#https://machinelearningmastery.com/time-series-forecasting-long-short-term-memory-network-python/
from pandas import DataFrame
from pandas import Series
from pandas import concat
from pandas import read_csv
from pandas import read_sql_query
from pandas import datetime
from sklearn.metrics import mean_squared_error
from sklearn.preprocessing import MinMaxScaler
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import LSTM
from math import sqrt
from matplotlib import pyplot
import numpy
import MySQLdb
import sys
#definiciones db
sql_hn = "********"
sql_p = 3306
sql_uid = "********"
sql_pwd = "********"
sql_db = "********"
#conexión db
conn = MySQLdb.connect(
host = sql_hn,
port = sql_p,
user = sql_uid,
passwd = sql_pwd,
db = sql_db
)
cursor = conn.cursor()
def imprimir(text):
sys.stdout.write(str(text))
sys.stdout.flush()
# date-time parsing function for loading the dataset
def parser(x):
return datetime.strptime(x, '%Y-%m-%d %H:%M:%S')
# frame a sequence as a supervised learning problem
def timeseries_to_supervised(data, lag=1):
df = DataFrame(data)
columns = [df.shift(i) for i in range(1, lag+1)]
columns.append(df)
df = concat(columns, axis=1)
df.fillna(0, inplace=True)
return df
# create a differenced series
def difference(dataset, interval=1):
diff = list()
for i in range(interval, len(dataset)):
value = dataset[i] - dataset[i - interval]
diff.append(value)
return Series(diff)
# invert differenced value
def inverse_difference(history, yhat, interval=1):
return yhat + history[-interval]
# scale train and test data to [-1, 1]
def scale(train, test):
# fit scaler
scaler = MinMaxScaler(feature_range=(-1, 1))
scaler = scaler.fit(train)
# transform train
train = train.reshape(train.shape[0], train.shape[1])
train_scaled = scaler.transform(train)
# transform test
test = test.reshape(test.shape[0], test.shape[1])
test_scaled = scaler.transform(test)
return scaler, train_scaled, test_scaled
# inverse scaling for a forecasted value
def invert_scale(scaler, X, value):
new_row = [x for x in X] + [value]
array = numpy.array(new_row)
array = array.reshape(1, len(array))
inverted = scaler.inverse_transform(array)
return inverted[0, -1]
# fit an LSTM network to training data
def fit_lstm(train, batch_size, nb_epoch, neurons):
X, y = train[:, 0:-1], train[:, -1]
X = X.reshape(X.shape[0], 1, X.shape[1])
model = Sequential()
model.add(LSTM(neurons, batch_input_shape=(batch_size, X.shape[1], X.shape[2]), stateful=True))
model.add(Dense(1))
model.compile(loss='mean_squared_error', optimizer='adam')
for i in range(nb_epoch):
model.fit(X, y, epochs=1, batch_size=batch_size, verbose=1, shuffle=False)
model.reset_states()
return model
# make a one-step forecast
def forecast_lstm(model, batch_size, X):
X = X.reshape(1, 1, len(X))
yhat = model.predict(X, batch_size=batch_size)
return yhat[0,0]
seleccion = " \
SELECT creacion, \
menores \
FROM( \
SELECT creacion, \
COUNT(*) as maximo, \
(SUM(CASE WHEN value < 2 THEN 1 ELSE 0 END)) as menores, \
(SUM(CASE WHEN value >= 2 THEN 1 ELSE 0 END)) as mayores, \
((SUM(CASE WHEN value < 2 THEN 1 ELSE 0 END)) - (SUM(CASE WHEN value >= 2 THEN 1 ELSE 0 END))) as diferencia, \
FLOOR(UNIX_TIMESTAMP(creacion)/(2 * 60)) AS lapso, \
DATE_FORMAT(creacion, '%T') as sub_creacion \
FROM crawler \
WHERE round > 500000 \
GROUP BY lapso \
) as sub \
ORDER BY creacion DESC"
# load dataset
#series = read_csv('shampoo.csv', header=0, parse_dates=[0], index_col=0, squeeze=True, date_parser=parser)
#series = read_csv('numeros.csv', header=0, parse_dates=[0], index_col=0, squeeze=True, date_parser=parser)
series = read_sql_query(seleccion, conn, parse_dates=['creacion'], index_col=['creacion'])
# transform data to be stationary
raw_values = series.values
diff_values = difference(raw_values, 1)
# transform data to be supervised learning
supervised = timeseries_to_supervised(diff_values, 1)
supervised_values = supervised.values
# split data into train and test-sets
#train, test = supervised_values[0:-12], supervised_values[-12:]
#dividimos la información
train_size = int(len(supervised_values) * 0.50)
test_size = len(supervised_values) - train_size
train, test = supervised_values[0:train_size,:], supervised_values[train_size:len(supervised_values),:]
# transform the scale of the data
scaler, train_scaled, test_scaled = scale(train, test)
# repeat experiment
repeats = 1
epochos = 1
error_scores = list()
for r in range(repeats):
# fit the model
lstm_model = fit_lstm(train_scaled, 1, epochos, 16)
# forecast the entire training dataset to build up state for forecasting
train_reshaped = train_scaled[:, 0].reshape(len(train_scaled), 1, 1)
lstm_model.predict(train_reshaped, batch_size=1)
# walk-forward validation on the test data
predictions = list()
for i in range(len(test_scaled)):
# make one-step forecast
X, y = test_scaled[i, 0:-1], test_scaled[i, -1]
yhat = forecast_lstm(lstm_model, 1, X)
# invert scaling
yhat = invert_scale(scaler, X, yhat)
# invert differencing
yhat = inverse_difference(raw_values, yhat, len(test_scaled)+1-i)
# store forecast
predictions.append(yhat)
# report performance
rmse = sqrt(mean_squared_error(raw_values[-test_size:], predictions))
print('%d) Test RMSE: %.3f' % (r+1, rmse))
error_scores.append(rmse)
# summarize results
#results = DataFrame()
#results['rmse'] = error_scores
#print(results.describe())
#results.boxplot()
#pyplot.show()
# report performance
#rmse = sqrt(mean_squared_error(raw_values[-test_size:], predictions))
#print('Test RMSE: %.3f' % rmse)
# line plot of observed vs predicted
#pyplot.plot(raw_values[-test_size:])
#pyplot.plot(predictions)
#pyplot.show()
print("******************* PREDICCIONES *******************")
while True:
#pedimos la informacion
seleccion = " \
SELECT creacion, \
menores \
FROM( \
SELECT creacion, \
COUNT(*) as maximo, \
(SUM(CASE WHEN value < 2 THEN 1 ELSE 0 END)) as menores, \
(SUM(CASE WHEN value >= 2 THEN 1 ELSE 0 END)) as mayores, \
((SUM(CASE WHEN value < 2 THEN 1 ELSE 0 END)) - (SUM(CASE WHEN value >= 2 THEN 1 ELSE 0 END))) as diferencia, \
FLOOR(UNIX_TIMESTAMP(creacion)/(2 * 60)) AS lapso, \
DATE_FORMAT(creacion, '%T') as sub_creacion \
FROM crawler \
GROUP BY lapso \
ORDER BY creacion DESC \
LIMIT 0, 300 \
) as sub \
ORDER BY creacion DESC"
#seleccionamos la información para hacer la predicción
predecir = read_sql_query(seleccion, conn, parse_dates=['creacion'], index_col=['creacion'])
#limpiamos la cache
conn.commit()
imprimir(predecir)
yhat = forecast_lstm(lstm_model, 1, predecir)
#ynew = ynew[0]
imprimir(yhat)
!
