Preprocessing for kit hierarchy data

notebook/data_preprocess.ipynb

@@ -18,7 +18,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 67,
+   "execution_count": 78,
    "id": "2709a4af",
    "metadata": {},
    "outputs": [
@@ -165,7 +165,7 @@
        "33                X  "
       ]
      },
-     "execution_count": 67,
+     "execution_count": 78,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -185,7 +185,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 68,
+   "execution_count": 79,
    "id": "75349f36",
    "metadata": {},
    "outputs": [
@@ -193,35 +193,35 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "/var/folders/t7/ldqv1xt97rs4jyjvhxf4shgw0000gn/T/ipykernel_12116/237579764.py:2: SettingWithCopyWarning: \n",
+      "/var/folders/t7/ldqv1xt97rs4jyjvhxf4shgw0000gn/T/ipykernel_12116/2577623884.py:2: SettingWithCopyWarning: \n",
       "A value is trying to be set on a copy of a slice from a DataFrame.\n",
       "Try using .loc[row_indexer,col_indexer] = value instead\n",
       "\n",
       "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
       "  master[\"kit_type\"] = \"master\"\n",
-      "/var/folders/t7/ldqv1xt97rs4jyjvhxf4shgw0000gn/T/ipykernel_12116/237579764.py:3: SettingWithCopyWarning: \n",
+      "/var/folders/t7/ldqv1xt97rs4jyjvhxf4shgw0000gn/T/ipykernel_12116/2577623884.py:3: SettingWithCopyWarning: \n",
       "A value is trying to be set on a copy of a slice from a DataFrame\n",
       "\n",
       "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
       "  master.rename(columns={\"Master Kit\": \"kit_name\", \"Master Kit  Description\": \"kit_description\"}, inplace=True)\n",
-      "/var/folders/t7/ldqv1xt97rs4jyjvhxf4shgw0000gn/T/ipykernel_12116/237579764.py:6: SettingWithCopyWarning: \n",
+      "/var/folders/t7/ldqv1xt97rs4jyjvhxf4shgw0000gn/T/ipykernel_12116/2577623884.py:6: SettingWithCopyWarning: \n",
       "A value is trying to be set on a copy of a slice from a DataFrame.\n",
       "Try using .loc[row_indexer,col_indexer] = value instead\n",
       "\n",
       "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
       "  subkit[\"kit_type\"] = \"subkit\"\n",
-      "/var/folders/t7/ldqv1xt97rs4jyjvhxf4shgw0000gn/T/ipykernel_12116/237579764.py:7: SettingWithCopyWarning: \n",
+      "/var/folders/t7/ldqv1xt97rs4jyjvhxf4shgw0000gn/T/ipykernel_12116/2577623884.py:7: SettingWithCopyWarning: \n",
       "A value is trying to be set on a copy of a slice from a DataFrame\n",
       "\n",
       "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
       "  subkit.rename(columns={\"Sub kit\": \"kit_name\", \"Sub kit Description\": \"kit_description\"}, inplace=True)\n",
-      "/var/folders/t7/ldqv1xt97rs4jyjvhxf4shgw0000gn/T/ipykernel_12116/237579764.py:11: SettingWithCopyWarning: \n",
+      "/var/folders/t7/ldqv1xt97rs4jyjvhxf4shgw0000gn/T/ipykernel_12116/2577623884.py:11: SettingWithCopyWarning: \n",
       "A value is trying to be set on a copy of a slice from a DataFrame.\n",
       "Try using .loc[row_indexer,col_indexer] = value instead\n",
       "\n",
       "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
       "  prepack[\"kit_type\"] = \"prepack\"\n",
-      "/var/folders/t7/ldqv1xt97rs4jyjvhxf4shgw0000gn/T/ipykernel_12116/237579764.py:12: SettingWithCopyWarning: \n",
+      "/var/folders/t7/ldqv1xt97rs4jyjvhxf4shgw0000gn/T/ipykernel_12116/2577623884.py:12: SettingWithCopyWarning: \n",
       "A value is trying to be set on a copy of a slice from a DataFrame\n",
       "\n",
       "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
@@ -285,65 +285,20 @@
        "      <td>IEHK 2024,Basic Medicine&amp;Renewable UNIT</td>\n",
        "      <td>master</td>\n",
        "    </tr>\n",
-       "    <tr>\n",
-       "      <th>...</th>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1840</th>\n",
-       "      <td>S9999939</td>\n",
-       "      <td>Prepack 2/2 Obstetric 3-renew. S9908302</td>\n",
-       "      <td>prepack</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1841</th>\n",
