import pandas as pd
import numpy as np
url='http://www.cdc.noaa.gov/Correlation/amon.us.long.data'
ts_raw = pd.read_table(url, sep=' ', skiprows=1, names=['year','jan','feb','mar','apr','may','jun','jul','aug','sep','oct','nov','dec'], skipinitialspace=True, parse_dates=True, skipfooter=4, index_col=0)
ts_raw.replace(-9.99900000e+01, np.NAN, inplace=True)
url='http://www.cdc.noaa.gov/Correlation/amon.us.long.data'
data = np.genfromtxt(url, skip_header=1, skip_footer=4)
nan_index = np.where(data[:]==-9.99900000e+01)
for i in range(len(nan_index[0])):
data[nan_index[0][i], nan_index[1][i]] = np.nan
in_amo = np.mean(data[:, 1:], axis=1)
print ts_raw.values.shape
ts_raw.values
(158, 12)
array([[ 0.22 , 0.153, 0.225, ..., 0.126, 0.137, 0.231], [ 0.216, -0.057, -0.073, ..., -0.132, -0.166, -0.281], [-0.219, -0.312, -0.068, ..., 0.15 , 0.277, 0.124], ..., [ 0.174, 0.136, 0.084, ..., 0.095, -0.043, -0.018], [-0.039, 0.03 , 0.05 , ..., 0.373, 0.208, 0.174], [ 0.157, 0.146, 0.187, ..., nan, nan, nan]])
print data[:, 1:].shape
data[:, 1:]
(158, 12)
array([[ 0.22 , 0.153, 0.224, ..., 0.126, 0.136, 0.23 ], [ 0.216, -0.058, -0.073, ..., -0.132, -0.167, -0.281], [-0.219, -0.312, -0.069, ..., 0.15 , 0.277, 0.124], ..., [ 0.175, 0.137, 0.085, ..., 0.096, -0.042, -0.017], [-0.039, 0.03 , 0.051, ..., 0.374, 0.209, 0.175], [ 0.158, 0.146, 0.188, ..., nan, nan, nan]])
ts_raw.values - data[:, 1:]
array([[ 0.00000000e+00, 0.00000000e+00, 1.00000000e-03, ..., 0.00000000e+00, 1.00000000e-03, 1.00000000e-03], [ 2.77555756e-17, 1.00000000e-03, 0.00000000e+00, ..., 0.00000000e+00, 1.00000000e-03, 0.00000000e+00], [ 2.77555756e-17, 0.00000000e+00, 1.00000000e-03, ..., 0.00000000e+00, -5.55111512e-17, 0.00000000e+00], ..., [ -1.00000000e-03, -1.00000000e-03, -1.00000000e-03, ..., -1.00000000e-03, -1.00000000e-03, -1.00000000e-03], [ 0.00000000e+00, 0.00000000e+00, -1.00000000e-03, ..., -1.00000000e-03, -1.00000000e-03, -1.00000000e-03], [ -1.00000000e-03, 0.00000000e+00, -1.00000000e-03, ..., nan, nan, nan]])