def KNeighbors_en(self, iter):
n_estimators = 10
model = BC(KNeighborsClassifier(n_neighbors =iter, weights = 'uniform', algorithm = 'auto', n_jobs = -1), max_samples= 0.5, n_estimators=n_estimators, n_jobs = -1)
model.fit(self.x_train, self.y_train)
predict = model.predict(self.x_test)
print("Ensemble kneighbors Regression : accurancy_is", metrics.accuracy_score(self.y_test, predict))
return predict
def make_model(self, n_estimators, n_jobs, verbose=1):
model1 = RF(n_estimators=1,
criterion='entropy',
bootstrap=False,
class_weight='balanced_subsample')
self.model = BC(base_estimator=model1,
n_estimators=n_estimators,
max_features=1.,
verbose=verbose)
def __init__(self, criterion_, max_depth_, random_state_, n_estimators_, n_jobs_): # initialize DTC self.tree = DTC(criterion=criterion_, max_depth=max_depth_, random_state=random_state_) # initialize BaggingClassifier, with # n_estimators being the only adjustable value self.bag = BC(base_estimator=self.tree, n_estimators=n_estimators_, n_jobs=n_jobs_, random_state=random_state_)
skip_header=1)
X = training_data[:, :1000]
Y = training_data[:, 1000]
# Various Classifiers
dtc_min_samples_leaf = DTC(min_samples_leaf=15)
etc = ETC()
gbc = GBC()
rfc = RFC()
dtc_max_depth = DTC(max_depth=8)
nb = BernoulliNB()
svc = SVC()
lr = LR()
abc = ABC()
bc = BC()
'''
inv_doc_freq = np.zeros(1000)
for i in range(len(inv_doc_freq)):
total = sum(X[:, i])
if total == 0:
inv_doc_freq[i] = 0
else:
inv_doc_freq[i] = math.log(N / sum(X[:, i]))
'''
# Data normalization
for i in range(len(X)):
max_freq = max(X[i])
if max_freq == 0:
pass
from sklearn.ensemble import AdaBoostClassifier as ABC
model = ABC(n_estimators=100, random_state=42,
learning_rate=.80).fit(X_train, y_train)
prediction = model.predict(X_test)
score = accuracy_score(y_test, prediction)
print(score)
# Bagging Classifier
# ----------------
# In[22]:
from sklearn.ensemble import BaggingClassifier as BC
model = BC(n_estimators=100, random_state=42).fit(X_train, y_train)
prediction = model.predict(X_test)
score = accuracy_score(y_test, prediction)
print(score)
# Extra Trees Classifier
# ----------------------
# In[23]:
from sklearn.ensemble import ExtraTreesClassifier as XTC
model = XTC(n_estimators=100,
random_state=42,
criterion='entropy',
max_depth=20).fit(X_train, y_train)
def __init__(self, matrixdatabase):
self._matrix_database = matrixdatabase
self._has_fit = False
self._bc = BC(n_estimators=10)
print(X_all.shape)
# one hot encode
y_s = np.zeros((y_all.shape[0], 2))
y_s[:, 1] = (y_all == 1).reshape(y_all.shape[0], )
y_s[:, 0] = (y_all == 0).reshape(y_all.shape[0], )
pos_weight = np.sum(y_s[:, 0]) / np.sum(y_s[:, 1])
X_train, X_test, y_train, y_test = train_test_split(X_all,
y_all,
test_size=0.30,
stratify=y_all,
random_state=42)
del X_all
clf = BC(**bc_params)
clf.fit(X_train, y_train.ravel())
#clf = RandomForestClassifier(min_samples_leaf=15, class_weight = 'balanced')#{0:1,1:pos_weight})
#clf.fit(X_train, y_train.ravel())
#print ('oob_score: ', clf.oob_score_)
# svm = SVC(probability = True, class_weight = 'balanced')
# svm.fit(X_train, y_train)
preds_tr = clf.predict_proba(X_train)
print("Predictions_tr:")
print(preds_tr[0:20])
print(np.median(preds_tr[:, 1]))
roc_auc_tr = metrics.roc_auc_score(y_train.ravel(), preds_tr[:, 1])
print('ROC AUC_tr:', roc_auc_tr)
import pandas as pd
from sklearn.ensemble import BaggingClassifier as BC
from sklearn.metrics import confusion_matrix
from sklearn.model_selection import train_test_split
