{
    "cells": [
        {
            "attachments": {},
            "cell_type": "markdown",
            "id": "1dd265b7",
            "metadata": {},
            "source": [
                "(tune-analysis-guide)=\n",
                "\n",
                "# Analyzing Tune Experiment Results\n",
                "\n",
                "In this guide, we'll walk through some common workflows of what analysis you might want to perform after running your Tune experiment with `tuner.fit()`.\n",
                "\n",
                "1. Loading Tune experiment results from a directory\n",
                "2. Basic *experiment-level* analysis: get a quick overview of how trials performed\n",
                "3. Basic *trial-level* analysis: access individual trial hyperparameter configs and last reported metrics\n",
                "4. Plotting the entire history of reported metrics for a trial\n",
                "5. Accessing saved checkpoints (assuming that you have enabled checkpointing) and loading into a model for test inference\n",
                "\n",
                "```python\n",
                "result_grid: ResultGrid = tuner.fit()\n",
                "best_result: Result = result_grid.get_best_result()\n",
                "```\n",
                "\n",
                "The output of `tuner.fit()` is a [`ResultGrid`](result-grid-docstring), which is a collection of [`Result`](result-docstring) objects. See the linked documentation references for [`ResultGrid`](result-grid-docstring) and [`Result`](result-docstring) for more details on what attributes are available.\n",
                "\n",
                "Let's start by performing a hyperparameter search with the MNIST PyTorch example. The training function is defined {doc}`here </tune/examples/includes/mnist_pytorch>`, and we pass it into a `Tuner` to start running the trials in parallel."
            ]
        },
        {
            "cell_type": "code",
            "execution_count": null,
            "id": "8479d7d2",
            "metadata": {},
            "outputs": [],
            "source": [
                "from ray import tune, air\n",
                "from ray.tune.examples.mnist_pytorch import train_mnist\n",
                "from ray.tune import ResultGrid\n",
                "\n",
                "storage_path = \"/tmp/ray_results\"\n",
                "exp_name = \"tune_analyzing_results\"\n",
                "tuner = tune.Tuner(\n",
                "    train_mnist,\n",
                "    param_space={\n",
                "        \"lr\": tune.loguniform(0.001, 0.1),\n",
                "        \"momentum\": tune.grid_search([0.8, 0.9, 0.99]),\n",
                "        \"should_checkpoint\": True,\n",
                "    },\n",
                "    run_config=air.RunConfig(\n",
                "        name=exp_name,\n",
                "        stop={\"training_iteration\": 100},\n",
                "        checkpoint_config=air.CheckpointConfig(\n",
                "            checkpoint_score_attribute=\"mean_accuracy\",\n",
                "            num_to_keep=5,\n",
                "        ),\n",
                "        storage_path=storage_path,\n",
                "    ),\n",
                "    tune_config=tune.TuneConfig(mode=\"max\", metric=\"mean_accuracy\", num_samples=3),\n",
                ")\n",
                "result_grid: ResultGrid = tuner.fit()"
            ]
        },
        {
            "attachments": {},
            "cell_type": "markdown",
            "id": "a18a988c",
            "metadata": {},
            "source": [
                "## Loading experiment results from an directory\n",
                "\n",
                "Although we have the `result_grid` object in memory because we just ran the Tune experiment above, we might be performing this analysis after our initial training script has exited. We can retrieve the `ResultGrid` from a [restored `Tuner`](tune-stopping-guide), passing in the experiment directory, which should look something like `~/ray_results/{exp_name}`. If you don't specify an experiment `name` in the `RunConfig`, the experiment name will be auto-generated and can be found in the logs of your experiment."
