Python, sklearn: Helper function for supervised learning

supervised_learner.py

def supervised_learner(df, clf, train_list, testsize = 0.3, predictors=df.columns[1:], target=df.columns[-1]):
    ### Import packages
    from sklearn.cross_validation import train_test_split
    from sklearn import linear_model
    from sklearn.linear_model import SGDClassifier
    from sklearn.metrics import confusion_matrix
    from sklearn.metrics import classification_report
    import pandas as pd
    import numpy as np
    from sklearn.metrics import roc_curve
    from sklearn.metrics import roc_auc_score
    
    unique_pkeys = df.pkey.unique()
    train_percent_reserved = np.true_divide(len(train_list), len(unique_pkeys))
    X_train_prior = df.loc[df.pkey.isin(train_list), predictors]
    y_train_prior = df.loc[df.pkey.isin(train_list), target]
    testsize += train_percent_reserved
    df_temp = df[-df.pkey.isin(train_list)]
    X_train, X_test, y_train, y_test = train_test_split(df.temp[predictors], df.temp[target], test_size=testsize)
    X_train = pd.concat(X_train, X_train_prior)
    y_train = pd.concat(y_train, y_train_prior)
    clf = clf
    clf.fit(X_train, y_train)
    y_train_pred = clf.predict(X_train)
    y_train_scores = clf.predict_proba(X_train)[:, 1]
    y_test_pred = clf.predict(X_test)
    y_test_scores = clf.predict_proba(X_test)[:, 1]
    train_classrep = classification_report(y_train, y_train_pred)
    test_classrep = classification_report(y_test, y_test_pred)
    train_confusion = confusion_matrix(y_train, y_train_pred)
    test_confusion = confusion_matrix(y_test, y_test_pred)
    train_fpr, train_tpr, train_thresholds = roc_curve(y_train, y_train_scores)
    test_fpr, test_tpr, test_thresholds = roc_curve(y_test, y_test_scores)
    train_auc = roc_auc_score(y_train, y_train_scores)
    test_auc = roc_auc_score(y_test, y_test_scores)

    print '-------------Training----------------'
    print train_classrep
    print 'AUC score is %.2f' % train_auc
    print 'ROC Curve'
    plt.plot(train_fpr, train_tpr)
   

    print '-------------Testing----------------'
    print train_classrep
    print 'AUC score is %.2f' % test_auc
    print 'ROC Curve'
    plt.plot(test_fpr, test_tpr)
    
    
    df_coeffs = pd.DataFrame('predictor': X_train.columns, 'coefficient': clf.coef_[0]})
    df_coeffs = df_coeffs.sort_values(by=['coefficient'], ascending=False)
    return clf, df_coeffs