abhimskywalker · August 29, 2015 14:06
diff --git a/Saturday night fun with Mattermark Investor Data b/Saturday night fun with Mattermark Investor Data
 {
 "metadata": {
  "name": "",
  "signature": "sha256:cab04666f12cfb49fe6cad41d9721df0ba1d4094b7fbb89254d8299eac3855c1"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "heading",
     "level": 1,
     "metadata": {},
     "source": [
      "Trying to plot the Investors Landscap"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "So today I found interesting data on momentum among various investors on mattermark site: http://mattermark.com/app/benchmarking\n",
      "I wondered if just based on this data I could group these investors for their preferences and what stages do they invest in.\n",
      "Let's first try to get hands on this data using our plain old python and BeautifulSoup."
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import urllib2\n",
      "import json\n",
      "from bs4 import BeautifulSoup\n",
      "\n",
      "url = \"http://mattermark.com/app/benchmarking\"\n",
      "\n",
      "content = urllib2.urlopen(url).read()\n",
      "\n",
      "soup = BeautifulSoup(content)\n",
      "\n",
      "# After exploring the page it seems like the last script returned is the one that contains the data in json format. \n",
      "# So extracting it in the below code\n",
      "dat_script = soup.findAll(\"script\")[-1]\n",
      "textValue = dat_script.string\n",
      "jsonValue = '{%s}' % (textValue.split('= {', 1)[1].rsplit('}};', 1)[0],)\n",
      "jsonValue = jsonValue + '}'\n",
      "parsed_value = json.loads(jsonValue)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 1
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "So now we have the data. Lets look at it's structure."
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "parsed_value.keys()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 2,
       "text": [
        "[u'data', u'last_updated']"
       ]
      }
     ],
     "prompt_number": 2
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "parsed_value['data'].keys()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 3,
       "text": [
        "[u'a', u'c', u'b', u'Pre Series A', u'late', u'portfolio']"
       ]
      }
     ],
     "prompt_number": 3
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "The 'portfolio' seems to be some kind of average among all others. Can't figure out what to do with it, so will ignore it for now."
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data = parsed_value['data']\n",
      "\n",
      "seed = data['Pre Series A']\n",
      "seriesA = data['a']\n",
      "seriesB = data['b']\n",
      "seriesC = data['c']\n",
      "late = data['late']\n",
      "\n",
      "stage_wise_data = [seed, seriesA, seriesB, seriesC, late]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 4
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "It seems there are different number of investors in each of the investment stages. Let's fisrt get an idea of distincts in each list and overall."
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "%matplotlib inline\n",
      "\n",
      "# Set up some better defaults for matplotlib\n",
      "from matplotlib import rcParams\n",
      "import brewer2mpl\n",
      "\n",
      "#colorbrewer2 Dark2 qualitative color table\n",
      "dark2_colors = brewer2mpl.get_map('Dark2', 'Qualitative', 7).mpl_colors\n",
      "\n",
      "rcParams['figure.figsize'] = (10, 6)\n",
      "rcParams['figure.dpi'] = 150\n",
      "rcParams['axes.color_cycle'] = dark2_colors\n",
      "rcParams['lines.linewidth'] = 2\n",
      "rcParams['axes.facecolor'] = 'white'\n",
      "rcParams['font.size'] = 14\n",
      "rcParams['patch.edgecolor'] = 'white'\n",
      "rcParams['patch.facecolor'] = dark2_colors[0]\n",
      "rcParams['font.family'] = 'StixGeneral'\n",
      "\n",
      "\n",
      "def remove_border(axes=None, top=False, right=False, left=True, bottom=True):\n",
      "    \"\"\"\n",
      "    Minimize chartjunk by stripping out unnecesasry plot borders and axis ticks\n",
      "    \n",
      "    The top/right/left/bottom keywords toggle whether the corresponding plot border is drawn\n",
      "    \"\"\"\n",
      "    ax = axes or plt.gca()\n",
      "    ax.spines['top'].set_visible(top)\n",
      "    ax.spines['right'].set_visible(right)\n",
      "    ax.spines['left'].set_visible(left)\n",
      "    ax.spines['bottom'].set_visible(bottom)\n",
      "    \n",
      "    #turn off all ticks\n",
      "    ax.yaxis.set_ticks_position('none')\n",
      "    ax.xaxis.set_ticks_position('none')\n",
      "    \n",
      "    #now re-enable visibles\n",
      "    if top:\n",
      "        ax.xaxis.tick_top()\n",
      "    if bottom:\n",
      "        ax.xaxis.tick_bottom()\n",
      "    if left:\n",
      "        ax.yaxis.tick_left()\n",
      "    if right:\n",
      "        ax.yaxis.tick_right()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 5
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# some more imports\n",
      "import prettyplotlib as ppl\n",
      "import matplotlib.pyplot as plt\n",
      "import numpy as np\n",
      "import string\n",
      "\n",
      "# Get the number of distinct investors in each stage and overall distinct\n",
      "stage_num_of_investors = []\n",
      "all_investors = []\n",
      "for stage in stage_wise_data:\n",
      "    stage_num_of_investors.append(len(stage))\n",
      "    all_investors += stage\n",
      "\n",
      "distinct_investors = list(set([item['investor_id'] for item in all_investors]))\n",
      "stage_num_of_investors.append(len(distinct_investors))\n",
      "\n",
      "color_set = ['#69D2E7','#A7DBD8','#E0E4CC','#F38630','#FA6900']\n",
      "color_set.append('#FE4365')\n",
      "names =  [\"Seed Stage\", \"Series A\", \"Series B\", \"Series C\", \"Late Stage\"]\n",
      "names.append(\"Distinct\")\n",
      "\n",
      "fig, ax = plt.subplots(1)\n",
      "n = len(stage_num_of_investors)\n",
      "ppl.bar(ax, np.arange(n), stage_num_of_investors, annotate=True, xticklabels=names, grid='y', color=color_set)\n",
      "ppl.plt.show()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAAAlQAAAFuCAYAAABHkYZ/AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nTkSuQmCC\n",
       "text": [
        "<matplotlib.figure.Figure at 0x10b175cd0>"
       ]
      }
     ],
     "prompt_number": 6
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "So in total we have 629 distinct investors. \n",
      "Now let's have a look at how they are distributed across the stages."
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "seed_id = [item['investor_id'] for item in seed]\n",
      "seriesA_id = [item['investor_id'] for item in seriesA]\n",
      "seriesB_id = [item['investor_id'] for item in seriesB]\n",
      "seriesC_id = [item['investor_id'] for item in seriesC]\n",
      "late_id = [item['investor_id'] for item in late]\n",
      "\n",
      "all_investor_presence_info = {}\n",
      "for id in distinct_investors:\n",
      "    all_investor_presence_info[id] = {'presence_stages':[],'presence':0}\n",
      "    if id in seed_id:\n",
      "        all_investor_presence_info[id]['presence_stages'].append('seed')\n",
      "    if id in seriesA_id:\n",
      "        all_investor_presence_info[id]['presence_stages'].append('seriesA')\n",
      "    if id in seriesB_id:\n",
      "        all_investor_presence_info[id]['presence_stages'].append('seriesB')\n",
      "    if id in seriesC_id:\n",
      "        all_investor_presence_info[id]['presence_stages'].append('seriesC')\n",
      "    if id in late_id:\n",
      "        all_investor_presence_info[id]['presence_stages'].append('late')\n",
      "    \n",
      "    all_investor_presence_info[id]['presence'] = len(all_investor_presence_info[id]['presence_stages'])\n"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 7
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import collections\n",