-       "      <td>S9999939</td>\n",
-       "      <td>Prepack 2/2 Obstetric 3-renew. S9908302</td>\n",
-       "      <td>prepack</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1842</th>\n",
-       "      <td>S9999939</td>\n",
-       "      <td>Prepack 2/2 Obstetric 3-renew. S9908302</td>\n",
-       "      <td>prepack</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1843</th>\n",
-       "      <td>S9999939</td>\n",
-       "      <td>Prepack 2/2 Obstetric 3-renew. S9908302</td>\n",
-       "      <td>prepack</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1846</th>\n",
-       "      <td>S9999299</td>\n",
-       "      <td>BAG for 50 x S0322010 CH12,ster,disp</td>\n",
-       "      <td>prepack</td>\n",
-       "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
-       "<p>675 rows × 3 columns</p>\n",
        "</div>"
       ],
       "text/plain": [
-       "      kit_name                          kit_description kit_type\n",
-       "30    S9901040  IEHK 2024,Basic Medicine&Renewable UNIT   master\n",
-       "32    S9901040  IEHK 2024,Basic Medicine&Renewable UNIT   master\n",
-       "33    S9901040  IEHK 2024,Basic Medicine&Renewable UNIT   master\n",
-       "36    S9901040  IEHK 2024,Basic Medicine&Renewable UNIT   master\n",
-       "37    S9901040  IEHK 2024,Basic Medicine&Renewable UNIT   master\n",
-       "...        ...                                      ...      ...\n",
-       "1840  S9999939  Prepack 2/2 Obstetric 3-renew. S9908302  prepack\n",
-       "1841  S9999939  Prepack 2/2 Obstetric 3-renew. S9908302  prepack\n",
-       "1842  S9999939  Prepack 2/2 Obstetric 3-renew. S9908302  prepack\n",
-       "1843  S9999939  Prepack 2/2 Obstetric 3-renew. S9908302  prepack\n",
-       "1846  S9999299     BAG for 50 x S0322010 CH12,ster,disp  prepack\n",
-       "\n",
-       "[675 rows x 3 columns]"
+       "    kit_name                          kit_description kit_type\n",
+       "30  S9901040  IEHK 2024,Basic Medicine&Renewable UNIT   master\n",
+       "32  S9901040  IEHK 2024,Basic Medicine&Renewable UNIT   master\n",
+       "33  S9901040  IEHK 2024,Basic Medicine&Renewable UNIT   master\n",
+       "36  S9901040  IEHK 2024,Basic Medicine&Renewable UNIT   master\n",
+       "37  S9901040  IEHK 2024,Basic Medicine&Renewable UNIT   master"
       ]
      },
-     "execution_count": 68,
+     "execution_count": 79,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -365,15 +320,13 @@
     "prepack.rename(columns={\"Prepack\": \"kit_name\", \"Prepack Description\": \"kit_description\"}, inplace=True)\n",
     "\n",
     "\n",
-    "df = pd.concat([master, subkit, prepack])\n",
-    "df.head()\n",
-    "cleaned_df = df.copy()\n",
-    "cleaned_df"
+    "cleaned_df = pd.concat([master, subkit, prepack])\n",
+    "cleaned_df.head()"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 69,
+   "execution_count": 80,
    "id": "2e6e197d",
    "metadata": {},
    "outputs": [],
@@ -386,15 +339,26 @@
     "\n",
     "cleaned_df.loc[cleaned_df['kit_name'].isin(standalone_masterkit_list),'line_type'] = 'long line'\n",
     "cleaned_df.loc[cleaned_df['kit_type']=='prepack','line_type'] = 'mini load'\n",
-    "cleaned_df.loc[cleaned_df['kit_type']=='subkit','line_type'] = 'long line'\n",
-    "cleaned_df.to_csv('../data/real_data_excel/converted_csv/Kit_Composition_and_relation_cleaned_with_line_type.csv', index=False)"
+    "cleaned_df.loc[cleaned_df['kit_type']=='subkit','line_type'] = 'long line'"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 70,
+   "execution_count": 81,
    "id": "9ff00aa6",
    "metadata": {},
+   "outputs": [],
+   "source": [
+    "cleaned_df.loc[cleaned_df['line_type']=='mini load', 'line_id'] = 7\n",
+    "cleaned_df.loc[cleaned_df['line_type']=='long line', 'line_id'] = 6\n",
+    "cleaned_df.to_csv('../data/real_data_excel/converted_csv/Kit_Composition_and_relation_cleaned_with_line_type_and_id.csv', index=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 83,
+   "id": "3d8d547c",
+   "metadata": {},
    "outputs": [