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 19,
            "id": "92ded070",
            "metadata": {},
            "outputs": [
                {
                    "name": "stdout",
                    "output_type": "stream",
                    "text": [
                        "Loading results from /tmp/ray_results/tune_analyzing_results...\n"
                    ]
                },
                {
                    "name": "stderr",
                    "output_type": "stream",
                    "text": [
                        "2022-10-17 16:04:54,189\tINFO experiment_analysis.py:795 -- No `self.trials`. Drawing logdirs from checkpoint file. This may result in some information that is out of sync, as checkpointing is periodic.\n"
                    ]
                }
            ],
            "source": [
                "experiment_path = f\"{storage_path}/{exp_name}\"\n",
                "print(f\"Loading results from {experiment_path}...\")\n",
                "\n",
                "restored_tuner = tune.Tuner.restore(experiment_path, trainable=train_mnist)\n",
                "result_grid = restored_tuner.get_results()"
            ]
        },
        {
            "attachments": {},
            "cell_type": "markdown",
            "id": "ea5085c8",
            "metadata": {},
            "source": [
                "## Experiment-level Analysis: Working with `ResultGrid`"
            ]
        },
        {
            "attachments": {},
            "cell_type": "markdown",
            "id": "a7182cd1",
            "metadata": {},
            "source": [
                "The first thing we might want to check is if there were any erroring trials."
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 3,
            "id": "008a8df7",
            "metadata": {},
            "outputs": [
                {
                    "name": "stdout",
                    "output_type": "stream",
                    "text": [
                        "No errors!\n"
                    ]
                }
            ],
            "source": [
                "# Check if there have been errors\n",
                "if result_grid.errors:\n",
                "    print(\"One of the trials failed!\")\n",
                "else:\n",
                "    print(\"No errors!\")"
            ]
        },
        {
            "attachments": {},
            "cell_type": "markdown",
            "id": "c95f6cef",
            "metadata": {},
            "source": [
                "Note that `ResultGrid` is an iterable, and we can access its length and index into it to access individual `Result` objects.\n",
                "\n",
                "We should have **9** results in this example, since we have 3 samples for each of the 3 grid search values."
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 4,
            "id": "4ccecf9c",
            "metadata": {},
            "outputs": [
                {
                    "name": "stdout",
                    "output_type": "stream",
                    "text": [
                        "Number of results: 9\n"
                    ]
                }
            ],
            "source": [
                "num_results = len(result_grid)\n",
                "print(\"Number of results:\", num_results)"
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 5,
            "id": "5cff1c8d",
            "metadata": {},
            "outputs": [
                {
                    "name": "stdout",
                    "output_type": "stream",
                    "text": [
                        "Trial #0 finished successfully with a mean accuracy metric of: 0.96875\n",
                        "Trial #1 finished successfully with a mean accuracy metric of: 0.925\n",
                        "Trial #2 finished successfully with a mean accuracy metric of: 0.946875\n",
                        "Trial #3 finished successfully with a mean accuracy metric of: 0.86875\n",
                        "Trial #4 finished successfully with a mean accuracy metric of: 0.94375\n",
                        "Trial #5 finished successfully with a mean accuracy metric of: 0.971875\n",
                        "Trial #6 finished successfully with a mean accuracy metric of: 0.91875\n",
                        "Trial #7 finished successfully with a mean accuracy metric of: 0.965625\n",
                        "Trial #8 finished successfully with a mean accuracy metric of: 0.740625\n"
                    ]
                }
            ],
            "source": [
                "# Iterate over results\n",
                "for i, result in enumerate(result_grid):\n",
                "    if result.error:\n",
                "        print(f\"Trial #{i} had an error:\", result.error)\n",
                "        continue\n",
                "\n",
                "    print(\n",
                "        f\"Trial #{i} finished successfully with a mean accuracy metric of:\",\n",
                "        result.metrics[\"mean_accuracy\"]\n",
                "    )"
            ]
        },
        {
            "attachments": {},
            "cell_type": "markdown",
            "id": "66c7ccc4",
            "metadata": {},
            "source": [
                "Above, we printed the **last reported** `mean_accuracy` metric for all trials by looping through the `result_grid`.\n",
                "We can access the same metrics for all trials in a pandas DataFrame."
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 6,
            "id": "c3541ea8",
            "metadata": {},
            "outputs": [
                {
                    "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>training_iteration</th>\n",
                            "      <th>mean_accuracy</th>\n",
                            "    </tr>\n",
                            "  </thead>\n",
                            "  <tbody>\n",
                            "    <tr>\n",
                            "      <th>0</th>\n",
                            "      <td>100</td>\n",
                            "      <td>0.968750</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>1</th>\n",
                            "      <td>100</td>\n",
                            "      <td>0.925000</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>2</th>\n",
                            "      <td>100</td>\n",
                            "      <td>0.946875</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>3</th>\n",
                            "      <td>100</td>\n",
                            "      <td>0.868750</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>4</th>\n",
                            "      <td>100</td>\n",
                            "      <td>0.943750</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>5</th>\n",
                            "      <td>100</td>\n",
                            "      <td>0.971875</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>6</th>\n",
                            "      <td>100</td>\n",
                            "      <td>0.918750</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>7</th>\n",
                            "      <td>100</td>\n",
                            "      <td>0.965625</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>8</th>\n",
                            "      <td>100</td>\n",
                            "      <td>0.740625</td>\n",
                            "    </tr>\n",
                            "  </tbody>\n",
                            "</table>\n",
                            "</div>"
                        ],
                        "text/plain": [
                            "   training_iteration  mean_accuracy\n",
                            "0                 100       0.968750\n",
                            "1                 100       0.925000\n",
                            "2                 100       0.946875\n",
                            "3                 100       0.868750\n",
                            "4                 100       0.943750\n",
                            "5                 100       0.971875\n",
                            "6                 100       0.918750\n",
                            "7                 100       0.965625\n",
                            "8                 100       0.740625"
                        ]
                    },
                    "execution_count": 6,
                    "metadata": {},
                    "output_type": "execute_result"
                }
            ],
            "source": [
                "results_df = result_grid.get_dataframe()\n",
                "results_df[[\"training_iteration\", \"mean_accuracy\"]]"
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 7,
            "id": "0117b332",
            "metadata": {},
            "outputs": [
                {
                    "name": "stdout",
                    "output_type": "stream",
                    "text": [
                        "Shortest training time: 28.826712369918823\n",
                        "Longest training time: 31.22410249710083\n"
                    ]
                }
            ],
            "source": [
                "print(\"Shortest training time:\", results_df[\"time_total_s\"].min())\n",
                "print(\"Longest training time:\", results_df[\"time_total_s\"].max())"
            ]
        },
        {
            "attachments": {},
            "cell_type": "markdown",
            "id": "184bd3ee",
            "metadata": {},
            "source": [
                "The last reported metrics might not contain the best accuracy each trial achieved. If we want to get maximum accuracy that each trial reported throughout its training, we can do so by using {meth}`ResultGrid.get_dataframe <ray.tune.result_grid.ResultGrid.get_dataframe>` specifying a metric and mode used to filter each trial's training history."
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 8,
            "id": "54f2d019",
            "metadata": {},
            "outputs": [
                {
                    "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>training_iteration</th>\n",
                            "      <th>mean_accuracy</th>\n",
                            "    </tr>\n",
                            "  </thead>\n",
                            "  <tbody>\n",
                            "    <tr>\n",
                            "      <th>0</th>\n",
                            "      <td>81</td>\n",
                            "      <td>0.978125</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>1</th>\n",
                            "      <td>44</td>\n",
                            "      <td>0.953125</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>2</th>\n",
                            "      <td>96</td>\n",
                            "      <td>0.953125</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>3</th>\n",
                            "      <td>94</td>\n",
                            "      <td>0.925000</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>4</th>\n",
                            "      <td>87</td>\n",
                            "      <td>0.975000</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>5</th>\n",
                            "      <td>92</td>\n",
                            "      <td>0.978125</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>6</th>\n",
                            "      <td>77</td>\n",
                            "      <td>0.959375</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>7</th>\n",
                            "      <td>59</td>\n",
                            "      <td>0.971875</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>8</th>\n",
                            "      <td>10</td>\n",
                            "      <td>0.896875</td>\n",
                            "    </tr>\n",
                            "  </tbody>\n",
                            "</table>\n",
                            "</div>"
                        ],
                        "text/plain": [
                            "   training_iteration  mean_accuracy\n",
                            "0                  81       0.978125\n",
                            "1                  44       0.953125\n",
                            "2                  96       0.953125\n",
                            "3                  94       0.925000\n",
                            "4                  87       0.975000\n",
                            "5                  92       0.978125\n",
                            "6                  77       0.959375\n",
                            "7                  59       0.971875\n",
                            "8                  10       0.896875"
                        ]
                    },
                    "execution_count": 8,
                    "metadata": {},
                    "output_type": "execute_result"
                }
            ],
            "source": [
                "best_result_df = result_grid.get_dataframe(\n",
                "    filter_metric=\"mean_accuracy\", filter_mode=\"max\"\n",
                ")\n",
                "best_result_df[[\"training_iteration\", \"mean_accuracy\"]]"
            ]
        },
        {
            "attachments": {},
            "cell_type": "markdown",
            "id": "a016e288",
            "metadata": {},
            "source": [
                "## Trial-level Analysis: Working with an individual `Result`"
            ]
        },
        {
            "attachments": {},
            "cell_type": "markdown",
            "id": "59d52e62",
            "metadata": {},
            "source": [
                "Let's take a look at the result that ended with the best `mean_accuracy` metric. By default, `get_best_result` will use the same metric and mode as defined in the `TuneConfig` above. However, it's also possible to specify a new metric/order in which results should be ranked."
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 9,
            "id": "1b59ac25",
            "metadata": {},
            "outputs": [],
            "source": [
                "from ray.train import Result\n",
                "\n",
                "# Get the result with the maximum test set `mean_accuracy`\n",
                "best_result: Result = result_grid.get_best_result()\n",
                "\n",
                "# Get the result with the minimum `mean_accuracy`\n",
                "worst_performing_result: Result = result_grid.get_best_result(\n",
                "    metric=\"mean_accuracy\", mode=\"min\"\n",
                ")"
            ]
        },
        {
            "attachments": {},
            "cell_type": "markdown",
            "id": "19d25389",
            "metadata": {},
            "source": [
                "We can examine a few of the properties of the best `Result`. See the [API reference](result-docstring) for a list of all accessible properties.\n",
                "\n",
                "First, we can access the best result's hyperparameter configuration with `Result.config`."
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 10,
            "id": "7ffc3edc",
            "metadata": {},
            "outputs": [
                {
                    "data": {
                        "text/plain": [
                            "{'lr': 0.0034759400828981743, 'momentum': 0.99, 'should_checkpoint': True}"
                        ]
                    },
                    "execution_count": 10,
                    "metadata": {},
                    "output_type": "execute_result"
                }
            ],
            "source": [
                "best_result.config"
            ]
        },
        {
            "attachments": {},
            "cell_type": "markdown",
            "id": "403111f9",
            "metadata": {},
            "source": [
                "Next, we can access the trial's log directory via `Result.log_dir`. The result `log_dir` gives the trial level directory that contains checkpoints (if you had checkpointing enabled) and logged metrics to load manually or inspect using a tool like Tensorboard (see `result.json`, `progress.csv`)."
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 11,
            "id": "c90dcc28",
            "metadata": {},
            "outputs": [
                {
                    "data": {
                        "text/plain": [
                            "PosixPath('/tmp/ray_results/tune_analyzing_results/train_mnist_daaa1_00005_5_lr=0.0035,momentum=0.9900_2022-10-17_16-03-12')"
                        ]
                    },
                    "execution_count": 11,
                    "metadata": {},
                    "output_type": "execute_result"
                }
            ],
            "source": [
                "best_result.log_dir"
            ]
        },
        {
            "attachments": {},
            "cell_type": "markdown",
            "id": "44d4080e",
            "metadata": {},
            "source": [
                "You can also directly get the latest checkpoint for a specific trial via `Result.checkpoint`."
