def test_univariate_normal_equation_std():
w_exp = np.array([[0.7]])
b_exp = np.array([0.0])
ne_lr = LinearRegression(minibatches=None)
ne_lr.fit(X_rm_std, y_std)
assert_almost_equal(ne_lr.w_, w_exp, decimal=1)
assert_almost_equal(ne_lr.b_, b_exp, decimal=1)
def test_multivariate_normal_equation():
w_exp = np.array([[5.1], [-0.6]])
b_exp = np.array([-1.5])
ne_lr = LinearRegression(minibatches=None)
ne_lr.fit(X_rm_lstat, y)
assert_almost_equal(ne_lr.w_, w_exp, decimal=1)
assert_almost_equal(ne_lr.b_, b_exp, decimal=1)
def test_univariate_stochastic_gradient_descent():
sgd_lr = LinearRegression(minibatches=len(y),
eta=0.0001,
epochs=100,
random_seed=0)
sgd_lr.fit(X_rm_std, y_std)
assert_almost_equal(sgd_lr.w_, expect_rm_std, decimal=2)
def test_progress_3():
gd_lr = LinearRegression(minibatches=1,
eta=0.001,
epochs=1,
print_progress=2,
random_seed=0)
gd_lr.fit(X_rm_std, y_std)
def test_multivariate_gradient_descent():
gd_lr = LinearRegression(eta=0.001,
epochs=500,
minibatches=1,
random_seed=0)
gd_lr.fit(X_rm_lstat_std, y_std)
assert_almost_equal(gd_lr.w_, expect_rm_lstat_std, decimal=3)
def test_progress_3():
gd_lr = LinearRegression(minibatches=1,
eta=0.001,
epochs=1,
print_progress=2,
random_seed=0)
gd_lr.fit(X_rm_std, y_std)
def test_multivariate_normal_equation():
w_exp = np.array([[5.1], [-0.6]])
b_exp = np.array([-1.5])
ne_lr = LinearRegression(minibatches=None)
ne_lr.fit(X_rm_lstat, y)
assert_almost_equal(ne_lr.w_, w_exp, decimal=1)
assert_almost_equal(ne_lr.b_, b_exp, decimal=1)
def test_univariate_normal_equation_std():
w_exp = np.array([[0.7]])
b_exp = np.array([0.0])
ne_lr = LinearRegression(minibatches=None)
ne_lr.fit(X_rm_std, y_std)
assert_almost_equal(ne_lr.w_, w_exp, decimal=1)
assert_almost_equal(ne_lr.b_, b_exp, decimal=1)
def test_multivariate_gradient_descent():
gd_lr = LinearRegression(eta=0.001,
epochs=500,
minibatches=1,
random_seed=0)
gd_lr.fit(X_rm_lstat_std, y_std)
assert_almost_equal(gd_lr.w_, expect_rm_lstat_std, decimal=3)
def test_univariate_normal_equation():
w_exp = np.array([[9.1]])
b_exp = np.array([-34.7])
ne_lr = LinearRegression(minibatches=None)
ne_lr.fit(X_rm, y)
assert_almost_equal(ne_lr.w_, w_exp, decimal=1)
assert_almost_equal(ne_lr.b_, b_exp, decimal=1)
def test_univariate_normal_equation():
w_exp = np.array([[9.1]])
b_exp = np.array([-34.7])
ne_lr = LinearRegression(minibatches=None)
ne_lr.fit(X_rm, y)
assert_almost_equal(ne_lr.w_, w_exp, decimal=1)
assert_almost_equal(ne_lr.b_, b_exp, decimal=1)
def test_univariate_stochastic_gradient_descent():
sgd_lr = LinearRegression(minibatches=len(y),
eta=0.0001,
epochs=100,
random_seed=0)
sgd_lr.fit(X_rm_std, y_std)
assert_almost_equal(sgd_lr.w_, expect_rm_std, decimal=2)
def test_univariate_gradient_descent():
gd_lr = LinearRegression(solver='gd',
eta=0.001,
epochs=500,
random_seed=0)
gd_lr.fit(X_rm_std, y_std)
assert_almost_equal(gd_lr.w_, expect_rm_std, decimal=3)
def test_multivariate_svd():
w_exp = np.array([[5.1], [-0.6]])
b_exp = np.array([-1.5])
svd_lr = LinearRegression(method='svd')
svd_lr.fit(X_rm_lstat, y)
assert_almost_equal(svd_lr.w_, w_exp, decimal=1)
assert_almost_equal(svd_lr.b_, b_exp, decimal=1)
def test_univariate_svd():
w_exp = np.array([[9.1]])
b_exp = np.array([-34.7])
