import tensorflow as tf
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

print(tf.__version__)

from google.colab import files
setdate = files.upload()

import pandas as pd
dataset = pd.read_csv('n7point.csv')

dataset.head()
dataset.shape


x = dataset.iloc[:,0:7].values
y = dataset.iloc[:,7].values

x[1,:]

x.shape, y.shape

# split dataset
from sklearn.model_selection import train_test_split
x_train,x_test, y_train,y_test = train_test_split(x,y,test_size=0.3,random_state=0)

x_train.shape, y_train.shape, x_test.shape, y_test.shape

x_train.shape, x_test.shape


x_train = x_train.reshape(11779, 7, 1)
x_test = x_test.reshape(2945, 7, 1)

model_CNN9 = tf.keras.models.Sequential()
model_CNN9.add(tf.keras.layers.Input(shape=(7,1)))
model_CNN9.add(tf.keras.layers.Conv1D(filters=64, kernel_size=2, activation='relu', name="Conv1D_1"))
model_CNN9.add(tf.keras.layers.Dropout(0.2))
model_CNN9.add(tf.keras.layers.Conv1D(filters=32, kernel_size=1, activation='relu', name="Conv1D_2"))
model_CNN9.add(tf.keras.layers.MaxPooling1D(pool_size=1, name="MaxPooling1D"))
model_CNN9.add(tf.keras.layers.Flatten(name="Flatten"))
model_CNN9.add(tf.keras.layers.Dense(32, activation="relu"))
model_CNN9.add(tf.keras.layers.Dense(1, activation = 'sigmoid'))
model_CNN9.compile(loss='binary_crossentropy',optimizer='adam',metrics=['accuracy'])
model_CNN9.summary()

hist=model_CNN9.fit(x_train, y_train,  validation_data=(x_test, y_test), epochs=100)

# Commented out IPython magic to ensure Python compatibility.
import matplotlib.pyplot as plt
# %matplotlib inline
import seaborn as sns
sns.set()
 
acc = hist.history['accuracy']
val = hist.history['val_accuracy']
epochs = range(1, len(acc) + 1)
 
plt.plot(epochs, acc, '-', label='Training accuracy')
plt.plot(epochs, val, ':', label='Validation accuracy')
plt.title('Training and Validation Accuracy')
plt.xlabel('Epoch')
plt.ylabel('Accuracy')
plt.legend(loc='lower right')
plt.plot()

acc = hist.history['accuracy']
val_acc = hist.history['val_accuracy']

loss = hist.history['loss']
val_loss = hist.history['val_loss']

epochs_range = range(100)

plt.figure(figsize=(8, 8))
plt.plot(epochs_range, acc, label='Training Accuracy')
plt.plot(epochs_range, val_acc, label='Validation Accuracy')
plt.legend(loc='lower right')
plt.title('Accuracy')

from google.colab import drive
drive.mount('/content/drive')

from tensorflow import keras
keras.utils.plot_model(model_CNN9, "/content/drive/MyDrive/IA_Samples/Doctorat/model9_CNN.png", show_shapes=True, expand_nested=True)

# Evaluate on test data
test_loss, test_acc = model_CNN9.evaluate(x_test, y_test)

print('Test Accuracy: {}'.format(test_acc))

# Evaluate on training data
train_loss, train_acc = model_CNN9.evaluate(x_train, y_train)

print('Train Accuracy: {}'.format(train_acc))

from sklearn.metrics import confusion_matrix
 
y_predicted = model_CNN9.predict(x_test) > 0.5
mat = confusion_matrix(y_test, y_predicted)
labels = ['class 0', 'class 1']
 
sns.heatmap(mat, square=True, annot=True, fmt='d', cbar=False, cmap='Blues',
            xticklabels=labels, yticklabels=labels)
 
plt.xlabel('Predicted label')
plt.ylabel('Actual label')

from sklearn.metrics import classification_report

print(classification_report(y_test, y_predicted))

import matplotlib.pyplot as plt
import numpy as np
from sklearn.metrics import accuracy_score, confusion_matrix, roc_auc_score, roc_curve

def plot_roc_curve(true_y, y_prob):
    """
    plots the roc curve based of the probabilities
    """

    fpr, tpr, thresholds = roc_curve(true_y, y_prob)
    plt.plot(fpr, tpr)
    plt.xlabel('False Positive Rate')
    plt.ylabel('True Positive Rate')

plot_roc_curve(y_test, y_predicted)
print(f'model CNN AUC score: {roc_auc_score(y_test, y_predicted)}')

# serialize model to JSON
model_json = model_CNN9.to_json()
with open("/content/drive/MyDrive/IA_Samples/Doctorat_Moraru1/model9_cnn.json", "w") as json_file:
    json_file.write(model_json)

# serialize weights to HDF5
model_CNN9.save_weights("/content/drive/MyDrive/IA_Samples/Doctorat_Moraru1/model9_cnn.h5")
print("Saved model to disk")