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 12,
            "id": "fa4018f1",
            "metadata": {},
            "outputs": [
                {
                    "data": {
                        "text/plain": [
                            "LegacyTorchCheckpoint(local_path=/tmp/ray_results/tune_analyzing_results/train_mnist_daaa1_00005_5_lr=0.0035,momentum=0.9900_2022-10-17_16-03-12/checkpoint_000099)"
                        ]
                    },
                    "execution_count": 12,
                    "metadata": {},
                    "output_type": "execute_result"
                }
            ],
            "source": [
                "# Get the last Ray AIR Checkpoint associated with the best-performing trial\n",
                "best_result.checkpoint"
            ]
        },
        {
            "attachments": {},
            "cell_type": "markdown",
            "id": "79661a56",
            "metadata": {},
            "source": [
                "You can also get the last-reported metrics associated with a specific trial via `Result.metrics`."
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 13,
            "id": "52d4b99c",
            "metadata": {},
            "outputs": [
                {
                    "data": {
                        "text/plain": [
                            "{'mean_accuracy': 0.971875,\n",
                            " 'time_this_iter_s': 0.23050832748413086,\n",
                            " 'should_checkpoint': True,\n",
                            " 'done': True,\n",
                            " 'timesteps_total': None,\n",
                            " 'episodes_total': None,\n",
                            " 'training_iteration': 100,\n",
                            " 'trial_id': 'daaa1_00005',\n",
                            " 'experiment_id': 'a15f57f8a3f84b1d823c2cf65c37aece',\n",
                            " 'date': '2022-10-17_16-03-45',\n",
                            " 'timestamp': 1666047825,\n",
                            " 'time_total_s': 29.587023496627808,\n",
                            " 'pid': 3699,\n",
                            " 'hostname': 'ip-172-31-113-120',\n",
                            " 'node_ip': '172.31.113.120',\n",
                            " 'config': {'lr': 0.0034759400828981743,\n",
                            "  'momentum': 0.99,\n",
                            "  'should_checkpoint': True},\n",
                            " 'time_since_restore': 29.587023496627808,\n",
                            " 'timesteps_since_restore': 0,\n",
                            " 'iterations_since_restore': 100,\n",
                            " 'warmup_time': 0.003263711929321289,\n",
                            " 'experiment_tag': '5_lr=0.0035,momentum=0.9900'}"
                        ]
                    },
                    "execution_count": 13,
                    "metadata": {},
                    "output_type": "execute_result"
                }
            ],
            "source": [
                "# Get the last reported set of metrics\n",
                "best_result.metrics"
            ]
        },
        {
            "attachments": {},
            "cell_type": "markdown",
            "id": "00705f44",
            "metadata": {},
            "source": [
                "Access the entire history of reported metrics from a `Result` as a pandas DataFrame:"
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 14,
            "id": "ca87204f",
            "metadata": {},
            "outputs": [
                {
                    "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>training_iteration</th>\n",
                            "      <th>mean_accuracy</th>\n",
                            "      <th>time_total_s</th>\n",
                            "    </tr>\n",
                            "  </thead>\n",
                            "  <tbody>\n",
                            "    <tr>\n",
                            "      <th>0</th>\n",
                            "      <td>1</td>\n",
                            "      <td>0.121875</td>\n",
                            "      <td>1.874643</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>1</th>\n",
                            "      <td>2</td>\n",
                            "      <td>0.340625</td>\n",
                            "      <td>2.110028</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>2</th>\n",
                            "      <td>3</td>\n",
                            "      <td>0.321875</td>\n",
                            "      <td>2.332039</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>3</th>\n",
                            "      <td>4</td>\n",
                            "      <td>0.521875</td>\n",
                            "      <td>2.621943</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>4</th>\n",
                            "      <td>5</td>\n",
                            "      <td>0.684375</td>\n",
                            "      <td>2.958664</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>...</th>\n",
                            "      <td>...</td>\n",
                            "      <td>...</td>\n",
                            "      <td>...</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>95</th>\n",
                            "      <td>96</td>\n",
                            "      <td>0.953125</td>\n",
                            "      <td>28.516581</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>96</th>\n",
                            "      <td>97</td>\n",
                            "      <td>0.959375</td>\n",
                            "      <td>28.819717</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>97</th>\n",
                            "      <td>98</td>\n",
                            "      <td>0.934375</td>\n",
                            "      <td>29.085851</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>98</th>\n",
                            "      <td>99</td>\n",
                            "      <td>0.968750</td>\n",
                            "      <td>29.356515</td>\n",
                            "    </tr>\n",
