# -*- coding: utf-8 -*-
"""
Created on Wed Aug 16 10:18:24 2017

@author: thanvaf
"""
### Libraries ###
from influxdb import InfluxDBClient
import pandas as pd
import datetime
from datetime import datetime, timedelta
from datetime import timedelta
import numpy as np
import matplotlib.pyplot as plt
import math
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import LSTM
from sklearn.preprocessing import MinMaxScaler
from sklearn.metrics import mean_squared_error

import time

### Modules ###
def roundTime(dt=None, roundTo=60):
   """Round a datetime object to any time laps in seconds
   dt : datetime.datetime object, default now.
   roundTo : Closest number of seconds to round to, default 1 minute.
   Author: Thierry Husson 2012 - Use it as you want but don't blame me.
   """
   if dt == None : dt = datetime.datetime.now()
   seconds = (dt.replace(tzinfo=None) - dt.min).seconds
   rounding = (seconds+roundTo/2) // roundTo * roundTo
   return dt + timedelta(0,rounding-seconds,-dt.microsecond)

def datetime_range(start, end, delta):
    current = start
    while current < end:
        yield current
        current += delta

# convert an array of values into a dataset matrix
def create_dataset(dataset, look_back=1):
	dataX, dataY = [], []
	for i in range(len(dataset)-look_back-1):
		a = dataset[i:(i+look_back), 0]
		dataX.append(a)
		dataY.append(dataset[i + look_back, 0])
	return np.array(dataX), np.array(dataY)
#==============================================================================
# Database parameters
#==============================================================================
localhost = 'hydra.iti.gr'
port = 8086
username = 'root'
password = 'root'
databaseN = '90676b79_3273_400e_8b57_368ca37e9f8c'
assignmentToken0 = '948a55d9-722e-4ec6-a176-8d1ea9c04c83'
assignmentToken1 = '8962cf27-704d-4f32-8d44-ae67762ae87b'
assignmentToken2 = '79c122e9-14ec-4ae4-a932-3efd208256cc'
assignmentToken3 = '721b460c-ad4f-4921-a71f-0f87cfb69ef0'
measurement = 'mx:kwhCons'
time0 = 'time'
#==============================================================================
# Various parameters (Initialization)
#==============================================================================
listamin = [];listamax = []; listamedian = []
#==============================================================================
# Dates parameters
#==============================================================================
N = 31
currentDate=datetime.utcnow()
endDate=(currentDate - timedelta(days = 1)).strftime('%Y-%m-%dT23:59:59.999Z')
startDate=(currentDate - timedelta(days = N)).strftime('%Y-%m-%dT00:00:00.000Z')
#==============================================================================
# Retrieve data from database based on specified parameters
#==============================================================================
client = InfluxDBClient(host = localhost, port = 8086, username = 'root', password = 'root', database = databaseN)
q = ("""SELECT "{0}","{1}" FROM events WHERE assignment = '{2}' AND time>='{3}' AND time<='{4}'""".format(time0, measurement, assignmentToken0,startDate,endDate))
#q = ("""SELECT "{0}" FROM events WHERE assignment = '{1}' AND time>='{2}T07:00:00Z' AND time<='{3}T13:51:00Z'""".format(measurement,assignmentToken1,start_date,end_date))
df = pd.DataFrame(client.query(q, chunked=True).get_points())
size = df.shape
#==============================================================================
# Time series of interest
#==============================================================================
# fix random seed for reproducibility
np.random.seed(7)

timeSeries = df[measurement].astype(float)
timeSeries = [[timeSeries[i]] for i in range(len(timeSeries)-500,len(timeSeries))]
dataset = np.array(timeSeries)
dataset = dataset.astype('float32')
# normalize the dataset
scaler = MinMaxScaler(feature_range=(0, 1))
dataset = scaler.fit_transform(dataset)

# split into train and test sets
train_size = int(len(dataset) * (1.0-0.192))
test_size = len(dataset) - train_size
train, test = dataset[0:train_size,:], dataset[train_size:len(dataset),:]

# reshape into X=t and Y=t+1
look_back = 4
trainX, trainY = create_dataset(train, look_back)
testX, testY = create_dataset(test, look_back)

# reshape input to be [samples, time steps, features]
trainX = np.reshape(trainX, (trainX.shape[0], 1, trainX.shape[1]))
testX = np.reshape(testX, (testX.shape[0], 1, testX.shape[1]))

start = time.time()

hidden_neurons = 30
epochs = 1500

# create and fit the LSTM network
model = Sequential()
model.add(LSTM(hidden_neurons, input_shape=(1, look_back))) # 3 is the number of LSTM blocks or neurons
model.add(Dense(1))
model.compile(loss='mean_squared_error', optimizer='adam', metrics = ['accuracy'])

history = model.fit(trainX, trainY, nb_epoch=epochs, batch_size=1, verbose=2)

end  = time.time()

overall_time = end-start
print overall_time
# make predictions
trainPredict = model.predict(trainX)
testPredict = model.predict(testX)
# invert predictions
trainPredict = scaler.inverse_transform(trainPredict)
trainY = scaler.inverse_transform([trainY])
testPredict = scaler.inverse_transform(testPredict)
testY = scaler.inverse_transform([testY])
# calculate root mean squared error
trainScore = math.sqrt(mean_squared_error(trainY[0], trainPredict[:,0]))
print('Train Score: %.2f RMSE' % (trainScore))
testScore = math.sqrt(mean_squared_error(testY[0], testPredict[:,0]))
print('Test Score: %.2f RMSE' % (testScore))

# shift train predictions for plotting
trainPredictPlot = np.empty_like(dataset)
trainPredictPlot[:, :] = np.nan
trainPredictPlot[look_back:len(trainPredict)+look_back, :] = trainPredict
# shift test predictions for plotting
testPredictPlot = np.empty_like(dataset)
testPredictPlot[:, :] = np.nan
testPredictPlot[len(trainPredict)+(look_back*2)+1:len(dataset)-1, :] = testPredict
# plot baseline and predictions
plt.plot(scaler.inverse_transform(dataset))
plt.plot(trainPredictPlot)
plt.plot(testPredictPlot)
plt.legend(['Initial','Train','Test'],loc='best')
plt.title('Epochs: '+str(epochs)+' Neurons: '+str(hidden_neurons)+' Lag: '+str(look_back))
plt.show()