Classifier.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Classifier.ipynb",
      "provenance": [],
      "collapsed_sections": [
        "88mvMkwlmILl",
        "80j6krx_mL4M",
        "vr3gruKPyfgq",
        "GQWEmvZyu2io"
      ],
      "authorship_tag": "ABX9TyNgKl4X7PDeAAxIh5doAMFr",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/Amirosein/Variable-Stars-Classification/blob/main/Classifier.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "82PHgIndpuaE"
      },
      "source": [
        "# Classifier Function\n",
        "-----"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "88mvMkwlmILl"
      },
      "source": [
        "# Pre"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "_xYXTtukc4Oe",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "73f57393-b363-4e88-c54d-6757411424fc"
      },
      "source": [
        "import pandas as pd\n",
        "import numpy as np\n",
        "import matplotlib.pyplot as plt\n",
        "import io, requests, zipfile\n",
        "from zipfile import ZipFile\n",
        "import seaborn as sns\n",
        "\n",
        "!pip install tsfresh\n",
        "from tsfresh import extract_features\n",
        "\n",
        "!pip install pyunpack\n",
        "!pip install patool\n",
        "from pyunpack import Archive\n",
        "\n",
        "import warnings\n",
        "warnings.filterwarnings('ignore')\n",
        "\n",
        "\n",
        "# plt.rcParams.update({'font.size': 20, 'figsize':(8,6)})\n",
        "SMALL_SIZE = 12\n",
        "MEDIUM_SIZE = 15\n",
        "BIGGER_SIZE = 18\n",
        "\n",
        "plt.rc('font', size=BIGGER_SIZE)          # controls default text sizes\n",
        "plt.rc('axes', titlesize=MEDIUM_SIZE)     # fontsize of the axes title\n",
        "plt.rc('axes', labelsize=BIGGER_SIZE)    # fontsize of the x and y labels\n",
        "plt.rc('xtick', labelsize=SMALL_SIZE)    # fontsize of the tick labels\n",
        "plt.rc('ytick', labelsize=SMALL_SIZE)    # fontsize of the tick labels\n",
        "plt.rc('legend', fontsize=MEDIUM_SIZE)    # legend fontsize\n",
        "plt.rc('figure', titlesize=BIGGER_SIZE)  # fontsize of the figure title\n",
        "\n",
        "plt.rc('axes', linewidth = 5 )\n",
        "plt.rc('lines', linewidth = 5 )\n",
        "\n",
        "plt.rc('lines', markersize = 5 )\n",
        "\n",
        "plt.rc('figure', figsize=(8,4) )         # Image size"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Requirement already satisfied: tsfresh in /usr/local/lib/python3.7/dist-packages (0.18.0)\n",
            "Requirement already satisfied: statsmodels>=0.9.0 in /usr/local/lib/python3.7/dist-packages (from tsfresh) (0.10.2)\n",
            "Requirement already satisfied: dask[dataframe]>=2.9.0 in /usr/local/lib/python3.7/dist-packages (from tsfresh) (2.12.0)\n",
            "Requirement already satisfied: scikit-learn>=0.22.0 in /usr/local/lib/python3.7/dist-packages (from tsfresh) (0.22.2.post1)\n",
            "Requirement already satisfied: tqdm>=4.10.0 in /usr/local/lib/python3.7/dist-packages (from tsfresh) (4.41.1)\n",
            "Requirement already satisfied: matrixprofile>=1.1.10<2.0.0 in /usr/local/lib/python3.7/dist-packages (from tsfresh) (1.1.10)\n",
            "Requirement already satisfied: patsy>=0.4.1 in /usr/local/lib/python3.7/dist-packages (from tsfresh) (0.5.1)\n",
            "Requirement already satisfied: requests>=2.9.1 in /usr/local/lib/python3.7/dist-packages (from tsfresh) (2.23.0)\n",
            "Requirement already satisfied: scipy>=1.2.0 in /usr/local/lib/python3.7/dist-packages (from tsfresh) (1.7.0)\n",
            "Requirement already satisfied: stumpy>=1.7.2 in /usr/local/lib/python3.7/dist-packages (from tsfresh) (1.8.0)\n",
            "Requirement already satisfied: pandas>=0.25.0 in /usr/local/lib/python3.7/dist-packages (from tsfresh) (1.1.5)\n",
            "Requirement already satisfied: numpy>=1.15.1 in /usr/local/lib/python3.7/dist-packages (from tsfresh) (1.19.5)\n",
            "Requirement already satisfied: distributed>=2.11.0 in /usr/local/lib/python3.7/dist-packages (from tsfresh) (2.30.1)\n",
            "Requirement already satisfied: toolz>=0.7.3 in /usr/local/lib/python3.7/dist-packages (from dask[dataframe]>=2.9.0->tsfresh) (0.11.1)\n",
            "Requirement already satisfied: fsspec>=0.6.0 in /usr/local/lib/python3.7/dist-packages (from dask[dataframe]>=2.9.0->tsfresh) (2021.7.0)\n",
