feed_forward_dense_colab.py

import tensorflow as tf
from tensorflow import keras
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
pima = pd.read_csv("diabetes.csv")
pima.head()
#split dataset in features and target variable
feature_cols = ['Pregnancies', 'Glucose', 'BloodPressure', 'SkinThickness','Insulin','BMI','DiabetesPedigreeFunction', 'Age']
Xraw = pima[feature_cols] # Features
y = pima.Outcome # Target variable
from sklearn.preprocessing import StandardScaler
scaler = StandardScaler()
X = scaler.fit_transform(Xraw)
# split X and y into training and testing sets
from sklearn.model_selection import train_test_split
X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.05,random_state=0)
print(y_test)
# We'll use Keras to create a Neural network
model = tf.keras.Sequential()
model.add(keras.layers.Dense(4, activation='relu', input_shape=(8,)))
model.add(keras.layers.Dense(2,activation='relu'))
#model.add(keras.layers.Dense(8,activation='relu'))
model.add(keras.layers.Dense(1,activation='sigmoid'))
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
history_1 = model.fit(X_train, y_train, epochs=500, validation_data=(X_test, y_test))
# Exclude the first few epochs so the graph is easier to read
loss = history_1.history['loss']
val_loss = history_1.history['val_loss']
epochs = range(1, len(loss) + 1)
SKIP = 10
plt.plot(epochs[SKIP:], loss[SKIP:], 'g.', label='Training loss')
plt.plot(epochs[SKIP:], val_loss[SKIP:], 'b.', label='Validation loss')
plt.title('Training and validation loss')
plt.xlabel('Epochs')
plt.ylabel('Loss')
plt.legend()
plt.show()
# Find the weights of the model
weights = model.get_weights()
print(weights)
# Saving the array in a text file
file = open("hyper_param.txt", "w+")
content = str(weights)
file.write(content)
file.close()
#y_pred = model.predict(X_test)
# extract the predicted probabilities
p_pred = model.predict(X_test)
p_pred = p_pred.flatten()
print(p_pred.round(2))
# [1. 0.01 0.91 0.87 0.06 0.95 0.24 0.58 0.78 ...

# extract the predicted class labels
y_pred = np.where(p_pred > 0.5, 1, 0)
print(y_pred)
# import the metrics class
from sklearn import metrics
cnf_matrix = metrics.confusion_matrix(y_test, y_pred)
cnf_matrix