ml-model-heart-diseases.ipynb

model.py

import pickle
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.impute import SimpleImputer
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from sklearn.naive_bayes import GaussianNB
import numpy as np
from math import *
# print("haha works")

#testing if the dataset file exists
file = open('data.data', 'r')
file.readline()
file.close()


#training the model

#load the data
data = np.genfromtxt('./data.data', delimiter=',', dtype=float)
X = data[:, range(0, 13)]
Y = data[:, 13]

#imputer was deprecated, so using the SimpleImputer as per the warning
imp = SimpleImputer(missing_values=np.nan, strategy='median')

#filter NaN values, because we don't need them?
X = imp.fit_transform(X)

#yay! splitting the training and testing the data, so we get to know what's up
X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.15, random_state=100)

# converting the y values(results column) to the one-dimentional array, because it IS a single column right? 
# seems unnecessary idk
y_train = y_train.ravel()
y_test = y_test.ravel()

# get the classifier from sklearn
clf = GaussianNB()

# train our data
clf.fit(X_train, y_train)

# test our data
result2 = clf.predict(X_test)


# calculate the accuracy of our trained model
score = accuracy_score(y_test, result2) * 100

print('accuracy: {} %'.format(round(score, 3)))

# we're skipping the most difficult / important part because we don't know how to do it.
# i.e. improving the accuracy

# saving the model
file = open('trained_clf.pkl', 'wb')

# saves the clf object to the opened file
pickle.dump(clf, file)

file.close()
print('successfully trained the model lol')

server.py

from sklearn.impute import SimpleImputer
import numpy as np
from flask import Flask ,render_template,url_for,request
import pickle

# load the trained model
file = open('trained_clf.pkl', 'rb')
clf = pickle.load(file)

#initiate Imputer 
imp = SimpleImputer(missing_values=np.nan, strategy='median')

# initiate server
app=Flask(__name__)

@app.route('/')
def home():
    return render_template('home.html')

@app.route('/predict',methods=['POST'])
def predict():
    if request.method=='POST' :
        try:
	        comment1= int(request.form['comment1'])
	        comment2 = int(request.form['comment2'])
	        comment3 = int(request.form['comment3'])
	        comment4=int(request.form['comment4'])
	        comment5=int(request.form['comment5'])
	        comment6 = int(request.form['comment6'])
	        comment7 = int(request.form['comment7'])
	        comment8 = int(request.form['comment8'])
	        comment9 = int(request.form['comment9'])
	        comment10 = int(request.form['comment10'])
	        comment11 = int(request.form['comment11'])
	        comment12 = int(request.form['comment12'])
	        comment13=int(request.form['comment13'])

	        data=[comment1,comment2,comment3,comment4,comment5,comment6,comment7,comment8,comment9,comment10,comment11,comment12,comment13]
	        data=np.array(data).reshape(-1,1).T
	        vect=imp.transform(data)
	        
	        my_prediction=clf.predict(vect)
          
          return render_template('results.html',prediction=my_prediction)
	    except e:
	    	print('Invalid values.')
	    	print(e)

if __name__=='__main__' :
    app.run(debug=True)