master-thesis/classification/classifier/hyp-metrics.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "747ddcf2",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[34m\u001b[1mwandb\u001b[0m: Currently logged in as: \u001b[33me1527193\u001b[0m (\u001b[33mflower-classification\u001b[0m). Use \u001b[1m`wandb login --relogin`\u001b[0m to force relogin\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "import os\n",
    "import time\n",
    "import random\n",
    "import wandb\n",
    "import torch\n",
    "wandb.login()\n",
    "\n",
    "def set_size(width, fraction=1, subplots=(1, 1)):\n",
    "    \"\"\"Set figure dimensions to avoid scaling in LaTeX.\n",
    "\n",
    "    Parameters\n",
    "    ----------\n",
    "    width: float\n",
    "            Document textwidth or columnwidth in pts\n",
    "    fraction: float, optional\n",
    "            Fraction of the width which you wish the figure to occupy\n",
    "\n",
    "    Returns\n",
    "    -------\n",
    "    fig_dim: tuple\n",
    "            Dimensions of figure in inches\n",
    "    \"\"\"\n",
    "    # Width of figure (in pts)\n",
    "    fig_width_pt = width * fraction\n",
    "\n",
    "    # Convert from pt to inches\n",
    "    inches_per_pt = 1 / 72.27\n",
    "\n",
    "    # Golden ratio to set aesthetic figure height\n",
    "    # https://disq.us/p/2940ij3\n",
    "    golden_ratio = (5**.5 - 1) / 2\n",
    "\n",
    "    # Figure width in inches\n",
    "    fig_width_in = fig_width_pt * inches_per_pt\n",
    "    # Figure height in inches\n",
    "    fig_height_in = fig_width_in * golden_ratio * (subplots[0] / subplots[1])\n",
    "\n",
    "    fig_dim = (fig_width_in, fig_height_in)\n",
    "\n",
    "    return fig_dim\n",
    "\n",
    "torch.manual_seed(42)\n",
    "np.random.seed(42)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4d29e56f-ee81-4f43-96ff-99bb22c52f6a",
   "metadata": {},
   "source": [
    "# Download Metrics from WandB"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "76cc2ca7",
   "metadata": {},
   "outputs": [],
   "source": [
    "api = wandb.Api()\n",
    "\n",
    "# Project is specified by <entity/project-name>\n",
    "runs = api.runs(\"flower-classification/pytorch-sweeps-demo\")\n",
    "\n",
    "summary_list, config_list, name_list = [], [], []\n",
    "for run in runs: \n",
    "    # .summary contains the output keys/values for metrics like accuracy.\n",
    "    #  We call ._json_dict to omit large files \n",
    "    summary_list.append(run.summary._json_dict)\n",
    "\n",
    "    # .config contains the hyperparameters.\n",
    "    #  We remove special values that start with _.\n",
    "    config_list.append(\n",
    "        {k: v for k,v in run.config.items()\n",
    "          if not k.startswith('_')})\n",
    "\n",
    "    # .name is the human-readable name of the run.\n",
    "    name_list.append(run.name)\n",
    "\n",
    "runs_df = pd.DataFrame({\n",
    "    \"summary\": summary_list,\n",
    "    \"config\": config_list,\n",
    "    \"name\": name_list\n",
    "    })\n",
    "\n",
    "runs_df.to_csv(\"hyp-metrics.csv\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "821aeb7d-784b-4e38-b4f8-c49245ee25ce",
   "metadata": {},
   "source": [
    "# Transform Metrics\n",
    "\n",
    "The column `summary` contains most of the metrics we are interested in (`test/precision`,…) but all of the metrics are in a dictionary in this column."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "353f9082",
   "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>Unnamed: 0</th>\n",
       "      <th>name</th>\n",
       "      <th>_step</th>\n",
       "      <th>_timestamp</th>\n",
       "      <th>test/recall</th>\n",
       "      <th>test/f1-score</th>\n",
       "      <th>test/epoch_acc</th>\n",
       "      <th>test/epoch_loss</th>\n",
       "      <th>train/epoch_loss</th>\n",
       "      <th>epoch</th>\n",
       "      <th>...</th>\n",
       "      <th>test/batch_loss</th>\n",
       "      <th>eps</th>\n",
       "      <th>gamma</th>\n",
       "      <th>epochs</th>\n",
       "      <th>beta_one</th>\n",
       "      <th>beta_two</th>\n",
       "      <th>optimizer</th>\n",
       "      <th>step_size</th>\n",
       "      <th>batch_size</th>\n",
       "      <th>learning_rate</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>fiery-sweep-26</td>\n",
       "      <td>2059</td>\n",
       "      <td>1.680693e+09</td>\n",
       "      <td>0.617021</td>\n",
       "      <td>0.707317</td>\n",
       "      <td>0.733333</td>\n",
       "      <td>0.566462</td>\n",
       "      <td>0.424106</td>\n",