      "investors_present_in_all_5_stages = []\n",
      "investors_present_in_all_4_stages = []\n",
      "investors_present_in_all_3_stages = []\n",
      "investors_present_in_all_2_stages = []\n",
      "investors_present_in_all_1_stages = []\n",
      "investors_present_in_all_5_stages_cnt = 0\n",
      "investors_present_in_all_4_stages_cnt = 0\n",
      "investors_present_in_all_3_stages_cnt = 0\n",
      "investors_present_in_all_2_stages_cnt = 0\n",
      "investors_present_in_all_1_stages_cnt = 0\n",
      "for key, value in all_investor_presence_info.iteritems():\n",
      "    if value['presence'] == 5:\n",
      "        investors_present_in_all_5_stages_cnt += 1\n",
      "        investors_present_in_all_5_stages += value['presence_stages']\n",
      "    if value['presence'] == 4:\n",
      "        investors_present_in_all_4_stages_cnt += 1\n",
      "        investors_present_in_all_4_stages += value['presence_stages']\n",
      "    if value['presence'] == 3:\n",
      "        investors_present_in_all_3_stages_cnt += 1\n",
      "        investors_present_in_all_3_stages += value['presence_stages']\n",
      "    if value['presence'] == 2:\n",
      "        investors_present_in_all_2_stages_cnt += 1\n",
      "        investors_present_in_all_2_stages += value['presence_stages']\n",
      "    if value['presence'] == 1:\n",
      "        investors_present_in_all_1_stages_cnt += 1\n",
      "        investors_present_in_all_1_stages += value['presence_stages']\n",
      "\n",
      "# Getting total count of investors by no. of stages they are active in\n",
      "investors_present_stages_cnt = [investors_present_in_all_5_stages_cnt, investors_present_in_all_4_stages_cnt, investors_present_in_all_3_stages_cnt, investors_present_in_all_2_stages_cnt, investors_present_in_all_1_stages_cnt]\n",
      "\n",
      "# Let's try to get how among these 5 groups are the no. of investros distributed by the stage in which they are active\n",
      "investors_present_in_all_5_stages_cnts = collections.Counter(investors_present_in_all_5_stages)\n",
      "investors_present_in_all_4_stages_cnts = collections.Counter(investors_present_in_all_4_stages)\n",
      "investors_present_in_all_3_stages_cnts = collections.Counter(investors_present_in_all_3_stages)\n",
      "investors_present_in_all_2_stages_cnts = collections.Counter(investors_present_in_all_2_stages)\n",
      "investors_present_in_all_1_stages_cnts = collections.Counter(investors_present_in_all_1_stages)\n",
      "\n",
      "print investors_present_in_all_5_stages_cnts\n",
      "print investors_present_in_all_4_stages_cnts\n",
      "print investors_present_in_all_3_stages_cnts\n",
      "print investors_present_in_all_2_stages_cnts\n",
      "print investors_present_in_all_1_stages_cnts\n"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "Counter({'seriesB': 89, 'seriesA': 89, 'seed': 89, 'late': 89, 'seriesC': 89})\n",
        "Counter({'seriesB': 60, 'seed': 57, 'seriesA': 46, 'seriesC': 46, 'late': 43})\n",
        "Counter({'seed': 91, 'seriesB': 84, 'seriesA': 75, 'late': 36, 'seriesC': 23})\n",
        "Counter({'seed': 124, 'seriesA': 92, 'late': 36, 'seriesB': 21, 'seriesC': 11})\n",
        "Counter({'seed': 207, 'late': 12, 'seriesB': 8, 'seriesA': 5})\n"
       ]
      }
     ],
     "prompt_number": 8
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Things look fine. Let's proceed.\n",
      "\n",
      "investors_present_in_all_5_stages_distribution = collections.Counter(investors_present_in_all_5_stages)\n",
      "for key in investors_present_in_all_5_stages_distribution.keys():\n",
      "    investors_present_in_all_5_stages_distribution[key] = investors_present_in_all_5_stages_distribution[key]*100.00/investors_present_in_all_5_stages_cnt*1.00\n",
      "investors_present_in_all_4_stages_distribution = collections.Counter(investors_present_in_all_4_stages)\n",
      "for key in investors_present_in_all_4_stages_distribution.keys():\n",
