Classification_Task3_200100173.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "7C5rAxwPGDQf"
   },
   "source": [
    "# Importing useful libraries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "id": "8qvrslgsF4Mn"
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd \n",
    "from pandas import Series, DataFrame\n",
    "import sklearn\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "6aYOLI2BHF6m"
   },
   "source": [
    "## Loading the dataset.\n",
    "The dataset can be found [here](https://github.com/shreedharmalpani/Intro-To-ML-Hello-FOSS/blob/main/iris.csv)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {
    "id": "_hccks2pF4Mq"
   },
   "outputs": [],
   "source": [
    "df = pd.read_csv(\"iris.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {
    "id": "um0L09IOF4Ms"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>sepal_length</th>\n",
       "      <th>sepal_width</th>\n",
       "      <th>petal_length</th>\n",
       "      <th>petal_width</th>\n",
       "      <th>species</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>5.1</td>\n",
       "      <td>3.5</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "      <td>setosa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4.9</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "      <td>setosa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>4.7</td>\n",
       "      <td>3.2</td>\n",
       "      <td>1.3</td>\n",
       "      <td>0.2</td>\n",
       "      <td>setosa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4.6</td>\n",
       "      <td>3.1</td>\n",
       "      <td>1.5</td>\n",
       "      <td>0.2</td>\n",
       "      <td>setosa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5.0</td>\n",
       "      <td>3.6</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "      <td>setosa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>145</th>\n",
       "      <td>6.7</td>\n",
       "      <td>3.0</td>\n",
       "      <td>5.2</td>\n",
       "      <td>2.3</td>\n",
       "      <td>virginica</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>146</th>\n",
       "      <td>6.3</td>\n",
       "      <td>2.5</td>\n",
       "      <td>5.0</td>\n",
       "      <td>1.9</td>\n",
       "      <td>virginica</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>147</th>\n",
       "      <td>6.5</td>\n",
       "      <td>3.0</td>\n",
       "      <td>5.2</td>\n",
       "      <td>2.0</td>\n",
       "      <td>virginica</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>148</th>\n",
       "      <td>6.2</td>\n",
       "      <td>3.4</td>\n",
       "      <td>5.4</td>\n",
       "      <td>2.3</td>\n",
       "      <td>virginica</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>149</th>\n",
       "      <td>5.9</td>\n",
       "      <td>3.0</td>\n",
       "      <td>5.1</td>\n",
       "      <td>1.8</td>\n",
       "      <td>virginica</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>150 rows × 5 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     sepal_length  sepal_width  petal_length  petal_width    species\n",
       "0             5.1          3.5           1.4          0.2     setosa\n",
       "1             4.9          3.0           1.4          0.2     setosa\n",
       "2             4.7          3.2           1.3          0.2     setosa\n",
       "3             4.6          3.1           1.5          0.2     setosa\n",
       "4             5.0          3.6           1.4          0.2     setosa\n",
       "..            ...          ...           ...          ...        ...\n",
       "145           6.7          3.0           5.2          2.3  virginica\n",
       "146           6.3          2.5           5.0          1.9  virginica\n",
       "147           6.5          3.0           5.2          2.0  virginica\n",
       "148           6.2          3.4           5.4          2.3  virginica\n",
       "149           5.9          3.0           5.1          1.8  virginica\n",
       "\n",
       "[150 rows x 5 columns]"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "id": "cbx8gP4zF4Mt"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 150 entries, 0 to 149\n",
      "Data columns (total 5 columns):\n",
      " #   Column        Non-Null Count  Dtype  \n",
      "---  ------        --------------  -----  \n",
      " 0   sepal_length  150 non-null    float64\n",
      " 1   sepal_width   150 non-null    float64\n",
      " 2   petal_length  150 non-null    float64\n",
      " 3   petal_width   150 non-null    float64\n",
      " 4   species       150 non-null    object \n",
      "dtypes: float64(4), object(1)\n",
      "memory usage: 6.0+ KB\n"
     ]
    }
   ],
   "source": [
    "df.info() "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "vjH1pAqoJna2"
