def RunIterativePredict(FeaturesDFin, currentStep):
FeaturesDF = FeaturesDFin.copy()
FeaturesDF_raw = FeaturesDF.copy()
if Settings["Normalise"] == "Yes":
for col in FeaturesDF.columns:
FeaturesDF[col] = (
FeaturesDF[col] -
FeaturesDF_raw[col].mean()) / FeaturesDF_raw[col].std()
if Settings["Regressor"] == "NN":
nn_options = { # options for neural network
'hidden_layer_sizes': (2, 1),
'solver': 'lbfgs',
'activation': 'tanh',
'max_iter': 1500, # default 200
'alpha': 0.001, # default 0.0001
'random_state': None # default None
}
model = MLPRegressor(**nn_options)
elif Settings["Regressor"] == "GPR":
mainRolling_kernel = ConstantKernel() + Matern() + DotProduct(
) + WhiteKernel() # + PairwiseKernel() + RBF() + ExpSineSquared()
#mainRolling_kernel = 1**2*ConstantKernel() + 1**2*Matern() + 1**2*DotProduct() + 1**2* ExpSineSquared() + 1**2*WhiteKernel() # + PairwiseKernel() + RBF() + ExpSineSquared()
model = GaussianProcessRegressor(
kernel=mainRolling_kernel,
random_state=0,
n_restarts_optimizer=2) #, normalize_y=True
elif Settings["Regressor"] == "LSTM":
model = Sequential()
model.add(LSTM(7, input_shape=(1, FeaturesDF.shape[1])))
model.add(Dense(1))
model.compile(loss='mean_squared_error', optimizer='adam')
iterPredsList = []
iterPreds_Std_List = []
if "SingleStepPredict" in Settings["Reporter"]:
fitInputX = FeaturesDF.shift(1).bfill().values
fitTargetY = FeaturesDF[targetVarName].values.reshape(-1, 1)
if Settings["Regressor"] == "LSTM":
fitInputX = fitInputX.reshape(trainX, (1, FeaturesDF.shape[1]))
for i in range(10):
model.fit(fitInputX,
fitTargetY,
epochs=1,
batch_size=5,
verbose=0,
shuffle=False)
model.reset_states()
else:
model.fit(fitInputX, fitTargetY)
if Settings['Regressor'] in ["NN", "LSTM"]:
firstPred = model.predict(FeaturesDF.iloc[-1].values.reshape(
1, -1))[0]
firstPred_Std = 0
elif Settings['Regressor'] == "GPR":
firstPred, firstPred_Std = model.predict(
FeaturesDF.iloc[-1].values.reshape(1, -1), return_std=True)
firstPred = firstPred[0][0]
firstPred_Std = firstPred_Std[0]
iterPredsList.append(firstPred)
iterPreds_Std_List.append(firstPred_Std)
elif "Iterative" in Settings["Reporter"]:
"Iterative Predictions"
inputDataList_rep = []
for j in range(Settings["predictAhead"] - 1):
if j == 0:
fitInputX = FeaturesDF.shift(1).bfill().values
fitTargetY = FeaturesDF[targetVarName].values.reshape(
-1, 1)
if Settings["Regressor"] == "LSTM":
fitInputX = np.reshape(fitInputX,
(1, FeaturesDF.shape[1]))
for i in range(10):
model.fit(fitInputX,
fitTargetY,
epochs=1,
batch_size=1,
verbose=0,
shuffle=False)
model.reset_states()
else:
model.fit(fitInputX, fitTargetY)
if Settings['Regressor'] in ["NN", "LSTM"]:
firstPred = model.predict(
FeaturesDF.iloc[-1].values.reshape(1, -1))[0]
firstPred_Std = 0
elif Settings['Regressor'] == "GPR":
firstPred, firstPred_Std = model.predict(
FeaturesDF.iloc[-1].values.reshape(1, -1),
return_std=True)
#print(firstPred)
#print(firstPred_Std)
#time.sleep(3000)
firstPred = firstPred[0][0]
firstPred_Std = firstPred_Std[0]
iterPredsList.append(firstPred)
iterPreds_Std_List.append(firstPred_Std)
expanding_infectedDF = infectedDF.copy().iloc[:currentStep +
j + 1]
newDate = expanding_infectedDF.index[-1]
knownWeather = allWeatherDF.loc[newDate].values
knownMobility = mobility_df.loc[newDate]
if Settings["Normalise"] == "Yes":
invertNormIterPreds = [
x * FeaturesDF_raw[targetVarName].std() +
FeaturesDF_raw[targetVarName].mean()
for x in iterPredsList
]
else:
invertNormIterPreds = iterPredsList
expanding_infectedDF.iloc[-len(iterPredsList):] = np.array(
invertNormIterPreds)
expanding_infectedDF_shifted = getShifts(
expanding_infectedDF, Settings['lags'])
if Settings["Scenario"] <= 1:
inputDataList = [invertNormIterPreds[-1]]
for elem in expanding_infectedDF_shifted.iloc[-1]:
inputDataList.append(elem)
for elem in knownWeather:
inputDataList.append(elem)
inputDataList.append(knownMobility)
elif Settings["Scenario"] in [2, 3]:
inputDataList = [invertNormIterPreds[-1]]
for elem in expanding_infectedDF_shifted.iloc[-1]:
inputDataList.append(elem)
elif Settings["Scenario"] == 4:
inputDataList = [invertNormIterPreds[-1]]
inputDataList.append(knownMobility)
elif Settings["Scenario"] == 5:
inputDataList = [invertNormIterPreds[-1]]
for elem in knownWeather:
inputDataList.append(elem)
inputDataList_rep.append([newDate, str(inputDataList)])
if Settings["Normalise"] == "Yes":
for colCount in range(len(FeaturesDF_raw.columns)):
inputDataList[colCount] = (
inputDataList[colCount] -
FeaturesDF_raw.iloc[:, colCount].mean()
) / FeaturesDF_raw.iloc[:, colCount].std()
if Settings["Regressor"] == "NN":
inputPointArray = np.array(inputDataList)
iterPred = model.predict(inputPointArray.reshape(1, -1))[0]
iterPred_std = 0
else:
inputPointArray = np.array(inputDataList)
iterPred, iterPred_std = model.predict(
inputPointArray.reshape(1, -1), return_std=True)
iterPred = iterPred[0][0]
iterPred_std = iterPred_std[0]
iterPredsList.append(iterPred)
iterPreds_Std_List.append(iterPred_std)
iterPredsList.insert(0, FeaturesDF_raw.index[-1])
iterPreds_Std_List.insert(0, FeaturesDF_raw.index[-1])
if Settings["Normalise"] == "Yes":
"standard normalisation"
iterPredsList[1:] = [
x * FeaturesDF_raw[targetVarName].std() +
FeaturesDF_raw[targetVarName].mean() for x in iterPredsList[1:]
]
iterPreds_Std_List[1:] = [
x * FeaturesDF_raw[targetVarName].std()
for x in iterPreds_Std_List[1:]
]
if (Settings["Scenario"] == 1) & (RegionName
in ["Campania", "Lombardia"]):
pd.concat([expanding_infectedDF, infectedDF.loc[expanding_infectedDF.index], allWeatherDF.loc[expanding_infectedDF.index], mobility_df.loc[expanding_infectedDF.index], pd.DataFrame(inputDataList_rep, columns=['data', 'inputs']).set_index('data', )], axis=1)\
.to_excel(modelDataPath+str(Settings["Scenario"])+RegionName+"_expanding_infectedDF.xlsx")
return [iterPredsList, iterPreds_Std_List]
