From bb63dec94e1d1f0cbd44bb06560342b6acf61766 Mon Sep 17 00:00:00 2001 From: JAnns98 <88357898+JAnns98@users.noreply.github.com> Date: Wed, 20 Mar 2024 16:15:05 +0800 Subject: [PATCH] Update 07-forest_plot.ipynb Many spelling and wording/layout changes. Still WIP --- nbs/tutorials/07-forest_plot.ipynb | 73 ++++++++++-------------------- 1 file changed, 23 insertions(+), 50 deletions(-) diff --git a/nbs/tutorials/07-forest_plot.ipynb b/nbs/tutorials/07-forest_plot.ipynb index 82afbbca..0d3c9d22 100644 --- a/nbs/tutorials/07-forest_plot.ipynb +++ b/nbs/tutorials/07-forest_plot.ipynb @@ -17,9 +17,9 @@ "id": "cfdb7e31", "metadata": {}, "source": [ - "Version 2023.02.14, DABEST also supports the comparison and analysis of different delta-delta analysis through a function called \"forest_plot\". \n", + "Version 2023.02.14, DABEST now supports the comparison of different delta-delta or mini-meta analyses through a function called \"forest_plot\". \n", "\n", - "Many experimental designs investigate the effects of two interacting independent variables on a dependent variable. The delta-delta effect size enables us distill the net effect of the two variables. \n", + "Many experimental designs investigate the effects of two interacting independent variables on a dependent variable. The delta-delta effect size enables us to distill the net effect of the two variables. \n", "\n", "\n", "Consider 3 experiments where in each of the experiment we test the efficacy of 3 drugs named ``Drug1``, ``Drug2`` , and ``Drug3`` on a disease-causing mutation M based on disease metric Y. The greater the value Y has, the more severe the disease phenotype is. Phenotype Y has been shown to be caused by a gain-of-function mutation M, so we expect a difference between wild type (W) subjects and mutant subjects (M). Now, we want to know whether this effect is ameliorated by the administration of Drug treatment. We also administer a placebo as a control. In theory, we only expect Drug to have an effect on the M group, although in practice, many drugs have non-specific effects on healthy populations too." @@ -349,32 +349,29 @@ "id": "982afbdb", "metadata": {}, "source": [ - "Important Inputs:\n", + "Key Parameters:\n", "\n", - "1. A list of contrast objects \n", + "- ``contrasts``: A list of contrast objects \n", "\n", - "2. contrast_labels e.g. ``['Drug1', 'Drug2', 'Drug3']``\n", + "- ``contrast_type``: Select between ``\"delta2\"`` (for delta-delta) or ``\"mini_meta\"`` for mini-meta \n", "\n", - "3. title: default is ``\"ΔΔ Forest\"``\n", + "- ``contrast_labels``: A list of labels for the contrast objects. E.g., ``['Drug1', 'Drug2', 'Drug3']``\n", "\n", - "4. y_label: default as ``\"value\"``, please change it according to your measurement units/ types\n", + "- ``effect_size``: Select the effect size metric from ``\"mean_diff\", \"median_diff\", \"cliffs_delta\", \"cohens_d\", \ + \"hedges_g\", or \"delta_g\"``. The default is ``\"mean_diff\"``\n", "\n", - "5. contrast_type ``delta-delta`` and ``mini-meta`` are supported\n", + "- ``ylabel``: The axis label of dependent variable (Y-axis for vertical layout, X-axis for horizontal layout). The default is ``\"value\"``\n", "\n", - "6. Which effect size to plot (default is ``delta-delta mean-diff``, but you can specify which effect size you want to use)\\n\n", + "- ``title``: The plot title. The default is ``\"ΔΔ Forest\"``\n", "\n", - "7. Axes to put the plot into existing figures \\n\n", + "- ``ax``: Specify a matplotlib axes to put the plot into existing figures \n", "\n", - "8. The argument ``horizontal`` is a boolean input (``True``/ ``False``) \\n\n", + "- ``horizontal``: A boolean input (``True``/ ``False``) to adjust the plot orientation. The default