def KNearestNCA():
'''
Test the nearest neighbor regressor.
Separate function, to play with NCA.
'''
nca = neighbors.NeighborhoodComponentsAnalysis(random_state=42)
knn = neighbors.KNeighborsRegressor()
nca_pipe = Pipeline([('nca', nca), ('knn', knn)])
#nca_pipe.fit(X_train, y_train)
rmselist = loopTrainSizeFixedMdl(nca_pipe, tsize=30, rep=1000)
random_state=0,
eigen_solver="arpack")
t0 = time()
X_se = embedder.fit_transform(X)
plot_embedding(X_se,
"Spectral embedding of the digits (time %.2fs)" % (time() - t0))
# ----------------------------------------------------------------------
# t-SNE embedding of the digits dataset
print("Computing t-SNE embedding")
tsne = manifold.TSNE(n_components=2, init='pca', random_state=0)
t0 = time()
X_tsne = tsne.fit_transform(X)
plot_embedding(X_tsne,
"t-SNE embedding of the digits (time %.2fs)" % (time() - t0))
# ----------------------------------------------------------------------
# NCA projection of the digits dataset
print("Computing NCA projection")
nca = neighbors.NeighborhoodComponentsAnalysis(init='random',
n_components=2,
random_state=0)
t0 = time()
X_nca = nca.fit_transform(X, y)
plot_embedding(X_nca,
"NCA embedding of the digits (time %.2fs)" % (time() - t0))
plt.show()
fullX, fullY = createSetForSelection()
rank = selection(fullX, fullY, 1)
finalRank = labelAndSortScores(rank, "dane/features.txt")
# WYPISANIE RANKINGU CECH DO PLIKU
#outputFile = open("indexed_sortedRank.txt", "w")
#for record in finalRank:
# outputFile.write(str(record)+"\n")
#outputFile.close()
#initialising custom metric component
weightedMetric = WeightedEucledianMetric()
# initialising analysis component
nca = neighbors.NeighborhoodComponentsAnalysis()
amountOfTests = 25
testOutputFile = open("statisticTestResults.txt", "w")
testOutputFile.write("Testing metrics for averaged " + str(amountOfTests) +
" random tests\n")
testOutputFile.close()
# square root from number of cases in the training set (90% of the whole data set)
numOfNeighbours = int(math.sqrt(len(fullY) * 0.9))
featuresFromTo = [53, 45, 37, 30, 22, 15, 10]
# for now number of neighbors is based on features
# neighboursFromTo = [5,10,15]
for featuresToInclude in featuresFromTo:
