{
  "cells": [
    {
      "cell_type": "markdown",
      "source": [
        "<img align=\"left\" src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open in Colab\" title=\"Open in Google Colaboratory\"></a><p><a href=\"https://githubtocolab.com/vmcf-konfmi/MB100T01/blob/main/advanced_image_analysis_mb100t01/02_plotting/03_Statistic_Annotations_in_Seaborn_Bonus.ipynb\">"
      ],
      "metadata": {
        "id": "7jA5Vgb0tpm3"
      }
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "-TM003HVDmy9"
      },
      "source": [
        "# Adding Statistic Annotations"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "fpPtZgqIvuXz"
      },
      "source": [
        "Sources and inspiration:\n",
        "\n",
        "\n",
        "*   https://www.kaggle.com/code/tirendazacademy/penguin-dataset-data-visualization-with-seaborn#Penguin-Dataset:-Data-Visualization-with-Seaborn\n",
        "*   https://seaborn.pydata.org/tutorial/categorical.html\n",
        "* https://pandas.pydata.org/docs/user_guide/visualization.html\n",
        "* https://levelup.gitconnected.com/statistics-on-seaborn-plots-with-statannotations-2bfce0394c00\n",
        "\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "E_OiailfvxsI"
      },
      "source": [
        "If running this from Google Colab, uncomment the cell below and run it. Otherwise, just skip it."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "5saSBc40voZF"
      },
      "outputs": [],
      "source": [
        "# !pip install watermark\n",
        "# !pip install statannotations"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "cgfXd-tzqFqA",
        "pycharm": {
          "name": "#%%\n"
        }
      },
      "outputs": [],
      "source": [
        "import matplotlib.pyplot as plt\n",
        "import pandas as pd\n",
        "import seaborn as sns\n",
        "\n",
        "\n",
        "import numpy as np\n",
        "from scipy.stats import mannwhitneyu"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "y2Wl1yTAY1dp"
      },
      "source": [
        "## Seaborn with statistics annotations"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "mKQgwkRfRA-q"
      },
      "source": [
        "### Introduction\n",
        "\n",
        "Many libraries are available in Python to clean, analyze, and plot data.\n",
        "Python also has robust statistical packages which are used by thousands of other projects.\n",
        "\n",
        "That said, if you wish, basically, to add statistics to your plots, with the beautiful brackets as you can see in papers\n",
        "using R or other statistical software, there are not many options.\n",
        "\n",
        "\n",
        "In this part, we will use `statannotations`, a package to add statistical significance annotations on seaborn\n",
        "categorical plots."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "t2uiAYgNRJig"
      },
      "source": [
        "Specifically, we will answer the following questions:\n",
        "- How to add custom annotations to a seaborn plot?\n",
        "- How to automatically format previously computed p-values in several different ways, then add these to a plot in a\n",
        "  single function call?\n",
        "- How to both perform the statistical tests and add their results to a plot, optionally applying a multiple comparisons\n",
        "  correction method?"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "fWt2Xu4LRKQR"
      },
      "source": [
        "**DISCLAIMER**: This tutorial aims to describe *how to use a plot annotation library, not to teach statistics*. The\n",
        "examples are meant only to illustrate the plots, not the statistical methodology, and we will not draw any conclusions\n",
        "about the dataset explored.\n",
        "\n",
        "A correct approach would have required the careful definition of a research question based, evaluation how the data acquisitions and\n",
        "maybe, ultimately, different group comparisons and/or tests. Of course, the p-value is not the right answer for\n",
        "everything either. *But the aim is to learn how to aproach this so you can later easily reuse the notebooks, charts and even share it with your research!*"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Kd-U89tEqFp_"
      },
      "source": [
        "### Preparing the tools\n",
        "First, let's prepare the data we will use as example.\n",
        "\n",
        "We make 3 subsets from the penguins data cleaned, split by 'species'. We also split one of the species by 'sex'."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "A6Gi_GYV-8Dm"
      },
      "outputs": [],
      "source": [
        "# Load and clean penguins data\n",
        "penguins = sns.load_dataset(\"penguins\")\n",
        "penguins_cleaned = penguins.dropna()\n",
        "\n",
        "# Split penguins data by species\n",
        "Adelie_values =  penguins_cleaned[penguins_cleaned['species']=='Adelie']\n",
        "Chinstrap_values = penguins_cleaned[penguins_cleaned['species']=='Chinstrap']\n",
        "Gentoo_values = penguins_cleaned[penguins_cleaned['species']=='Gentoo']\n",
        "\n",
        "# Split 'Gentoo' species by sex\n",
        "Gentoo_values_male=Gentoo_values[Gentoo_values.sex=='Male']\n",
        "Gentoo_values_female=Gentoo_values[Gentoo_values.sex=='Female']"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "ayxl3R4BqFqU"
      },
      "source": [
        "## Using statannotations\n",
        "The general pattern is\n",
        "\n",
        "0. Decide which pairs of data you would like to annotate\n",
        "\n",
        "\n",
        "1. Instantiate an `Annotator` (or reuse it on a new plot, we'll cover that later)\n",
        "\n",
        "\n",
        "2. Configure it (text formatting, statistical test, multiple comparisons correction method...)\n",
        "\n",
        "\n",
        "3. Make the annotations (we'll cover these cases)\n",
        "\n",
        "    - By providing completely custom annotations (A)\n",
        "    - By providing pvalues to be formatted before being added to the plot (B)\n",
        "    - By applying a configured test (C)\n",
        "\n",
        "\n",
        "4. Annotate !"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "dSH6VHomrc4p"
      },
      "outputs": [],
      "source": [
        "from statannotations.Annotator import Annotator"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "J9KGqEVlqFqU"
      },
      "source": [
        "If we already have a seaborn plot (and its associated `axes`), and statistical results, or any other text we would like to\n",
        " display on the plot, these are the detailed steps required.\n",
        "\n",
        "**STEP 0**: What to compare\n",
        "\n",
        "A pre-requisite to annotating the plot, is deciding which pairs you are comparing.\n",
        "You'll pass which boxes (or bars, violins, etc) you want to annotate in a `pairs` parameter. In this case, it is the\n",
        "equivalent of `'Adelie vs Chinstrap'` and others.\n",
        "\n",
        "For statannotations, we specify this as a list of tuples like `('Adelie', 'Chinstrap')`\n",
        "\n",
        "```python\n",
        "pairs = [('Adelie', 'Chinstrap'),\n",
        "         ('Adelie', 'Gentoo'),\n",
        "         ('Chinstrap', 'Gentoo'),\n",
        "         ]\n",
        "```\n",
        "**STEP 1**: The annotator\n",
        "\n",
        "We now have all we need to instantiate the annotator\n",
        "```python\n",
        "annotator = Annotator(ax, pairs, ...)  # With ... = all parameters passed to seaborn's plotter\n",
        "```\n",
        "\n",
        "**STEP 2**: In this first example, we will not configure anything.\n",
        "\n",
        "**STEP 3**: We'll then add the raw pvalues from scipy's returned values\n",
        "```python\n",
        "\n",
        "pvalues = [mannwhitneyu(Adelie_values['bill_length_mm'], Chinstrap_values['bill_length_mm']).pvalue,\n",
        "           mannwhitneyu(Adelie_values['bill_length_mm'], Gentoo_values['bill_length_mm']).pvalue,\n",
        "           mannwhitneyu(Chinstrap_values['bill_length_mm'], Gentoo_values['bill_length_mm']).pvalue]\n",
        "```\n",
        "using\n",
        "```python\n",
        "annotator.set_custom_annotations(pvalues)\n",
        "```\n",
        "**STEP 4**: Annotate !\n",
        "```python\n",
        "annotator.annotate()\n",
        "```\n",
        "\n",
        "(*) Make sure pairs and annotations (pvalues here) are in the same order"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 504
        },
        "id": "T6RMakx085Ji",
        "outputId": "a084085e-43fb-4225-c115-9c3d0b2022b7"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "[Text(0.5, 1.0, 'Bill Length for 3 Penguin Species')]"
            ]
          },
          "execution_count": 4,
          "metadata": {},
          "output_type": "execute_result"
        },
        {
          "data": {
            "image/png": "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",
            "text/plain": [
              "<Figure size 1000x500 with 1 Axes>"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ],
      "source": [
        "figure, axes = plt.subplots(figsize=(10, 5))\n",
        "\n",
        "sns.boxplot(\n",
        "    data = Gentoo_values,\n",