            "Requirement already satisfied: partd>=0.3.10 in /usr/local/lib/python3.7/dist-packages (from dask[dataframe]>=2.9.0->tsfresh) (1.2.0)\n",
            "Requirement already satisfied: tornado>=5 in /usr/local/lib/python3.7/dist-packages (from distributed>=2.11.0->tsfresh) (5.1.1)\n",
            "Requirement already satisfied: click>=6.6 in /usr/local/lib/python3.7/dist-packages (from distributed>=2.11.0->tsfresh) (7.1.2)\n",
            "Requirement already satisfied: pyyaml in /usr/local/lib/python3.7/dist-packages (from distributed>=2.11.0->tsfresh) (3.13)\n",
            "Requirement already satisfied: msgpack>=0.6.0 in /usr/local/lib/python3.7/dist-packages (from distributed>=2.11.0->tsfresh) (1.0.2)\n",
            "Requirement already satisfied: zict>=0.1.3 in /usr/local/lib/python3.7/dist-packages (from distributed>=2.11.0->tsfresh) (2.0.0)\n",
            "Requirement already satisfied: sortedcontainers!=2.0.0,!=2.0.1 in /usr/local/lib/python3.7/dist-packages (from distributed>=2.11.0->tsfresh) (2.4.0)\n",
            "Requirement already satisfied: setuptools in /usr/local/lib/python3.7/dist-packages (from distributed>=2.11.0->tsfresh) (57.2.0)\n",
            "Requirement already satisfied: cloudpickle>=1.5.0 in /usr/local/lib/python3.7/dist-packages (from distributed>=2.11.0->tsfresh) (1.6.0)\n",
            "Requirement already satisfied: tblib>=1.6.0 in /usr/local/lib/python3.7/dist-packages (from distributed>=2.11.0->tsfresh) (1.7.0)\n",
            "Requirement already satisfied: psutil>=5.0 in /usr/local/lib/python3.7/dist-packages (from distributed>=2.11.0->tsfresh) (5.4.8)\n",
            "Requirement already satisfied: matplotlib>=3.0.3 in /usr/local/lib/python3.7/dist-packages (from matrixprofile>=1.1.10<2.0.0->tsfresh) (3.2.2)\n",
            "Requirement already satisfied: protobuf==3.11.2 in /usr/local/lib/python3.7/dist-packages (from matrixprofile>=1.1.10<2.0.0->tsfresh) (3.11.2)\n",
            "Requirement already satisfied: six>=1.9 in /usr/local/lib/python3.7/dist-packages (from protobuf==3.11.2->matrixprofile>=1.1.10<2.0.0->tsfresh) (1.15.0)\n",
            "Requirement already satisfied: pyparsing!=2.0.4,!=2.1.2,!=2.1.6,>=2.0.1 in /usr/local/lib/python3.7/dist-packages (from matplotlib>=3.0.3->matrixprofile>=1.1.10<2.0.0->tsfresh) (2.4.7)\n",
            "Requirement already satisfied: python-dateutil>=2.1 in /usr/local/lib/python3.7/dist-packages (from matplotlib>=3.0.3->matrixprofile>=1.1.10<2.0.0->tsfresh) (2.8.1)\n",
            "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.7/dist-packages (from matplotlib>=3.0.3->matrixprofile>=1.1.10<2.0.0->tsfresh) (0.10.0)\n",
            "Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.7/dist-packages (from matplotlib>=3.0.3->matrixprofile>=1.1.10<2.0.0->tsfresh) (1.3.1)\n",
            "Requirement already satisfied: pytz>=2017.2 in /usr/local/lib/python3.7/dist-packages (from pandas>=0.25.0->tsfresh) (2018.9)\n",
            "Requirement already satisfied: locket in /usr/local/lib/python3.7/dist-packages (from partd>=0.3.10->dask[dataframe]>=2.9.0->tsfresh) (0.2.1)\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>=2.9.1->tsfresh) (1.24.3)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.7/dist-packages (from requests>=2.9.1->tsfresh) (2021.5.30)\n",
            "Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.7/dist-packages (from requests>=2.9.1->tsfresh) (2.10)\n",
            "Requirement already satisfied: chardet<4,>=3.0.2 in /usr/local/lib/python3.7/dist-packages (from requests>=2.9.1->tsfresh) (3.0.4)\n",
            "Requirement already satisfied: joblib>=0.11 in /usr/local/lib/python3.7/dist-packages (from scikit-learn>=0.22.0->tsfresh) (1.0.1)\n",
            "Requirement already satisfied: numba>=0.48 in /usr/local/lib/python3.7/dist-packages (from stumpy>=1.7.2->tsfresh) (0.51.2)\n",
            "Requirement already satisfied: llvmlite<0.35,>=0.34.0.dev0 in /usr/local/lib/python3.7/dist-packages (from numba>=0.48->stumpy>=1.7.2->tsfresh) (0.34.0)\n",
            "Requirement already satisfied: heapdict in /usr/local/lib/python3.7/dist-packages (from zict>=0.1.3->distributed>=2.11.0->tsfresh) (1.0.1)\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "/usr/local/lib/python3.7/dist-packages/statsmodels/tools/_testing.py:19: FutureWarning: pandas.util.testing is deprecated. Use the functions in the public API at pandas.testing instead.\n",
