classification_Iris_species.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "2cc94caf",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "from sklearn.datasets import load_iris\n",
    "iris_dataset = load_iris()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "b3b222f3",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "keys of iris_dataset: \n",
      "dict_keys(['data', 'target', 'frame', 'target_names', 'DESCR', 'feature_names', 'filename', 'data_module'])\n"
     ]
    }
   ],
   "source": [
    "print(\"keys of iris_dataset: \\n{}\".format(iris_dataset.keys()))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "8518a322",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Target names: ['setosa' 'versicolor' 'virginica']\n"
     ]
    }
   ],
   "source": [
    "print(\"Target names: {}\".format(iris_dataset['target_names']))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "8e0da7f8",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Feature names: \n",
      "['sepal length (cm)', 'sepal width (cm)', 'petal length (cm)', 'petal width (cm)']\n"
     ]
    }
   ],
   "source": [
    "print(\"Feature names: \\n{}\".format(iris_dataset['feature_names']))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "e9d52b69",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Type of data: <class 'numpy.ndarray'>\n"
     ]
    }
   ],
   "source": [
    "print(\"Type of data: {}\".format(type(iris_dataset['data'])))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "4c45a42f",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "shape od data :(150, 4)\n"
     ]
    }
   ],
   "source": [
    "print(\"shape od data :{}\".format(iris_dataset['data'].shape))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "54003dd8",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "first five columns of data: <class 'numpy.ndarray'>\n"
     ]
    }
   ],
   "source": [
    "print(\"first five columns of data: {}\".format(type(iris_dataset['target'])))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "3b329852",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "shape of target: (150,)\n"
     ]
    }
   ],
   "source": [
    "print(\"shape of target: {}\".format(iris_dataset['target'].shape))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "522af113",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "target:\n",
      "[0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0\n",
      " 0 0 0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1\n",
      " 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 2 2 2 2 2 2 2 2 2 2\n",
      " 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2\n",
      " 2 2]\n"
     ]
    }
   ],
   "source": [
    "print(\"target:\\n{}\".format(iris_dataset['target']))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "7097abc4",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "X_train, X_test, y_train, y_test = train_test_split(iris_dataset['data'], iris_dataset['target'], random_state=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "bbe14a37",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "X_train shape: (112, 4)\n",
      "y_train shape: (112,)\n"
     ]
    }
   ],
   "source": [
    "print(\"X_train shape: {}\".format(X_train.shape))\n",
    "print(\"y_train shape: {}\".format(y_train.shape))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "eae21ae1",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "X_test shape: (38, 4)\n",
      "y_test shape: (38,)\n"
     ]
    }
   ],
   "source": [
    "print(\"X_test shape: {}\".format(X_test.shape))\n",
    "print(\"y_test shape: {}\".format(y_test.shape))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "15befa40",
   "metadata": {},
   "outputs": [
    {
     "ename": "NameError",
     "evalue": "name 'mglearn' is not defined",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mNameError\u001b[0m                                 Traceback (most recent call last)",
      "Input \u001b[1;32mIn [17]\u001b[0m, in \u001b[0;36m<cell line: 7>\u001b[1;34m()\u001b[0m\n\u001b[0;32m      4\u001b[0m \u001b[38;5;66;03m# crate a scatter matrix from the dataframe, colour by y_train\u001b[39;00m\n\u001b[0;32m      5\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mpandas\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mplotting\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m scatter_matrix\n\u001b[1;32m----> 7\u001b[0m grr \u001b[38;5;241m=\u001b[39m pd\u001b[38;5;241m.\u001b[39mplotting\u001b[38;5;241m.\u001b[39mscatter_matrix(iris_dataframe, c\u001b[38;5;241m=\u001b[39my_train, fidsize\u001b[38;5;241m=\u001b[39m(\u001b[38;5;241m15\u001b[39m,\u001b[38;5;241m15\u001b[39m), marker\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m0\u001b[39m\u001b[38;5;124m'\u001b[39m, hist_kwds\u001b[38;5;241m=\u001b[39m{\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mbins\u001b[39m\u001b[38;5;124m'\u001b[39m: \u001b[38;5;241m20\u001b[39m}, s\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m60\u001b[39m, alpha\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m.8\u001b[39m, cmap\u001b[38;5;241m=\u001b[39m\u001b[43mmglearn\u001b[49m\u001b[38;5;241m.\u001b[39mcm3)\n",
      "\u001b[1;31mNameError\u001b[0m: name 'mglearn' is not defined"
     ]
    }
   ],
   "source": [
    "# crate dataframe from dataa in X_train\n",
    "# label the column using the string in iris_dataset.feature_names\n",
    "iris_dataframe = pd.DataFrame(X_train, columns=iris_dataset.feature_names)\n",
    "# crate a scatter matrix from the dataframe, colour by y_train\n",
    "from pandas.plotting import scatter_matrix\n",
    "\n",
    "grr = pd.plotting.scatter_matrix(iris_dataframe, c=y_train, fidsize=(15,15), marker='0', hist_kwds={'bins': 20}, s=60, alpha=.8, cmap=mglearn.cm3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "48bc00f4",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "knn = KNeighborsClassifier(n_neighbors=1)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "8ecb5cac",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "KNeighborsClassifier(n_neighbors=1)"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "knn.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "fb9cac19",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "X_new.shape: (1, 4)\n"
     ]
    }
   ],
   "source": [
    "X_new = np.array([[5, 2.9, 1, 0.2]])\n",
    "print(\"X_new.shape: {}\".format(X_new.shape))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "243200b6",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Prediction: [0]\n",
      "Predicted target name: ['setosa']\n"
     ]
    }
   ],
   "source": [
    "prediction = knn.predict(X_new)\n",
    "print(\"Prediction: {}\".format(prediction))\n",
    "print(\"Predicted target name: {}\".format(iris_dataset['target_names'][prediction]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "d29ba99e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "test set predictions:\n",
      " [2 1 0 2 0 2 0 1 1 1 2 1 1 1 1 0 1 1 0 0 2 1 0 0 2 0 0 1 1 0 2 1 0 2 2 1 0\n",
      " 2]\n"
     ]
    }
   ],
   "source": [
    "y_pred = knn.predict(X_test)\n",
    "print(\"test set predictions:\\n {}\".format(y_pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "a8d661b6",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "test set score: 0.9736842105263158\n"
     ]
    }
   ],
   "source": [
    "print(\"test set score: {}\".format(np.mean(y_pred == y_test)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "7a4722e7",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "test set score: 0.9736842105263158\n"
     ]
    }
   ],
   "source": [
    "print(\"test set score: {}\".format(knn.score(X_test, y_test)))"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.9.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}