In [ ]:
# Import modules
import math
import pandas as pd
import numpy as np
import datetime as datetime
# Plotly Imports
import plotly.plotly as py
import plotly.graph_objs as go
import plotly
plotly.offline.init_notebook_mode()
# Keras Imports
from keras.models import Sequential
from keras.layers import Dense
In [ ]:
# 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)]
dataX.append(a)
dataY.append(dataset[i + look_back])
return np.array(dataX), np.array(dataY)
def split_dataset(dataset):
dataset = dataset.astype('float32')
# split into train and test sets
train_size = int(len(dataset) * 0.67)
test_size = len(dataset) - train_size
train, test = dataset[0:train_size], dataset[train_size:len(dataset)]
print(len(train), len(test))
return train, test
def train_model(dataset, save_model=False):
train, test = split_dataset(dataset)
# reshape into X=t and Y=t+1
look_back = 10
trainX, trainY = create_dataset(train, look_back)
testX, testY = create_dataset(test, look_back)
# create and fit Multilayer Perceptron model
model = Sequential()
model.add(Dense(8, input_dim=look_back, activation='relu'))
model.add(Dense(1))
model.compile(loss='mean_squared_error', optimizer='adam')
model.fit(trainX, trainY, nb_epoch=200, batch_size=2, verbose=2)
# Estimate model performance
trainScore = model.evaluate(trainX, trainY, verbose=0)
print('Train Score: %.2f MSE (%.2f RMSE)' % (trainScore, math.sqrt(trainScore)))
testScore = model.evaluate(testX, testY, verbose=0)
print('Test Score: %.2f MSE (%.2f RMSE)' % (testScore, math.sqrt(testScore)))
# Save model
if (save_model):
model.save('timeseries_rolling_cpu.h5')
return model
def create_data_with_rolling_avg(df):
# Create rolling average with window: 20
pdf = pd.DataFrame(df, columns=['MEAN_MAX_AIR_TEMP'])
pdf['MEAN_MAX_AIR_TEMP'].rolling(window=20,center=False)
rounded_data = np.round(pdf['MEAN_MAX_AIR_TEMP'].rolling(window=20,center=False).mean(),2)
rounded_data = rounded_data.dropna()
rounded_data.head()
# Get values as a np.array
dataset = rounded_data.values
return dataset
def predict_from_model(model, train, test, look_back = 10):
# generate predictions for training
trainX, trainY = create_dataset(train, look_back)
testX, testY = create_dataset(test, look_back)
trainPredict = model.predict(trainX)
testPredict = model.predict(testX)
# shift train predictions for plotting
trainPredictPlot = np.empty_like(dataset)
trainPredictPlot[:] = np.nan
trainPredictPlot[look_back:len(trainPredict)+look_back] = trainPredict[:,0]
# shift test predictions for plotting
testPredictPlot = np.empty_like(dataset)
testPredictPlot[:] = np.nan
testPredictPlot[len(trainPredict)+(look_back*2)+1:len(dataset)-1] = testPredict[:,0]
return trainPredictPlot, testPredictPlot
def plot_all(model, train, test):
trainPredictPlot, testPredictPlot = predict_from_model(model, train, test)
traces = [
go.Scatter(
y=dataset,
name='Max Temp',
opacity=0.7,
fill='tozeroy'
),
go.Scatter(
y=trainPredictPlot,
name='Training Prediction Max Temp',
opacity=0.7,
fill='tozeroy'
)
]
plotly.offline.iplot(traces)
traces = [
go.Scatter(
y=dataset,
name='Max Temp',
opacity=0.7,
fill='tozeroy'
),
go.Scatter(
y=testPredictPlot,
name='Test Prediction Max Temp',
opacity=0.7,
fill='tozeroy'
)
]
plotly.offline.iplot(traces)
Data source : BOREAS AES Five-day Averaged Surface Meteorological and Upper Air Data
In [ ]:
df = pd.read_csv('canadian_5_day_avg_daily.dat')
# Calculate local Start Time
df.index = pd.DatetimeIndex(pd.to_datetime(df["START_DATE"]), tz="UTC")
df["local_starttime"]=df.index.tz_convert("America/Santiago")
# Calculate local End Time
df.index = pd.DatetimeIndex(pd.to_datetime(df["END_DATE"]), tz="UTC")
df["local_endtime"]=df.index.tz_convert("America/Santiago")
# Set Start and End Date
df['start_date'] = datetime.datetime(1975,1,1)
df['end_date'] = datetime.datetime(1975,1,1)
for index, row in df.iterrows():
df.loc[index, 'start_date'] = datetime.datetime(row.local_starttime.year, row.local_starttime.month, row.local_starttime.day)
df.loc[index, 'end_date'] = datetime.datetime(row.local_endtime.year, row.local_endtime.month, row.local_endtime.day)
# Replace invalid values with 0
df['MEAN_AVG_AIR_TEMP'].replace(-999, 0, inplace=True)
df['MEAN_MAX_AIR_TEMP'].replace(-999, 0, inplace=True)
df['MEAN_MIN_AIR_TEMP'].replace(-999, 0, inplace=True)
df.head()
In [ ]:
# Verify model can be loaded
from keras.models import load_model
saved_model = load_model('timeseries_rolling_cpu.h5')
In [ ]:
pdf = pd.DataFrame(df, columns=['MEAN_MAX_AIR_TEMP'])
dataset = pdf['MEAN_MAX_AIR_TEMP'].values # create_data_with_rolling_avg(pdf)
train, test = split_dataset(dataset)
In [ ]:
plot_all(saved_model, train, test)
In [ ]:
pdf = pd.DataFrame(df, columns=['MEAN_MAX_AIR_TEMP'])
dataset = create_data_with_rolling_avg(pdf)
train, test = split_dataset(dataset)
In [ ]:
plot_all(saved_model, train, test)
In [ ]:
train_model(dataset) # This may take a while if you don't have NVIDIA CUDA-enabled GPU
In [ ]: