SO 51469446 bounty.ipynb

so-51469446-bounty.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "SO 51469446 bounty.ipynb",
      "version": "0.3.2",
      "provenance": [],
      "collapsed_sections": [],
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/gist/shadiakiki1986/173dd44fd7fec7c202605c596069e604/so-51469446-bounty.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "metadata": {
        "id": "BTeyQ8XeGt3H",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "# https://stackoverflow.com/questions/51469446/keras-and-error-setting-an-array-element-with-a-sequence\n",
        "from keras.models import Sequential\n",
        "from keras.layers import Dense\n",
        "from keras.optimizers import RMSprop\n",
        "\n",
        "def network():\n",
        "        model = Sequential()\n",
        "        model.add(Dense(units=50, activation='relu', input_dim=8)) # <<< input_dim is now 8\n",
        "        model.add(Dense(units=50, activation='relu'))\n",
        "        model.add(Dense(units=50, activation='relu'))\n",
        "        model.add(Dense(units=1, activation='softmax'))\n",
        "        opt = RMSprop(lr=0.00025)\n",
        "        model.compile(loss='mse', optimizer=opt)\n",
        "        return model\n",
        "\n",
        "      \n",
        "      \n",
        "      \n",
        "import pandas as pd\n",
        "import random\n",
        "\n",
        "data = pd.DataFrame()\n",
        "state = [0]*3\n",
        "for i in range(3):\n",
        "    state[i]= random.choice([True, False])\n",
        "move = random.randint(1,4)\n",
        "reward = random.choice([-1, -10, 10])\n",
        "future_state = [0]*3\n",
        "for i in range(3):\n",
        "    future_state[i] = random.choice([True, False])\n",
        "Q = 1\n",
        "\n",
        "# Flatten the arrays here\n",
        "#\n",
        "#        vvvvvvvvvvvvvvvvvvvvvvvvvvvv                vvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvv\n",
        "#        vvvvvvvvvvvvvvvvvvvvvvvvvvvv                vvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvv\n",
        "array = [state[0], state[1], state[2], move, reward, future_state[0], future_state[1], future_state[2], Q]\n",
        "\n",
        "data = data.append([array])\n",
        "\n",
        "idx_target = len(array)-1 # <<< index of target is the last one\n",
        "training = data.drop([idx_target], axis = 1)\n",
        "target = data[idx_target]"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "cSZ_nngMHo1i",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 35
        },
        "outputId": "8de3f127-6996-4b87-8ae0-48740b03b606"
      },
      "cell_type": "code",
      "source": [
        "array"
      ],
      "execution_count": 20,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[False, False, True, 4, -10, False, True, False, 1]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 20
        }
      ]
    },
    {
      "metadata": {
        "id": "WGJMyG5PHhBN",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 80
        },
        "outputId": "1559166e-d29f-4249-c570-86b01987a835"
      },
      "cell_type": "code",
      "source": [
        "training"
      ],
      "execution_count": 21,
      "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>0</th>\n",
              "      <th>1</th>\n",
              "      <th>2</th>\n",
              "      <th>3</th>\n",
              "      <th>4</th>\n",
              "      <th>5</th>\n",
              "      <th>6</th>\n",
              "      <th>7</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>False</td>\n",
              "      <td>False</td>\n",
              "      <td>True</td>\n",
              "      <td>4</td>\n",
              "      <td>-10</td>\n",
              "      <td>False</td>\n",
              "      <td>True</td>\n",
              "      <td>False</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "       0      1     2  3   4      5     6      7\n",
              "0  False  False  True  4 -10  False  True  False"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 21
        }
      ]
    },
    {
      "metadata": {
        "id": "vq78ey1eHjjY",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 53
        },
        "outputId": "27856fc7-70b1-4eb2-841c-6adf7f4f123e"
      },
      "cell_type": "code",
      "source": [
        "target"
      ],
      "execution_count": 22,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0    1\n",
              "Name: 8, dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 22
        }
      ]
    },
    {
      "metadata": {
        "id": "80OCrqsEHhJf",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 107
        },
        "outputId": "d99db3f5-7b42-44b0-a056-f5b7a72813f7"
      },
      "cell_type": "code",
      "source": [
        "model = network()\n",
        "model.fit(training,target,epochs=2)"
      ],
      "execution_count": 23,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Epoch 1/2\n",
            "1/1 [==============================] - 0s 400ms/step - loss: 0.0000e+00\n",
            "Epoch 2/2\n",
            "1/1 [==============================] - 0s 2ms/step - loss: 0.0000e+00\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<keras.callbacks.History at 0x7fb5cea17630>"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 23
        }
      ]
    },
    {
      "metadata": {
        "id": "wHYj5f2fG9ZX",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        ""
      ],
      "execution_count": 0,
      "outputs": []
    }
  ]
}