model_train (gboost).ipynb

{
  "nbformat": 4,
  "nbformat_minor": 5,
  "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": "3.7.9"
    },
    "colab": {
      "name": "model_train (gboost).ipynb",
      "provenance": [],
      "include_colab_link": true
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/OvinduWijethunge/Next-Day-Rain-Predicts-In-Australia/blob/master/model_train%20(gboost).ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "8fa44372"
      },
      "source": [
        "# Here I choose Gradient Boosting model as my ML model. i prefer to go with it. \n",
        "# i do not try multiple models here."
      ],
      "id": "8fa44372",
      "execution_count": 1,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "8OQ6zjpIN31k",
        "outputId": "55e5bcb9-de28-430e-df58-2a4b183fa6d7",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "source": [
        "!nvidia-smi"
      ],
      "id": "8OQ6zjpIN31k",
      "execution_count": 24,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Fri Jun  4 04:20:15 2021       \n",
            "+-----------------------------------------------------------------------------+\n",
            "| NVIDIA-SMI 465.27       Driver Version: 460.32.03    CUDA Version: 11.2     |\n",
            "|-------------------------------+----------------------+----------------------+\n",
            "| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |\n",
            "| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |\n",
            "|                               |                      |               MIG M. |\n",
            "|===============================+======================+======================|\n",
            "|   0  Tesla T4            Off  | 00000000:00:04.0 Off |                    0 |\n",
            "| N/A   39C    P8     9W /  70W |      0MiB / 15109MiB |      0%      Default |\n",
            "|                               |                      |                  N/A |\n",
            "+-------------------------------+----------------------+----------------------+\n",
            "                                                                               \n",
            "+-----------------------------------------------------------------------------+\n",
            "| Processes:                                                                  |\n",
            "|  GPU   GI   CI        PID   Type   Process name                  GPU Memory |\n",
            "|        ID   ID                                                   Usage      |\n",
            "|=============================================================================|\n",
            "|  No running processes found                                                 |\n",
            "+-----------------------------------------------------------------------------+\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "K5v0DJrEN3qE",
        "outputId": "bfe99892-db3c-4075-f552-ba1e62c55f6c",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "source": [
        "!pip install tensorflow-gpu"
      ],
      "id": "K5v0DJrEN3qE",
      "execution_count": 2,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Collecting tensorflow-gpu\n",
            "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/1d/a2/5ccf0a418eb22e0a2ae9edc1e7f5456d0a4b8b49524572897564b4030a9b/tensorflow_gpu-2.5.0-cp37-cp37m-manylinux2010_x86_64.whl (454.3MB)\n",
            "\u001b[K     |████████████████████████████████| 454.3MB 37kB/s \n",
            "\u001b[?25hRequirement already satisfied: astunparse~=1.6.3 in /usr/local/lib/python3.7/dist-packages (from tensorflow-gpu) (1.6.3)\n",
            "Requirement already satisfied: google-pasta~=0.2 in /usr/local/lib/python3.7/dist-packages (from tensorflow-gpu) (0.2.0)\n",
            "Requirement already satisfied: numpy~=1.19.2 in /usr/local/lib/python3.7/dist-packages (from tensorflow-gpu) (1.19.5)\n",
            "Requirement already satisfied: wrapt~=1.12.1 in /usr/local/lib/python3.7/dist-packages (from tensorflow-gpu) (1.12.1)\n",
            "Requirement already satisfied: keras-preprocessing~=1.1.2 in /usr/local/lib/python3.7/dist-packages (from tensorflow-gpu) (1.1.2)\n",
            "Requirement already satisfied: six~=1.15.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow-gpu) (1.15.0)\n",
            "Requirement already satisfied: h5py~=3.1.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow-gpu) (3.1.0)\n",
            "Requirement already satisfied: absl-py~=0.10 in /usr/local/lib/python3.7/dist-packages (from tensorflow-gpu) (0.12.0)\n",
            "Requirement already satisfied: opt-einsum~=3.3.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow-gpu) (3.3.0)\n",
            "Requirement already satisfied: flatbuffers~=1.12.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow-gpu) (1.12)\n",
            "Requirement already satisfied: wheel~=0.35 in /usr/local/lib/python3.7/dist-packages (from tensorflow-gpu) (0.36.2)\n",