      "    investors_present_in_all_4_stages_distribution[key] = investors_present_in_all_4_stages_distribution[key]*100.00/investors_present_in_all_4_stages_cnt*1.00\n",
      "investors_present_in_all_3_stages_distribution = collections.Counter(investors_present_in_all_3_stages)\n",
      "for key in investors_present_in_all_3_stages_distribution.keys():\n",
      "    investors_present_in_all_3_stages_distribution[key] = investors_present_in_all_3_stages_distribution[key]*100.00/investors_present_in_all_3_stages_cnt*1.00\n",
      "investors_present_in_all_2_stages_distribution = collections.Counter(investors_present_in_all_2_stages)\n",
      "for key in investors_present_in_all_2_stages_distribution.keys():\n",
      "    investors_present_in_all_2_stages_distribution[key] = investors_present_in_all_2_stages_distribution[key]*100.00/investors_present_in_all_2_stages_cnt*1.00\n",
      "investors_present_in_all_1_stages_distribution = collections.Counter(investors_present_in_all_1_stages)\n",
      "for key in investors_present_in_all_1_stages_distribution.keys():\n",
      "    investors_present_in_all_1_stages_distribution[key] = investors_present_in_all_1_stages_distribution[key]*100.00/investors_present_in_all_1_stages_cnt*1.00\n",
      "\n",
      "print [investors_present_in_all_5_stages_distribution,investors_present_in_all_4_stages_distribution,investors_present_in_all_3_stages_distribution,investors_present_in_all_2_stages_distribution,investors_present_in_all_1_stages_distribution]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "[Counter({'seriesB': 100.0, 'seriesA': 100.0, 'seed': 100.0, 'late': 100.0, 'seriesC': 100.0}), Counter({'seriesB': 95.23809523809524, 'seed': 90.47619047619048, 'seriesA': 73.01587301587301, 'seriesC': 73.01587301587301, 'late': 68.25396825396825}), Counter({'seed': 88.3495145631068, 'seriesB': 81.55339805825243, 'seriesA': 72.81553398058253, 'late': 34.95145631067961, 'seriesC': 22.33009708737864}), Counter({'seed': 87.32394366197182, 'seriesA': 64.78873239436619, 'late': 25.35211267605634, 'seriesB': 14.788732394366198, 'seriesC': 7.746478873239437}), Counter({'seed': 89.22413793103448, 'late': 5.172413793103448, 'seriesB': 3.4482758620689653, 'seriesA': 2.1551724137931036})]\n"
       ]
      }
     ],
     "prompt_number": 9
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "seed_cnt = []\n",
      "seriesA_cnt = []\n",
      "seriesB_cnt = []\n",
      "seriesC_cnt = []\n",
      "late_cnt = []\n",
      "\n",
      "stage_wise_cnts = [investors_present_in_all_5_stages_distribution,investors_present_in_all_4_stages_distribution,investors_present_in_all_3_stages_distribution,investors_present_in_all_2_stages_distribution,investors_present_in_all_1_stages_distribution]\n",
      "\n",
      "for swc in stage_wise_cnts:\n",
      "    if swc.has_key('seed'):\n",
      "        seed_cnt.append(swc['seed'])\n",
      "    else:\n",
      "        seed_cnt.append(0)\n",
      "    if swc.has_key('seriesA'):\n",
      "        seriesA_cnt.append(swc['seriesA'])\n",
      "    else:\n",
      "        seriesA_cnt.append(0)\n",
      "    if swc.has_key('seriesB'):\n",
      "        seriesB_cnt.append(swc['seriesB'])\n",
      "    else:\n",
      "        seriesB_cnt.append(0)\n",
      "    if swc.has_key('seriesC'):\n",
      "        seriesC_cnt.append(swc['seriesC'])\n",
      "    else:\n",
      "        seriesC_cnt.append(0)\n",
      "    if swc.has_key('late'):\n",
      "        late_cnt.append(swc['late'])\n",
      "    else:\n",
      "        late_cnt.append(0)\n",
      "\n",
      "print seed_cnt, seriesA_cnt, seriesB_cnt, seriesC_cnt,late_cnt"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "[100.0, 90.47619047619048, 88.3495145631068, 87.32394366197182, 89.22413793103448] [100.0, 73.01587301587301, 72.81553398058253, 64.78873239436619, 2.1551724137931036] [100.0, 95.23809523809524, 81.55339805825243, 14.788732394366198, 3.4482758620689653] [100.0, 73.01587301587301, 22.33009708737864, 7.746478873239437, 0] [100.0, 68.25396825396825, 34.95145631067961, 25.35211267605634, 5.172413793103448]\n"
