Python ensemble.BaggingRegressor类代码示例

def model_fit_rf_bagging():

	def in_limits(x):
		if x<1: return 1
		if x>3: return 3
		return x

	print "STARTING MODEL"
	X = full_data[['count_words','count_digits','match_d_title','match_d_description','match_w_title','match_w_description','match_d_attribute','match_w_attribute']].values
	y = full_data['relevance'].values
	X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=42)
	
	rf = RandomForestRegressor(n_estimators=15, max_depth=6, random_state=0)
	clf = BaggingRegressor(rf, n_estimators=45, max_samples=0.1, random_state=25)
	clf.fit(X_train, y_train)
	y_pred = clf.predict(X_test)

	in_limits = np.vectorize(in_limits,otypes=[np.float])
	y_pred = in_limits(y_pred)
	RMSE = mean_squared_error(y_test, y_pred)**0.5
	print "RMSE: ",RMSE

	# for the submission
	real_X_test = real_full_test[['count_words','count_digits','match_d_title','match_d_description','match_w_title','match_w_description','match_d_attribute','match_w_attribute']].values
	test_pred = clf.predict(real_X_test)
	test_pred = in_limits(test_pred)

	return test_pred

def train_model(train, test, labels):
    rf = RandomForestRegressor(n_estimators=15, max_depth=6, random_state=10)
    #rf = RandomForestRegressor(n_estimators=45, max_depth=9, random_state=10)
    clf = BaggingRegressor(rf, n_estimators=45, max_samples=0.2, random_state=25)
    clf.fit(train, labels)
    #clf = SVR(C=1.0, epsilon=0.2)
    #clf.fit(train, labels)
    #clf = GaussianNB()
    #clf.fit(train, labels)
    print "Good!"
    predictions = clf.predict(test)
    print predictions.shape
    predictions = pd.DataFrame(predictions, columns = ['relevance'])
    print "Good again!"
    print "Predictions head -------"
    print predictions.head()
    print predictions.shape
    print "TEST head -------"
    print test.head()
    print test.shape
    #test['id'].to_csv("TEST_TEST.csv",index=False)
    #predictions.to_csv("PREDICTIONS.csv",index=False)
    #test = test.reset_index()
    #predictions = predictions.reset_index()
    #test = test.groupby(level=0).first()
    #predictions = predictions.groupby(level=0).first()
    predictions = pd.concat([test['id'],predictions], axis=1, verify_integrity=False)
    print predictions
    return predictions

def train_bagging_xgboost(X, Y):
    adaboost = BaggingRegressor(xgb.XGBRegressor(max_depth=6, learning_rate=0.02, n_estimators=300, silent=True,
                                                 objective='reg:linear', subsample=0.7, reg_alpha=0.8,
                                                 reg_lambda=0.8, booster="gblinear")
                                , max_features=0.7, n_estimators=30)
    adaboost.fit(X, Y)
    return adaboost

def test_oob_score_regression():
    # Check that oob prediction is a good estimation of the generalization
    # error.
    rng = check_random_state(0)
    X_train, X_test, y_train, y_test = train_test_split(boston.data,
                                                        boston.target,
                                                        random_state=rng)

    clf = BaggingRegressor(base_estimator=DecisionTreeRegressor(),
                           n_estimators=50,
                           bootstrap=True,
                           oob_score=True,
                           random_state=rng).fit(X_train, y_train)

    test_score = clf.score(X_test, y_test)

    assert_less(abs(test_score - clf.oob_score_), 0.1)

    # Test with few estimators
    assert_warns(UserWarning,
                 BaggingRegressor(base_estimator=DecisionTreeRegressor(),
                                  n_estimators=1,
                                  bootstrap=True,
                                  oob_score=True,
                                  random_state=rng).fit,
                 X_train,
                 y_train)

def test_bootstrap_samples():
    """Test that bootstraping samples generate non-perfect base estimators."""
    rng = check_random_state(0)
    X_train, X_test, y_train, y_test = train_test_split(boston.data,
                                                        boston.target,
                                                        random_state=rng)

    base_estimator = DecisionTreeRegressor().fit(X_train, y_train)

    # without bootstrap, all trees are perfect on the training set
    ensemble = BaggingRegressor(base_estimator=DecisionTreeRegressor(),
                                max_samples=1.0,
                                bootstrap=False,
                                random_state=rng).fit(X_train, y_train)

    assert_equal(base_estimator.score(X_train, y_train),
                 ensemble.score(X_train, y_train))

