Rerun analysis

enveda · May 24, 2021 · f2791ce · f2791ce
1 parent af3e355
commit f2791ce
Showing 1 changed file with 37 additions and 55 deletions.
diff --git a/notebooks/4.0-subgraph_full_analysis.ipynb b/notebooks/4.0-subgraph_full_analysis.ipynb
@@ -54,35 +54,15 @@
    "id": "sonic-animal",
    "metadata": {},
    "source": [
-    "# Load dataset-generated network dataframe - Unfiltered"
+    "# Load KG"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 3,
-   "id": "included-metadata",
+   "id": "leading-shopper",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "openbiolink_df = pd.read_csv(\n",
-    "#     os.path.join(KG_DATA_PATH, 'shuffled_openbiolink.tsv'),\n",
-    "    'shuffled_openbiolink_kg.tsv',\n",
-    "    sep='\\t'\n",
-    ")\n",
-    "openbiolink_df.rename(columns={\"relation\": \"polarity\"}, inplace=True)\n",
-    "\n",
-    "custom_df = pd.read_csv(\n",
-    "#     os.path.join(KG_DATA_PATH, 'shuffled_custom.tsv'),\n",
-    "    'shuffled_custom_kg.tsv',\n",
-    "    sep='\\t'\n",
-    ")\n",
-    "custom_df.rename(columns={\"relation\": \"polarity\"}, inplace=True)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "persistent-membrane",
-   "metadata": {},
    "source": [
     "openbiolink_df = pd.read_csv(\n",
     "    os.path.join(KG_DATA_PATH, 'openbiolink_filtered_kg.tsv'),\n",
@@ -106,9 +86,11 @@
    ]
   },
   {
-   "cell_type": "markdown",
-   "id": "tested-franklin",
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "assured-geology",
    "metadata": {},
+   "outputs": [],
    "source": [
     "with open(os.path.join(DATA_DIR, 'transcriptomics', 'creed_harmonized_expression.json')) as file:\n",
     "    creed_dict = json.load(file)\n",
@@ -123,26 +105,6 @@
     "    open_target_dict = json.load(file4)"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "compact-contribution",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "with open(os.path.join(DATA_DIR, 'transcriptomics', 'creed_permuted.json')) as file:\n",
-    "    creed_dict = json.load(file)\n",
-    "    \n",
-    "with open(os.path.join(DATA_DIR, 'transcriptomics', 'geo_permuted.json')) as file2:\n",
-    "    geo_dict = json.load(file2)\n",
-    "    \n",
-    "with open(os.path.join(DATA_DIR, 'transcriptomics', 'lc1000_permuted.json')) as file3:\n",
-    "    lc1000_dict = json.load(file3)\n",
-    "    \n",
-    "with open(os.path.join(DATA_DIR, 'transcriptomics', 'target_permuted.json')) as file4:\n",
-    "    open_target_dict = json.load(file4)"
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "twelve-diesel",
@@ -227,7 +189,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 8,
    "id": "marked-tower",
    "metadata": {
     "scrolled": false
@@ -244,10 +206,10 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Getting paths: 100%|██████████| 620/620 [13:55<00:00,  1.35s/it]\n",
-      "Calculating concordance: 100%|██████████| 3/3 [02:38<00:00, 52.87s/it]\n",
-      "Getting paths: 100%|██████████| 1170/1170 [03:52<00:00,  5.02it/s]\n",
-      "Calculating concordance: 100%|██████████| 3/3 [00:05<00:00,  1.91s/it]\n"
+      "Getting paths: 100%|██████████| 620/620 [01:02<00:00,  9.96it/s]\n",
+      "Calculating concordance: 100%|██████████| 3/3 [00:01<00:00,  1.67it/s]\n",
+      "Getting paths: 100%|██████████| 1170/1170 [04:40<00:00,  4.16it/s]\n",
+      "Calculating concordance: 100%|██████████| 3/3 [00:12<00:00,  4.11s/it]\n"
      ]
     },
     {
@@ -261,10 +223,10 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Getting paths: 100%|██████████| 310/310 [04:46<00:00,  1.08it/s]\n",
-      "Calculating concordance: 100%|██████████| 3/3 [00:47<00:00, 15.76s/it]\n",
-      "Getting paths: 100%|██████████| 510/510 [01:51<00:00,  4.56it/s]\n",
-      "Calculating concordance: 100%|██████████| 3/3 [00:03<00:00,  1.03s/it]\n"
+      "Getting paths: 100%|██████████| 310/310 [00:43<00:00,  7.06it/s]\n",
+      "Calculating concordance: 100%|██████████| 3/3 [00:01<00:00,  2.01it/s]\n",
+      "Getting paths: 100%|██████████| 510/510 [02:41<00:00,  3.16it/s]\n",
+      "Calculating concordance: 100%|██████████| 3/3 [00:11<00:00,  3.85s/it]\n"
      ]
     },
     {
@@ -278,7 +240,27 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Getting paths:  91%|█████████▏| 3495/3820 [36:29<13:41,  2.53s/it]  "
+      "Getting paths: 100%|██████████| 3820/3820 [03:56<00:00, 16.16it/s]\n",
+      "Calculating concordance: 100%|██████████| 3/3 [00:04<00:00,  1.45s/it]\n",
+      "Getting paths: 100%|██████████| 7722/7722 [38:23<00:00,  3.35it/s]  \n",
+      "Calculating concordance: 100%|██████████| 3/3 [01:32<00:00, 30.91s/it]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "### lc1000-geo ###\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Getting paths: 100%|██████████| 1910/1910 [01:58<00:00, 16.07it/s]\n",
+      "Calculating concordance: 100%|██████████| 3/3 [00:04<00:00,  1.53s/it]\n",
+      "Getting paths: 100%|██████████| 3366/3366 [17:59<00:00,  3.12it/s]  \n",
+      "Calculating concordance: 100%|██████████| 3/3 [01:53<00:00, 37.77s/it]\n"
      ]
     }
    ],
@@ -371,7 +353,7 @@
     "                            ignore_index=True\n",
     "                        )\n",
     "\n",
-    "    n_file_path = os.path.join(DATA_DIR, 'concordant_paths', f'{graph_name}-permuted.tsv')\n",
+    "    n_file_path = os.path.join(DATA_DIR, 'concordant_paths', f'{graph_name}-results.tsv')\n",
     "    df.to_csv(n_file_path, sep='\\t', index=False)    "
    ]
   },