BNO_hmw3.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Untitled1.ipynb",
      "provenance": [],
      "collapsed_sections": [],
      "authorship_tag": "ABX9TyOchh42dWFeOWXW6rywcCi/",
      "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/busranurorhan/Complete-Python-3-Bootcamp/blob/master/BNO_hmw3.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "eUxUEjYxnDkr",
        "outputId": "8c7ef017-aedd-4e1c-c171-89c95dea6cad"
      },
      "source": [
        "!apt-get update\n",
        "!apt-get install openjdk-8-jdk-headless -qq > /dev/null\n",
        "import os\n",
        "os.environ[\"JAVA_HOME\"] = \"/usr/lib/jvm/java-8-openjdk-amd64\"\n",
        "!update-alternatives --set java /usr/lib/jvm/java-8-openjdk-amd64/jre/bin/java\n",
        "!java -version\n",
        "!pip install pyspark"
      ],
      "execution_count": 1,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\r0% [Working]\r            \rGet:1 http://security.ubuntu.com/ubuntu bionic-security InRelease [88.7 kB]\n",
            "Get:2 https://cloud.r-project.org/bin/linux/ubuntu bionic-cran40/ InRelease [3,626 B]\n",
            "Ign:3 https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64  InRelease\n",
            "Get:4 http://ppa.launchpad.net/c2d4u.team/c2d4u4.0+/ubuntu bionic InRelease [15.9 kB]\n",
            "Hit:5 http://archive.ubuntu.com/ubuntu bionic InRelease\n",
            "Ign:6 https://developer.download.nvidia.com/compute/machine-learning/repos/ubuntu1804/x86_64  InRelease\n",
            "Get:7 http://archive.ubuntu.com/ubuntu bionic-updates InRelease [88.7 kB]\n",
            "Hit:8 https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64  Release\n",
            "Hit:9 https://developer.download.nvidia.com/compute/machine-learning/repos/ubuntu1804/x86_64  Release\n",
            "Get:10 http://security.ubuntu.com/ubuntu bionic-security/main amd64 Packages [2,365 kB]\n",
            "Hit:11 http://ppa.launchpad.net/cran/libgit2/ubuntu bionic InRelease\n",
            "Get:12 http://security.ubuntu.com/ubuntu bionic-security/universe amd64 Packages [1,430 kB]\n",
            "Get:13 http://archive.ubuntu.com/ubuntu bionic-backports InRelease [74.6 kB]\n",
            "Get:14 http://ppa.launchpad.net/deadsnakes/ppa/ubuntu bionic InRelease [15.9 kB]\n",
            "Hit:15 http://ppa.launchpad.net/graphics-drivers/ppa/ubuntu bionic InRelease\n",
            "Get:16 http://ppa.launchpad.net/c2d4u.team/c2d4u4.0+/ubuntu bionic/main Sources [1,802 kB]\n",
            "Get:19 http://ppa.launchpad.net/c2d4u.team/c2d4u4.0+/ubuntu bionic/main amd64 Packages [922 kB]\n",
            "Get:20 http://archive.ubuntu.com/ubuntu bionic-updates/universe amd64 Packages [2,209 kB]\n",
            "Get:21 http://archive.ubuntu.com/ubuntu bionic-updates/main amd64 Packages [2,801 kB]\n",
            "Get:22 http://ppa.launchpad.net/deadsnakes/ppa/ubuntu bionic/main amd64 Packages [40.8 kB]\n",
            "Fetched 11.9 MB in 3s (3,860 kB/s)\n",
            "Reading package lists... Done\n",
            "update-alternatives: using /usr/lib/jvm/java-8-openjdk-amd64/jre/bin/java to provide /usr/bin/java (java) in manual mode\n",
            "openjdk version \"1.8.0_292\"\n",
            "OpenJDK Runtime Environment (build 1.8.0_292-8u292-b10-0ubuntu1~18.04-b10)\n",
            "OpenJDK 64-Bit Server VM (build 25.292-b10, mixed mode)\n",
            "Collecting pyspark\n",
            "  Downloading pyspark-3.1.2.tar.gz (212.4 MB)\n",
            "\u001b[K     |████████████████████████████████| 212.4 MB 60 kB/s \n",
            "\u001b[?25hCollecting py4j==0.10.9\n",
            "  Downloading py4j-0.10.9-py2.py3-none-any.whl (198 kB)\n",
            "\u001b[K     |████████████████████████████████| 198 kB 69.1 MB/s \n",
            "\u001b[?25hBuilding wheels for collected packages: pyspark\n",
            "  Building wheel for pyspark (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for pyspark: filename=pyspark-3.1.2-py2.py3-none-any.whl size=212880768 sha256=cfb8d268e7dd12913edfff36c47f6e6b469df2d3bccc5c293f7ea42be396a240\n",
            "  Stored in directory: /root/.cache/pip/wheels/a5/0a/c1/9561f6fecb759579a7d863dcd846daaa95f598744e71b02c77\n",
            "Successfully built pyspark\n",
            "Installing collected packages: py4j, pyspark\n",
            "Successfully installed py4j-0.10.9 pyspark-3.1.2\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "0Dv4TiK7nuOY",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "87c8eabf-06f4-448e-ad07-c33d101c227d"
      },
      "source": [
        "from pyspark.sql import SparkSession\n",
