changed paths

sustainable-processes · Jan 17, 2024 · 7b4b0f5 · 7b4b0f5
1 parent a880d9c
commit 7b4b0f5
Showing 1 changed file with 121 additions and 19 deletions.
diff --git a/notebooks/inspect_orderly_data.ipynb b/notebooks/inspect_orderly_data.ipynb
@@ -10,7 +10,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 36,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -23,7 +23,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [
     {
@@ -32,7 +32,7 @@
        "'[S:1](=[O:4])(=[O:3])=[O:2].[S:5](=[O:9])(=[O:8])([OH:7])[OH:6]>>[OH:8][S:5]([OH:9])(=[O:7])=[O:6].[O:2]=[S:1](=[O:4])=[O:3] |f:2.3|'"
       ]
      },
-     "execution_count": 10,
+     "execution_count": 2,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -53,7 +53,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [
     {
@@ -62,7 +62,7 @@
        "'uspto-grants-1993_09'"
       ]
      },
-     "execution_count": 12,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -73,13 +73,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 37,
+   "execution_count": 13,
    "metadata": {},
    "outputs": [],
    "source": [
     "# Can also find ORD file just given the hash:\n",
     "def open_ord(ord_hash):\n",
-    "    folder_path = '/Users/dsw46/Projects_local/ORDerly/data/ord'\n",
+    "    folder_path = '/Users/danielwigh/projects_local/ORDerly_project/ORDerly/data/ord'\n",
     "    # look for files within that folder path or deeper for a file that contains the ord_hash\n",
     "    for root, dirs, files in os.walk(folder_path):\n",
     "        for file in files:\n",
@@ -93,25 +93,45 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 39,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "'uspto-grants-2001_07'"
+       "'uspto-grants-1986_09'"
       ]
      },
-     "execution_count": 39,
+     "execution_count": 15,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "data = open_ord('ord_dataset-85c00026681b46f89ef8634d2b8618c3')\n",
+    "data = open_ord('ord_dataset-0b70410902ae4139bd5d334881938f69')\n",
     "data.name"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'/Users/danielwigh/projects_local/ORDerly_project/ORDerly/notebooks'"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "pwd"
+   ]
+  },
   {
    "attachments": {},
    "cell_type": "markdown",
@@ -122,7 +142,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 17,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -131,34 +151,116 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 30,
+   "execution_count": 18,
    "metadata": {},
    "outputs": [],
    "source": [
-    "path = \"../data/orderly/uspto_no_trust/extracted_ords/uspto-grants-1993_09.parquet\"\n",
+    "path = \"../data/orderly/uspto_no_trust/extracted_ords/uspto-grants-1986_09.parquet\"\n",
     "df = pd.read_parquet(path)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 31,
+   "execution_count": 20,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "'[S:1](=[O:4])(=[O:3])=[O:2].[S:5](=[O:9])(=[O:8])([OH:7])[OH:6]>>[OH:8][S:5]([OH:9])(=[O:7])=[O:6].[O:2]=[S:1](=[O:4])=[O:3]'"
+       "262    C([O:8][C:9](=[O:32])[C@@H:10]1[CH2:14][CH2:13...\n",
+       "265    C(OC([N:11]1[CH2:15][CH2:14][CH2:13][C@H:12]1[...\n",
+       "273    C([O:8][C:9](=[O:35])[C@@H:10]1[CH2:14][CH2:13...\n",
+       "275    C([O:8][C:9](=[O:25])[C@H:10]([CH2:19][C:20]1[...\n",
+       "276    C(OC([N:11]1[CH2:15][CH2:14][CH2:13][C@H:12]1[...\n",
+       "277    C(OC([N:11]1[CH2:23][CH2:22][CH2:21][C@H:12]1[...\n",
+       "279    C(OC([N:11]1[CH2:15][CH2:14][CH2:13][C@H:12]1[...\n",
+       "281    C(OC([N:11]1[CH2:15][CH2:14][CH2:13][C@H:12]1[...\n",
+       "285    C(OC([N:11]1[CH2:15][CH2:14][CH2:13][C@H:12]1[...\n",
+       "368    [ClH:1].C(OC([NH:12][CH:13]([CH2:23][CH2:24][C...\n",
+       "377    [C:1]([O:4][CH2:5][CH2:6][CH2:7][NH:8]C(OCC1C=...\n",
+       "379    [ClH:1].[C:2]([O:5][CH2:6][CH2:7][CH2:8][NH:9]...\n",
+       "582    [CH3:1][C:2]1[O:3][C:4](=[O:14])[C:5](=[CH:7][...\n",
+       "Name: rxn_str, dtype: object"
       ]
      },
-     "execution_count": 31,
+     "execution_count": 20,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "df['rxn_str'][0]"
+    "# find df['rxn_str'] which contains [Pd] and [C]\n",
+    "\n",
+    "filtered_df = df[df['rxn_str'].str.contains('\\[Pd\\]') & df['rxn_str'].str.contains('\\[C\\]')]\n",
+    "filtered_df['rxn_str']\n"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'C([O:8][C:9](=[O:32])[C@@H:10]1[CH2:14][CH2:13][CH2:12][N:11]1[C:15](=[O:31])[C@H:16]([CH2:25][C:26]1[N:30]=[CH:29][NH:28][CH:27]=1)[NH:17][C:18]([C@H:20]1[NH:23][C:22](=[O:24])[CH2:21]1)=[O:19])C1C=CC=CC=1>CO.[C].[Pd]>[NH:23]1[C@H:20]([C:18]([NH:17][C@H:16]([C:15]([N:11]2[CH2:12][CH2:13][CH2:14][C@H:10]2[C:9]([OH:32])=[O:8])=[O:31])[CH2:25][C:26]2[N:30]=[CH:29][NH:28][CH:27]=2)=[O:19])[CH2:21][C:22]1=[O:24]'"
+      ]
+     },
+     "execution_count": 22,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.loc[262]['rxn_str']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "rxn = 'C([O:8][C:9](=[O:32])[C@@H:10]1[CH2:14][CH2:13][CH2:12][N:11]1[C:15](=[O:31])[C@H:16]([CH2:25][C:26]1[N:30]=[CH:29][NH:28][CH:27]=1)[NH:17][C:18]([C@H:20]1[NH:23][C:22](=[O:24])[CH2:21]1)=[O:19])C1C=CC=CC=1>CO.[C].[Pd]>[NH:23]1[C@H:20]([C:18]([NH:17][C@H:16]([C:15]([N:11]2[CH2:12][CH2:13][CH2:14][C@H:10]2[C:9]([OH:32])=[O:8])=[O:31])[CH2:25][C:26]2[N:30]=[CH:29][NH:28][CH:27]=2)=[O:19])[CH2:21][C:22]1=[O:24]'\n",
+    "react,ag,prod=rxn.split('>')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'O=C1C[C@@H](C(=O)N[C@@H](Cc2c[nH]cn2)C(=O)N2CCC[C@H]2C(=O)O)N1'"
+      ]
+     },
+     "execution_count": 28,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.loc[262]['product_000']\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "O=C1C[C@@H](C(=O)N[C@@H](Cc2c[nH]cn2)C(=O)N2CCC[C@H]2C(=O)O)N1"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
   {
    "attachments": {},
    "cell_type": "markdown",
@@ -1248,7 +1350,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.12"
+   "version": "3.10.13"
   },
   "orig_nbformat": 4
  },