   },
   "source": [
    "# Data Cleaning & Data Visualization"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "PNfSyZF1F4Mu"
   },
   "source": [
    "### 1) Remove unneeded columns\n",
    "### 2) Check for duplicate rows \n",
    "### 2) Check for rows with missing values\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {
    "id": "HKFsVhubF4Mx"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>sepal_length</th>\n",
       "      <th>sepal_width</th>\n",
       "      <th>petal_length</th>\n",
       "      <th>petal_width</th>\n",
       "      <th>species</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>5.1</td>\n",
       "      <td>3.5</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "      <td>setosa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4.9</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "      <td>setosa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>4.7</td>\n",
       "      <td>3.2</td>\n",
       "      <td>1.3</td>\n",
       "      <td>0.2</td>\n",
       "      <td>setosa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4.6</td>\n",
       "      <td>3.1</td>\n",
       "      <td>1.5</td>\n",
       "      <td>0.2</td>\n",
       "      <td>setosa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5.0</td>\n",
       "      <td>3.6</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "      <td>setosa</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   sepal_length  sepal_width  petal_length  petal_width species\n",
       "0           5.1          3.5           1.4          0.2  setosa\n",
       "1           4.9          3.0           1.4          0.2  setosa\n",
       "2           4.7          3.2           1.3          0.2  setosa\n",
       "3           4.6          3.1           1.5          0.2  setosa\n",
       "4           5.0          3.6           1.4          0.2  setosa"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#code\n",
    "df.isna().sum() # found no missing entry\n",
    "df = df.dropna(how = \"any\", axis=0)\n",
    "df = df.drop_duplicates(keep = 'first')\n",
    "df = df.reset_index(drop = True)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "L1cnZS5XF4M2"
   },
   "source": [
    "### EDA (Exploratory Data Analysis) with Iris"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {
    "id": "DjsnhAraF4M7",
    "outputId": "d8d58921-fa2f-4d75-c884-268986342894"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x504 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "##Displaying a scatter plot to show the distribution of Pepal Length vs width the dataset\n",
    "\n",
    "fig = df[df.species == 'setosa'].plot(kind='scatter', x='petal_length', y='petal_width', color='orange', label='Setosa')\n",
    "df[df.species == 'versicolor'].plot(kind='scatter', x='petal_length', y='petal_width', color='blue', label='Versicolor', ax=fig)\n",
    "df[df.species == 'virginica'].plot(kind='scatter', x='petal_length', y='petal_width', color='green', label='Virginica', ax=fig)\n",
    "\n",
    "fig.set_xlabel('Petal Length')\n",
    "fig.set_ylabel('Petal Width')\n",
    "fig.set_title('Petal Length and Width comparison')\n",
    "\n",
    "fig=plt.gcf()\n",
    "fig.set_size_inches(10, 7)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "id": "O_eYByFvF4M5",
    "outputId": "b7404bc7-4879-482e-ca9d-8d9680a8f6a7"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x504 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "#Display a scatter plot to show the distribution of Sepal Length vs width the dataset (Like previous Petal lenght vs width scatter plot)\n",
    "\n",
    "\n",
    "#code\n",
    "\n",
    "fig = df[df.species == 'setosa'].plot(kind='scatter', x='sepal_length', y='sepal_width', color='orange', label='Setosa')\n",
    "df[df.species == 'versicolor'].plot(kind='scatter', x='sepal_length', y='sepal_width', color='blue', label='Versicolor', ax=fig)\n",
    "df[df.species == 'virginica'].plot(kind='scatter', x='sepal_length', y='sepal_width', color='green', label='Virginica', ax=fig)\n",
    "\n",
    "fig.set_xlabel('Sepal Length')\n",
    "fig.set_ylabel('Sepal Width')\n",
    "fig.set_title('Sepal Length and Width comparison')\n",
    "\n",
    "fig=plt.gcf()\n",
    "fig.set_size_inches(10, 7)\n",
    "plt.show()\n",
    "#example plot"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {
    "id": "EIh_yKQAF4M6",
    "outputId": "91706df0-4dd1-4a8b-92e7-41e04e6e602d"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<seaborn.axisgrid.FacetGrid at 0x253d7432fd0>"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 300.75x216 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 300.75x216 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "#plot the FacetGrid plot using the seaborn library\n",
