Graph_analysis_Python.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Data creation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 249,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "\n",
    "df = pd.DataFrame({'ID':[1,2,3,4,5,6], \n",
    "                   'First Name':['Felix', 'Jean', 'James', 'Daphne', 'James', 'Peter'], \n",
    "                   'Family Name': ['Revert', 'Durand', 'Wright', 'Hull', 'Conrad', 'Donovan'],\n",
    "                   'Phone number': ['+33 6 12 34 56 78', '+33 7 00 00 00 00', '+33 6 12 34 56 78', '+33 6 99 99 99 99', '+852 0123 4567', '+852 0123 4567'],\n",
    "                   'Email': ['felix.revert@gmail.com', 'jean.durand@gmail.com', 'j.custom@gmail.com', pd.np.nan, 'j.custom@gmail.com', pd.np.nan]})\n",
    "\n",
    "\n",
    "# G.add_nodes_from(df.ID.unique().tolist(), label='user')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Data preparation"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Phone numbers"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 250,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "column_edge = 'Phone number'\n",
    "column_ID = 'ID'\n",
    "\n",
    "data_to_merge = df[[column_ID, column_edge]].dropna(subset=[column_edge]).drop_duplicates() # select columns, remove NaN\n",
    "\n",
    "# To create connections between people who have the same number,\n",
    "# join data with itself on the 'ID' column.\n",
    "data_to_merge = data_to_merge.merge(\n",
    "    data_to_merge[[column_ID, column_edge]].rename(columns={column_ID:column_ID+\"_2\"}), \n",
    "    on=column_edge\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 251,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>ID</th>\n",
       "      <th>Phone number</th>\n",
       "      <th>ID_2</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>+33 6 12 34 56 78</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>+33 6 12 34 56 78</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>+33 6 12 34 56 78</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>+33 6 12 34 56 78</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2</td>\n",
       "      <td>+33 7 00 00 00 00</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>4</td>\n",
       "      <td>+33 6 99 99 99 99</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>5</td>\n",
       "      <td>+852 0123 4567</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>5</td>\n",
       "      <td>+852 0123 4567</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>6</td>\n",
       "      <td>+852 0123 4567</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>6</td>\n",
       "      <td>+852 0123 4567</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   ID       Phone number  ID_2\n",
       "0   1  +33 6 12 34 56 78     1\n",
       "1   1  +33 6 12 34 56 78     3\n",
       "2   3  +33 6 12 34 56 78     1\n",
       "3   3  +33 6 12 34 56 78     3\n",
       "4   2  +33 7 00 00 00 00     2\n",
       "5   4  +33 6 99 99 99 99     4\n",
       "6   5     +852 0123 4567     5\n",
       "7   5     +852 0123 4567     6\n",
       "8   6     +852 0123 4567     5\n",
       "9   6     +852 0123 4567     6"
      ]
     },
     "execution_count": 251,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data_to_merge"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 252,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# By joining the data with itself, people will have a connection with themselves.\n",
    "# Remove self connections, to keep only connected people who are different.\n",
    "d = data_to_merge[~(data_to_merge[column_ID]==data_to_merge[column_ID+\"_2\"])] \\\n",
    "    .dropna()[[column_ID, column_ID+\"_2\", column_edge]]\n",
    "    \n",
    "# To avoid counting twice the connections (person 1 connected to person 2 and person 2 connected to person 1)\n",
    "# we force the first ID to be \"lower\" then ID_2\n",
    "d.drop(d.loc[d[column_ID+\"_2\"]<d[column_ID]].index.tolist(), inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 253,
   "metadata": {
    "collapsed": false,
    "scrolled": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>ID</th>\n",
       "      <th>ID_2</th>\n",
       "      <th>Phone number</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>+33 6 12 34 56 78</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>5</td>\n",
       "      <td>6</td>\n",
       "      <td>+852 0123 4567</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   ID  ID_2       Phone number\n",
       "1   1     3  +33 6 12 34 56 78\n",
       "7   5     6     +852 0123 4567"
      ]
     },
     "execution_count": 253,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "d"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Creation of the graph"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 254,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import networkx as nx\n",
    "\n",
    "G = nx.from_pandas_edgelist(df=d, source=column_ID, target=column_ID+'_2', edge_attr=column_edge)\n",
    "\n",
    "G.add_nodes_from(nodes_for_adding=df.ID.tolist())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 255,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "NodeView((1, 3, 5, 6, 2, 4))"
      ]
     },
     "execution_count": 255,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "G.nodes()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Emails"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 256,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "column_edge = 'Email'\n",
    "column_ID = 'ID'\n",
    "\n",
    "data_to_merge = df[[column_ID, column_edge]].dropna(subset=[column_edge]).drop_duplicates()\n",
    "\n",
    "data_to_merge = data_to_merge.merge(\n",
    "    data_to_merge[[column_ID, column_edge]].rename(columns={column_ID:column_ID+\"_2\"}), \n",
    "    on=column_edge\n",
    ")\n",
    "\n",
    "d = data_to_merge[~(data_to_merge[column_ID]==data_to_merge[column_ID+\"_2\"])] \\\n",
