LSTM Time Series Forecasting for Air Quality

In [1]:

    

from tensorflow import keras


    

In [2]:

    

import pandas as pd
import numpy as np

df_raw = pd.read_csv("datasets/AirQualityUCI.csv", sep=';')


    

In [3]:

    

df_raw.head()


    

    
Out[3]:







  

    

      

      
Date
      
Time
      
CO(GT)
      
PT08.S1(CO)
      
NMHC(GT)
      
C6H6(GT)
      
PT08.S2(NMHC)
      
NOx(GT)
      
PT08.S3(NOx)
      
NO2(GT)
      
PT08.S4(NO2)
      
PT08.S5(O3)
      
T
      
RH
      
AH
      
Unnamed: 15
      
Unnamed: 16
    
  
  

    

      
0
      
10/03/2004
      
18.00.00
      
2,6
      
1360.0
      
150.0
      
11,9
      
1046.0
      
166.0
      
1056.0
      
113.0
      
1692.0
      
1268.0
      
13,6
      
48,9
      
0,7578
      
NaN
      
NaN
    
    

      
1
      
10/03/2004
      
19.00.00
      
2
      
1292.0
      
112.0
      
9,4
      
955.0
      
103.0
      
1174.0
      
92.0
      
1559.0
      
972.0
      
13,3
      
47,7
      
0,7255
      
NaN
      
NaN
    
    

      
2
      
10/03/2004
      
20.00.00
      
2,2
      
1402.0
      
88.0
      
9,0
      
939.0
      
131.0
      
1140.0
      
114.0
      
1555.0
      
1074.0
      
11,9
      
54,0
      
0,7502
      
NaN
      
NaN
    
    

      
3
      
10/03/2004
      
21.00.00
      
2,2
      
1376.0
      
80.0
      
9,2
      
948.0
      
172.0
      
1092.0
      
122.0
      
1584.0
      
1203.0
      
11,0
      
60,0
      
0,7867
      
NaN
      
NaN
    
    

      
4
      
10/03/2004
      
22.00.00
      
1,6
      
1272.0
      
51.0
      
6,5
      
836.0
      
131.0
      
1205.0
      
116.0
      
1490.0
      
1110.0
      
11,2
      
59,6
      
0,7888
      
NaN
      
NaN
    
  

In [4]:

    

df = df_raw.dropna(subset=['Date'])


    

In [5]:

    

df_raw.describe()


    

    
Out[5]:







  

    

      

      
PT08.S1(CO)
      
NMHC(GT)
      
PT08.S2(NMHC)
      
NOx(GT)
      
PT08.S3(NOx)
      
NO2(GT)
      
PT08.S4(NO2)
      
PT08.S5(O3)
      
Unnamed: 15
      
Unnamed: 16
    
  
  

    

      
count
      
9357.000000
      
9357.000000
      
9357.000000
      
9357.000000
      
9357.000000
      
9357.000000
      
9357.000000
      
9357.000000
      
0.0
      
0.0
    
    

      
mean
      
1048.990061
      
-159.090093
      
894.595276
      
168.616971
      
794.990168
      
58.148873
      
1391.479641
      
975.072032
      
NaN
      
NaN
    
    

      
std
      
329.832710
      
139.789093
      
342.333252
      
257.433866
      
321.993552
      
126.940455
      
467.210125
      
456.938184
      
NaN
      
NaN
    
    

      
min
      
-200.000000
      
-200.000000
      
-200.000000
      
-200.000000
      
-200.000000
      
-200.000000
      
-200.000000
      
-200.000000
      
NaN
      
NaN
    
    

      
25%
      
921.000000
      
-200.000000
      
711.000000
      
50.000000
      
637.000000
      
53.000000
      
1185.000000
      
700.000000
      
NaN
      
NaN
    
    

      
50%
      
1053.000000
      
-200.000000
      
895.000000
      
141.000000
      
794.000000
      
96.000000
      
1446.000000
      
942.000000
      
NaN
      
NaN
    
    

      
75%
      
1221.000000
      
-200.000000
      
1105.000000
      
284.000000
      
960.000000
      
133.000000
      
1662.000000
      
1255.000000
      
NaN
      
NaN
    
    

      
max
      
2040.000000
      
1189.000000
      
2214.000000
      
1479.000000
      
2683.000000
      
340.000000
      
2775.000000
      
2523.000000
      
NaN
      
NaN
    
  

In [6]:

    

df.describe()


    

    
Out[6]:







  

    

      

      
PT08.S1(CO)
      
NMHC(GT)
      
PT08.S2(NMHC)
      
