1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66
| dataset = read_csv('tt.csv', parse_dates = ['date'], index_col=0)
#dataset.drop('No', axis=1, inplace=True)
# manually specify column names
#dataset.columns = ['pollution', 'dew', 'temp', 'press', 'wnd_dir', 'wnd_spd', 'snow', 'rain']
dataset.index.name = 'date'
print(dataset.head(5))
# save to file
dataset.to_csv('((ttt.csv')))
# load dataset
dataset = read_csv('tt', header=0, index_col=0)
values = dataset.values
# convert series to supervised learning
def series_to_supervised(data, n_in=1, n_out=1, dropnan=True):
n_vars = 1 if type(data) is list else data.shape[1]
df = DataFrame(data)
cols, names = list(), list()
# input sequence (t-n, ... t-1)
for i in range(n_in, 0, -1):
cols.append(df.shift(i))
names += [('var%d(t-%d)' % (j+1, i)) for j in range(n_vars)]
# forecast sequence (t, t+1, ... t+n)
for i in range(0, n_out):
cols.append(df.shift(-i))
if i == 0:
names += [('var%d(t)' % (j+1)) for j in range(n_vars)]
else:
names += [('var%d(t+%d)' % (j+1, i)) for j in range(n_vars)]
# put it all together
agg = concat(cols, axis=1)
agg.columns = names
# drop rows with NaN values
if dropnan:
agg.dropna(inplace=True)
return agg
# ensure all data is float
values = values.astype('float32')
# normalize features
scaler = MinMaxScaler(feature_range=(0, 1))
scaled = scaler.fit_transform(values)
# frame as supervised learning
reframed = series_to_supervised(scaled, 1, 1)
# drop columns we don't want to predict
#reframed.drop(reframed.columns[[9,10,11,12,13,14,15]], axis=1, inplace=True)
print(reframed.head())
values = reframed.values
n_train_hours =160
train = values[:n_train_hours, :]
test = values[n_train_hours:, :]
train_X, train_y = train[:, :-1], train[:, -1]
test_X, test_y = test[:, :-1], test[:, -1]
train_X = train_X.reshape((train_X.shape[0], 1, train_X.shape[1]))
test_X = test_X.reshape((test_X.shape[0],1, test_X.shape[1]))
print(train_X.shape, train_y.shape, test_X.shape, test_y.shape)
print(train_X.shape[1], train_X.shape[2])
model = Sequential()
model.add(LSTM(units=15,return_sequences=True, input_shape=(train_X.shape[1], train_X.shape[2])))
model.add(Dropout(rate=0.2))
model.add(LSTM(units=15,return_sequences=True))
model.add(Dropout(rate=0.2))
model.add(LSTM(units=15,return_sequences=False))
model.add(Dropout(rate=0.2))
model.add(Dense(1,activation="sigmoid"))
model.compile( loss="binary_crossentropy", optimizer="adam", metrics=["accuracy"])
# fit network
history = model.fit(train_X, train_y, epochs=100, batch_size=20, validation_split=0.1, verbose=1, shuffle=False) |