def randproj(tx, ty, rx, ry):
compressor = RandomProjection(tx[1].size)
newtx = compressor.fit_transform(tx)
compressor = RandomProjection(tx[1].size)
newrx = compressor.fit_transform(rx)
#em(newtx, ty, newrx, ry, add="wRPtr", times=10)
#km(newtx, ty, newrx, ry, add="wRPtr", times=10)
nn(newtx, ty, newrx, ry, add="wRP")
def caller(tx, ty, rx, ry):
nums = [4,8,12,16]
for n in nums:
print("PCA")
print(n)
compressor = PCA(n_components = n)
compressor.fit(tx, y=ty)
newtx = compressor.transform(tx)
newrx = compressor.transform(rx)
nnTable(newtx, ty, newrx, ry, alg="PCA")
for n in nums:
print("ICA")
print(n)
compressor = ICA(n_components = n)
compressor.fit(tx, y=ty)
newtx = compressor.transform(tx)
newrx = compressor.transform(rx)
nnTable(newtx, ty, newrx, ry, alg="ICA")
for n in nums:
print("RandProj")
print(n)
compressor = RandomProjection(n)
compressor.fit(tx, y=ty)
newtx = compressor.transform(tx)
newrx = compressor.transform(rx)
nnTable(newtx, ty, newrx, ry, alg="PCA")
for n in nums:
print("kbest")
print(n)
compressor = best(k=n)
compressor.fit(tx, y=ty)
newtx = compressor.transform(tx)
newrx = compressor.transform(rx)
nnTable(newtx, ty, newrx, ry, alg="PCA")
def graphCallerNN(tx, ty, rx, ry):
n = tx[1].size/2
compressor = PCA(n_components = n)
compressor.fit(tx, y=ty)
newtx = compressor.transform(tx)
newrx = compressor.transform(rx)
newtx = oneem(newtx, ty, newrx, ry)
myNN(newtx, ty, newrx, ry, "EM-PCA")
# nnTable(newtx, ty, newrx, ry, alg="EM-PCA")
compressor = ICA(n_components = n)
compressor.fit(tx, y=ty)
newtx = compressor.transform(tx)
newrx = compressor.transform(rx)
newtx = oneem(newtx, ty, newrx, ry)
nnTable(newtx, ty, newrx, ry, alg="EM-ICA")
myNN(newtx, ty, newrx, ry, "EM-Ica")
compressor = RandomProjection(n)
compressor.fit(tx, y=ty)
newtx = compressor.transform(tx)
newrx = compressor.transform(rx)
newtx = oneem(newtx, ty, newrx, ry)
nnTable(newtx, ty, newrx, ry, alg="EM-RP")
myNN(newtx, ty, newrx, ry, "EM-RP")
compressor = best(k=n)
compressor.fit(tx, y=ty)
newtx = compressor.transform(tx)
newrx = compressor.transform(rx)
newtx = oneem(newtx, ty, newrx, ry)
nnTable(newtx, ty, newrx, ry, alg="EM-KB")
myNN(newtx, ty, newrx, ry, "EM-KB")
def randproj(tx, ty, rx, ry):
compressor = RandomProjection(tx[1].size)
compressor.fit(tx, y=ty)
newtx = compressor.transform(tx)
newrx = compressor.transform(rx)
em(newtx, ty, newrx, ry, add="wRPtr", times=10)
km(newtx, ty, newrx, ry, add="wRPtr", times=10)
nn(newtx, ty, newrx, ry, add="wRPtr")
def randproj(tx, ty, rx, ry, dataset):
compressor = RandomProjection(tx[1].size/2)
compressor = RandomProjection(tx[1].size/2)
compressor.fit(tx, y=ty)
pca = RandomProjection(2)
pca.fit(tx)
result=pd.DataFrame(pca.transform(tx), columns=['RP%i' % i for i in range(2)])
my_color = pd.Series(ty).astype('category').cat.codes
fig = plt.figure()
ax = fig.add_subplot(111, projection='2d')
ax = fig.add_subplot(111)
ax.scatter(result['RP0'], result['RP1'], c=my_color, cmap="Dark2_r", s=60)
ax.set_xlabel("RP1")
ax.set_ylabel("RP2")
ax.set_title("RP on the "+ dataset + " data set")
plt.show()
Store results of PCA in a data frame
result=pd.DataFrame(compressor.transform(tx), columns=['ICA%i' % i for i in range(3)])
my_color = pd.Series(ty).astype('category').cat.codes
fig = plt.figure()
ax = fig.add_subplot(111, projection='3d')
ax.scatter(result['ICA0'], result['ICA1'], result['ICA2'], c=my_color, cmap="Dark2_r", s=60)
xAxisLine = ((min(result['ICA0']), max(result['ICA0'])), (0, 0), (0,0))
ax.plot(xAxisLine[0], xAxisLine[1], xAxisLine[2], 'r')
yAxisLine = ((0, 0), (min(result['ICA1']), max(result['ICA1'])), (0,0))
ax.plot(yAxisLine[0], yAxisLine[1], yAxisLine[2], 'r')