       ]
      }
     ],
     "prompt_number": 10
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# The distributions look correct, so let's plot them now!\n",
      "plt.subplot(211)\n",
      "n = 5\n",
      "plt.bar(np.arange(n), investors_present_stages_cnt, width=0.95)\n",
      "plt.xticks(np.arange(n)+0.95/2, ['All 5 stages', 'In 4 stages', 'In 3 stages', 'In 2 stages', 'In 1 stage only'], rotation='horizontal')\n",
      "plt.ylabel(\"Number of investors\")\n",
      "plt.xlabel(\"Investments activity\")\n",
      "plt.title(\"How many Investors are investing in how many stages\")\n",
      "remove_border()\n",
      "\n",
      "for x, y in zip(np.arange(n), investors_present_stages_cnt):\n",
      "    plt.annotate(\"%i\" % y, (x+0.95/2, y + 5), ha='center')\n",
      "\n",
      "plt.show()\n",
      "\n",
      "plt.subplot(111)\n",
      "n = 5\n",
      "\n",
      "plt.xticks([0.5,1,1.5,2,2.5,3,3.5], ['','All 5 stages', 'In 4 stages', 'In 3 stages', 'In 2 stages', 'In 1 stages',''], rotation='horizontal')\n",
      "plt.yticks(np.arange(n+2)+1, ['Seed Stage', 'Series A', 'Series B', 'Series C', 'Late',''], rotation='horizontal')\n",
      "plt.ylabel(\"Investment Stage\")\n",
      "plt.xlabel(\"Investments activity\")\n",
      "plt.legend(loc='best')\n",
      "plt.title(\"What % of Investors are invested in different stages\")\n",
      "remove_border()\n",
      "\n",
      "plt.scatter([0.5,1,1.5,2,2.5,3,3.5], [0.5]*7, s=[0,0,0,0,0,0,0], c=color_set[0])\n",
      "plt.scatter([0.5,1,1.5,2,2.5,3,3.5], [1]*7, s=map(lambda x: x*30, [0]+seed_cnt+[0]), c=color_set[0])\n",
      "plt.scatter([0.5,1,1.5,2,2.5,3,3.5], [2]*7, s=map(lambda x: x*30, [0]+seriesA_cnt+[0]), c=color_set[1])\n",
      "plt.scatter([0.5,1,1.5,2,2.5,3,3.5], [3]*7, s=map(lambda x: x*30, [0]+seriesB_cnt+[0]), c=color_set[2])\n",
      "plt.scatter([0.5,1,1.5,2,2.5,3,3.5], [4]*7, s=map(lambda x: x*30, [0]+seriesC_cnt+[0]), c=color_set[3])\n",
      "plt.scatter([0.5,1,1.5,2,2.5,3,3.5], [5]*7, s=map(lambda x: x*30, [0]+late_cnt+[0]), c=color_set[4])\n",
      "plt.scatter([0.5,1,1.5,2,2.5,3,3.5], [5.5]*7, s=[0,0,0,0,0,0,0], c=color_set[0])\n",
      "\n",
      "for x, y, s in zip([1,1.5,2,2.5,3], [1]*5, seed_cnt):\n",
      "    plt.annotate(\"%i%%\" % s, (x, y-0.06), ha='center', color='white')\n",
      "\n",
      "for x, y, s in zip([1,1.5,2,2.5,3], [2]*5, seriesA_cnt):\n",
      "    if x == 3:\n",
      "        plt.annotate(\"%i%%\" % s, (x+0.11, y-0.06), ha='center', color='grey')\n",
      "    else:\n",
      "        plt.annotate(\"%i%%\" % s, (x, y-0.06), ha='center', color='white')\n",
      "\n",
      "for x, y, s in zip([1,1.5,2,2.5,3], [3]*5, seriesB_cnt):\n",
      "    if x == 3:\n",
      "        plt.annotate(\"%i%%\" % s, (x+0.11, y-0.06), ha='center', color='grey')\n",
      "    elif x == 2.5:\n",
      "        plt.annotate(\"%i%%\" % s, (x+0.13, y-0.06), ha='center', color='grey')\n",
      "    else:\n",
      "        plt.annotate(\"%i%%\" % s, (x, y-0.06), ha='center', color='white')\n",
      "    \n",
      "for x, y, s in zip([1,1.5,2,2.5,3], [4]*5, seriesC_cnt):\n",
      "    if x == 3:\n",
      "        plt.annotate(\"%i%%\" % s, (x, y-0.06), ha='center', color='grey')\n",
      "    elif x == 2.5:\n",
      "        plt.annotate(\"%i%%\" % s, (x+0.11, y-0.06), ha='center', color='grey')\n",
      "    else:\n",
      "        plt.annotate(\"%i%%\" % s, (x, y-0.06), ha='center', color='white')\n",
      "\n",
      "for x, y, s in zip([1,1.5,2,2.5,3], [5]*5, late_cnt):\n",
      "    if x == 3:\n",
      "        plt.annotate(\"%i%%\" % s, (x+0.11, y-0.06), ha='center', color='grey')\n",
      "    else:\n",
      "        plt.annotate(\"%i%%\" % s, (x, y-0.06), ha='center', color='white')\n",
      "\n",
      "plt.show()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAAAmcAAADbCAYAAAAoJTY2AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nIiIiUjP+P0bkcRIBYFeeAAAAAElFTkSuQmCC\n",
