import numpy as np
import pandas as pd
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
from sklearn.feature_selection import SelectFromModel
from scipy.io import arff
data = arff.loadarff("C:\\Users\\manib\\Desktop\\Python Job\\Project Work\\Breast\\Breast.arff")
df = pd.DataFrame(data[0])
df.head()
df["Class"].value_counts()
X = df.iloc[:,:24481].values
y = df.iloc[:, -1].values
from sklearn import preprocessing
label_encoder = preprocessing.LabelEncoder()
y=y.astype('str')
y= label_encoder.fit_transform(y)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4, random_state=0)
sel = SelectFromModel(RandomForestClassifier(n_estimators = 100))
sel.fit(X_train, y_train)
sel.get_support()
selected_feat= X_train.columns[(sel.get_support())]
len(selected_feat)
print(selected_feat)
$\begingroup$
$\endgroup$
Add a comment
|
2 Answers
$\begingroup$
$\endgroup$
The problem is that train_test_split(X, y, ...) returns numpy arrays and not pandas dataframes. Numpy arrays have no attribute named columns
If you want to see what features SelectFromModel kept, you need to substitute X_train (which is a numpy.array) with X which is a pandas.DataFrame.
selected_feat= X.columns[(sel.get_support())]
This will return a list of the columns kept by the feature selector.
If you wanted to see how many features were kept you can just run this:
sel.get_support().sum() # by default this will count 'True' as 1 and 'False' as 0
$\begingroup$
$\endgroup$
because this :
X = df.iloc[:,:24481].values
y = df.iloc[:, -1].values
you should remove .values or make extra X_col, y_col like that
X_col = df.iloc[:,:24481]
y_col = df.iloc[:, -1]