    # with bootstrap, trees are no longer perfect on the training set
    ensemble = BaggingRegressor(base_estimator=DecisionTreeRegressor(),
                                max_samples=1.0,
                                bootstrap=True,
                                random_state=rng).fit(X_train, y_train)

    assert_greater(base_estimator.score(X_train, y_train),
                   ensemble.score(X_train, y_train))

def avmPredict(params):
	town = getPlace(params['lat'], params['long'])[0]

	x, y, z = getXYZ(params['lat'], params['long'])

	r = 1.0

	data = []
	target = []
	header = []

	with open('../../../data/working22.csv') as f:
	
		f = csv.reader(f)
		header = next(f)

		for row in f:
			t = (map(float, row[:3] + row[4:]), float(row[3]))

			if weightF([x, y, z], t[0][0:3], r):
				data.append(t[0])
				target.append(t[1])

	ensemble = BaggingRegressor()
	ensemble.fit(data, target)

	test = createTest(params)
	return ensemble.predict(test)

    def fit(self):
        """Scale data and train the model with the indicated algorithm.

        Do not forget to tune the hyperparameters.

        Parameters
        ----------
        algorithm : String,
            "KernelRidge", "SVM", "LinearRegression", "Lasso", "ElasticNet", "NeuralNet", "BaggingNeuralNet", default = "SVM"

        """
        self.X_scaler.fit(self.X_train)
        self.Y_scaler.fit(self.y_train)

        # scaling the data in all cases, it may not be used during the fit later
        self.X_train_sc = self.X_scaler.transform(self.X_train)
        self.y_train_sc = self.Y_scaler.transform(self.y_train)

        self.X_test_sc = self.X_scaler.transform(self.X_test)
        self.y_test_sc = self.Y_scaler.transform(self.y_test)

        if self.algorithm == "KernelRidge":
            clf_kr = KernelRidge(kernel=self.user_kernel)
            self.model = sklearn.model_selection.GridSearchCV(clf_kr, cv=5, param_grid=self.param_kr)

        elif self.algorithm == "SVM":
            clf_svm = SVR(kernel=self.user_kernel)
            self.model = sklearn.model_selection.GridSearchCV(clf_svm, cv=5, param_grid=self.param_svm)

        elif self.algorithm == "Lasso":
            clf_lasso = sklearn.linear_model.Lasso(alpha=0.1,random_state=self.rand_state)
            self.model = sklearn.model_selection.GridSearchCV(clf_lasso, cv=5,
                                                              param_grid=dict(alpha=np.logspace(-5,5,30)))

        elif self.algorithm == "ElasticNet":
            clf_ElasticNet = sklearn.linear_model.ElasticNet(alpha=0.1, l1_ratio=0.5,random_state=self.rand_state)
            self.model = sklearn.model_selection.GridSearchCV(clf_ElasticNet,cv=5,
                                                              param_grid=dict(alpha=np.logspace(-5,5,30)))

        elif self.algorithm == "LinearRegression":
            self.model = sklearn.linear_model.LinearRegression()

        elif self.algorithm == "NeuralNet":
            self.model = MLPRegressor(**self.param_neurons)
        elif self.algorithm == "BaggingNeuralNet":
            nn_m = MLPRegressor(**self.param_neurons)

            self.model = BaggingRegressor(base_estimator = nn_m, **self.param_bag)

        if self.scaling == True:
            self.model.fit(self.X_train_sc, self.y_train_sc.reshape(-1,))
            predict_train_sc = self.model.predict(self.X_train_sc)
            self.prediction_train = self.Y_scaler.inverse_transform(predict_train_sc.reshape(-1,1))
            predict_test_sc = self.model.predict(self.X_test_sc)
            self.prediction_test = self.Y_scaler.inverse_transform(predict_test_sc.reshape(-1,1))
        else:
            self.model.fit(self.X_train, self.y_train.reshape(-1,))
            self.prediction_train = self.model.predict(self.X_train)
            self.prediction_test = self.model.predict(self.X_test)

def random_forest(X,Y,Xt):
    print('learn')    
    rf = RandomForestRegressor(n_estimators=15, max_depth=6, random_state=0)
    clf = BaggingRegressor(rf, n_estimators=45, max_samples=0.1, random_state=25)
    clf.fit(X, Y)
    print('predict')
    Yp_clamped = clf.predict(Xt)
    return Yp_clamped

def test_sparse_regression():
    # Check regression for various parameter settings on sparse input.
    rng = check_random_state(0)
    X_train, X_test, y_train, y_test = train_test_split(boston.data[:50],
                                                        boston.target[:50],
                                                        random_state=rng)

    class CustomSVR(SVR):
        """SVC variant that records the nature of the training set"""