       "      <td>9</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.000000e-01</td>\n",
       "      <td>0.1</td>\n",
       "      <td>10</td>\n",
       "      <td>0.99</td>\n",
       "      <td>0.900</td>\n",
       "      <td>adam</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>0.0003</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>radiant-sweep-25</td>\n",
       "      <td>1039</td>\n",
       "      <td>1.680693e+09</td>\n",
       "      <td>0.822222</td>\n",
       "      <td>0.747475</td>\n",
       "      <td>0.722222</td>\n",
       "      <td>0.645458</td>\n",
       "      <td>0.64979</td>\n",
       "      <td>9</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.000000e+00</td>\n",
       "      <td>0.5</td>\n",
       "      <td>10</td>\n",
       "      <td>0.99</td>\n",
       "      <td>0.900</td>\n",
       "      <td>adam</td>\n",
       "      <td>2</td>\n",
       "      <td>8</td>\n",
       "      <td>0.0003</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>blooming-sweep-24</td>\n",
       "      <td>1039</td>\n",
       "      <td>1.680692e+09</td>\n",
       "      <td>0.783784</td>\n",
       "      <td>0.852941</td>\n",
       "      <td>0.888889</td>\n",
       "      <td>0.348129</td>\n",
       "      <td>0.016143</td>\n",
       "      <td>9</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.000000e-08</td>\n",
       "      <td>0.5</td>\n",
       "      <td>10</td>\n",
       "      <td>0.90</td>\n",
       "      <td>0.999</td>\n",
       "      <td>sgd</td>\n",
       "      <td>5</td>\n",
       "      <td>8</td>\n",
       "      <td>0.0030</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>visionary-sweep-23</td>\n",
       "      <td>529</td>\n",
       "      <td>1.680692e+09</td>\n",
       "      <td>0.833333</td>\n",
       "      <td>0.795455</td>\n",
       "      <td>0.800000</td>\n",
       "      <td>0.555318</td>\n",
       "      <td>0.532423</td>\n",
       "      <td>9</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.000000e+00</td>\n",
       "      <td>0.1</td>\n",
       "      <td>10</td>\n",
       "      <td>0.90</td>\n",
       "      <td>0.900</td>\n",
       "      <td>sgd</td>\n",
       "      <td>2</td>\n",
       "      <td>16</td>\n",
       "      <td>0.0003</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4</td>\n",
       "      <td>ancient-sweep-22</td>\n",
       "      <td>410</td>\n",
       "      <td>1.680692e+09</td>\n",
       "      <td>0.884615</td>\n",
       "      <td>0.707692</td>\n",
       "      <td>0.577778</td>\n",
       "      <td>1.560271</td>\n",
       "      <td>0.75081</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.000000e-08</td>\n",
       "      <td>0.5</td>\n",
       "      <td>10</td>\n",
       "      <td>0.90</td>\n",
       "      <td>0.990</td>\n",
       "      <td>adam</td>\n",
       "      <td>7</td>\n",
       "      <td>4</td>\n",
       "      <td>0.0100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>133</th>\n",
       "      <td>133</td>\n",
       "      <td>different-sweep-5</td>\n",
       "      <td>1159</td>\n",
       "      <td>1.678732e+09</td>\n",
       "      <td>0.714286</td>\n",
       "      <td>0.813953</td>\n",
       "      <td>0.822222</td>\n",
       "      <td>0.493642</td>\n",
       "      <td>0.518635</td>\n",
       "      <td>9</td>\n",
       "      <td>...</td>\n",
       "      <td>0.506896</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.5</td>\n",
       "      <td>10</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>sgd</td>\n",
       "      <td>3</td>\n",
       "      <td>8</td>\n",
       "      <td>0.0001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>134</th>\n",
       "      <td>134</td>\n",
       "      <td>wise-sweep-4</td>\n",
       "      <td>1159</td>\n",
       "      <td>1.678731e+09</td>\n",
       "      <td>0.846154</td>\n",
       "      <td>0.835443</td>\n",
       "      <td>0.855556</td>\n",
       "      <td>0.548264</td>\n",
       "      <td>0.54292</td>\n",
       "      <td>9</td>\n",
       "      <td>...</td>\n",
       "      <td>0.515937</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.5</td>\n",
       "      <td>10</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>sgd</td>\n",
       "      <td>2</td>\n",
       "      <td>8</td>\n",
       "      <td>0.0001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>135</th>\n",
       "      <td>135</td>\n",
       "      <td>misty-sweep-3</td>\n",
       "      <td>2289</td>\n",
       "      <td>1.678731e+09</td>\n",