svd_lr = LinearRegression(method='svd')
svd_lr.fit(X_rm, y)
assert_almost_equal(svd_lr.w_, w_exp, decimal=1)
assert_almost_equal(svd_lr.b_, b_exp, decimal=1)
def test_multivariate_stochastic_gradient_descent():
sgd_lr = LinearRegression(eta=0.0001,
epochs=500,
solver='sgd',
random_seed=0)
sgd_lr.fit(X_rm_lstat_std, y_std)
assert_almost_equal(sgd_lr.w_, expect_rm_lstat_std, decimal=2)
def test_multivariate_stochastic_gradient_descent():
sgd_lr = LinearRegression(eta=0.0001,
epochs=500,
solver='sgd',
random_seed=0)
sgd_lr.fit(X_rm_lstat_std, y_std)
assert_almost_equal(sgd_lr.w_, expect_rm_lstat_std, decimal=2)
def test_ary_persistency_in_shuffling():
orig = X_rm_lstat_std.copy()
sgd_lr = LinearRegression(eta=0.0001,
epochs=500,
minibatches=len(y),
random_seed=0)
sgd_lr.fit(X_rm_lstat_std, y_std)
np.testing.assert_almost_equal(orig, X_rm_lstat_std, 6)
def test_ary_persistency_in_shuffling():
orig = X_rm_lstat_std.copy()
sgd_lr = LinearRegression(eta=0.0001,
epochs=500,
minibatches=len(y),
random_seed=0)
sgd_lr.fit(X_rm_lstat_std, y_std)
np.testing.assert_almost_equal(orig, X_rm_lstat_std, 6)
def test_univariate_stochastic_gradient_descent():
w_exp = np.array([[0.7]])
b_exp = np.array([0.0])
sgd_lr = LinearRegression(minibatches=len(y),
eta=0.0001,
epochs=150,
random_seed=0)
sgd_lr.fit(X_rm_std, y_std)
assert_almost_equal(sgd_lr.w_, w_exp, decimal=1)
assert_almost_equal(sgd_lr.b_, b_exp, decimal=1)
def test_multivariate_gradient_descent():
w_exp = np.array([[0.4], [-0.5]])
b_exp = np.array([0.0])
gd_lr = LinearRegression(eta=0.001,
epochs=500,
minibatches=1,
random_seed=0)
gd_lr.fit(X_rm_lstat_std, y_std)
assert_almost_equal(gd_lr.w_, w_exp, decimal=1)
assert_almost_equal(gd_lr.b_, b_exp, decimal=1)
def test_multivariate_stochastic_gradient_descent():
w_exp = np.array([[0.389], [-0.499]])
b_exp = np.array([0.000])
sgd_lr = LinearRegression(eta=0.0001,
epochs=500,
minibatches=len(y),
random_seed=0)
sgd_lr.fit(X_rm_lstat_std, y_std)
assert_almost_equal(sgd_lr.w_, w_exp, decimal=3)
assert_almost_equal(sgd_lr.b_, b_exp, decimal=3)
def test_univariate_gradient_descent():
w_exp = np.array([[0.695]])
b_exp = np.array([0.00])
gd_lr = LinearRegression(minibatches=1,
eta=0.001,
epochs=500,
random_seed=0)
gd_lr.fit(X_rm_std, y_std)
assert_almost_equal(gd_lr.w_, w_exp, decimal=3)
assert_almost_equal(gd_lr.b_, b_exp, decimal=3)
def test_univariate_stochastic_gradient_descent():
w_exp = np.array([[0.7]])
b_exp = np.array([0.0])
sgd_lr = LinearRegression(minibatches=len(y),
eta=0.0001,
epochs=150,
random_seed=0)
sgd_lr.fit(X_rm_std, y_std)
assert_almost_equal(sgd_lr.w_, w_exp, decimal=1)
assert_almost_equal(sgd_lr.b_, b_exp, decimal=1)
def test_multivariate_stochastic_gradient_descent():
w_exp = np.array([[0.389], [-0.499]])
b_exp = np.array([0.000])
sgd_lr = LinearRegression(eta=0.0001,
epochs=500,
minibatches=len(y),
random_seed=0)
sgd_lr.fit(X_rm_lstat_std, y_std)
assert_almost_equal(sgd_lr.w_, w_exp, decimal=3)
assert_almost_equal(sgd_lr.b_, b_exp, decimal=3)
def test_multivariate_gradient_descent():
w_exp = np.array([[0.4], [-0.5]])
b_exp = np.array([0.0])
gd_lr = LinearRegression(eta=0.001,
epochs=500,
minibatches=1,
random_seed=0)
gd_lr.fit(X_rm_lstat_std, y_std)
assert_almost_equal(gd_lr.w_, w_exp, decimal=1)