is vertical orientation (``False``) \n", "\n", - " default is ``vertical``, (``False``) that changes the default orientation, \\n\n", - " \n", - " if ``True`` the delta-delta values will be reflected on the x axis and the delta plots will be plotted horizontally. \\n\n", - "9. Plot kwargs are supported such as violin plot kwargs, fontsize, marker_size, ci_line_width\n", + "- ``custom_palette`: A list of colors, one for each contrast object. E.g., ``[\'gray\', \'blue\', \'green\']``\n", "\n", - "output:\n", + "- Additional kwargs are supported such as ``violin_kwargs``, ``fontsize``, ``marker_size``, ``ci_line_width``, ``rotation_for_xlabels``, ``alpha_violin_plot``, ``remove_spines``, and ``additional_plotting_kwargs``\n", "\n", - "- A plot with horizontally/vertically laid out half violin plots of each of the prescribed delta bootstraps. \n" ] }, { @@ -382,7 +379,7 @@ "id": "06b93055", "metadata": {}, "source": [ - "#### Vertical (default) Layout" + "#### Vertical Layout (default)" ] }, { @@ -438,20 +435,6 @@ " horizontal=True);\n" ] }, - { - "cell_type": "markdown", - "id": "dc49a603", - "metadata": {}, - "source": [ - "Additiionall, for aesthetics and labels, you can use:\n", - "\n", - "1. The ``custom_palette`` argument to specify the colors you would like to indicate each experiment in a list \\n\n", - " e.g [\"gray\", \"blue\", \"green\" ].\n", - " \n", - "2. Additionally. the argument ``ylabel`` should be specified to specify the unit or \n", - " the exact name of the measurement of experiments, for example \"delta_deltas\", the default is \"value\"" - ] - }, { "cell_type": "markdown", "id": "4100ba2c", @@ -480,7 +463,7 @@ "source": [ "forest2_vertical = forest_plot(paired_contrasts, \n", " contrast_labels =['Drug1', 'Drug2', 'Drug3'], \n", - " custom_palette= ['gray', 'blue', 'green' ], \n", + " custom_palette= ['gray', 'blue', 'green'], \n", " effect_size='delta_g');" ] }, @@ -505,7 +488,7 @@ "\n", "forest2_horizontal = forest_plot(paired_contrasts, \n", " contrast_labels =['Drug1', 'Drug2', 'Drug3'], \n", - " custom_palette= ['gray', 'blue', 'green' ],\n", + " custom_palette= ['gray', 'blue', 'green'],\n", " horizontal=True, effect_size='delta_g');\n", "\n", "\n" @@ -516,15 +499,7 @@ "id": "6787aa97", "metadata": {}, "source": [ - "### Using existing axis \"ax\" as the optional input to plot forest_plot \\n\n", - "\n", - "\n", - "\n", - "With other kinds of dabest plots side by side or in other possible orientations, \\n\n", - "\n", - "We will specify the x_labels that we want to indicate in a list of strings and parse it as the argument contrast_labels, \\n\n", - "\n", - "for example ['Drug1', 'Drug2', 'Drug3']." + "## Embedding forest plots into existing axes with the ``ax`` parameter\n", ] }, { @@ -532,7 +507,7 @@ "id": "180cae3a", "metadata": {}, "source": [ - "### Two forest plots plotted together in one axis" + "### Two forest plots plotted together in one figure" ] }, { @@ -577,7 +552,7 @@ "id": "829f0d03", "metadata": {}, "source": [ - "### Four different plots, 3 ``delta-delta`` and 1 ``forest plot``" + "### A forest plot added as a subfigure with a figure with a variety of DABEST plots" ] }, { @@ -652,9 +627,7 @@ "id": "964471ab", "metadata": {}, "source": [ - "## Forest plot also supports:\n", - "\n", - "### ``mini-meta`` comparisons and with the contrast type changed to ``\"mini_meta_delta\"``" + "## Forest plot of mini-meta:\n", ] }, { @@ -742,7 +715,7 @@ "id": "e04e1ac4", "metadata": {}, "source": [ - "## Use the contrast list and forest_plot() function to generate figures" + "## Generate the Figure" ] }, { @@ -750,7 +723,7 @@ "id": "c760a179", "metadata": {}, "source": [ - "### Verticle (default) Layout" + "### Vertical Layout (default)" ] }, {