How to pass multiple parameters to map function in panda

Question

I have the following data file

mn = pd.DataFrame({'fld1': [2.23, 4.45, 7.87, 9.02, 8.85, 3.32, 5.55],'fld2': [125000, 350000,700000, 800000, 200000, 600000, 500000],'lType': ['typ1','typ2','typ3','typ1','typ3','typ1','typ2'], 'counter': [100,200,300,400,500,600,700]})

Display function

def getTag(rangeAttribute):
    sliceDef = {'tag1': [1, 4], 'tag2': [4, 6], 'tag3': [6, 9],
                'tag4': [9, 99]}
    for sl in sliceDef.keys():
        bounds = sliceDef[sl]
        if ((float(rangeAttribute) >= float(bounds[0]))
            and (float(rangeAttribute) <= float(bounds[1]))):
            return sl


def getTag1(rangeAttribute):
    sliceDef = {'100-150': [100000, 150000],
                '150-650': [150000, 650000],
                '650-5M': [650000, 5000000]}
    for sl in sliceDef.keys():
        bounds = sliceDef[sl]
        if ((float(rangeAttribute) >= float(bounds[0]))
            and (float(rangeAttribute) <= float(bounds[1]))):
            return sl

I want to calculate the sum based on tags for fld1 and fld2. Currently, I have to write different functions with hard-coded values ​​for different types of fields. The MAP function takes only 1 argument. Is there a function other than MAP that can also take sliceDef as an input parameter.

mn.groupby([mn['fld1'].map(getTag),mn['fld2'].map(getTag1),'lType'] ).sum()

Answer 1

Instead of using a map, you can use pd.cut (thanks to DSM and Jeff for pointing this out):

import numpy as np
import pandas as pd

mn = pd.DataFrame(
    {'fld1': [2.23, 4.45, 7.87, 9.02, 8.85, 3.32, 5.55],
     'fld2': [125000, 350000, 700000, 800000, 200000, 600000, 500000],
     'lType': ['typ1', 'typ2', 'typ3', 'typ1', 'typ3', 'typ1', 'typ2'],
     'counter': [100, 200, 300, 400, 500, 600, 700]})

result = mn.groupby(
    [pd.cut(mn['fld1'], [1,4,6,9,99], labels=['tag1', 'tag2', 'tag3', 'tag4']),
     pd.cut(mn['fld2'], [100000, 150000, 650000, 5000000],
            labels=['100-150', '150-650', '650-5M']),
     'lType']).sum()

print(result)

gives

                    counter   fld1    fld2
             lType                        
tag1 100-150 typ1       100   2.23  125000
     150-650 typ1       600   3.32  600000
tag2 150-650 typ2       900  10.00  850000
tag3 150-650 typ3       500   8.85  200000
     650-5M  typ3       300   7.87  700000
tag4 650-5M  typ1       400   9.02  800000

, getTag getTag1 . pd.cut np.searchsorted, ( , searchsorted O (log n) , C O (n), Python).

---

: , sliceDef.keys(), - . ( , Python3). :

    if ((float(rangeAttribute) >= float(bounds[0]))
        and (float(rangeAttribute) <= float(bounds[1]))):

, , rangeAttribute bounds.

, .

pd.cut , , .

---

: , - ( Andy Hayden):

import numpy as np
import pandas as pd

def getTag(rangeAttribute, sliceDef):
    for sl in sliceDef.keys():
        bounds = sliceDef[sl]
        if ((float(rangeAttribute) >= float(bounds[0]))
            and (float(rangeAttribute) <= float(bounds[1]))):
            return sl

sliceDef = {'tag1': [1, 4], 'tag2': [4, 6], 'tag3': [6, 9],
            'tag4': [9, 99]}
sliceDef1 = {'100-150': [100000, 150000],
            '150-650': [150000, 650000],
            '650-5M': [650000, 5000000]}

mn = pd.DataFrame(
    {'fld1': [2.23, 4.45, 7.87, 9.02, 8.85, 3.32, 5.55],
     'fld2': [125000, 350000, 700000, 800000, 200000, 600000, 500000],
     'lType': ['typ1', 'typ2', 'typ3', 'typ1', 'typ3', 'typ1', 'typ2'],
     'counter': [100, 200, 300, 400, 500, 600, 700]})

result = mn.groupby([mn['fld1'].apply(getTag, args=(sliceDef, ))
                     ,mn['fld2'].apply(getTag, args=(sliceDef1, )),
                     'lType'] ).sum()
print(result)

, apply , pd.cut , . , apply , .

---