            "Requirement already satisfied: protobuf>=3.9.2 in /usr/local/lib/python3.7/dist-packages (from tensorflow-gpu) (3.12.4)\n",
            "Requirement already satisfied: grpcio~=1.34.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow-gpu) (1.34.1)\n",
            "Requirement already satisfied: termcolor~=1.1.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow-gpu) (1.1.0)\n",
            "Requirement already satisfied: tensorboard~=2.5 in /usr/local/lib/python3.7/dist-packages (from tensorflow-gpu) (2.5.0)\n",
            "Requirement already satisfied: gast==0.4.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow-gpu) (0.4.0)\n",
            "Requirement already satisfied: keras-nightly~=2.5.0.dev in /usr/local/lib/python3.7/dist-packages (from tensorflow-gpu) (2.5.0.dev2021032900)\n",
            "Requirement already satisfied: typing-extensions~=3.7.4 in /usr/local/lib/python3.7/dist-packages (from tensorflow-gpu) (3.7.4.3)\n",
            "Requirement already satisfied: tensorflow-estimator<2.6.0,>=2.5.0rc0 in /usr/local/lib/python3.7/dist-packages (from tensorflow-gpu) (2.5.0)\n",
            "Requirement already satisfied: cached-property; python_version < \"3.8\" in /usr/local/lib/python3.7/dist-packages (from h5py~=3.1.0->tensorflow-gpu) (1.5.2)\n",
            "Requirement already satisfied: setuptools in /usr/local/lib/python3.7/dist-packages (from protobuf>=3.9.2->tensorflow-gpu) (57.0.0)\n",
            "Requirement already satisfied: google-auth<2,>=1.6.3 in /usr/local/lib/python3.7/dist-packages (from tensorboard~=2.5->tensorflow-gpu) (1.30.0)\n",
            "Requirement already satisfied: google-auth-oauthlib<0.5,>=0.4.1 in /usr/local/lib/python3.7/dist-packages (from tensorboard~=2.5->tensorflow-gpu) (0.4.4)\n",
            "Requirement already satisfied: tensorboard-data-server<0.7.0,>=0.6.0 in /usr/local/lib/python3.7/dist-packages (from tensorboard~=2.5->tensorflow-gpu) (0.6.1)\n",
            "Requirement already satisfied: tensorboard-plugin-wit>=1.6.0 in /usr/local/lib/python3.7/dist-packages (from tensorboard~=2.5->tensorflow-gpu) (1.8.0)\n",
            "Requirement already satisfied: markdown>=2.6.8 in /usr/local/lib/python3.7/dist-packages (from tensorboard~=2.5->tensorflow-gpu) (3.3.4)\n",
            "Requirement already satisfied: werkzeug>=0.11.15 in /usr/local/lib/python3.7/dist-packages (from tensorboard~=2.5->tensorflow-gpu) (1.0.1)\n",
            "Requirement already satisfied: requests<3,>=2.21.0 in /usr/local/lib/python3.7/dist-packages (from tensorboard~=2.5->tensorflow-gpu) (2.23.0)\n",
            "Requirement already satisfied: cachetools<5.0,>=2.0.0 in /usr/local/lib/python3.7/dist-packages (from google-auth<2,>=1.6.3->tensorboard~=2.5->tensorflow-gpu) (4.2.2)\n",
            "Requirement already satisfied: rsa<5,>=3.1.4; python_version >= \"3.6\" in /usr/local/lib/python3.7/dist-packages (from google-auth<2,>=1.6.3->tensorboard~=2.5->tensorflow-gpu) (4.7.2)\n",
            "Requirement already satisfied: pyasn1-modules>=0.2.1 in /usr/local/lib/python3.7/dist-packages (from google-auth<2,>=1.6.3->tensorboard~=2.5->tensorflow-gpu) (0.2.8)\n",
            "Requirement already satisfied: requests-oauthlib>=0.7.0 in /usr/local/lib/python3.7/dist-packages (from google-auth-oauthlib<0.5,>=0.4.1->tensorboard~=2.5->tensorflow-gpu) (1.3.0)\n",
            "Requirement already satisfied: importlib-metadata; python_version < \"3.8\" in /usr/local/lib/python3.7/dist-packages (from markdown>=2.6.8->tensorboard~=2.5->tensorflow-gpu) (4.0.1)\n",
            "Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /usr/local/lib/python3.7/dist-packages (from requests<3,>=2.21.0->tensorboard~=2.5->tensorflow-gpu) (1.24.3)\n",
            "Requirement already satisfied: chardet<4,>=3.0.2 in /usr/local/lib/python3.7/dist-packages (from requests<3,>=2.21.0->tensorboard~=2.5->tensorflow-gpu) (3.0.4)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.7/dist-packages (from requests<3,>=2.21.0->tensorboard~=2.5->tensorflow-gpu) (2020.12.5)\n",
            "Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.7/dist-packages (from requests<3,>=2.21.0->tensorboard~=2.5->tensorflow-gpu) (2.10)\n",
            "Requirement already satisfied: pyasn1>=0.1.3 in /usr/local/lib/python3.7/dist-packages (from rsa<5,>=3.1.4; python_version >= \"3.6\"->google-auth<2,>=1.6.3->tensorboard~=2.5->tensorflow-gpu) (0.4.8)\n",
            "Requirement already satisfied: oauthlib>=3.0.0 in /usr/local/lib/python3.7/dist-packages (from requests-oauthlib>=0.7.0->google-auth-oauthlib<0.5,>=0.4.1->tensorboard~=2.5->tensorflow-gpu) (3.1.0)\n",
            "Requirement already satisfied: zipp>=0.5 in /usr/local/lib/python3.7/dist-packages (from importlib-metadata; python_version < \"3.8\"->markdown>=2.6.8->tensorboard~=2.5->tensorflow-gpu) (3.4.1)\n",
            "Installing collected packages: tensorflow-gpu\n",
            "Successfully installed tensorflow-gpu-2.5.0\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Dnp5F65bMfbQ"
