Final Project Pengenalan Pola.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "from matplotlib import pyplot as plt\n",
    "from tkinter import *\n",
    "import tkinter as tk\n",
    "from PIL import Image, ImageTk"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "class MinMaxScaler(object):\n",
    "    def __init__(self, feature_range=(0, 1)):\n",
    "        self.low_, self.high_ = feature_range\n",
    "\n",
    "    def fit(self, X):\n",
    "        self.min_ = X.min(axis=0)\n",
    "        self.max_ = X.max(axis=0)\n",
    "        return self\n",
    "\n",
    "    def transform(self, X):\n",
    "        X_std = (X - self.min_) / (self.max_ - self.min_)\n",
    "        return X_std * (self.high_ - self.low_) + self.low_\n",
    "\n",
    "    def fit_transform(self, X):\n",
    "        return self.fit(X).transform(X)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "def init_params():\n",
    "    W1 = np.random.rand(8, 8) - 0.5\n",
    "    b1 = np.random.rand(8, 1) - 0.5\n",
    "    W2 = np.random.rand(6, 8) - 0.5\n",
    "    b2 = np.random.rand(6, 1) - 0.5\n",
    "    W3 = np.random.rand(1, 6) - 0.5\n",
    "    b3 = np.random.rand(1, 1) - 0.5\n",
    "    return W1, b1, W2, b2, W3, b3\n",
    "\n",
    "def ReLU(Z):\n",
    "    return np.maximum(Z, 0)\n",
    "\n",
    "def sigmoid(Z):\n",
    "    A = 1/(1+np.exp(-Z))\n",
    "    return A\n",
    "\n",
    "def forward_prop(W1, b1, W2, b2, W3, b3, X):\n",
    "    Z1 = W1.dot(X) + b1\n",
    "    A1 = ReLU(Z1)\n",
    "    Z2 = W2.dot(A1) + b2\n",
    "    A2 = ReLU(Z2)\n",
    "    Z3 = W3.dot(A2) + b3\n",
    "    A3 = sigmoid(Z3)\n",
    "    return Z1, A1, Z2, A2, Z3, A3\n",
    "\n",
    "def ReLU_deriv(Z):\n",
    "    return Z > 0\n",
    "\n",
    "def backward_prop(Z1, A1, Z2, A2, Z3, A3, W1, W2, W3, X, Y):\n",
    "    global m\n",
    "    reshapeY = Y.reshape(618,1)\n",
    "    dZ3 = A3 - reshapeY.T\n",
    "    dW3 = 1 / m * dZ3.dot(A2.T)\n",
    "    db3 = 1 / m * np.sum(dZ3)\n",
    "    dZ2 = W3.T.dot(dZ3) * ReLU_deriv(Z2)\n",
    "    dW2 = 1 / m * dZ2.dot(A1.T)\n",
    "    db2 = 1 / m * np.sum(dZ2)\n",
    "    dZ1 = W2.T.dot(dZ2) * ReLU_deriv(Z1)\n",
    "    dW1 = 1 / m * dZ1.dot(X.T)\n",
    "    db1 = 1 / m * np.sum(dZ1)\n",
    "    \n",
    "    return dW1, db1, dW2, db2, dW3, db3\n",
    "\n",
    "def update_params(W1, b1, W2, b2, W3, b3, dW1, db1, dW2, db2, dW3, db3, alpha):\n",
    "    W1 = W1 - alpha * dW1\n",
    "    b1 = b1 - alpha * db1    \n",
    "    W2 = W2 - alpha * dW2  \n",
    "    b2 = b2 - alpha * db2\n",
    "    W3 = W3 - alpha * dW3  \n",
    "    b3 = b3 - alpha * db3\n",
    "    \n",
    "    return W1, b1, W2, b2, W3, b3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_predictions(A3):\n",
    "    prediksi = []\n",
    "    for a in A3[0]:\n",
    "        if a >= 0.5:\n",
    "            output = 1\n",
    "        else:\n",
    "            output = 0\n",
    "        prediksi.append(output)\n",
    "    return prediksi\n",
    "\n",
    "def get_predictions_test(data):\n",
    "    \n",
    "    if data >= 0.5:\n",
    "        output = 1\n",
    "    else:\n",
    "        output = 0\n",
    "        \n",
    "    return output\n",
    "\n",
    "def get_accuracy(predictions, Y):\n",
    "    return np.sum(predictions == Y) / Y.size\n",
    "\n",