        "from pyspark.ml.feature import StringIndexer, VectorAssembler\n",
        "from pyspark.ml.regression import LinearRegression\n",
        "from pyspark.ml.evaluation import RegressionEvaluator\n",
        "from pyspark.ml.classification import RandomForestClassifier\n",
        "from pyspark.ml.evaluation import MulticlassClassificationEvaluator\n",
        "from pyspark.ml.tuning import CrossValidator,ParamGridBuilder\n",
        "from sklearn.model_selection import train_test_split, GridSearchCV,cross_val_score\n",
        "from sklearn.model_selection import GridSearchCV\n",
        "from sklearn.metrics import mean_squared_error, r2_score\n",
        "import matplotlib.pyplot as plt\n",
        "from sklearn.preprocessing import scale \n",
        "from sklearn import model_selection\n",
        "from sklearn.tree import DecisionTreeRegressor, DecisionTreeClassifier\n",
        "from sklearn.neighbors import KNeighborsRegressor\n",
        "from sklearn.ensemble import BaggingRegressor\n",
        "\n",
        "\n",
        "spark = SparkSession.Builder().appName('Spark DataFrame Introduction').getOrCreate()\n",
        "\n",
        "leafDF = spark.read.option('inferSchema','true')\\\n",
        "                        .option('header','false')\\\n",
        "                        .option('delimiter',',').csv('leaf.csv')\n",
        "\n",
        "leafDF = leafDF.withColumnRenamed(\"_c0\",\"Class\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c1\",\"specimen_number\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c2\",\"Eccentricity\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c3\",\"Aspect_Ratio\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c4\",\"Elongation\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c5\",\"Solidity\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c6\",\"Stochastic_Convexity\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c7\",\"Isoperimetric_Factor\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c8\",\"Maximal_Indentation_Depth\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c9\",\"Lobedness\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c10\",\"Average_Intensity\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c11\",\"Average_Contrast\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c12\",\"Smoothness\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c13\",\"Third_moment\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c14\",\"Uniformity\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c15\",\"Entropy\")\n",
        "\n",
        "#### Asagidaki kodların ikisini de çalıştırıp 340 bulduğum için  data setimizin distinct olup olmadığını anlıyorum###\n",
        "\n",
        "#leafDF.count()\n",
        "#leafDF.distinct().count()\n",
        "\n",
        "### Asagidaki kod ile data setimde null değerler olup olmadığına max&min&standart sapma ile bagimli ve bagimsiz degiskenlerin durunlarını gozlemliyorum##\n",
        "\n",
        "#leafDF.describe().show()\n",
        "\n",
        "\n",
        "#leafDF.printSchema()  #Bu iki kod ile data setimdeki tüm değişkenlerin sayısal olduğundan emin oluyorum\n",
        "#leafDF.dtypes\n",
        "\n",
        "\n",
        "#leafDF = leafDF.dropna()       #data setimdeki eksik gözlemlerden kurtulmak için bu komutu kosturdum ama eksik gozlem yoktu\n",
        "\n",
        "vec = VectorAssembler(inputCols=leafDF.columns[1:15],outputCol='features')\n",
        "leafDF = vec.transform(leafDF)\n",
        "\n",
        "leafDF = leafDF.withColumnRenamed('Class','label')\n",
        "\n",
        "leafDF = leafDF.select('features','label')\n",
        "\n",
        "#leafDF.show()\n",
        "\n",
        "trainDF, testDF = leafDF.randomSplit([0.75,0.25],seed=1234)\n",
        "\n",
        "rf = RandomForestClassifier()\n",
        "eva = MulticlassClassificationEvaluator(metricName='accuracy')\n",
        "myParams = ParamGridBuilder().addGrid(rf.numTrees,[30,40,50,60,100])\\\n",
        "                            .addGrid(rf.maxDepth,[4,5,6])\\\n",
        "                            .addGrid(rf.impurity,['gini','entropy']).build()\n",
        "validator = CrossValidator(parallelism=4, \n",
        "                                 estimator=rf,\n",
        "                                 estimatorParamMaps=myParams,\n",
        "                                 evaluator=eva,\n",
        "                                 numFolds=5)\n",
        "model = validator.fit(trainDF)\n",
        "print(\"Best Model hesaplandı\")\n",
        "print(\"Best NumTrees : \", model.bestModel.getNumTrees)\n",
        "print(\"Best MaxDepth : \", model.bestModel.getMaxDepth())\n",
