def apply_NN(trainX, trainY, testX, testY, window, source_pos, target_pos):
# Decision Tree
print("\n Nearest-neighbour-based weighting (Loog, 2015) ")
classifier = ImportanceWeightedClassifier(iwe='nn', loss="dtree")
classifier.fit(trainX, trainY, testX)
pred_naive = classifier.predict(testX)
acc_DT_NN, acc_DT_NN_INFO = check_accuracy(testY, pred_naive)
# Logistic Regression
print("\n Nearest-neighbour-based weighting (Loog, 2015) ")
classifier = ImportanceWeightedClassifier(iwe='nn', loss="logistic")
classifier.fit(trainX, trainY, testX)
pred_naive = classifier.predict(testX)
acc_LR_NN, acc_LR_NN_INFO = check_accuracy(testY, pred_naive)
# Naive Bayes Bernoulli
print("\n Nearest-neighbour-based weighting (Loog, 2015) ")
classifier = ImportanceWeightedClassifier(iwe='nn', loss="berno")
classifier.fit(trainX, trainY, testX)
pred_naive = classifier.predict(testX)
acc_NB_NN, acc_NB_NN_INFO = check_accuracy(testY, pred_naive)
#
return pd.DataFrame(
[{
'window': window,
'source_position': source_pos,
'target_position': target_pos,
'acc_LR_NN': acc_LR_NN,
'acc_LR_NN_INFO': str(acc_LR_NN_INFO),
'acc_DT_NN': acc_DT_NN,
'acc_DT_NN_INFO': str(acc_DT_NN_INFO),
'acc_NB_NN': acc_NB_NN,
'acc_NB_NN_INFO': str(acc_NB_NN_INFO),
}]
)
def apply_KMM(trainX, trainY, testX, testY, window, source_pos, target_pos):
# Decision Tree
print("\n Kernel Mean Matching (Huang et al., 2006) ")
classifier = ImportanceWeightedClassifier(iwe='kmm', loss="dtree")
classifier.fit(trainX, trainY, testX)
pred_naive = classifier.predict(testX)
acc_DT_KMM, acc_DT_KMM_INFO = check_accuracy(testY, pred_naive)
# Logistic Regression
classifier = ImportanceWeightedClassifier(iwe='kmm', loss="logistic")
classifier.fit(trainX, trainY, testX)
pred_naive = classifier.predict(testX)
acc_LR_KMM, acc_LR_KMM_INFO = check_accuracy(testY, pred_naive)
# Naive Bayes Bernoulli
classifier = ImportanceWeightedClassifier(iwe='kmm', loss="berno")
classifier.fit(trainX, trainY, testX)
pred_naive = classifier.predict(testX)
acc_NB_KMM, acc_NB_KMM_INFO = check_accuracy(testY, pred_naive)
#
return pd.DataFrame(
[{
'window': window,
'source_position': source_pos,
'target_position': target_pos,
'acc_LR_KMM': acc_LR_KMM,
'acc_LR_KMM_INFO': str(acc_LR_KMM_INFO),
'acc_DT_KMM': acc_DT_KMM,
'acc_DT_KMM_INFO': str(acc_DT_KMM_INFO),
'acc_NB_KMM': acc_NB_KMM,
'acc_NB_KMM_INFO': str(acc_NB_KMM_INFO),
}]
)
def test_predict():
"""Test for making predictions."""
X = rnd.randn(10, 2)
y = np.hstack((-np.ones((5,)), np.ones((5,))))
Z = rnd.randn(10, 2) + 1
clf = ImportanceWeightedClassifier()
clf.fit(X, y, Z)
u_pred = clf.predict(Z)
labels = np.unique(y)
assert len(np.setdiff1d(np.unique(u_pred), labels)) == 0
def run_6():
X = np.random.randn(10, 2)
y = np.vstack((-np.ones((5, )), np.ones((5, ))))
Z = np.random.randn(10, 2)
from libtlda.iw import ImportanceWeightedClassifier
clf = ImportanceWeightedClassifier(loss='quadratic', iwe='kmm')
clf.fit(X, y, Z)
u_pred = clf.predict(Z)
print(u_pred)
# Classifier based on subspace alignment
clf = StructuralCorrespondenceClassifier(num_pivots=2, num_components=1)
elif classifier == 'rba':
# Robust bias-aware classifier
clf = RobustBiasAwareClassifier(l2=0.1, max_iter=1000)
elif classifier == 'flda':
# Feature-level domain-adaptive classifier
clf = FeatureLevelDomainAdaptiveClassifier(l2=0.1, max_iter=1000)
elif classifier == 'tcpr':
# Target Contrastive Pessimistic Classifier
clf = TargetContrastivePessimisticClassifier(l2=0.1, tolerance=1e-20)
else:
raise ValueError('Classifier not recognized.')
