From 481b020c6c9e3667fa0f093415fcf8434c4bf463 Mon Sep 17 00:00:00 2001
From: "Hyunmin Kim (Brandon)" <hmkim@users.noreply.github.com>
Date: Thu, 10 Dec 2020 15:05:21 +0900
Subject: [PATCH] Update deep_generative_model_LINCS.ipynb

the directly reading input excel
---
 deep_generative_model_LINCS.ipynb | 21 +++++++++++----------
 1 file changed, 11 insertions(+), 10 deletions(-)

diff --git a/deep_generative_model_LINCS.ipynb b/deep_generative_model_LINCS.ipynb
index d9d41bd..dc9fece 100644
--- a/deep_generative_model_LINCS.ipynb
+++ b/deep_generative_model_LINCS.ipynb
@@ -180,20 +180,21 @@
     }
    ],
    "source": [
-    "pclFileNameSM = \"../Data/YX_Data/pcl_information.csv\"\n",
+    "pclFileNameSM_df = pd.read_excel('./data/1-s2.0-S0092867417313090-mmc1.xlsx', sheet_name='Table S7 PCL Statistics', skiprows=1)\n",
     "pertClassDicSM = {}\n",
     "classDicSM = {}\n",
     "pertCountSM = 0\n",
-    "with open(pclFileNameSM, \"r\") as myfile:\n",
-    "    for line in myfile.readlines():\n",
-    "        if not len(line):\n",
-    "            continue\n",
+    "for i, row in pclFileNameSM_df.iterrows():\n",
+    "    \n",
+    "    PCL_ID = row[0]\n",
+    "    PCL_members = row[4].split('|')\n",
+    "    for PCL_member in PCL_members:\n",
     "        pertCountSM += 1\n",
-    "        line = line.strip()\n",
-    "        spline = line.split(',')\n",
-    "        pertClassDicSM[spline[0]] = spline[1]\n",
-    "        c = classDicSM.setdefault(spline[1], 0)\n",
-    "        classDicSM[spline[1]] = c + 1\n",
+    "        pertClassDicSM[PCL_member] = PCL_ID\n",
+    "        c = classDicSM.setdefault(PCL_ID, 0)\n",
+    "        classDicSM[PCL_ID] = c + 1\n",
+    "\n",
+    "    \n",
     "print(\"The number of perturbagens with class information: \" + str(pertCountSM))\n",
     "print(\"The number of PCL: \" + str(len(classDicSM)))\n",
     "print(sorted(classDicSM.items(), key = operator.itemgetter(1), reverse = True)[0])"