    "plot_s = sns.FacetGrid(df, hue='species') \n",
    "plot_s.map_dataframe(sns.scatterplot, x=\"sepal_length\", y=\"sepal_width\")\n",
    "plot_s.add_legend() \n",
    "\n",
    "plot_p = sns.FacetGrid(df, hue='species')  \n",
    "plot_p.map_dataframe(sns.scatterplot, x=\"petal_length\", y=\"petal_width\") \n",
    "plot_p.add_legend()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {
    "id": "yadZQxoKF4M8",
    "outputId": "639d4b96-87a7-45d0-f358-ef061d08d230"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "#Plot the distritbution of the features using histgram\n",
    "columns=df.columns\n",
    "for column in columns:\n",
    "    if column!='species':\n",
    "        df.hist(column)\n",
    "    "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "xb-AFaG3PU0D"
   },
   "source": [
    "## Importing alll the necessary packages to use the various classification algorithms\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {
    "id": "cJVjbgAjF4M_"
   },
   "outputs": [],
   "source": [
    "from sklearn.linear_model import LogisticRegression # for Logistic Regression Algorithm\n",
    "from sklearn.model_selection import train_test_split # to split the dataset for training and testing \n",
    "from sklearn import svm # for suport vector machine algorithm\n",
    "from sklearn import metrics # for checking the model accuracy\n",
    "from sklearn.tree import DecisionTreeClassifier # for using DTA\n",
    "from sklearn import preprocessing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {
    "id": "8LizCSuWF4NA"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(147, 5)"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "WW5Hp1fFF4NC"
   },
   "source": [
    "Now, when we train any algorithm, the number of features and their correlation plays an important role. If there are features and many of the features are highly correlated, then training an algorithm with all the featues will reduce the accuracy. Thus features selection should be done carefully. This dataset has less featues but still we will see the correlation.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {
    "id": "YABeXMklF4ND",
    "outputId": "a212e140-712f-4e6f-f8f4-b6664bf29ff1"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(8,4))\n",
    "sns.heatmap(df.corr(), annot=True, cmap='cubehelix_r') # draws heatmap with input as correlation matrix calculated by df.corr() \n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "gsd6QaoaF4NE"
   },
   "source": [
    "Observation--->\n",
    "The Sepal Width and Length are not correlated The Petal Width and Length are highly correlated\n",
    "We will use all the features for training the algorithm and check the accuracy.\n",
    "\n",
    "Then we will use 1 Petal Feature and 1 Sepal Feature to check the accuracy of the algorithm as we are using only 2 features that are not correlated. Thus we can have a variance in the dataset which may help in better accuracy. We will check it later.\n",
    "\n",
    "Steps To Be followed When Applying an Algorithm\n",
    "\n",
    "Split the dataset into training and testing dataset. The testing dataset is generally smaller than training one as it will help in training the model better.\n",
    "\n",
    "Select any algorithm based on the problem (classification or regression) whatever you feel may be good.\n",
    "Then pass the training dataset to the algorithm to train it. We use the .fit() method\n",
    "Then pass the testing data to the trained algorithm to predict the outcome. We use the .predict() method.\n",
    "We then check the accuracy by passing the predicted outcome and the actual output to the model."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "QAD_cNirF4NF"
   },
   "source": [
    "# Splitting The Data into Training And Testing Dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(102, 5)\n",
      "(45, 5)\n"
     ]
    }
   ],
   "source": [
    "train, test = train_test_split(df, test_size=0.3) # our main data split into train and test\n",
    "# the attribute test_size=0.3 splits the data into 70% and 30% ratio. train=70% and test=30%\n",
    "print(train.shape)\n",
    "print(test.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {
    "id": "yO2J2FpjF4NG"
   },
   "outputs": [],
   "source": [
    "train_X = train[['sepal_length','sepal_width','petal_length','petal_width']] # taking the training data features\n",
    "train_y = train.species # output of the training data\n",
    "\n",
    "test_X = test[['sepal_length','sepal_width','petal_length','petal_width']] # taking test data feature\n",
    "test_y = test.species # output value of the test data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {
    "id": "yR9D2qgQF4NG"
   },
   "outputs": [],
   "source": [
    "scaler = preprocessing.StandardScaler().fit(train_X)\n",