     {
      "data": {
@@ -417,125 +381,425 @@
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
-       "      <th>kit_name</th>\n",
-       "      <th>kit_description</th>\n",
-       "      <th>kit_type</th>\n",
-       "      <th>line_type</th>\n",
+       "      <th>Master Kit</th>\n",
+       "      <th>Sub kit</th>\n",
+       "      <th>Prepack</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>30</th>\n",
        "      <td>S9901040</td>\n",
-       "      <td>IEHK 2024,Basic Medicine&amp;Renewable UNIT</td>\n",
-       "      <td>master</td>\n",
-       "      <td>NaN</td>\n",
+       "      <td>S9991041</td>\n",
+       "      <td>S9991044</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>32</th>\n",
+       "      <th>36</th>\n",
        "      <td>S9901040</td>\n",
-       "      <td>IEHK 2024,Basic Medicine&amp;Renewable UNIT</td>\n",
-       "      <td>master</td>\n",
-       "      <td>NaN</td>\n",
+       "      <td>S9991042</td>\n",
+       "      <td>S9991045</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>33</th>\n",
-       "      <td>S9901040</td>\n",
-       "      <td>IEHK 2024,Basic Medicine&amp;Renewable UNIT</td>\n",
-       "      <td>master</td>\n",
-       "      <td>NaN</td>\n",
+       "      <th>216</th>\n",
+       "      <td>S9902219</td>\n",
+       "      <td>S9999898</td>\n",
+       "      <td>S9999941</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>36</th>\n",
-       "      <td>S9901040</td>\n",
-       "      <td>IEHK 2024,Basic Medicine&amp;Renewable UNIT</td>\n",
-       "      <td>master</td>\n",
-       "      <td>NaN</td>\n",
+       "      <th>225</th>\n",
+       "      <td>S9902219</td>\n",
+       "      <td>S9999898</td>\n",
+       "      <td>S9999942</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>37</th>\n",
-       "      <td>S9901040</td>\n",
-       "      <td>IEHK 2024,Basic Medicine&amp;Renewable UNIT</td>\n",
-       "      <td>master</td>\n",
-       "      <td>NaN</td>\n",
+       "      <th>232</th>\n",
+       "      <td>S9902219</td>\n",
+       "      <td>S9999898</td>\n",
+       "      <td>S9999940</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>...</th>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
+       "      <th>418</th>\n",
+       "      <td>S9902450</td>\n",
+       "      <td>S9992451</td>\n",
+       "      <td>S9992450</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>1840</th>\n",
-       "      <td>S9999939</td>\n",
-       "      <td>Prepack 2/2 Obstetric 3-renew. S9908302</td>\n",
-       "      <td>prepack</td>\n",
-       "      <td>mini load</td>\n",
+       "      <th>508</th>\n",
+       "      <td>S9902470</td>\n",
+       "      <td>S9992470</td>\n",
+       "      <td>S9992414</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>1841</th>\n",
-       "      <td>S9999939</td>\n",
-       "      <td>Prepack 2/2 Obstetric 3-renew. S9908302</td>\n",
-       "      <td>prepack</td>\n",
-       "      <td>mini load</td>\n",
+       "      <th>514</th>\n",
+       "      <td>S9902470</td>\n",
+       "      <td>S9992470</td>\n",
+       "      <td>S9992415</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>1842</th>\n",
-       "      <td>S9999939</td>\n",
-       "      <td>Prepack 2/2 Obstetric 3-renew. S9908302</td>\n",
-       "      <td>prepack</td>\n",
-       "      <td>mini load</td>\n",
+       "      <th>574</th>\n",
+       "      <td>S9902480</td>\n",
+       "      <td>S9992483</td>\n",
+       "      <td>S9992480</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>673</th>\n",
+       "      <td>S9903003</td>\n",
+       "      <td>S9999144</td>\n",
+       "      <td>S9999149</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>676</th>\n",
+       "      <td>S9903003</td>\n",
+       "      <td>S9999145</td>\n",
+       "      <td>S9999143</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>684</th>\n",
+       "      <td>S9903003</td>\n",
+       "      <td>S9999145</td>\n",
