How to use the sklearn.metrics.mean_squared_error function in sklearn

To help you get started, we’ve selected a few sklearn examples, based on popular ways it is used in public projects.

Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.

github vecxoz / vecstack / tests / test_sklearn_api_regression.py View on Github external
def test_custom_metric_and_scores_1_estimator(self):

        model = LinearRegression()
        scorer = make_scorer(mean_squared_error)
        scores_1 = cross_val_score(model, X_train, y=y_train,
                                   cv=n_folds, scoring=scorer,
                                   n_jobs=1, verbose=0)
        
        # fit then transform
        estimators = [('lr', LinearRegression())]
        stack = StackingTransformer(estimators, regression=True,
                                    metric=mean_squared_error,
                                    n_folds=n_folds, shuffle=False,
                                    variant='B', random_state=0,
                                    verbose=0)
        stack = stack.fit(X_train, y_train)
        scores_2 = stack.scores_[0].copy()
        
        # mean and std
        mean_1 = np.mean(scores_1)
github roshanmadhushanka / PythonML / Flow9.py View on Github external
# Train model
ls.fit(X=x, y=y)

# Get prediction results
result = []
for row in tX:
    if len(row) == 1:
        row = row.reshape(-1, 1)
    elif len(row) > 1:
        row = row.reshape(1, -1)
    result.append(ls.predict(row)[0])

# Analyze performance
print "Performance"
print "-----------"
print "Root Mean Squared Error", mean_squared_error(tY, np.array(result)) ** 0.5
print "Mean Absolute Error", mean_absolute_error(tY, np.array(result))

# Dump pickle files
joblib.dump(df_mapper, "mapper.pkl", compress = 3)
joblib.dump(ls, "estimator.pkl", compress = 3)

# Build pmml
command = "java -jar converter-executable-1.1-SNAPSHOT.jar --pkl-mapper-input mapper.pkl --pkl-estimator-input estimator.pkl --pmml-output mapper-estimator.pmml"
os.system(command)
github jcvasquezc / DisVoice / prosody / prosody_functions.py View on Github external
F0min=np.min(F0nz)
        F0skew=st.skew(F0nz)
        F0kurt=st.kurtosis(F0nz)
        tilt=[]
        mse=[]
        F0nzlist=np.split(F0, np.where(F0 == 0)[0]+1)
        F0nzlist=[F0nzlist[j] for j in range(len(F0nzlist) ) if len(F0nzlist[j])>1]
        F0nzlist=[F0nzlist[j][:-1] for j in  range(len(F0nzlist) )]
        for k in range(len(F0nzlist)):
            if len(F0nzlist[k])>1:
                t=np.arange(len(F0nzlist[k]))*tsf0
                pol=np.polyfit(t, F0nzlist[k],1)
                if not np.isnan(pol[0]):
                    tilt.append(pol[0])
                    f0rec=t*pol[0]+pol[1]
                    msef0t=mean_squared_error(F0nzlist[k],f0rec)
                    mse.append(msef0t)

        tiltmean=np.mean(np.asarray(tilt))
        msemean=np.mean(np.asarray(mse))
        tiltstd=np.std(np.asarray(tilt))
        msestd=np.std(np.asarray(mse))
        tiltmax=np.max(np.asarray(tilt))
        msemax=np.max(np.asarray(mse))
        tiltmin=np.min(np.asarray(tilt))
        msemin=np.min(np.asarray(mse))
        tiltskw=st.skew(np.asarray(tilt))
        mseskw=st.skew(np.asarray(mse))
        tiltku=st.kurtosis(np.asarray(tilt))
        mseku=st.kurtosis(np.asarray(mse))

        f01mean=np.mean(F0nzlist[0])
github FraPochetti / StocksProject / functions.py View on Github external
def performAdaBoostReg(train, test, features, output):
    """
    Ada Boost Regression
    """

    clf = AdaBoostRegressor()
    clf.fit(train[features], train[output])
    Predicted = clf.predict(test[features])
    
    plt.plot(test[output])
    plt.plot(Predicted, color='red')
    plt.show()        
    