assert_almost_equal(gd_lr.b_, b_exp, decimal=1)
def test_univariate_gradient_descent():
w_exp = np.array([[0.695]])
b_exp = np.array([0.00])
gd_lr = LinearRegression(minibatches=1,
eta=0.001,
epochs=500,
random_seed=0)
gd_lr.fit(X_rm_std, y_std)
assert_almost_equal(gd_lr.w_, w_exp, decimal=3)
assert_almost_equal(gd_lr.b_, b_exp, decimal=3)
import numpy as np
import matplotlib.pyplot as plt
from mlxtend.regressor import LinearRegression
X = np.array([1.0, 2.1, 3.6, 4.2, 6])[:, np.newaxis]
y = np.array([1.0, 2.0, 3.0, 4.0, 5.0])
print X
print y
ne_lr = LinearRegression(minibatches=None)
ne_lr.fit(X, y)
print('Intercept: %.2f' % ne_lr.b_)
print('Slope: %.2f' % ne_lr.w_[0])
def lin_regplot(X, y, model):
plt.scatter(X, y, c='blue')
plt.plot(X, model.predict(X), color='red')
return
lin_regplot(X, y, ne_lr)
plt.show()
def test_multivariate_normal_equation():
ne_lr = LinearRegression(solver='normal equation')
ne_lr.fit(X_rm_lstat, y)
assert_almost_equal(ne_lr.w_, expect_rm_lstat, decimal=3)
and test and compare them on linear regression over your synthetic data-points.
You need not to perform a cross-validation scheme here; only use the whole data set as your training set.
"""
X = np.asanyarray(x).reshape(
-1, 1
) #x need to be converted into matrix without changing the array values to fit the model
eta1 = 0.0001
eta2 = 0.1
from mlxtend.regressor import LinearRegression
from sklearn import metrics
ada1_bgd = LinearRegression(method='sgd',
eta=eta1,
epochs=20,
random_seed=0,
minibatches=1) #for adalline bgd
ada1_bgd.fit(X, y)
y_pred = ada1_bgd.predict(X)
mse1 = metrics.mean_squared_error(y_pred, y)
ada2_bgd = LinearRegression(method='sgd',
eta=eta2,
epochs=20,
random_seed=0,
minibatches=1) #for adaline bgd
ada2_bgd.fit(X, y)
y_pred = ada2_bgd.predict(X)
mse2 = metrics.mean_squared_error(y_pred, y)
print("Adaline Batch Gradient Descent Regression Algorithm")
print("-----------------------------------------------------")
def test_multivariate_normal_equation():
ne_lr = LinearRegression(solver='normal equation')
ne_lr.fit(X_rm_lstat, y)
assert_almost_equal(ne_lr.w_, expect_rm_lstat, decimal=3)
def test_univariate_gradient_descent():
gd_lr = LinearRegression(solver='gd', eta=0.001, epochs=500, random_seed=0)
gd_lr.fit(X_rm_std, y_std)
assert_almost_equal(gd_lr.w_, expect_rm_std, decimal=3)
def test_univariate_normal_equation_std():
ne_lr = LinearRegression(solver='normal equation')
ne_lr.fit(X_rm_std, y_std)
assert_almost_equal(ne_lr.w_, expect_rm_std, decimal=3)
for j in month_count:
mult_month_count.append([j])
# print mult_month_count
X = np.array(mult_index)[:, np.newaxis]
y = np.array(month_count)
# print len(X)
# print len(y)
# print "X: ", X
# print "y: ", y
# Linear Regression
# reg = LinearRegression(minibatches=None)
# reg.fit(X, y)
reg = LinearRegression(minibatches=None)
reg.fit(X, y)
# X_train, X_test, y_train, y_test
file_name = filename[70:]
file_name = file_name.replace(".csv", "")
# print file_name
# print reg.w_
print 'Intercept: %.2f' % reg.b_
print 'Slope: %.2f\n' % reg.w_[0]
filenames.append(file_name)
intercepts.append(reg.b_)
slopes.append(reg.w_)
def test_clone():
regr = LinearRegression()
clone(regr)
def test_univariate_normal_equation_std():
ne_lr = LinearRegression(minibatches=None)
ne_lr.fit(X_rm_std, y_std)
assert_almost_equal(ne_lr.w_, expect_rm_std, decimal=3)
rowdata = pd.read_csv('data/normal/爱情字典-287637.csv')
year = rowdata.year
month = rowdata.month
day = rowdata.day
date = {}
for i in range(len(year)):
da = f'{year[i]}-{month[i]}-{day[i]}'
if da not in date.keys():
date[da] = 1
else:
date[da] += 1
points = [(key, value) for key, value in date.items()][::-1]
gd_lr = LinearRegression()
x_ = [float(time.mktime(time.strptime(x[0], "%Y-%m-%d"))) for x in points]
y_ = [float(y[1]) for y in points]
gd_lr.fit(np.array(x_)[:, np.newaxis], np.array(y_))
x_axis = [time.strftime("%Y-%m-%d", time.localtime(i)) for i in x_]
print(x_axis[::18])
plt.rcParams['font.sans-serif'] = ['simhei'] #设置字体
plt.figure(figsize=[12, 8])
plt.title('回归模型')
plt.scatter(x_axis, y_, alpha=0.4, edgecolors='white')
#plt.xticks(range(7), [2013,2014,2015,2016,2017,2018,2019])
#plt.yticks(y_, fontsize=9)
plt.plot(x_axis, gd_lr.predict(np.array(x_)[:, np.newaxis]), color='gray')
ax = plt.gca()
ax.spines['right'].set_color('none')
usecols=[0, 1, 2, 3],
nrows=data_size)
X = dataframe[["Feature 1", "Feature 2", "Feature 3"]]
Y = dataframe["Target"]
print(set_sizes[0])
print('here', set_sizes[nrows] * 0.7)
X_train = X.head(int(set_sizes[nrows] * 0.7))
X_test = X.tail(int(set_sizes[nrows] * 0.3))
Y_train = Y.head(int(set_sizes[nrows] * 0.7))
Y_test = Y.tail(int(set_sizes[nrows] * 0.3))
ne_lr = LinearRegression(minibatches=None)
Y2 = pd.to_numeric(Y, downcast='float')
print("here", type((Y2)))
print(type(Y_train))
ne_lr.fit(X_train, pd.to_numeric(Y_train, downcast='float'))
print(ne_lr)
y_pred = ne_lr.predict(X_test)
res = mean_squared_error(Y_test, y_pred)
#res = scoring(y_target=Y_test, y_predicted=y_pred, metric='rmse')
print("results: ", res)
def test_multivariate_normal_equation():
ne_lr = LinearRegression(minibatches=None)
ne_lr.fit(X_rm_lstat, y)
assert_almost_equal(ne_lr.w_, expect_rm_lstat, decimal=3)
from sklearn.model_selection import GridSearchCV
from xgboost import XGBRegressor
from timeseries.time_series_processing import *
if __name__ == '__main__':
####生成数据集
scaler, train_X, train_y, test_X, test_y = generate_mul_dataset(
2, 1, 1, -90)
xgbt = XGBRegressor()
gbdt = GradientBoostingRegressor()
####加入随机森林模型
rf = RandomForestRegressor()
####加入线性模型
lr = LinearRegression()
sclf = StackingRegressor(regressors=[rf, gbdt, xgbt], meta_regressor=rf)
# 对预测结果进行展示
for clf, label in zip([rf, gbdt, sclf],
['model1', 'Random Forest', 'StackingClassifier']):
clf.fit(train_X, train_y)
lr_train = clf.predict(train_X)
####对模型进行打分
print("模型打分情况：", metrics.r2_score(train_y, lr_train))
yhat = clf.predict(test_X)
# 对预测结果进行展示
plot_mul_results(scaler, test_X, yhat, test_y)
def test_univariate_normal_equation_std():
ne_lr = LinearRegression(solver='normal equation')
ne_lr.fit(X_rm_std, y_std)
assert_almost_equal(ne_lr.w_, expect_rm_std, decimal=3)
def test_univariate_normal_equation_std():
ne_lr = LinearRegression(minibatches=None)
ne_lr.fit(X_rm_std, y_std)
assert_almost_equal(ne_lr.w_, expect_rm_std, decimal=3)
def test_multivariate_normal_equation():
ne_lr = LinearRegression(minibatches=None)
ne_lr.fit(X_rm_lstat, y)
assert_almost_equal(ne_lr.w_, expect_rm_lstat, decimal=3)