# DTLZ STUFFS
data = pd.read_csv("features with R2.csv")
inputs_train = data[data.keys()[1:11]]
outputs_train = data[data.keys()[11:]]
targetnames = ["SVM", "GPR", "NN", "EN"]
target_train = outputs_train.idxmax(axis=1)
num_classes = len(targetnames)
clf = BC()
clf = clf.fit(inputs_train, target_train)
# WFG STUFFS
data_wfg = pd.read_csv("WFG features with R2.csv")
predictions = clf.predict(x_test)
con_mat = confusion_matrix(target_test, predictions)
cost_mat = output_test
cost_mat = -cost_mat.sub(cost_mat.max(axis=1), axis=0)
print(con_mat)
num_samples, num_classes = cost_mat.shape
cost = 0
lenp = len(predictions)
for index in range(num_samples):
cost += cost_mat.iloc[index][predictions[index]]
# print('Cost independent classification', cost/lenp)
cic = cost / lenp
def Find_Optimal_Features(ML_DATA):
# Creates all combinations of features
lst = list(itertools.product([0, 1], repeat=8))
lst.remove((0, 0, 0, 0, 0, 0, 0, 0))
for i in range(len(lst)):
lst[i] = list(lst[i])
outs = []
for i in range(8):
outs.append([])
# Clasifiers put into array for easier access and expandability
clfs = [
DTC(),
KNN(),
BC(ETC()),
LSVC(max_iter=10_000),
RFC(),
SVC(),
SGDC(),
MLP(max_iter=10_000)
]
tot = len(lst)
y = []
# Trains all models on all feature sets and gets scores
for i, item in enumerate(lst[:15]):
X_train, ys_train, ya_train, X_test, ys_test, ya_test = ML_DATA.Make_Set(
item, 0.25)
for item in clfs:
item.fit(X_train, ys_train)
scores = []
for j, item in enumerate(clfs):
scores.append(item.score(X_test, ys_test))
outs[j].append(scores[j])
PBR(i + 1, tot, name="Test Set", end="\r")
y = ys_test
print()
temp = Counter(y)
total = len(y)
rand_ratio = 0
for item in temp.values():
rand_ratio += item / total
rand_ratio = (rand_ratio / 8) * 100
print("Random Choice :", rand_ratio)
final = np.zeros(8)
final_top = np.zeros(8)
final_btop = np.zeros(8)
names = [
"Decision Tree", "KNN", "Bag Extra Tree", "Linear SVC",
"Random Forest", "SVC", "SGDC", "MLP"
]
# Prints all results
for k, name in enumerate(names):
o = RAS(outs[k], 10)
final_top += np.asarray(lst[o[0]])
f = np.zeros(8)
count = 0
best = outs[k][0]
print(name + ":")
for i, item in enumerate(o):
if i == 0:
best = outs[k][item]
print("\t\t{:2}) {:7.4f}% {}".format(i, outs[k][item] * 100,
lst[item]))
if outs[k][item] == best:
count += 1
f += np.asarray(lst[item])
final += np.asarray(lst[item])
final_btop += f / count
print()
print(final)
print(final_top)
print(final_btop)
print(con_mat)
lent = len(target_test)
lenp = len(predictions)
cost_mat = output_test
cost_mat = -cost_mat.sub(cost_mat.max(axis=1), axis=0)
cost = classifier.cost_loss(x_test, cost_mat)
# print(lent == lenp, 'Cost based classification', cost/lenp)
cbc = cost / lenp
""" classifier.optmize_weights(x_t2, o_t2)
w = classifier.weights
cost = classifier.weightedcost(w, x_test, cost_mat)
print(lent == lenp, 'Weighted Votes Cost based classification', cost) """
################################################
num_classes = len(targetnames)
clf = BC()
clf = clf.fit(x_train, target_train)
predictions = clf.predict(x_test)
con_mat = confusion_matrix(target_test, predictions)
cost_mat = output_test
cost_mat = -cost_mat.sub(cost_mat.max(axis=1), axis=0)
print(con_mat)
num_samples, num_classes = cost_mat.shape
cost = 0
lenp = len(predictions)
for index in range(num_samples):
cost += cost_mat.iloc[index][predictions[index]]
# print('Cost independent classification', cost/lenp)
cic = cost / lenp
classes = targetnames
cost_mat = output_train
def gogo_bagged_svm( fxpath, mpath, spath ):
