Python SelectFpr.transform方法代码示例

# 需要导入模块: from sklearn.feature_selection import SelectFpr [as 别名]
# 或者: from sklearn.feature_selection.SelectFpr import transform [as 别名]
def multisplit(skf,X,y,stepsize=1000):
    total_score = 0
    for train_index, test_index in skf:
        wl = []
        pred1 = np.matrix([])
        # Training
        for x in range(0, len(X[0]), stepsize):
            clf1 = plib.classif(X[train_index, x:x + stepsize], y[train_index])
            tmp_p = np.matrix(clf1.decision_function(X[train_index, x:x + stepsize]))
            if pred1.size == 0:
                pred1 = tmp_p
            else:
                pred1 = np.concatenate((pred1, tmp_p), axis=1)
            wl.append(clf1)
        #selectf = SelectKBest(f_classif, k=5).fit(pred1, y[train_index])
        selectf = SelectFpr().fit(pred1, y[train_index])
        clf3 = AdaBoostClassifier(n_estimators=100)
        #clf3 = svm.SVC(class_weight='auto')
        #clf3 = RandomForestClassifier(n_estimators=20)
        clf3.fit(selectf.transform(pred1), y[train_index])
        # Testing
        predtest = np.matrix([])
        k = 0
        for x in range(0, len(X[0]), stepsize):
            tmp_p = np.matrix(wl[k].decision_function(X[test_index, x:x + stepsize]))
            if predtest.size == 0:
                predtest = tmp_p
            else:
                predtest = np.concatenate((predtest, tmp_p), axis=1)
            k += 1
        # Final prediction
        predfinal = clf3.predict(selectf.transform(predtest))
        print "Target     : ", y[test_index]
        print "Prediction : ", predfinal
        matchs = np.equal(predfinal, y[test_index])
        score = np.divide(np.sum(matchs), np.float64(matchs.size))
        total_score = score + total_score
    return np.divide(total_score, skf.n_folds)

# 需要导入模块: from sklearn.feature_selection import SelectFpr [as 别名]
# 或者: from sklearn.feature_selection.SelectFpr import transform [as 别名]
def train_decisiontree_FPR(configurationname, train_data, score_function, undersam=False, oversam=False, export=False):
    print("Training with configuration " + configurationname)
    X_train, y_train, id_to_a_train = train_data
    dtc = DecisionTreeClassifier(random_state=0)

    print("Feature Selection")
    # selector = SelectFpr(score_function)
    selector = SelectFpr(score_function)
    result = selector.fit(X_train, y_train)
    X_train = selector.transform(X_train)

    fitted_ids = [i for i in result.get_support(indices=True)]

    print("Apply Resampling")
    print(Counter(y_train))
    if undersam and not oversam:
        renn = RepeatedEditedNearestNeighbours()
        X_train, y_train = renn.fit_resample(X_train, y_train)
    if oversam and not undersam:
        # feature_indices_array = list(range(len(f_to_id)))
        # smote_nc = SMOTENC(categorical_features=feature_indices_array, random_state=0)
        # X_train, y_train = smote_nc.fit_resample(X_train, y_train)
        sm = SMOTE(random_state=42)
        X_train, y_train = sm.fit_resample(X_train, y_train)
    if oversam and undersam:
        smote_enn = SMOTEENN(random_state=0)
        X_train, y_train = smote_enn.fit_resample(X_train, y_train)
    print(Counter(y_train))

    print("Train Classifier")
    dtc = dtc.fit(X_train, y_train, check_input=True)

    if export:
        export_graphviz(dtc, out_file=DATAP + "/temp/trees/sltree_" + configurationname + ".dot", filled=True)
        transform(fitted_ids)

    print("Self Accuracy: " + str(dtc.score(X_train, y_train)))

    return selector, dtc

# 需要导入模块: from sklearn.feature_selection import SelectFpr [as 别名]
# 或者: from sklearn.feature_selection.SelectFpr import transform [as 别名]
print "SelectPercentile -- chi2"
print X_fitted_4.scores_
print X_fitted_4.pvalues_
print X_fitted_4.get_support()
X_transformed_4 = X_fitted_4.transform(X)
print X_transformed_4.shape

#SelectFpr --- chi2
from sklearn.feature_selection import SelectFpr
from sklearn.feature_selection import chi2
X_fitted_5 = SelectFpr(chi2, alpha=2.50017968e-15).fit(X,y)
print "SelectFpr --- chi2"
print X_fitted_5.scores_
print X_fitted_5.pvalues_
print X_fitted_5.get_support()
X_transformed_5 = X_fitted_5.transform(X)
print X_transformed_5.shape

#SelectFpr --- f_classif
from sklearn.feature_selection import SelectFpr
from sklearn.feature_selection import f_classif
X_fitted_6 = SelectFpr(f_classif, alpha=1.66966919e-31 ).fit(X,y)
print "SelectFpr --- f_classif"
print X_fitted_6.scores_
print X_fitted_6.pvalues_
print X_fitted_6.get_support()
X_transformed_6 = X_fitted_6.transform(X)
print X_transformed_6.shape

# SelectFdr  和 SelectFwe 的用法和上面类似，只是选择特征时候的依据不同，真正决定得分不同的是
#统计检验方法，从上面可以看到，使用f_classif的得出的参数都相同。