        "print(\"Best Impurity : \", model.bestModel.getImpurity())\n",
        "resultDF = model.transform(testDF)\n",
        "result = eva.evaluate(resultDF)\n",
        "print('Accuracy',result)"
      ],
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Best Model hesaplandı\n",
            "Best NumTrees :  30\n",
            "Best MaxDepth :  6\n",
            "Best Impurity :  entropy\n",
            "Accuracy 0.6222222222222222\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "nTCD0sMaT0ne",
        "outputId": "dbcd39a5-0fdc-4d76-e473-317a589b572e"
      },
      "source": [
        "from pyspark.sql import SparkSession\n",
        "from pyspark.ml.feature import VectorAssembler\n",
        "from pyspark.ml.evaluation import RegressionEvaluator\n",
        "from pyspark.ml.classification import DecisionTreeClassifier\n",
        "from pyspark.ml.evaluation import MulticlassClassificationEvaluator\n",
        "from pyspark.ml.tuning import CrossValidator,ParamGridBuilder\n",
        "from sklearn.model_selection import train_test_split, GridSearchCV,cross_val_score\n",
        "from sklearn.model_selection import GridSearchCV\n",
        "from sklearn.metrics import mean_squared_error, r2_score\n",
        "from sklearn import model_selection\n",
        "from pyspark.ml.regression import DecisionTreeRegressor\n",
        "\n",
        "\n",
        "spark = SparkSession.Builder().appName('Spark DataFrame Introduction').getOrCreate()\n",
        "\n",
        "leafDF = spark.read.option('inferSchema','true')\\\n",
        "                        .option('header','false')\\\n",
        "                        .option('delimiter',',').csv('leaf.csv')\n",
        "\n",
        "leafDF = leafDF.withColumnRenamed(\"_c0\",\"Class\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c1\",\"specimen_number\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c2\",\"Eccentricity\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c3\",\"Aspect_Ratio\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c4\",\"Elongation\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c5\",\"Solidity\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c6\",\"Stochastic_Convexity\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c7\",\"Isoperimetric_Factor\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c8\",\"Maximal_Indentation_Depth\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c9\",\"Lobedness\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c10\",\"Average_Intensity\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c11\",\"Average_Contrast\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c12\",\"Smoothness\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c13\",\"Third_moment\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c14\",\"Uniformity\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c15\",\"Entropy\")\n",
        "\n",
        "#### Asagidaki kodların ikisini de çalıştırıp 340 bulduğum için  data setimizin distinct olup olmadığını anlıyorum###\n",
        "\n",
        "#leafDF.count()\n",
        "#leafDF.distinct().count()\n",
        "\n",
        "### Asagidaki kod ile data setimde null değerler olup olmadığına max&min&standart sapma ile bagimli ve bagimsiz degiskenlerin durunlarını gozlemliyorum##\n",
        "\n",
        "#leafDF.describe().show()\n",
        "\n",
        "\n",
        "#leafDF.printSchema()  #Bu iki kod ile data setimdeki tüm değişkenlerin sayısal olduğundan emin oluyorum\n",
        "#leafDF.dtypes\n",
        "\n",
        "\n",
        "#leafDF = leafDF.dropna()       #data setimdeki eksik gözlemlerden kurtulmak için bu komutu kosturdum ama eksik gozlem yoktu\n",
        "\n",
        "vec = VectorAssembler(inputCols=leafDF.columns[1:15],outputCol='features')\n",
        "leafDF = vec.transform(leafDF)\n",
        "\n",
        "leafDF = leafDF.withColumnRenamed('Class','label')\n",
        "\n",
        "leafDF = leafDF.select('features','label')\n",
        "\n",
        "#leafDF.show()\n",
        "\n",
        "trainDF, testDF = leafDF.randomSplit([0.75,0.25],seed=1234)\n",
        "\n",
        "dt = DecisionTreeRegressor(labelCol=\"label\", featuresCol=\"features\")\n",
        "\n",
        "eva = MulticlassClassificationEvaluator(metricName='accuracy')\n",
        "\n",
        "\n",
        "\n",
        "myParams = (ParamGridBuilder()\n",
        "             #.addGrid(dt.maxDepth, [10, 20, 30])            \n",
        "             #.addGrid(dt.maxDepth, [2, 5, 10])\n",
        "             .addGrid(dt.maxBins, [10, 20, 40, 80, 100])            \n",