+       "      <td>S9999138</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>692</th>\n",
+       "      <td>S9903003</td>\n",
+       "      <td>S9999145</td>\n",
+       "      <td>S9999137</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>743</th>\n",
+       "      <td>S9906706</td>\n",
+       "      <td>S9999701</td>\n",
+       "      <td>S9999703</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>752</th>\n",
+       "      <td>S9906706</td>\n",
+       "      <td>S9999701</td>\n",
+       "      <td>S9999704</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>759</th>\n",
+       "      <td>S9906706</td>\n",
+       "      <td>S9999701</td>\n",
+       "      <td>S9999705</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>762</th>\n",
+       "      <td>S9906706</td>\n",
+       "      <td>S9999702</td>\n",
+       "      <td>S9999299</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>807</th>\n",
+       "      <td>S9906708</td>\n",
+       "      <td>S9999721</td>\n",
+       "      <td>S9999728</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>1843</th>\n",
+       "      <th>814</th>\n",
+       "      <td>S9906708</td>\n",
+       "      <td>S9999726</td>\n",
+       "      <td>S9999729</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>853</th>\n",
+       "      <td>S9906710</td>\n",
+       "      <td>S9996710</td>\n",
+       "      <td>S9986712</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>858</th>\n",
+       "      <td>S9906710</td>\n",
+       "      <td>S9996710</td>\n",
+       "      <td>S9986711</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>859</th>\n",
+       "      <td>S9906710</td>\n",
+       "      <td>S9996711</td>\n",
+       "      <td>S9986711</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>862</th>\n",
+       "      <td>S9906710</td>\n",
+       "      <td>S9996711</td>\n",
+       "      <td>S9986713</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>864</th>\n",
+       "      <td>S9906710</td>\n",
+       "      <td>S9996711</td>\n",
+       "      <td>S9986714</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>871</th>\n",
+       "      <td>S9906710</td>\n",
+       "      <td>S9996711</td>\n",
+       "      <td>S9986715</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>906</th>\n",
+       "      <td>S9906712</td>\n",
+       "      <td>S9999491</td>\n",
+       "      <td>S9999494</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>917</th>\n",
+       "      <td>S9906712</td>\n",
+       "      <td>S9999491</td>\n",
+       "      <td>S9999495</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>923</th>\n",
+       "      <td>S9906712</td>\n",
+       "      <td>S9999491</td>\n",
+       "      <td>S9999496</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>968</th>\n",
+       "      <td>S9906713</td>\n",
+       "      <td>S9999506</td>\n",
+       "      <td>S9999503</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>973</th>\n",
+       "      <td>S9906713</td>\n",
+       "      <td>S9999507</td>\n",
+       "      <td>S9999504</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1135</th>\n",
+       "      <td>S9906729</td>\n",
+       "      <td>S9996722</td>\n",
+       "      <td>S9996726</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1252</th>\n",
+       "      <td>S9906733</td>\n",
+       "      <td>S9993731</td>\n",
+       "      <td>S9993736</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1258</th>\n",
+       "      <td>S9906733</td>\n",
+       "      <td>S9993731</td>\n",
+       "      <td>S9993737</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1266</th>\n",
+       "      <td>S9906733</td>\n",
+       "      <td>S9993732</td>\n",
+       "      <td>S9993739</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1268</th>\n",
+       "      <td>S9906733</td>\n",
+       "      <td>S9993733</td>\n",
+       "      <td>S9993738</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1279</th>\n",
+       "      <td>S9906733</td>\n",
+       "      <td>S9993734</td>\n",