       "text": [
        "<matplotlib.figure.Figure at 0x10aeb8a90>"
       ]
      },
      {
       "metadata": {},
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAAApAAAAGRCAYAAADSAYNoAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
       "text": [
        "<matplotlib.figure.Figure at 0x10b4974d0>"
       ]
      }
     ],
     "prompt_number": 14
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Finally I have the graphs I initially wanted to see. (Also had fun learning about iPython notebooks and matplotlib. Yay!)\n",
      "\n",
      "It seems there are a lot of investors who are active in only one stage and majority of them invest at seed stage. I wonder how many of them would be recent entrants. No data on that yet, perhaps will deal with this curiosity later sometime.\n",
      "\n",
      "Also it looks like that everyone likes seed stage investing. I guess it's the possibility of high returns with relatively minor investments.\n",
      "\n",
      "Looking at the size of investments in combination of the above might be interesting as well I think. I guess the fine people at Mattermark will look at that. :)\n",
      "\n",
      "Now let's say I want to get the investors who are only present in 1 satge but also invest only in late stage."
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# available data keys\n",
      "data.keys()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 12,
       "text": [
        "[u'a', u'c', u'b', u'Pre Series A', u'late', u'portfolio']"
       ]
      }
     ],
     "prompt_number": 12
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import pandas as pd\n",
      "from pandas.io.json import json_normalize\n",
      "\n",
      "# options are 1,2,3,4,5\n",
      "num_stages = 1\n",
      "# options are 'seed', 'seriesA', 'seriesA', 'seriesA', 'late'\n",
      "investment_stage = 'late'\n",
      "\n",
      "# Rest below should be able to select the particular combination os investors we are looking for.\n",
      "data_dict_stage_mapping = {'seed': 'Pre Series A', 'seriesA':'a', 'seriesB':'b', 'seriesC':'c', 'late':'late'}\n",
      "data_dict_key = data_dict_stage_mapping[investment_stage]\n",
      "\n",
      "shortlist_ids = []\n",
      "\n",
      "for key, value in all_investor_presence_info.iteritems():\n",
      "    if all_investor_presence_info[key]['presence'] == num_stages and investment_stage in all_investor_presence_info[key]['presence_stages']:\n",
      "        shortlist_ids.append(str(key))\n",
      "\n",
      "shortlist_data = [investor for investor in data[data_dict_key] if investor['investor_id'] in shortlist_ids ]\n",
      "shortlist_table = 'Not Available'\n",
      "if shortlist_data:\n",
      "    shortlist_table = json_normalize(shortlist_data)\n",
      "\n",
      "# We just present the data based on the two selections above, namely 'num_stages' and 'investment_stage'\n",
      "print 'Number of such investors active in', num_stages, 'stages and also investing in', investment_stage, ' stage is:', len(shortlist_data)\n",
      "print 'Detailed list as below: (more information on http://mattermark.com/app/benchmarking)'\n",
      "shortlist_table\n"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "Number of such investors active in 1 stages and also investing in late  stage is: 12\n",
        "Detailed list as below: (more information on http://mattermark.com/app/benchmarking)\n"
       ]
      },
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>average_mm</th>\n",
        "      <th>delta</th>\n",
        "      <th>investor</th>\n",
        "      <th>investor_id</th>\n",
        "      <th>rank</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0 </th>\n",
        "      <td> 458</td>\n",
        "      <td>  2</td>\n",
        "      <td>               T. Rowe Price</td>\n",
        "      <td>   253</td>\n",
        "      <td>  11</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1 </th>\n",