        "             #.addGrid(dt.maxBins, [10, 20])\n",
        "             .build())\n",
        "\n",
        "# Evaluate model\n",
        "dtevaluator = RegressionEvaluator(predictionCol=\"prediction\", labelCol=\"label\", metricName=\"rmse\")\n",
        "\n",
        "\n",
        "\n",
        "validator = CrossValidator(estimator = dt,\n",
        "                      estimatorParamMaps = myParams,\n",
        "                      evaluator = dtevaluator,\n",
        "                      numFolds = 5)\n",
        "model = validator.fit(trainDF)\n",
        "\n",
        "print(\"Best Model hesaplandı\")\n",
        "\n",
        "print(model)\n",
        "\n",
        "resultDF = model.transform(testDF)\n",
        "result = eva.evaluate(resultDF)\n",
        "print('Accuracy',result)\n",
        "\n"
      ],
      "execution_count": 51,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Best Model hesaplandı\n",
            "CrossValidatorModel_f8f64b5ef5ef\n",
            "Accuracy 0.4444444444444444\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 374
        },
        "id": "8Z9zvBcfob-T",
        "outputId": "f075c6d5-5adc-41d6-b06a-6080a3f5d060"
      },
      "source": [
        "from pyspark.sql import SparkSession\n",
        "import numpy as np\n",
        "from pyspark.ml.feature import VectorAssembler\n",
        "from pyspark.ml.evaluation import RegressionEvaluator\n",
        "from pyspark.ml.classification import DecisionTreeClassifier\n",
        "from pyspark.ml.evaluation import MulticlassClassificationEvaluator\n",
        "from pyspark.ml.tuning import CrossValidator,ParamGridBuilder\n",
        "from sklearn.model_selection import train_test_split, GridSearchCV,cross_val_score\n",
        "from sklearn.model_selection import GridSearchCV\n",
        "from sklearn.metrics import mean_squared_error, r2_score\n",
        "from sklearn import model_selection\n",
        "from pyspark.ml.regression import DecisionTreeRegressor\n",
        "from pyspark.ml.classification import LogisticRegression\n",
        "\n",
        "spark = SparkSession.Builder().appName('Spark DataFrame Introduction').getOrCreate()\n",
        "\n",
        "leafDF = spark.read.option('inferSchema','true')\\\n",
        "                        .option('header','false')\\\n",
        "                        .option('delimiter',',').csv('leaf.csv')\n",
        "\n",
        "leafDF = leafDF.withColumnRenamed(\"_c0\",\"Class\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c1\",\"specimen_number\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c2\",\"Eccentricity\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c3\",\"Aspect_Ratio\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c4\",\"Elongation\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c5\",\"Solidity\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c6\",\"Stochastic_Convexity\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c7\",\"Isoperimetric_Factor\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c8\",\"Maximal_Indentation_Depth\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c9\",\"Lobedness\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c10\",\"Average_Intensity\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c11\",\"Average_Contrast\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c12\",\"Smoothness\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c13\",\"Third_moment\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c14\",\"Uniformity\")\n",
        "leafDF = leafDF.withColumnRenamed(\"_c15\",\"Entropy\")\n",
        "\n",
        "#### Asagidaki kodların ikisini de çalıştırıp 340 bulduğum için  data setimizin distinct olup olmadığını anlıyorum###\n",
        "\n",
        "#leafDF.count()\n",
        "#leafDF.distinct().count()\n",
        "\n",
        "### Asagidaki kod ile data setimde null değerler olup olmadığına max&min&standart sapma ile bagimli ve bagimsiz degiskenlerin durunlarını gozlemliyorum##\n",
        "\n",
        "#leafDF.describe().show()\n",
        "\n",
        "\n",
        "#leafDF.printSchema()  #Bu iki kod ile data setimdeki tüm değişkenlerin sayısal olduğundan emin oluyorum\n",
        "#leafDF.dtypes\n",
        "\n",
        "\n",
        "#leafDF = leafDF.dropna()       #data setimdeki eksik gözlemlerden kurtulmak için bu komutu kosturdum ama eksik gozlem yoktu\n",
        "\n",
        "vec = VectorAssembler(inputCols=leafDF.columns[1:15],outputCol='features')\n",
        "leafDF = vec.transform(leafDF)\n",
        "\n",
        "leafDF = leafDF.withColumnRenamed('Class','label')\n",
        "\n",
