'\nKmeans',
'nr estimators',
'silhouete',
percentage=False)
plt.show()
#%%
n_clusters = 5
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,
"class", ["class", "id"],
n_features=2,
as_int=True,
alg=algs[a])
y: np.ndarray = datar[to_clf].values
X: np.ndarray = datar.drop([to_clf, "id"], axis=1).values
kmeans_model = cluster.KMeans(n_clusters=n_clusters,
random_state=rs).fit(X)
labels = kmeans_model.labels_
cluster_centers = kmeans_model.cluster_centers_
labels_unique = np.unique(labels)
n_clusters_ = len(labels_unique)
#plot
#plt.clf()
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
kmeans_model = cluster.KMeans(n_clusters=n_clusters, random_state=rs).fit(X)
labels = kmeans_model.labels_
cluster_centers = kmeans_model.cluster_centers_
labels_unique = np.unique(labels)
n_clusters_ = len(labels_unique)
#plot
#plt.clf()
colors = cycle('bgrcmykbgrcmykbgrcmykbgrcmyk')
for k, col in zip(range(n_clusters_), colors):
my_members = labels == k
thresholds = [1 ,0.95, 0.90, 0.8]
selects = [1, 0.9, 0.8, 0.75, 0.6]
algs = ["selectkbest", "PCA"]
plt.figure()
fig, axs = plt.subplots(2, 2, figsize=(12, 7), squeeze=False)
for k in range(len(algs)):
f = algs[k]
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"