       "      <td>0.775000</td>\n",
       "      <td>0.849315</td>\n",
       "      <td>0.877778</td>\n",
       "      <td>0.241948</td>\n",
       "      <td>0.020604</td>\n",
       "      <td>9</td>\n",
       "      <td>...</td>\n",
       "      <td>1.758836</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.5</td>\n",
       "      <td>10</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>sgd</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>0.0030</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>136</th>\n",
       "      <td>136</td>\n",
       "      <td>unique-sweep-2</td>\n",
       "      <td>1159</td>\n",
       "      <td>1.678730e+09</td>\n",
       "      <td>0.684211</td>\n",
       "      <td>0.753623</td>\n",
       "      <td>0.811111</td>\n",
       "      <td>0.479234</td>\n",
       "      <td>0.42905</td>\n",
       "      <td>9</td>\n",
       "      <td>...</td>\n",
       "      <td>0.455120</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.1</td>\n",
       "      <td>10</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>sgd</td>\n",
       "      <td>3</td>\n",
       "      <td>8</td>\n",
       "      <td>0.0003</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>137</th>\n",
       "      <td>137</td>\n",
       "      <td>polar-sweep-1</td>\n",
       "      <td>2289</td>\n",
       "      <td>1.678730e+09</td>\n",
       "      <td>0.863636</td>\n",
       "      <td>0.883721</td>\n",
       "      <td>0.888889</td>\n",
       "      <td>0.544247</td>\n",
       "      <td>0.024021</td>\n",
       "      <td>9</td>\n",
       "      <td>...</td>\n",
       "      <td>2.532007</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.5</td>\n",
       "      <td>10</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>sgd</td>\n",
       "      <td>7</td>\n",
       "      <td>4</td>\n",
       "      <td>0.0030</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>138 rows × 25 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     Unnamed: 0                name  _step    _timestamp  test/recall  \\\n",
       "0             0      fiery-sweep-26   2059  1.680693e+09     0.617021   \n",
       "1             1    radiant-sweep-25   1039  1.680693e+09     0.822222   \n",
       "2             2   blooming-sweep-24   1039  1.680692e+09     0.783784   \n",
       "3             3  visionary-sweep-23    529  1.680692e+09     0.833333   \n",
       "4             4    ancient-sweep-22    410  1.680692e+09     0.884615   \n",
       "..          ...                 ...    ...           ...          ...   \n",
       "133         133   different-sweep-5   1159  1.678732e+09     0.714286   \n",
       "134         134        wise-sweep-4   1159  1.678731e+09     0.846154   \n",
       "135         135       misty-sweep-3   2289  1.678731e+09     0.775000   \n",
       "136         136      unique-sweep-2   1159  1.678730e+09     0.684211   \n",
       "137         137       polar-sweep-1   2289  1.678730e+09     0.863636   \n",
       "\n",
       "     test/f1-score  test/epoch_acc  test/epoch_loss train/epoch_loss  epoch  \\\n",
       "0         0.707317        0.733333         0.566462         0.424106      9   \n",
       "1         0.747475        0.722222         0.645458          0.64979      9   \n",
       "2         0.852941        0.888889         0.348129         0.016143      9   \n",
       "3         0.795455        0.800000         0.555318         0.532423      9   \n",
       "4         0.707692        0.577778         1.560271          0.75081      1   \n",
       "..             ...             ...              ...              ...    ...   \n",
       "133       0.813953        0.822222         0.493642         0.518635      9   \n",
       "134       0.835443        0.855556         0.548264          0.54292      9   \n",
       "135       0.849315        0.877778         0.241948         0.020604      9   \n",
       "136       0.753623        0.811111         0.479234          0.42905      9   \n",
       "137       0.883721        0.888889         0.544247         0.024021      9   \n",
       "\n",
       "     ...  test/batch_loss           eps  gamma epochs  beta_one  beta_two  \\\n",
       "0    ...              NaN  1.000000e-01    0.1     10      0.99     0.900   \n",
       "1    ...              NaN  1.000000e+00    0.5     10      0.99     0.900   \n",
       "2    ...              NaN  1.000000e-08    0.5     10      0.90     0.999   \n",
       "3    ...              NaN  1.000000e+00    0.1     10      0.90     0.900   \n",
       "4    ...              NaN  1.000000e-08    0.5     10      0.90     0.990   \n",
       "..   ...              ...           ...    ...    ...       ...       ...   \n",
       "133  ...         0.506896           NaN    0.5     10       NaN       NaN   \n",
       "134  ...         0.515937           NaN    0.5     10       NaN       NaN   \n",
       "135  ...         1.758836           NaN    0.5     10       NaN       NaN   \n",
       "136  ...         0.455120           NaN    0.1     10       NaN       NaN   \n",
       "137  ...         2.532007           NaN    0.5     10       NaN       NaN   \n",
       "\n",
       "     optimizer  step_size  batch_size  learning_rate  \n",
       "0         adam          3           4         0.0003  \n",
       "1         adam          2           8         0.0003  \n",
       "2          sgd          5           8         0.0030  \n",
       "3          sgd          2          16         0.0003  \n",
       "4         adam          7           4         0.0100  \n",
       "..         ...        ...         ...            ...  \n",
       "133        sgd          3           8         0.0001  \n",
       "134        sgd          2           8         0.0001  \n",
       "135        sgd          3           4         0.0030  \n",
       "136        sgd          3           8         0.0003  \n",
       "137        sgd          7           4         0.0030  \n",
       "\n",
       "[138 rows x 25 columns]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv('hyp-metrics.csv',\n",
    "                 delimiter=',')\n",
    "df['summary'] = df['summary'].map(eval)\n",
    "df['config'] = df['config'].map(eval)\n",
    "df = df.join(pd.json_normalize(df['summary'])).drop('summary', axis='columns')\n",
    "df = df.join(pd.json_normalize(df['config'])).drop('config', axis='columns')\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "4679b2f8",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/run/user/1000/ipykernel_39845/2346208349.py:1: FutureWarning: In a future version of pandas all arguments of Series.sort_values will be keyword-only.\n",
      "  df['learning_rate'].value_counts().sort_values(0)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "0.0100    21\n",
       "0.1000    21\n",
       "0.0003    23\n",
       "0.0010    23\n",
       "0.0001    23\n",
       "0.0030    27\n",
       "Name: learning_rate, dtype: int64"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['learning_rate'].value_counts().sort_values(0)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "1b1a54fc",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Style the plots (with grid this time)\n",
    "width = 418\n",
    "sns.set_theme(style='whitegrid',\n",
    "              rc={'text.usetex': True, 'font.family': 'serif', 'axes.labelsize': 16,\n",
    "                  'font.size': 16, 'legend.fontsize': 11,\n",
    "                  'xtick.labelsize': 12, 'ytick.labelsize': 12})\n",
    "\n",
    "fig_save_dir = '../../thesis/graphics/'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "00efa25b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 578.387x357.463 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "df_prepared = df.rename(columns={'learning_rate': 'learning rate', 'batch_size': 'batch size'})\n",
    "fig, ax = plt.subplots(1, 1, figsize=set_size(width, subplots=(1,1)))\n",
    "sns.scatterplot(x=\"learning rate\", y=\"test/f1-score\", hue=\"batch size\",\n",
    "                palette=sns.cubehelix_palette(5, light=0.8, gamma=1.2),\n",
    "                sizes=(5, 30), linewidth=0, s=50,\n",
    "                data=df_prepared, ax=ax)\n",
    "ax.set_xscale('log')\n",
    "ax.set_xticks([0.0001, 0.0003, 0.001, 0.003, 0.01, 0.1])\n",
    "ax.set_xticklabels(labels = ['0.0001', '0.0003', '0.001', '0.003', '0.01', '0.1'])\n",
    "fig.tight_layout()\n",
    "fig.savefig(fig_save_dir + 'classifier-hyp-metrics.pdf', format='pdf', bbox_inches='tight')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "44e275ab",
   "metadata": {},
   "outputs": [],
   "source": [
    "parameters_dict = {\n",
    "    'optimizer': {\n",
    "        'values': ['adam', 'sgd']\n",
    "    },\n",
    "}\n",
    "\n",
    "parameters_dict.update({\n",
    "    'batch_size': {\n",
    "        'values': [4, 8, 16, 32, 64]},\n",
    "    'learning_rate': {\n",
    "        'values': [0.0001, 0.0003, 0.001, 0.003, 0.01, 0.1]},\n",
    "    'step_size': {\n",
    "        'values': [2, 3, 5, 7]},\n",
    "    'gamma': {\n",
    "        'values': [0.1, 0.5]},\n",
    "    'beta_one': {\n",
    "        'values': [0.9, 0.99]},\n",
    "    'beta_two': {\n",
    "        'values': [0.5, 0.9, 0.99, 0.999]},\n",
    "    'eps': {\n",
    "        'values': [1e-08, 0.1, 1]}\n",
    "})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "7d3c2860",
   "metadata": {},
   "outputs": [],
   "source": [
    "params = pd.DataFrame.from_dict(parameters_dict)\n",
    "params = params.transpose()\n",
    "params['values_string'] = [', '.join(map(str, l)) for l in params['values']]\n",
    "params['values'] = params['values_string']\n",
    "params = params.drop(['values_string'], axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "acc3a77e",
   "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>values</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>optimizer</th>\n",
       "      <td>adam, sgd</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>batch_size</th>\n",
       "      <td>4, 8, 16, 32, 64</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>learning_rate</th>\n",
       "      <td>0.0001, 0.0003, 0.001, 0.003, 0.01, 0.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>step_size</th>\n",
       "      <td>2, 3, 5, 7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>gamma</th>\n",
       "      <td>0.1, 0.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>beta_one</th>\n",
       "      <td>0.9, 0.99</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>beta_two</th>\n",
       "      <td>0.5, 0.9, 0.99, 0.999</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>eps</th>\n",
       "      <td>1e-08, 0.1, 1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                values\n",
       "optimizer                                    adam, sgd\n",
       "batch_size                            4, 8, 16, 32, 64\n",
       "learning_rate  0.0001, 0.0003, 0.001, 0.003, 0.01, 0.1\n",
       "step_size                                   2, 3, 5, 7\n",
       "gamma                                         0.1, 0.5\n",
       "beta_one                                     0.9, 0.99\n",
       "beta_two                         0.5, 0.9, 0.99, 0.999\n",
       "eps                                      1e-08, 0.1, 1"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "params"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "73a26951",
   "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>optimizer</th>\n",
       "      <th>batch_size</th>\n",
       "      <th>learning_rate</th>\n",
       "      <th>step_size</th>\n",
       "      <th>gamma</th>\n",
       "      <th>beta_one</th>\n",
       "      <th>beta_two</th>\n",
       "      <th>eps</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>values</th>\n",
       "      <td>adam</td>\n",
       "      <td>4</td>\n",
       "      <td>0.0001</td>\n",
       "      <td>2</td>\n",
       "      <td>0.1</td>\n",
       "      <td>0.9</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>values</th>\n",
       "      <td>adam</td>\n",
       "      <td>4</td>\n",
       "      <td>0.0001</td>\n",
       "      <td>2</td>\n",
       "      <td>0.1</td>\n",
       "      <td>0.9</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>values</th>\n",
       "      <td>adam</td>\n",
       "      <td>4</td>\n",
       "      <td>0.0001</td>\n",
       "      <td>2</td>\n",
       "      <td>0.1</td>\n",
       "      <td>0.9</td>\n",
       "      <td>0.5</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>values</th>\n",
       "      <td>adam</td>\n",
       "      <td>4</td>\n",
       "      <td>0.0001</td>\n",
       "      <td>2</td>\n",
       "      <td>0.1</td>\n",
       "      <td>0.9</td>\n",
       "      <td>0.9</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>values</th>\n",
       "      <td>adam</td>\n",
       "      <td>4</td>\n",
       "      <td>0.0001</td>\n",
       "      <td>2</td>\n",
       "      <td>0.1</td>\n",
       "      <td>0.9</td>\n",
       "      <td>0.9</td>\n",
       "      <td>0.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>values</th>\n",
       "      <td>sgd</td>\n",
       "      <td>64</td>\n",
       "      <td>0.1</td>\n",
       "      <td>7</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.99</td>\n",
       "      <td>0.99</td>\n",
       "      <td>0.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>values</th>\n",
       "      <td>sgd</td>\n",
       "      <td>64</td>\n",
       "      <td>0.1</td>\n",
       "      <td>7</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.99</td>\n",
       "      <td>0.99</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>values</th>\n",
       "      <td>sgd</td>\n",
       "      <td>64</td>\n",
       "      <td>0.1</td>\n",
       "      <td>7</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.99</td>\n",
       "      <td>0.999</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>values</th>\n",
       "      <td>sgd</td>\n",
       "      <td>64</td>\n",
       "      <td>0.1</td>\n",
       "      <td>7</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.99</td>\n",
       "      <td>0.999</td>\n",
       "      <td>0.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>values</th>\n",
       "      <td>sgd</td>\n",
       "      <td>64</td>\n",
       "      <td>0.1</td>\n",
       "      <td>7</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.99</td>\n",
       "      <td>0.999</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>11520 rows × 8 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       optimizer batch_size learning_rate step_size gamma beta_one beta_two  \\\n",
       "values      adam          4        0.0001         2   0.1      0.9      0.5   \n",
       "values      adam          4        0.0001         2   0.1      0.9      0.5   \n",
       "values      adam          4        0.0001         2   0.1      0.9      0.5   \n",
       "values      adam          4        0.0001         2   0.1      0.9      0.9   \n",
       "values      adam          4        0.0001         2   0.1      0.9      0.9   \n",
       "...          ...        ...           ...       ...   ...      ...      ...   \n",
       "values       sgd         64           0.1         7   0.5     0.99     0.99   \n",
       "values       sgd         64           0.1         7   0.5     0.99     0.99   \n",
       "values       sgd         64           0.1         7   0.5     0.99    0.999   \n",
       "values       sgd         64           0.1         7   0.5     0.99    0.999   \n",
       "values       sgd         64           0.1         7   0.5     0.99    0.999   \n",
       "\n",
       "        eps  \n",
       "values  0.0  \n",
       "values  0.1  \n",
       "values    1  \n",
       "values  0.0  \n",
       "values  0.1  \n",
       "...     ...  \n",
       "values  0.1  \n",
       "values    1  \n",
       "values  0.0  \n",
       "values  0.1  \n",
       "values    1  \n",
       "\n",
       "[11520 rows x 8 columns]"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.DataFrame.from_dict(parameters_dict).explode('optimizer').explode('batch_size').explode('learning_rate').explode('step_size').explode('gamma').explode('beta_one').explode('beta_two').explode('eps')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0d01bf18",
   "metadata": {},
   "source": [
    "# F1-score stratified 10-fold cross validation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "bb567230",
   "metadata": {},
   "outputs": [],
   "source": [
    "f_scores_test = pd.read_csv('f1-scores-folds.csv', delimiter=',')\n",
    "f_scores_test['epoch'] = np.resize(np.arange(25), 10*25)\n",
    "f_scores_test['fold'] = np.repeat(np.arange(10), 25)\n",
    "f_scores_test = pd.melt(f_scores_test[['epoch', 'fold', 'StratifiedKFold-ROC - test/f1-score']], ['epoch', 'fold'])\n",
    "\n",
    "f_scores_train = pd.read_csv('f1-scores-folds-train.csv', delimiter=',')\n",
    "f_scores_train['epoch'] = np.resize(np.arange(25), 10*25)\n",
    "f_scores_train['fold'] = np.repeat(np.arange(10), 25)\n",
    "f_scores_train = pd.melt(f_scores_train[['epoch', 'fold', 'StratifiedKFold-ROC - train/f1-score']], ['epoch', 'fold'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "id": "493e415e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 578.387x714.925 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, ax = plt.subplots(2, 1, figsize=set_size(width, subplots=(2,1)), sharex=True)\n",
    "sns.lineplot(x=\"epoch\", y=\"value\",\n",
    "                hue='fold',\n",
    "                palette=sns.cubehelix_palette(10, light=0.8, gamma=1.2),\n",
    "                linewidth=1,\n",
    "                data=f_scores_train, ax=ax[0])\n",
    "\n",
    "sns.lineplot(x=\"epoch\", y=\"value\",\n",
    "                hue='fold',\n",
    "                palette=sns.cubehelix_palette(10, light=0.8, gamma=1.2),\n",
    "                linewidth=1,\n",
    "                data=f_scores_test, ax=ax[1])\n",
    "ax[0].set_ylabel('train/f1-score')\n",
    "ax[1].set_ylabel('test/f1-score')\n",
    "fig.tight_layout()\n",
    "fig.savefig(fig_save_dir + 'classifier-hyp-folds-f1.pdf', format='pdf', bbox_inches='tight')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2c642d40",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.11.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}