How to use test_inner method in pytest-django

Best Python code snippet using pytest-django_python

regression.py

Source:regression.py

1import numpy as np2import sklearn3from sklearn.linear_model import ARDRegression, LinearRegression4from sklearn.metrics import roc_curve, auc5import sklearn.linear_model6import util7import metrics as ranking_metrics8import predict91011def ARDRegression_on_fold(feature_sets, train, test, y, y_all, X, dim, dimsum, learn_options):12    '''13    '''14    clf = ARDRegression()15    clf.fit(X[train], y[train][:, 0])16    y_pred = clf.predict(X[test])[:, None]17    return y_pred, clf181920def train_linreg_model(alpha, l1r, learn_options, fold, X, y, y_all):21    '''22    fold is something like train_inner (boolean array specifying what is in the fold)23    '''24    if learn_options["penalty"] == "L2":25        clf = sklearn.linear_model.Ridge(alpha=alpha, fit_intercept=True, normalize=True, copy_X=True, max_iter=None, tol=0.001, solver='auto')26        weights = get_weights(learn_options, fold, y, y_all)27        clf.fit(X[fold], y[fold], sample_weight=weights)28    elif learn_options["penalty"] == 'EN' or learn_options["penalty"] == 'L1':29        if learn_options["loss"] == "squared":30            clf = sklearn.linear_model.ElasticNet(alpha=alpha, l1_ratio=l1r, fit_intercept=True, normalize=True, max_iter=3000)31        elif learn_options["loss"] == "huber":32            clf = sklearn.linear_model.SGDRegressor('huber', epsilon=0.7, alpha=alpha,33                                                    l1_ratio=l1r, fit_intercept=True, n_iter=10,34                                                    penalty='elasticnet', shuffle=True)35        clf.fit(X[fold], y[fold])36    return clf373839def logreg_on_fold(feature_sets, train, test, y, y_all, X, dim, dimsum, learn_options):40    '''41    (L1/L2 penalized) logistic reggresion using scikitlearn42    '''4344    assert len(np.unique(y)) <= 2, "if using logreg need binary targets"45    assert learn_options["weighted"] is None, "cannot do weighted Log reg"46    assert learn_options['feature_select'] is False, "cannot do feature selection yet in logistic regression--see linreg_on_fold to implement"4748    cv, n_folds = set_up_folds(learn_options, y_all.iloc[train])4950    assert learn_options['penalty'] == "L1" or learn_options['penalty'] == "L2", "can only use L1 or L2 with logistic regression"5152    performance = np.zeros((len(learn_options["alpha"]), 1))53    # degenerate_pred = np.zeros((len(learn_options["alpha"])))54    for train_inner, test_inner in cv:55        for i, alpha in enumerate(learn_options["alpha"]):56            clf = sklearn.linear_model.LogisticRegression(penalty=learn_options['penalty'], dual=False,57                                                          fit_intercept=True, class_weight='auto', tol=0.001, C=1.0/alpha)58            clf.fit(X[train][train_inner], y[train][train_inner].flatten())59            tmp_pred = clf.predict(X[train][test_inner])6061            if learn_options["training_metric"] == "AUC":62                fpr, tpr, _ = roc_curve(y_all[learn_options["ground_truth_label"]][train][test_inner], tmp_pred)63                assert ~np.any(np.isnan(fpr)), "found nan fpr"64                assert ~np.any(np.isnan(tpr)), "found nan tpr"65                tmp_auc = auc(fpr, tpr)66                performance[i] += tmp_auc67            else:68                raise Exception("can only use AUC metric for cv with classification")6970    performance /= n_folds7172    max_score_ind = np.where(performance == np.nanmax(performance))73    assert max_score_ind != len(performance), "enlarge alpha range as hitting max boundary"7475    # in the unlikely event of tied scores, take the first one.76    if len(max_score_ind[0]) > 1:77        max_score_ind = [max_score_ind[0][0], max_score_ind[1][0]]7879    best_alpha = learn_options["alpha"][max_score_ind[0]]8081    print "\t\tbest alpha is %f from range=%s" % (best_alpha, learn_options["alpha"][[0, -1]])82    max_perf = np.nanmax(performance)8384    if max_perf < 0.0:85        raise Exception("performance is negative")8687    print "\t\tbest performance is %f" % np.nanmax(performance)8889    clf = sklearn.linear_model.LogisticRegression(penalty=learn_options['penalty'],90                                                  