    return mean_squared_error(test[output],Predicted), r2_score(test[output], Predicted)
github denik / vwoptimize / vwoptimize.py View on Github external
def root_mean_squared_error(*args, **kwargs):
    import sklearn.metrics
    return math.sqrt(sklearn.metrics.mean_squared_error(*args, **kwargs))
github fairlearn / fairlearn / fairlearn / metrics / _skm_wrappers.py View on Github external
def internal_mse_wrapper(y_true, y_pred, sample_weight=None):
        return skm.mean_squared_error(y_true, y_pred,
                                      multioutput=multioutput,
                                      sample_weight=sample_weight)
github ahmedhamdi96 / ML4T / machine_learning / development / optimized_lstm / lstm.py View on Github external
def evaluate(Y_test, predictions, Y_test_inv_scaled, predictions_inv_scaled):
    rmse = (mean_squared_error(Y_test, predictions) ** 0.5)
    print('\nNormalized RMSE: %.3f' %(rmse))
    nrmse = ((mean_squared_error(Y_test, predictions) ** 0.5))/np.mean(Y_test)
    print('Normalized NRMSE: %.3f' %(nrmse))
    mae = mean_absolute_error(Y_test, predictions)
    print('Normalized MAE: %.3f' %(mae))
    mape = compute_mape(Y_test, predictions)
    print('Normalized MAPE: %.3f' %(mape))
    correlation = np.corrcoef(Y_test.T, predictions.T)
    print("Normalized Correlation: %.3f"%(correlation[0, 1]))
    r2 = r2_score(Y_test, predictions)
    print("Normalized r^2: %.3f"%(r2))
    normalized_metrics = [rmse, nrmse, mae, mape, correlation[0, 1], r2]

    #evaluating the model on the inverse-normalized dataset
    rmse = (mean_squared_error(Y_test_inv_scaled, predictions_inv_scaled) ** 0.5)
    print('\nInverse-Normalized Outsample RMSE: %.3f' %(rmse))
github pailabteam / pailab / pailab / ml_repo / repo.py View on Github external
def _compute_mse(self, target_data, eval_data):
        """ Computes the mean squared error error measure

        Args:
            target_data ([type]): the target data
            eval_data ([type]): the evaluated data

        Returns:
            double -- the error
        """

        from sklearn.metrics import mean_squared_error
        return mean_squared_error(target_data, eval_data)
github ThoughtWorksInc / ml-app-template / src / train.py View on Github external
# save model 
joblib.dump(model, 'models/model.joblib') 
joblib.dump(column_order, 'models/column_order.joblib')

if settings.SHOULD_USE_MLFLOW == 'true':
    # log training run to mlflow
    mlflow.set_tracking_uri(uri=f'http://{settings.MLFLOW_IP}:5000')
    if settings.CI == 'true':
        mlflow.set_experiment('CI')
    else:
        mlflow.set_experiment('dev')

    with mlflow.start_run() as run:
        # calculate evaluation metrics
        y_test_pred = model.predict(x_test)
        rmse = sqrt(metrics.mean_squared_error(y_true=y_test, y_pred=y_test_pred))
        r2_score = metrics.r2_score(y_true=y_test, y_pred=y_test_pred)

        # log hyperparameters to mlflow
        mlflow.log_param('n_estimators', N_ESTIMATORS)
        mlflow.log_param('max_depth', MAX_DEPTH)
        
        # log metrics to mlflow
        mlflow.log_metric("rmse_validation_data", rmse)
        mlflow.log_metric("r2_score_validation_data", r2_score)
else:
    print('Not logging training run because MLFlow tracking server is not up, or its URL is not set in train.py')
github czbiohub / molecular-cross-validation / src / molecular_cross_validation / scripts / pca_sweep.py View on Github external
# run n_trials for self-supervised sweep
    for i in range(args.n_trials):
        umis_X, umis_Y = ut.split_molecules(umis, data_split, overlap, random_state)

        umis_X = np.sqrt(umis_X)
        umis_Y = np.sqrt(umis_Y)

        U, S, V = randomized_svd(umis_X, n_components=args.max_components)
        US = U.dot(np.diag(S))

        for j, k in enumerate(k_range):
            pca_X = US[:, :k].dot(V[:k, :])
            conv_exp = ut.convert_expectations(pca_X, data_split, data_split_complement)

            rec_loss[i, j] = mean_squared_error(umis_X, pca_X)
            mcv_loss[i, j] = mean_squared_error(umis_Y, conv_exp)
            gt1_loss[i, j] = mean_squared_error(exp_split_means, conv_exp)

    results = {
        "dataset": dataset_name,
        "method": "pca",
        "loss": "mse",
        "normalization": "sqrt",
        "param_range": k_range,
        "rec_loss": rec_loss,
        "mcv_loss": mcv_loss,
        "gt0_loss": gt0_loss,
        "gt1_loss": gt1_loss,
    }

    with open(output_file, "wb") as out:
        pickle.dump(results, out)