Breast Cancer Detection.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "s=100\n",
    "X_train = []\n",
    "y_train = []\n",
    "for folder in  os.listdir(trainpath +'TrainingSet') : \n",
    "    files = gb.glob(pathname= str( trainpath +'TrainingSet//' + folder + '/*.png'))\n",
    "    for file in files: \n",
    "        image = cv2.imread(file)\n",
    "        image_array = cv2.resize(image , (s,s))\n",
    "        X_train.append(list(image_array))\n",
    "        y_train.append(code[folder])\n",
    "\n",
    "\n",
    "\n",
    "X_pred = []\n",
    "s=100\n",
    "files = gb.glob(pathname= str(testpath + 'ValidationSet/*.png'))\n",
    "for file in files: \n",
    "    image = cv2.imread(file)\n",
    "    image_array = cv2.resize(image , (s,s))\n",
    "    X_pred.append(list(image_array))\n",
    "\n",
    "\n",
    "\n",
    "X_train = np.array(X_train)\n",
    "y_train = np.array(y_train)\n",
    "X_pred_array = np.array(X_pred)\n",
    "\n",
    "\n",
    "print(f'X_train shape  is {X_train.shape}')\n",
    "print(f'y_train shape  is {y_train.shape}')\n",
    "print(f'X_pred shape  is {X_pred_array.shape}')\n",
    "\n",
    "\n",
    "\n",
    "KerasModel = keras.models.Sequential([\n",
    "        keras.layers.Conv2D(200,kernel_size=(3,3),activation='relu',input_shape=(s,s,3)),\n",
    "        keras.layers.Conv2D(150,kernel_size=(3,3),activation='relu'),\n",
    "        keras.layers.MaxPool2D(4,4),\n",
    "        keras.layers.Conv2D(120,kernel_size=(3,3),activation='relu'),    \n",
    "        keras.layers.Conv2D(80,kernel_size=(3,3),activation='relu'),    \n",
    "        keras.layers.Conv2D(50,kernel_size=(3,3),activation='relu'),\n",
    "        keras.layers.MaxPool2D(4,4),\n",
    "        keras.layers.Flatten() ,    \n",
    "        keras.layers.Dense(120,activation='relu') ,    \n",
    "        keras.layers.Dense(100,activation='relu') ,    \n",
    "        keras.layers.Dense(50,activation='relu') ,        \n",
    "        keras.layers.Dropout(rate=0.5) ,            \n",
    "        keras.layers.Dense(3,activation='softmax') ,    \n",
    "        ])\n",
    "\n",
    "KerasModel.compile(optimizer ='adam',loss='sparse_categorical_crossentropy',metrics=['accuracy'])\n",
    "print('Model Details are : ')\n",
    "print(KerasModel.summary())\n",
    "\n",
    "\n",
    "epochs = 15\n",
    "\n",
    "ThisModel = KerasModel.fit(X_train, y_train, epochs=epochs,batch_size=16,verbose=1, callbacks=[learn_control, checkpoint])\n",
    "\n",
    "\n",
    "ModelLoss, ModelAccuracy = KerasModel.evaluate(X_train, y_train)\n",
    "\n",
    "print('Total Loss is {}'.format(ModelLoss))\n",
    "print('Total Accuracy is {}'.format(ModelAccuracy ))\n",
    "\n",
    "\n",
    "\n",
    "y_result = KerasModel.predict(X_pred_array)\n",
    "\n",
    "print('Prediction Shape is {}'.format(y_result.shape))\n",
    "\n",
    "\n",
    "\n",
    "import warnings\n",
    "warnings.filterwarnings('always')\n",
    "warnings.filterwarnings('ignore')\n",
    "import fnmatch \n",
    "import os \n",
    "from sklearn.metrics import confusion_matrix\n",
    "\n",
    "image_path = 'Data\\ValidationSet'\n",
    "for filename in os.listdir(image_path):\n",
    "    filename = os.path.basename(filename)\n",
    "    Actual_list    = []\n",
    "    Predicted_list = []       \n",
    "    if any(map(filename.startswith, 'InSitu_')):\n",
    "        Actual='Insitu'\n",
    "            \n",
    "    if any(map(filename.startswith, 'SOB_B_')):\n",
    "        Actual='Benign'\n",