transform = True
svc_params = {'penalty':'l2',
'loss':'l2',
'dual':False,
'C':33.0,
'intercept_scaling':1e4,
'class_weight':'auto',
'random_state':42}
bc_params = {'base_estimator':LinearSVC(**svc_params),
'n_estimators':96,
'max_samples':0.1,
'max_features':0.8,
'oob_score':False,
# if you have tons of memory (i.e. 32gb ram + 32gb swap)
# incresaing this parameter may help performance. else,
# increasing it may cause "out of memory" errors.
'n_jobs':1,
#'n_jobs':8,
'verbose':1,
'random_state':42}
'''
lr_params = {'C':1e6,#tr(-3,3,7),
'penalty':'l2',
'class_weight':'auto',
'intercept_scaling':1e6}#tr(-1,6,7)}
'''
preds = []
kpca_fname = '%s/kpca_rbf_{0}_{1}.pkl' % mpath
s_fname = '%s/kpca_linear_svm{0}_{1}_preds.csv' % spath
for i in range(7):
if i < 5:
nbreed = 1
sbreed = 'dog'
nsubject = i+1
else:
nbreed = 2
sbreed = 'human'
nsubject = 1 + abs(5-i)
print('breed%d.subject%d..' % ( nbreed, nsubject ))
X_ictal = load_features( fxpath, nbreed, nsubject, 1 )
X_inter = load_features( fxpath, nbreed, nsubject, 2 )
X_train = vstack((X_inter, X_ictal))
Y = [0 for x in X_inter] + [1 for x in X_ictal]
wi = 1.0/len(X_inter) * 1000
wp = 1.0/len(X_ictal) * 1000
W = array([wp if y else wi for y in Y])
del X_inter, X_ictal; gc.collect()
with open(kpca_fname.format(sbreed,nsubject),'rb') as f:
kpca = pickle.load(f)
if transform:
X_train = kpca_preprocess_features(X_train)
X_train = kpca_incremental_transform(kpca,X_train)
gc.collect()
X_test = load_features( fxpath, nbreed, nsubject, 3 )
if transform:
X_test = kpca_preprocess_features(X_test)
X_test = kpca_incremental_transform(kpca,X_test)
gc.collect()
bc = BC(**bc_params)
bc.fit(X_train,Y)
#print 'oob_score: ', bc.oob_score_
subject_preds = bc.predict_proba(X_test)[:,1]
preds.append(subject_preds)
subject_preds = pd.DataFrame(subject_preds)
subject_preds.to_csv(s_fname.format(sbreed,nsubject),index=False,header=None)
del X_train, X_test; gc.collect()
sys.stdout.flush()
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier as DTC
from sklearn.ensemble import BaggingClassifier as BC, RandomForestClassifier as RFC
from sklearn.metrics import accuracy_score
digits = load_digits()
fig = plt.figure()
fig.subplots_adjust(left=0, right=1, bottom=0, top=1, hspace=0.05, wspace=0.05)
for i in range(36):
ax = fig.add_subplot(6, 6, i + 1, xticks=[], yticks=[])
ax.imshow(digits.images[i], cmap='binary', interpolation='nearest')
ax.text(0, 0.05, str(digits.target[i]), transform=ax.transAxes)
xtr, xte, ytr, yte = train_test_split(digits.data,
digits.target,
test_size=0.2,
random_state=0)
names = ['DTC', 'BC', 'RFC']
models = [
DTC(),
BC(n_estimators=300, max_samples=0.8, random_state=0),
RFC(n_estimators=300, random_state=0)
]
for name, model in zip(names, models):
print('模型{0}的预测准确率：'.format(name), end='\t')
model.fit(xtr, ytr)
ypred = model.predict(xte)
print(accuracy_score(yte, ypred))
plt.show()