      },
      "source": [
        "import tensorflow as tf"
      ],
      "id": "Dnp5F65bMfbQ",
      "execution_count": 25,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "tpzk5AflNHcL",
        "outputId": "aa5f478f-e749-4f1e-b9ce-b8c87badd06f",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 35
        }
      },
      "source": [
        "tf.__version__"
      ],
      "id": "tpzk5AflNHcL",
      "execution_count": 26,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            },
            "text/plain": [
              "'2.5.0'"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 26
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "9JKf5KQ5NMhh"
      },
      "source": [
        ""
      ],
      "id": "9JKf5KQ5NMhh",
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "82234de0"
      },
      "source": [
        "import pandas as pd\n",
        "import numpy as np\n",
        "import matplotlib.pyplot as plt\n",
        "import seaborn as sns"
      ],
      "id": "82234de0",
      "execution_count": 27,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "eeab9ff4"
      },
      "source": [
        "#df = pd.read_csv('./datasets/preprocessed.csv')\n",
        "df = pd.read_csv('https://raw.githubusercontent.com/OvinduWijethunge/Next-Day-Rain-Predicts-In-Australia/master/datasets/preprocessed.csv')"
      ],
      "id": "eeab9ff4",
      "execution_count": 28,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "691a1077",
        "outputId": "2b5f0ecc-34bd-4078-fadc-a3c7efd98ad8",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 215
        }
      },
      "source": [
        "df.head()"
      ],
      "id": "691a1077",
      "execution_count": 29,
      "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>Location</th>\n",
              "      <th>MinTemp</th>\n",
              "      <th>MaxTemp</th>\n",
              "      <th>Rainfall</th>\n",
              "      <th>Evaporation</th>\n",
              "      <th>Sunshine</th>\n",
              "      <th>WindGustDir</th>\n",
              "      <th>WindGustSpeed</th>\n",
              "      <th>WindDir9am</th>\n",
              "      <th>WindDir3pm</th>\n",
              "      <th>WindSpeed9am</th>\n",
              "      <th>WindSpeed3pm</th>\n",
              "      <th>Humidity9am</th>\n",
              "      <th>Humidity3pm</th>\n",
              "      <th>Pressure9am</th>\n",
              "      <th>Pressure3pm</th>\n",
              "      <th>Cloud9am</th>\n",
              "      <th>Cloud3pm</th>\n",
              "      <th>Temp9am</th>\n",
              "      <th>Temp3pm</th>\n",
              "      <th>RainToday</th>\n",
              "      <th>RainTomorrow</th>\n",
              "      <th>Month</th>\n",
              "      <th>Day</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>22</td>\n",
              "      <td>8.694688</td>\n",
              "      <td>13.589273</td>\n",
              "      <td>0.6</td>\n",
              "      <td>2.263869</td>\n",
              "      <td>57.554920</td>\n",
              "      <td>0</td>\n",
              "      <td>8.870193</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>12.139245</td>\n",
              "      <td>14.131102</td>\n",
              "      <td>34.891151</td>\n",
              "      <td>13.142729</td>\n",
              "      <td>318.255596</td>\n",
              "      <td>1.375390</td>\n",
              "      <td>8.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>10.549671</td>\n",
              "      <td>13.043088</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>12</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>22</td>\n",
              "      <td>5.301024</td>\n",
              "      <td>14.668806</td>\n",
              "      <td>0.0</td>\n",
              "      <td>2.406140</td>\n",
              "      <td>69.201128</td>\n",
              "      <td>1</td>\n",
              "      <td>8.870193</td>\n",
              "      <td>4</td>\n",
              "      <td>2</td>\n",
              "      <td>3.174802</td>\n",
              "      <td>13.142729</td>\n",
              "      <td>23.417682</td>\n",
              "      <td>14.620089</td>\n",
              "      <td>319.018654</td>\n",
              "      <td>1.375395</td>\n",
              "      <td>7.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>10.705502</td>\n",
              "      <td>14.278149</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>12</td>\n",
              "      <td>2</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>22</td>\n",
              "      <td>8.423478</td>\n",
              "      <td>14.960437</td>\n",
              "      <td>0.0</td>\n",
              "      <td>2.496163</td>\n",
              "      <td>59.559201</td>\n",
              "      <td>2</td>\n",
              "      <td>9.074396</td>\n",
              "      <td>0</td>\n",
              "      <td>2</td>\n",