        "leafDF = leafDF.select('features','label')\n",
        "\n",
        "#leafDF.show()\n",
        "\n",
        "trainDF, testDF = leafDF.randomSplit([0.75,0.25],seed=1234)\n",
        "\n",
        "lr = LogisticRegression()\n",
        "\n",
        "penalty = ['11','12']\n",
        "\n",
        "C = np.logspace(0,4,10)\n",
        "\n",
        "hyperparameters = dict(C=C,penalty=penalty)\n",
        "\n",
        "\n",
        "clf = GridSearchCV(lr, hyperparameters, cv=5, verbose=0)\n",
        "\n",
        "model = clf.fit(trainDF)\n",
        "\n",
        "\n",
        "print(\"Best Model hesaplandı\")\n",
        "\n",
        "\n",
        "\n",
        "resultDF = model.transform(testDF)\n",
        "result = eva.evaluate(resultDF)\n",
        "print('Accuracy',result)\n"
      ],
      "execution_count": 53,
      "outputs": [
        {
          "output_type": "error",
          "ename": "TypeError",
          "evalue": "ignored",
          "traceback": [
            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
            "\u001b[0;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
            "\u001b[0;32m<ipython-input-53-eca223b2c4ff>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m     72\u001b[0m \u001b[0mclf\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mGridSearchCV\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlr\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mhyperparameters\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcv\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m5\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mverbose\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     73\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 74\u001b[0;31m \u001b[0mmodel\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mclf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtrainDF\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     75\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     76\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;36mfit\u001b[0;34m(self, X, y, groups, **fit_params)\u001b[0m\n\u001b[1;32m    627\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    628\u001b[0m         scorers, self.multimetric_ = _check_multimetric_scoring(\n\u001b[0;32m--> 629\u001b[0;31m             self.estimator, scoring=self.scoring)\n\u001b[0m\u001b[1;32m    630\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    631\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmultimetric_\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/metrics/_scorer.py\u001b[0m in \u001b[0;36m_check_multimetric_scoring\u001b[0;34m(estimator, scoring)\u001b[0m\n\u001b[1;32m    471\u001b[0m     if callable(scoring) or scoring is None or isinstance(scoring,\n\u001b[1;32m    472\u001b[0m                                                           str):\n\u001b[0;32m--> 473\u001b[0;31m         \u001b[0mscorers\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m{\u001b[0m\u001b[0;34m\"score\"\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mcheck_scoring\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mestimator\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mscoring\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mscoring\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    474\u001b[0m         \u001b[0;32mreturn\u001b[0m \u001b[0mscorers\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;32mFalse\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    475\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;32m/usr/local/lib/python3.7/dist-packages/sklearn/metrics/_scorer.py\u001b[0m in \u001b[0;36mcheck_scoring\u001b[0;34m(estimator, scoring, allow_none)\u001b[0m\n\u001b[1;32m    424\u001b[0m                 \u001b[0;34m\"If no scoring is specified, the estimator passed should \"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    425\u001b[0m                 \u001b[0;34m\"have a 'score' method. The estimator %r does not.\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 426\u001b[0;31m                 % estimator)\n\u001b[0m\u001b[1;32m    427\u001b[0m     \u001b[0;32melif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mscoring\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mIterable\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    428\u001b[0m         raise ValueError(\"For evaluating multiple scores, use \"\n",
            "\u001b[0;31mTypeError\u001b[0m: If no scoring is specified, the estimator passed should have a 'score' method. The estimator LogisticRegression_bc075a396bf3 does not."
          ]
        }
      ]
    }
  ]
}