alphas = [1, 0.8, 0.6, 0.4, 0.2, 0]
plt.figure()
fig, axs = plt.subplots(1, 1, figsize=(16, 10), squeeze=False)
values = {}
yvalues = []
for a in alphas:
nb = BernoulliNB(alpha=a)
nb.fit(trnX, trnY)
pred = nb.predict(valX)
yvalues.append(metrics.accuracy_score(valY, pred))
values["Bern"] = yvalues
plot.multiple_line_chart(axs[0, 0],
alphas,
values,
'Bernoulli with various alpha',
'nr estimators',
'accuracy',
percentage=True)
plt.show()
#Alpha não faz diferença excepto sendo 0 que piora
#%%
#binarize
#%%
binarizes = [1, 0.8, 0.6, 0.4, 0.2, 0]
plt.figure()
fig, axs = plt.subplots(1, 1, figsize=(16, 10), squeeze=False)
values = {}
X: np.ndarray = df.drop(to_clf, axis=1).values
for n in n_clusters:
kmeans = cluster.KMeans(n_clusters=n, random_state=1).fit(X)
prdY = kmeans.labels_
inertias.append(kmeans.inertia_)
sil.append(metrics.silhouette_score(X, prdY))
ivalues={}
svalues={}
ivalues["norm"] = inertias
svalues["norm"] = sil
print(sil[4])
plot.multiple_line_chart(axs[0, 0], n_clusters, ivalues, '\nKmeans',
'nr estimators', 'inertia', percentage=False)
plot.multiple_line_chart(axs[0, 1], n_clusters, svalues, '\nKmeans',
'nr estimators', 'silhouete', percentage=False)
plt.show()
#%%
n_clusters=6
algs = ["PCA", "selectkbest"]
plt.figure()
fig, axs = plt.subplots(2 ,len(algs), figsize=(14, 8), squeeze=False)
for a in range(len(algs)):
datar = datapp.feature_reduction(df, to_clf,categoric+[to_clf], n_features=2, as_int=True, alg=algs[a])
y: np.ndarray = datar[to_clf].values
X: np.ndarray = datar.drop([to_clf], axis=1).values
"class", ["class", "id"],
d,
alg=f)
xg_clf = GradientBoostingClassifier()
startTime = time.process_time()
acc, sens, _ = eval.train_predict_kfold(df,
"class",
xg_clf,
bal=bal)
print(time.process_time() - startTime)
yvalues.append(acc)
syvalues.append(sens)
values[d] = yvalues
svalues[d] = syvalues
plot.multiple_line_chart(axs[0, k], thresholds, values,
'XGBoost with %s reduction' % f,
'threshold of reduction', 'accuracy')
plot.multiple_line_chart(axs[1, k],
thresholds,
svalues,
'XGBoost with %s reduction' % f,
'threshold of reduction',
'sensitivity',
percentage=False)
plt.show()
#%%
tr = 0.9
f = "selectkbest"
selectk = 0.75
values = {}
svalues = {}
for d in selects:
yvalues = []
syvalues = []
for tr in thresholds:
datared = datapp.preprocess_alt(data, "class", red_corr=True, tr=tr, n=5, normalization=normalization,
ignore_classes=categoric, as_df=True)
df = datapp.feature_reduction(datared, "class",["class","id"], d, alg=f)
rf = RandomForestClassifier(random_state=rs)
acc, sens, _ = eval.train_predict_kfold(df, "class", rf, bal=bal)
yvalues.append(acc)
syvalues.append(sens)
values[d] = yvalues
svalues[d] = syvalues
plot.multiple_line_chart(axs[0, k], thresholds, values, 'Random Forests with %s reduction' % f,
'threshold of reduction', 'accuracy')
plot.multiple_line_chart(axs[1, k], thresholds, svalues, 'Random Forests with %s reduction' % f,
'threshold of reduction', 'sensitivity', percentage=False)
plt.show()
#%%
tr=0.95
f= "selectkbest"
selectk = 0.6
datared = datapp.preprocess_alt(data, "class", red_corr=True, tr=tr, n=5, normalization=normalization,
ignore_classes=categoric, as_df=True)
df = datapp.feature_reduction(datared, "class",["class","id"], n_features=selectk, alg=f)
df.shape
#%%
d,
alg=alg)
acc, sens, x = eval.train_predict_kfold(df,
"class",
f,
bal=bal)
yvalues.append(acc)
syvalues.append(sens)
values[d] = yvalues
svalues[d] = syvalues
plot.multiple_line_chart(axs[0 + 2 * i, k],
thresholds,
values,
'{} with {}'.format(f, str(alg)),
'threshold of reduction',
'accuracy',
percentage=False)
plot.multiple_line_chart(axs[1 + 2 * i, k],
thresholds,
svalues,
'{} with {}'.format(f, str(alg)),
'threshold of reduction',
'sensitivity',
percentage=False)
plt.show()
#%%
tr = 0.9
f = "PCA"
for i in range(len(bins)):
q_lifts.append(rules_q[i]["lift"].mean())
c_lifts.append(rules_c[i]["lift"].mean())
q_sup = []
c_sup = []
for i in range(len(bins)):
q_sup.append(rules_qsup[i]["support"].mean())
c_sup.append(rules_csup[i]["support"].mean())
#%%
lvalues = {}
lvalues["cut"] = c_lifts
lvalues["qcut"] = q_lifts
svalues = {}
svalues["cut"] = c_sup
svalues["qcut"] = q_sup
plt.figure()
fig, axs = plt.subplots(1, 2, figsize=(12, 6), squeeze=False)
axs[0, 0].set_xticks(bins)
