CODEWITHSUNDEEP
pythonnumpy
user9238790
user9238790

Reputation:

Print maximum value name as string

import sklearn
import sklearn.datasets
import sklearn.ensemble
import numpy as np
from treeinterpreter import treeinterpreter as ti


iris = sklearn.datasets.load_iris()

rf = sklearn.ensemble.RandomForestClassifier(n_estimators=500, random_state = 50 )
rf.fit(iris.data, iris.target)

instances =iris.data[100].reshape(1,-1)

prediction, biases, contributions = ti.predict(rf, instances)


for i in range(len(instances)):

    for c, feature in sorted(zip(contributions[i], 
                                 iris.feature_names), 
                             key=lambda x: ~abs(x[0].any())):

        print (feature, c)

I am trying to print the maximum value name in this list but I get True instead. Any ideas why and how to mitigate this?

You can copy/paste the code to run it in your environment

Update

I slightly modified the question to print the name of column of the maximum value, rather than the maximum value

The output is

Feature contributions:
--------------------
sepal length (cm) [-0.046 -0.01   0.057]
sepal width (cm) [-0. -0.  0.]
petal length (cm) [-0.136 -0.153  0.289]
petal width (cm) [-0.148 -0.171  0.319]

The output I am hoping for

petal width (cm)

Upvotes: 0

Views: 76

Answers (1)

Sevy
Sevy

Reputation: 698

You should be using c.max() instead c.all() if you want to get the max element of the array. This section of code should give you what you want:

maxFeatures = []
for i in range(len(instances)):
    maxList= 0
    maxFeature = ''
    for c, feature in sorted(zip(contributions[i], 
                             iris.feature_names), 
                         key=lambda x: ~abs(x[0].any())):
        if c.max()>maxList:
            maxList=c.max()
            maxFeature=feature
        print (feature, c)
    maxFeatures.append(maxFeature)
print( maxFeatures )

Upvotes: 1

Related Questions