color=color,
lw=1,
label='ROC curve of class {0} (area = {1:0.2f})'
''.format(i, roc_auc[i]))
plt.plot([0, 1], [0, 1], 'k--', lw=1)
plt.xlim([-0.05, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title(title)
plt.legend(loc="lower right")
plt.show()
if __name__ == "__main__":
X_data, Y_data = load_data(ROOT_PATH + SPLASH + MFCC_FILE_PATH)
X_train, X_test, Y_train, Y_test = train_test_split_by_ratio(
X_data, Y_data, test_size=0.3, random_state=2333)
parameters = {
"svc__tol": [1e-3, 1e-4, 1e-5, 1e-6, 1e-7, 1e-8],
"svc__C": np.logspace(-2, 5, 10)
}
for label_index in range(Y_train.shape[1]):
y_train = Y_train[:, label_index]
y_test = Y_test[:, label_index]
smote = SMOTE(random_state=2333)
X_train_smote, y_train_smote = smote.fit_sample(X_train, y_train)
X_test_smote, y_test_smote = smote.fit_sample(X_test, y_test)
__email__ = '*****@*****.**'
__date__ = '10/30/2019 10:57 PM'
from collections import Counter
import numpy as np
import pandas as pd
from sklearn.cluster import KMeans
from ay_hw_5._global import ROOT_PATH, SPLASH, MFCC_FILE_PATH, LABELS_NAME
from ay_hw_5.util_data import load_data
PREDICT_LABEL = 'predicted'
if __name__ == "__main__":
X_train, y_data = load_data(ROOT_PATH + SPLASH + MFCC_FILE_PATH)
y_data = pd.DataFrame(y_data, columns=LABELS_NAME)
hamming_loss_list = list()
hamming_dist = list()
avg_scores = []
for i in range(1, 10):
temp_avg_scores = []
predicted_results = []
for k in range(3, 5):
k_means_clf = KMeans(n_clusters=k, random_state=i)
predicted_labels = k_means_clf.fit_predict(X_train)
predicted_results.append(predicted_labels)
temp_avg_scores.append(silhouette_score(X_train, predicted_labels))
hamming_dist.append(
sum(
np.min(cdist(X_train, k_means_clf.cluster_centers_,