Add experiment date (#46)

* added date_of_experiment column * regen tst data * edit authors page * check that dtype of datetime cols is correct * fixed dtype issue * balck --------- Co-authored-by: Daniel Wigh <[email protected]>
sustainable-processes · Apr 14, 2023 · 3adc792 · 3adc792
1 parent fdc206e
commit 3adc792
Show file tree

Hide file tree

Showing 27 changed files with 1,769 additions and 1,608 deletions.
diff --git a/AUTHORS b/AUTHORS
@@ -0,0 +1,11 @@
+# This is the official list of ORDly authors for copyright purposes.
+# 
+# Names should be added to this file as:
+# Name or Organization <email address>
+# The email address is not required for organizations.
+
+Daniel S. Wigh <[email protected]>
+Joe Arrowsmith <[email protected]>
+Alexander Pomberger <[email protected]>
+Alexei A. Lapkin <[email protected]>
+University of Cambridge
diff --git a/inspections.ipynb b/inspections.ipynb
@@ -7,13 +7,6 @@
     "# inspect df"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -23,7 +16,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -112,7 +105,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 39,
+   "execution_count": 19,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -124,7 +117,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 45,
+   "execution_count": 20,
    "metadata": {},
    "outputs": [
     {
@@ -137,7 +130,7 @@
        "]"
       ]
      },
-     "execution_count": 45,
+     "execution_count": 20,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -146,6 +139,152 @@
     "data.reactions[0].outcomes[0].products[0].measurements"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'07/01/2008'"
+      ]
+     },
+     "execution_count": 28,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data.reactions[0].provenance.experiment_start.value"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 44,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "07/01/2008\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "pandas._libs.tslibs.timestamps.Timestamp"
+      ]
+     },
+     "execution_count": 44,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "i = 0\n",
+    "d = data.reactions[i].provenance.experiment_start.value\n",
+    "print(d)\n",
+    "type(pd.to_datetime(d, format=\"%m/%d/%Y\"))\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 45,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "df = pd.DataFrame({'a': [1, 2, 3], 'b': [None, None, None]})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 49,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "AttributeError",
+     "evalue": "'Series' object has no attribute 'isempty'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[49], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m df[\u001b[39m'\u001b[39;49m\u001b[39mb\u001b[39;49m\u001b[39m'\u001b[39;49m]\u001b[39m.\u001b[39;49mdropna()\u001b[39m.\u001b[39;49misempty()\n",
+      "File \u001b[0;32m~/opt/anaconda3/envs/chemistry/lib/python3.10/site-packages/pandas/core/generic.py:5902\u001b[0m, in \u001b[0;36mNDFrame.__getattr__\u001b[0;34m(self, name)\u001b[0m\n\u001b[1;32m   5895\u001b[0m \u001b[39mif\u001b[39;00m (\n\u001b[1;32m   5896\u001b[0m     name \u001b[39mnot\u001b[39;00m \u001b[39min\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_internal_names_set\n\u001b[1;32m   5897\u001b[0m     \u001b[39mand\u001b[39;00m name \u001b[39mnot\u001b[39;00m \u001b[39min\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_metadata\n\u001b[1;32m   5898\u001b[0m     \u001b[39mand\u001b[39;00m name \u001b[39mnot\u001b[39;00m \u001b[39min\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_accessors\n\u001b[1;32m   5899\u001b[0m     \u001b[39mand\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_info_axis\u001b[39m.\u001b[39m_can_hold_identifiers_and_holds_name(name)\n\u001b[1;32m   5900\u001b[0m ):\n\u001b[1;32m   5901\u001b[0m     \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39m[name]\n\u001b[0;32m-> 5902\u001b[0m \u001b[39mreturn\u001b[39;00m \u001b[39mobject\u001b[39;49m\u001b[39m.\u001b[39;49m\u001b[39m__getattribute__\u001b[39;49m(\u001b[39mself\u001b[39;49m, name)\n",
+      "\u001b[0;31mAttributeError\u001b[0m: 'Series' object has no attribute 'isempty'"
+     ]
+    }
+   ],
+   "source": [
+    "df['b'].dropna()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Timestamp('2008-07-01 00:00:00')"
+      ]
+     },
+     "execution_count": 27,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "pd.Timestamp(data.reactions[0].provenance.experiment_start.value)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "07/01/2008\n",
+      "05/16/2008\n",
+      "05/06/2008\n",
+      "05/08/2008\n",
+      "05/15/2008\n",
+      "09/11/2008\n",
+      "05/01/2008\n",
+      "09/05/2008\n",
+      "04/15/2010\n",
+      "05/18/2009\n"
+     ]
+    }
+   ],
+   "source": [
+    "for i in range(10):\n",
+    "    print(data.reactions[i].provenance.experiment_start.value)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -1026,51 +1165,6 @@
     "item_frequencies = series.value_counts()"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[Na+]                      425\n",
-       "[K+]                       221\n",
-       "other                      203\n",
-       "Cl                         133\n",
-       "[Pd]                        71\n",
-       "[Na]                        37\n",
-       "O=S(=O)(O)O                 34\n",
-       "O                           29\n",
-       "[Li+]                       22\n",
-       "O=C([O-])/C=C/C(=O)[O-]     18\n",
-       "[Li]CCCC                    18\n",
-       "C[NH2+]C                    16\n",
-       "[Al+3]                      15\n",
-       "Br                          15\n",
-       "Cc1ccc(S(=O)(=O)O)cc1       15\n",
-       "[Ni]                        15\n",
-       "C(=NC1CCCCC1)=NC1CCCCC1     13\n",
-       "Cl[Ti](Cl)(Cl)Cl            10\n",
-       "[Mg]                         8\n",
-       "[NH4+]                       6\n",
-       "CC(=O)[O-]                   4\n",
-       "[Cl-]                        2\n",
-       "[OH-]                        1\n",
-       "[H-]                         1\n",
-       "[H][H]                       1\n",
-       "Name: agent_0, dtype: int64"
-      ]
-     },
-     "execution_count": 11,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "item_frequencies"
-   ]
-  },
   {
    "cell_type": "markdown",
    "metadata": {},