    "def gradient_descent(X, Y, alpha, iterations):\n",
    "    global akurasi\n",
    "    W1, b1, W2, b2, W3, b3 = init_params()\n",
    "    for i in range(iterations):\n",
    "        Z1, A1, Z2, A2, Z3, A3 = forward_prop(W1, b1, W2, b2, W3, b3, X)\n",
    "        dW1, db1, dW2, db2, dW3, db3 = backward_prop(Z1, A1, Z2, A2, Z3, A3, W1, W2, W3, X, Y)\n",
    "        W1, b1, W2, b2, W3, b3 = update_params(W1, b1, W2, b2, W3, b3, dW1, db1, dW2, db2, dW3, db3, alpha)\n",
    "        if i % 10 == 0:\n",
    "            print(\"Iteration: \", i)\n",
    "            predictions = get_predictions(A3)\n",
    "            akurasi = get_accuracy(predictions, Y)\n",
    "            print(akurasi)\n",
    "    return W1, b1, W2, b2, W3, b3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "def make_predictions(X, W1, b1, W2, b2, W3, b3):\n",
    "    _, _, _, _, _, A3 = forward_prop(W1, b1, W2, b2, W3, b3, X)\n",
    "    predictions = get_predictions(A3)\n",
    "    \n",
    "    if predictions == 1:\n",
    "        diabetes = \"Diabetes\"\n",
    "    else:\n",
    "        diabetes = \"Tidak Diabetes\"\n",
    "    \n",
    "    return diabetes\n",
    "\n",
    "def test_prediction(index, W1, b1, W2, b2, W3, b3):\n",
    "    global hasilprediksi_text, prediksi_btn, canvas\n",
    "\n",
    "    prediction = make_predictions(index, W1, b1, W2, b2, W3, b3)\n",
    "    \n",
    "    canvas = tk.Canvas(root, width=600, height=300)\n",
    "    canvas.grid(columnspan=8, rowspan=3)\n",
    "    \n",
    "    hasilprediksi_text = tk.Label(root, text=\"Prediksi : \"+prediction, font=30)\n",
    "    hasilprediksi_text.grid(columnspan=8, column=1, row=1)\n",
    "    \n",
    "    prediksi_btn = tk.Button(root, text=\"Prediksi\", width=15, command=masukkan_prediksi)\n",
    "    prediksi_btn.grid(columnspan=8, row=2, column=1)\n",
    "    \n",
    "    print(index)\n",
    "    print(\"Prediction: \", prediction)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Iteration:  0\n",
      "0.6472491909385113\n",
      "Iteration:  10\n",
      "0.6472491909385113\n",
      "Iteration:  20\n",
      "0.6472491909385113\n",
      "Iteration:  30\n",
      "0.6472491909385113\n",
      "Iteration:  40\n",
      "0.6456310679611651\n",
      "Iteration:  50\n",
      "0.6504854368932039\n",
      "Iteration:  60\n",
      "0.6521035598705501\n",
      "Iteration:  70\n",
      "0.6537216828478964\n",
      "Iteration:  80\n",
      "0.6666666666666666\n",
      "Iteration:  90\n",
      "0.6715210355987055\n",
      "Iteration:  100\n",
      "0.6715210355987055\n",
      "Iteration:  110\n",
      "0.6763754045307443\n",
      "Iteration:  120\n",
      "0.6747572815533981\n",
      "Iteration:  130\n",
      "0.6796116504854369\n",
      "Iteration:  140\n",
      "0.6779935275080906\n",
      "Iteration:  150\n",
      "0.6844660194174758\n",
      "Iteration:  160\n",
      "0.6844660194174758\n",
      "Iteration:  170\n",
      "0.6812297734627831\n",
      "Iteration:  180\n",
      "0.6844660194174758\n",
      "Iteration:  190\n",
      "0.6877022653721683\n",
      "Iteration:  200\n",
      "0.686084142394822\n",
      "Iteration:  210\n",
      "0.6974110032362459\n",
      "Iteration:  220\n",
      "0.6893203883495146\n",
      "Iteration:  230\n",
      "0.6925566343042071\n",
      "Iteration:  240\n",
