Tweak NYC (non-mutating)

gistfile1.py

def  tweak_nyc(raw):
    def clean_col(val):
        return val.strip().replace(' ', '_')
    return (raw
            .rename(columns=clean_col)
            .assign(PrecipitationIn=pd.to_numeric(
                raw.PrecipitationIn.replace('T', '0.001')),
                   Events=raw[' Events'].fillna(''),
                   )
            .assign(PrecipitationCM=lambda df_:df_.PrecipitationIn*2.54)
           )
nyc2 = tweak_nyc(nyc)

names = '''obs
year
month
day
date
latitude
longitude
zon.winds
mer.winds
humidity
air temp.
s.s.temp.'''.split('\n')

nino = pd.read_csv('data/tao-all2.dat.gz', sep=' ', names=names, na_values='.', 
                   parse_dates=[[1,2,3]])

def clean_nino_col(col):
    return col.rstrip('.').replace('.', '_').replace(' ', '_')

def tweak_nino(raw):
    return (raw
        .rename(columns=clean_nino_col)
        .assign(air_temp_F=lambda df_:df_.air_temp *9/5+32,
                zon_winds_mph=lambda df_:df_.zon_winds*2.237,
                mer_winds_mph=lambda df_:df_.mer_winds*2.237,
                date=pd.to_datetime(raw.date, format='%y%m%d')
               )
        .drop(columns='obs')
        )
nino = tweak_nino(nino)#.dtypes