            "  import pandas.util.testing as tm\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "stream",
          "text": [
            "Collecting pyunpack\n",
            "  Downloading pyunpack-0.2.2-py2.py3-none-any.whl (3.8 kB)\n",
            "Collecting easyprocess\n",
            "  Downloading EasyProcess-0.3-py2.py3-none-any.whl (7.9 kB)\n",
            "Collecting entrypoint2\n",
            "  Downloading entrypoint2-0.2.4-py3-none-any.whl (6.2 kB)\n",
            "Installing collected packages: entrypoint2, easyprocess, pyunpack\n",
            "Successfully installed easyprocess-0.3 entrypoint2-0.2.4 pyunpack-0.2.2\n",
            "Collecting patool\n",
            "  Downloading patool-1.12-py2.py3-none-any.whl (77 kB)\n",
            "\u001b[K     |████████████████████████████████| 77 kB 4.7 MB/s \n",
            "\u001b[?25hInstalling collected packages: patool\n",
            "Successfully installed patool-1.12\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "80j6krx_mL4M"
      },
      "source": [
        "# load model"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ROWskVRmlVcm"
      },
      "source": [
        "import pickle\n",
        "\n",
        "a_file = open(\"/content/finalized_model.sav\", \"rb\")\n",
        "model = pickle.load(a_file)\n",
        "a_file.close()\n",
        "\n",
        "b_file = open(\"/content/ktfcp.pkl\", \"rb\")\n",
        "kind_to_fc_parameters = pickle.load(b_file)\n",
        "b_file.close()\n",
        "\n",
        "from sklearn import preprocessing\n",
        "encoder = preprocessing.LabelEncoder()\n",
        "encoder.classes_ = np.load('/content/classes.npy', allow_pickle=True)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "vr3gruKPyfgq"
      },
      "source": [
        "# necessary functions"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "S9uVkBionnJK"
      },
      "source": [
        "from pathlib import Path\n",
        "import csv\n",
        "from pathlib import Path\n",
        "\n",
        "f = open(\"/content/draft.csv\", \"x\")\n",
        "\n",
        "# function\n",
        "def data2csv(path, var, sn):\n",
        "  files = Path(path).rglob(\"*.dat\")\n",
        "\n",
        "  i = 0\n",
        "\n",
        "  for file in files:\n",
        "    datContent = [i.strip().split() for i in open(file).readlines()]\n",
        "    id = sn +'-'+ Path(file).stem\n",
        "    \n",
        "    # write it as a new CSV file\n",
        "    with open(\"/content/draft.csv\", \"w\") as f:\n",
        "      writer = csv.writer(f)\n",
        "      writer.writerows(datContent)\n",
        "\n",
        "    df = pd.read_csv(\"/content/draft.csv\", names=['time','value','e']) \n",
        "    df = df[['time','value']]\n",
        "    df['id'] = id\n",
        "    df['kind'] = var\n",
        "\n",
        "    if i==0:\n",
        "      data = df\n",
        "    else:\n",
        "      data = pd.concat([data,df], axis=0)\n",
        "\n",
        "    i = i+1\n",
        "    #print(i)\n",
        "\n",
        "  return data"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "CgD0dr6475kz"
      },
      "source": [
        "def feat_ex(X):\n",
        "  m = extract_features(X, column_id=\"id\", column_sort=\"time\", n_jobs= 20,\n",
        "                       column_kind=\"kind\", column_value=\"value\",\n",
        "                       kind_to_fc_parameters = kind_to_fc_parameters)\n",
        "  return m"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "xD9in4AunQvj"
      },
      "source": [
        "def dat2feat(urlI,urlV,sn):\n",
        "  mI = data2csv(urlI, 'I',sn)\n",
        "  mV = data2csv(urlV, 'V',sn)\n",
        "  m = pd.concat([mI,mV])\n",
        "  \n",
        "  f = feat_ex(m)\n",
        "  return f"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "GQWEmvZyu2io"
      },
      "source": [
        "# Classifier Function :"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "zA_IICyYu4_-"
      },
      "source": [
        "def classifier(url_I,url_V,sn):\n",
        "  # sn = survey name\n",
        "  \n",
        "  features = dat2feat(url_I,url_V,sn)\n",
        "  y = model.predict(features)\n",
        "  encoded_y = encoder.inverse_transform(y)\n",
        "  return encoded_y"
      ],
      "execution_count": null,
      "outputs": []
    }
  ]
}