def OMP(problem, **kwargs):
r"""High level description.
Parameters
----------
problem : type
Description
kwargs : dictionary
kwargs['choose'] must be a positive integer
kwargs['coef_tolerance'] must be a nonnegative float
Returns
-------
"""
data_list = [datum['data']['values'] for datum in problem.data]
data = numpy.array(data_list)
OMP = OrthogonalMatchingPursuit(n_nonzero_coefs=kwargs['choose'])
OMP.fit(data.T, problem.goal['data']['values'])
OMP_coefficients = OMP.coef_
optimum = [
problem.data[index] for index, element in enumerate(OMP_coefficients)
if abs(element) > kwargs['coef_tolerance']
]
maximum = OMP.score(data.T, problem.goal['data']['values'])
return (optimum, maximum)
class image_data_repo:
def __init__(self, name='image_', image_feature_dict={}, reconsitution_element_nums=6, error_limit=0.1):
self.name = name
self.image_feature_dict = image_feature_dict.copy()
self.reconsitution_element_nums=reconsitution_element_nums
self.error_limit=error_limit
self.omp=OrthogonalMatchingPursuit(n_nonzero_coefs=reconsitution_element_nums)
def image_nums(self):
return np.size(self.image_feature_dict.keys())
def add_element(self, keys, values):
self.image_feature_dict[keys]=values
def use_image(self, image_feature):
data = np.array(self.image_feature_dict.values()).T
self.omp.fit(data, image_feature)
err = 1 - self.omp.score(data, image_feature)
if err<self.error_limit:
return False,err
else:
return True,err
def update(self):
image_list = self.image_feature_dict.items()
data = np.array([i[1] for i in image_list])
name = [i[0] for i in image_list]
similar_coef = np.amax( np.dot(data.T,data))
filename = name[ np.argmax( similar_coef )]
dst_filename = '';
self.image_feature_dict.pop( filename)
os.system('cp ~/caffe/{} ~/rubbish/'.format(filename))
os.system('rm -f ~/caffe/{}'.format(filename))
return
def _orthogonal_matching_pursuit(response_mat, diff_vec, opt):
""" Calculated n_correctors via orthogonal matching pursuit"""
if opt.n_correctors is None:
raise ValueError(
"n_correctors setting needed for orthogonal matching pursuit.")
# return orthogonal_mp(response_mat, diff_vec, opt.n_correctors)
res = OrthogonalMatchingPursuit(opt.n_correctors).fit(
response_mat, diff_vec)
coef = res.coef_
LOG.debug("Orthogonal Matching Pursuit Results:")
LOG.debug(" Chosen variables: {:s}".format(
str(response_mat.columns.values[coef.nonzero()])))
LOG.debug(" Score: {:f}".format(res.score(response_mat, diff_vec)))
return coef
else:
X = X_train
print X.shape[1]
param_grid={'n_nonzero_coefs':range(1,X.shape[1])}
grid_values= np.array(param_grid.values()).astype('int')
print grid_values
gridSize=grid_values.shape[1]
OMP_regr = OrthogonalMatchingPursuit()
cv_grid_scores_mean,cv_grid_scores_std = grid_search_helper(X, Y_train,OMP_regr, param_grid,gridSize, n_jobs=-1,
n_folds=n_folds, n_repetitions=noRep, scoring=mse_scorer, iid=False)
#Find optimum val and calculate r2_score on testing set or each polynomial
opt_ind = np.where(-cv_grid_scores_mean == np.amin(-cv_grid_scores_mean))
OMP_regr= OrthogonalMatchingPursuit(n_nonzero_coefs= grid_values[0,opt_ind])
print X.shape
OMP_regr.fit(X,Y_train)
print OMP_regr.score(X,Y_train)
if(i>1):
X_val_tr = pfeat.fit_transform(X_val)
else:
X_val_tr = X_val
r2Poly[i-1]=OMP_regr.score(X_val_tr,Y_val)
print r2Poly
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()
# PCA + LARS lars = Lars() lars.fit(reduced_training_features, training_labels) preds = lars.predict(reduced_testing_features) score = lars.score(reduced_testing_features,testing_labels) print 'PCA + LARS Results:' print 'R2 score:', score print 'MAE:', mean_absolute_error(testing_labels,preds) # Orthogonal Matching Pursuit from sklearn.linear_model import OrthogonalMatchingPursuit omp = OrthogonalMatchingPursuit() omp.fit(training_features, training_labels) preds = omp.predict(testing_features) score = omp.score(testing_features,testing_labels) print 'Orthogonal Matching Pursuit Regression Results:' print 'R2 score:', score print 'MAE:', mean_absolute_error(testing_labels,preds), '\n' # PCA + Orthogonal Matching Pursuit omp = OrthogonalMatchingPursuit() omp.fit(reduced_training_features, training_labels) preds = omp.predict(reduced_testing_features) score = omp.score(reduced_testing_features,testing_labels) print 'PCA + Orthogonal Matching Pursuit Results:' print 'R2 score:', score print 'MAE:', mean_absolute_error(testing_labels,preds) # Bayesian Ridge Regression from sklearn.linear_model import BayesianRidge
print "R^2: ", r2
print "\n**********测试OrthogonalMatchingPursuit类**********"
# 在初始化OrthogonalMatchingPursuit类时, 指定参数n_nonzero_coefs, 默认值是None.
omp = OrthogonalMatchingPursuit(n_nonzero_coefs=3)
# 拟合训练集
omp.fit(train_X, train_Y)
# 打印模型的系数
print "系数:", omp.coef_
print "截距:", omp.intercept_
print '训练集R2: ', r2_score(train_Y, omp.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 = omp.predict(test_X)
print "测试集得分:", omp.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, omp.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OrthogonalMatchingPursuitCV类**********"
ompCV = OrthogonalMatchingPursuitCV(cv=5)
# 拟合训练集
ompCV.fit(train_X, train_Y.values.ravel())
# 打印最好的n_nonzero_coefs值
