import pandas as pd, numpy as np, seaborn as sns, matplotlib.pyplot as plt

from sklearn.linear_model import LogisticRegression

import statsmodels.api as sm

from flask import Flask, render_template, request

from sklearn.metrics import confusion_matrix

from sklearn import metrics

import webbrowser

from threading import Timer

app = Flask(__name__)

@app.route("/")

@app.route("/home")

def home():

return render_template("health_index.html")

@app.route("/result", methods= ["POST", 'GET'])

def result():

Rawdf = pd.read_csv("https://97221248-9bb3-4fc9-9d37-d1ad34bc7154.usrfiles.com/ugd/972212_590fd873a65640c1843bb2e745ec52fc.csv", sep=";")

Rawdf['AgeinYr'] = (Rawdf.age)//365

Rawdf['BP_Status'] = [1 if i > 140 or j > 90 else 0 for i,j in zip(Rawdf.ap_hi, Rawdf.ap_lo) ]

Finaldf = Rawdf[['gender','height','weight','cholesterol','alco','active','cardio','AgeinYr', 'BP_Status']]

Finaldf['gender'] = Finaldf.gender.map({1:0,2:1}) # 1 - Male 0 - Female

X_train = Finaldf.drop('BP_Status', axis=1)

y_train = Finaldf[['BP_Status']]

lr1 = sm.GLM(y_train, X_train, family= sm.families.Binomial())

lm1 = lr1.fit()

y_train_predict = lm1.predict(X_train)

Pred_DF = pd.DataFrame({'Actual':y_train.values, 'Predict' : y_train_predict})

Matrix_df = pd.DataFrame(columns=['Cut_off', 'accuracy', 'Sensitivity', 'Specificity'])

cutt_off = list(np.arange(0,1,0.01))

for i in cutt_off:

val = [1 if j > i else 0 for j in Pred_DF.Predict]

Pred_DF[i] = val

for i in cutt_off:

cm = metrics.confusion_matrix(Pred_DF.Actual,Pred_DF[i])

total_val = sum(sum(cm))

TP = cm[1,1]

TN = cm[0,0]

FP = cm[0,1]

FN = cm[1,0]

accuracy = (TP+TN)/total_val

Sensitivity = TP / (TP+FN)

Specificity = TN / (TN+FP)

Matrix_df.loc[i] = [i, accuracy, Sensitivity, Specificity]

Matrix_df['Dif'] = abs(Matrix_df.Sensitivity - Matrix_df.Specificity)

Matrix_df = Matrix_df.sort_values(by = 'Dif', ascending=False)

Optimum_cutoff = Matrix_df[Matrix_df.Dif == Matrix_df.Dif.min()]

ct_off = Optimum_cutoff['Cut_off'].values[0]

output = request.form.to_dict()

X_test = pd.DataFrame({'gender':int(output['gender']), 'height':int(output['height']), 'weight':int(output['weight']),

'cholesterol':int(output['chol']), 'alco':int(output['alcohol']), 'active':int(output['active']),

'cardio':int(output['cardio']), 'AgeinYr':int(output['age'])}, index=[0])

y_test_pred = lm1.predict(X_test)

if y_test_pred.values > 0.218:

prediction = 'Chances of Hypertension'

else:

prediction = 'Low Chance of Hypertension'

return render_template("health_index.html", prediction = prediction)

def open_browser():

webbrowser.open_new('http://127.0.0.1:5000/')

if __name__ == '__main__':

Timer(1, open_browser).start()

app.run(port=5000)

Ateendra Jha

Case Study

Subscribe to my Updates