        def fit(self, X, y):
            super().fit(X, y)
            self.data_type_ = type(X)
            return self

    parameter_sets = [
        {"max_samples": 0.5,
         "max_features": 2,
         "bootstrap": True,
         "bootstrap_features": True},
        {"max_samples": 1.0,
         "max_features": 4,
         "bootstrap": True,
         "bootstrap_features": True},
        {"max_features": 2,
         "bootstrap": False,
         "bootstrap_features": True},
        {"max_samples": 0.5,
         "bootstrap": True,
         "bootstrap_features": False},
    ]

    for sparse_format in [csc_matrix, csr_matrix]:
        X_train_sparse = sparse_format(X_train)
        X_test_sparse = sparse_format(X_test)
        for params in parameter_sets:

            # Trained on sparse format
            sparse_classifier = BaggingRegressor(
                base_estimator=CustomSVR(),
                random_state=1,
                **params
            ).fit(X_train_sparse, y_train)
            sparse_results = sparse_classifier.predict(X_test_sparse)

            # Trained on dense format
            dense_results = BaggingRegressor(
                base_estimator=CustomSVR(),
                random_state=1,
                **params
            ).fit(X_train, y_train).predict(X_test)

            sparse_type = type(X_train_sparse)
            types = [i.data_type_ for i in sparse_classifier.estimators_]

            assert_array_almost_equal(sparse_results, dense_results)
            assert all([t == sparse_type for t in types])
            assert_array_almost_equal(sparse_results, dense_results)

def procedureA(goldenFlag = False):
	# Trains and generates a prediction file
	# Uses hard heuristic for buy_or_not

	popFlag = True
	X, Y = getDataXY(currYearFlag = False, popFlag = popFlag)
	X, Y = shuffle(X, Y, random_state = 0)

	if popFlag:
		encoder = oneHot(X[:, 2:])
		Xt = encoder.transform(X[:, 2:])
		Xt = np.hstack((X[:,:2], Xt))
	else:
		encoder = oneHot(X)
		Xt = encoder.transform(X)

	buySet = set()
	for i in range(X.shape[0]):
		tmpTup = (X[i][0], X[i][2])
		buySet.add(tmpTup)
	# Y_buy = [1] * Xt.shape[0]

	min_max_scaler = preprocessing.MinMaxScaler()

	# Xt = min_max_scaler.fit_transform(Xt)

	if goldenFlag:
		print Xt.shape
		Xt = getGoldenX(Xt, 2, 2 + encoder.feature_indices_[1], 2 + encoder.feature_indices_[0], 2 + min(9, encoder.feature_indices_[1]))


	split = 0.9
	X_train, X_test = Xt[:(int(Xt.shape[0]*split)),:], Xt[int(Xt.shape[0]*split):, :]
	Y_train, Y_test = Y[:(int(Y.shape[0]*split)),:], Y[int(Y.shape[0]*split):, :]
	Y_train = Y_train.ravel()
	Y_test = Y_test.ravel()

	print X_train.shape
	print X_test.shape

	# clf = Ridge(alpha = 100)
	# clf = SVR(C = 10.0, kernel = 'poly', degree = 2)
	# clf = LinearSVR(C = 1.0)
	clf = BaggingRegressor(DecisionTreeRegressor(), n_estimators = 125, n_jobs = 4, random_state = 0)
	# clf = AdaBoostRegressor(DecisionTreeRegressor(), n_estimators = 100)
	# clf = DecisionTreeRegressor()
	# clf = RandomForestRegressor(random_state = 0, n_estimators = 200, n_jobs = 4)
	clf.fit(X_train, Y_train.ravel())

	Y_pred = clf.predict(X_test)
	evaluatePred(Y_pred, Y_test)

	return clf, encoder, min_max_scaler

    def __init__(self):
#         self.clf = GradientBoostingRegressor(n_estimators=200, max_features="sqrt", max_depth=5)
#         self.clf = LinearRegression() 
         self.clf = BaggingRegressor(LinearRegression())
#         self.clf = GaussianProcess(theta0=4)
#         self.sp = RandomizedLasso()       
         self.sp = SparseRandomProjection(n_components=5)

def test_single_estimator():
    # Check singleton ensembles.
    rng = check_random_state(0)
    X_train, X_test, y_train, y_test = train_test_split(boston.data,
                                                        boston.target,
                                                        random_state=rng)

    clf1 = BaggingRegressor(base_estimator=KNeighborsRegressor(),
                            n_estimators=1,
                            bootstrap=False,
                            bootstrap_features=False,
                            random_state=rng).fit(X_train, y_train)

