CODEWITHSUNDEEP
pythonscikit-learn
Anderson
Anderson

Reputation: 1

The problem of feature selection in sklearn dataset

I'm a beginner.I am now writing a feature selection algorithm under sklearn, and I wrote a simple program to try it out. The goal is to take out certain columns in the dataset, but the result is an error. The following is the code and error message. Please help me,Thank you.What should i do?

import numpy as np
from sklearn.datasets import load_iris
data = load_iris()
data=np.array(data)
print(data[:,[0,1]]) #Take the first two columns of the dataset and print

error message:

Traceback (most recent call last):
  File "K:/b/f_s_DF.py", line 6, in <module>
    print(data[:,[0,1]])#Take the first two columns of the dataset and print
IndexError: too many indices for array: array is 0-dimensional, but 2 were indexed

Upvotes: 0

Views: 98

Answers (2)

Subbu VidyaSekar
Subbu VidyaSekar

Reputation: 2615

First thing, you need to change the iris type <class 'sklearn.utils.Bunch'> to pandas dataframe. then numpy ndarray

import numpy as np
from sklearn.datasets import load_iris
iris = load_iris()
data1 = np.array(pd.DataFrame(data= np.c_[iris['data'], iris['target']],
                     columns= iris['feature_names'] + ['target']))
print(data1[:,:2])

while getting the value from ndarray, no need to give the index like 1,2. you can give :2.

Upvotes: 1

Tarequzzaman Khan
Tarequzzaman Khan

Reputation: 494

Rather than converting Numpy.ndarray You con convert these data on pandas Dataframe and Easily see the Fist two or any Column. Please check out the below code:


import pandas as pd
from sklearn.datasets import load_iris
data = load_iris()
datasets = pd.DataFrame(data['data'], columns = 
           data['feature_names'])
target_val = pd.Series(data['target'], name = 
            'target_values')
datasets['target'] = target_val
datasets[:2]

Output:


    sepal length      sepal width   petal length    petal width  target
0      5.1                3.5            1.4             0.2       0
1      4.9                3.0            1.4             0.2       0

Upvotes: 0

Related Questions