Python ensemble.AdaBoostRegressor类代码示例

    def fit(self, start_date, end_date):

        for ticker in self.tickers:
            self.stocks[ticker] = Stock(ticker)

        params_ada = [{
            'n_estimators': [25, 50, 100],
            'learning_rate': [0.01, 0.1, 1, 10],
            'loss': ['linear', 'square', 'exponential']
            }]

        params = ParameterGrid(params_ada)

        # Find the split for training and CV
        mid_date = train_test_split(start_date, end_date)
        for ticker, stock in self.stocks.items():

            X_train, y_train = stock.get_data(start_date, mid_date, fit=True)
            # X_train = self.pca.fit_transform(X_train.values)
            X_train = X_train.values
            # pdb.set_trace()
            X_cv, y_cv = stock.get_data(mid_date, end_date)
            # X_cv = self.pca.transform(X_cv.values)
            X_cv = X_cv.values

            lowest_mse = np.inf
            for i, param in enumerate(params):
                ada = AdaBoostRegressor(**param)
                ada.fit(X_train, y_train.values)
                mse = mean_squared_error(
                    y_cv, ada.predict(X_cv))
                if mse <= lowest_mse:
                    self.models[ticker] = ada

        return self

def round2(X_df, featurelist):
    # Set parameters
    model = AdaBoostRegressor()
    y_df = X_df['target']
    n = len(y_df)

    # Perform 5-fold cross validation
    scores = []
    kf = KFold(n, n_folds=5, shuffle=True)

    # Calculate mean absolute deviation for train/test for each fold
    for train_idx, test_idx in kf:
        X_train, X_test = X_df.iloc[train_idx, :], X_df.iloc[test_idx, :]
        # y_train, y_test = y_df[train_idx], y_df[test_idx]

        X_train, X_test = applyFeatures(X_train, X_test, featurelist)
        Xtrain_array, ytrain_array, Xtest_array, ytest_array = dfToArray(X_train, X_test)
        model.fit(Xtrain_array, ytrain_array)
        prediction = model.predict(Xtest_array)
        rmse = np.sqrt(mean_squared_error(ytest_array, prediction))
        scores.append(rmse)
        print rmse
        print "Finish fold"

    return scores

def train_learning_model_decision_tree_ada_boost(df):
    #code taken from sklearn
    X_all, y_all = preprocess_data(df)
    X_train, X_test, y_train, y_test = split_data(X_all, y_all)

    tree_regressor = DecisionTreeRegressor(max_depth = 6)
    ada_regressor = AdaBoostRegressor(DecisionTreeRegressor(max_depth=6), n_estimators = 500, learning_rate = 0.01, random_state = 1)

    tree_regressor.fit(X_train, y_train)
    ada_regressor.fit(X_train, y_train)

    y_pred_tree = tree_regressor.predict(X_test)
    y_pred_ada = ada_regressor.predict(X_test)
    
    mse_tree = mean_squared_error(y_test, y_pred_tree)
    mse_ada = mean_squared_error(y_test, y_pred_ada)

    mse_tree_train = mean_squared_error(y_train, tree_regressor.predict(X_train))
    mse_ada_train = mean_squared_error(y_train, ada_regressor.predict(X_train))
    
    print ("MSE tree: %.4f " %mse_tree)
    print ("MSE ada: %.4f " %mse_ada)

    print ("MSE tree train: %.4f " %mse_tree_train)
    print ("MSE ada train: %.4f " %mse_ada_train)

    def predict(tour_data):

        vec = DictVectorizer()

        tour_data = get_tour_data()

        transformed = vec.fit_transform(tour_data).toarray()
        categories = vec.get_feature_names()

        y = transformed[:,[categories.index('rating')]]
        X = transformed[:,np.arange(transformed.shape[1])!=categories.index('rating')]

        reg_tree = DecisionTreeRegressor()

        addboost_tree = AdaBoostRegressor(DecisionTreeRegressor(max_depth=4),
                              n_estimators=300, random_state=rng)

        red_tree.fit(X,y)
        addboost_tree(X,y)