      "0.6925566343042071\n",
      "Iteration:  250\n",
      "0.6893203883495146\n",
      "Iteration:  260\n",
      "0.7006472491909385\n",
      "Iteration:  270\n",
      "0.6909385113268608\n",
      "Iteration:  280\n",
      "0.6990291262135923\n",
      "Iteration:  290\n",
      "0.7071197411003236\n",
      "Iteration:  300\n",
      "0.6877022653721683\n",
      "Iteration:  310\n",
      "0.6844660194174758\n",
      "Iteration:  320\n",
      "0.6844660194174758\n",
      "Iteration:  330\n",
      "0.6812297734627831\n",
      "Iteration:  340\n",
      "0.6844660194174758\n",
      "Iteration:  350\n",
      "0.686084142394822\n",
      "Iteration:  360\n",
      "0.6844660194174758\n",
      "Iteration:  370\n",
      "0.6796116504854369\n",
      "Iteration:  380\n",
      "0.6925566343042071\n",
      "Iteration:  390\n",
      "0.6893203883495146\n",
      "Iteration:  400\n",
      "0.6844660194174758\n",
      "Iteration:  410\n",
      "0.6941747572815534\n",
      "Iteration:  420\n",
      "0.6601941747572816\n",
      "Iteration:  430\n",
      "0.6925566343042071\n",
      "Iteration:  440\n",
      "0.6909385113268608\n",
      "Iteration:  450\n",
      "0.6844660194174758\n",
      "Iteration:  460\n",
      "0.6957928802588996\n",
      "Iteration:  470\n",
      "0.6941747572815534\n",
      "Iteration:  480\n",
      "0.6909385113268608\n",
      "Iteration:  490\n",
      "0.6877022653721683\n",
      "Iteration:  500\n",
      "0.7006472491909385\n",
      "Iteration:  510\n",
      "0.6893203883495146\n",
      "Iteration:  520\n",
      "0.6957928802588996\n",
      "Iteration:  530\n",
      "0.6877022653721683\n",
      "Iteration:  540\n",
      "0.6796116504854369\n",
      "Iteration:  550\n",
      "0.6893203883495146\n",
      "Iteration:  560\n",
      "0.6941747572815534\n",
      "Iteration:  570\n",
      "0.6925566343042071\n",
      "Iteration:  580\n",
      "0.6941747572815534\n",
      "Iteration:  590\n",
      "0.6925566343042071\n",
      "Iteration:  600\n",
      "0.686084142394822\n",
      "Iteration:  610\n",
      "0.6909385113268608\n",
      "Iteration:  620\n",
      "0.6957928802588996\n",
      "Iteration:  630\n",
      "0.6828478964401294\n",
      "Iteration:  640\n",
      "0.6909385113268608\n",
      "Iteration:  650\n",
      "0.6925566343042071\n",
      "Iteration:  660\n",
      "0.6877022653721683\n",
      "Iteration:  670\n",
      "0.6909385113268608\n",
      "Iteration:  680\n",
      "0.6925566343042071\n",
      "Iteration:  690\n",
      "0.6893203883495146\n",
      "Iteration:  700\n",
      "0.6941747572815534\n",
      "Iteration:  710\n",
      "0.6941747572815534\n",
      "Iteration:  720\n",
      "0.6974110032362459\n",
      "Iteration:  730\n",
      "0.7006472491909385\n",
      "Iteration:  740\n",
      "0.7006472491909385\n",
      "Iteration:  750\n",
      "0.6909385113268608\n",
      "Iteration:  760\n",
      "0.6957928802588996\n",
      "Iteration:  770\n",
      "0.6893203883495146\n",
      "Iteration:  780\n",
      "0.6925566343042071\n",
      "Iteration:  790\n",
      "0.6893203883495146\n",
      "Iteration:  800\n",
      "0.6941747572815534\n",
      "Iteration:  810\n",
      "0.6990291262135923\n",
      "Iteration:  820\n",
      "0.6941747572815534\n",
      "Iteration:  830\n",
      "0.7006472491909385\n",