dual=False, fit_intercept=True, class_weight='auto',91                                                  tol=0.001, C=1.0/best_alpha)92    clf.fit(X[train], y[train].flatten())93    y_pred = clf.predict(X[test])94    y_pred = y_pred[:, None]95    return y_pred, clf969798def linreg_on_fold(feature_sets, train, test, y, y_all, X, dim, dimsum, learn_options):99    '''100    linreg using scikitlearn, using more standard regression models with penalization requiring101    nested-cross-validation102    '''103104    if learn_options["weighted"] is not None and (learn_options["penalty"] != "L2" or learn_options["method"] != "linreg"):105        raise NotImplementedError("weighted prediction not implemented for any methods by L2 at the moment")106107    cv, n_folds = set_up_folds(learn_options, y_all.iloc[train])108109    if learn_options['penalty'] == "L1":110        l1_ratio = [1.0]111    elif learn_options['penalty'] == "L2":112        l1_ratio = [0.0]113    elif learn_options['penalty'] == "EN":  # elastic net114        l1_ratio = np.linspace(0.0, 1.0, 20)115116    performance = np.zeros((len(learn_options["alpha"]), len(l1_ratio)))117    degenerate_pred = np.zeros((len(learn_options["alpha"])))118    for train_inner, test_inner in cv:119        for i, alpha in enumerate(learn_options["alpha"]):120            for j, l1r in enumerate(l1_ratio):121                clf = train_linreg_model(alpha, l1r, learn_options, train_inner, X[train], y[train], y_all.iloc[train])122                if learn_options["feature_select"]:123                    clf, tmp_pred = feature_select(clf, learn_options, test_inner, train_inner, X[train], y[train])124                else:125                    tmp_pred = clf.predict(X[train][test_inner])126127                if learn_options["training_metric"] == "AUC":128                    fpr, tpr, _ = roc_curve(y_all[learn_options["ground_truth_label"]][train][test_inner], tmp_pred)129                    assert ~np.any(np.isnan(fpr)), "found nan fpr"130                    assert ~np.any(np.isnan(tpr)), "found nan tpr"131                    tmp_auc = auc(fpr, tpr)132                    performance[i, j] += tmp_auc133134                elif learn_options['training_metric'] == 'spearmanr':135                    spearman = util.spearmanr_nonan(y_all[learn_options['ground_truth_label']][train][test_inner], tmp_pred.flatten())[0]136                    performance[i, j] += spearman137138                elif learn_options['training_metric'] == 'score':139                    performance[i, j] += clf.score(X[test_inner], y_all[learn_options['ground_truth_label']][train][test_inner])140141                elif learn_options["training_metric"] == "NDCG":142                    assert "thresh" not in learn_options["ground_truth_label"], "for NDCG must not use thresholded ranks, but pure ranks"143144                    # sorted = tmp_pred[np.argsort(y_all[ground_truth_label].values[test_inner])[::-1]].flatten()145                    # sortedgt = np.sort(y_all[ground_truth_label].values[test_inner])[::-1].flatten()146                    # tmp_perf = ranking_metrics.ndcg_at_k_ties(sorted, learn_options["NDGC_k"], sortedgt)147                    tmp_truth = y_all[learn_options["ground_truth_label"]].values[train][test_inner].flatten()148                    tmp_perf = ranking_metrics.ndcg_at_k_ties(tmp_truth, tmp_pred.flatten(), learn_options["NDGC_k"])149                    performance[i, j] += tmp_perf150151                    degenerate_pred_tmp = len(np.unique(tmp_pred)) < len(tmp_pred)/2.0152                    degenerate_pred[i] += degenerate_pred_tmp153154                    # sanity checking metric wrt ties, etc.155                    # rmse = np.sqrt(np.mean((tmp_pred - tmp_truth)**2))156                    tmp_pred_r, tmp_truth_r = ranking_metrics.rank_data(tmp_pred, tmp_truth)157                    # rmse_r = np.sqrt(np.mean((tmp_pred_r-tmp_truth_r)**2))158159    performance /= n_folds160161    max_score_ind = np.where(performance == np.nanmax(performance))162    assert max_score_ind != len(performance), "enlarge alpha range as hitting max boundary"163    # assert degenerate_pred[max_score_ind[0][0]]==0, "found degenerate predictions at max score"164165    # in the unlikely event of tied scores, take the first one.166    