Routes File

routes.py

+from keras.models import load_model
+from flask import render_template, request
+from app import app
+import numpy as np  # linear algebra
+import pandas as pd  # data processing, CSV file I/O (e.g. pd.read_csv)
+import os
+import cv2
+from pathlib import Path
+import pickle
+import tensorflow as tf
+import sklearn
+from tensorflow.keras.models import load_model
+from tensorflow.keras.preprocessing import image
+
+#### Home Page ####
+
+
+@app.route('/')
+@app.route('/home')
+def home():
+    return render_template('home.html')
+
+
+@app.route('/about')
+def about():
+    return render_template('about.html')
+
+
+
+
+######################## Stroke ############################
+
+
+@app.route('/stroke')
+def stroke():
+    return render_template('strokePage.html')
+
+
+@app.route('/predictStrokepage')
+def predictStrokepage():
+    return render_template('stroke_predict.html')
+
+# predict stroke
+
+
+@app.route('/predictStroke', methods=['POST'])
+def predictStroke():
+    gender = request.form['gender']
+    age = request.form['age']
+    hypertension = request.form['hypertension']
+    heart_disease = request.form['heart_disease']
+    ever_married = request.form['ever_married']
+    work_type = request.form['work_type']
+    Residence_type = request.form['Residence_type']
+    avg_glucose_level = request.form['avg_glucose_level']
+    bmi = request.form['bmi']
+    smoking_status = request.form['smoking_status']
+
+    with open('models/finalized_model_stroke_prediction_RF.sav', 'rb') as f:
+        model = pickle.load(f)
+
+    input_data = (gender, age, hypertension, heart_disease, ever_married,
+                  work_type, Residence_type, avg_glucose_level, bmi, smoking_status)
+    # input_data3 = np.array(input_data).astype(int)
+
+    input_data_as_numpy_array = np.asarray(input_data)
+
+    input_data_reshaped = input_data_as_numpy_array.reshape(1, -1)
+    prediction = model.predict(input_data_reshaped)
+    print(input_data)
+    if (prediction == 1):
+        result = "You are at risk of having a stroke"
+        disease = 'stroke'
+        return docRec(disease, result, value="stroke")
+    else:
+        result = "You are not at risk of having a stroke"
+        return render_template('results.html', result=result)
+
+# CT image detection
+
+
+@app.route('/predictStrokeCt')
+def predictStrokeCt():
+    return render_template('stroke_detection_CT.html')
+
+
+def predict4(img):
+    model = tf.keras.models.load_model('models/finalized_model_strokeCT.h5')
+
+    # model = load_model('finalized_model_strokeCT.h5')
+
+    model = load_model('models/finalized_model_strokeCT.h5')
+
+    pic = []
+    img = cv2.resize(img, (224, 224))
+    # Convert the image to a numpy array and preprocess it
+    x = image.img_to_array(img)
+    x = np.expand_dims(x, axis=0)
+    x /= 255
+
+    # Make a prediction using the model
+    prediction = model.predict(x)
+
+    # Print the predicted class (0 = non-stroke, 1 = stroke)
+    if prediction < 0.5:
+        return ("You don't have a stroke")
+    else:
+        return ("You have a Stroke")
+
+
+@app.route('/process_image_stroke', methods=['POST'])
+def process_image_stroke():
+    if request.method == 'POST':
+        file = request.files['file']
+        img_bytes = file.read()  # Read image data as bytes
+        # Convert bytes to OpenCV image
+        img = cv2.imdecode(np.frombuffer(img_bytes, np.uint8), -1)
+        img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)  # Convert BGR to RGB
+        prediction = predict4(img)  # Make prediction using img
+        disease = 'stroke'
+        return docRec(disease, prediction, value="stroke")
+
+    return 'File uploaded successfully!'
+
+
+def docRec(disease, result, value):
+    df = pd.read_excel('docs\RELEVANTDOCTORS.xlsx')
+
+    # find rows that contain a keyword in a specific column
+    keyword = str(disease)
+    column_name = 'Disease'
+    rec = df[df[column_name].str.contains(keyword)]
+
+    rec = rec.iloc[:, 1:]
+    table_classes = 'table table-striped table-bordered table-hover'
+    if value =="skinT":
+        textshow= True
+    else:
+        textshow=False
+
+    if value == "lung":
+        show_button = True
+        # render the output in a table format
+        return render_template('results.html', rec=rec.to_html(index=False, classes=table_classes), result=result, show_button=show_button,textshow=textshow)
+    else:
+        show_button = False
+        return render_template('results.html', rec=rec.to_html(index=False, classes=table_classes), result=result, show_button=show_button,textshow=textshow)