      "Iteration:  840\n",
      "0.6925566343042071\n",
      "Iteration:  850\n",
      "0.6909385113268608\n",
      "Iteration:  860\n",
      "0.6925566343042071\n",
      "Iteration:  870\n",
      "0.6941747572815534\n",
      "Iteration:  880\n",
      "0.6925566343042071\n",
      "Iteration:  890\n",
      "0.6893203883495146\n",
      "Iteration:  900\n",
      "0.6909385113268608\n",
      "Iteration:  910\n",
      "0.7055016181229773\n",
      "Iteration:  920\n",
      "0.6957928802588996\n",
      "Iteration:  930\n",
      "0.6941747572815534\n",
      "Iteration:  940\n",
      "0.6941747572815534\n",
      "Iteration:  950\n",
      "0.7022653721682848\n",
      "Iteration:  960\n",
      "0.7006472491909385\n",
      "Iteration:  970\n",
      "0.7055016181229773\n",
      "Iteration:  980\n",
      "0.7087378640776699\n",
      "Iteration:  990\n",
      "0.7087378640776699\n",
      "[[0.04054054]\n",
      " [1.        ]\n",
      " [0.48648649]\n",
      " [0.23648649]\n",
      " [0.        ]\n",
      " [0.22702703]\n",
      " [0.00423649]\n",
      " [0.33783784]]\n",
      "Prediction:  Tidak Diabetes\n",
      "[[0.        ]\n",
      " [1.        ]\n",
      " [0.45333333]\n",
      " [0.23333333]\n",
      " [0.        ]\n",
      " [0.23333333]\n",
      " [0.00333333]\n",
      " [0.16666667]]\n",
      "Prediction:  Tidak Diabetes\n"
     ]
    }
   ],
   "source": [
    "class Table:\n",
    "    table = []\n",
    "    def __init__(self,root, array, k):\n",
    "        # code for creating table\n",
    "        for i in range(total_rows):\n",
    "            for j in range(total_columns):\n",
    "                  \n",
    "                self.e = Entry(root, width=20, fg='blue',\n",
    "                               font=('Arial',8,'bold'))\n",
    "                self.table.append(self.e)  \n",
    "                self.e.grid(row=k, column=j)\n",
    "                self.e.insert(END, array[i][j])\n",
    "            k+=1\n",
    "    def label_del(self) :\n",
    "        for i in self.table :\n",
    "            i.destroy()\n",
    "            \n",
    "def prediksi():\n",
    "    global W1, W2, W3, b1, b2, b3\n",
    "    global my_label_pregnant, my_box_pregnant, my_label_glucose, my_box_glucose, my_label_bloodpressure, my_box_bloodpressure\n",
    "    global my_label_skinthickness, my_box_skinthickness, my_label_insulin, my_box_insulin, my_label_bmi, my_box_bmi\n",
    "    global my_label_dpf, my_box_dpf, my_label_age, my_box_age, masukkan2_btn, canvas\n",
    "    \n",
    "    try:\n",
    "        testarray = []\n",
    "        \n",
    "        pregnant = float(my_box_pregnant.get())\n",
    "        glucose = float(my_box_glucose.get())\n",
    "        bloodpressure = float(my_box_bloodpressure.get())\n",
    "        skinthickness = float(my_box_skinthickness.get())\n",
    "        insulin = float(my_box_insulin.get())\n",
    "        bmi = float(my_box_bmi.get())\n",
    "        dpf = float(my_box_dpf.get())\n",
    "        age = float(my_box_age.get())\n",
    "        \n",
    "        testarray.append(pregnant)\n",
    "        testarray.append(glucose)\n",
    "        testarray.append(bloodpressure)\n",
    "        testarray.append(skinthickness)\n",
    "        testarray.append(insulin)\n",
    "        testarray.append(bmi)\n",