        # Predict
        y_1 = red_tree.predict(X)
        y_2 = addboost_tree.predict(X)

        return prediction

def backTest(trainEndDate, code, testDate, predictDate):
    conn = db.get_history_data_db('D')
    df = None
    # train more date
    # model = pickle.load(open('%s/%s.pkl' % (config.model_dir, code), 'r'))
    rng = np.random.RandomState(1)
    model = AdaBoostRegressor(DecisionTreeRegressor(
        max_depth=4), n_estimators=1000, random_state=rng, loss='square')
    df = pd.read_sql_query(
        "select * from history_data where date([date])<='%s' and code='%s' order by code, date([date]) asc" % (
            trainEndDate, code), conn)
    shift_1 = df['close'].shift(-2)
    df['target'] = shift_1
    data = df[df['target'] > -1000]

    X_train = data.ix[:, 'code':'turnover']
    y_train = data.ix[:, 'target']
    if len(X_train) < 500:
        return
    print len(X_train)
    # print data
    # for i in range(0, 10):
    #     model.fit(X_train, y_train)
    model.fit(X_train, y_train)
    # predict tomorrow
    try:
        df = pd.read_sql_query(config.sql_history_data_by_code_date % (code, testDate), conn)
        # print df
    except Exception, e:
        print e

def main():



    ab = AdaBoostRegressor(base_estimator=None, n_estimators=50, 
                            learning_rate=1.0, loss='exponential', 
                            random_state=None)  

    ab.fit(X_train, y_train)

    #Evaluation in train set
    #Evaluation in train set
    pred_proba_train = ab.predict(X_train)
        
    mse_train = mean_squared_error(y_train, pred_proba_train)
    rmse_train = np.sqrt(mse_train)
    logloss_train = log_loss(y_train, pred_proba_train)
    
    #Evaluation in validation set
    pred_proba_val = ab.predict(X_val)
        
    mse_val = mean_squared_error(y_val, pred_proba_val)
    rmse_val = np.sqrt(mse_val)
    logloss_val = log_loss(y_val, pred_proba_val)
    
    rmse_train
    rmse_val
    logloss_train
    logloss_val

def ada_boost_regressor(train_x, train_y, pred_x, review_id, v_curve=False, l_curve=False, get_model=True):
    """
    :param train_x: train
    :param train_y: text
    :param pred_x: test set to predict
    :param review_id: takes in a review id
    :param v_curve: run the model for validation curve
    :param l_curve: run the model for learning curve
    :param get_model: run the model
    :return: the predicted values,learning curve, validation curve
    """
    ada = AdaBoostRegressor(n_estimators=5)
    if get_model:
        print "Fitting Ada..."
        ada.fit(train_x, np.log(train_y+1))
        ada_pred = np.exp(ada.predict(pred_x))-1
        Votes = ada_pred[:,np.newaxis]
        Id = np.array(review_id)[:,np.newaxis]
        # create submission csv for Kaggle
        submission_ada= np.concatenate((Id,Votes),axis=1)
        np.savetxt("submission_ada.csv", submission_ada,header="Id,Votes", delimiter=',',fmt="%s, %0.2f", comments='')
    # plot validation and learning curves
    if l_curve:
        print "Working on Learning Curves"
        plot_learning_curve(AdaBoostRegressor(), "Learning curve: Adaboost", train_x, np.log(train_y+1.0))
    if v_curve:
        print "Working on Validation Curves"
        plot_validation_curve(AdaBoostRegressor(), "Validation Curve: Adaboost", train_x, np.log(train_y+1.0),
                              param_name="n_estimators", param_range=[2, 5, 10, 15, 20, 25, 30])

def Round2(X, y):
    # Set parameters
    min_score = {}
    for loss in ['linear', 'square', 'exponential']:
        model = AdaBoostRegressor(loss=loss)
        n = len(y)

