🎨 Supp. Fig. 5b,c - overlay bars with actual measurments

RasmussenLab · Apr 11, 2024 · 59c8ddb · 59c8ddb
1 parent a677cce
commit 59c8ddb
Show file tree

Hide file tree

Showing 3 changed files with 70 additions and 32 deletions.
diff --git a/project/03_1_best_models_comparison.ipynb b/project/03_1_best_models_comparison.ipynb
@@ -6,18 +6,18 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "import logging\n",
     "from pathlib import Path\n",
-    "import pandas as pd\n",
     "\n",
     "import matplotlib.pyplot as plt\n",
+    "import pandas as pd\n",
     "import seaborn as sns\n",
     "\n",
-    "import vaep.pandas\n",
     "import vaep.nb\n",
-    "\n",
-    "import logging\n",
+    "import vaep.pandas\n",
     "import vaep.plotting\n",
     "from vaep.logging import setup_logger\n",
+    "\n",
     "logger = setup_logger(logger=logging.getLogger('vaep'), level=10)\n",
     "\n",
     "plt.rcParams['figure.figsize'] = [4.0, 2.0]\n",
@@ -164,16 +164,34 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "ax = sns.barplot(x='data level',\n",
-    "                 y='MAE',\n",
-    "                 hue='model',\n",
-    "                 order=IDX[0],\n",
-    "                 palette=vaep.plotting.defaults.color_model_mapping,\n",
-    "                 ci=95,\n",
-    "                 errwidth=1.5,\n",
-    "                 data=view_long)\n",
-    "ax.set_xlabel('')\n",
-    "fig = ax.get_figure()"
+    "# individual points overlaid on bar plot:\n",
+    "# seaborn 12.2\n",
+    "# https://stackoverflow.com/a/69398767/9684872\n",
+    "sns.set_theme(context='paper', )  # font_scale=.8)\n",
+    "sns.set_style(\"whitegrid\")\n",
+    "g = sns.catplot(x=\"data level\", y=\"MAE\", hue='model', data=view_long,\n",
+    "                kind=\"bar\",\n",
+    "                errorbar=\"ci\",  # ! 95% confidence interval bootstrapped (using 1000 draws by default)\n",
+    "                edgecolor=\"black\",\n",
+    "                errcolor=\"black\",\n",
+    "                hue_order=IDX[1],\n",
+    "                order=IDX[0],\n",
+    "                palette=vaep.plotting.defaults.color_model_mapping,\n",
+    "                alpha=0.9,\n",
+    "                height=2,  # set the height of the figure\n",
+    "                aspect=1.8  # set the aspect ratio of the figure\n",
+    "                )\n",
+    "\n",
+    "# map data to stripplot\n",
+    "g.map(sns.stripplot, 'data level', 'MAE', 'model',\n",
+    "      hue_order=IDX[1], order=IDX[0],\n",
+    "      palette=vaep.plotting.defaults.color_model_mapping,\n",
+    "      dodge=True, alpha=1, ec='k', linewidth=1,\n",
+    "      s=2)\n",
+    "\n",
+    "fig = g.figure\n",
+    "ax = fig.get_axes()[0]\n",
+    "_ = ax.set_xlabel('')"
    ]
   },
   {
@@ -182,7 +200,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "vaep.savefig(fig, FOLDER / \"model_performance_repeated_runs.pdf\")"
+    "vaep.savefig(fig, FOLDER / \"model_performance_repeated_runs.pdf\", tight_layout=False)"
    ]
   },
   {

diff --git a/project/03_1_best_models_comparison.py b/project/03_1_best_models_comparison.py
@@ -14,18 +14,18 @@
 # ---
 
 # %%
+import logging
 from pathlib import Path
-import pandas as pd
 
 import matplotlib.pyplot as plt
+import pandas as pd
 import seaborn as sns
 
-import vaep.pandas
 import vaep.nb
-
-import logging
+import vaep.pandas
 import vaep.plotting
 from vaep.logging import setup_logger
+
 logger = setup_logger(logger=logging.getLogger('vaep'), level=10)
 
 plt.rcParams['figure.figsize'] = [4.0, 2.0]
@@ -102,19 +102,37 @@
 view_long
 
 # %%
-ax = sns.barplot(x='data level',
-                 y='MAE',
-                 hue='model',
-                 order=IDX[0],
-                 palette=vaep.plotting.defaults.color_model_mapping,
-                 ci=95,
-                 errwidth=1.5,
-                 data=view_long)
-ax.set_xlabel('')
-fig = ax.get_figure()
+# individual points overlaid on bar plot:
+# seaborn 12.2
+# https://stackoverflow.com/a/69398767/9684872
+sns.set_theme(context='paper', )  # font_scale=.8)
+sns.set_style("whitegrid")
+g = sns.catplot(x="data level", y="MAE", hue='model', data=view_long,
+                kind="bar",
+                errorbar="ci",  # ! 95% confidence interval bootstrapped (using 1000 draws by default)
+                edgecolor="black",
+                errcolor="black",
+                hue_order=IDX[1],
+                order=IDX[0],
+                palette=vaep.plotting.defaults.color_model_mapping,
+                alpha=0.9,
+                height=2,  # set the height of the figure
+                aspect=1.8  # set the aspect ratio of the figure
+                )
+
+# map data to stripplot
+g.map(sns.stripplot, 'data level', 'MAE', 'model',
+      hue_order=IDX[1], order=IDX[0],
+      palette=vaep.plotting.defaults.color_model_mapping,
+      dodge=True, alpha=1, ec='k', linewidth=1,
+      s=2)
+
+fig = g.figure
+ax = fig.get_axes()[0]
+_ = ax.set_xlabel('')
 
 # %%
-vaep.savefig(fig, FOLDER / "model_performance_repeated_runs.pdf")
+vaep.savefig(fig, FOLDER / "model_performance_repeated_runs.pdf", tight_layout=False)
 
 # %%
 writer.close()

diff --git a/vaep/plotting/__init__.py b/vaep/plotting/__init__.py
@@ -45,14 +45,16 @@
 
 def _savefig(fig, name, folder: pathlib.Path = '.',
              pdf=True,
-             dpi=300  # default 'figure'
+             dpi=300,  # default 'figure',
+             tight_layout=True,
              ):
     """Save matplotlib Figure (having method `savefig`) as pdf and png."""
     folder = pathlib.Path(folder)
     fname = folder / name
     folder = fname.parent  # in case name specifies folders
     folder.mkdir(exist_ok=True, parents=True)
-    fig.tight_layout()
+    if tight_layout:
+        fig.tight_layout()
     fig.savefig(fname.with_suffix('.png'), dpi=dpi)
     if pdf:
         fig.savefig(fname.with_suffix('.pdf'), dpi=dpi)