        "    x = \"sex\",\n",
        "    y = \"bill_length_mm\",\n",
        "    ax = axes)\n",
        "\n",
        "axes.set(title=\"Bill Length for 3 Penguin Species\")"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 643
        },
        "id": "ixhXamiy6T67",
        "outputId": "8549b547-ac37-475c-8d87-65aebcd86e33"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "p-value annotation legend:\n",
            "      ns: p <= 1.00e+00\n",
            "       *: 1.00e-02 < p <= 5.00e-02\n",
            "      **: 1.00e-03 < p <= 1.00e-02\n",
            "     ***: 1.00e-04 < p <= 1.00e-03\n",
            "    ****: p <= 1.00e-04\n",
            "\n",
            "Female vs. Male: p=5.59e-13\n"
          ]
        },
        {
          "data": {
            "text/plain": [
              "[Text(0.5, 1.0, 'Bill Length for Gentoo, based on sex')]"
            ]
          },
          "execution_count": 7,
          "metadata": {},
          "output_type": "execute_result"
        },
        {
          "data": {
            "image/png": "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",
            "text/plain": [
              "<Figure size 1000x500 with 1 Axes>"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ],
      "source": [
        "pairs = [('Female', 'Male'),\n",
        "        #  ('data 1', 'data 2'),\n",
        "         ]\n",
        "\n",
        "# pvalues with scipy, format based on pairs:\n",
        "stat_results_GMF = [mannwhitneyu(Gentoo_values_female['bill_length_mm'], Gentoo_values_male['bill_length_mm'], alternative=\"two-sided\"),]\n",
        "pvalues = [result.pvalue for result in stat_results_GMF]\n",
        "\n",
        "formatted_pvalues = [f\"p={p:.2e}\" for p in pvalues]\n",
        "\n",
        "# Create new plot\n",
        "figure, axes = plt.subplots(figsize=(10, 5))\n",
        "\n",
        "plotting_parameters = {\n",
        "    'data':Gentoo_values,\n",
        "    'x':'sex',\n",
        "    'y':'bill_length_mm',\n",
        "}\n",
        "\n",
        "# Plot with seaborn\n",
        "sns.boxplot(ax=axes, **plotting_parameters)\n",
        "\n",
        "# Add annotations\n",
        "annotator = Annotator(ax=axes, pairs=pairs, **plotting_parameters)\n",
        "annotator.set_custom_annotations(formatted_pvalues)\n",
        "annotator.annotate()\n",
        "\n",
        "axes.set(title=\"Bill Length for Gentoo, based on sex\")"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "OV1g1q3FqFqY"
      },
      "source": [
        "### Use statannotations to apply scipy test"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "tEY7A5YlqFqY"
      },
      "source": [
        "Finally, `statannotations` can take care of most of the steps required to run the test by calling `scipy.stats` directly\n",
        "and annotate the plot.\n",
        "The available options are\n",
        "\n",
        "- Mann-Whitney\n",
        "- t-test (independent and paired)\n",
        "- Welch's t-test\n",
        "- Levene test\n",
        "- Wilcoxon test\n",
        "- Kruskal-Wallis test\n",
        "\n",
        "We will cover how to use a test that is not one of those already interfaced in `statannotations`.\n",
        "If you are curious, you can also take a look at the usage\n",
        "[notebook](https://github.com/trevismd/statannotations/blob/master/usage/example.ipynb) in the project repository."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "HTqNfcpdCKNr"
      },
      "source": [
        "### Simple"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 556
        },
        "id": "uNILgwc4_3Uw",
        "outputId": "2ee46cf9-802d-4653-806a-947b2f6aebb1"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Adelie vs. Chinstrap: Mann-Whitney-Wilcoxon test two-sided, P_val:9.063e-31 U_stat=1.000e+02\n",
            "Chinstrap vs. Gentoo: Mann-Whitney-Wilcoxon test two-sided, P_val:2.947e-03 U_stat=5.105e+03\n",
            "Adelie vs. Gentoo: Mann-Whitney-Wilcoxon test two-sided, P_val:2.022e-42 U_stat=2.160e+02\n"
          ]
        },
        {
          "data": {
            "text/plain": [
              "[Text(0.5, 1.0, 'Bill Length Comparison')]"
            ]
          },
          "execution_count": 8,
          "metadata": {},
          "output_type": "execute_result"
        },
        {
          "data": {
            "image/png": "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",
            "text/plain": [
              "<Figure size 1000x500 with 1 Axes>"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ],
      "source": [
        "# Create new plot\n",
        "figure, axes = plt.subplots(figsize=(10, 5))\n",
