Flower Species Classification.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Iris.ipynb",
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "code",
      "metadata": {
        "id": "131C5y2bGQV1"
      },
      "source": [
        "# Importing Libraries\n",
        "import numpy as np\n",
        "import pandas as pd\n",
        "from sklearn.preprocessing import LabelEncoder\n",
        "from sklearn.impute import SimpleImputer\n",
        "from sklearn.linear_model import LogisticRegression\n",
        "from sklearn.tree import DecisionTreeClassifier\n",
        "from sklearn.model_selection import train_test_split\n",
        "from sklearn.metrics import accuracy_score,confusion_matrix\n",
        "\n"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "8bz_DoK-HlZ6"
      },
      "source": [
        "# Importing Dataset\n",
        "#iris = datasets.load_iris()\n",
        "data = pd.read_csv(\"/content/Iris.csv\")   "
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ZJEIdP3TiCeU",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "d8590878-81a3-4c3a-e7c0-606b750203d1"
      },
      "source": [
        "# Display size of dataset\n",
        "data.shape"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(150, 6)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 82
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "BOHsmkPdIU5N",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "outputId": "4519fae2-955f-4c47-9141-96c95a7f756d"
      },
      "source": [
        "# Display top rows\n",
        "data.head()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>Id</th>\n",
              "      <th>SepalLengthCm</th>\n",
              "      <th>SepalWidthCm</th>\n",
              "      <th>PetalLengthCm</th>\n",
              "      <th>PetalWidthCm</th>\n",
              "      <th>Species</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>1</td>\n",
              "      <td>NaN</td>\n",
              "      <td>3.5</td>\n",
              "      <td>1.4</td>\n",
              "      <td>0.2</td>\n",
              "      <td>Iris-setosa</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>2</td>\n",
              "      <td>4.9</td>\n",
              "      <td>3.0</td>\n",
              "      <td>1.4</td>\n",
              "      <td>0.2</td>\n",
              "      <td>Iris-setosa</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>3</td>\n",
              "      <td>4.7</td>\n",
              "      <td>3.2</td>\n",
              "      <td>1.3</td>\n",
              "      <td>0.2</td>\n",
              "      <td>Iris-setosa</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>4</td>\n",
              "      <td>4.6</td>\n",
              "      <td>3.1</td>\n",
              "      <td>1.5</td>\n",
              "      <td>0.2</td>\n",
              "      <td>Iris-setosa</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>5</td>\n",
              "      <td>5.0</td>\n",
              "      <td>3.6</td>\n",
              "      <td>1.4</td>\n",
              "      <td>0.2</td>\n",
              "      <td>Iris-setosa</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "   Id  SepalLengthCm  SepalWidthCm  PetalLengthCm  PetalWidthCm      Species\n",
              "0   1            NaN           3.5            1.4           0.2  Iris-setosa\n",
              "1   2            4.9           3.0            1.4           0.2  Iris-setosa\n",
              "2   3            4.7           3.2            1.3           0.2  Iris-setosa\n",
              "3   4            4.6           3.1            1.5           0.2  Iris-setosa\n",
              "4   5            5.0           3.6            1.4           0.2  Iris-setosa"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 83
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ir14bfj-JKn0",
        "outputId": "f84d89a4-3c2b-4f2d-9bae-01d9ca9669f2"
      },
      "source": [
        "#Finding the missing values\n",
        "data.isnull().sum()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Id               0\n",
              "SepalLengthCm    1\n",
              "SepalWidthCm     0\n",
              "PetalLengthCm    0\n",
              "PetalWidthCm     0\n",
              "Species          0\n",
              "dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 84
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "N3DrxNYUJz5i",
        "outputId": "45c88f4a-93b8-4c74-8f27-6a346abf6e78"
      },
      "source": [
        "#drop miss val\n",
        "data.dropna(inplace=True)\n",
        "data.isnull().sum()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Id               0\n",
              "SepalLengthCm    0\n",
              "SepalWidthCm     0\n",
              "PetalLengthCm    0\n",
              "PetalWidthCm     0\n",
              "Species          0\n",
              "dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 85
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "QRrr01EIPAWB"
      },
      "source": [
        "data.head()"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "pE_DQLUmAxFw"
      },
      "source": [
        "# Encoding the data\n",
        "lbl = LabelEncoder()\n",
        "data[\"Species\"] =lbl.fit_transform(data[\"Species\"])"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "rCnEr0yVAzIa",