# Train classifier
clf.fit(X, y, Z)
# Make predictions
pred_adapt = clf.predict(Z)
# Compute error rates
err_naive = np.mean(pred_naive != u, axis=0)
err_adapt = np.mean(pred_adapt != u, axis=0)
# Report results
print('Error naive: ' + str(err_naive))
print('Error adapt: ' + str(err_adapt))
# Split out test data
tst_X = X[tst_index, :]
tst_Y = Y[tst_index]
# Define classifiers
clf_n = linear_model.LogisticRegression(C=0.1)
clf_a = ImportanceWeightedClassifier(loss='logistic', l2=0.1)
# Train classifier on data from current and previous days
clf_n.fit(trn_X, trn_Y)
clf_a.fit(trn_X, trn_Y, tst_X)
# Make predictions
preds_n = clf_n.predict(tst_X)
preds_a = clf_a.predict(tst_X)
# Test on data from current day and store
perf_n.append(np.mean(preds_n != tst_Y))
perf_a.append(np.mean(preds_a != tst_Y))
# Store day and rumour
days_array.append(days[d])
rums_array.append(rumour)
# Compact to DataFrame
performance = pd.DataFrame({
'err_n': perf_n,
'err_a': perf_a,
'days': days_array,
'rumours': rums_array
def build_models(trainX, trainY, testX, testY, source_pos, target_pos, window):
#######################
### SEMI-SUPERVISED ###
########################
# Label Propagation
label_prop_model = LabelPropagation(kernel='knn')
label_prop_model.fit(trainX, trainY)
Y_Pred = label_prop_model.predict(testX)
acc_ss_propagation, acc_ss_propagation_INFO = checkAccuracy(testY, Y_Pred)
# Label Spreading
label_prop_models_spr = LabelSpreading(kernel='knn')
label_prop_models_spr.fit(trainX, trainY)
Y_Pred = label_prop_models_spr.predict(testX)
acc_ss_spreading, acc_ss_spreading_INFO = checkAccuracy(testY, Y_Pred)
########################
#### WITHOUT TL ########
########################
# LogisticRegression
modelLR = LogisticRegression()
modelLR.fit(trainX, trainY)
predLR = modelLR.predict(testX)
accLR, acc_LR_INFO = checkAccuracy(testY, predLR)
# DecisionTreeClassifier
modelDT = tree.DecisionTreeClassifier()
modelDT.fit(trainX, trainY)
predDT = modelDT.predict(testX)
accDT, acc_DT_INFO = checkAccuracy(testY, predDT)
# BernoulliNB
modelNB = BernoulliNB()
modelNB.fit(trainX, trainY)
predND = modelNB.predict(testX)
accNB, acc_NB_INFO = checkAccuracy(testY, predND)
#
print("WITHOUT TL ACC_LR:", accLR, " ACC_DT:", accDT, " ACC_NB:", accNB)
########################
#### WITH TL ########
########################
####################################################
### Kernel Mean Matching (Huang et al., 2006)
###
# Decision Tree
print("\n Kernel Mean Matching (Huang et al., 2006) ")
classifier = ImportanceWeightedClassifier(iwe='kmm', loss="dtree")
classifier.fit(trainX, trainY, testX)
pred_naive = classifier.predict(testX)
acc_DT_KMM, acc_DT_KMM_INFO = checkAccuracy(testY, pred_naive)
print("ACC:", acc_DT_KMM)
# Logistic Regression
classifier = ImportanceWeightedClassifier(iwe='kmm', loss="logistic")
classifier.fit(trainX, trainY, testX)
pred_naive = classifier.predict(testX)
acc_LR_KMM, acc_LR_KMM_INFO = checkAccuracy(testY, pred_naive)
print("ACC:", acc_LR_KMM)
# Naive Bayes Bernoulli
classifier = ImportanceWeightedClassifier(iwe='kmm', loss="berno")
classifier.fit(trainX, trainY, testX)
pred_naive = classifier.predict(testX)
acc_NB_KMM, acc_NB_KMM_INFO = checkAccuracy(testY, pred_naive)
print("ACC:", acc_NB_KMM)
####################################################
### Nearest-neighbour-based weighting (Loog, 2015)
###
# Decision Tree
print("\n Nearest-neighbour-based weighting (Loog, 2015) ")