              "      <td>11.631293</td>\n",
              "      <td>15.105825</td>\n",
              "      <td>20.724608</td>\n",
              "      <td>17.019013</td>\n",
              "      <td>318.229277</td>\n",
              "      <td>1.375401</td>\n",
              "      <td>8.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>12.642979</td>\n",
              "      <td>13.737467</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>12</td>\n",
              "      <td>3</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>22</td>\n",
              "      <td>6.355600</td>\n",
              "      <td>16.068119</td>\n",
              "      <td>0.0</td>\n",
              "      <td>2.589230</td>\n",
              "      <td>77.023050</td>\n",
              "      <td>3</td>\n",
              "      <td>6.419909</td>\n",
              "      <td>12</td>\n",
              "      <td>14</td>\n",
              "      <td>7.376108</td>\n",
              "      <td>6.240251</td>\n",
              "      <td>23.860366</td>\n",
              "      <td>10.079368</td>\n",
              "      <td>320.859017</td>\n",
              "      <td>1.375428</td>\n",
              "      <td>0.0</td>\n",
              "      <td>5.0</td>\n",
              "      <td>11.170317</td>\n",
              "      <td>15.347521</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>12</td>\n",
              "      <td>4</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>22</td>\n",
              "      <td>10.860881</td>\n",
              "      <td>18.099591</td>\n",
              "      <td>1.0</td>\n",
              "      <td>2.819463</td>\n",
              "      <td>88.580965</td>\n",
              "      <td>0</td>\n",
              "      <td>8.553172</td>\n",
              "      <td>8</td>\n",
              "      <td>11</td>\n",
              "      <td>5.061140</td>\n",
              "      <td>12.139245</td>\n",
              "      <td>39.340953</td>\n",
              "      <td>18.425882</td>\n",
              "      <td>319.071265</td>\n",
              "      <td>1.375382</td>\n",
              "      <td>7.0</td>\n",
              "      <td>8.0</td>\n",
              "      <td>11.015816</td>\n",
              "      <td>16.877070</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>12</td>\n",
              "      <td>5</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "   Location    MinTemp    MaxTemp  ...  RainTomorrow  Month  Day\n",
              "0        22   8.694688  13.589273  ...             0     12    1\n",
              "1        22   5.301024  14.668806  ...             0     12    2\n",
              "2        22   8.423478  14.960437  ...             0     12    3\n",
              "3        22   6.355600  16.068119  ...             0     12    4\n",
              "4        22  10.860881  18.099591  ...             0     12    5\n",
              "\n",
              "[5 rows x 24 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 29
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "d7e2503f"
      },
      "source": [
        ""
      ],
      "id": "d7e2503f",
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "d14ac8fb",
        "outputId": "7b1f7232-1a03-4fee-c27d-33ee8ef6d517",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "source": [
        "df.shape"
      ],
      "id": "d14ac8fb",
      "execution_count": 30,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(141626, 24)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 30
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "dc8f4731",
        "outputId": "ecddb62b-375e-4984-f1e8-da54238ed58b",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "source": [
        "df.isnull().mean()*100"
      ],
      "id": "dc8f4731",
      "execution_count": 31,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Location         0.0\n",
              "MinTemp          0.0\n",
              "MaxTemp          0.0\n",
              "Rainfall         0.0\n",
              "Evaporation      0.0\n",
              "Sunshine         0.0\n",
              "WindGustDir      0.0\n",
              "WindGustSpeed    0.0\n",
              "WindDir9am       0.0\n",
              "WindDir3pm       0.0\n",
              "WindSpeed9am     0.0\n",
              "WindSpeed3pm     0.0\n",
              "Humidity9am      0.0\n",
              "Humidity3pm      0.0\n",
              "Pressure9am      0.0\n",
              "Pressure3pm      0.0\n",
              "Cloud9am         0.0\n",
              "Cloud3pm         0.0\n",
              "Temp9am          0.0\n",
              "Temp3pm          0.0\n",
              "RainToday        0.0\n",
              "RainTomorrow     0.0\n",
              "Month            0.0\n",
              "Day              0.0\n",
              "dtype: float64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 31
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "720caad2"
      },
      "source": [
