We can say the filter method is just for filtering a large set of features and not the most reliable? However, the two other methods don’t have same top three features? Are some methods more reliable than others? Or does this come down to domain knowledge? Univariate is filter method and I believe the RFE and Feature Importance are both wrapper methods.Īll three selector have listed three important features. Number of pregnancy, weight(bmi), and Diabetes pedigree test. RFE chose the top 3 features as preg, mass, and pedi. Glucose tolerance test, weight(bmi), and age)
The score suggests the three important features are plas, mass, and age. When using Feature Importance using ExtraTreesClassifier (glucose tolerance test, insulin test, age)Ģ. Plas, test, and age as three important features. When using Univariate with k=3 chisquare you get I noticed that when you use three feature selectors: Univariate Selection, Feature Importance and RFE you get different result for three important features.ġ. #print(“Feature Ranking: %s”) % fit.ranking_ĩ print(“Num Features: %d”) % fit.n_features_ġ0 print(“Selected Features: %s”) % fit.support_ #print(“Selected Features: %s”) % fit.support_ #print(“Num Features: %d”) % fit.n_features_ ValueError: could not convert string to float: ‘no’įrom sklearn.feature_selection import RFEįrom sklearn.linear_model import LogisticRegressionĭata = read_csv(‘C:\\Users\\abc\\Downloads\\xyz\\api.csv’,names = ) –> 433 array = np.array(array, dtype=dtype, order=order, copy=copy) ~\Anaconda3\lib\site-packages\sklearn\utils\validation.py in check_array(array, accept_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, ensure_min_samples, ensure_min_features, warn_on_dtype, estimator) –> 573 ensure_min_features, warn_on_dtype, estimator)ĥ75 y = check_array(y, ‘csr’, force_all_finite=True, ensure_2d=False, ~\Anaconda3\lib\site-packages\sklearn\utils\validation.py in check_X_y(X, y, accept_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, multi_output, ensure_min_samples, ensure_min_features, y_numeric, warn_on_dtype, estimator)ĥ71 X = check_array(X, accept_sparse, dtype, order, copy, force_all_finite,ĥ72 ensure_2d, allow_nd, ensure_min_samples, ~\Anaconda3\lib\site-packages\sklearn\feature_selection\univariate_selection.py in fit(self, X, y) ValueError Traceback (most recent call last) I am doing simple classification but there is coming an issue But when I try to do the same for both biomarkers I get the same result in all the combinations of my 6 biomarkers. Print(metrics.accuracy_score(y_test, y_pred)) #predicting response variables corresponding to test data Knn = KNeighborsClassifier(n_neighbors=1) X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=5)įrom sklearn.neighbors import KNeighborsClassifier # use train/test split with different random_state values This is what I have done for the best and worst predictors:
#DRAW WATSON ANALYZER WITH GOOGLE CHARTS STACK OVERFLOW HOW TO#
That is my problem: I don’t know how to calculate which are the two best predictors. In our research, we want to determine the best biomarker and the worst, but also the synergic effect that would have the use of two biomarkers. The bioinformatic method I am using is very simple but we are trying to predict metastasis with some protein data. I am a biochemistry student in Spain and I am on a project about predictive biomarkers in cancer. We will select the 4 best features using this method in the example below. This can be used via the f_classif() function. For example the ANOVA F-value method is appropriate for numerical inputs and categorical data, as we see in the Pima dataset. Many different statistical test scan be used with this selection method. The scikit-learn library provides the SelectKBest class that can be used with a suite of different statistical tests to select a specific number of features.
Statistical tests can be used to select those features that have the strongest relationship with the output variable. This is a binary classification problem where all of the attributes are numeric. Recipes uses the Pima Indians onset of diabetes dataset to demonstrate the feature selection method. This post contains recipes for feature selection methods.Įach recipe was designed to be complete and standalone so that you can copy-and-paste it directly into you project and use it immediately. This section lists 4 feature selection recipes for machine learning in Python
0 kommentar(er)
