from google.colab import drive
drive.mount('/content/drive')
%cd /content/drive/MyDrive/Datasets/

import numpy as np
import pandas as pd
import tensorflow as tf
from tensorflow import keras
from keras.models import Sequential
from keras.layers import Dense
import matplotlib.pyplot as plt
import seaborn as sns

dataset = pd.read_csv('Diabetes.tsv', sep='\t')
dataset.head()

dataset.info()

dataset.isnull().sum()

f, ax = plt.subplots(1, 2, figsize = (12, 6))
f.suptitle("Diabetes?", fontsize = 18.)
_ = dataset.Outcome.value_counts().plot.bar(ax = ax[0], rot = 0, 
                                            color = (sns.color_palette()[0], sns.color_palette()[2])).set(xticklabels = ["No", "Yes"])
_ = dataset.Outcome.value_counts().plot.pie(labels = ("No", "Yes"), autopct = "%.2f%%", 
                                            label = "", fontsize = 13., ax = ax[1],\
colors = (sns.color_palette()[0], sns.color_palette()[2]), wedgeprops = {"linewidth": 1.5, "edgecolor": "#F7F7F7"}), 
ax[1].texts[1].set_color("#F7F7F7"), ax[1].texts[3].set_color("#F7F7F7")

fig, ax = plt.subplots(4,2, figsize=(16,16))
sns.distplot(dataset.Age, bins = 20, ax=ax[0,0]) 
sns.distplot(dataset.Preg, bins = 20, ax=ax[0,1]) 
sns.distplot(dataset.GLU, bins = 20, ax=ax[1,0]) 
sns.distplot(dataset.BP, bins = 20, ax=ax[1,1]) 
sns.distplot(dataset.ST, bins = 20, ax=ax[2,0])
sns.distplot(dataset.INS, bins = 20, ax=ax[2,1])
sns.distplot(dataset.BMI, bins = 20, ax=ax[3,0]) 
sns.distplot(dataset.DPF, bins = 20, ax=ax[3,1]) 

corr=dataset.corr()

sns.set(font_scale=1.15)
plt.figure(figsize=(14, 10))

sns.heatmap(corr, vmax=.8, linewidths=0.01,
            square=True,annot=True,cmap='YlGnBu',linecolor="black")
plt.title('Correlation between features');

sns.pairplot(data=dataset, hue='Outcome')
plt.show()

x = dataset.iloc[:,0:8].values
y = dataset.iloc[:, -1].values

x

y

# from sklearn.preprocessing import MinMaxScaler
# sc = MinMaxScaler()
# x = sc.fit_transform(x)

from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
x = sc.fit_transform(x)

x

x.shape

from sklearn.model_selection import train_test_split
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.20, random_state=12)

x_test.shape

y_test.shape

model = Sequential()
model.add(Dense(32, input_dim=8, activation='softmax'))
model.add(Dense(16, activation='relu'))
model.add(Dense(8, activation='relu'))
model.add(Dense(1, activation='sigmoid'))

model.compile(loss='MSE', optimizer='adam', metrics=['accuracy'])



model.summary()

from keras.utils.vis_utils import plot_model
from IPython.display import Image
plot_model(model, to_file='nn_model_plot.png', show_shapes=True, show_layer_names=True)
Image(retina=True, filename='nn_model_plot.png')

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

# Train and Test accuracy
scores = model.evaluate(x_train,y_train)
print("Training Accuracy: %.2f%%\n" % (scores[1]*100))
scores = model.evaluate(x_test,y_test)
print("Testing Accuracy: %.2f%%\n" % (scores[1]*100))

y_pred = model.predict(x_test)
y_pred = (y_pred > 0.5)
print(np.concatenate((y_pred.reshape(len(y_pred),1), y_test.reshape(len(y_test),1)),1))

from sklearn.metrics import confusion_matrix, accuracy_score
cm = confusion_matrix(y_test, y_pred)
print(cm)
accuracy_score(y_test, y_pred)

ax = sns.heatmap(cm, annot=True, xticklabels=["No Diabetes",'Diabetes'], yticklabels=['No Diabetes','Diabetes'],
                cbar=False,cmap='Blues')
ax.set_xlabel('Prediction')
ax.set_ylabel('Actual')
plt.show()

acc = hist.history['accuracy']
loss = hist.history['loss'] 

from matplotlib import pyplot as plt
plt.plot(hist.history['accuracy'])
plt.title('model accuracy')
plt.ylabel('accuracy')
plt.xlabel('epoch')
plt.legend(['train'], loc='upper left')
plt.show()
plt.savefig('accuracy_curve.png')

plt.plot(hist.history['loss'])
plt.title('model loss')
plt.ylabel('loss')
plt.xlabel('epoch')
plt.legend(['train'], loc='upper left')
plt.show()
plt.savefig('loss_curve.png')