        "\n",
        "plotting_parameters = {\n",
        "    'data': penguins_cleaned,\n",
        "    'x':'species',\n",
        "    'y':'bill_length_mm',\n",
        "}\n",
        "\n",
        "pairs = [('Adelie', 'Chinstrap'),\n",
        "         ('Adelie', 'Gentoo'),\n",
        "         ('Chinstrap', 'Gentoo'),\n",
        "         ]\n",
        "\n",
        "\n",
        "# Plot with seaborn\n",
        "sns.boxplot(ax=axes, **plotting_parameters)\n",
        "\n",
        "# Add annotations\n",
        "annotator.new_plot(ax=axes, pairs=pairs, **plotting_parameters)\n",
        "annotator.configure(test='Mann-Whitney', text_format=\"simple\", verbose=True).apply_and_annotate()\n",
        "\n",
        "axes.set(title=\"Bill Length Comparison\")"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Nlkn34-xCGjC"
      },
      "source": [
        "### Full"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 556
        },
        "id": "zOEObtlVA57c",
        "outputId": "d188e044-be5a-4b38-8610-dbe4a7ddc5a9"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Adelie vs. Chinstrap: Mann-Whitney-Wilcoxon test two-sided, P_val:9.063e-31 U_stat=1.000e+02\n",
            "Chinstrap vs. Gentoo: Mann-Whitney-Wilcoxon test two-sided, P_val:2.947e-03 U_stat=5.105e+03\n",
            "Adelie vs. Gentoo: Mann-Whitney-Wilcoxon test two-sided, P_val:2.022e-42 U_stat=2.160e+02\n"
          ]
        },
        {
          "data": {
            "text/plain": [
              "[Text(0.5, 1.0, 'Bill Length Comparison')]"
            ]
          },
          "execution_count": 9,
          "metadata": {},
          "output_type": "execute_result"
        },
        {
          "data": {
            "image/png": "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",
            "text/plain": [
              "<Figure size 1000x500 with 1 Axes>"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ],
      "source": [
        "# Create new plot\n",
        "figure, axes = plt.subplots(figsize=(10, 5))\n",
        "\n",
        "plotting_parameters = {\n",
        "    'data': penguins_cleaned,\n",
        "    'x':'species',\n",
        "    'y':'bill_length_mm',\n",
        "}\n",
        "\n",
        "pairs = [('Adelie', 'Chinstrap'),\n",
        "         ('Adelie', 'Gentoo'),\n",
        "         ('Chinstrap', 'Gentoo'),\n",
        "         ]\n",
        "\n",
        "\n",
        "# Plot with seaborn\n",
        "sns.boxplot(ax=axes, **plotting_parameters)\n",
        "\n",
        "# Add annotations\n",
        "annotator.new_plot(axes, pairs=pairs, **plotting_parameters)\n",
        "annotator.configure(test='Mann-Whitney', text_format=\"full\", verbose=True).apply_and_annotate()\n",
        "\n",
        "axes.set(title=\"Bill Length Comparison\")"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "BeRm6H8hCBTi"
      },
      "source": [
        "### Star"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 678
        },
        "id": "6qbsWRMhA7E2",
        "outputId": "f5232a8d-8719-407c-ad73-3393b3b27450"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "p-value annotation legend:\n",
            "      ns: p <= 1.00e+00\n",
            "       *: 1.00e-02 < p <= 5.00e-02\n",
            "      **: 1.00e-03 < p <= 1.00e-02\n",
            "     ***: 1.00e-04 < p <= 1.00e-03\n",
            "    ****: p <= 1.00e-04\n",
            "\n",
            "Adelie vs. Chinstrap: Mann-Whitney-Wilcoxon test two-sided, P_val:9.063e-31 U_stat=1.000e+02\n",
            "Chinstrap vs. Gentoo: Mann-Whitney-Wilcoxon test two-sided, P_val:2.947e-03 U_stat=5.105e+03\n",
            "Adelie vs. Gentoo: Mann-Whitney-Wilcoxon test two-sided, P_val:2.022e-42 U_stat=2.160e+02\n"
          ]
        },
        {
          "data": {
            "text/plain": [
              "[Text(0.5, 1.0, 'Bill Length Comparison')]"
            ]
          },
          "execution_count": 10,
          "metadata": {},
          "output_type": "execute_result"
        },
        {
          "data": {
            "image/png": "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",
            "text/plain": [
              "<Figure size 1000x500 with 1 Axes>"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ],
      "source": [
        "# Create new plot\n",
        "figure, axes = plt.subplots(figsize=(10, 5))\n",
        "\n",
        "plotting_parameters = {\n",
        "    'data': penguins_cleaned,\n",
        "    'x':'species',\n",
        "    'y':'bill_length_mm',\n",
        "}\n",
        "\n",
        "pairs = [('Adelie', 'Chinstrap'),\n",
        "         ('Adelie', 'Gentoo'),\n",
