def test_simple_vs_refined_algorithm(theta, fit_path):
# Test the consistency of the results between the 2 versions of
# the algorithm.
# Simple Algorithm (2 steps of Lasso Lars)
lasso1 = LassoLars(alpha=alpha)
lasso1.fit(X_train, y_train)
X1 = X_train.copy()
X1[:, lasso1.coef_ == 0] = 0
lasso2 = LassoLars(alpha=alpha*theta)
lasso2.fit(X1, y_train)
pred_simple = lasso2.predict(X_test)
# Refined Algorithm
relasso = RelaxedLassoLars(alpha=alpha, theta=theta, fit_path=fit_path)
relasso.fit(X_train, y_train)
pred_refined = relasso.predict(X_test)
assert_array_almost_equal(pred_simple, pred_refined)
assert_array_almost_equal(lasso2.coef_, relasso.coef_)
assert_almost_equal(lasso2.score(X_test, y_test),
relasso.score(X_test, y_test),
decimal=2)
# LassoLars Regression import numpy as np from sklearn import datasets from sklearn.linear_model import LassoLars # load the iris datasets dataset = datasets.load_diabetes() # fit a LASSO using LARS model to the data model = LassoLars(alpha=0.1) model.fit(dataset.data, dataset.target) print(model) # make predictions expected = dataset.target predicted = model.predict(dataset.data) # summarize the fit of the model mse = np.mean((predicted-expected)**2) print(mse) print(model.score(dataset.data, dataset.target))
# LassoLars Regression # The Least Angle Regression (LARS) can be used as an alternative method for calculating Least Absolute Shrinkage # and Selection Operator (LASSO) fit. import numpy as np from sklearn import datasets from sklearn.linear_model import LassoLars # load the iris datasets dataset = datasets.load_diabetes() # fit a LASSO using LARS model to the data model = LassoLars(alpha=0.1) model.fit(dataset.data, dataset.target) print(model) # make predictions expected = dataset.target predicted = model.predict(dataset.data) # summarize the fit of the model mse = np.mean((predicted - expected)**2) print(mse) print(model.score(dataset.data, dataset.target))
def task2(data):
df = data
dfreg = df.loc[:, ['Adj Close', 'Volume']]
dfreg['HL_PCT'] = (df['High'] - df['Low']) / df['Close'] * 100.0
dfreg['PCT_change'] = (df['Close'] - df['Open']) / df['Open'] * 100.0
# Drop missing value
dfreg.fillna(value=-99999, inplace=True)
# We want to separate 1 percent of the data to forecast
forecast_out = int(math.ceil(0.01 * len(dfreg)))
# Separating the label here, we want to predict the AdjClose
forecast_col = 'Adj Close'
dfreg['label'] = dfreg[forecast_col].shift(-forecast_out)
X = np.array(dfreg.drop(['label'], 1))
# Scale the X so that everyone can have the same distribution for linear regression
X = preprocessing.scale(X)
# Finally We want to find Data Series of late X and early X (train) for model generation and evaluation
X_lately = X[-forecast_out:]
X = X[:-forecast_out]
# Separate label and identify it as y
y = np.array(dfreg['label'])
y = y[:-forecast_out]
#Split data
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.2,
random_state=0)
##################
##################
##################
# Linear regression
clfreg = LinearRegression(n_jobs=-1)
clfreg.fit(X_train, y_train)
# Quadratic Regression 2
clfpoly2 = make_pipeline(PolynomialFeatures(2), Ridge())
clfpoly2.fit(X_train, y_train)
# Quadratic Regression 3
clfpoly3 = make_pipeline(PolynomialFeatures(3), Ridge())
clfpoly3.fit(X_train, y_train)
# KNN Regression
clfknn = KNeighborsRegressor(n_neighbors=2)
clfknn.fit(X_train, y_train)
# Lasso Regression
clflas = Lasso()
clflas.fit(X_train, y_train)
# Multitask Lasso Regression
# clfmtl = MultiTaskLasso(alpha=1.)
# clfmtl.fit(X_train, y_train).coef_
# Bayesian Ridge Regression
clfbyr = BayesianRidge()
clfbyr.fit(X_train, y_train)
# Lasso LARS Regression
clflar = LassoLars(alpha=.1)
clflar.fit(X_train, y_train)
# Orthogonal Matching Pursuit Regression
clfomp = OrthogonalMatchingPursuit(n_nonzero_coefs=2)
clfomp.fit(X_train, y_train)
# Automatic Relevance Determination Regression
clfard = ARDRegression(compute_score=True)
clfard.fit(X_train, y_train)
# Logistic Regression
# clflgr = linear_model.LogisticRegression(penalty='l1', solver='saga', tol=1e-6, max_iter=int(1e6), warm_start=True)
# coefs_ = []
# for c in cs:
# clflgr.set_params(C=c)
# clflgr.fit(X_train, y_train)
# coefs_.append(clflgr.coef_.ravel().copy())
clfsgd = SGDRegressor(random_state=0, max_iter=1000, tol=1e-3)
clfsgd.fit(X_train, y_train)
##################
##################
##################
#Create confindence scores
confidencereg = clfreg.score(X_test, y_test)
confidencepoly2 = clfpoly2.score(X_test, y_test)
confidencepoly3 = clfpoly3.score(X_test, y_test)
confidenceknn = clfknn.score(X_test, y_test)
confidencelas = clflas.score(X_test, y_test)
# confidencemtl = clfmtl.score(X_test, y_test)
confidencebyr = clfbyr.score(X_test, y_test)
confidencelar = clflar.score(X_test, y_test)
confidenceomp = clfomp.score(X_test, y_test)
confidenceard = clfard.score(X_test, y_test)
confidencesgd = clfsgd.score(X_test, y_test)
# results
print('The linear regression confidence is:', confidencereg * 100)
print('The quadratic regression 2 confidence is:', confidencepoly2 * 100)
print('The quadratic regression 3 confidence is:', confidencepoly3 * 100)
print('The knn regression confidence is:', confidenceknn * 100)
print('The lasso regression confidence is:', confidencelas * 100)
# print('The lasso regression confidence is:',confidencemtl*100)
print('The Bayesian Ridge regression confidence is:', confidencebyr * 100)
print('The Lasso LARS regression confidence is:', confidencelar * 100)
print('The OMP regression confidence is:', confidenceomp * 100)
print('The ARD regression confidence is:', confidenceard * 100)
print('The SGD regression confidence is:', confidencesgd * 100)
#Create new columns
forecast_reg = clfreg.predict(X_lately)
forecast_pol2 = clfpoly2.predict(X_lately)
forecast_pol3 = clfpoly3.predict(X_lately)
forecast_knn = clfknn.predict(X_lately)
forecast_las = clflas.predict(X_lately)
forecast_byr = clfbyr.predict(X_lately)
forecast_lar = clflar.predict(X_lately)
forecast_omp = clfomp.predict(X_lately)
forecast_ard = clfard.predict(X_lately)
forecast_sgd = clfsgd.predict(X_lately)
#Process all new columns data
dfreg['Forecast_reg'] = np.nan
last_date = dfreg.iloc[-1].name
last_unix = last_date
next_unix = last_unix + datetime.timedelta(days=1)
for i in forecast_reg:
next_date = next_unix
next_unix += datetime.timedelta(days=1)
dfreg.loc[next_date] = [np.nan for _ in range(len(dfreg.columns))]
dfreg['Forecast_reg'].loc[next_date] = i
dfreg['Forecast_pol2'] = np.nan
last_date = dfreg.iloc[-26].name
last_unix = last_date
next_unix = last_unix + datetime.timedelta(days=1)
for i in forecast_pol2:
next_date = next_unix
next_unix += datetime.timedelta(days=1)
dfreg['Forecast_pol2'].loc[next_date] = i
dfreg['Forecast_pol3'] = np.nan
last_date = dfreg.iloc[-26].name
last_unix = last_date
next_unix = last_unix + datetime.timedelta(days=1)
for i in forecast_pol3:
next_date = next_unix
next_unix += datetime.timedelta(days=1)
dfreg['Forecast_pol3'].loc[next_date] = i
dfreg['Forecast_knn'] = np.nan
last_date = dfreg.iloc[-26].name
last_unix = last_date
next_unix = last_unix + datetime.timedelta(days=1)
for i in forecast_knn:
next_date = next_unix
next_unix += datetime.timedelta(days=1)
dfreg['Forecast_knn'].loc[next_date] = i
dfreg['Forecast_las'] = np.nan
last_date = dfreg.iloc[-26].name
last_unix = last_date
next_unix = last_unix + datetime.timedelta(days=1)
for i in forecast_las:
next_date = next_unix
next_unix += datetime.timedelta(days=1)
dfreg['Forecast_las'].loc[next_date] = i
dfreg['Forecast_byr'] = np.nan
last_date = dfreg.iloc[-26].name
last_unix = last_date
next_unix = last_unix + datetime.timedelta(days=1)
for i in forecast_byr:
next_date = next_unix
next_unix += datetime.timedelta(days=1)
dfreg['Forecast_byr'].loc[next_date] = i
dfreg['Forecast_lar'] = np.nan
last_date = dfreg.iloc[-26].name
last_unix = last_date
next_unix = last_unix + datetime.timedelta(days=1)
for i in forecast_lar:
next_date = next_unix
next_unix += datetime.timedelta(days=1)
dfreg['Forecast_lar'].loc[next_date] = i
dfreg['Forecast_omp'] = np.nan
last_date = dfreg.iloc[-26].name
last_unix = last_date
next_unix = last_unix + datetime.timedelta(days=1)
for i in forecast_omp:
next_date = next_unix
next_unix += datetime.timedelta(days=1)
dfreg['Forecast_omp'].loc[next_date] = i
dfreg['Forecast_ard'] = np.nan
last_date = dfreg.iloc[-26].name
last_unix = last_date
next_unix = last_unix + datetime.timedelta(days=1)
for i in forecast_ard:
next_date = next_unix
next_unix += datetime.timedelta(days=1)
dfreg['Forecast_ard'].loc[next_date] = i
dfreg['Forecast_sgd'] = np.nan
last_date = dfreg.iloc[-26].name
last_unix = last_date
next_unix = last_unix + datetime.timedelta(days=1)
for i in forecast_sgd:
next_date = next_unix
next_unix += datetime.timedelta(days=1)
dfreg['Forecast_sgd'].loc[next_date] = i
return dfreg.index.format(formatter=lambda x: x.strftime(
'%Y-%m-%d')), dfreg['Adj Close'].to_list(
), dfreg['Forecast_reg'].to_list(), dfreg['Forecast_pol2'].to_list(
), dfreg['Forecast_pol3'].to_list(), dfreg['Forecast_knn'].to_list(
), dfreg['Forecast_las'].to_list(), dfreg['Forecast_byr'].to_list(
), dfreg['Forecast_lar'].to_list(), dfreg['Forecast_omp'].to_list(
), dfreg['Forecast_ard'].to_list(), dfreg['Forecast_sgd'].to_list()
#!/usr/bin/env python
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LassoLars
data = pd.read_csv("dataset.csv", header=0)
X = data.loc[:, ["Commune", "Etage", "Superficie", "Piece"]].values
Y = data.loc[:, "Prix"].values
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2)
regressor = LassoLars(alpha=0.1)
regressor.fit(X_train, Y_train)
score = regressor.score(X_test, Y_test)
print(score)
l_reg=LinearRegression() lasso_reg=LassoLars() # In[380]: l_reg.fit(X_train,y_train) # In[382]: l_reg.score(X_test,y_test) # In[383]: lasso_reg.fit(X_train,y_train) # In[384]: lasso_reg.score(X_test,y_test)
model_EN.fit(X_train, y_train) model_EN.score(X_train, y_train) print "Score of Elastic-net on train data: ", model_EN.score(X_train, y_train) print "Score of Elastic-net on test data: ", model_EN.score(X_test, y_test) print "L1 ratio: ", models.l1_ratio_ print "Alpha: ", models.alpha_ # At this point we should be our final model on the entire dataset # using previously tunned parameters # Lasso-lars models = LassoLarsCV(max_n_alphas=40, verbose=1, cv=folds) models.fit(X_train, y_train) model_LL = LassoLars(alpha=models.alpha_) model_LL.fit(X_train, y_train) print "Score of Lasso-Lars on train data: ", model_LL.score(X_train, y_train) print "Score of Lasso-Lars on test data: ", model_LL.score(X_test, y_test) ''' =============== PCA ================== 3 first components explain only ~33% of the variance when applied non-normalized data You can test it by copying following code to preprocessing.py from sklearn.decomposition import PCA pca = PCA(3) X = pca.fit_transform(data.iloc[:,1:]) print pca.explained_variance_ratio_ Actually I was surprised by how poorly it performed so I even wrote a simple MatLab script because it didn't feel right, but it outputs exactly same numbers.
mse = mean_squared_error(y_test, lasso_pred)
print("Root Mean Squared Error: ", np.sqrt(mse))
fig = plt.figure(figsize=[10, 8])
ax = plt.subplot(111)
ax.plot(y_test.index, lasso_pred, label='Predicted')
ax.plot(y_test, label='Test')
ax.legend()
plt.show()
# Evaluation
confidence_lr = lr.score(X_test, y_test)
confidence_poly2 = poly2.score(X_test, y_test)
confidence_poly3 = poly3.score(X_test, y_test)
confidence_knn = knn.score(X_test, y_test)
confidence_lasso = lasso.score(X_test, y_test)
print("Results: ", confidence_lr, confidence_poly2, confidence_poly3,
confidence_knn, confidence_lasso)
# all on one graph
fig = plt.figure(figsize=[10, 8])
ax = plt.subplot(111)
ax.plot(y_test.index, lasso_pred, label='Lasso', color='red')
ax.plot(y_test.index, knn_pred, label='KNN', color='blue')
ax.plot(y_test.index, poly2_pred, label='Poly2', color='green')
ax.plot(y_test.index, poly3_pred, label='Poly3', color='orange')
ax.plot(y_test.index, y_pred_lr, label='LR', color='cyan')
ax.plot(y_test, label='Test', color='magenta')
ax.legend()
from sklearn.model_selection import train_test_split
# 准备数据
boston = load_boston()
X,Y = boston.data,boston.target
X_train,X_test,Y_train,Y_test = train_test_split(X,Y,test_size=.3)
'''
利用LARS的lasso回归：
不知道说什么了，因为完全不了解
'''
rg = LassoLars(alpha=1.0, fit_intercept=True, verbose=False, normalize=True, precompute='auto', max_iter=500, eps=2.2204460492503131e-16, copy_X=True, fit_path=True, positive=False)
rg.fit(X_train,Y_train)
Y_pre = rg.predict(X_test)
rg.score(X_test,Y_test)
rg.coef_
rg.intercept_
'''
alpha
fit_intercept
verbose
normalize
precompute
max_iter
eps
copy_X
fit_path
positive
'''
poly = PolynomialFeatures(include_bias=False)
X_poly = poly.fit_transform(scale(X))
print(X_poly.shape) # 104 features
X_train, X_test, y_train, y_test = train_test_split(X_poly, y, random_state=0)
################ Lasso-Lars ################
from sklearn.linear_model import LassoLars
from sklearn.pipeline import make_pipeline
from sklearn.model_selection import cross_val_score
lasso_lars = LassoLars(alpha=0.01)
lasso_lars.fit(X_train, y_train)
lasso_lars.score(X_test, y_test)
np.mean(cross_val_score(lasso_lars, X_train, y_train, cv=10))
###### Tuning alpha parameter
from sklearn.model_selection import GridSearchCV
param_grid = {'alpha': np.logspace(-3, 3, 13)}
grid = GridSearchCV(lasso_lars, param_grid, cv=10)
grid.fit(X_train, y_train)
print(grid.best_params_)
print(grid.best_score_)
lm = lm.fit(X_final, y) # plot regression coefficient fig2, ax2 = plt.subplots() plt.bar(ivs, lm.coef_) plt.tight_layout() # visualize dim-reduced data along the two dimension with the greatest coefficients indices = np.argsort(np.abs(lm.coef_)) y_tmp = y - np.min(y) y_tmp /= np.max(y_tmp) cmap = plt.cm.inferno colors = cmap(y_tmp) #colors[:, 3] = y_tmp fig, axes = plt.subplots(nrows=3) plt.sca(axes[0]) plt.scatter(X_final[:, indices[-1]], X_final[:, indices[-2]], c=colors) axes[0].set_xlabel(ivs[indices[-1]]) axes[0].set_ylabel(ivs[indices[-2]]) plt.sca(axes[1]) plt.scatter(X_final[:, indices[-1]], X_final[:, indices[-3]], c=colors) axes[1].set_xlabel(ivs[indices[-1]]) axes[1].set_ylabel(ivs[indices[-3]]) plt.sca(axes[2]) plt.scatter(X_final[:, indices[-2]], X_final[:, indices[-3]], c=colors) axes[2].set_xlabel(ivs[indices[-2]]) axes[2].set_ylabel(ivs[indices[-3]]) plt.tight_layout() print(lm.score(X_final, y)) plt.show()
print "R^2: ", r2
print "\n**********测试LassoLars类**********"
# 在初始化LassoLars类时, 指定超参数α, 默认值是1.0.
lassoLars = LassoLars(alpha=0.005)
# 拟合训练集
lassoLars.fit(train_X, train_Y)
# 打印模型的系数
print "系数:", lassoLars.coef_
print "截距:", lassoLars.intercept_
print '训练集R2: ', r2_score(train_Y, lassoLars.predict(train_X))
# 对于线性回归模型, 一般使用均方误差(Mean Squared Error,MSE)或者
# 均方根误差(Root Mean Squared Error,RMSE)在测试集上的表现来评该价模型的好坏.
test_Y_pred = lassoLars.predict(test_X)
print "测试集得分:", lassoLars.score(test_X, test_Y)
print "测试集MSE:", mean_squared_error(test_Y, test_Y_pred)
print "测试集RMSE:", np.sqrt(mean_squared_error(test_Y, test_Y_pred))
print "测试集R2:", r2_score(test_Y, test_Y_pred)
tss, rss, ess, r2 = xss(Y, lassoLars.predict(X))
print "TSS(Total Sum of Squares): ", tss
print "RSS(Residual Sum of Squares): ", rss
print "ESS(Explained Sum of Squares): ", ess
print "R^2: ", r2
print "\n**********测试LassoLarsCV类**********"
lassoLarscv = LassoLarsCV(cv=5)
# 拟合训练集
lassoLarscv.fit(train_X, train_Y.values.ravel())
# 打印模型的系数