    "train_X_copy = scaler.transform(train_X)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {
    "id": "KcGbNGkcF4NH"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>sepal_length</th>\n",
       "      <th>sepal_width</th>\n",
       "      <th>petal_length</th>\n",
       "      <th>petal_width</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>135</th>\n",
       "      <td>6.4</td>\n",
       "      <td>3.1</td>\n",
       "      <td>5.5</td>\n",
       "      <td>1.8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>4.3</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.1</td>\n",
       "      <td>0.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>4.6</td>\n",
       "      <td>3.4</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50</th>\n",
       "      <td>6.9</td>\n",
       "      <td>3.1</td>\n",
       "      <td>4.9</td>\n",
       "      <td>1.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>45</th>\n",
       "      <td>4.6</td>\n",
       "      <td>3.2</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     sepal_length  sepal_width  petal_length  petal_width\n",
       "135           6.4          3.1           5.5          1.8\n",
       "13            4.3          3.0           1.1          0.1\n",
       "6             4.6          3.4           1.4          0.3\n",
       "50            6.9          3.1           4.9          1.5\n",
       "45            4.6          3.2           1.4          0.2"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "scaler = preprocessing.StandardScaler().fit(test_X)\n",
    "test_X_copy = scaler.transform(test_X)\n",
    "test_X.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {
    "id": "5sFmts-IF4NI"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "69     versicolor\n",
       "35         setosa\n",
       "96     versicolor\n",
       "49     versicolor\n",
       "105     virginica\n",
       "Name: species, dtype: object"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train_y.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "S_w4Me2bF4NL"
   },
   "source": [
    "## Logistic Regression "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {
    "id": "gOQ5JrqrF4NL"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The accuracy of Logistic Regression is:  0.8\n"
     ]
    }
   ],
   "source": [
    "model_1 = LogisticRegression(random_state=0)\n",
    "model_1.fit(train_X_copy, train_y)\n",
    "prediction_lr = model_1.predict(test_X_copy)\n",
    "print('The accuracy of Logistic Regression is: ', metrics.accuracy_score(prediction_lr, test_y))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "e1NNX-EGF4NJ"
   },
   "source": [
    "## Support Vector Machine SVM"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {
    "id": "zSJmVzqnF4NK"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The accuracy of Support Vector Machine is:  0.9333333333333333\n"
     ]
    }
   ],
   "source": [
    "#implement using Support Vector Machine (SVM)\n",
    "#code\n",
    "model_2 = svm.SVC(kernel='rbf')\n",
    "model_2.fit(train_X, train_y)\n",
    "prediction_SVM = model_2.predict(test_X)\n",
    "print('The accuracy of Support Vector Machine is: ', metrics.accuracy_score(prediction_SVM, test_y))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "GWfemKzPF4NN"
   },
   "source": [
    "## Decision Tree"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {
    "id": "iRXy3EZIF4NN",
    "outputId": "f470e075-fc92-4f3f-c343-7a8257e2c5d2"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The accuracy of Decision Tree is:  0.8444444444444444\n"
     ]
    }
   ],
   "source": [
    "#implementing using Decision Tree\n",
    "#code\n",
    "model_3 = DecisionTreeClassifier(random_state=0)\n",
    "model_3.fit(train_X, train_y)\n",
    "prediction_DT = model_3.predict(test_X)\n",
    "\n",
    "print('The accuracy of Decision Tree is: ', metrics.accuracy_score(prediction_DT, test_y))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "uB2Co6f_F4NQ"
   },
   "source": [
    "### We used all the features of iris in above models. Now we will use Petals and Sepals Seperately"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "1_v6cAZMF4NQ"
   },
   "source": [
    "### Creating Petals And Sepals Training Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {
    "id": "e1Q-1b9YF4NQ"
   },
   "outputs": [],
   "source": [
    "petal = df[['petal_length','petal_width','species']]\n",
    "sepal = df[['sepal_length','sepal_width','species']]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "Lv-nab5oF4NQ"
   },
   "source": [
    "### For Iris Petal"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {
    "id": "DuOqLUWZF4NQ"
   },
   "outputs": [],
   "source": [