        "outputId": "ea4ef3b7-17b2-42a3-dbae-2118a5f87ede"
      },
      "source": [
        "data.head()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>Id</th>\n",
              "      <th>SepalLengthCm</th>\n",
              "      <th>SepalWidthCm</th>\n",
              "      <th>PetalLengthCm</th>\n",
              "      <th>PetalWidthCm</th>\n",
              "      <th>Species</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>2</td>\n",
              "      <td>4.9</td>\n",
              "      <td>3.0</td>\n",
              "      <td>1.4</td>\n",
              "      <td>0.2</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>3</td>\n",
              "      <td>4.7</td>\n",
              "      <td>3.2</td>\n",
              "      <td>1.3</td>\n",
              "      <td>0.2</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>4</td>\n",
              "      <td>4.6</td>\n",
              "      <td>3.1</td>\n",
              "      <td>1.5</td>\n",
              "      <td>0.2</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>5</td>\n",
              "      <td>5.0</td>\n",
              "      <td>3.6</td>\n",
              "      <td>1.4</td>\n",
              "      <td>0.2</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>5</th>\n",
              "      <td>6</td>\n",
              "      <td>5.4</td>\n",
              "      <td>3.9</td>\n",
              "      <td>1.7</td>\n",
              "      <td>0.4</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "   Id  SepalLengthCm  SepalWidthCm  PetalLengthCm  PetalWidthCm  Species\n",
              "1   2            4.9           3.0            1.4           0.2        0\n",
              "2   3            4.7           3.2            1.3           0.2        0\n",
              "3   4            4.6           3.1            1.5           0.2        0\n",
              "4   5            5.0           3.6            1.4           0.2        0\n",
              "5   6            5.4           3.9            1.7           0.4        0"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 87
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "tHi7CjdCF7Pk"
      },
      "source": [
        "# Identify Dependent and Independent variable\n",
        "x = data.iloc[:,1:5].values\n",
        "y = data.iloc[:,-1].values"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "SD6-bYEnC2l0"
      },
      "source": [
        "# Another strategy for handling missing val\n",
        "imputer = SimpleImputer(missing_values = np.nan , strategy = 'mean',)\n",
        "imputer = imputer.fit(x[:,:])\n",
        "x[:,:] = imputer.transform(x[:,:])"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "xu3Zbp-fGszx"
      },
      "source": [
        "x[0]"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "TCmQWuUVLrOY"
      },
      "source": [
        "# split dataset into train and test\n",
        "x_train,x_test,y_train,y_test = train_test_split(x,y,test_size=0.3, random_state=32)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "bXI2J31JRj9E"
      },
      "source": [
        "# Intializing the algorithm\n",
        "cls = DecisionTreeClassifier()\n",
        "#cls = LogisticRegression()"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "LjTD0nX9R28H"
      },
      "source": [
        "# Training of Algorithm\n",
        "cls = cls.fit(x_train,y_train)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "uCmFwXvVSA6D"
      },
      "source": [
        "# testing of result\n",
        "y_pred = cls.predict(x_test)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Na8PdVDpSaCr",
        "outputId": "dc2ca6bc-1401-4775-be04-b44fb38edffb"
      },
      "source": [
        "# Print val\n",
        "y_pred"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([1, 0, 0, 1, 2, 2, 0, 0, 1, 0, 2, 2, 1, 1, 2, 2, 1, 2, 2, 0, 0, 2,\n",
              "       2, 0, 0, 1, 0, 2, 0, 0, 1, 0, 0, 2, 1, 0, 0, 2, 2, 1, 0, 2, 0, 2,\n",
              "       0])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 93
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "dMaGjfk0SdEW",
        "outputId": "61909bb9-8636-42d6-ed99-6aab26699304"
      },
      "source": [
        "# print actual values\n",
        "y_test"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([1, 0, 0, 1, 2, 2, 0, 0, 1, 0, 1, 2, 1, 1, 2, 2, 1, 2, 1, 0, 0, 2,\n",
              "       2, 0, 0, 1, 0, 2, 0, 0, 1, 0, 0, 2, 1, 0, 0, 2, 2, 1, 0, 2, 0, 2,\n",
              "       0])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 94
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "J9hbEuJFds4-",
        "outputId": "76f3832c-3698-41fe-a3bd-18c45c72477c"
      },
      "source": [
        "# Performance Evaluation\n",
        "confusion_matrix(y_test, y_pred)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[19,  0,  0],\n",
              "       [ 0, 10,  2],\n",
              "       [ 0,  0, 14]])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 95
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "PV4M-TtYUGq-",
        "outputId": "15b58eab-40c3-4b01-807f-4fc09b3610ae"
      },
      "source": [
        "# Performance Evaluation\n",
        "print(\"Accuracy:\",accuracy_score(y_test, y_pred))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Accuracy: 0.9555555555555556\n"
          ],
          "name": "stdout"
        }
      ]
    }
  ]
}