Python BaggingRegressor.fit方法代码示例

# 需要导入模块: from sklearn.ensemble import BaggingRegressor [as 别名]
# 或者: from sklearn.ensemble.BaggingRegressor import fit [as 别名]
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

# 需要导入模块: from sklearn.ensemble import BaggingRegressor [as 别名]
# 或者: from sklearn.ensemble.BaggingRegressor import fit [as 别名]
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

# 需要导入模块: from sklearn.ensemble import BaggingRegressor [as 别名]
# 或者: from sklearn.ensemble.BaggingRegressor import fit [as 别名]
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)

# 需要导入模块: from sklearn.ensemble import BaggingRegressor [as 别名]
# 或者: from sklearn.ensemble.BaggingRegressor import fit [as 别名]
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

# 需要导入模块: from sklearn.ensemble import BaggingRegressor [as 别名]
# 或者: from sklearn.ensemble.BaggingRegressor import fit [as 别名]
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

# 需要导入模块: from sklearn.ensemble import BaggingRegressor [as 别名]
# 或者: from sklearn.ensemble.BaggingRegressor import fit [as 别名]
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

# 需要导入模块: from sklearn.ensemble import BaggingRegressor [as 别名]
# 或者: from sklearn.ensemble.BaggingRegressor import fit [as 别名]
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

# 需要导入模块: from sklearn.ensemble import BaggingRegressor [as 别名]
# 或者: from sklearn.ensemble.BaggingRegressor import fit [as 别名]
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)

# 需要导入模块: from sklearn.ensemble import BaggingRegressor [as 别名]
# 或者: from sklearn.ensemble.BaggingRegressor import fit [as 别名]
def get_bagging_prediction(X_train, y_train, X_test, X_valid=None, GS=False):
    if not GS:
        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)
        if X_valid is None:
            return y_pred
        else:
            return y_pred, clf.predict(X_valid)
    else:
        rf = RandomForestRegressor(n_estimators=15, max_depth=6, random_state=0)
        clf = BaggingRegressor(rf, n_estimators=45, max_samples=0.1, random_state=25)
        param_grid = {'rfr__max_features': [10], 'rfr__max_depth': [20]}
        model = grid_search.GridSearchCV(estimator=clf, param_grid=param_grid, n_jobs=-1, cv=2, verbose=VERBOSE, scoring=RMSE)
        model.fit(X_train, y_train)
        y_pred = model.predict(X_test)
        if X_valid is None:
            return y_pred
        else:
            return y_pred, model.predict(X_valid)

# 需要导入模块: from sklearn.ensemble import BaggingRegressor [as 别名]
# 或者: from sklearn.ensemble.BaggingRegressor import fit [as 别名]
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)

# 需要导入模块: from sklearn.ensemble import BaggingRegressor [as 别名]
# 或者: from sklearn.ensemble.BaggingRegressor import fit [as 别名]
def runTests():

    # Generate the training samples, extract training features and target
    trainSamples = GenSamples(numSamples)
    trainFeatures = extractFeatures(trainSamples)
    trainPred = extractPred(trainSamples)

    # Generate the test samples, extracr test features and target
    testSamples = GenSamples(numTestSamples)
    testFeatures = extractFeatures(testSamples)
    testPred = extractPred(testSamples)

    R2List = OrderedDict()
    R2List['TrainROI'] = []
    R2List['TestROI'] = []
    print 'Running Tests: '
    for i in range(numTests):
        # Bootstrap is True by default i.e., sampling with replacement
        # Bootstrap features is False by default i.e., all features used
        classifier = BaggingRegressor(base_estimator=DecisionTreeRegressor(),
                                      n_estimators=numTrees,
                                      max_samples=int(0.5*numSamples),
                                      max_features=int(1))

        classifier.fit(trainFeatures, trainPred)
        predictROI = {}
        predictROI['Training'] = classifier.predict(trainFeatures)
        predictROI['Test'] = classifier.predict(testFeatures)

        R2 = {}
        R2['Train'] = r2_score(trainPred, predictROI['Training'])
        R2['Test'] = r2_score(testPred, predictROI['Test'])

        R2List['TrainROI'].append(R2['Train'])
        R2List['TestROI'].append(R2['Test'])

    print 'Best Train ROI: ', max(R2List['TrainROI'])
    print 'Best Test ROI: ', max(R2List['TestROI'])

# 需要导入模块: from sklearn.ensemble import BaggingRegressor [as 别名]
# 或者: from sklearn.ensemble.BaggingRegressor import fit [as 别名]
def test_bagging_regressor_with_missing_inputs():
    # Check that BaggingRegressor can accept X with missing/infinite data
    X = np.array([
        [1, 3, 5],
        [2, None, 6],
        [2, np.nan, 6],
        [2, np.inf, 6],
        [2, np.NINF, 6],
    ])
    y_values = [
        np.array([2, 3, 3, 3, 3]),
        np.array([
            [2, 1, 9],
            [3, 6, 8],
            [3, 6, 8],
            [3, 6, 8],
            [3, 6, 8],
        ])
    ]
    for y in y_values:
        regressor = DecisionTreeRegressor()
        pipeline = make_pipeline(
            Imputer(),
            Imputer(missing_values=np.inf),
            Imputer(missing_values=np.NINF),
            regressor
        )
        pipeline.fit(X, y).predict(X)
        bagging_regressor = BaggingRegressor(pipeline)
        y_hat = bagging_regressor.fit(X, y).predict(X)
        assert_equal(y.shape, y_hat.shape)

