CODEWITHSUNDEEP
algorithmmachine-learningtargetsupervised-learning
Kratos
Kratos

Reputation: 1114

Getting two target values from prediction algorithms

I have a dataset with sequence tuples and targets like the following:

       input_0  input_1 input_2 output
0        0       1.0    2.0      4.0
1        1       2.0    4.0      2.0
2        2       4.0    2.0      4.0
3        4       2.0    4.0      7.0
4        2       4.0    7.0      8.0

I have trained algorithms using the output as a target value.

What I want though, is to get the two most possible variables that can occur by one tupple.

For example if i have two tuples for training: a,b,c,d and a,b,c,e I want to get d and e as a result with the respective percentage.

Is there something like that possible?

Upvotes: 1

Views: 208

Answers (1)

Ami Tavory
Ami Tavory

Reputation: 76376

From your comments, this seems to be a pandas.DataFrame. Say you start with

from collections import Counter

df = pd.DataFrame({
    'input_0': [1, 1, 2, 4, 2], 
    'input_1': [1, 1, 2, 4, 4], 
    'input_2': [2, 2, 2, 4, 7],
    'output': [4, 3, 4, 7, 8]})
>>> df
    input_0 input_1 input_2 output
0   1   1   2   4
1   1   1   2   3
2   2   2   2   4
3   4   4   4   7
4   2   4   7   8

Then the following will show the two most common elements per each input tuple, as well as their counts:

>>> df.output.groupby([df.input_0, df.input_1, df.input_2]).apply(lambda s: Counter(s).most_common(2)).reset_index()
    input_0 input_1 input_2 output
0   1   1   2   [(3, 1), (4, 1)]
1   2   2   2   [(4, 1)]
2   2   4   7   [(8, 1)]
3   4   4   4   [(7, 1)]

Upvotes: 1

Related Questions