classifier = ImportanceWeightedClassifier(iwe='nn', loss="dtree")
classifier.fit(trainX, trainY, testX)
pred_naive = classifier.predict(testX)
acc_DT_NN, acc_DT_NN_INFO = checkAccuracy(testY, pred_naive)
print("ACC:", acc_DT_NN)
# Logistic Regression
print("\n Nearest-neighbour-based weighting (Loog, 2015) ")
classifier = ImportanceWeightedClassifier(iwe='nn', loss="logistic")
classifier.fit(trainX, trainY, testX)
pred_naive = classifier.predict(testX)
acc_LR_NN, acc_LR_NN_INFO = checkAccuracy(testY, pred_naive)
print("ACC:", acc_LR_NN)
# Naive Bayes Bernoulli
print("\n Nearest-neighbour-based weighting (Loog, 2015) ")
classifier = ImportanceWeightedClassifier(iwe='nn', loss="berno")
classifier.fit(trainX, trainY, testX)
pred_naive = classifier.predict(testX)
acc_NB_NN, acc_NB_NN_INFO = checkAccuracy(testY, pred_naive)
print("ACC:", acc_NB_NN)
####################################################
### Transfer Component Analysis (Pan et al, 2009)
###
# Decision Tree
print("\n Transfer Component Analysis (Pan et al, 2009)")
classifier = TransferComponentClassifier(loss="dtree", num_components=6)
classifier.fit(trainX, trainY, testX)
pred_naive = classifier.predict(testX)
acc_DT_TCA, acc_DT_TCA_INFO = checkAccuracy(testY, pred_naive)
print("ACC:", acc_DT_TCA)
# Logistic Regression
classifier = TransferComponentClassifier(loss="logistic", num_components=6)
classifier.fit(trainX, trainY, testX)
pred_naive = classifier.predict(testX)
acc_LR_TCA, acc_LR_TCA_INFO = checkAccuracy(testY, pred_naive)
print("ACC:", acc_LR_TCA)
# Naive Bayes Bernoulli
classifier = TransferComponentClassifier(loss="berno", num_components=6)
classifier.fit(trainX, trainY, testX)
pred_naive = classifier.predict(testX)
acc_NB_TCA, acc_NB_TCA_INFO = checkAccuracy(testY, pred_naive)
print("ACC:", acc_NB_TCA)
####################################################
### Subspace Alignment (Fernando et al., 2013)
###
# Decision Tree
print("\n Subspace Alignment (Fernando et al., 2013) ")
classifier = SubspaceAlignedClassifier(loss="dtree")
classifier.fit(trainX, trainY, testX)
pred_naive = classifier.predict(testX)
acc_DT_SA, acc_DT_SA_INFO = checkAccuracy(testY, pred_naive)
print("ACC:", acc_DT_SA)
# Logistic Regression
print("\n Subspace Alignment (Fernando et al., 2013) ")
classifier = SubspaceAlignedClassifier(loss="logistic")
classifier.fit(trainX, trainY, testX)
pred_naive = classifier.predict(testX)
acc_LR_SA, acc_LR_SA_INFO = checkAccuracy(testY, pred_naive)
print("ACC:", acc_LR_SA)
# Naive Bayes Bernoulli
print("\n Subspace Alignment (Fernando et al., 2013) ")
classifier = SubspaceAlignedClassifier(loss="berno")
classifier.fit(trainX, trainY, testX)
pred_naive = classifier.predict(testX)
acc_NB_SA, acc_NB_SA_INFO = checkAccuracy(testY, pred_naive)
print("ACC:", acc_NB_SA)
#################################
############# ENSEMBLE ##########
#################################
classifier_SA_DT = SubspaceAlignedClassifier(loss="dtree")
classifier_SA_LR = SubspaceAlignedClassifier(loss="logistic")
classifier_SA_NB = SubspaceAlignedClassifier(loss="berno")
classifier_TCA_DT = TransferComponentClassifier(loss="dtree")
classifier_TCA_LR = TransferComponentClassifier(loss="logistic")
classifier_TCA_NB = TransferComponentClassifier(loss="berno")
classifier_NN_DT = ImportanceWeightedClassifier(iwe='nn', loss="dtree")
