tf_iris.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "11ddc5ce",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'2.5.0'"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import tensorflow as tf\n",
    "import numpy as np\n",
    "from keras.utils import np_utils\n",
    "from sklearn.datasets import load_iris\n",
    "from sklearn.model_selection import train_test_split\n",
    "tf.__version__"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "49713421",
   "metadata": {},
   "outputs": [],
   "source": [
    "iris = load_iris()\n",
    "x_train, x_test, y_train, y_test = train_test_split(\n",
    "    iris.data, iris.target, test_size=0.33, random_state=2021)\n",
    "y_train=np_utils.to_categorical(y_train, num_classes=3)\n",
    "y_test=np_utils.to_categorical(y_test, num_classes=3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "4cd18d2a",
   "metadata": {},
   "outputs": [],
   "source": [
    "model = tf.keras.Sequential([\n",
    "    tf.keras.layers.Dense(500, input_dim=4, activation='relu'),\n",
    "    tf.keras.layers.Dense(256, activation='relu'),\n",
    "    tf.keras.layers.Dense(256, activation='relu'),\n",
    "    tf.keras.layers.Dense(128, activation='relu'),\n",
    "    tf.keras.layers.Dropout(0.2),\n",
    "    tf.keras.layers.Dense(128, activation='relu'),\n",
    "    tf.keras.layers.Dense(3, activation='softmax')\n",
    "])\n",
    "\n",
    "model.compile(loss='categorical_crossentropy',\n",
    "              optimizer='adam',\n",
    "              metrics=['accuracy'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "826d1420",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<tensorflow.python.keras.callbacks.History at 0x1589a17b8>"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.fit(x_train,y_train, validation_data=(x_test,y_test), batch_size=20,epochs=30,verbose=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "2b34acf5",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy of the dataset 99.0\n"
     ]
    }
   ],
   "source": [
    "prediction=model.predict(x_train)\n",
    "length=len(prediction)\n",
    "y_label=np.argmax(y_train,axis=1)\n",
    "predict_label=np.argmax(prediction,axis=1)\n",
    "\n",
    "accuracy=np.sum(y_label==predict_label)/length * 100 \n",
    "print(\"Accuracy of the dataset\",accuracy )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "afd9f85f",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy of the dataset 94.0\n"
     ]
    }
   ],
   "source": [
    "prediction=model.predict(x_test)\n",
    "length=len(prediction)\n",
    "y_label=np.argmax(y_test,axis=1)\n",
    "predict_label=np.argmax(prediction,axis=1)\n",
    "\n",
    "accuracy=np.sum(y_label==predict_label)/length * 100 \n",
    "print(\"Accuracy of the dataset\",accuracy )"
   ]
  }
 ],
 "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": "3.6.2"
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": true,
   "sideBar": true,
   "skip_h1_title": false,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {},
   "toc_section_display": true,
   "toc_window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}