From 0306f28a68c5abf47027ad9c4d5e3b70177daa5f Mon Sep 17 00:00:00 2001
From: nuluh <dam.ar@outlook.com>
Date: Tue, 3 Sep 2024 11:09:47 +0700
Subject: [PATCH] docs(notebooks): add `extract_numbers` docstring

---
 code/notebooks/03_feature_extraction.ipynb | 153 +++------------------
 1 file changed, 19 insertions(+), 134 deletions(-)

diff --git a/code/notebooks/03_feature_extraction.ipynb b/code/notebooks/03_feature_extraction.ipynb
index b21cbb2..c32d240 100644
--- a/code/notebooks/03_feature_extraction.ipynb
+++ b/code/notebooks/03_feature_extraction.ipynb
@@ -302,7 +302,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -325,12 +325,25 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
     "# Define a function to extract numbers from a filename that later used as labels features\n",
     "def extract_numbers(filename):\n",
+    "    '''\n",
+    "    Extract numbers from a filename\n",
+    "\n",
+    "    Parameters\n",
+    "    ----------\n",
+    "    filename : str\n",
+    "        The filename to extract numbers from\n",
+    "\n",
+    "    Returns\n",
+    "    -------\n",
+    "    list\n",
+    "        A list of extracted numbers: [damage_number, test_number, sensor_number]\n",
+    "    '''\n",
     "    # Find all occurrences of one or more digits in the filename\n",
     "    numbers = re.findall(r'\\d+', filename)\n",
     "    # Convert the list of number strings to integers\n",
@@ -372,7 +385,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "data_dir = \"../../data/raw\"\n",
+    "data_dir = \"../../data/QUGS/raw\"\n",
     "# Extract features\n",
     "df1 = build_features(data_dir, sensor=1)\n",
     "df2 = build_features(data_dir, sensor=2)"
@@ -411,145 +424,17 @@
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
-       "      <th>Mean</th>\n",
-       "      <th>Max</th>\n",
-       "      <th>Peak (Pm)</th>\n",
-       "      <th>Peak-to-Peak (Pk)</th>\n",
-       "      <th>RMS</th>\n",
-       "      <th>Variance</th>\n",
-       "      <th>Standard Deviation</th>\n",
-       "      <th>Power</th>\n",
-       "      <th>Crest Factor</th>\n",
-       "      <th>Form Factor</th>\n",
-       "      <th>Pulse Indicator</th>\n",
-       "      <th>Margin</th>\n",
-       "      <th>Kurtosis</th>\n",
-       "      <th>Skewness</th>\n",
-       "      <th>label</th>\n",
-       "      <th>filename</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>-0.075377</td>\n",
-       "      <td>1.466510</td>\n",
-       "      <td>2.254903</td>\n",
-       "      <td>3.721414</td>\n",
-       "      <td>1.037986</td>\n",
-       "      <td>1.071734</td>\n",
-       "      <td>1.091245</td>\n",
-       "      <td>1.077416</td>\n",
-       "      <td>2.172382</td>\n",
-       "      <td>-13.770555</td>\n",
-       "      <td>-29.914909</td>\n",
-       "      <td>2.764892</td>\n",
-       "      <td>2.817839</td>\n",
-       "      <td>-0.649122</td>\n",
-       "      <td>1</td>\n",
-       "      <td>D1_TEST01_1.csv</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>-0.227331</td>\n",
-       "      <td>1.307743</td>\n",
-       "      <td>1.575323</td>\n",
-       "      <td>2.883067</td>\n",
-       "      <td>0.953077</td>\n",
-       "      <td>0.856677</td>\n",
-       "      <td>0.975635</td>\n",
-       "      <td>0.908357</td>\n",
-       "      <td>1.652881</td>\n",
-       "      <td>-4.192466</td>\n",
-       "      <td>-6.929646</td>\n",
-       "      <td>1.821195</td>\n",
-       "      <td>1.915737</td>\n",
-       "      <td>0.260070</td>\n",
-       "      <td>1</td>\n",