        "      <td> 286</td>\n",
        "      <td>  -</td>\n",
        "      <td>                  Marker LLC</td>\n",
        "      <td> 20462</td>\n",
        "      <td>  35</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2 </th>\n",
        "      <td> 262</td>\n",
        "      <td>  -</td>\n",
        "      <td>           Four Rivers Group</td>\n",
        "      <td>   584</td>\n",
        "      <td>  44</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3 </th>\n",
        "      <td> 261</td>\n",
        "      <td>  -</td>\n",
        "      <td>            American Express</td>\n",
        "      <td>  8374</td>\n",
        "      <td>  46</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4 </th>\n",
        "      <td> 222</td>\n",
        "      <td> 20</td>\n",
        "      <td>    Glynn Capital Management</td>\n",
        "      <td>   189</td>\n",
        "      <td>  69</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>5 </th>\n",
        "      <td> 213</td>\n",
        "      <td> 25</td>\n",
        "      <td>           Fidelity Ventures</td>\n",
        "      <td>   819</td>\n",
        "      <td>  72</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>6 </th>\n",
        "      <td> 126</td>\n",
        "      <td> 11</td>\n",
        "      <td>             Lehman Brothers</td>\n",
        "      <td>   708</td>\n",
        "      <td> 124</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>7 </th>\n",
        "      <td>  64</td>\n",
        "      <td>  -</td>\n",
        "      <td>             Aisling Capital</td>\n",
        "      <td>  4077</td>\n",
        "      <td> 171</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>8 </th>\n",
        "      <td>  36</td>\n",
        "      <td> 36</td>\n",
        "      <td>               Ventures West</td>\n",
        "      <td>  1831</td>\n",
        "      <td> 194</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>9 </th>\n",
        "      <td>  35</td>\n",
        "      <td>  -</td>\n",
        "      <td>               Aeris Capital</td>\n",
        "      <td>   881</td>\n",
        "      <td> 196</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>10</th>\n",
        "      <td>  27</td>\n",
        "      <td> 41</td>\n",
        "      <td> Frazier Healthcare Ventures</td>\n",
        "      <td>  2736</td>\n",
        "      <td> 204</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>11</th>\n",
        "      <td>  18</td>\n",
        "      <td> 44</td>\n",
        "      <td>             Delphi Ventures</td>\n",
        "      <td>  3476</td>\n",
        "      <td> 209</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "<p>12 rows \u00d7 5 columns</p>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 13,
       "text": [
        "   average_mm delta                     investor investor_id rank\n",
        "0         458     2                T. Rowe Price         253   11\n",
        "1         286     -                   Marker LLC       20462   35\n",
        "2         262     -            Four Rivers Group         584   44\n",
        "3         261     -             American Express        8374   46\n",
        "4         222    20     Glynn Capital Management         189   69\n",
        "5         213    25            Fidelity Ventures         819   72\n",
        "6         126    11              Lehman Brothers         708  124\n",
        "7          64     -              Aisling Capital        4077  171\n",
        "8          36    36                Ventures West        1831  194\n",
        "9          35     -                Aeris Capital         881  196\n",
        "10         27    41  Frazier Healthcare Ventures        2736  204\n",
        "11         18    44              Delphi Ventures        3476  209\n",
        "\n",
        "[12 rows x 5 columns]"
       ]
      }
     ],
     "prompt_number": 13
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 13
    }
   ],
   "metadata": {}
  }
 ]
 }