def dr_cluster(X, y, X_test, dr_steps, savedir, ds):
"""
Apply dimensionality reduction and then KMeans and EM clustering
:param X: np array, training samples
:param y: np array, labels
:param X_test: np.array, test data
:param dr_steps: list of dimensionality reduction objects
:param savedir: string, output directory
:param ds: string, name of dataset
:return: tuple, best clusters for each dr type
"""
cluster_idx = {'musk': 1, 'cancer': 0, 'shoppers': 0}
best_km = []
best_em = []
best_test_km = []
best_test_em = []
for dr_step in dr_steps:
km, em, km_test, em_test = A3.cluster(range(2, 21),
X,
y,
savedir,
ds,
tnse_range=range(3, 5),
dr_step=dr_step,
X_test=X_test)
best_km.append(km[cluster_idx[ds]])
best_em.append(em[cluster_idx[ds]])
best_test_km.append(km_test[cluster_idx[ds]])
best_test_em.append(em_test[cluster_idx[ds]])
return best_km, best_em, best_test_km, best_test_em
def cluster_nn(X_train, y_train, X_test, y_test, savedir, ds, cluster_type):
logging.info(
'Running neural net with {} clusters as features'.format(cluster_type))
pipe = A3.baseline_ann(X_train, y_train, ds)
ypred = pipe.predict(X_test)
util.confusionMatrix('{}-{}-ann'.format(ds, cluster_type), y_test, ypred,
savedir)
return f1_score(y_test, ypred)
def sum_primes_below(n):
"""Compute the sum of primes below the given threshold.
>>> sum_primes_below(10)
17
>>> sum_primes_below(2000000)
142913828922
"""
return sum(A3.prime_generator(n))
def dr_ann(X_train,
y_train,
X_test,
y_test,
dr_steps,
savedir,
ds,
cluster=None):
if cluster is not None:
c = ' with clustering from {}'.format(cluster)
else:
c = ''
logging.info('ANN: Running baseline neural net' + c)
baseline = A3.baseline_ann(X_train, y_train, ds)
ypred = baseline.predict(X_test)
util.confusionMatrix('{}{}-baseline'.format(ds, cluster), y_test, ypred,
savedir)
scores = [f1_score(y_test, ypred)]
score_names = ['baseline']
for dr_step in dr_steps:
drname = dr_step.__class__.__name__.lower()
score_names.append(drname)
logging.info('ANN: Running neural net with {} dimension reduction'.
format(drname) + c)
# Get trained ann with dr
ann = A3.dr_ann(X_train, y_train, dr_step, ds)
ypred = ann.predict(X_test)
util.confusionMatrix('{}-{}{}'.format(ds, drname, cluster), y_test,
ypred, savedir)
scores.append(f1_score(y_test, ypred))
logging.info('ANN {} F1 Scores: {}'.format(c, scores))
util.plotBarScores(scores,
score_names,
ds,
savedir,
phaseName='{}-{}'.format(ds, cluster))
plt.close('all')
def factor_map(n):
"""Compute prime factors of an integer.
>>> factor_map(29)
{29: 1}
>>> factor_map(72)
{2: 3, 3: 2}
"""
map = {}
for factor in A3.factor_list(n):
map[factor] = map.get(factor, 0) + 1
return map
def run(Ex):
if Ex == "1":
A1.a()
elif Ex == "2":
A2.b()
elif Ex == "3":
A3.c()
elif Ex == "4":
A4.d()
elif Ex == "5":
A5.e()
elif Ex == "6":
A6.f()
elif Ex == "7":
A7.g()
elif Ex == "8":
A8.h()
elif Ex == "9":
A9.i()
elif Ex == "10":
A10.j()
elif Ex == "intro":
Aintro.A()
else:
print "Invalid Exercise"
def find_nth_prime(n):
"""Compute the nth prime number using an unbounded prime generator.