        # Perform 5-fold cross validation
        scores = []
        kf = KFold(n, n_folds=5, shuffle=True)

        # Calculate mean absolute deviation for train/test for each fold
        for train_idx, test_idx in kf:
            X_train, X_test = X[train_idx], X[test_idx]
            y_train, y_test = y[train_idx], y[test_idx]
            model.fit(X_train, y_train)
            prediction = model.predict(X_test)
            rmse = np.sqrt(mean_squared_error(y_test, prediction))
            # score = model.score(X_test, y_test)
            scores.append(rmse)
        if len(min_score) == 0:
            min_score['loss'] = loss
            min_score['scores'] = scores
        else:
            if np.mean(scores) < np.mean(min_score['scores']):
                min_score['loss'] = loss
                min_score['scores'] = scores

        print "Loss:", loss
        print scores
        print np.mean(scores)
    return min_score

def predict_volatility_1year_ahead(rows, day, num_days):
    """
    SUMMARY: Predict volatility 1 year into the future
    ALGORITHM:
      a) The predictor will train on all data up to exactly 1 year (252 trading days) before `day`
      b) The newest 10 days up to and including `day` will be used as the feature vector for the prediction
         i.e. if day = 0, then the feature vector for prediction will consist of days (0, 1, 2, 3, 4, 5, 6, 7, 8, 9)
              if day = 10, then the feature vector for predictor input will be days (10, 11, 12, 13, 14, 15, 16, 17, 19)
    INPUT: minimum of (1 year + 10 days) of data before `day` (newest data is day=0)
  
    """

    '''enforce that `day` is in the required range'''
    assert len(rows) >= 252+num_days + day, 'You need to have AT LEAST 252+%d rows AFTER the day index. See predict_volatility_1year_ahead() for details.' % num_days
    assert day >= 0

    '''Compile features for fitting'''
    feature_sets = []
    value_sets = [];
    for ii in range(day+num_days+252, len(rows) - num_days):
        features = []
        for jj in range(num_days):
            day_index = ii + jj
            features += [
        	float(rows[day_index][7]), 
        	float(rows[day_index][8]),
        	float(rows[day_index][9]), 
        	float(rows[day_index][10]),
        	float(rows[day_index][11]),
        	float(rows[day_index][12]),
        	float(rows[day_index][13]),
            ]
            #print("issue here: " + str(rows[day_index][0]))
        feature_sets += [features]
        value_sets += [float(rows[ii-252][9])]

    '''Create Regressor and fit'''
    num_features = 16
    rng = np.random.RandomState(1)
    regr = AdaBoostRegressor(CustomClassifier(), n_estimators=3, random_state=rng)
    regr.fit(feature_sets, value_sets)

    '''Get prediction features'''
    ii = day
    features = []
    for jj in range( num_days ):
        day_index = ii + jj   
        features += [
        float(rows[day_index][7]), 
        float(rows[day_index][8]),
        float(rows[day_index][9]), 
        float(rows[day_index][10]),
        float(rows[day_index][11]),
        float(rows[day_index][12]),
        float(rows[day_index][13]),
        ]
        
    return float(regr.predict([features]))

def ada_learning(labels, train, test):
    label_log=np.log1p(labels)
    # try 50 / 1.0
    #boost GradientBoostingRegressor(n_estimators=200, max_depth=8, learning_rate=0.1)
    clf=AdaBoostRegressor(GradientBoostingRegressor(n_estimators=200, max_depth=8, learning_rate=0.1),n_estimators=50, learning_rate=1.0)
    model=clf.fit(train, label_log)
    preds1=model.predict(test)
    preds=np.expm1(preds1)
    return  preds

class Regressor(BaseEstimator):
    def __init__(self):
        self.clf = AdaBoostRegressor(RandomForestRegressor(n_estimators=500, max_depth=78, max_features=10), n_estimators=40)

    def fit(self, X, y):
        self.clf.fit(X, y)