        "y = df['RainTomorrow']\n",
        "X = df.drop(['RainTomorrow'],axis=1)"
      ],
      "id": "720caad2",
      "execution_count": 32,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "900550e3",
        "outputId": "15407b31-6e89-4548-d42b-25e7216dfb40",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "source": [
        "X.columns"
      ],
      "id": "900550e3",
      "execution_count": 33,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Index(['Location', 'MinTemp', 'MaxTemp', 'Rainfall', 'Evaporation', 'Sunshine',\n",
              "       'WindGustDir', 'WindGustSpeed', 'WindDir9am', 'WindDir3pm',\n",
              "       'WindSpeed9am', 'WindSpeed3pm', 'Humidity9am', 'Humidity3pm',\n",
              "       'Pressure9am', 'Pressure3pm', 'Cloud9am', 'Cloud3pm', 'Temp9am',\n",
              "       'Temp3pm', 'RainToday', 'Month', 'Day'],\n",
              "      dtype='object')"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 33
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "cee95c3d",
        "outputId": "f5961349-02e3-4c51-f600-17b6755c2452",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "source": [
        "y"
      ],
      "id": "cee95c3d",
      "execution_count": 34,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0         0\n",
              "1         0\n",
              "2         0\n",
              "3         0\n",
              "4         0\n",
              "         ..\n",
              "141621    0\n",
              "141622    0\n",
              "141623    0\n",
              "141624    0\n",
              "141625    0\n",
              "Name: RainTomorrow, Length: 141626, dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 34
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "b4db0d38",
        "outputId": "6d319a9d-f6ed-4ea6-9a06-c58f94097cde",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "source": [
        "from imblearn.over_sampling import RandomOverSampler\n",
        "from collections import Counter\n",
        "\n",
        "os=RandomOverSampler(0.9)\n",
        "X_ns,y_ns=os.fit_sample(X,y)\n",
        "print(\"The number of classes before fit {}\".format(Counter(y)))\n",
        "print(\"The number of classes after fit {}\".format(Counter(y_ns)))\n",
        "\n",
        "X = X_ns\n",
        "y = y_ns"
      ],
      "id": "b4db0d38",
      "execution_count": 35,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "The number of classes before fit Counter({0: 110382, 1: 31244})\n",
            "The number of classes after fit Counter({0: 110382, 1: 99343})\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "/usr/local/lib/python3.7/dist-packages/sklearn/utils/deprecation.py:87: FutureWarning: Function safe_indexing is deprecated; safe_indexing is deprecated in version 0.22 and will be removed in version 0.24.\n",
            "  warnings.warn(msg, category=FutureWarning)\n"
          ],
          "name": "stderr"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "c6bee4bc"
      },
      "source": [
        "from sklearn.model_selection import train_test_split\n",
        "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)"
      ],
      "id": "c6bee4bc",
      "execution_count": 36,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "a4ecca86"
      },
      "source": [
        "from sklearn.ensemble import GradientBoostingClassifier"
      ],
      "id": "a4ecca86",
      "execution_count": 37,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "a6dab556"
      },
      "source": [
        "gb = GradientBoostingClassifier()"
      ],
      "id": "a6dab556",
      "execution_count": 38,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "8207af41",
        "outputId": "0e1914d9-8ee1-4cc4-8270-8a7005adf92e",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "source": [
        "gb.get_params()"
      ],
      "id": "8207af41",
      "execution_count": 39,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "{'ccp_alpha': 0.0,\n",
              " 'criterion': 'friedman_mse',\n",
              " 'init': None,\n",
              " 'learning_rate': 0.1,\n",
              " 'loss': 'deviance',\n",
              " 'max_depth': 3,\n",
              " 'max_features': None,\n",
              " 'max_leaf_nodes': None,\n",
              " 'min_impurity_decrease': 0.0,\n",
              " 'min_impurity_split': None,\n",
              " 'min_samples_leaf': 1,\n",
              " 'min_samples_split': 2,\n",
              " 'min_weight_fraction_leaf': 0.0,\n",
              " 'n_estimators': 100,\n",
              " 'n_iter_no_change': None,\n",
              " 'presort': 'deprecated',\n",
              " 'random_state': None,\n",
              " 'subsample': 1.0,\n",
              " 'tol': 0.0001,\n",
              " 'validation_fraction': 0.1,\n",
              " 'verbose': 0,\n",
              " 'warm_start': False}"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 39
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "311c10f7"