>>> find_nth_prime(6)
13
>>> find_nth_prime(101)
547
>>> find_nth_prime(10001)
104743
"""
primes = A3.prime_generator()
for x in range(n):
prime = primes.next()
return prime
def computed_with_prime_powers(n):
"""A faster method observes that for any prime number, a simple power of
that prime number will be the smallest number with the that factorization
count. For example, 16 is the largest power of 2 less than or equal to 20.
>>> computed_with_prime_powers(20)
232792560
>>> computed_with_prime_powers(40)
5342931457063200
>>> computed_with_prime_powers(80)
32433859254793982911622772305630400L
>>> computed_with_prime_powers(160)
117671955487901874837890815641362681946988303003141220897970719568000L
"""
product = 1
for prime in A3.prime_generator(n):
count = int(math.log(n, prime))
product *= prime ** count
return product
def B3(command, subject, player_input):
global success
if command == 1:
history.append('visited')
B4.B4_text(B4.history)
success = True
elif command == 2 or command == 4:
print
delay("A wall blocks your way.")
print
success = False
elif command == 3:
history.append('visited')
A3.A3_text(A3.history)
elif command == 5:
if subject.lower() in B3_inventory:
overall.main_character.inventory[subject] = B3_inventory[subject]
del B3_inventory[subject]
print
delay("%s has been added to inventory" % (subject))
elif subject.lower(
) in overall.final_enemy.inventory and overall.final_enemy.is_alive == False:
overall.main_character.inventory[
subject] = overall.final_enemy.inventory[subject]
del overall.final_enemy.inventory[subject]
print
delay("%s added to inventory" % (subject))
elif subject.lower(
) in overall.final_enemy.inventory and overall.final_enemy.is_alive == True and overall.final_enemy.is_asleep == True:
print
delay("The ENEMY is still, you can not take items from it.")
elif subject.lower() in overall.main_character.inventory:
print
delay('%s already in inventory' % (subject))
else:
print
delay("Can not pick up %s" % (subject))
print
sucess = False
elif command == 6:
print
if subject.lower() in overall.main_character.inventory:
B3_inventory[subject] = overall.main_character.inventory[subject]
del overall.main_character.inventory[subject]
delay('%s has been removed from inventory' % (subject))
else:
delay('%s not in inventory' % (subject))
print
success = False
elif command == 7:
if subject.lower() == 'enemy' and overall.if_empty(
overall.final_enemy.inventory
) == False and overall.final_enemy.is_alive == False:
print
delay("The body of the enemy contains a: ")
print
for item in overall.final_enemy.inventory:
print
delay(item)
print
print
elif subject.lower() == 'enemy' and overall.if_empty(
overall.final_enemy.inventory
) == True and overall.final_enemy.is_alive == False:
print
delay("This body carries nothing on it.")
print
elif subject.lower(
) == 'enemy' and overall.final_enemy.is_alive == True and overall.final_enemy.is_asleep == True:
print
delay("This ENEMY is still alive. You can not search it.")
print
else:
print
delay("Cannot search %s" % (subject))
print
print
success = False
elif command == 8:
print
if subject.lower(
) in overall.main_character.inventory and overall.main_character.inventory[
subject.lower(
)].form == 'weapon' and overall.final_enemy.is_asleep == True:
print
delay("As you attack the ENEMY stirs from its slumber.")
print
overall.final_enemy.is_asleep = False
B3_combat(command, subject, 0)
elif subject.lower() in overall.main_character.inventory:
overall.main_character.inventory[subject.lower()].use()
if overall.main_character.inventory[
subject.lower()].form == 'food':
del overall.main_character.inventory[subject.lower()]
else:
delay('No %s in inventory' % (subject))
print
success = False
elif command == 9:
for item in overall.main_character.inventory:
print
delay(item)
print
if overall.if_empty(overall.main_character.inventory) == True:
print
delay("You have nothing in your inventory!")