                            "    <tr>\n",
                            "      <th>99</th>\n",
                            "      <td>100</td>\n",
                            "      <td>0.971875</td>\n",
                            "      <td>29.587023</td>\n",
                            "    </tr>\n",
                            "  </tbody>\n",
                            "</table>\n",
                            "<p>100 rows × 3 columns</p>\n",
                            "</div>"
                        ],
                        "text/plain": [
                            "    training_iteration  mean_accuracy  time_total_s\n",
                            "0                    1       0.121875      1.874643\n",
                            "1                    2       0.340625      2.110028\n",
                            "2                    3       0.321875      2.332039\n",
                            "3                    4       0.521875      2.621943\n",
                            "4                    5       0.684375      2.958664\n",
                            "..                 ...            ...           ...\n",
                            "95                  96       0.953125     28.516581\n",
                            "96                  97       0.959375     28.819717\n",
                            "97                  98       0.934375     29.085851\n",
                            "98                  99       0.968750     29.356515\n",
                            "99                 100       0.971875     29.587023\n",
                            "\n",
                            "[100 rows x 3 columns]"
                        ]
                    },
                    "execution_count": 14,
                    "metadata": {},
                    "output_type": "execute_result"
                }
            ],
            "source": [
                "result_df = best_result.metrics_dataframe\n",
                "result_df[[\"training_iteration\", \"mean_accuracy\", \"time_total_s\"]]"
            ]
        },
        {
            "attachments": {},
            "cell_type": "markdown",
            "id": "20bc50e9",
            "metadata": {},
            "source": [
                "## Plotting metrics\n",
                "\n",
                "We can use the metrics DataFrame to quickly visualize learning curves. First, let's plot the mean accuracy vs. training iterations for the best result."
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 15,
            "id": "1ff489ec",
            "metadata": {},
            "outputs": [
                {
                    "data": {
                        "text/plain": [
                            "<AxesSubplot: xlabel='training_iteration'>"
                        ]
                    },
                    "execution_count": 15,
                    "metadata": {},
                    "output_type": "execute_result"
                },
                {
                    "data": {
                        "image/png": "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",
                        "text/plain": [
                            "<Figure size 640x480 with 1 Axes>"
                        ]
                    },
                    "metadata": {},
                    "output_type": "display_data"
                }
            ],
            "source": [
                "best_result.metrics_dataframe.plot(\"training_iteration\", \"mean_accuracy\")"
            ]
        },
        {
            "attachments": {},
            "cell_type": "markdown",
            "id": "4fd2f85b",
            "metadata": {},
            "source": [
                "We can also iterate through the entire set of results and create a combined plot of all trials with the hyperparameters as labels."
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 16,
            "id": "54b78da6",
            "metadata": {},
            "outputs": [
                {
                    "data": {
                        "text/plain": [
                            "Text(0, 0.5, 'Mean Test Accuracy')"
                        ]
                    },
                    "execution_count": 16,
                    "metadata": {},
                    "output_type": "execute_result"
                },
                {
                    "data": {
                        "image/png": "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",
                        "text/plain": [
                            "<Figure size 640x480 with 1 Axes>"
                        ]
                    },
                    "metadata": {},
                    "output_type": "display_data"
                }
            ],
            "source": [
                "ax = None\n",
                "for result in result_grid:\n",
                "    label = f\"lr={result.config['lr']:.3f}, momentum={result.config['momentum']}\"\n",
                "    if ax is None:\n",
                "        ax = result.metrics_dataframe.plot(\"training_iteration\", \"mean_accuracy\", label=label)\n",
                "    else:\n",
                "        result.metrics_dataframe.plot(\"training_iteration\", \"mean_accuracy\", ax=ax, label=label)\n",
                "ax.set_title(\"Mean Accuracy vs. Training Iteration for All Trials\")\n",
                "ax.set_ylabel(\"Mean Test Accuracy\")"
            ]
        },
        {
            "attachments": {},
            "cell_type": "markdown",
            "id": "be02fc7a",
            "metadata": {},
            "source": [
                "## Accessing checkpoints and loading for test inference\n",
                "\n",
                "We noticed earlier that `Result` contains the last checkpoint associated with a trial. Let's see how we can use this checkpoint to load a model for performing inference on some sample MNIST images.\n",
                "\n",
                "If you are running a Tune experiment with Ray AIR Trainers, the checkpoints saved may be framework-specific checkpoints such as `LegacyTorchCheckpoint`. Refer to [documentation on framework-specific integrations](air-trainer-ref) to learn how to load from these types of checkpoints."
