python类ElasticNet()的实例源码

def build_model(train_file, test_file, attr_file, model_out, predictions_out, algorithm='ridge'):
  classifiers = ['ridge', 'linear', 'lasso', 'rf', 'en']
  if algorithm not in classifiers:
    raise NotImplementedError("only implemented algorithms: " + str(classifiers))

  train_data = pd.read_pickle(train_file)
  attrs = read_attrs(attr_file)

  target_attr = attrs[0]
  usable_attrs = attrs[1:]

  if algorithm == 'ridge':
    clf = Ridge()
  elif algorithm == 'linear':
    clf = LinearRegression()
  elif algorithm == 'lasso':
    clf = Lasso()
  elif algorithm == 'en':
    clf = ElasticNet()
  else:
    clf = RandomForestRegressor()

  clf.fit(train_data[usable_attrs], train_data[target_attr])

  test_data = pd.read_pickle(test_file)
  predictions = clf.predict(test_data[usable_attrs])
  errors = predictions - test_data[target_attr]

  prediction_results = test_data[[target_attr] + usable_attrs].copy()
  prediction_results['predicted'] = predictions
  prediction_results.to_pickle(predictions_out)

  print "Modeling '%s'" % target_attr
  print "   Train:", train_file, '(%d examples)' % len(train_data)
  print "   Test:", test_file, '(%d examples)' % len(test_data)
  print "Algorithm:", algorithm

  if hasattr(clf, 'coef_'):
    print 'Coefficients:'
    for i,c in enumerate(clf.coef_):
      print '    %-20s' % usable_attrs[i] + ':', '%20.4f' % c

  print 'MSE  : %10.4f' % np.mean(errors ** 2)
  print 'medSE: %10.4f' % np.median(errors ** 2)
  print 'SSE  : %10.4f' % np.sum(errors ** 2)
  print 'Variance score: %.4f' % clf.score(test_data[usable_attrs], test_data[target_attr])

  pickle.dump(clf, open(model_out, 'wb'))

def getSKLearnModel(modelName):
    if modelName == 'LinearRegression':
        model = linear_model.LinearRegression()
    elif modelName == 'BayesianRidge':
        model = linear_model.BayesianRidge()
    elif modelName == 'ARDRegression':
        model = linear_model.ARDRegression()
    elif modelName == 'ElasticNet':
        model = linear_model.ElasticNet()
    elif modelName == 'HuberRegressor':
        model = linear_model.HuberRegressor()
    elif modelName == 'Lasso':
        model = linear_model.Lasso()
    elif modelName == 'LassoLars':
        model = linear_model.LassoLars()
    elif modelName == 'Rigid':
        model = linear_model.Ridge()
    elif modelName == 'SGDRegressor':
        model = linear_model.SGDRegressor()
    elif modelName == 'SVR':
        model = SVR()
    elif modelName=='MLPClassifier':
        model = MLPClassifier()
    elif modelName=='KNeighborsClassifier':
        model = KNeighborsClassifier()
    elif modelName=='SVC':
        model = SVC()
    elif modelName=='GaussianProcessClassifier':
        model = GaussianProcessClassifier()
    elif modelName=='DecisionTreeClassifier':
        model = DecisionTreeClassifier()
    elif modelName=='RandomForestClassifier':
        model = RandomForestClassifier()
    elif modelName=='AdaBoostClassifier':
        model = AdaBoostClassifier()
    elif modelName=='GaussianNB':
        model = GaussianNB()
    elif modelName=='LogisticRegression':
        model = linear_model.LogisticRegression()
    elif modelName=='QuadraticDiscriminantAnalysis':
        model = QuadraticDiscriminantAnalysis()

    return model