print
success = False
elif command == 10:
print
if subject.lower() in overall.main_character.inventory:
overall.main_character.inventory[subject].describe()
else:
delay('%s not in inventory' % (subject))
print
success = False
elif command == 11:
print
overall.main_character.death()
success = False
else:
success = False
if success == False:
B3_reit(nothing)
def dr(X, y, savedir, ds):
# First do pca
pca_pipe = A3.pca(X, y)
pca = pca_pipe.named_steps['pca']
plt.savefig('{}/{}-pca.png'.format(savedir, ds))
np.savetxt('{}/{}-pca-ev.csv'.format(savedir, ds), pca.explained_variance_)
np.savetxt('{}/{}-pca-ev-ratio.csv'.format(savedir, ds),
pca.explained_variance_ratio_)
plt.close('all')
plt.plot(np.cumsum(pca.explained_variance_ratio_))
plt.xlabel('n_components')
plt.ylabel('explained variance (%)')
plt.savefig('{}/{}-pca-ev.png'.format(savedir, ds))
plt.close('all')
reconstruction_error = A3.recon_error(pca, X)
logging.info('PCA reconstruction error: {}'.format(reconstruction_error))
# second ICA
ica = None
max_kurtosis = -np.inf
ica_range = range(10, X.shape[1], 10)
kurt_per_comp = []
for i in ica_range:
ica_pipe = A3.ica(X, y, i)
# This should be selected by kurtosis
kurt = A3.avg_kurtosis(ica_pipe.transform(X))
kurt_per_comp.append(kurt)
logging.info('ICA {} average kurtosis: {}'.format(i, kurt))
if kurt > max_kurtosis:
ica = ica_pipe.named_steps['fastica']
max_kurtosis = kurt
logging.info('ICA max kurtosis {} with {} components'.format(
max_kurtosis, ica.components_.shape[0]))
plt.plot(ica_range, kurt_per_comp)
plt.xlabel('n_components')
plt.ylabel('mean kurtosis')
plt.savefig('{}/{}-ica-kurtosis.png'.format(savedir, ds))
# RP
logging.info('Starting randomized projection...')
rp_errors = []
rp = None
best_rp_err = np.inf
reconstruction_errors = []
for rp_run in range(10):
logging.info('RP iteration {}'.format(rp_run))
best_run = np.inf
run_errors = []
for i in range(10, X.shape[1], 10):
rp_pipe = A3.random_projection(X, y, i)
err = A3.recon_error(
rp_pipe.named_steps['gaussianrandomprojection'], X)
run_errors.append(err)
logging.info('RP {} components reconstruction error: {}'.format(
i, err))
if err < best_rp_err:
rp = rp_pipe.named_steps['gaussianrandomprojection']
best_rp_err = err
if err < best_run:
best_run = err
reconstruction_errors.append(run_errors)
rp_errors.append(best_run)
pd.DataFrame(reconstruction_errors,
columns=range(10, X.shape[1], 10)).to_csv(
'{}/{}-rp-reconstruction.csv'.format(savedir, ds))
# Manually set random projection
if ds == 'musk':
rp.set_params(n_components=50)
elif ds == 'shoppers':
rp.set_params(n_components=30)
plt.figure()
plt.plot(range(10), rp_errors)
plt.xlabel('iteration')
plt.ylabel('reconstruction error')
plt.savefig('{}/{}-rp-reconstruction.png'.format(savedir, ds))
plt.close('all')
logging.info('RP best n_components: {}'.format(rp.n_components_))
# TODO: fourth dimension reduction
rf_pipe = A3.rfselect(X, y)
rf = rf_pipe.named_steps['randomforest']
return [pca, ica, rp, rf]
def main():
args = get_args()
savedir = util.mktmpdir(args.outdir)
# Logging copy-pasted from logging cookbook
# http://docs.python.org/howto/logging-cookbook.html#logging-to-multiple-destinations
logging.basicConfig(format='%(asctime)s %(message)s',
filename='{}/output.log'.format(savedir),
level=logging.INFO)
console = logging.StreamHandler()
console.setLevel(logging.INFO)
logging.getLogger('').addHandler(console)
for ds in ['musk', 'shoppers']:
formatter = logging.Formatter(
