|
Size: 498
Comment:
|
Size: 1456
Comment:
|
| Deletions are marked like this. | Additions are marked like this. |
| Line 3: | Line 3: |
| * Series | |
| Line 7: | Line 6: |
| * Apply common numpy statistics | |
| Line 12: | Line 12: |
| import pandas as P | import pandas as p |
| Line 15: | Line 15: |
| hamNc = Nio.open_file('10147-precip.nc') helNc = Nio.open_file('10015-precip.nc') |
nc1 = Nio.open_file('10147-precip.nc') # hamburg nc2 = Nio.open_file('10015-precip.nc') # helgoland |
| Line 18: | Line 18: |
| hamTime = hamNc.variables['time'][:] helTime = helNc.variables['time'][:] |
time1 = nc1.variables['time'][:] time2 = nc2.variables['time'][:] |
| Line 21: | Line 21: |
| hamRain = hamNc.variables['rainfall_rain_rate'][:] helRain = helNc.variables['rainfall_rain_rate'][:] ham = hamNc.variables['rainfall_rain_rate'][:] |
rain1 = nc1.variables['rainfall_rate_hour'][:] rain2 = nc2.variables['rainfall_rate_hour'][:] # plot data # plot(rain1, 'g', rain2, 'b') # Timestamps shall be python dates dates1 = num2date(epoch2num(time1)) dates2 = num2date(epoch2num(time2)) # Indexed arrays - p.Series ds1 = p.Series(rain1, index = dates1) ds2 = p.Series(rain2, index = dates2) # Pandas is using numpy.na representation of not-a-number, # while Nio returns masked arrays # Many basic array operations are valid for pandas Series ds1 = np.where(ds1<0, nan, ds1) ds2 = np.where(ds2<0, nan, ds2) # built-in plotting functions ds1.plot() ds2.plot() # newer pandas version can drop NaN's, # current one can only fill, # otherwise drop by hand (hint: nan is not equal to nan :) ds1=ds1[ds1==ds1] ds2=ds2[ds2==ds2] # now we have series of different length print ds1.shape[0], ds2.shape[0] # to get the equal index it's possible to use from # one of the series ds2_nan = ds2.reindex(ds1.index) ds2_backfill = ds2.reindex(ds1.index, method = 'backfill') }}} |
Pandas
1 import numpy as np
2 import pandas as p
3 import Nio
4
5 nc1 = Nio.open_file('10147-precip.nc') # hamburg
6 nc2 = Nio.open_file('10015-precip.nc') # helgoland
7
8 time1 = nc1.variables['time'][:]
9 time2 = nc2.variables['time'][:]
10
11 rain1 = nc1.variables['rainfall_rate_hour'][:]
12 rain2 = nc2.variables['rainfall_rate_hour'][:]
13
14
15 # plot data
16 # plot(rain1, 'g', rain2, 'b')
17
18 # Timestamps shall be python dates
19 dates1 = num2date(epoch2num(time1))
20 dates2 = num2date(epoch2num(time2))
21
22 # Indexed arrays - p.Series
23 ds1 = p.Series(rain1, index = dates1)
24 ds2 = p.Series(rain2, index = dates2)
25
26 # Pandas is using numpy.na representation of not-a-number,
27 # while Nio returns masked arrays
28 # Many basic array operations are valid for pandas Series
29 ds1 = np.where(ds1<0, nan, ds1)
30 ds2 = np.where(ds2<0, nan, ds2)
31
32 # built-in plotting functions
33 ds1.plot()
34 ds2.plot()
35
36 # newer pandas version can drop NaN's,
37 # current one can only fill,
38 # otherwise drop by hand (hint: nan is not equal to nan :)
39 ds1=ds1[ds1==ds1]
40 ds2=ds2[ds2==ds2]
41
42 # now we have series of different length
43 print ds1.shape[0], ds2.shape[0]
44
45 # to get the equal index it's possible to use from
46 # one of the series
47 ds2_nan = ds2.reindex(ds1.index)
48 ds2_backfill = ds2.reindex(ds1.index, method = 'backfill')