      },
      "source": [
        "grid={\n",
        "    'learning_rate':[0.15,0.1,0.05,0.01,0.005,0.001], \n",
        "    'n_estimators':[x for x in range(100,1000,2)],\n",
        "    'max_depth':[2,3,4,5,6,7],\n",
        "    'min_samples_split':[2,4,6,8,10,20,40,60,100], \n",
        "    'min_samples_leaf':[1,3,5,7,9],\n",
        "    'max_features':[2,3,4,5,6,7],\n",
        "    'subsample':[0.7,0.75,0.8,0.85,0.9,0.95,1]\n",
        "}"
      ],
      "id": "311c10f7",
      "execution_count": 40,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "5db49065"
      },
      "source": [
        "from sklearn.model_selection import StratifiedKFold\n",
        "cv = StratifiedKFold(n_splits=10, shuffle=True)"
      ],
      "id": "5db49065",
      "execution_count": 41,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "f22dfc5b"
      },
      "source": [
        "from sklearn.model_selection import RandomizedSearchCV\n",
        "gb_random = RandomizedSearchCV(estimator=gb, param_distributions=grid, n_jobs=-1,n_iter = 50, cv=cv, scoring='accuracy',error_score=0,return_train_score=True,verbose=2)"
      ],
      "id": "f22dfc5b",
      "execution_count": 42,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "fb88a238",
        "outputId": "2ef9fa88-4e21-4d94-c774-f1e469ce91f0",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 354
        }
      },
      "source": [
        "gb_random.fit(X_train,y_train)"
      ],
      "id": "fb88a238",
      "execution_count": 43,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Fitting 10 folds for each of 50 candidates, totalling 500 fits\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.\n",
            "[Parallel(n_jobs=-1)]: Done  37 tasks      | elapsed: 26.2min\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "error",
          "ename": "KeyboardInterrupt",
          "evalue": "ignored",
          "traceback": [
            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
            "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
            "\u001b[0;32m<ipython-input-43-c45dccee484b>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mgb_random\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX_train\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0my_train\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
            "\u001b[0;32m/usr/local/lib/python3.7/dist-packages/sklearn/model_selection/_search.py\u001b[0m in \u001b[0;36mfit\u001b[0;34m(self, X, y, groups, **fit_params)\u001b[0m\n\u001b[1;32m    708\u001b[0m                 \u001b[0;32mreturn\u001b[0m \u001b[0mresults\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    709\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 710\u001b[0;31m             \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_run_search\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mevaluate_candidates\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    711\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    712\u001b[0m         \u001b[0;31m# For multi-metric evaluation, store the best_index_, best_params_ and\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.7/dist-packages/sklearn/model_selection/_search.py\u001b[0m in \u001b[0;36m_run_search\u001b[0;34m(self, evaluate_candidates)\u001b[0m\n\u001b[1;32m   1482\u001b[0m         evaluate_candidates(ParameterSampler(\n\u001b[1;32m   1483\u001b[0m             \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mparam_distributions\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mn_iter\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1484\u001b[0;31m             random_state=self.random_state))\n\u001b[0m",
            "\u001b[0;32m/usr/local/lib/python3.7/dist-packages/sklearn/model_selection/_search.py\u001b[0m in \u001b[0;36mevaluate_candidates\u001b[0;34m(candidate_params)\u001b[0m\n\u001b[1;32m    687\u001b[0m                                \u001b[0;32mfor\u001b[0m \u001b[0mparameters\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mtrain\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtest\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    688\u001b[0m                                in product(candidate_params,\n\u001b[0;32m--> 689\u001b[0;31m                                           cv.split(X, y, groups)))\n\u001b[0m\u001b[1;32m    690\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    691\u001b[0m                 \u001b[0;32mif\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mout\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m<\u001b[0m \u001b[0;36m1\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.7/dist-packages/joblib/parallel.