    "            \n",
    "    if any(map(filename.startswith, 'SOB_M_')):\n",
    "        Actual='Invasive'\n",
    "\n",
    "plt.figure(figsize=(20,40))\n",
    "for n , i in enumerate(list(np.random.randint(0,len(X_pred),306))) : \n",
    "    plt.subplot(34,9,n+1)\n",
    "    plt.imshow(X_pred[i]) \n",
    "    plt.axis('off')\n",
    "    Predicted= getcode(np.argmax(y_result[i]))\n",
    "    plt.title('Predicted:  ' + Predicted +'\\n' + 'Actual:' + Actual)\n",
    "    Actual_list.append(Actual)\n",
    "    Predicted_list.append(Predicted)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_tested_predictions(Actual_list, Predicted_list):\n",
    "    correct_preds = []\n",
    "    incorrect_preds = []\n",
    "    correct_count = 0\n",
    "    incorrect_count = 0\n",
    "    for ii in range(len(Actual_list)):\n",
    "        label_idx = np.argmax(Actual_list[ii])\n",
    "        prediction_idx = np.argmax(Predicted_list[ii])\n",
    "        prediction = preds[ii][prediction_idx]\n",
    "        if prediction_idx == label_idx:\n",
    "            correct_preds.append(prediction)\n",
    "            incorrect_preds.append(np.nan)\n",
    "            correct_count = correct_count + 1\n",
    "        if prediction_idx != label_idx:\n",
    "            incorrect_preds.append(prediction)\n",
    "            correct_preds.append(np.nan)\n",
    "            incorrect_count = incorrect_count + 1\n",
    "    return correct_preds, correct_count, incorrect_preds, incorrect_count\n",
    "\n",
    "correct_preds, correct_count, incorrect_preds, incorrect_count = get_tested_predictions(Actual_list,Predicted_list)\n",
    "print(\"Correct predictions: %d/%d\" % (correct_count,len(Predicted_list)))\n",
    "print(\"Incorrect predictions: %d/%d\" % (incorrect_count,len(Predicted_list)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import itertools\n",
    "from sklearn.metrics import confusion_matrix\n",
    "\n",
    "y_trues = [np.argmax(ii) for ii in Actual_list]\n",
    "y_preds = [np.argmax(ii) for ii in Predicted_list]\n",
    "\n",
    "\n",
    "def plot_confusion_matrix(cm, classes,\n",
    "                          normalize=False,\n",
    "                          title='Confusion matrix',\n",
    "                          cmap=plt.cm.Blues):\n",
    "\n",
    "    plt.imshow(cm, interpolation='nearest', cmap=cmap)\n",
    "    plt.title(title)\n",
    "    plt.colorbar()\n",
    "    tick_marks = np.arange(len(classes))\n",
    "    plt.xticks(tick_marks, classes, rotation=45)\n",
    "    plt.yticks(tick_marks, classes)\n",
    "\n",
    "    fmt = '.2f' if normalize else 'd'\n",
    "    thresh = cm.max() / 2.\n",
    "    for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):\n",
    "        plt.text(j, i, format(cm[i, j], fmt),\n",
    "                 horizontalalignment=\"center\",\n",
    "                 color=\"white\" if cm[i, j] > thresh else \"black\")\n",
    "\n",
    "    plt.tight_layout()\n",
    "    plt.ylabel('True label')\n",
    "    plt.xlabel('Predicted label')\n",
    "\n",
    "cnf_matrix = confusion_matrix(y_trues, y_preds)\n",
    "class_names=list(set(np.concatenate((y_trues,y_preds),axis=0)))\n",
    "\n",
    "# Plot non-normalized confusion matrix\n",
    "plt.figure()\n",
    "plot_confusion_matrix(cnf_matrix, classes=class_names, title='Confusion matrix, without normalization')\n",
    "plt.show()\n"
   ]
  }
 ],
 "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": "3.8.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}