columns=heads_vad
sianipar16.set_index('Word', inplace=True)
#sianipar16=sianipar16[~sianipar16.index.duplicated(keep='first')]
sianipar16=drop_duplicates(sianipar16)
return sianipar16
def load_briesemeister11():
briesemeister11=pd.read_excel(cs.briesemeister11)
briesemeister11=briesemeister11[['WORD_LOWER', 'HAP_MEAN', 'ANG_MEAN',
'SAD_MEAN', 'FEA_MEAN', 'DIS_MEAN']]
briesemeister11.columns=heads_be5
briesemeister11.set_index('Word', inplace=True)
briesemeister11=drop_duplicates(briesemeister11)
# print(briesemeister11.head())
# print(briesemeister11.shape)
return briesemeister11
def load_schmidtke14(lower_case=False):
schmidtke14=pd.read_excel(cs.schmidtke14)
# schmidtke14=schmidtke14[['Word','Valence','Arousal','Dominance']]
schmidtke14=schmidtke14[['G-word', 'VAL_Mean', 'ARO_Mean_(ANEW)', 'DOM_Mean']]
schmidtke14.columns=['Word', 'Valence', 'Arousal', 'Dominance']
# schmidtke14['Word']=schmidtke14['Word'].str.lower()
schmidtke14.set_index('Word', inplace=True)
if lower_case:
schmidtke14.index=schmidtke14.index.str.lower()
#schmidtke14=schmidtke14[~schmidtke14.index.duplicated(keep='first')]
schmidtke14=drop_duplicates(schmidtke14)
schmidtke14.Valence = [scaleInRange(x = x, oldmin = -3.,
oldmax = 3., newmin = 1., newmax=9.)
for x in schmidtke14.Valence]
# ### setting word column to lower case for compatiblity with briesemeister11
# # print(schmidtke14.head())
# # print(schmidtke14.shape)
return schmidtke14
def get_german_schmidtke(): angst=load_schmidtke14() angst.set_index(angst.index.str.lower(), inplace=True) data = angst.join(load_briesemeister11(), how='inner') data = drop_duplicates(data) return data
def get_spanish_ferre(): va=pd.concat([load_redondo07(), load_guasch15()]) df=va.join(load_ferre16(), how='inner') df=drop_duplicates(df) df=df[['Valence', 'Arousal', 'Joy', 'Anger', 'Sadness', 'Fear', 'Disgust']] return(df)
def load_anew99():
anew=pd.read_csv(cs.anew99, sep='\t')
anew.columns=heads_vad
anew.set_index('Word', inplace=True)
anew=drop_duplicates(anew)
return anew