-       "      <td>D1_TEST02_1.csv</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>0.009247</td>\n",
-       "      <td>1.139160</td>\n",
-       "      <td>1.476295</td>\n",
-       "      <td>2.615455</td>\n",
-       "      <td>0.906951</td>\n",
-       "      <td>0.822475</td>\n",
-       "      <td>0.955961</td>\n",
-       "      <td>0.822560</td>\n",
-       "      <td>1.627755</td>\n",
-       "      <td>98.077724</td>\n",
-       "      <td>159.646548</td>\n",
-       "      <td>1.868548</td>\n",
-       "      <td>1.763273</td>\n",
-       "      <td>-0.503998</td>\n",
-       "      <td>1</td>\n",
-       "      <td>D1_TEST03_1.csv</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>0.050242</td>\n",
-       "      <td>2.637336</td>\n",
-       "      <td>2.637336</td>\n",
-       "      <td>4.445498</td>\n",
-       "      <td>1.135680</td>\n",
-       "      <td>1.287244</td>\n",
-       "      <td>1.195939</td>\n",
-       "      <td>1.289768</td>\n",
-       "      <td>2.322254</td>\n",
-       "      <td>22.604275</td>\n",
-       "      <td>52.492866</td>\n",
-       "      <td>3.417678</td>\n",
-       "      <td>3.644127</td>\n",
-       "      <td>0.696925</td>\n",
-       "      <td>1</td>\n",
-       "      <td>D1_TEST04_1.csv</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>-0.063636</td>\n",
-       "      <td>1.814052</td>\n",
-       "      <td>1.814052</td>\n",
-       "      <td>3.213308</td>\n",
-       "      <td>0.919439</td>\n",
-       "      <td>0.841319</td>\n",
-       "      <td>0.966850</td>\n",
-       "      <td>0.845369</td>\n",
-       "      <td>1.972998</td>\n",
-       "      <td>-14.448310</td>\n",
-       "      <td>-28.506483</td>\n",
-       "      <td>2.255246</td>\n",
-       "      <td>2.633599</td>\n",
-       "      <td>0.716632</td>\n",
-       "      <td>1</td>\n",
-       "      <td>D1_TEST05_1.csv</td>\n",
-       "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "text/plain": [
-       "       Mean       Max  Peak (Pm)  Peak-to-Peak (Pk)       RMS  Variance  \\\n",
-       "0 -0.075377  1.466510   2.254903           3.721414  1.037986  1.071734   \n",
-       "1 -0.227331  1.307743   1.575323           2.883067  0.953077  0.856677   \n",
-       "2  0.009247  1.139160   1.476295           2.615455  0.906951  0.822475   \n",
-       "3  0.050242  2.637336   2.637336           4.445498  1.135680  1.287244   \n",
-       "4 -0.063636  1.814052   1.814052           3.213308  0.919439  0.841319   \n",
-       "\n",
-       "   Standard Deviation     Power  Crest Factor  Form Factor  Pulse Indicator  \\\n",
-       "0            1.091245  1.077416      2.172382   -13.770555       -29.914909   \n",
-       "1            0.975635  0.908357      1.652881    -4.192466        -6.929646   \n",
-       "2            0.955961  0.822560      1.627755    98.077724       159.646548   \n",
-       "3            1.195939  1.289768      2.322254    22.604275        52.492866   \n",
-       "4            0.966850  0.845369      1.972998   -14.448310       -28.506483   \n",
-       "\n",
-       "     Margin  Kurtosis  Skewness  label         filename  \n",
-       "0  2.764892  2.817839 -0.649122      1  D1_TEST01_1.csv  \n",
-       "1  1.821195  1.915737  0.260070      1  D1_TEST02_1.csv  \n",
-       "2  1.868548  1.763273 -0.503998      1  D1_TEST03_1.csv  \n",
-       "3  3.417678  3.644127  0.696925      1  D1_TEST04_1.csv  \n",
-       "4  2.255246  2.633599  0.716632      1  D1_TEST05_1.csv  "
+       "Empty DataFrame\n",
+       "Columns: []\n",
+       "Index: []"
       ]
      },
      "execution_count": 7,