Differences between revisions 4 and 7 (spanning 3 versions)

Pandas

Indexed arrays
DateFrame
DateRange
Indexing, slicing
Apply common numpy statistics
Data alignment

   1 import numpy as np
   2 import pandas as p
   3 import Nio
   4 
   5 
   6 nc1 = Nio.open_file('10147-precip.nc') # hamburg
   7 nc2 = Nio.open_file('10015-precip.nc') # helgoland
   8 
   9 time1 = nc1.variables['time'][:]
  10 time2 = nc2.variables['time'][:]
  11 
  12 rain1 = nc1.variables['rainfall_rate_hour'][:]
  13 rain2 = nc2.variables['rainfall_rate_hour'][:]
  14 
  15 
  16 # plot data 
  17 plot(rain1, 'g', rain2, 'b')
  18 
  19 # Timestamps shall be python dates
  20 dates1 = num2date(epoch2num(time1))
  21 dates2 = num2date(epoch2num(time2))
  22 
  23 # Indexed arrays - p.Series
  24 ds1 = p.Series(rain1, index = dates1)
  25 ds2 = p.Series(rain2, index = dates2)
  26 
  27 # Pandas is using numpy.na representation of not-a-number,
  28 # while Nio returns masked arrays
  29 # Many basic array operations are valid for pandas Series
  30 ds1 = np.where(ds1<0, nan, ds1)
  31 ds2 = np.where(ds2<0, nan, ds2)
  32 
  33 # plotting functions
  34 ds1.plot()
  35 ds2.plot()

LehreWiki: PythonCourse/PythonLES/Pandas (last edited 2012-11-05 10:53:39 by anonymous)

-  ⇤ ← Revision 4 as of 2012-10-24 15:16:15 → 
  Size: 507
  Editor: MikhailItkin
  Comment:
+   ← Revision 7 as of 2012-10-24 16:29:35 → ⇥
  Size: 1025
  Editor: MikhailItkin
  Comment:
-Deletions are marked like this.
+Additions are marked like this.
 Line 3:
- * Series
-Line 7:
+Line 6:
+ * Apply common numpy statistics
 Line 12:
-import pandas as P
+import pandas as p
 Line 15:
-hamNc = Nio.open_file('10147-precip.nc')
helNc = Nio.open_file('10015-precip.nc')
-Line 18:
+Line 16:
-hamTime = hamNc.variables['time'][:]
helTime = helNc.variables['time'][:]
+nc1 = Nio.open_file('10147-precip.nc') # hamburg
nc2 = Nio.open_file('10015-precip.nc') # helgoland
-Line 21:
+Line 19:
-hamRain = hamNc.variables['rainfall_rate_hour'][:]
helRain = helNc.variables['rainfall_rate_hour'][:]
ham = hamNc.variables['rainfall_rain_rate'][:]
+time1 = nc1.variables['time'][:]
time2 = nc2.variables['time'][:]

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)

# plotting functions
ds1.plot()
ds2.plot()