read_cabrillo

import pandas as pd


from dataclasses import dataclass
@dataclass
class CabRecord:
    freq:float
    mode: str
    when:str
    mycall:str
    myrst:str
    myexch:str
    dxcall:str
    dxrst:str
    dxexch:str
    txnum:int



def read_cab(filename):
    with open(filename,'rt') as ifp:
        data=ifp.read().split('\n')

    return data

def only_qso(data):
    qso_data=[a for a in data if a.startswith('QSO')]
    return qso_data

def make_records(qso_data):

    """                            --------info sent------- -------info rcvd--------
    QSO: freq  mo date       time call          rst exch   call          rst exch   t
    QSO: ***** ** yyyy-mm-dd nnnn ************* nnn ****** ************* nnn ****** n
    QSO:  3799 PH 1999-03-06 0711 HC8N          59  001    W1AW          59  001    0
    000000000111111111122222222223333333333444444444455555555556666666666777777777788
    123456789012345678901234567890123456789012345678901234567890123456789012345678901
    """
    fields=[(5,10),
                 (11,13),
                 (14,29),
                 (30,43),
                 (44,46),
                 (48,54),
                 (55,68),
                 (69,72),
                 (73,79),
                 (80,81)]
    recs=[]

    for n in qso_data:
        parts = [n[f[0]:f[1]].strip() for f in fields] 
        #self.data.append(parts)
        recs.append(CabRecord(*parts))
    return recs

records=make_records(only_qso(read_cab("2022 ARRL International DX Contest CW.cbr")))


df=pd.DataFrame(records)

df.head()

from ham.dxcc import DxccAll
from ham.band import HamBand

# Make freq a float
df['freq'] = df.freq.apply(lambda x: float('0'+x))

#create my dx object from my DxccAll
dx=DxccAll()

def get_country(call):
    fnd = dx.find(call)
    if fnd and fnd.Country_Name:
        return fnd.Country_Name
    else:
        return ""

# No point in this - as it was an ARRL Contest :) ... but just to check
df['Country']=df.dxcall.apply(lambda x: get_country(x))

df.head(10)

df['State']=df.dxexch.    #Use their Exchange as the State
df.groupby(by=['State']).agg({'dxexch':'count'},as_index=False).sort_values(['dxexch'],ascending=False)[:5]

#Just alter the Value sort
df.groupby(by=['State']).agg({'dxexch':'count'},as_index=False).sort_values(['dxexch'],ascending=True)[:5]