        # Verify that exceptions can be raised by wrapper regressor
        regressor = DecisionTreeRegressor()
        pipeline = make_pipeline(regressor)
        assert_raises(ValueError, pipeline.fit, X, y)
        bagging_regressor = BaggingRegressor(pipeline)
        assert_raises(ValueError, bagging_regressor.fit, X, y)

# 需要导入模块: from sklearn.ensemble import BaggingRegressor [as 别名]
# 或者: from sklearn.ensemble.BaggingRegressor import fit [as 别名]
class BaggingRegressor(BaseEstimator):
    """
    Usage:

    ```
    "model": {
        "class": "ume.ensemble.BaggingRegressor",
        "params": {
            "base_estimator": {
                "class": "sklearn.svm.SVR",
                "params": {
                    "kernel": "rbf",
                    "degree": 1,
                    "C": 1000000.0,
                    "epsilon": 0.01,
                },
            },
            "bag_kwargs": {
                "n_estimators": 100,
                "n_jobs": 5,
                "max_samples": 0.9,
            },
        }
    }
    ```
    """
    def __init__(self, base_estimator=None, bag_kwargs=None):
        klass = dynamic_load(base_estimator['class'])
        svr_reg = klass(**base_estimator['params'])
        self.__clf = SK_BaggingRegressor(base_estimator=svr_reg, **bag_kwargs)

    def fit(self, X, y):
        return self.__clf.fit(X, y)

    def predict(self, X):
        return self.__clf.predict(X)

# 需要导入模块: from sklearn.ensemble import BaggingRegressor [as 别名]
# 或者: from sklearn.ensemble.BaggingRegressor import fit [as 别名]
    X[np.isnan(X)] = 0.

    print '******************************************'
    print name
    print '******************************************'
    
    if name=='Boston' or name=='Diabetes': # Regression problem
    
        rfr = RandomForestRegressor(**params)
        rfr.fit(X, y)
        print 'Score RandomForestRegressor = %s' % (rfr.score(X, y))
        scores_rfr = cross_val_score(rfr, X, y ,cv=5)
        print 'Cross Val Score RandomForestRegressor = %s' % (np.mean(scores_rfr))
        
        br = BaggingRegressor(base_estimator=DecisionTreeRegressor(max_depth=max_depth), n_estimators=n_estimators)
        br.fit(X, y)
        print 'Score BaggingRegressor = %s' % (br.score(X, y))
        scores_br = cross_val_score(br, X, y, cv=5)
        print 'Cross Val Scores of BR = %s' %(np.mean(scores_br))
        
    if name=='Iris' or name=='Digits': # Classificaiton problem
    
        rfc = RandomForestClassifier(**params)
        rfc.fit(X, y)
        print 'Score RandomForestClassifier = %s' % (rfc.score(X, y))
        scores_rfc = cross_val_score(rfc, X, y ,cv=5)
        print 'Corss Val Scores of RandomForestClassifier = %s' %(np.mean(scores_rfc))

        bc = BaggingClassifier(base_estimator=DecisionTreeClassifier(max_depth=max_depth), n_estimators=n_estimators)
        bc.fit(X, y)        
        print 'Score BaggingClassifier == %s' % (bc.score(X, y))

# 需要导入模块: from sklearn.ensemble import BaggingRegressor [as 别名]
# 或者: from sklearn.ensemble.BaggingRegressor import fit [as 别名]
ax2.set_title('Error between actual and predicted loads')
ax2.set_ylabel("Error, MW")

featImportances=gradBoost.feature_importances_
pos = np.arange(len(features))
pairs = zip(features, featImportances)
sorted_pairs = sorted(pairs, key = lambda pair: pair[1])
features_sorted, featImportances_sorted = zip(*sorted_pairs)
fig, ax = plt.subplots()
plt.barh(pos, featImportances_sorted, 1, color = "blue")
plt.yticks(pos,features_sorted)
ax.set_title('Gradient Boosting: Relative Feature Importance')

#Tree Bagging
TreeBagger=BaggingRegressor()
TreeBagger.fit(Xtrain, Ytrain)
fig = plt.figure()
ax1 = fig.add_subplot(2, 1, 1)
ax1.plot_date(dates, modeldata.Load[45000:50000], 'r-',tz=None, xdate=True,
          ydate=False, label='Actual Load')
ax1.set_title('Tree Bagging: Actual and Predicted Loads')          
plt.plot(dates, TreeBagger.predict(Xtest), 'g-',label='Predicted Load')
ax1.legend()
ax2 = fig.add_subplot(2, 1, 2)
ax2.plot_date(dates, modeldata.Load[45000:50000]-TreeBagger.predict(Xtest), 'r-',tz=None, xdate=True,
          ydate=False)
ax2.set_title('Error between actual and predicted loads, MW')

MSEs_Bagging=[mean_squared_error(Ytest, TreeBagger.predict(Xtest)), mean_squared_error(Ytrain, TreeBagger.predict(Xtrain))]

#Model Comparison: Bar charts