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, iterable)\u001b[0m\n\u001b[1;32m   1052\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1053\u001b[0m             \u001b[0;32mwith\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_backend\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mretrieval_context\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1054\u001b[0;31m                 \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mretrieve\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1055\u001b[0m             \u001b[0;31m# Make sure that we get a last message telling us we are done\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1056\u001b[0m             \u001b[0melapsed_time\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtime\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtime\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m-\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_start_time\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.7/dist-packages/joblib/parallel.py\u001b[0m in \u001b[0;36mretrieve\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    931\u001b[0m             \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    932\u001b[0m                 \u001b[0;32mif\u001b[0m \u001b[0mgetattr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_backend\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'supports_timeout'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;32mFalse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 933\u001b[0;31m                     \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_output\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mextend\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mjob\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtimeout\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtimeout\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    934\u001b[0m                 \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    935\u001b[0m                     \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_output\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mextend\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mjob\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.7/dist-packages/joblib/_parallel_backends.py\u001b[0m in \u001b[0;36mwrap_future_result\u001b[0;34m(future, timeout)\u001b[0m\n\u001b[1;32m    540\u001b[0m         AsyncResults.get from multiprocessing.\"\"\"\n\u001b[1;32m    541\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 542\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mfuture\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mresult\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtimeout\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mtimeout\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    543\u001b[0m         \u001b[0;32mexcept\u001b[0m \u001b[0mCfTimeoutError\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    544\u001b[0m             \u001b[0;32mraise\u001b[0m \u001b[0mTimeoutError\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/lib/python3.7/concurrent/futures/_base.py\u001b[0m in \u001b[0;36mresult\u001b[0;34m(self, timeout)\u001b[0m\n\u001b[1;32m    428\u001b[0m                 \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__get_result\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    429\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 430\u001b[0;31m             \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_condition\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwait\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtimeout\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    431\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    432\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_state\u001b[0m \u001b[0;32min\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0mCANCELLED\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mCANCELLED_AND_NOTIFIED\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/lib/python3.7/threading.py\u001b[0m in \u001b[0;36mwait\u001b[0;34m(self, timeout)\u001b[0m\n\u001b[1;32m    294\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m    \u001b[0;31m# restore state no matter what (e.g., KeyboardInterrupt)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    295\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0mtimeout\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 296\u001b[0;31m                 \u001b[0mwaiter\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0macquire\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    297\u001b[0m                 \u001b[0mgotit\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mTrue\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    298\u001b[0m             \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "78228d48"
      },
      "source": [
        "best_model = gb_random.best_estimator_"
      ],
      "id": "78228d48",
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "c7db35d9"
      },
      "source": [
        "best_model"
      ],
      "id": "c7db35d9",
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "c1aa9362"
      },
      "source": [
        "gb_random.best_params_"
      ],
      "id": "c1aa9362",