    clf2 = KNeighborsRegressor().fit(X_train, y_train)

    assert_array_almost_equal(clf1.predict(X_test), clf2.predict(X_test))

def train_model(training, testing, window=5, n=5):
	X_train, y_train = prepare_data(training)
	X_test, y_test = prepare_data(testing)
	rf = RandomForestRegressor()
	rf.fit(X_train, y_train)
	predrf = rf.predict(X_test)
	print "mse for random forest regressor: ", mean_squared_error(predrf, y_test)

	gb = GradientBoostingRegressor(n_estimators=100, learning_rate=0.025)
	gb.fit(X_train, y_train)
	predgb = gb.predict(X_test)
	print "mse for gradient boosting regressor: ", mean_squared_error(predgb, y_test)
	## plot feature importance using GBR results
	fx_imp = pd.Series(gb.feature_importances_, index=['bb', 'momentum', 'sma', 'volatility'])
	fx_imp /= fx_imp.max()  # normalize
	fx_imp.sort()
	ax = fx_imp.plot(kind='barh')
	fig = ax.get_figure()
	fig.savefig("output/feature_importance.png")

	adb = AdaBoostRegressor(DecisionTreeRegressor())
	adb.fit(X_train, y_train)
	predadb = adb.predict(X_test)
	print "mse for adaboosting decision tree regressor: ", mean_squared_error(predadb, y_test)

	scale = StandardScaler()
	scale.fit(X_train)
	X_trainscale = scale.transform(X_train)
	X_testscale = scale.transform(X_test)

	knn = BaggingRegressor(KNeighborsRegressor(n_neighbors=10), max_samples=0.5, max_features=0.5)
	knn.fit(X_trainscale, y_train)
	predknn = knn.predict(X_testscale)
	print "mse for bagging knn regressor: ", mean_squared_error(predknn, y_test)

	pred_test = 0.1*predrf+0.2*predgb+0.1*predadb+0.6*predknn
	print "mse for ensemble all the regressors: ", mean_squared_error(pred_test, y_test)
	result = testing.copy()
	result.ix[5:-5, 'trend'] = pred_test
	result.ix[10:, 'pred'] = pred_test * result.ix[5:-5, 'IBM'].values
	result.ix[:-5, 'pred_date'] = result.index[5:]

	return result

def procc_modelfusion(df_test, data_test):
    from sklearn.ensemble import BaggingRegressor
    from sklearn import linear_model
    train_df = df.filter(regex='Survived|Age_.*|SibSp|Parch|Fare_.*|Cabin_.*|Embarked_.*|Sex_.*|Pclass.*|Mother|Child|Family|Title')
    train_np = train_df.as_matrix()

    # y即Survival结果
    y = train_np[:, 0]

    # X即特征属性值
    X = train_np[:, 1:]

    # fit到BaggingRegressor之中
    clf = linear_model.LogisticRegression(C=1.0, penalty='l1', tol=1e-6)
    bagging_clf = BaggingRegressor(clf, n_estimators=10, max_samples=0.8, max_features=1.0, bootstrap=True, bootstrap_features=False, n_jobs=-1)
    bagging_clf.fit(X, y)

    test = df_test.filter(regex='Age_.*|SibSp|Parch|Fare_.*|Cabin_.*|Embarked_.*|Sex_.*|Pclass.*|Mother|Child|Family|Title')
    predictions = bagging_clf.predict(test)
    result = pd.DataFrame({'PassengerId' : data_test['PassengerId'].as_matrix(), 'Survived':predictions.astype(np.int32)})
    result.to_csv("logistic_regression_predictions3.csv", index=False)

class Regressor(BaseEstimator):
    def __init__(self):
#         self.clf = GradientBoostingRegressor(n_estimators=200, max_features="sqrt", max_depth=5)
#         self.clf = LinearRegression() 
         self.clf = BaggingRegressor(LinearRegression())
#         self.clf = GaussianProcess(theta0=4)
#         self.sp = RandomizedLasso()       
         self.sp = SparseRandomProjection(n_components=5)
#         self.sp = TruncatedSVD()
 #        self.sp = KernelPCA(n_components=3, tol=0.0001, kernel="poly")
    # self.clf = ExtraTreesRegressor(n_estimators=200, max_features="sqrt", max_depth=5)

    def fit(self, X, y):
#        print(self.sp)

#        Xr = self.sp.fit_transform(X, y)
        self.clf.fit(X, y.ravel())
 
    def predict(self, X):
#        Xr = self.sp.transform(X)
        return self.clf.predict(X)