def pronostico_normal(data,dirFestivos,dataMet,estacion,contaminant,dirData,dirTrain):
data = data.reset_index(drop=True)
data = separateDate(data)
data = totalUnionData(data, dirFestivos)
data = df.concat([data, dataMet], axis=1, join='inner')
#data = data.merge(dataMet, how='left', on='fecha')
data = filterData(data, dirData + estacion + "_" + contaminant + ".csv")
data = data.fillna(value=-1)
index = data.index.values
arrayPred = []
for x in index:
pred = data.ix[x].values
valPred = pred[2:]
valNorm = pre.normalize(valPred, estacion, contaminant, dirData)
arrayPred.append(convert(valNorm))
result = pre.prediction(estacion, contaminant, arrayPred, dirTrain, dirData)
columnContaminant = findTable2(contaminant)
real = pre.desNorm(result, estacion, contaminant, dirData, columnContaminant+ '_')
for xs in range(len(real)):
fechaPronostico = data['fecha'].iloc[xs].values
fechaPronostico = datetime.strptime(fechaPronostico[1], '%Y-%m-%d %H:%M:%S')
fechaPronostico = fechaPronostico - timedelta(days=1)
pronostico = real[xs]
guardarPrediccion(estacion, fechaPronostico, [pronostico],contaminant,2)
return 1
def forecast_month(month, year, dirData, dirTotalCsv, dirTrain,estacion, contaminant):
lastDay = calendar.monthrange(year,month)[1]
fechaInicio = str(year) + '-' + numString(month) + '-01 00:00:00'
fechaFinal = str(year) + '-' + numString(month) + '-'+ numString(lastDay) +' 23:00:00'
#print(fechaInicio)
#print(fechaFinal)
data = fd.readData(fechaInicio, fechaFinal, [estacion], contaminant)
data = separateDate(data)
data = unionMeteorologia(data,dirTotalCsv)
data = data.fillna(value=-1)
#print(data)
#sys.out
frame_dates = data['fecha'].values
data = filterData(data, dirData + estacion + "_" + contaminant + ".csv")
data = data.fillna(value=-1)
index = data.index.values
arrayPred = []
for x in index:
pred = data.ix[x].values
valPred= pred[1:]
valNorm = pre.normalize(valPred,estacion, contaminant, dirData)
arrayPred.append(convert(valNorm))
result = pre.prediction(estacion, contaminant, arrayPred, dirTrain, dirData)
nameCont = findTable2(contaminant)
real = pre.desNorm(result, estacion,contaminant, dirData, nameCont + '_')
for xs in range(len(frame_dates)):
fecha = frame_dates[xs]
ts = df.to_datetime(str(fecha))
fecha_string = ts.strftime('%Y-%m-%d %H:%M:%S')
pronostico = real[xs]
guardarPrediccion(estacion, fecha_string,[pronostico],contaminant,4)
def prediccion(estacion, data, dirData, dirTrain, contaminant):
"""
function that sends the data to the neural network for the prediction of the pollutant
:param estacion: name the station
:type estacion: String
:param data: information for the prediction
:type data : list float32
:param dirData: address of the files with training information
:type dirData: String
:param dirTrain: address of the training files of the neural network
:type dirTrain: String
:return: prdiction values
:type return : float32
"""
temp = data.ix[0].values
temp = temp[1:]
dataPred = pre.normalize(temp, estacion, contaminant, dirData)
dataPred = convert(dataPred)
prediccion = pre.prediction(estacion, contaminant, [dataPred], dirTrain,
dirData)
print(prediccion)
columnContaminant = findTable2(contaminant)
prediccion1 = pre.desNorm(prediccion, estacion, contaminant, dirData,
columnContaminant + '_')
return prediccion1
def dataCorrelacion(contaminant, estacion, fechaInicio, fechaFin, dataMet,
dirData, dirTrain, dirFestivos):
print('COrrelacion')