    "train_p,test_p = train_test_split(petal, test_size=0.3, random_state=0) #petals\n",
    "train_x_p = train_p[['petal_length','petal_width']] \n",
    "train_y_p = train_p.species  \n",
    "\n",
    "test_x_p = test_p[['petal_length','petal_width']]\n",
    "test_y_p = test_p.species   "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "bgNB8kaNF4NU"
   },
   "source": [
    "### For Iris Sepal"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {
    "id": "6hVj5MW3F4NU"
   },
   "outputs": [],
   "source": [
    "#Similarly define the split for sepals\n",
    "#define the training and test data's Sepal features followed by the output of the training and test data\n",
    "train_s,test_s = train_test_split(sepal, test_size=0.3, random_state=0)\n",
    "train_x_s = train_s[['sepal_length','sepal_width']]  \n",
    "train_y_s = train_s.species \n",
    "test_x_s = test_s[['sepal_length','sepal_width']]  \n",
    "test_y_s = test_s.species  \n",
    "#code"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "y08e1O6aU9mx"
   },
   "source": [
    "Implementing the algorithms just like we did on the complete dataset but separately on sepals and petals and calculating accuracy"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "TeMWnQr6F4NV"
   },
   "source": [
    "## SVM Algorithm"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {
    "id": "jhlutJ78F4NV"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The accuracy of the SVM using Petals is: 1.0\n",
      "The accuracy of the SVM using Sepals is: 0.8\n"
     ]
    }
   ],
   "source": [
    "model_pl_SVM = svm.SVC(kernel='rbf')\n",
    "model_pl_SVM.fit(train_x_p, train_y_p)\n",
    "prediction_SVM_pl = model_pl_SVM.predict(test_x_p)\n",
    "print('The accuracy of the SVM using Petals is:',metrics.accuracy_score(prediction_SVM_pl,test_y_p))\n",
    "\n",
    "model_sl_SVM = svm.SVC(kernel='rbf')\n",
    "model_sl_SVM.fit(train_x_s, train_y_s)\n",
    "prediction_SVM_sl = model_sl_SVM.predict(test_x_s)\n",
    "print('The accuracy of the SVM using Sepals is:',metrics.accuracy_score(prediction_SVM_sl,test_y_s))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "Mli7zcq_F4NV"
   },
   "source": [
    "## Logistic Regression"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {
    "id": "2DqK_dFCF4NV"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The accuracy of the Logistic Regression using Petals is: 1.0\n",
      "The accuracy of the Logistic Regression using Sepals is: 0.7777777777777778\n"
     ]
    }
   ],
   "source": [
    "model_pl_LR = LogisticRegression()\n",
    "model_pl_LR.fit(train_x_p, train_y_p)\n",
    "prediction_LR_pl = model_pl_LR.predict(test_x_p)\n",
    "print('The accuracy of the Logistic Regression using Petals is:',metrics.accuracy_score(prediction_LR_pl,test_y_p))\n",
    "\n",
    "model_sl_LR = LogisticRegression()\n",
    "model_sl_LR.fit(train_x_s, train_y_s)\n",
    "prediction_LR_sl = model_sl_LR.predict(test_x_s)\n",
    "print('The accuracy of the Logistic Regression using Sepals is:',metrics.accuracy_score(prediction_LR_sl,test_y_s))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "aM-7Zx95F4NW"
   },
   "source": [
    "## Decision Tree"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {
    "id": "S8tXp-gMF4NW"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The accuracy of the Decision Tree using Petals is: 1.0\n",
      "The accuracy of the Decision Tree using Sepals is: 0.7111111111111111\n"
     ]
    }
   ],
   "source": [
    "model_pl_DT = DecisionTreeClassifier(random_state=0)\n",
    "model_pl_DT.fit(train_x_p, train_y_p)\n",
    "prediction_DT_pl = model_pl_DT.predict(test_x_p)\n",
    "print('The accuracy of the Decision Tree using Petals is:',metrics.accuracy_score(prediction_DT_pl,test_y_p))\n",
    "\n",
    "model_sl_DT = DecisionTreeClassifier(random_state=0)\n",
    "model_sl_DT.fit(train_x_s, train_y_s)\n",
    "prediction_DT_sl = model_sl_DT.predict(test_x_s)\n",
    "print('The accuracy of the Decision Tree using Sepals is:',metrics.accuracy_score(prediction_DT_sl,test_y_s))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "6ec0NUyJF4NW"
   },
   "source": [
    "\n",
    "\n",
    "\n",
    "### Question:\n",
    "Does Using Petals over Sepals for training the data give a much better accuracy? Why?\n",
    "Ans: Yes, petals data have given much better accuracy becuase as we can see that petals data is much correlated as compared to sepals data is hence it helps our machine learning model to easily identify patterns in training set which may occur and help our ml model to deal easliy with new data since."
   ]
  }
 ],
 "metadata": {
  "colab": {
   "name": "Classification_Task3.ipynb",
   "provenance": []
  },
  "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": "3.8.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}