axs[0, 1].set_xticks(bins)
plot.multiple_line_chart(axs[0, 0], bins, lvalues,
'Lift of top rules of corresponding bins', 'bins',
'lift')
plot.multiple_line_chart(axs[0, 1], bins, svalues,
'Support of top rules of corresponding bins', 'bins',
'support')
plt.show()
for d in selects:
yvalues = []
syvalues = []
for tr in thresholds:
datared = datapp.preprocess_alt(data, "class", red_corr=True, tr=tr, n=5, normalization=normalization,
ignore_classes=categoric, as_df=True)
df = datapp.feature_reduction(datared, "class",["class","id"], d, alg=f)
tree = DecisionTreeClassifier(random_state=rs)
acc, sens, _ = eval.train_predict_kfold(df, "class", tree, bal=bal)
yvalues.append(acc)
syvalues.append(sens)
values[d] = yvalues
svalues[d] = syvalues
plot.multiple_line_chart(axs[0, k], thresholds, values, 'Decision Trees with %s reduction' % f,
'threshold of reduction', 'accuracy')
plot.multiple_line_chart(axs[1, k], thresholds, svalues, 'Decision Trees with %s reduction' % f,
'threshold of reduction', 'sensitivity', percentage=False)
plt.show()
#%%
tr=0.95
f= "selectkbest"
selectk = 1
datared = datapp.preprocess_alt(data, "class", red_corr=True, tr=tr, n=5, normalization=normalization,
ignore_classes=categoric, as_df=True)
df = datapp.feature_reduction(datared, "class",["class","id"], n_features=selectk, alg=f)
df.shape
# %%
# PARAMETERS PARA TESTAR: criterion, splitter, max_depth, min_sample_leaf, min_samples_split
criteria = ['entropy', 'gini']
plt.figure()
fig, axs = plt.subplots(1, len(criteria), figsize=(12, 7), squeeze=False)
for k in range(len(criteria)):
f = criteria[k]
values = {}
for d in max_depths:
yvalues = []
for n in min_samples_leaf:
tree = DecisionTreeClassifier(min_samples_leaf=n, max_depth=d, criterion=f, random_state=rs)
tree.fit(trnX, trnY)
pred = tree.predict(valX)
yvalues.append(metrics.accuracy_score(valY, pred))
values[d] = yvalues
plot.multiple_line_chart(axs[0, k], min_samples_leaf, values, 'Decision Trees with %s criteria' % f,
'min_samples_leaf', 'accuracy', percentage=True)
plt.show()
# %%
criterion = "gini"
# %%
min_samples_leaf = [.01, .0075, .005, .0025, .001]
max_depths = [5, 10, 25]
splitters = ['best', 'random']
plt.figure()
fig, axs = plt.subplots(1, len(splitters), figsize=(12, 7), squeeze=False)
for k in range(len(splitters)):
ignore_classes=categoric,
as_df=True)
df = datapp.feature_reduction(datared,
"class", ["class", "id"],
d,
alg=f)
knn = KNeighborsClassifier()
acc, sens, x = eval.train_predict_kfold(df, "class", knn, bal=bal)
yvalues.append(acc)
syvalues.append(sens)
values[d] = yvalues
svalues[d] = syvalues
plot.multiple_line_chart(axs[0, k], thresholds, values,
'KNN with %s reduction' % f,
'threshold of reduction', 'accuracy')
plot.multiple_line_chart(axs[1, k],
thresholds,
svalues,
'KNN with %s reduction' % f,
'threshold of reduction',
'sensitivity',
percentage=False)
plt.show()
#%%
tr = 0.9
f = "selectkbest"
selectk = 1
datared = datapp.preprocess_alt(data,
print("max depth cycle")
yvalues = []
for n in n_estimators:
rf = RandomForestClassifier(n_estimators=n,
max_depth=d,
max_features=f,
random_state=rs)
# rf = GaussianNB()
rf.fit(trnX, trnY)
pred = rf.predict(valX)
yvalues.append(metrics.accuracy_score(valY, pred))
values[d] = yvalues
plot.multiple_line_chart(axs[0, k],
n_estimators,
values,
'Random Forests with %s features' % f,
'nr estimators',
'accuracy',
percentage=False)
plt.show()
# %%
max_features = 0.3
# %%
n_estimators = [50, 100, 200, 300, 400]
max_depths = [10, 25, 50]
criterions = ['gini', 'entropy']
plt.figure()
f = lr[k]
values = {}
for d in n_estimators:
yvalues = []
for n in min_samples_leaf:
gb = GradientBoostingClassifier(min_samples_leaf=n,
n_estimators=d,
loss=loss,
learning_rate=f,
random_state=rs)
gb.fit(trnX, trnY)
pred = gb.predict(valX)
yvalues.append(metrics.accuracy_score(valY, pred))
values[d] = yvalues
plot.multiple_line_chart(axs[0, k], min_samples_leaf, values,
'Gradient Boosting with %s lf' % f,
'min_samples_leaf', 'accuracy')
plt.show()
#%%
lr = 0.5
#%%
min_samples_leaf = [.05, .025, .01, .005, .0025, .001]
n_estimators = [100, 200, 300]
max_depth = [3, 10, 15, 25]
plt.figure()
fig, axs = plt.subplots(2, len(max_depth), figsize=(12, 7), squeeze=False)
for k in range(len(max_depth)):
f = max_depth[k]