data_Corr = df.read_csv(
'/media/storageBK/AirQualityForecast/Scripts/ContaminationForecast/Data/Correlacion_table.csv',
index_col=0)
corr_est = data_Corr[estacion].sort_values(ascending=False)
estacion_corr = corr_est.index[1]
data = fd.readData_corr(fechaInicio, fechaFin, [estacion_corr],
contaminant)
if data.empty:
useClimatology(contaminant, estacion, fechaUltima, fechaFin, dataMet,
dirData, dirTrain, dirFestivos)
else:
data = data.drop_duplicates(keep='first')
data = data.reset_index(drop=True)
index_values = data.columns.values[1:]
for xs in index_values:
data.rename(columns={
xs: xs.replace(estacion_corr.lower(), estacion.lower())
},
inplace=True)
data = separateDate(data)
data = totalUnionData(data, dirFestivos)
data = df.concat([data, dataMet], axis=1, join='inner')
print(data)
#data = data.merge(dataMet, how='left', on='fecha')
data = filterData(data,
dirData + estacion + "_" + contaminant + ".csv")
data = data.fillna(value=-1)
index = data.index.values
arrayPred = []
for x in index:
pred = data.ix[x].values
valPred = pred[2:]
print(valPred)
valNorm = pre.normalize(valPred, estacion, contaminant, dirData)
arrayPred.append(convert(valNorm))
result = pre.prediction(estacion, contaminant, arrayPred, dirTrain,
dirData)
columnContaminant = findTable2(contaminant)
real = pre.desNorm(result, estacion, contaminant, dirData,
columnContaminant + '_')
for xs in range(len(real)):
fechaPronostico = data['fecha'].iloc[xs].values
fechaPronostico = datetime.strptime(fechaPronostico[1],
'%Y-%m-%d %H:%M:%S')
pronostico = real[xs]
guardarPrediccionRep(estacion, fechaPronostico, [pronostico],
contaminant, 5)
def useClimatology(contaminant, estacion, fechaInicio, fechaFinal, dataMet,
dirData, dirTrain, dirFestivos):
"""
function to make the forecast using climatologies
:param contaminant: name of the pollutant
:type contaminant: String
:param estacion: name of the weather station
:type estacion: String
:param fechaInicio: range of data wit wich the vaues of tue query are extracted
:type fechaInicio: datetime
:param fechaFinal: range of data wit wich the vaues of tue query are extracted
:type fechaFinal: datetime
:param dataMet: dataframe with the climatological information
:type dataMet: DataFrame
"""
data = fd.get_climatology(fechaInicio, fechaFinal, estacion)
print(data)
data = makeDates(fechaInicio, fechaFinal, data)
#sys.out
print(data)
data = data.reset_index(drop=True)
print(data)
data = separateDate(data)
data = totalUnionData(data, dirFestivos)
data = df.concat([data, dataMet], axis=1, join='inner')
#data = data.merge(dataMet, how='left', on='fecha')
data = data.fillna(value=-1)
data = filterData(data, dirData + estacion + "_" + contaminant + ".csv")
data = data.fillna(value=-1)
index = data.index.values
arrayPred = []
for x in index:
pred = data.ix[x].values
valPred = pred[2:]
valNorm = pre.normalize(valPred, estacion, contaminant, dirData)
arrayPred.append(convert(valNorm))
result = pre.prediction(estacion, contaminant, arrayPred, dirTrain,
dirData)
columnContaminant = findTable2(contaminant)
real = pre.desNorm(result, estacion, contaminant, dirData,
columnContaminant + '_')
fechaPronostico = fechaInicio
for xs in real:
print(fechaPronostico)
fechaUpdate = fechaPronostico
fechaUpdate = fechaUpdate - timedelta(days=1)
guardarPrediccion(estacion, fechaUpdate, [xs], contaminant, 1)
fechaPronostico = fechaPronostico + timedelta(hours=1)
print('Climatologia:' + estacion)