From 025c72c8dd3962a07ba4170049921c4da7c523a8 Mon Sep 17 00:00:00 2001
From: Anirban Biswas <friendlyrony2050@gmail.com>
Date: Mon, 18 Mar 2019 18:31:13 +0530
Subject: [PATCH] code for conversion of embed files into suitable csv format

---
 src/postprocessing/convert_to_csv.ipynb | 50 +++++++++++++++++++++++++
 src/postprocessing/func_convert.py      | 35 +++++++++++++++++
 2 files changed, 85 insertions(+)
 create mode 100644 src/postprocessing/convert_to_csv.ipynb
 create mode 100644 src/postprocessing/func_convert.py

diff --git a/src/postprocessing/convert_to_csv.ipynb b/src/postprocessing/convert_to_csv.ipynb
new file mode 100644
index 0000000..5513a61
--- /dev/null
+++ b/src/postprocessing/convert_to_csv.ipynb
@@ -0,0 +1,50 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "../../data/cora/cora.embed\n",
+      "(2708, 128)\n"
+     ]
+    }
+   ],
+   "source": [
+    "import func_convert as converter\n",
+    "\n",
+    "datasets = ['cora']\n",
+    "embed_fnames = ['cora.embed']\n",
+    "\n",
+    "for dataset in datasets:\n",
+    "    for embed_fname in embed_fnames:\n",
+    "        converter.conv_to_csv( dataset, embed_fname)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 2",
+   "language": "python",
+   "name": "python2"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.15"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/src/postprocessing/func_convert.py b/src/postprocessing/func_convert.py
new file mode 100644
index 0000000..4dae61e
--- /dev/null
+++ b/src/postprocessing/func_convert.py
@@ -0,0 +1,35 @@
+
+# coding: utf-8
+
+# In[70]:
+
+import numpy as np
+
+
+# In[ ]:
+
+def conv_to_csv(dataset, name):
+    path = '../../data/'+dataset
+    fpath = path+'/'+name
+    print fpath
+    
+    with open(fpath,'r') as f:
+        data = f.read().split('\n')
+        if len(data[-1]) == 0:
+            data.pop()
+        
+    l=data[0]
+    l=l.split(' ')
+    
+    mat2 = np.zeros((int(l[0]),int(l[1])))
+    
+    for line in data[1:]:
+        l = line.split(' ')
+        l = [float(x) for x in l]
+        ind = int(l[0])
+        mat2[ind,:] = l[1:]    
+        
+    print('Number of data points :: %s ' % mat2.shape[0])
+    print('Number of data points :: %s ' % mat2.shape[1])
+    np.savetxt(fpath+'.csv',mat2,fmt='%.6e')
+