IIabm/AmendFirm_20230216.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "from sklearn.preprocessing import MinMaxScaler\n",
    "import networkx as nx\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "plt.rcParams['font.sans-serif'] = 'SimHei'\n",
    "\n",
    "BomNodes = pd.read_csv('BomNodes.csv', index_col=0)\n",
    "BomNodes.set_index('Code', inplace=True)\n",
    "BomCateNet = pd.read_csv('BomCateNet.csv', index_col=0)\n",
    "BomCateNet.fillna(0, inplace=True)\n",
    "\n",
    "G = nx.from_pandas_adjacency(BomCateNet, create_using=nx.MultiDiGraph())\n",
    "\n",
    "labels_dict = {}\n",
    "for code in G.nodes:\n",
    "    labels_dict[code] = BomNodes.loc[code].to_dict()\n",
    "nx.set_node_attributes(G, labels_dict)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {},
   "outputs": [],
   "source": [
    "# amend\n",
    "dict_nodes = {0: sorted([node for node in G.nodes() if G.out_degree(node)==0])}\n",
    "level = 1\n",
    "while True:\n",
    "    nodes = [list(G.predecessors(node)) for node in dict_nodes[level-1]]\n",
    "    nodes = sorted(list(set([i for j in nodes for i in j])))\n",
    "    if nodes:\n",
    "        dict_nodes[level] = nodes\n",
    "        level += 1\n",
    "    else:\n",
    "        break\n",
    "\n",
    "Firm = pd.read_csv(\"Firm.csv\")\n",
    "Firm.loc[:, '1':].fillna(0, inplace=True)\n",
    "Firm_copy = Firm.copy()\n",
    "\n",
    "# size\n",
    "# Firm_copy['Assets_Std_Log'] = Firm_copy['Assets'].map()\n",
    "\n",
    "\n",
    "for tier in list(dict_nodes.keys())[1:]:\n",
    "    for node in dict_nodes[tier]:\n",
    "        list_neighbors = list(G.neighbors(node))\n",
    "        firm_list = Firm_copy.index[(Firm_copy[list_neighbors]==1).all(axis=1)].to_list()\n",
    "        if firm_list:\n",
    "            Firm_copy.loc[firm_list, node] = 1\n",
    "            Firm_copy.loc[firm_list, list_neighbors] = 0\n",
    "Firm_copy.to_csv('Firm_amended.csv', index=False, encoding='utf-8-sig')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\25759\\AppData\\Local\\Temp\\ipykernel_1648\\3829775229.py:1: RuntimeWarning: divide by zero encountered in log\n",
      "  np.log(MinMaxScaler().fit_transform(Firm_copy['Assets'].array.reshape(-1,1)).reshape(-1))\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "array([-5.79695865e+00, -1.05315349e+01,             nan,             nan,\n",
       "                   nan,             nan, -9.82489222e+00,             nan,\n",
       "                   nan,             nan,             nan, -8.54791316e+00,\n",
       "                   nan, -7.39462390e+00, -6.49144375e+00, -6.63297162e+00,\n",
       "       -8.74295074e+00,             nan,             nan,             nan,\n",
       "                   nan, -4.98672129e+00,             nan, -7.15116331e+00,\n",
       "       -8.67997329e+00, -9.03351444e+00,             nan,             nan,\n",
       "       -6.41683918e+00, -1.19415961e+00,             nan,             nan,\n",
       "                   nan,             nan,             nan,             nan,\n",
       "       -8.92590857e+00, -8.00385163e+00,             nan, -5.62126006e+00,\n",
       "       -6.94229562e+00, -7.35938613e+00,             nan, -8.47199108e+00,\n",
       "       -8.46956851e+00,             nan,             nan,             nan,\n",
       "       -6.27245916e+00, -1.22964831e+01,             nan,             nan,\n",
       "                   nan, -7.09439697e+00,             nan,             nan,\n",
       "       -1.07941709e+01,             nan, -6.68846593e+00,             nan,\n",
       "                   nan, -1.02805224e+01,             nan,             nan,\n",
       "                   nan, -2.89581363e+00, -3.14642534e+00, -2.01442648e+00,\n",
       "       -8.44633549e+00, -5.33806488e+00, -4.00155152e+00, -7.47168894e+00,\n",
       "       -5.76243404e+00, -5.11629547e+00, -3.43739566e+00, -2.72060618e+00,\n",
       "                   nan, -2.72740307e+00,             nan, -6.10253090e+00,\n",