NOx(GT)
      
PT08.S3(NOx)
      
NO2(GT)
      
PT08.S4(NO2)
      
PT08.S5(O3)
      
Unnamed: 15
      
Unnamed: 16
    
  
  

    

      
count
      
9357.000000
      
9357.000000
      
9357.000000
      
9357.000000
      
9357.000000
      
9357.000000
      
9357.000000
      
9357.000000
      
0.0
      
0.0
    
    

      
mean
      
1048.990061
      
-159.090093
      
894.595276
      
168.616971
      
794.990168
      
58.148873
      
1391.479641
      
975.072032
      
NaN
      
NaN
    
    

      
std
      
329.832710
      
139.789093
      
342.333252
      
257.433866
      
321.993552
      
126.940455
      
467.210125
      
456.938184
      
NaN
      
NaN
    
    

      
min
      
-200.000000
      
-200.000000
      
-200.000000
      
-200.000000
      
-200.000000
      
-200.000000
      
-200.000000
      
-200.000000
      
NaN
      
NaN
    
    

      
25%
      
921.000000
      
-200.000000
      
711.000000
      
50.000000
      
637.000000
      
53.000000
      
1185.000000
      
700.000000
      
NaN
      
NaN
    
    

      
50%
      
1053.000000
      
-200.000000
      
895.000000
      
141.000000
      
794.000000
      
96.000000
      
1446.000000
      
942.000000
      
NaN
      
NaN
    
    

      
75%
      
1221.000000
      
-200.000000
      
1105.000000
      
284.000000
      
960.000000
      
133.000000
      
1662.000000
      
1255.000000
      
NaN
      
NaN
    
    

      
max
      
2040.000000
      
1189.000000
      
2214.000000
      
1479.000000
      
2683.000000
      
340.000000
      
2775.000000
      
2523.000000
      
NaN
      
NaN
    
  

In [13]:

    

df.columns


    

    
Out[13]:





Index(['Date', 'Time', 'CO(GT)', 'PT08.S1(CO)', 'NMHC(GT)', 'C6H6(GT)',
       'PT08.S2(NMHC)', 'NOx(GT)', 'PT08.S3(NOx)', 'NO2(GT)', 'PT08.S4(NO2)',
       'PT08.S5(O3)', 'T', 'RH', 'AH', 'Unnamed: 15', 'Unnamed: 16',
       'Timestamp'],
      dtype='object')

In [7]:

    

df["Date"]


    

    
Out[7]:





0       10/03/2004
1       10/03/2004
2       10/03/2004
3       10/03/2004
4       10/03/2004
           ...    
9352    04/04/2005
9353    04/04/2005
9354    04/04/2005
9355    04/04/2005
9356    04/04/2005
Name: Date, Length: 9357, dtype: object

In [8]:

    

df["Time"]


    

    
Out[8]:





0       18.00.00
1       19.00.00
2       20.00.00
3       21.00.00
4       22.00.00
          ...   
9352    10.00.00
9353    11.00.00
9354    12.00.00
9355    13.00.00
9356    14.00.00
Name: Time, Length: 9357, dtype: object

In [9]:

    

df["Timestamp"] = df["Date"].map(str) + " " + df["Time"]
df["Timestamp"] = pd.to_datetime(df["Timestamp"], format="%d/%m/%Y %H.%M.%S")


    

    




c:\users\mcama\appdata\local\programs\python\python36\lib\site-packages\ipykernel_launcher.py:1: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  """Entry point for launching an IPython kernel.
c:\users\mcama\appdata\local\programs\python\python36\lib\site-packages\ipykernel_launcher.py:2: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  

In [10]:

    

df["Timestamp"]


    

    
Out[10]:





0      2004-03-10 18:00:00
1      2004-03-10 19:00:00
2      2004-03-10 20:00:00
3      2004-03-10 21:00:00
4      2004-03-10 22:00:00
               ...        
9352   2005-04-04 10:00:00
9353   2005-04-04 11:00:00
9354   2005-04-04 12:00:00
9355   2005-04-04 13:00:00
9356   2005-04-04 14:00:00
Name: Timestamp, Length: 9357, dtype: datetime64[ns]

In [11]:

    

%matplotlib notebook

import matplotlib
import matplotlib.pyplot as plt
plt.rcParams['figure.figsize'] = [9.5, 6]


    

In [18]:

    

figure = plt.figure()

plt.plot(df["Timestamp"], df["RH"])


    

    















    












    
Out[18]:





[<matplotlib.lines.Line2D at 0x1cd0d3901d0>]

In [ ]:

    




    

In [ ]: