Remove unused cp features

0.download_data/download_data.ipynb

@@ -30,7 +30,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "labeled_data_hash = \"639e3db8e5b828f4f24f2d0817f94dafd6a7096e\"\n",
+    "labeled_data_hash = \"20369033f579dca1334cb2c58a1c6d532322f93e\"\n",
     "labeled_data_url = f\"https://raw.github.com/WayScience/mitocheck_data/{labeled_data_hash}/3.normalize_data/normalized_data/training_data.csv.gz\""
    ]
   },
@@ -357,7 +357,7 @@
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
-       "<p>2916 rows × 1458 columns</p>\n",
+       "<p>2916 rows × 1450 columns</p>\n",
        "</div>"
       ],
       "text/plain": [
@@ -452,7 +452,7 @@
        "2914              -2.037700               0.667556               2.438798  \n",
        "2915              -0.574826               1.004447               1.320133  \n",
        "\n",
-       "[2916 rows x 1458 columns]"
+       "[2916 rows x 1450 columns]"
       ]
      },
      "execution_count": 3,
@@ -543,7 +543,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.13"
+   "version": "3.9.16"
   },
   "orig_nbformat": 4,
   "vscode": {

0.download_data/scripts/nbconverted/download_data.py

@@ -15,7 +15,7 @@
 # In[2]:
 
 
-labeled_data_hash = "e1f86cd007657f8247310b78df92891b22e51621"
+labeled_data_hash = "20369033f579dca1334cb2c58a1c6d532322f93e"
 labeled_data_url = f"https://raw.github.com/WayScience/mitocheck_data/{labeled_data_hash}/3.normalize_data/normalized_data/training_data.csv.gz"
 
 

1.split_data/split_data.ipynb

@@ -40,7 +40,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "(2862, 1458)\n"
+      "(2862, 1450)\n"
      ]
     }
    ],
@@ -60,8 +60,8 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Training data has shape: (2432, 1458)\n",
-      "Testing data has shape: (430, 1458)\n"
+      "Training data has shape: (2432, 1450)\n",
+      "Testing data has shape: (430, 1450)\n"
      ]
     }
    ],
@@ -250,7 +250,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.13"
+   "version": "3.9.16"
   },
   "orig_nbformat": 4,
   "vscode": {

2.train_model/train_multi_class_models.ipynb

@@ -358,7 +358,7 @@
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
-       "<p>2432 rows × 1458 columns</p>\n",
+       "<p>2432 rows × 1450 columns</p>\n",
        "</div>"
       ],
       "text/plain": [
@@ -453,7 +453,7 @@
        "2914              -2.037700               0.667556               2.438798  \n",
        "2915              -0.574826               1.004447               1.320133  \n",
        "\n",
-       "[2432 rows x 1458 columns]"
+       "[2432 rows x 1450 columns]"
       ]
      },
      "execution_count": 2,
@@ -501,34 +501,34 @@
       "Parameters being tested during grid search: {'C': array([1.e-03, 1.e-02, 1.e-01, 1.e+00, 1.e+01, 1.e+02, 1.e+03]), 'l1_ratio': array([0. , 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1. ])}\n",
       "\n",
       "Training final model on CP features...\n",
-      "X has shape (2432, 165), y has shape (2432,)\n",
-      "Best parameters: {'C': 1.0, 'l1_ratio': 0.30000000000000004}\n",
-      "Score of best estimator: 0.8160827228903825\n",
+      "X has shape (2432, 157), y has shape (2432,)\n",
+      "Best parameters: {'C': 10.0, 'l1_ratio': 0.2}\n",
+      "Score of best estimator: 0.814474832382009\n",
       "\n",
       "Training final model on DP features...\n",
       "X has shape (2432, 1280), y has shape (2432,)\n",
       "Best parameters: {'C': 1.0, 'l1_ratio': 1.0}\n",
       "Score of best estimator: 0.7383705853823289\n",
       "\n",
       "Training final model on CP_and_DP features...\n",
-      "X has shape (2432, 1445), y has shape (2432,)\n",
+      "X has shape (2432, 1437), y has shape (2432,)\n",
       "Best parameters: {'C': 0.1, 'l1_ratio': 0.30000000000000004}\n",
-      "Score of best estimator: 0.8356118079369516\n",
+      "Score of best estimator: 0.8348844749097128\n",
       "\n",
       "Training shuffled_baseline model on CP features...\n",
-      "X has shape (2432, 165), y has shape (2432,)\n",
-      "Best parameters: {'C': 0.01, 'l1_ratio': 0.0}\n",
-      "Score of best estimator: 0.10215136994867735\n",
+      "X has shape (2432, 157), y has shape (2432,)\n",
+      "Best parameters: {'C': 0.1, 'l1_ratio': 0.30000000000000004}\n",
+      "Score of best estimator: 0.10104514628410396\n",
       "\n",
       "Training shuffled_baseline model on DP features...\n",
       "X has shape (2432, 1280), y has shape (2432,)\n",
-      "Best parameters: {'C': 0.001, 'l1_ratio': 0.0}\n",
-      "Score of best estimator: 0.0943542807030858\n",
+      "Best parameters: {'C': 0.1, 'l1_ratio': 1.0}\n",
+      "Score of best estimator: 0.10077527791551757\n",
       "\n",
       "Training shuffled_baseline model on CP_and_DP features...\n",
-      "X has shape (2432, 1445), y has shape (2432,)\n",
-      "Best parameters: {'C': 0.1, 'l1_ratio': 0.9}\n",
-      "Score of best estimator: 0.09320506604460571\n",
+      "X has shape (2432, 1437), y has shape (2432,)\n",
+      "Best parameters: {'C': 0.1, 'l1_ratio': 0.1}\n",
+      "Score of best estimator: 0.10170801022131686\n",
       "\n"
      ]
     }
@@ -610,7 +610,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.13"
+   "version": "3.9.16"
   },
   "orig_nbformat": 4,
   "vscode": {