    "        testarray.append(dpf)\n",
    "        testarray.append(age)\n",
    "        \n",
    "        my_label_pregnant.destroy()\n",
    "        my_box_pregnant.destroy()\n",
    "        my_label_glucose.destroy()\n",
    "        my_box_glucose.destroy()\n",
    "        my_label_bloodpressure.destroy()\n",
    "        my_box_bloodpressure.destroy()\n",
    "        my_label_skinthickness.destroy()\n",
    "        my_box_skinthickness.destroy()\n",
    "        my_label_insulin.destroy()\n",
    "        my_box_insulin.destroy()\n",
    "        my_label_bmi.destroy()\n",
    "        my_box_bmi.destroy()\n",
    "        my_label_dpf.destroy()\n",
    "        my_box_dpf.destroy()\n",
    "        my_label_age.destroy()\n",
    "        my_box_age.destroy()\n",
    "        masukkan2_btn.destroy()\n",
    "        \n",
    "        testarray = np.array(testarray)\n",
    "        scaler = MinMaxScaler(feature_range=(0,1)).fit(testarray)\n",
    "        testarray = scaler.transform(testarray)\n",
    "        reshapetestarray = testarray.reshape(1,-1)\n",
    "        \n",
    "        canvas.destroy()\n",
    "        \n",
    "        test_prediction(reshapetestarray.T, W1, b1, W2, b2, W3, b3)\n",
    "        \n",
    "    except ValueError:\n",
    "        my_label_pregnant.destroy()\n",
    "        my_box_pregnant.destroy()\n",
    "        my_label_glucose.destroy()\n",
    "        my_box_glucose.destroy()\n",
    "        my_label_bloodpressure.destroy()\n",
    "        my_box_bloodpressure.destroy()\n",
    "        my_label_skinthickness.destroy()\n",
    "        my_box_skinthickness.destroy()\n",
    "        my_label_insulin.destroy()\n",
    "        my_box_insulin.destroy()\n",
    "        my_label_bmi.destroy()\n",
    "        my_box_bmi.destroy()\n",
    "        my_label_dpf.destroy()\n",
    "        my_box_dpf.destroy()\n",
    "        my_label_age.destroy()\n",
    "        my_box_age.destroy()\n",
    "        masukkan2_btn.destroy()\n",
    "        canvas.destroy()\n",
    "        \n",
    "        masukkan_prediksi()\n",
    "    \n",
    "def masukkan_prediksi():\n",
    "    global W1_text, W2_text, W3_text, akurasi_text, t, t2, t3, prediksi_btn\n",
    "    global my_label_pregnant, my_box_pregnant, my_label_glucose, my_box_glucose, my_label_bloodpressure, my_box_bloodpressure\n",
    "    global my_label_skinthickness, my_box_skinthickness, my_label_insulin, my_box_insulin, my_label_bmi, my_box_bmi\n",
    "    global my_label_dpf, my_box_dpf, my_label_age, my_box_age, masukkan2_btn, hasilprediksi_text, canvas\n",
    "    \n",
    "    canvas.destroy()\n",
    "    hasilprediksi_text = tk.Label(root, text=\"Prediksi : \", font=30)\n",
    "    \n",
    "    W1_text.destroy()\n",
    "    W2_text.destroy()\n",
    "    W3_text.destroy()\n",
    "    akurasi_text.destroy()\n",
    "    t.label_del()\n",
    "    t2.label_del()\n",
    "    t3.label_del()\n",
    "    prediksi_btn.destroy()\n",
    "    hasilprediksi_text.destroy()\n",
    "    canvas = tk.Canvas(root, width=600, height=300)\n",
    "    canvas.grid(columnspan=8, rowspan=3)\n",
    "    \n",
    "    my_label_pregnant = Label(root, text=\"Pregnancies : \")\n",
    "    my_label_pregnant.grid(column=1, row=0)\n",
    "\n",
    "    my_box_pregnant = Entry(root)\n",
    "    my_box_pregnant.grid(column=2, row=0)\n",
