No module named 'PIL'

pip install --upgrade pip

 pip install pillow

Pytorch, Infinite DataLoader using iter & next

 

# create dataloader-iterator

data_iter = iter(data_loader)

# iterate over dataset

# alternatively you could use while(True)

for i in range(NUM_ITERS_YOU_WANT)

try:

data = next(data_iter)

except StopIteration:

# StopIteration is thrown if dataset ends

# reinitialize data loader

data_iter = iter(data_loader)

data = next(data_iter)

python argparse example

import argparse

paser = argparse.ArgumentParser()

args = paser.parse_args("")

args.cuda = False

args.show_summary = False

args.device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')

print(args.cuda)

find best (optimal) threshold using roc curve

 def plot_roc_curve(fpr, tpr):

    plt.plot(fpr, tpr, color='orange', label='ROC')
    plt.plot([0, 1], [0, 1], color='darkblue', linestyle='--')
    plt.xlabel('False Positive Rate')
    plt.ylabel('True Positive Rate')
    plt.title('Receiver Operating Characteristic (ROC) Curve')
    plt.legend()
    plt.show()

y_true = np.array([0,0, 1, 1,1])
y_scores = np.array([0.0,0.09, .05, .75,1])

fpr, tpr, thresholds = roc_curve(y_true, y_scores)
print(tpr)
print(fpr)
print(thresholds)
print(roc_auc_score(y_true, y_scores))
optimal_idx = np.argmax(tpr - fpr)
optimal_threshold = thresholds[optimal_idx]
print("Threshold value is:", optimal_threshold)
plot_roc_curve(fpr, tpr)

What AUC(area under curve) value is better ?

 What AUC(area under curve) value is better ?

0.9 ~ 1 : excellent
0.8 ~ 0.9: good
0.7 ~ 0.8 : normal
0.6 ~ 0.7 : poor
0.5 ~ 0.6 : fail

python measure processing time

 

from time import process_time

# Start the stopwatch / counter

t1_start = process_time()

###

#processing

###

# Stop the stopwatch / counter

t1_stop = process_time()

sec = t1_stop-t1_start

split train test dataset

 

import random

from sklearn.model_selection import train_test_split

random.shuffle(pkl_list)

pkl_train, pkl_test = train_test_split(pkl_list, test_size=0.2)