'{}: %(levelname)-8s %(message)s'.format(ds))
console.setFormatter(formatter)
logging.info('==========Starting {} Dataset =============='.format(ds))
dataset = datajanitor.getDataset(ds)
dataset.getData()
x_train, x_test, y_train, y_test = \
dataset.partitionData(percent=0.3, randomState=10)
# ********************* #
# **** Clustering **** #
# ********************* #
if 'cluster' in args.phase or 'cluster-ann' in args.phase:
km_train_clust, em_train_clust, km_test_clust, em_test_clust = \
A3.cluster(range(2, 21), x_train, y_train, savedir, ds,
tnse_range=None,
X_test=x_test)
# ******************************* #
# **** Clusters as features **** #
# ******************************* #
# one-hot encode and then add clusters to train and test features
cluster_nn_scores = {
'km': [],
'em': [],
'km+em': [],
'km_only': [],
'em_only': [],
'kmem_only': []
}
if 'cluster-ann' in args.phase:
for i in range(5):
km_x_train = add_cluster_dims(x_train, km_train_clust[i])
km_x_test = add_cluster_dims(x_test, km_test_clust[i])
em_x_train = add_cluster_dims(x_train, em_train_clust[i])
em_x_test = add_cluster_dims(x_test, em_test_clust[i])
km_score = cluster_nn(km_x_train, y_train, km_x_test,
y_test, savedir, ds,
'km{}'.format(i + 2))
em_score = cluster_nn(em_x_train, y_train, em_x_test,
y_test, savedir, ds,
'em{}'.format(i + 2))
kmem_x_train = add_cluster_dims(km_x_train,
em_train_clust[i])
kmem_x_test = add_cluster_dims(km_x_test, em_test_clust[i])
kmem_score = cluster_nn(kmem_x_train, y_train, kmem_x_test,
y_test, savedir, ds,
'kmem{}'.format(i + 2))
# do only clusters
km_only = cluster_nn(km_train_clust[i].reshape(-1,
1), y_train,
km_test_clust[i].reshape(-1, 1),
y_test, savedir, ds,
'km_only{}'.format(i + 2))
em_only = cluster_nn(km_train_clust[i].reshape(-1,
1), y_train,
km_test_clust[i].reshape(-1, 1),
y_test, savedir, ds,
'em_only{}'.format(i + 2))
kmem_only = cluster_nn(
np.append(km_train_clust[i].reshape(-1, 1),
em_train_clust[i].reshape(-1, 1),
axis=1), y_train,
np.append(km_test_clust[i].reshape(-1, 1),
em_test_clust[i].reshape(-1, 1),
axis=1), y_test, savedir, ds,
'kmem_only{}'.format(i + 2))
util.plotBarScores([
km_score, em_score, kmem_score, km_only, em_only,
kmem_only
], [
'km-ann', 'em-ann', 'kmem-ann', 'km_only', 'em_only',
'kmem_only'
],
ds,
savedir,
phaseName='{}-cluster-{}-ann'.format(
ds, i + 2))
cluster_nn_scores['km'].append(km_score)
cluster_nn_scores['em'].append(em_score)
cluster_nn_scores['km+em'].append(kmem_score)
cluster_nn_scores['km_only'].append(km_only)
cluster_nn_scores['em_only'].append(em_only)
cluster_nn_scores['kmem_only'].append(kmem_only)
plt.close('all')
pd.DataFrame.from_dict(data=cluster_nn_scores).to_csv(
'{}/{}-clusternn.csv'.format(savedir, ds))
# ************************ #
# **** Dim Reduction **** #
# ************************ #
# You actually have to do dimension reduction, there is no choice
dr_steps = dr(x_train, y_train, savedir, ds)
# *********************** #
# **** DR + Cluster **** #
# *********************** #
if 'dr-cluster' in args.phase:
km_train_clust, em_train_clust, km_test_clust, em_test_clust = \
dr_cluster(x_train, y_train, x_test, dr_steps, savedir, ds)
# ******************* #
# **** DR + ANN **** #
# ******************* #
dr_ann(x_train, y_train, x_test, y_test, dr_steps, savedir, ds)
def A2(command, subject, player_input):
global success
if command == 1:
if 'unlocked' in history:
print
history.append('visited')
A3.A3_text(A3.history)
success = True