    "\n",
    "    my_label_glucose = Label(root, text=\"Glucose : \")\n",
    "    my_label_glucose.grid(column=3, row=0)\n",
    "\n",
    "    my_box_glucose = Entry(root)\n",
    "    my_box_glucose.grid(column=4, row=0)\n",
    "\n",
    "    my_label_bloodpressure = Label(root, text=\"Blood Pressure : \")\n",
    "    my_label_bloodpressure.grid(column=5, row=0)\n",
    "\n",
    "    my_box_bloodpressure = Entry(root)\n",
    "    my_box_bloodpressure.grid(column=6, row=0)\n",
    "\n",
    "    my_label_skinthickness = Label(root, text=\"Skin Thickness : \")\n",
    "    my_label_skinthickness.grid(column=7, row=0)\n",
    "\n",
    "    my_box_skinthickness = Entry(root)\n",
    "    my_box_skinthickness.grid(column=8, row=0)\n",
    "\n",
    "    my_label_insulin = Label(root, text=\"Insulin : \")\n",
    "    my_label_insulin.grid(column=1, row=1)\n",
    "\n",
    "    my_box_insulin = Entry(root)\n",
    "    my_box_insulin.grid(column=2, row=1)\n",
    "\n",
    "    my_label_bmi = Label(root, text=\"BMI : \")\n",
    "    my_label_bmi.grid(column=3, row=1)\n",
    "\n",
    "    my_box_bmi = Entry(root)\n",
    "    my_box_bmi.grid(column=4, row=1)\n",
    "\n",
    "    my_label_dpf = Label(root, text=\"Diabetes Predigree Function : \")\n",
    "    my_label_dpf.grid(column=5, row=1)\n",
    "\n",
    "    my_box_dpf = Entry(root)\n",
    "    my_box_dpf.grid(column=6, row=1)\n",
    "\n",
    "    my_label_age = Label(root, text=\"Age : \")\n",
    "    my_label_age.grid(column=7, row=1)\n",
    "\n",
    "    my_box_age = Entry(root)\n",
    "    my_box_age.grid(column=8, row=1)\n",
    "    \n",
    "    masukkan2_btn = tk.Button(root, text=\"Mulai Prediksi\", width=15, command=prediksi)\n",
    "    masukkan2_btn.grid(columnspan=8, row=2, column=1)\n",
    "\n",
    "def mulai():\n",
    "    global m, total_rows, total_columns, akurasi, W1_text, W2_text, W3_text, my_label_learningrate, my_label_iterasi, canvas\n",
    "    global akurasi_text, t, t2, t3, W1, W2, W3, b1, b2, b3, my_box_learningrate, my_box_iterasi, masukkan_btn, prediksi_btn\n",
    "    \n",
    "    try:\n",
    "        learningrate = float(my_box_learningrate.get())\n",
    "        iterasi = int(my_box_iterasi.get())\n",
    "        \n",
    "        my_label_learningrate.destroy()\n",
    "        my_label_iterasi.destroy()\n",
    "        my_box_learningrate.destroy()\n",
    "        my_box_iterasi.destroy()\n",
    "        masukkan_btn.destroy()\n",
    "\n",
    "        data = pd.read_csv('diabetes.csv')\n",
    "\n",
    "        data = np.array(data)\n",
    "        m, n = data.shape\n",
    "        np.random.shuffle(data)\n",
    "\n",
    "        data_dev = data[0:150].T\n",
    "        Y_dev = data_dev[-1]\n",
    "        X_dev = data_dev[:n-1]\n",
    "\n",
    "        data_train = data[150:m].T\n",
    "        Y_train = data_train[-1]\n",
    "        X_train = data_train[:n-1]\n",
    "\n",
    "        scaler = MinMaxScaler(feature_range=(0,1)).fit(X_train)\n",
    "        X_train = scaler.transform(X_train)\n",
    "\n",
    "        W1, b1, W2, b2, W3, b3 = gradient_descent(X_train, Y_train, learningrate, iterasi)\n",
    "\n",
    "        total_rows = len(W1)\n",
    "        total_columns = len(W1[0])\n",
    "\n",
    "        W1_text = tk.Label(root, text=\"W1 hasil training\", font=30)\n",