    "    .dropna()[[column_ID, column_ID+\"_2\", column_edge]]\n",
    "\n",
    "d.drop(d.loc[d[column_ID+\"_2\"]<d[column_ID]].index.tolist(), inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 257,
   "metadata": {
    "collapsed": false,
    "scrolled": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>ID</th>\n",
       "      <th>ID_2</th>\n",
       "      <th>Email</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>5</td>\n",
       "      <td>j.custom@gmail.com</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   ID  ID_2               Email\n",
       "3   3     5  j.custom@gmail.com"
      ]
     },
     "execution_count": 257,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "d"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 258,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "# Create the connections in the graph\n",
    "links_attributes = {tuple(row[[column_ID, column_ID+\"_2\"]]): {column_edge: row[column_edge]} for i,row in d.iterrows()}\n",
    "\n",
    "G.add_edges_from(links_attributes) # create the connection, without attribute. Check it with G.get_edge_data(3,5)\n",
    "nx.set_edge_attributes(G=G, values=links_attributes) # adds the attribute. Check it with G.get_edge_data(3,5)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Graph analysis"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Drawing graphs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 259,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAeEAAAFCCAYAAADGwmVOAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nsAAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x14c4a5f8>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "nx.draw(G)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 272,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{1: 'Felix Revert',\n",
       " 2: 'Jean Durand',\n",
       " 3: 'James Wright',\n",
       " 4: 'Daphne Hull',\n",
       " 5: 'James Conrad',\n",
       " 6: 'Peter Donovan'}"
      ]
     },
     "execution_count": 272,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "{row[column_ID]:row['First Name'] +' '+ row['Family Name'] for i,row in df.iterrows()}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 275,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "nx.set_node_attributes(G, {row[column_ID]:{'Name': row['First Name'] +' '+ row['Family Name']} for i,row in df.iterrows()})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 357,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "EDGE_SIZE = {\n",
    "    'Phone number': 2,\n",
    "    'Email': 1,\n",
    "}\n",
    "\n",
    "EDGE_COLOR = {\n",
    "    'Phone number': 'purple',\n",
    "    'Email': 'red',\n",
    "}\n",
    "\n",
    "def clean_edge(edge):\n",
    "    s.edge[edge[0], edge[1]].values()\n",
    "\n",
    "def c_(list_edges): return [a for a in list_edges if a in list(EDGE_COLOR.keys())]\n",
    "    \n",
    "# For nx.Graph()\n",
    "def edge_sizes(s): return [EDGE_SIZE[c_(list(s.edges[edge[0], edge[1]].keys()))[-1]] for edge in s.edges()] # /!\\ multiple links => one size\n",
    "def edge_colors(s): return [EDGE_COLOR[c_(list(s.edges[edge[0], edge[1]].keys()))[-1]] for edge in s.edges()] # /!\\ multiple links => one color\n",
    "\n",
    "# For nx.MultiDiGraph()\n",
    "# def edge_sizes(s): return [EDGE_SIZE[s.edge[edge[0]][edge[1]][0]['label']] for edge in s.edges()] # /!\\ multiple links => one size\n",
    "# def edge_colors(s): return [EDGE_COLOR[s.edge[edge[0]][edge[1]][0]['label']] for edge in s.edges()] # /!\\ multiple links => one color\n",
    "\n",
    "def draw(s):\n",
    "    pos = nx.spring_layout(s, scale=0.5)\n",
    "    node_labels = dict((n,d['Name']) for n,d in s.nodes(data=True))\n",
    "#     labels = {**node_labels, **edge_labels}\n",
    "    nx.draw(s, pos=pos, width=edge_sizes(s), edge_color=edge_colors(s), alpha=0.8, arrows=False, node_color='lightgrey', node_size=400,\n",
    "            labels=node_labels, \n",
    "            font_color='black', font_size=8, font_weight='bold',\n",
    "           )\n",
    "    edge_labels = dict(((u,v),list(d.values())[0]) for u,v,d in G.edges(data=True))\n",
    "    nx.draw_networkx_edge_labels(G, pos, edge_labels = edge_labels, font_size=8)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 371,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAeEAAAFCCAYAAADGwmVOAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nIiJikP8H2LA4mUI9DbcAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x19d87a58>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "draw(nx.ego_graph(G=G, n=1, radius=3))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Automated detection of strange patterns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 360,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "degrees = list(nx.degree(G))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 378,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>ID</th>\n",
       "      <th>degree</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>5</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>6</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   ID  degree\n",
       "1   3       2\n",
       "2   5       2\n",
       "0   1       1\n",
       "3   6       1\n",
       "4   2       0"
      ]
     },
     "execution_count": 378,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.DataFrame([list(d) for d in degrees], columns=['ID', 'degree']).sort_values('degree', ascending=False).head(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 384,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAeEAAAFCCAYAAADGwmVOAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nF0wfR/RhL1IAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x19c2d390>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "draw(nx.ego_graph(G=G, n=3, radius=2))"
   ]
  }
 ],
 "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": "3.6.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}