Commit @mzargham's exploratory work to master (#24)

This is a rescue/recreation of #20, which unfortunately got stuck in
rebsae hell.

exploratory/mZargham/pre-infra/.ipynb_checkpoints/pageRankerChecker-checkpoint.ipynb

@@ -0,0 +1,61 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "ModuleNotFoundError",
+     "evalue": "No module named 'import_graph'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mModuleNotFoundError\u001b[0m                       Traceback (most recent call last)",
+      "\u001b[0;32m<ipython-input-1-9b2e3b4647d3>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      5\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mos\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      6\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mpage_ranker\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mpr\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 7\u001b[0;31m \u001b[0;32mimport\u001b[0m \u001b[0mimport_graph\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mig\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      8\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      9\u001b[0m \u001b[0mget_ipython\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrun_line_magic\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'matplotlib'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'inline'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;31mModuleNotFoundError\u001b[0m: No module named 'import_graph'"
+     ]
+    }
+   ],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import networkx as nx\n",
+    "import json\n",
+    "import os\n",
+    "import page_ranker as pr\n",
+    "import import_graph as ig\n",
+    "\n",
+    "%matplotlib inline"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

exploratory/mZargham/pre-infra/.ipynb_checkpoints/pageRankerChecker-lazy-checkpoint.ipynb

@@ -0,0 +1,188 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import networkx as nx\n",
+    "import json\n",
+    "import os\n",
+    "import page_ranker as pr\n",
+    "import import_graph as ig\n",
+    "import inspect_subgraph as isg\n",
+    "\n",
+    "import matplotlib.pyplot as plt\n",
+    "%matplotlib inline"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "cwd = os.getcwd()\n",
+    "\n",
+    "rel_path = \"sample_graphs/sourcecred_sourcecred.json\"\n",
+    "abs_file_path = os.path.abspath(os.path.join(cwd, '..', rel_path))\n",
+    "\n",
+    "with open(abs_file_path) as json_file:  \n",
+    "    data = json.load(json_file)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "G = ig.jsonToMultiDiGraph(data)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "iterations = 50\n",
+    "\n",
+    "\n",
+    "alpha = 0\n",
+    "seed = {n:1/len(G.nodes) for n in G.nodes}\n",
+    "self_loop_wt = 1/1000\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "r, df, g = pr.pageRanker(G,\n",
+    "                         alpha,\n",
+    "                         iterations,\n",
+    "                         seed=seed,\n",
+    "                         initial_value = seed,\n",
+    "                         lazy=False,\n",
+    "                         self_loop_wt=self_loop_wt)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(array([2.000e+00, 2.000e+00, 1.000e+00, 5.100e+01, 2.051e+03, 1.723e+03,\n",
+       "        9.860e+02, 5.520e+02, 5.390e+02, 2.100e+01, 1.000e+00, 0.000e+00,\n",
+       "        0.000e+00, 2.000e+00, 1.000e+00]),\n",
+       " array([-6.62636919, -6.2259882 , -5.82560721, -5.42522622, -5.02484523,\n",
+       "        -4.62446424, -4.22408325, -3.82370226, -3.42332126, -3.02294027,\n",
+       "        -2.62255928, -2.22217829, -1.8217973 , -1.42141631, -1.02103532,\n",
+       "        -0.62065432]),\n",
+       " <a list of 15 Patch objects>)"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plt.hist(np.log10(r), bins = 15)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.apply(np.log10).plot(legend=False, figsize=(20,10),alpha=.5)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "top25 = list(df.T.reset_index().sort_values(iterations).tail(25).index)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "isg.inspectSubGraph(G, top25, expand=False, verbose=False, label=True,pos = \"kk\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.sum(axis=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "plt.hist([np.log10(v) for v in list(nx.get_node_attributes(G,'total_wt').values())])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}