+       "      <td>S9993730</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1315</th>\n",
+       "      <td>S9906734</td>\n",
+       "      <td>S9994732</td>\n",
+       "      <td>S9994735</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1325</th>\n",
+       "      <td>S9906734</td>\n",
+       "      <td>S9994732</td>\n",
+       "      <td>S9994736</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1330</th>\n",
+       "      <td>S9906734</td>\n",
+       "      <td>S9994733</td>\n",
+       "      <td>S9994737</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1338</th>\n",
+       "      <td>S9906734</td>\n",
+       "      <td>S9994738</td>\n",
+       "      <td>S9994738</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1431</th>\n",
+       "      <td>S9906737</td>\n",
+       "      <td>S9997731</td>\n",
+       "      <td>S9997739</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1434</th>\n",
+       "      <td>S9906737</td>\n",
+       "      <td>S9997731</td>\n",
+       "      <td>S9997730</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1487</th>\n",
+       "      <td>S9906753</td>\n",
+       "      <td>S9996752</td>\n",
+       "      <td>S9996751</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1557</th>\n",
+       "      <td>S9906791</td>\n",
+       "      <td>S9999751</td>\n",
+       "      <td>S9999691</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1570</th>\n",
+       "      <td>S9906791</td>\n",
+       "      <td>S9999751</td>\n",
+       "      <td>S9999692</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1581</th>\n",
+       "      <td>S9906791</td>\n",
+       "      <td>S9999752</td>\n",
+       "      <td>S9999693</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1584</th>\n",
+       "      <td>S9906791</td>\n",
+       "      <td>S9999753</td>\n",
+       "      <td>S9999694</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1652</th>\n",
+       "      <td>S9906800</td>\n",
+       "      <td>S9986721</td>\n",
+       "      <td>S9986716</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1655</th>\n",
+       "      <td>S9906800</td>\n",
+       "      <td>S9986722</td>\n",
+       "      <td>S9986716</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1658</th>\n",
+       "      <td>S9906800</td>\n",
+       "      <td>S9986722</td>\n",
+       "      <td>S9986717</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1666</th>\n",
+       "      <td>S9906800</td>\n",
+       "      <td>S9986722</td>\n",
+       "      <td>S9986710</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1767</th>\n",
+       "      <td>S9908300</td>\n",
+       "      <td>S9999995</td>\n",
+       "      <td>S9999944</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1773</th>\n",
+       "      <td>S9908300</td>\n",
+       "      <td>S9999995</td>\n",
+       "      <td>S9999945</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1834</th>\n",
+       "      <td>S9908302</td>\n",
+       "      <td>S9999883</td>\n",
+       "      <td>S9999938</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1838</th>\n",
+       "      <td>S9908302</td>\n",
+       "      <td>S9999884</td>\n",
        "      <td>S9999939</td>\n",
-       "      <td>Prepack 2/2 Obstetric 3-renew. S9908302</td>\n",
-       "      <td>prepack</td>\n",
-       "      <td>mini load</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1846</th>\n",
+       "      <td>S9908302</td>\n",
+       "      <td>S9999884</td>\n",
        "      <td>S9999299</td>\n",
-       "      <td>BAG for 50 x S0322010 CH12,ster,disp</td>\n",
-       "      <td>prepack</td>\n",
-       "      <td>mini load</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
-       "<p>675 rows × 4 columns</p>\n",
        "</div>"
       ],
       "text/plain": [
-       "      kit_name                          kit_description kit_type  line_type\n",
-       "30    S9901040  IEHK 2024,Basic Medicine&Renewable UNIT   master        NaN\n",
