import pandas as pd
from datetime import datetime
import scipy.stats as sts

def parse(yr, mon):
    date = datetime(year=int(yr), day=2, month=int(mon))
    return date

url='http://www.cpc.ncep.noaa.gov/data/indices/sstoi.indices'

data = pd.read_table(url, sep=' ', header=0, skiprows=0, parse_dates = [['YR', 'MON']], skipinitialspace=True, index_col=0, date_parser=parse)                     
print data.describe
print '\n'
print data.index

grouped = data.groupby(lambda x: x.year)
grouped

zscore = lambda x: (x - x.mean()) / x.std()
transformed = grouped.transform(zscore)
print transformed['ANOM.3']

npdata = np.genfromtxt(url, skip_header=1)
unique_enso_year = [int(value) for value in set(npdata[:, 0])]
nin34 = np.zeros(len(unique_enso_year))
for ind, year in enumerate(unique_enso_year):
    indexes = np.flatnonzero(npdata[:, 0]==year)
    if len(indexes) == 12:
        nin34[ind] = np.mean(npdata[indexes, 9])
    else:
        nin34[ind] = np.nan

nin34x = (nin34 - sts.nanmean(nin34)) / sts.nanstd(nin34)
nin34y = np.vstack((unique_enso_year, nin34x))
nin34y

attempt_cheating = (grouped.mean()['ANOM.3'][:-1] - sts.nanmean(grouped.mean()['ANOM.3'][:-1])) / sts.nanstd(grouped.mean()['ANOM.3'][:-1])

attempt_cheating - nin34x[:-1]

grouped2 = data.groupby(lambda x: x.year).apply(lambda sdf: sdf if len(sdf) > 11 else None).reset_index(drop=True)
print grouped2
print '\n'
print grouped2.index

(grouped.mean()['ANOM.3'][:-1] - sts.nanmean(grouped.mean()['ANOM.3'][:-1])) / sts.nanstd(grouped.mean()['ANOM.3'][:-1])

gist = !jist -p test.ipynb
nbviewer = gist[0].replace('https://gist.github.com/','http://nbviewer.ipython.org/')
print nbviewer