       "       -3.40938096e+00, -3.33850521e+00,             nan, -4.39675140e+00,\n",
       "       -2.87207515e+00, -4.89774846e+00, -2.78787497e+00, -4.39833209e+00,\n",
       "       -3.54839710e+00, -5.20610112e+00,             nan,             nan,\n",
       "       -5.80176128e+00, -6.12994085e+00, -4.03249194e+00, -3.55212392e+00,\n",
       "       -3.02365487e+00, -2.31068645e+00, -1.79283273e+00, -2.61379988e+00,\n",
       "       -5.43652599e+00, -3.64625906e+00, -1.56173681e+00, -4.99005631e+00,\n",
       "       -4.36943191e+00, -2.47700081e+00, -1.11022302e-16, -7.98515146e+00,\n",
       "       -3.51829256e+00, -6.65807194e+00,             nan, -8.62279785e+00,\n",
       "       -1.04760385e+01,             nan,             nan, -3.94669845e+00,\n",
       "       -8.74978915e+00,             nan,             nan, -7.23791464e+00,\n",
       "                   nan,             nan, -8.61078329e+00, -8.64809500e+00,\n",
       "       -4.14946141e+00,             nan,             nan,             nan,\n",
       "       -8.23878056e+00, -8.35536371e+00, -7.06209095e+00,             nan,\n",
       "       -8.37466693e+00, -7.72472197e+00, -1.07697369e+01, -8.14581821e+00,\n",
       "       -3.57151721e+00, -1.10235174e+01, -8.85687933e+00, -1.00163709e+01,\n",
       "       -8.95076486e+00,             nan, -7.15287212e+00,             nan,\n",
       "       -9.55820652e+00,             nan, -1.14908579e+01, -7.28574198e+00,\n",
       "       -2.07280506e+00,             nan, -8.89899629e+00,            -inf,\n",
       "       -7.58795439e+00,             nan,             nan, -3.85259181e+00,\n",
       "                   nan,             nan, -1.08449064e+01, -4.41480330e+00,\n",
       "       -7.22166822e+00,             nan,             nan,             nan,\n",
       "                   nan,             nan,             nan, -5.17433354e+00,\n",
       "       -7.21006323e+00, -4.09344850e+00])"
      ]
     },
     "execution_count": 59,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.log(MinMaxScaler().fit_transform(Firm_copy['Assets'].array.reshape(-1,1)).reshape(-1))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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
      "text/plain": [
       "<Figure size 3600x3600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# visualization\n",
    "firm_num_dict = {}\n",
    "for node in nx.nodes(G):\n",
    "    firm_num_dict[node]= sum(Firm_copy[node]==1)\n",
    "nx.set_node_attributes(G, firm_num_dict, name=\"Num_Firm\")\n",
    "\n",
    "pos = nx.nx_agraph.graphviz_layout(G, prog=\"twopi\", args=\"\")\n",
    "dict_num_firm = nx.get_node_attributes(G, 'Num_Firm')\n",
    "dict_node_name = nx.get_node_attributes(G, 'Name')\n",
    "node_labels = {}\n",
    "for node in nx.nodes(G):\n",
    "    node_labels[node] = f\"{node} {str(dict_node_name[node])} {str(dict_num_firm[node])}\"\n",
    "plt.figure(figsize=(12, 12), dpi=300)\n",
    "nx.draw_networkx_nodes(G, pos)\n",
    "nx.draw_networkx_edges(G, pos)\n",
    "nx.draw_networkx_labels(G, pos, labels = node_labels, font_size=4)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0      True\n",
       "1      True\n",
       "2      True\n",
       "3      True\n",
       "4      True\n",
       "       ... \n",
       "165    True\n",
       "166    True\n",
       "167    True\n",
       "168    True\n",
       "169    True\n",
       "Name: Num_Employ, Length: 170, dtype: bool"
      ]
     },
     "execution_count": 64,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import seaborn as sns\n",
    "data = Firm_copy[Firm_copy['Num_Employ'] > 0]['Num_Employ']\n",
    "data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "base",
   "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": "3.8.8"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "bcdafc093860683ffb58d6956591562b7f8ed5d58147d17d71a5d4d6605a08df"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}