Concat_and_MissingData-checkpoint.ipynb

Kernel: Python 3

import pandas as pd

df1 = pd.read_csv('NetAtmo_2016.csv', parse_dates = True,)

df2 = pd.read_csv('NetAtmo_2017.csv', parse_dates = True)

df1.head(1)

	Timestamp	Timezone : America/Los_Angeles	Temperature	Humidity	CO2	Noise	Pressure
0	1455917199	2/19/16 13:26	18.8	76	NaN	NaN	1015.7

df2.head(1)

	Timestamp	Time	Temperature	Humidity	CO2	Noise	Pressure
0	1483257658	1/1/17 0:00	21.8	34	482	39	1009.1

df1['Time'] = df1['Timezone : America/Los_Angeles']
df1.head(1)

	Timestamp	Timezone : America/Los_Angeles	Temperature	Humidity	CO2	Noise	Pressure	Time
0	1455917199	2/19/16 13:26	18.8	76	NaN	NaN	1015.7	2/19/16 13:26

df1.drop(df1.columns[[0,1,2,3,5,6]], axis =1, inplace = True)
df1.head(1)

	CO2	Time
0	NaN	2/19/16 13:26

df2.drop(df2.columns[[0,2,3,5,6]], axis =1, inplace = True)
df2.head(1)

	Time	CO2
0	1/1/17 0:00	482

#df1['Time'] = pd.to_datetime(df1.Time)

#df2['Time'] = pd.to_datetime(df2.Time)

df1.head(1)

	CO2	Time
0	NaN	2/19/16 13:26

df2.head(2)

	Time	CO2
0	1/1/17 0:00	482
1	1/1/17 0:05	491

#df1.set_index('Time', inplace = True)

#df2.set_index('Time', inplace = True)

df1.head(1)

	CO2	Time
0	NaN	2/19/16 13:26

df2.tail(1)

	Time	CO2
10847	2/12/17 18:47	480

df3 = pd.concat([df1,df2])

df3.head()

	CO2	Time
0	NaN	2/19/16 13:26
1	718.0	2/19/16 13:27
2	NaN	2/19/16 13:27
3	337.0	2/19/16 13:31
4	332.0	2/19/16 13:36

df3.tail()

	CO2	Time
10843	484.0	2/12/17 18:27
10844	486.0	2/12/17 18:32
10845	469.0	2/12/17 18:37
10846	485.0	2/12/17 18:42
10847	480.0	2/12/17 18:47

df3.dropna(how ='any', inplace = True)

df3.describe()

	CO2
count	100985.000000
mean	547.646878
std	304.511307
min	201.000000
25%	362.000000
50%	438.000000
75%	615.000000
max	2777.000000

df3.reset_index()

	index	CO2	Time
0	1	718.0	2/19/16 13:27
1	3	337.0	2/19/16 13:31
2	4	332.0	2/19/16 13:36
3	5	328.0	2/19/16 13:41
4	6	307.0	2/19/16 13:46
5	7	296.0	2/19/16 13:51
6	8	289.0	2/19/16 13:56
7	9	280.0	2/19/16 14:02
8	10	273.0	2/19/16 14:07
9	11	272.0	2/19/16 14:12
10	12	269.0	2/19/16 14:17
11	13	267.0	2/19/16 14:22
12	14	283.0	2/19/16 14:27
13	15	284.0	2/19/16 14:32
14	16	288.0	2/19/16 14:37
15	17	290.0	2/19/16 14:42
16	18	308.0	2/19/16 14:47
17	19	304.0	2/19/16 14:52
18	20	322.0	2/19/16 14:57
19	21	319.0	2/19/16 15:02
20	22	343.0	2/19/16 15:07
21	23	359.0	2/19/16 15:12
22	24	373.0	2/19/16 15:17
23	25	378.0	2/19/16 15:22
24	26	383.0	2/19/16 15:27
25	27	383.0	2/19/16 15:32
26	28	383.0	2/19/16 15:37
27	29	393.0	2/19/16 15:42
28	30	382.0	2/19/16 15:47
29	31	393.0	2/19/16 15:52
...	...	...	...
100955	10818	491.0	2/12/17 16:21
100956	10819	489.0	2/12/17 16:26
100957	10820	479.0	2/12/17 16:31
100958	10821	487.0	2/12/17 16:36
100959	10822	485.0	2/12/17 16:41
100960	10823	495.0	2/12/17 16:46
100961	10824	484.0	2/12/17 16:51
100962	10825	496.0	2/12/17 16:56
100963	10826	490.0	2/12/17 17:01
100964	10827	496.0	2/12/17 17:06
100965	10828	492.0	2/12/17 17:11
100966	10829	481.0	2/12/17 17:16
100967	10830	472.0	2/12/17 17:21
100968	10831	489.0	2/12/17 17:26
100969	10832	490.0	2/12/17 17:31
100970	10833	492.0	2/12/17 17:36
100971	10834	482.0	2/12/17 17:41
100972	10835	475.0	2/12/17 17:46
100973	10836	484.0	2/12/17 17:51
100974	10837	485.0	2/12/17 17:56
100975	10838	493.0	2/12/17 18:02
100976	10839	478.0	2/12/17 18:07
100977	10840	470.0	2/12/17 18:12
100978	10841	485.0	2/12/17 18:17
100979	10842	479.0	2/12/17 18:22
100980	10843	484.0	2/12/17 18:27
100981	10844	486.0	2/12/17 18:32
100982	10845	469.0	2/12/17 18:37
100983	10846	485.0	2/12/17 18:42
100984	10847	480.0	2/12/17 18:47

100985 rows × 3 columns

df3.to_csv('InfiltrationCleanedData.csv')