classifier_NN_LR = ImportanceWeightedClassifier(iwe='nn', loss="logistic")
classifier_NN_NB = ImportanceWeightedClassifier(iwe='nn', loss="berno")
classifier_KMM_DT = ImportanceWeightedClassifier(iwe='kmm', loss="dtree")
classifier_KMM_LR = ImportanceWeightedClassifier(iwe='kmm',
loss="logistic")
classifier_KMM_NB = ImportanceWeightedClassifier(iwe='kmm', loss="berno")
#
eclf = EnsembleClassifier(
clfs=[classifier_TCA_DT, classifier_NN_DT, classifier_KMM_DT])
eclf.fit(trainX, trainY, testX)
pred = eclf.predict_v2(testX)
acc_ENSEMBLE, acc_ENSEMBLE_INFO = checkAccuracy(testY, pred)
########################
#### RETURN ########
########################
return pd.DataFrame([{
'window': window,
'source_position': source_pos,
'target_position': target_pos,
'acc_SS_propagation': acc_ss_propagation,
'acc_SS_propagation_INFO': acc_ss_propagation_INFO,
'acc_SS_spreading': acc_ss_spreading,
'acc_SS_spreading_INFO': acc_ss_spreading_INFO,
'acc_ENSEMBLE': acc_ENSEMBLE,
'acc_LR': accLR,
'acc_LR_INFO': str(acc_LR_INFO),
'acc_DT': accDT,
'acc_DT_INFO': str(acc_DT_INFO),
'acc_NB': accNB,
'acc_NB_INFO': str(acc_NB_INFO),
'acc_LR_KMM': acc_LR_KMM,
'acc_LR_KMM_INFO': str(acc_LR_KMM_INFO),
'acc_LR_NN': acc_LR_NN,
'acc_LR_NN_INFO': str(acc_LR_NN_INFO),
'acc_LR_TCA': acc_LR_TCA,
'acc_LR_TCA_INFO': str(acc_LR_TCA_INFO),
'acc_LR_SA': acc_LR_SA,
'acc_LR_SA_INFO': str(acc_LR_SA_INFO),
'acc_DT_KMM': acc_DT_KMM,
'acc_DT_KMM_INFO': str(acc_DT_KMM_INFO),
'acc_DT_NN': acc_DT_NN,
'acc_DT_NN_INFO': str(acc_DT_NN_INFO),
'acc_DT_TCA': acc_DT_TCA,
'acc_DT_TCA_INFO': str(acc_DT_TCA_INFO),
'acc_DT_SA': acc_DT_SA,
'acc_DT_SA_INFO': str(acc_DT_SA_INFO),
'acc_NB_KMM': acc_NB_KMM,
'acc_NB_KMM_INFO': str(acc_NB_KMM_INFO),
'acc_NB_NN': acc_NB_NN,
'acc_NB_NN_INFO': str(acc_NB_NN_INFO),
'acc_NB_TCA': acc_NB_TCA,
'acc_NB_TCA_INFO': str(acc_NB_TCA_INFO),
'acc_NB_SA': acc_NB_SA,
'acc_NB_SA_INFO': str(acc_NB_SA_INFO)
}])
def run_5(n_samples=100):
from libtlda.iw import ImportanceWeightedClassifier
clf = ImportanceWeightedClassifier(loss='quadratic', iwe='kmm')
# X ~ N(0.5, 0.5²)
# Z ~ N(0.0, 0.3²)
x = np.random.normal(0.5, 0.5**2, (n_samples, 1))
z = np.random.normal(0, 0.3**2, (n_samples, 1))
x_noise = np.random.normal(0, 0.07, (n_samples, 1))
z_noise = np.random.normal(0, 0.03, (n_samples, 1))
def data_func(var):
return var**3 - var
y = data_func(x)
y = np.array(y)
y = y.ravel()
# + bruit
X = x + x_noise
Z = z + z_noise
# distribution différente à approximer avec une distrib initiale
y_bis = data_func(z)
y_bis = np.array(y_bis)
y_bis = y_bis.ravel()
print(X.shape)
print(y.shape)
print(Z.shape)
print(y_bis.shape)
clf.fit(X, y, Z)
preds = clf.predict(Z)
print(np.linalg.norm(preds - Z))
from sklearn.linear_model import LinearRegression
clf_linear = LinearRegression()
clf_linear.fit(Z, y_bis)
true_coefs = clf_linear.coef_
# print(clf.get_weights())
print(preds)
# plot facilities
x_range = np.linspace(-0.4, 1.2, 100)
kmm_line = x_range * preds
true_line = x_range * true_coefs
plt.axis([-0.4, 1.2, -0.5, 1])
plt.scatter(X, y, label='X points', color='blue', marker='o')
plt.plot(x_range, data_func(x_range), label='X distribution', color='blue')
plt.scatter(Z, y_bis, label='Z points', color='red', marker='+')
plt.plot(x_range, kmm_line, label='Z kmm regression line', color='red')
plt.plot(x_range, true_line, label='Z OLS line', color='black')
plt.legend()
plt.show()
"""