def call_data():
loading = instant_data()
df, mode = loading.hourly_instant(), 'hour'
df = df[start_p:stop_p]
data = df
data = data.interpolate(limit=300000000, limit_direction='both').astype(
'float32'
) #interpolate neighbor first, for rest NA fill with mean() #.apply(lambda x: x.fillna(x.mean()),axis=0)
data['Day'] = data.index.dayofyear
# # MARS
mars_cutoff = 0.3
data_mar = call_mar(data, target, mode, cutoff=mars_cutoff)
data_mar = move_column_inplace(data_mar, target, 0)
return data_mar
def datapreprocess():
loading = instant_data()
df,mode = loading.hourly_instant(),'hour'
df = df[start_p:stop_p]
data = df
data = data.interpolate(limit=300000000,limit_direction='both').astype('float32')#interpolate neighbor first, for rest NA fill with mean() #.apply(lambda x: x.fillna(x.mean()),axis=0)
data[target].plot()
# # MARS
mars_cutoff = 0.3
data_mar = call_mar(data,target,mode,cutoff=mars_cutoff)
data_mar = move_column_inplace(data_mar,target,0)
# # SCALE
# scaler = MinMaxScaler()
# df_scaled = pd.DataFrame(scaler.fit_transform(data_mar), columns=data_mar.columns,index=data_mar.index)
scaler_tar = MinMaxScaler()
scaler_tar.fit(data[target].to_numpy().reshape(-1,1))
return data_mar,scaler_tar
return X, y, xlabels
def inti_data(df):
global start_p, stop_p
data = df[start_p:stop_p].astype('float32')
# data['Day'] = data.index.dayofyear #add day
data = data.interpolate(limit=30000000, limit_direction='both').astype(
'float32') #interpolate neighbor first, for rest NA fill with mean()
data[target] = data[target].shift(-out_t_step)
data.dropna(inplace=True)
return data
#--------------------------------------------------------#
loading = instant_data()
df, mode = loading.hourly_instant(), 'hour'
# df,mode = loading.daily_instant(),'day'
st = 'CPY012'
target, start_p, stop_p, host_path = station_sel(st, mode)
if mode == 'hour': n_past, n_future = 24 * 6, 72
elif mode == 'day': n_past, n_future = 60, 30
n_pca = 4
split_date = '2016-11-01'
#----------------------------------------#
save_path = host_path + 'ML_svr/'
if not os.path.exists(save_path):
os.makedirs(save_path)
###########################################
