chilaka_7088cem_cw.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "source": [
        "# ALE Prediction with MLP Regression models\n"
      ],
      "metadata": {
        "id": "-f9nAiuTzs6P"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Load Dataset"
      ],
      "metadata": {
        "id": "K3Fx3gFJ0DjR"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 134,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "Hnx1f1SbtCWF",
        "outputId": "b00cdea1-4dff-45f8-807c-5821d44e9938"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "   anchor_ratio  trans_range  node_density  iterations       ale    sd_ale\n",
              "0            30           15           200          40  0.773546  0.250555\n",
              "1            15           15           100          70  0.911941  0.498329\n",
              "2            30           15           100          50  0.814867  0.255546\n",
              "3            15           20           100          20  1.435332  0.394603\n",
              "4            30           15           100          40  1.265909  0.302943"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-ad4387bd-4aa1-47c1-9ff0-5a2cbab2241f\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <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>anchor_ratio</th>\n",
              "      <th>trans_range</th>\n",
              "      <th>node_density</th>\n",
              "      <th>iterations</th>\n",
              "      <th>ale</th>\n",
              "      <th>sd_ale</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>30</td>\n",
              "      <td>15</td>\n",
              "      <td>200</td>\n",
              "      <td>40</td>\n",
              "      <td>0.773546</td>\n",
              "      <td>0.250555</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>15</td>\n",
              "      <td>15</td>\n",
              "      <td>100</td>\n",
              "      <td>70</td>\n",
              "      <td>0.911941</td>\n",
              "      <td>0.498329</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>30</td>\n",
              "      <td>15</td>\n",
              "      <td>100</td>\n",
              "      <td>50</td>\n",
              "      <td>0.814867</td>\n",
              "      <td>0.255546</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>15</td>\n",
              "      <td>20</td>\n",
              "      <td>100</td>\n",
              "      <td>20</td>\n",
              "      <td>1.435332</td>\n",
              "      <td>0.394603</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>30</td>\n",
              "      <td>15</td>\n",
              "      <td>100</td>\n",
              "      <td>40</td>\n",
              "      <td>1.265909</td>\n",
              "      <td>0.302943</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-ad4387bd-4aa1-47c1-9ff0-5a2cbab2241f')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-ad4387bd-4aa1-47c1-9ff0-5a2cbab2241f button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-ad4387bd-4aa1-47c1-9ff0-5a2cbab2241f');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 134
        }
      ],
      "source": [
        "import numpy as np\n",
        "import pandas as pd\n",
        "from sklearn import metrics\n",
        "from sklearn.model_selection import train_test_split\n",
        "import matplotlib.pyplot as plt\n",
        "import seaborn as sns\n",
        "\n",
        "%matplotlib inline\n",
        "\n",
        "# load dataset\n",
        "filename = \"/content/mcs_ds_edited_iter_shuffled.csv\"\n",
        "df=pd.read_csv(filename)\n",
        "\n",
        "df.head(5)"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### Analyse features and shape of dataframe"
      ],
      "metadata": {
        "id": "FMn6W9ib0YEd"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "df.info"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "mT6-MdhHVV7u",
        "outputId": "02294e1f-ff95-40a7-9af5-249d5fd70965"
      },
      "execution_count": 135,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<bound method DataFrame.info of      anchor_ratio  trans_range  node_density  iterations       ale    sd_ale\n",
              "0              30           15           200          40  0.773546  0.250555\n",
              "1              15           15           100          70  0.911941  0.498329\n",
              "2              30           15           100          50  0.814867  0.255546\n",
              "3              15           20           100          20  1.435332  0.394603\n",
              "4              30           15           100          40  1.265909  0.302943\n",
              "..            ...          ...           ...         ...       ...       ...\n",
              "102            18           23           100          20  1.287472  0.375227\n",
              "103            14           17           200          60  0.899102  0.231822\n",
              "104            15           20           100          50  1.171140  0.372001\n",
              "105            20           20           100          40  1.234493  0.599834\n",
              "106            15           15           200          40  0.635426  0.139791\n",
              "\n",
              "[107 rows x 6 columns]>"
            ]
          },
          "metadata": {},
          "execution_count": 135
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### Check dataframe for null values"
      ],
      "metadata": {
        "id": "yieJ3Dzw0QfJ"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "df.isnull().any()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "1gKtnpBGyTRH",
        "outputId": "f773732e-1d3d-4dec-d0d3-966ff300bf56"
      },
      "execution_count": 136,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "anchor_ratio    False\n",
              "trans_range     False\n",
              "node_density    False\n",
              "iterations      False\n",
              "ale             False\n",
              "sd_ale          False\n",
              "dtype: bool"
            ]
          },
          "metadata": {},
          "execution_count": 136
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Split dataset into training data and testing data (80% training, 20% testing)"
