Dynamic pandas frame filtering

Question

I am trying to filter a pandas data frame using threshold values ​​for three columns

import pandas as pd
df = pd.DataFrame({"A" : [6, 2, 10, -5, 3],
                   "B" : [2, 5, 3, 2, 6],
                   "C" : [-5, 2, 1, 8, 2]})
df = df.loc[(df.A > 0) & (df.B > 2) & (df.C > -1)].reset_index(drop = True)

df
    A  B  C
0   2  5  2
1  10  3  1
2   3  6  2

However, I want to do this inside a function where the column names and their threshold values ​​are given to me in the dictionary. Here is my first attempt, which works fine. Essentially, I put a filter inside a variable condand just run it:

df = pd.DataFrame({"A" : [6, 2, 10, -5, 3],
                   "B" : [2, 5, 3, 2, 6],
                   "C" : [-5, 2, 1, 8, 2]})
limits_dic = {"A" : 0, "B" : 2, "C" : -1}
cond = "df = df.loc["
for key in limits_dic.keys():
    cond += "(df." + key + " > " + str(limits_dic[key])+ ") & "
cond = cond[:-2] + "].reset_index(drop = True)"
exec(cond)
df
    A  B  C
0   2  5  2
1  10  3  1
2   3  6  2

Now, finally, I put everything inside the function and stops working (maybe the function execdoes not like to be used inside the function!):

df = pd.DataFrame({"A" : [6, 2, 10, -5, 3],
                   "B" : [2, 5, 3, 2, 6],
                   "C" : [-5, 2, 1, 8, 2]})
limits_dic = {"A" : 0, "B" : 2, "C" : -1}
def filtering(df, limits_dic):
    cond = "df = df.loc["
    for key in limits_dic.keys():
        cond += "(df." + key + " > " + str(limits_dic[key])+ ") & "
    cond = cond[:-2] + "].reset_index(drop = True)"
    exec(cond)
    return(df)

df = filtering(df, limits_dic)
df
    A  B  C
0   6  2 -5
1   2  5  2
2  10  3  1
3  -5  2  8
4   3  6  2

, exec -, , , . , , : 1) df 2) limits_dic = {"A" : 0, "B" : 2, "C" : -1}. .

Answer 1

, . , str.join:

query = ' & '.join(['{}>{}'.format(k, v) for k, v in limits_dic.items()])

, f -strings python-3. 6+,

query = ' & '.join([f'{k}>{v}' for k, v in limits_dic.items()])

print(query)

'A>0 & C>-1 & B>2'

df.query, :

out = df.query(query)
print(out)

    A  B  C
1   2  5  2
2  10  3  1
4   3  6  2

---

df.eval, , :

mask = df.eval(query)
print(mask)

0    False
1     True
2     True
3    False
4     True
dtype: bool

out = df[mask]
print(out)

    A  B  C
1   2  5  2
2  10  3  1
4   3  6  2

---

, , .

( ):

df = pd.DataFrame({'gender':list('MMMFFF'),
                   'height':[4,5,4,5,5,4],
                   'age':[70,80,90,40,2,3]})

print (df)
  gender  height  age
0      M       4   70
1      M       5   80
2      M       4   90
3      F       5   40
4      F       5    2
5      F       4    3

, :

column = ['height', 'age', 'gender']
equal = ['>', '>', '==']
condition = [1.68, 20, 'F']

:

query = ' & '.join(f'{i} {j} {repr(k)}' for i, j, k in zip(column, equal, condition))
df.query(query)

   age gender  height
3   40      F       5

---

pd.eval(), . pd.eval().

Answer 2

@coldspeed:

conditions = None
for key, val in limit_dic.items():
    cond = df[key] > val
    if conditions is None:
        conditions = cond
    else:
        conditions = conditions & cond
print(df[conditions])

Answer 3

An alternative to both published, which may or may not be more pythonic:

import pandas as pd
import operator
from functools import reduce

df = pd.DataFrame({"A": [6, 2, 10, -5, 3],
                   "B": [2, 5, 3, 2, 6],
                   "C": [-5, 2, 1, 8, 2]})

limits_dic = {"A": 0, "B": 2, "C": -1}

# equiv to [df['A'] > 0, df['B'] > 2 ...]
loc_elements = [df[key] > val for key, val in limits_dic.items()]

df = df.loc[reduce(operator.and_, loc_elements)]

Run code