-       "32    S9901040  IEHK 2024,Basic Medicine&Renewable UNIT   master        NaN\n",
-       "33    S9901040  IEHK 2024,Basic Medicine&Renewable UNIT   master        NaN\n",
-       "36    S9901040  IEHK 2024,Basic Medicine&Renewable UNIT   master        NaN\n",
-       "37    S9901040  IEHK 2024,Basic Medicine&Renewable UNIT   master        NaN\n",
-       "...        ...                                      ...      ...        ...\n",
-       "1840  S9999939  Prepack 2/2 Obstetric 3-renew. S9908302  prepack  mini load\n",
-       "1841  S9999939  Prepack 2/2 Obstetric 3-renew. S9908302  prepack  mini load\n",
-       "1842  S9999939  Prepack 2/2 Obstetric 3-renew. S9908302  prepack  mini load\n",
-       "1843  S9999939  Prepack 2/2 Obstetric 3-renew. S9908302  prepack  mini load\n",
-       "1846  S9999299     BAG for 50 x S0322010 CH12,ster,disp  prepack  mini load\n",
-       "\n",
-       "[675 rows x 4 columns]"
+       "     Master Kit   Sub kit   Prepack\n",
+       "30     S9901040  S9991041  S9991044\n",
+       "36     S9901040  S9991042  S9991045\n",
+       "216    S9902219  S9999898  S9999941\n",
+       "225    S9902219  S9999898  S9999942\n",
+       "232    S9902219  S9999898  S9999940\n",
+       "418    S9902450  S9992451  S9992450\n",
+       "508    S9902470  S9992470  S9992414\n",
+       "514    S9902470  S9992470  S9992415\n",
+       "574    S9902480  S9992483  S9992480\n",
+       "673    S9903003  S9999144  S9999149\n",
+       "676    S9903003  S9999145  S9999143\n",
+       "684    S9903003  S9999145  S9999138\n",
+       "692    S9903003  S9999145  S9999137\n",
+       "743    S9906706  S9999701  S9999703\n",
+       "752    S9906706  S9999701  S9999704\n",
+       "759    S9906706  S9999701  S9999705\n",
+       "762    S9906706  S9999702  S9999299\n",
+       "807    S9906708  S9999721  S9999728\n",
+       "814    S9906708  S9999726  S9999729\n",
+       "853    S9906710  S9996710  S9986712\n",
+       "858    S9906710  S9996710  S9986711\n",
+       "859    S9906710  S9996711  S9986711\n",
+       "862    S9906710  S9996711  S9986713\n",
+       "864    S9906710  S9996711  S9986714\n",
+       "871    S9906710  S9996711  S9986715\n",
+       "906    S9906712  S9999491  S9999494\n",
+       "917    S9906712  S9999491  S9999495\n",
+       "923    S9906712  S9999491  S9999496\n",
+       "968    S9906713  S9999506  S9999503\n",
+       "973    S9906713  S9999507  S9999504\n",
+       "1135   S9906729  S9996722  S9996726\n",
+       "1252   S9906733  S9993731  S9993736\n",
+       "1258   S9906733  S9993731  S9993737\n",
+       "1266   S9906733  S9993732  S9993739\n",
+       "1268   S9906733  S9993733  S9993738\n",
+       "1279   S9906733  S9993734  S9993730\n",
+       "1315   S9906734  S9994732  S9994735\n",
+       "1325   S9906734  S9994732  S9994736\n",
+       "1330   S9906734  S9994733  S9994737\n",
+       "1338   S9906734  S9994738  S9994738\n",
+       "1431   S9906737  S9997731  S9997739\n",
+       "1434   S9906737  S9997731  S9997730\n",
+       "1487   S9906753  S9996752  S9996751\n",
+       "1557   S9906791  S9999751  S9999691\n",
+       "1570   S9906791  S9999751  S9999692\n",
+       "1581   S9906791  S9999752  S9999693\n",
+       "1584   S9906791  S9999753  S9999694\n",
+       "1652   S9906800  S9986721  S9986716\n",
+       "1655   S9906800  S9986722  S9986716\n",
+       "1658   S9906800  S9986722  S9986717\n",
+       "1666   S9906800  S9986722  S9986710\n",
+       "1767   S9908300  S9999995  S9999944\n",
+       "1773   S9908300  S9999995  S9999945\n",
+       "1834   S9908302  S9999883  S9999938\n",
+       "1838   S9908302  S9999884  S9999939\n",
+       "1846   S9908302  S9999884  S9999299"
       ]
      },
-     "execution_count": 70,
+     "execution_count": 83,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "cleaned_df"
+    "df[[\"Master Kit\", \"Sub kit\", \"Prepack\"]].drop_duplicates()"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "3d8d547c",
+   "id": "76aa422c",
    "metadata": {},
    "outputs": [],
    "source": []