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 17,
            "id": "50d3acff",
            "metadata": {},
            "outputs": [],
            "source": [
                "from ray.train.torch import LegacyTorchCheckpoint, TorchPredictor\n",
                "from ray.tune.examples.mnist_pytorch import ConvNet, get_data_loaders\n",
                "\n",
                "checkpoint: LegacyTorchCheckpoint = best_result.checkpoint\n",
                "\n",
                "# Create a Predictor using the best result's checkpoint\n",
                "predictor = TorchPredictor.from_checkpoint(checkpoint, ConvNet())"
            ]
        },
        {
            "attachments": {},
            "cell_type": "markdown",
            "id": "2813c45d",
            "metadata": {},
            "source": [
                "Refer to the training loop definition {doc}`here </tune/examples/includes/mnist_pytorch>` to see how we are saving the checkpoint in the first place.\n",
                "\n",
                "Next, let's test our model with a sample data point and print out the predicted class."
            ]
        },
        {
            "cell_type": "code",
            "execution_count": 18,
            "id": "eb8f6942",
            "metadata": {},
            "outputs": [
                {
                    "name": "stdout",
                    "output_type": "stream",
                    "text": [
                        "Predicted Class = 4\n"
                    ]
                },
                {
                    "data": {
                        "image/png": "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",
                        "text/plain": [
                            "<Figure size 200x200 with 1 Axes>"
                        ]
                    },
                    "metadata": {},
                    "output_type": "display_data"
                }
            ],
            "source": [
                "import matplotlib.pyplot as plt\n",
                "import numpy as np\n",
                "\n",
                "_, test_loader = get_data_loaders()\n",
                "test_img = next(iter(test_loader))[0][0]\n",
                "# Need to reshape to (batch_size, channels, width, height)\n",
                "test_img = test_img.numpy().reshape((1, 1, 28, 28))\n",
                "plt.figure(figsize=(2, 2))\n",
                "plt.imshow(test_img.reshape((28, 28)))\n",
                "\n",
                "predicted_class = np.argmax(predictor.predict(test_img))\n",
                "print(\"Predicted Class =\", predicted_class)"
            ]
        },
        {
            "attachments": {},
            "cell_type": "markdown",
            "id": "1699bab7",
            "metadata": {},
            "source": [
                "Consider using Ray AIR batch prediction if you want to use a checkpointed model for large scale inference!"
            ]
        },
        {
            "attachments": {},
            "cell_type": "markdown",
            "id": "16c25683",
            "metadata": {},
            "source": [
                "## Summary\n",
                "\n",
                "In this guide, we looked at some common analysis workflows you can perform using the `ResultGrid` output returned by `Tuner.fit`. These included: **loading results from an experiment directory, exploring experiment-level and trial-level results, plotting logged metrics, and accessing trial checkpoints for inference.**\n",
                "\n",
                "Take a look at [Tune's experiment tracking integrations](tune-experiment-tracking-examples) for more analysis tools that you can build into your Tune experiment with a few callbacks!"
            ]
        }
    ],
    "metadata": {
        "kernelspec": {
            "display_name": "ray_dev_py38",
            "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"
        },
        "vscode": {
            "interpreter": {
                "hash": "265d195fda5292fe8f69c6e37c435a5634a1ed3b6799724e66a975f68fa21517"
            }
        }
    },
    "nbformat": 4,
    "nbformat_minor": 5
}