zAxisLine = ((0, 0), (0,0), (min(result['ICA2']), max(result['ICA2'])))
ax.plot(zAxisLine[0], zAxisLine[1], zAxisLine[2], 'r')
ax.set_xlabel("RP1")
ax.set_ylabel("RP2")
ax.set_zlabel("RP3")
ax.set_title("RP on the Car data set")
plt.show()
reduced_data = RandomProjection(2).fit_transform(tx)
em(tx, ty, rx, ry, reduced_data, add="", times=4, dataset=dataset, alg="RP")
newtx = compressor.transform(tx)
newrx = compressor.transform(rx)
em(newtx, ty, newrx, ry, [], add="", times=4, dataset=dataset, alg="RP")
em(newtx, ty, newrx, ry, RandomProjection(n_components=2).fit_transform(tx), add="wRPtr", times=9, dataset=dataset, alg="RandProj")
# nn(newtx, ty, newrx, ry, add="wRPtr")
myNN(newtx, ty, newrx, ry, "RandProj")
# Scale the data
scaler = StandardScaler()
scaler.fit(X)
X_train_std = scaler.transform(X)
X_test_std = scaler.transform(X)
X_toTransform = X_train_std
y_input = y
######
# Run initial Projection Analysis with 1:n components
######
reconstructionErrors = []
maxComponents = 46
minComponents = 1
for i in range(minComponents, maxComponents):
projection = RandomProjection(n_components=i)
projection.fit(X_toTransform)
reconstructionErrors.append(reconstructionError(projection, X_toTransform))
# print diagnostics
#print('Components \n', projection.components_)
print('Number of Components ', projection.n_components_)
print('Reconstruction Error ',
reconstructionError(projection, X_toTransform))
print(reconstructionErrors)
print('Min reconstruction error: ' % np.max(reconstructionErrors), 'with ',
np.max(reconstructionErrors == np.max(reconstructionErrors)) + 1,
'components')
# Save reconstruction error plot
with plt.style.context('seaborn-whitegrid'):
def kmtable(tx, ty, rx, ry, dataset=""):
processed = []
adj_rand = []
v_meas = []
mutual_info = []
adj_mutual_info = []
sil = []
inertia = []
compressor = PCA(n_components = tx[1].size/2)
compressor.fit(tx, y=ty)
pcatx = compressor.transform(tx)
pcarx = compressor.transform(rx)
p = []
compressor = ICA(n_components = tx[1].size/2)
compressor.fit(tx, y=ty)
icatx = compressor.transform(tx)
icarx = compressor.transform(rx)
ic = []
compressor = RandomProjection(tx[1].size/2)
compressor.fit(tx, y=ty)
rptx = compressor.transform(tx)
rprx = compressor.transform(rx)
r = []
compressor = best(k=tx[1].size/2)
compressor.fit(tx, y=ty)
kbtx = compressor.transform(tx)
kbrx = compressor.transform(rx)
k = []
for i in range(2,8):
# clusters = {x:[] for x in range(i)}
clf = KM(n_clusters=i)
clf.fit(pcatx)
test = clf.predict(pcatx)
result = clf.predict(pcarx)
p.append(metrics.v_measure_score(ry.ravel(), result))
clf = KM(n_clusters=i)
clf.fit(icatx)
test = clf.predict(icatx)
result = clf.predict(icarx)
ic.append(metrics.v_measure_score(ry.ravel(), result))
clf = KM(n_clusters=i)
clf.fit(rptx)
test = clf.predict(rptx)
result = clf.predict(rprx)
r.append(metrics.v_measure_score(ry.ravel(), result))
clf = KM(n_clusters=i)
clf.fit(kbtx)
test = clf.predict(kbtx)
result = clf.predict(kbrx)
k.append(metrics.v_measure_score(ry.ravel(), result))
# adj_rand.append(metrics.adjusted_rand_score(ry.ravel(), result))
# v_meas.append(metrics.v_measure_score(ry.ravel(), result))
# mutual_info.append(metrics.fowlkes_mallows_score(ry.ravel(), result))
# adj_mutual_info.append(metrics.homogeneity_score(ry.ravel(), result))
plt.figure()
plt.title(dataset+": KM Clustering & DR")
plt.xlabel('Number of clusters')
plt.ylabel('V Measure Score value')
plt.plot(range(2,8), p, label="PCA")
plt.plot(range(2,8), ic, label="ICA")
plt.plot(range(2,8), r, label = "RP")
plt.plot(range(2,8), k, label="KB")
plt.legend()
plt.ylim(ymin=-0.05, ymax=0.5)
plt.savefig("KM_DR_"+dataset+"_VM.png", dpi=300)