        "         ('Chinstrap', 'Gentoo'),\n",
        "         ]\n",
        "\n",
        "\n",
        "# Plot with seaborn\n",
        "sns.boxplot(ax=axes, **plotting_parameters)\n",
        "\n",
        "# Add annotations\n",
        "annotator.new_plot(ax=axes, pairs=pairs, **plotting_parameters)\n",
        "annotator.configure(test='Mann-Whitney', text_format=\"star\", verbose=True).apply_and_annotate()\n",
        "\n",
        "axes.set(title=\"Bill Length Comparison\")"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 678
        },
        "id": "6eZcf_W7DCuz",
        "outputId": "15086014-b0e8-4c56-ee6d-ef40ec877760"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "p-value annotation legend:\n",
            "      ns: p <= 1.00e+00\n",
            "       *: 1.00e-02 < p <= 5.00e-02\n",
            "      **: 1.00e-03 < p <= 1.00e-02\n",
            "     ***: 1.00e-04 < p <= 1.00e-03\n",
            "    ****: p <= 1.00e-04\n",
            "\n",
            "Adelie vs. Chinstrap: Mann-Whitney-Wilcoxon test two-sided, P_val:9.063e-31 U_stat=1.000e+02\n",
            "Chinstrap vs. Gentoo: Mann-Whitney-Wilcoxon test two-sided, P_val:2.947e-03 U_stat=5.105e+03\n",
            "Adelie vs. Gentoo: Mann-Whitney-Wilcoxon test two-sided, P_val:2.022e-42 U_stat=2.160e+02\n"
          ]
        },
        {
          "data": {
            "text/plain": [
              "[Text(0.5, 1.0, 'Bill Length Comparison of Penguin Species')]"
            ]
          },
          "execution_count": 11,
          "metadata": {},
          "output_type": "execute_result"
        },
        {
          "data": {
            "image/png": "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",
            "text/plain": [
              "<Figure size 1000x500 with 1 Axes>"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ],
      "source": [
        "# Create new plot\n",
        "figure, axes = plt.subplots(figsize=(10, 5))\n",
        "\n",
        "plotting_parameters = {\n",
        "    'data':penguins_cleaned,\n",
        "    'x':'species',\n",
        "    'y':'bill_length_mm',\n",
        "}\n",
        "\n",
        "pairs = [('Adelie', 'Chinstrap'),\n",
        "         ('Adelie', 'Gentoo'),\n",
        "         ('Chinstrap', 'Gentoo'),\n",
        "         ]\n",
        "\n",
        "\n",
        "# Plot with seaborn\n",
        "sns.violinplot(ax=axes, **plotting_parameters)\n",
        "\n",
        "# Add annotations\n",
        "annotator.new_plot(ax=axes, pairs=pairs, **plotting_parameters)\n",
        "annotator.configure(test='Mann-Whitney', text_format=\"star\", verbose=True).apply_and_annotate()\n",
        "\n",
        "axes.set(title=\"Bill Length Comparison of Penguin Species\")"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "FWFdMvzuDbkM"
      },
      "outputs": [],
      "source": [
        "figure.savefig('violin_annotated_PNG.png', dpi=300)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "wyUoyKXHj2UQ"
      },
      "source": [
        "---"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "iH1jL0baGMJW",
        "outputId": "dd7307d6-eb5b-4ed0-c233-32574ddb0c40"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Last updated: 2023-08-25T19:06:19.247868+02:00\n",
            "\n",
            "Python implementation: CPython\n",
            "Python version       : 3.9.17\n",
            "IPython version      : 8.14.0\n",
            "\n",
            "Compiler    : MSC v.1929 64 bit (AMD64)\n",
            "OS          : Windows\n",
            "Release     : 10\n",
            "Machine     : AMD64\n",
            "Processor   : Intel64 Family 6 Model 165 Stepping 2, GenuineIntel\n",
            "CPU cores   : 16\n",
            "Architecture: 64bit\n",
            "\n",
            "watermark      : 2.4.3\n",
            "numpy          : 1.23.5\n",
            "pandas         : 2.0.3\n",
            "seaborn        : 0.12.2\n",
            "matplotlib     : 3.7.2\n",
            "scipy          : 1.11.2\n",
            "statannotations: 0.4.4\n",
            "\n"
          ]
        }
      ],
      "source": [
        "from watermark import watermark\n",
        "watermark(iversions=True, globals_=globals())\n",
        "print(watermark())\n",
        "print(watermark(packages=\"watermark,numpy,pandas,seaborn,matplotlib,scipy,statannotations\"))"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "loBmozTxtQBi"
      },
      "outputs": [],
      "source": []
    }
  ],
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "display_name": "Python 3",
      "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": "3.9.17"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}