    "        W1_text.grid(columnspan=8, column=1, row=1)\n",
    "        \n",
    "        t = Table(root, W1, 2)\n",
    "\n",
    "        total_rows = len(W2)\n",
    "        total_columns = len(W2[0])\n",
    "\n",
    "        W2_text = tk.Label(root, text=\"W2 hasil training\", font=30)\n",
    "        W2_text.grid(columnspan=8, column=1, row=10)\n",
    "\n",
    "        t2 = Table(root, W2, 11)\n",
    "\n",
    "        total_rows = len(W3)\n",
    "        total_columns = len(W3[0])\n",
    "\n",
    "        W3_text = tk.Label(root, text=\"W3 hasil training\", font=30)\n",
    "        W3_text.grid(columnspan=8, column=1, row=17)\n",
    "\n",
    "        t3 = Table(root, W3, 18)\n",
    "\n",
    "        akurasi = str(akurasi)\n",
    "\n",
    "        akurasi_text = tk.Label(root, text=\"Accuracy : \"+akurasi, font=30)\n",
    "        akurasi_text.grid(columnspan=8, column=1, row=19)\n",
    "        \n",
    "        canvas.destroy()\n",
    "        \n",
    "        prediksi_btn = tk.Button(root, text=\"Prediksi\", width=15, command=masukkan_prediksi)\n",
    "        prediksi_btn.grid(columnspan=8, row=20, column=1)\n",
    "    \n",
    "    except ValueError:\n",
    "        my_label_learningrate.destroy()\n",
    "        my_label_iterasi.destroy()\n",
    "        my_box_learningrate.destroy()\n",
    "        my_box_iterasi.destroy()\n",
    "        masukkan_btn.destroy()\n",
    "        masukkan()\n",
    "\n",
    "def masukkan():\n",
    "    global judul_text, logo_label, start_btn, my_box_learningrate, my_box_iterasi, my_label_learningrate, my_label_iterasi\n",
    "    global masukkan_btn, canvas\n",
    "    \n",
    "    judul_text.destroy()\n",
    "    logo_label.destroy()\n",
    "    start_btn.destroy()\n",
    "    \n",
    "    my_label_learningrate = Label(root, text=\"Learning Rate : \")\n",
    "    my_label_learningrate.grid(column=1, row=0)\n",
    "\n",
    "    my_box_learningrate = Entry(root)\n",
    "    my_box_learningrate.grid(column=2, row=0)\n",
    "\n",
    "    my_label_iterasi = Label(root, text=\"Jumlah Iterasi : \")\n",
    "    my_label_iterasi.grid(column=3, row=0)\n",
    "\n",
    "    my_box_iterasi = Entry(root)\n",
    "    my_box_iterasi.grid(column=4, row=0)\n",
    "    \n",
    "    masukkan_btn = tk.Button(root, text=\"Mulai Proses Training\", width=18, command=mulai)\n",
    "    masukkan_btn.grid(columnspan=8, row=1, column=1)\n",
    "\n",
    "global judul_text, logo_label, start_btn, canvas\n",
    "    \n",
    "root = tk.Tk()\n",
    "canvas = tk.Canvas(root, width=600, height=300)\n",
    "canvas.grid(columnspan=8, rowspan=3)\n",
    "\n",
    "logo = Image.open('logo.jpg')\n",
    "logo = logo.resize((200, 200), Image.ANTIALIAS)\n",
    "logo = ImageTk.PhotoImage(logo)\n",
    "logo_label = tk.Label(image=logo)\n",
    "logo_label.image = logo\n",
    "logo_label.grid(columnspan=8, row=1, column=1)\n",
    "\n",
    "judul_text = tk.Label(root, text=\"Prediksi Diabetes Menggunakan Jaringan Syaraf Tiruan\", font=30)\n",
    "judul_text.grid(columnspan=8, column=1, row=0)\n",
    "\n",
    "start_btn = tk.Button(root, text=\"Mulai\", width=15, command=masukkan)\n",
    "start_btn.grid(columnspan=8, row=2, column=1)\n",
    "\n",
    "root.mainloop()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}