ludwig-ai--ludwig/examples/wine_quality/model_defaults_example.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import logging\n",
    "import os\n",
    "import shutil\n",
    "from pprint import pprint\n",
    "\n",
    "import pandas as pd\n",
    "\n",
    "from ludwig.api import LudwigModel"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Receive data for training"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "train_df = pd.read_csv(\"./data/winequalityN.csv\")\n",
    "train_df[\"quality\"] = train_df[\"quality\"].apply(str)\n",
    "train_df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Replace white space in column names with underscore\n",
    "new_col = []\n",
    "for i in range(len(train_df.columns)):\n",
    "    new_col.append(train_df.columns[i].replace(\" \", \"_\"))\n",
    "\n",
    "train_df.columns = new_col"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "train_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "train_df.describe().T"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "train_df.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "train_df[\"quality\"].value_counts().sort_index()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = list(set(train_df.columns) - set([\"quality\"]))\n",
    "features = train_df[cols]\n",
    "\n",
    "# extract categorical features\n",
    "categorical_features = []\n",
    "for p in features:\n",
    "    if train_df[p].dtype == \"object\":\n",
    "        categorical_features.append(p)\n",
    "\n",
    "print(\"categorical features:\", categorical_features, \"\\n\")\n",
    "\n",
    "# get numerical features\n",
    "numerical_features = list(set(features) - set(categorical_features))\n",
    "\n",
    "print(\"numerical features:\", numerical_features, \"\\n\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "for feature in categorical_features:\n",
    "    print(f\"# of distinct values in categorical feature '{feature}' : {train_df[feature].nunique()}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Create Ludwig Config"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# template for config\n",
    "config = {\"input_features\": [], \"output_features\": [], \"trainer\": {}}\n",
    "\n",
    "# setup input features for categorical features\n",
    "for p in categorical_features:\n",
    "    a_feature = {\"name\": p.replace(\" \", \"_\"), \"type\": \"category\"}\n",
    "    config[\"input_features\"].append(a_feature)\n",
    "\n",
    "# setup input features for numerical features\n",
    "for p in numerical_features:\n",
    "    a_feature = {\"name\": p.replace(\" \", \"_\"), \"type\": \"number\"}\n",
    "    config[\"input_features\"].append(a_feature)\n",
    "\n",
    "# set up output variable\n",
    "config[\"output_features\"].append({\"name\": \"quality\", \"type\": \"category\"})\n",
    "\n",
    "# set default preprocessing and encoder for numerical features\n",
    "config[\"defaults\"] = {\n",
    "    \"number\": {\n",
    "        \"preprocessing\": {\"missing_value_strategy\": \"fill_with_mean\", \"normalization\": \"zscore\"},\n",
    "        \"encoder\": {\"type\": \"dense\", \"num_layers\": 2},\n",
    "    },\n",
    "    \"category\": {\"encoder\": {\"type\": \"sparse\"}, \"decoder\": {\"top_k\": 2}, \"loss\": {\"confidence_penalty\": 0.1}},\n",
    "}\n",
    "\n",
    "# set up trainer\n",
    "config[\"trainer\"] = {\"epochs\": 5}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "pprint(config, indent=2)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Initialize and Train LudwigModel"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "model = LudwigModel(config, backend=\"local\", logging_level=logging.INFO)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Inspecting Config After Model Initialization"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "pprint(model.config[\"input_features\"], indent=2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "pprint(model.config[\"output_features\"], indent=2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "eval_stats, train_stats, _, _ = model.experiment(dataset=train_df, experiment_name=\"wine_quality\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Cleanup"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "try:\n",
    "    shutil.rmtree(\"./results\")\n",
    "    items = os.listdir(\"./\")\n",
    "    for item in items:\n",
    "        if item.endswith(\".hdf5\") or item.endswith(\".json\") or item == \".lock_preprocessing\":\n",
    "            os.remove(os.path.join(\"./\", item))\n",
    "except Exception:\n",
    "    pass"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.8.13 64-bit",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.13"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "949777d72b0d2535278d3dc13498b2535136f6dfe0678499012e853ee9abcab1"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}