TF_Forum_11404.ipynb

tf_forum_11404.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "authorship_tag": "ABX9TyMWeJfNXq8JqdlZk0IGFCoN",
      "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/gist/kiransair/f8c5bae4c4d95562520e4ba527a460dc/tf_forum_11404.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 2,
      "metadata": {
        "id": "9pvWAFpCGsKC"
      },
      "outputs": [],
      "source": [
        "import csv\n",
        "import pandas as pd\n",
        "import tensorflow as tf"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "data = [\n",
        "    {'gender': 'M', 'products': [1, 2]},\n",
        "    {'gender': 'M', 'products': [1, 7, 5, 8]}\n",
        "]"
      ],
      "metadata": {
        "id": "rmLW7W7QGys2"
      },
      "execution_count": 3,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "file_name = 'tset.csv'"
      ],
      "metadata": {
        "id": "ZlcaiiL6G524"
      },
      "execution_count": 4,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "with open(file_name, mode='w', newline='') as file:\n",
        "    writer = csv.DictWriter(file, fieldnames=['gender', 'products'])\n",
        "    writer.writeheader()\n",
        "    for row in data:\n",
        "      writer.writerow(row)\n"
      ],
      "metadata": {
        "id": "YhiEcDhOG7rt"
      },
      "execution_count": 5,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "data=pd.read_csv('/content/tset.csv')"
      ],
      "metadata": {
        "id": "MhKkYCojG9JK"
      },
      "execution_count": 6,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "ds = tf.data.Dataset.from_tensor_slices((data['gender'].values, data['products'].values))"
      ],
      "metadata": {
        "id": "I3-HtzhzG--M"
      },
      "execution_count": 7,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "def convert_to_ragged(gender, products):\n",
        "    products = tf.strings.regex_replace(products, \"[\\[\\]']\", \"\")\n",
        "    split_products = tf.strings.split(products, ',')\n",
        "    ragged_tensor = tf.RaggedTensor.from_row_lengths(split_products, row_lengths=tf.strings.length(split_products))\n",
        "    return gender, ragged_tensor"
      ],
      "metadata": {
        "id": "Ab3KchTRHA9c"
      },
      "execution_count": 8,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "rds = ds.map(convert_to_ragged)"
      ],
      "metadata": {
        "id": "bXeSpIAmHCzv"
      },
      "execution_count": 9,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "rds"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "PbPWwYAaHFEL",
        "outputId": "8c6b1a53-6d29-46a0-e704-7c660493e894"
      },
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<_MapDataset element_spec=(TensorSpec(shape=(), dtype=tf.string, name=None), RaggedTensorSpec(TensorShape([None, None]), tf.string, 1, tf.int32))>"
            ]
          },
          "metadata": {},
          "execution_count": 10
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "K701nYogHF2o"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}