#
# Tensorflow Keras NN for cancer data
# Warning: overfitting, too many parameters and too many epochs.
#
import numpy as np
from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers

# Load dataset
cancer = load_breast_cancer()
X, y = cancer.data, cancer.target


# Train/test split
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, random_state=42
)

# Normalize features (important for neural nets)
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)

"""
# Keras model
model = keras.Sequential([
    layers.Dense(64, activation="relu", input_shape=(X_train.shape[1],)),
    layers.Dense(64, activation="relu"),
    layers.Dense(1)  
])
"""
# Another way to define the model
Dense = layers.Dense
model = keras.Sequential()
model.add(Dense(64, activation="relu", input_shape=(X_train.shape[1],)))
model.add(Dense(64, activation='relu'))
model.add(Dense(100, activation='relu'))
model.add(Dense(100, activation='relu'))
model.add(Dense(100, activation='relu'))
model.add(Dense(100, activation='relu'))
model.add(Dense(100, activation='relu'))
model.add(Dense(20, activation='relu'))
model.add(Dense(1, activation='sigmoid')) # output is a binary number 0 or 1


# Compile model
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

# Examine model
model.summary()

# Train model
history = model.fit(X_train, y_train, 
                    validation_split=0.2,
                    epochs=50, 
                    batch_size=16,
                    verbose=1)

# Evaluate
loss, accuracy = model.evaluate(X_test, y_test) # , verbose=0)
print(f"accuracy = {accuracy:.2f}")

# Plotting
# -------- 
# Plot training & validation accuracy 
import matplotlib.pyplot as plt
plt.figure(figsize=(12,5))
plt.subplot(1,2,1)

plt.plot(history.history['accuracy'])
plt.plot(history.history['val_accuracy']) # needs validation_split in model.fit
plt.title('Model accuracy')
plt.ylabel('Accuracy')
plt.xlabel('Epoch')
plt.legend(['Train', 'Validation'], loc='upper left')


# Plot training & validation loss values
plt.subplot(1,2,2)

plt.plot(history.history['loss'])
plt.plot(history.history['val_loss']) # needs validation_split in model.fit
plt.title('Model loss')
plt.ylabel('Loss')
plt.xlabel('Epoch')
plt.legend(['Train', 'Validation'], loc='upper left')
plt.show()