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "b831ba6b"
      },
      "source": [
        "gb_random.best_score_"
      ],
      "id": "b831ba6b",
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "85bfe268"
      },
      "source": [
        "y_pred = best_model.predict(X_test)"
      ],
      "id": "85bfe268",
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "949a3930"
      },
      "source": [
        "err  =(y_pred- y_test)"
      ],
      "id": "949a3930",
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "83f0df60"
      },
      "source": [
        "err.value_counts().plot(kind='bar',color='purple')"
      ],
      "id": "83f0df60",
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "673848ab"
      },
      "source": [
        "from sklearn import metrics\n",
        "print('MAE:', metrics.mean_absolute_error(y_test,y_pred))\n",
        "print('MSE:', metrics.mean_squared_error(y_test, y_pred))\n",
        "print('RMSE:', np.sqrt(metrics.mean_squared_error(y_test, y_pred)))"
      ],
      "id": "673848ab",
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "8a96a410"
      },
      "source": [
        "indices=list(X_train)\n",
        "feat_imp = pd.Series(best_model.feature_importances_, indices).sort_values(ascending=False)\n",
        "feat_imp.plot(kind='bar', title='Importance of Features')\n",
        "plt.ylabel('Feature Importance Score')"
      ],
      "id": "8a96a410",
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "de7a441a"
      },
      "source": [
        "from sklearn.metrics import classification_report, confusion_matrix\n",
        "print(confusion_matrix(y_test, y_pred))\n",
        "print(classification_report(y_test, y_pred))"
      ],
      "id": "de7a441a",
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "129eb9dc"
      },
      "source": [
        "print(\"accuracy is {}\".format(best_model.score(X_test, y_test)))"
      ],
      "id": "129eb9dc",
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "3bdf0065"
      },
      "source": [
        "from sklearn import metrics\n",
        "from sklearn.metrics import roc_auc_score\n",
        "from sklearn.metrics import roc_curve"
      ],
      "id": "3bdf0065",
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "b60df881"
      },
      "source": [
        "baseline_roc_auc = roc_auc_score(y_test, best_model.predict(X_test))\n",
        "fprB, tprB, thresholdsB = roc_curve(y_test, best_model.predict_proba(X_test)[:,1])"
      ],
      "id": "b60df881",
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "a6c1736e"
      },
      "source": [
        "plt.figure()\n",
        "plt.plot(fprB, tprB, label='GB(area = %0.2f)' % baseline_roc_auc)\n",
        "plt.plot([0, 1], [0, 1],'r--')\n",
        "plt.xlim([0.0, 1.0])\n",
        "plt.ylim([0.0, 1.05])\n",
        "plt.xlabel('False Positive Rate')\n",
        "plt.ylabel('True Positive Rate')\n",
        "plt.title('Receiver operating characteristic')\n",
        "plt.legend(loc=\"lower right\")\n",
        "plt.show()"
      ],
      "id": "a6c1736e",
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "4742d790"
      },
      "source": [
        "# ROC - AUC simple code\n",
        "#metrics.plot_roc_curve(knn, X_test, y_test)\n",
        "#metrics.roc_auc_score(y_test, y_pred4, average=None)"
      ],
      "id": "4742d790",
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "6fe59660"
      },
      "source": [
        "### Predict test_y values and probabilities based on random forest model\n",
        "probs_y=best_model.predict_proba(X_test) \n",
        "  # probs_y is a 2-D array of probability of being labeled as 0 (first column of array) vs 1 (2nd column in array)\n",
        "\n",
        "from sklearn.metrics import precision_recall_curve\n",
        "precision, recall, thresholds = precision_recall_curve(y_test, probs_y[:, 1]) \n",
        "   #retrieve probability of being 1(in second column of probs_y)\n",
        "pr_auc = metrics.auc(recall, precision)\n",
        "\n",
        "plt.title(\"Precision-Recall vs Threshold Chart\")\n",
        "plt.plot(thresholds, precision[: -1], \"b--\", label=\"Precision\")\n",
        "plt.plot(thresholds, recall[: -1], \"r--\", label=\"Recall\")\n",
        "plt.ylabel(\"Precision, Recall\")\n",
        "plt.xlabel(\"Threshold\")\n",
        "plt.legend(loc=\"lower left\")\n",
        "plt.ylim([0,1])"
      ],
      "id": "6fe59660",
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "3b209cca"
      },
      "source": [
        "import pickle\n",
        "#open a file, where you ant to store the data\n",
        "file = open('gboost.pkl', 'wb')\n",
        "# dump information to that file\n",
        "pickle.dump(best_model, file)\n",
        "file.close()"
      ],
      "id": "3b209cca",
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "414fa1fd"
      },
      "source": [
        ""
      ],
      "id": "414fa1fd",
      "execution_count": null,
      "outputs": []
    }
  ]
}