esmitt

from scipy.stats import describe
import numpy as np

# arr_values is a numpy array
def print_stats(arr_values: np.array) -> None:
  stats = describe(arr_values)
  print(f'min: {stats.minmax[0]:.5f}, max: {stats.minmax[1]:.4f}')
  print(f'mean: {stats.mean:.5f}')
  print(f'standard: {np.std(arr_values):.5f}')
  print(f'variance: {stats.variance:.5f}')

esmitt

@echo off

REM Remove files generated by compiler in this directory and all subdirectories.
REM Essential release files are kept.

echo Removing "*.csproj.user" files...
for /f "delims==" %%i in ('dir /b /on /s "%~p0*.csproj.user"') do del "%%i" /f /q
echo.

echo Removing "*.exe.config" files...

esmitt

from sklearn.metrics import roc_auc_score, roc_curve

def plot_roc(name: str, labels: numpy.ndarray, predictions: numpy.ndarray, **kwargs) -> ():
  fp, tp, _ = roc_curve(labels, predictions)
  auc_roc = roc_auc_score(labels, predictions)
  plt.plot(100*fp, 100*tp, label=name + " (" + str(round(auc_roc, 3)) + ")", 
           linewidth=2, **kwargs)
  plt.xlabel('False positives [%]')
  plt.ylabel('True positives [%]')
  plt.title('ROC curve')

esmitt

precision = Precision()
precision.update_state(y_train, y_train_pred)
precision.result().numpy()

esmitt

from sklearn.metrics import confusion_matrix
import seaborn as sns

# notice the threshold
def plot_cm(labels: numpy.ndarray, predictions: numpy.ndarray, p: float=0.5) -> ():
    cm = confusion_matrix(labels, predictions > p)
    # you can normalize the confusion matrix

    plt.figure(figsize=(5,5))
    sns.heatmap(cm, annot=True, fmt="d")

esmitt

# Evaluate the model on the test data using `evaluate`
print("Evaluate on test data")
score_test = model.evaluate(test_ds.batch(batch_size))
for name, value in zip(model.metrics_names, score_test):
    print(name, ': ', value)

esmitt

def plot_metrics(history: History) -> ():
    metrics =  ['loss', 'precision', 'recall', 'auc', 'tp', 'sensitivity']
    for n, metric in enumerate(metrics):
        name = metric.replace("_"," ").capitalize()
        plt.subplot(3, 2, n+1)  # adjust according to metrics
        plt.plot(history.epoch,  history.history[metric], color=colors[0], label='Train')
        plt.plot(history.epoch, history.history['val_'+metric],
                 color=colors[0], linestyle="--", label='Val')
        plt.xlabel('Epoch')
        plt.ylabel(name)

esmitt

import matplotlib.pyplot as plt
from matplotlib import rcParams

rcParams['figure.figsize'] = (12, 10)
colors = plt.rcParams['axes.prop_cycle'].by_key()['color']

def plot_log_loss(history: History, title_label: str, n: int) -> ():
    # Use a log scale to show the wide range of values.
    plt.semilogy(history.epoch,  history.history['loss'],
               color=colors[n], label='Train '+title_label)

esmitt

batch_size = 64

"""
Training the model for 60 epochs using our dataset.
The batch size (64) is the same for the validation data.
Only 1 callback was used, but could be more like TensorBoard, ModelCheckpoint, etc.
"""
history = model.fit(train_ds.batch(batch_size=batch_size),
                    epochs=60,
                    validation_data=validation_ds.batch(batch_size=batch_size),

esmitt

from tensorflow.keras.callbacks import EarlyStopping

"""
This callback will stop the training when there is no improvement in the validation accuracy across epochs
"""
early_callback = EarlyStopping(monitor='val_auc', 
                               verbose=1,
                               patience=10,
                               mode='max',
                               restore_best_weights=True)