else:
print
delay('This door is locked')
print
success = False
elif command == 2:
history.append('visited')
B2.B2_text(B2.history)
elif command == 3:
print
delay("A wall blocks your way")
print
success = False
elif command == 4:
history.append("visited")
A1.A1_text(A1.history)
elif command == 5:
if subject.lower() in A2_inventory:
overall.main_character.inventory[subject] = A2_inventory[subject]
del A2_inventory[subject]
print
delay('%s has been added to inventory' %(subject))
elif subject.lower() in overall.main_character.inventory:
print
delay('%s already in inventory' %(subject))
else:
print
delay("Can not pick up %s" %(subject))
print
success = False
elif command == 6:
print
if subject.lower() in overall.main_character.inventory:
A2_inventory[subject] = overall.main_character.inventory[subject]
del overall.main_character.inventory[subject]
delay('%s has been removed from inventory' %(subject))
else:
delay('%s not in inventory' %(subject))
print
success = False
elif command == 7:
print
delay('Nothing here to search')
print
success = False
elif command == 8:
print
if subject.lower() == 'iron key' and subject.lower() in overall.main_character.inventory:
history.append('unlocked')
delay("IRON KEY unlocks the NORTH door")
print
elif subject.lower() in overall.main_character.inventory:
overall.main_character.inventory[subject].use()
if overall.main_character.inventory[subject.lower()].form == 'food':
del overall.main_character.inventory[subject.lower()]
else:
delay('No %s in inventory' %(subject))
print
success = False
elif command == 9:
for item in overall.main_character.inventory:
print
delay(item)
print
if overall.if_empty(overall.main_character.inventory) == True:
print
delay("You have nothing in your inventory!")
print
success = False
elif command == 10:
print
if subject.lower() in overall.main_character.inventory:
overall.main_character.inventory[subject].describe()
else:
delay('%s not in inventory' %(subject))
print
success = False
elif command == 11:
print
overall.main_character.death()
success = False
else:
success = False
if success == False:
A2_reit(nothing)
#!/bin/python
import A3
import os
path = os.getcwd()
filename = 'keys.txt'
path = path + '/' + filename
#A3.debug = True
print(A3.createDictionaries(path))
tmp = A3.encode('Hello World')
print(tmp)
print(A3.decode(tmp))
if result:
print("A1 Suspicious")
for line in result:
print(line)
else:
print("A1 Benign")
result = A2.evaluate(sourceCode)
if result:
print("A2 Suspicious")
for line in result:
print(line)
else:
print("A2 Benign")
result = A3.evaluate(sourceCode)
if result:
print("A3 Suspicious")
for line in result:
print(line)
else:
print("A3 Benign")
result = A4.evaluate(sourceCode)
if result:
print("A4 Suspicious")
for line in result:
print(line)
else:
print("A4 Benign")
import A3
import A4
flag = True
epochs = 250
print('Project Υπολογιστικής Νοημοσύνης - Μέρος Α')
while flag:
rn = input('Επιλέξτε ερώτημα: \nA2\nA3\nA4\nA5\n\'all\''
' to run all 7 files\n'
'')
if rn == 'all':
single_layer.single_layer(epochs)
extra_layer.extra_layer(epochs)
early_stopping.early_stopping(epochs)
A3.a3(epochs)
A4.a4(epochs)
if rn == 'A2':
rn_2 = input(
'Επιλέξτε υποερώτημα: \n1 (Single-layer MLP)\n2 (Two-Layer MLP)\n3 (Early-Stopping)\n'
)
if rn_2 == '1':
single_layer.single_layer(epochs)
flag = False
if rn_2 == '2':
extra_layer.extra_layer(epochs)
flag = False
if rn_2 == '3':
early_stopping.early_stopping(epochs)
flag = False
if rn == 'A3':