if len(max_score_ind[0]) > 1:167        max_score_ind = [max_score_ind[0][0], max_score_ind[1][0]]168169    best_alpha, best_l1r = learn_options["alpha"][max_score_ind[0]], l1_ratio[max_score_ind[1]]170171    print "\t\tbest alpha is %f from range=%s" % (best_alpha, learn_options["alpha"][[0, -1]])172    if learn_options['penalty'] == "EN":173        print "\t\tbest l1_ratio is %f from range=%s" % (best_l1r, l1_ratio[[0, -1]])174    max_perf = np.nanmax(performance)175176    if max_perf < 0.0:177        raise Exception("performance is negative")178179    print "\t\tbest performance is %f" % max_perf180181    clf = train_linreg_model(best_alpha, l1r, learn_options, train, X, y, y_all)182    if learn_options["feature_select"]:183        raise Exception("untested in a long time, should double check")184        clf, y_pred = feature_select(clf, learn_options, test, train, X, y)185    else:186        y_pred = clf.predict(X[test])187188    if learn_options["penalty"] != "L2":189        y_pred = y_pred[:, None]190191    return y_pred, clf192193194def feature_select(clf, learn_options, test_inner, train_inner, X, y):195    assert not learn_options["weighted"] is not None, "cannot currently do feature selection with weighted regression"196    assert learn_options["loss"] is not "huber", "won't use huber loss function with feature selection"197    non_zero_coeff = (clf.coef_ != 0.0)198    if non_zero_coeff.sum() > 0:199        clf = LinearRegression()200        clf.fit(X[train_inner][:, non_zero_coeff.flatten()], y[train_inner])201        tmp_pred = clf.predict(X[test_inner][:, non_zero_coeff.flatten()])202    else:203        tmp_pred = np.ones_like(test_inner)204    return clf, tmp_pred205206207def get_weights(learn_options, fold, y, y_all):208    '''209    fold is an object like train_inner which is boolean for which indexes are in the fold210    '''211    weights = None212    if learn_options["weighted"] == "variance":213        weights = 1.0/y_all["variance"].values[fold]214    elif learn_options["weighted"] == "ndcg":215        # DCG: r[0] + np.sum(r[1:] / np.log2(np.arange(2, r.size + 1)))216        N = len(fold)217        r = np.ones(N)218        discount = np.concatenate((np.array([r[0]]), r[1:] / np.log2(np.arange(2, r.size + 1))))[::1]219        ind = np.argsort(y[fold], axis=0).flatten()220        weights = np.ones(len(ind))221        weights[ind] = discount222    elif learn_options["weighted"] == "rank":223        N = len(y[fold])224        inverse_ranks = (np.arange(N) + 1.0)[::-1]225        ind = np.argsort(y[fold], axis=0).flatten()226        weights = np.ones(len(ind))227        weights[ind] = inverse_ranks228    elif learn_options["weighted"] == "score":229        N = len(y[fold])230        score = y[fold] + np.abs(np.min(y[fold]))231        ind = np.argsort(y[fold], axis=0).flatten()232        weights = np.ones(len(ind))233        weights[ind] = score234    elif learn_options["weighted"] == "random":235        N = len(y[fold])236        weights = np.random.rand(N)237    elif learn_options["weighted"] is not None:238        raise Exception("invalid weighted type, %s" % learn_options["weighted"])239    # plt.plot(weights, y[train_inner],'.')240    return weights241242243def set_up_folds(learn_options, y):244    if learn_options["cv"] == "stratified":245        label_encoder = sklearn.preprocessing.LabelEncoder()246        label_encoder.fit(y['Target gene'].values)247        gene_classes = label_encoder.transform(y['Target gene'].values)248        n_folds = len(np.unique(gene_classes))249        cv = sklearn.cross_validation.StratifiedKFold(gene_classes, n_folds=n_folds, shuffle=True)250    elif learn_options["cv"] == "gene":251        gene_list = np.unique(y['Target gene'].values)252        cv = []253        for gene in gene_list:254            cv.append(predict.get_train_test(gene, y))255        n_folds = len(cv)
...

Automation Testing Tutorials

Learn to execute automation testing from scratch with LambdaTest Learning Hub. Right from setting up the prerequisites to run your first automation test, to following best practices and diving deeper into advanced test scenarios. LambdaTest Learning Hubs compile a list of step-by-step guides to help you be proficient with different test automation frameworks i.e. Selenium, Cypress, TestNG etc.