      ],
      "metadata": {
        "id": "MN3wne520hsp"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Spliting data into Features and predictand\n",
        "X=df[['anchor_ratio', 'trans_range', 'node_density', 'iterations']]\n",
        "y=df['ale']\n",
        "\n",
        "# Split dataset into training set and test set, 80% training and 20% test\n",
        "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=1)"
      ],
      "metadata": {
        "id": "C-A2F-_OunCN"
      },
      "execution_count": 137,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Define function for Method 1 MLP Regression model"
      ],
      "metadata": {
        "id": "42DvP0FD01AZ"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.preprocessing import StandardScaler, MaxAbsScaler\n",
        "from sklearn.pipeline import make_pipeline\n",
        "from sklearn.neural_network import MLPRegressor\n",
        "\n",
        "# Function contains method 1 regression model pipline, evaulation metrics and scatter plot\n",
        "def mlppipe(X_train,X_test,y_train,y_test):\n",
        "  mlp = make_pipeline(\n",
        "      StandardScaler(),\n",
        "      MLPRegressor(hidden_layer_sizes=(12, 6), random_state=15, \n",
        "                   activation='tanh', solver='lbfgs',max_iter=204),\n",
        "  )\n",
        "  mlp.fit(X_train,y_train)\n",
        "  exp_y  = y_test\n",
        "  pred_y = mlp.predict(X_test)\n",
        "  print(\"r2 score= \", metrics.r2_score(exp_y, pred_y))\n",
        "  print(\"mean sqrd log err= \", metrics.mean_squared_log_error(exp_y, pred_y))\n",
        "  print(\"rmse =\", metrics.mean_squared_error(exp_y, pred_y, squared=False))\n",
        "  plt.figure(figsize=(10,10))\n",
        "  sns.regplot(exp_y, pred_y, fit_reg=True, scatter_kws={\"s\": 125})\n"
      ],
      "metadata": {
        "id": "wvUAlwT13NDV"
      },
      "execution_count": 138,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Define function for Method 2 MLP Regression model"
      ],
      "metadata": {
        "id": "0dxJsSn-1R-X"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Function contains method 2 regression model pipline, evaulation metrics and scatter plot\n",
        "def mamlppipe(X_train,X_test,y_train,y_test):\n",
        "  mamlp = make_pipeline(\n",
        "        MaxAbsScaler(),\n",
        "        MLPRegressor(hidden_layer_sizes=(12, 6), random_state=15, \n",
        "                    activation='tanh', solver='lbfgs',max_iter=204),\n",
        "    )\n",
        "  mamlp.fit(X_train,y_train)\n",
        "  exp_y  = y_test\n",
        "  pred_y = mamlp.predict(X_test)\n",
        "  print(\"r2 score= \", metrics.r2_score(exp_y, pred_y))\n",
        "  print(\"mean sqrd log err= \", metrics.mean_squared_log_error(exp_y, pred_y))\n",
        "  print(\"rmse =\", metrics.mean_squared_error(exp_y, pred_y, squared=False))\n",
        "  plt.figure(figsize=(10,10))\n",
        "  sns.regplot(exp_y, pred_y, fit_reg=True, scatter_kws={\"s\": 125})"
      ],
      "metadata": {
        "id": "mrRtSOblJFjU"
      },
      "execution_count": 139,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "### Method 1 results and Scatter Plot"
      ],
      "metadata": {
        "id": "LxpNz02WLb3_"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Display Method 1 results\n",
        "print('Results for Standard Scaled data: \\n')\n",
        "mlppipe(X_train,X_test,y_train,y_test)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 852
        },
        "id": "pzERcBgR5e5R",
        "outputId": "c956092d-6cc6-443e-eb3d-2206a8c6c1f4"
      },
      "execution_count": 140,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Results for Standard Scaled data: \n",
            "\n",
            "r2 score=  0.5618865477413895\n",
            "mean sqrd log err=  0.009957664776347337\n",
            "rmse = 0.20084428776208\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.8/dist-packages/sklearn/neural_network/_multilayer_perceptron.py:541: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
            "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
            "\n",
            "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
            "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
            "  self.n_iter_ = _check_optimize_result(\"lbfgs\", opt_res, self.max_iter)\n",
            "/usr/local/lib/python3.8/dist-packages/seaborn/_decorators.py:36: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.\n",
            "  warnings.warn(\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 720x720 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### Method 2 results and scatterplot"
      ],
      "metadata": {
        "id": "mrRWbjKPLT_v"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Display Method 2 results\n",
        "print('Results for Max Absolute Scaled data: \\n')\n",
        "mamlppipe(X_train,X_test,y_train,y_test)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 852
        },
        "id": "NINM_w7SLKJw",
        "outputId": "c349a31e-fafa-48c1-fd1e-2fee3ea60aec"
      },
      "execution_count": 141,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Results for Max Absolute Scaled data: \n",
            "\n",
            "r2 score=  0.8063502154220884\n",
            "mean sqrd log err=  0.004067404844870628\n",
            "rmse = 0.13352872413004094\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.8/dist-packages/sklearn/neural_network/_multilayer_perceptron.py:541: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
            "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
            "\n",
            "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
            "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
            "  self.n_iter_ = _check_optimize_result(\"lbfgs\", opt_res, self.max_iter)\n",
            "/usr/local/lib/python3.8/dist-packages/seaborn/_decorators.py:36: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.\n",
            "  warnings.warn(\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 720x720 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    }
  ]
}