-
Notifications
You must be signed in to change notification settings - Fork 0
/
pollution-lstm.py
160 lines (130 loc) · 4.31 KB
/
pollution-lstm.py
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
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
from math import sqrt
from numpy import concatenate
from matplotlib import pyplot
from pandas import set_option
from pandas import read_csv
from pandas import DataFrame
from pandas import concat
from sklearn.preprocessing import MinMaxScaler
from sklearn.preprocessing import LabelEncoder
from sklearn.metrics import mean_squared_error
#from keras import backend as Keras
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import LSTM
import tensorflow as tf
from tensorflow import keras
print(tf.__version__)
set_option('display.max_columns', None)
# Set CPU as available physical device
#my_devices = tf.config.experimental.list_physical_devices(device_type='CPU')
#tf.config.experimental.set_visible_devices(devices= my_devices, device_type='CPU')
# 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
# load dataset
dataset = read_csv('pollution.csv', header=0, index_col=0)
values = dataset.values
print(dataset.head())
# integer encode direction
encoder = LabelEncoder()
values[:, 4] = encoder.fit_transform(values[:, 4])
# 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
print(reframed.head())
reframed.drop(reframed.columns[[9, 10, 11, 12, 13, 14, 15]], axis=1, inplace=True)
print(reframed.head())
# split into train and test sets
values = reframed.values
n_train_hours = 365 * 24
train = values[:n_train_hours, :]
test = values[n_train_hours:, :]
# split into input and outputs
train_X, train_y = train[:, :-1], train[:, -1]
test_X, test_y = test[:, :-1], test[:, -1]
# reshape input to be 3D [samples, timesteps, features]
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)
# design network
model = Sequential()
model.add(LSTM(50, input_shape=(train_X.shape[1], train_X.shape[2])))
model.add(Dense(1))
model.compile(loss='mae', optimizer='adam')
# fit network
history = model.fit(
train_X,
train_y,
epochs=50,
batch_size=72,
validation_data=(test_X, test_y),
verbose=1,
shuffle=False)
print("save model")
model.save('pollution-model')
#model = keras.models.load_model('pollution-model')
# plot history
#pyplot.plot(history.history['loss'], label='train')
#pyplot.plot(history.history['val_loss'], label='test')
#pyplot.legend()
#pyplot.show()
# make a prediction
yhat = model.predict(test_X)
test_X = test_X.reshape((test_X.shape[0], test_X.shape[2]))
# invert scaling for forecast
inv_yhat = concatenate((yhat, test_X[:, 1:]), axis=1)
inv_yhat = scaler.inverse_transform(inv_yhat)
inv_yhat = inv_yhat[:, 0]
# invert scaling for actual
test_y = test_y.reshape((len(test_y), 1))
inv_y = concatenate((test_y, test_X[:, 1:]), axis=1)
inv_y = scaler.inverse_transform(inv_y)
inv_y = inv_y[:, 0]
print("predicted")
df_yhat = DataFrame(yhat)
print(df_yhat.head())
print("...")
print(df_yhat.tail())
print("inv_y")
df_test_y = DataFrame(test_y)
print(df_test_y.head())
print("...")
print(df_test_y.tail())
# calculate RMSE
rmse = sqrt(mean_squared_error(inv_y, inv_yhat))
print('Test RMSE: %.3f' % rmse)
#virtualenv -p python3.7 ./venv
#source ./venv/bin/activate
#pip install --upgrade pip
#pip install matplotlib tensorflow pandas sklearn keras
#https://medium.com/@alexmarginean/installing-tensorflow-on-fedora-29-862573ef2ab9