🎨 make data work independent of location, label plots better

RasmussenLab · Nov 8, 2024 · eb9c3a0 · eb9c3a0
1 parent 6986e38
commit eb9c3a0
Show file tree

Hide file tree

Showing 2 changed files with 15 additions and 13 deletions.
diff --git a/project/04_1_train_pimms_models.ipynb b/project/04_1_train_pimms_models.ipynb
@@ -55,12 +55,11 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import os\n",
-    "\n",
-    "IN_COLAB = 'COLAB_GPU' in os.environ\n",
+    "from pathlib import Path\n",
     "\n",
-    "fn_intensities = 'data/dev_datasets/HeLa_6070/protein_groups_wide_N50.csv'\n",
-    "if IN_COLAB:\n",
+    "fn_intensities = Path('data/dev_datasets/HeLa_6070/protein_groups_wide_N50.csv')\n",
+    "if not fn_intensities.exists():\n",
+    "    print(\"Use example data from GitHub.\")\n",
     "    fn_intensities = ('https://raw.githubusercontent.com/RasmussenLab/pimms/main/'\n",
     "                      'project/data/dev_datasets/HeLa_6070/protein_groups_wide_N50.csv')"
    ]
@@ -651,7 +650,8 @@
     "        feat_medians=splits.train_X.median(),\n",
     "        ax=ax,\n",
     "        metric_name='MAE',\n",
-    "        palette=color_model_mapping)"
+    "        palette=color_model_mapping)\n",
+    "    ax.set_ylabel('Mean aboslute error (MAE)')"
    ]
   },
   {
@@ -724,7 +724,8 @@
     "                                ),\n",
     "    color=color_model_mapping[model_selected],\n",
     "    alpha=1)\n",
-    "_ = ax.legend()"
+    "_ = ax.legend()\n",
+    "ax.set_xlabel('log2 intensity bin')"
    ]
   }
  ],
@@ -749,7 +750,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.17"
+   "version": "3.11.9"
   },
   "mystnb": {
    "execution_raise_on_error": true,

diff --git a/project/04_1_train_pimms_models.py b/project/04_1_train_pimms_models.py
@@ -30,12 +30,11 @@
 # Specify example data:
 
 # %%
-import os
-
-IN_COLAB = 'COLAB_GPU' in os.environ
+from pathlib import Path
 
-fn_intensities = 'data/dev_datasets/HeLa_6070/protein_groups_wide_N50.csv'
-if IN_COLAB:
+fn_intensities = Path('data/dev_datasets/HeLa_6070/protein_groups_wide_N50.csv')
+if not fn_intensities.exists():
+    print("Use example data from GitHub.")
     fn_intensities = ('https://raw.githubusercontent.com/RasmussenLab/pimms/main/'
                       'project/data/dev_datasets/HeLa_6070/protein_groups_wide_N50.csv')
 
@@ -308,6 +307,7 @@
         ax=ax,
         metric_name='MAE',
         palette=color_model_mapping)
+    ax.set_ylabel('Mean aboslute error (MAE)')
 
 # %% [markdown]
 # replace predicted values with validation data values
@@ -349,3 +349,4 @@
     color=color_model_mapping[model_selected],
     alpha=1)
 _ = ax.legend()
+ax.set_xlabel('log2 intensity bin')