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

def train_predict(train_id, test_id):
	# load libsvm files for training dataset
	Xs_train = []
	ys_train = []
	n_train = load_libsvm_files(train_id, Xs_train, ys_train)
	# load libsvm files for testing dataset
	Xs_test = []
	ys_test = []
	n_test = load_libsvm_files(test_id, Xs_test, ys_test)

	# models
	model = []

	# ans
	ans_train = []
	ans_test = []

	# generate predictions for training dataset
	ps_train = []
	for i in range(0, n_train):
		ps_train.append([0.0 for j in range(10)])

	# generate predictions for testing dataset
	ps_test = []
	for i in range(0, n_test):
		ps_test.append([0.0 for j in range(10)])

	# fit models
	for i in range(10):
		l = np.array([ys_train[j][i] for j in range(n_train)])
		clf = AdaBoostRegressor(DecisionTreeRegressor(max_depth=params['max_depth']), n_estimators=params['n_estimators'], learning_rate=params['learning_rate'])
		clf.fit(Xs_train[i].toarray(), l)
		print "[%s] [INFO] %d model training done" % (t_now(), i)
		preds_train = clf.staged_predict(Xs_train[i].toarray())
		ans_train.append([item for item in preds_train])
		# print "len(ans_train[%d]) = %d" % (i, len(ans_train[i]))
		print "[%s] [INFO] %d model predict for training data set done" % (t_now(), i)
		preds_test = clf.staged_predict(Xs_test[i].toarray())
		ans_test.append([item for item in preds_test])
		print "[%s] [INFO] %d model predict for testing data set done" % (t_now(), i)

	#print "len_ans_train=%d" % len(ans_train[0])

	# predict for testing data set
	for i in range(params['n_estimators']):
		for j in range(10):
			tmp = min(i, len(ans_train[j]) - 1)
			for k in range(n_train):
				ps_train[k][j] = ans_train[j][tmp][k]
			tmp = min(i, len(ans_test[j]) - 1)
			for k in range(n_test):
				ps_test[k][j] = ans_test[j][tmp][k]
		print "%s,%d,%f,%f" % (t_now(), i + 1, mean_cos_similarity(ys_train, ps_train, n_train), mean_cos_similarity(ys_test, ps_test, n_test))

	return 0

class Regressor(BaseEstimator):
    def __init__(self):
        cl = RandomForestRegressor(n_estimators=10, max_depth=10, max_features=10)
        self.clf = AdaBoostRegressor(base_estimator = cl, n_estimators=100)

    def fit(self, X, y):
        self.clf.fit(X, y)

    def predict(self, X):
        return self.clf.predict(X)
#RandomForestClassifier

def ada_boost(data,classifier,sample):
    from sklearn.ensemble import AdaBoostRegressor
    from sklearn.tree import DecisionTreeClassifier, DecisionTreeRegressor
    from sklearn.cluster import KMeans
    from sklearn.naive_bayes import GaussianNB
    func = GaussianNB()
    func = DecisionTreeRegressor()
    func = KMeans(n_clusters=2)
    clf = AdaBoostRegressor(func,n_estimators=300,random_state=random.RandomState(1))
    clf.fit(data,classifier)
    print_result(clf,[sample])

def AdaBoost(xTrain, yTrain, xTest, yTest, treeNum):
	rms = dict()
	for trees in treeNum:
		ab = AdaBoostRegressor(n_estimators = trees)
		ab.fit(xTrain, yTrain)
		yPred = ab.predict(xTest)
		rms[trees] = sqrt(mean_squared_error(yTest, yPred))

	(bestRegressor, rmse) = sorted(rms.iteritems(), key = operator.itemgetter(1))[0]

	return bestRegressor, rmse