{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "ab75ca0c-004e-4350-a9e7-59972b2efff1",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "b107f3b2-57f3-4439-883b-146f22ea5e07",
   "metadata": {},
   "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>sku</th>\n",
       "      <th>national_inv</th>\n",
       "      <th>lead_time</th>\n",
       "      <th>in_transit_qty</th>\n",
       "      <th>forecast_3_month</th>\n",
       "      <th>forecast_6_month</th>\n",
       "      <th>forecast_9_month</th>\n",
       "      <th>sales_1_month</th>\n",
       "      <th>sales_3_month</th>\n",
       "      <th>sales_6_month</th>\n",
       "      <th>...</th>\n",
       "      <th>pieces_past_due</th>\n",
       "      <th>perf_6_month_avg</th>\n",
       "      <th>perf_12_month_avg</th>\n",
       "      <th>local_bo_qty</th>\n",
       "      <th>deck_risk</th>\n",
       "      <th>oe_constraint</th>\n",
       "      <th>ppap_risk</th>\n",
       "      <th>stop_auto_buy</th>\n",
       "      <th>rev_stop</th>\n",
       "      <th>went_on_backorder</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1888279</td>\n",
       "      <td>117</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>15</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>-99.00</td>\n",
       "      <td>-99.00</td>\n",
       "      <td>0</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1870557</td>\n",
       "      <td>7</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0.50</td>\n",
       "      <td>0.28</td>\n",
       "      <td>0</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1475481</td>\n",
       "      <td>258</td>\n",
       "      <td>15.0</td>\n",
       "      <td>10</td>\n",
       "      <td>10</td>\n",
       "      <td>77</td>\n",
       "      <td>184</td>\n",
       "      <td>46</td>\n",
       "      <td>132</td>\n",
       "      <td>256</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0.54</td>\n",
       "      <td>0.70</td>\n",
       "      <td>0</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1758220</td>\n",
       "      <td>46</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>6</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0.75</td>\n",
       "      <td>0.90</td>\n",
       "      <td>0</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>4 rows × 23 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       sku  national_inv  lead_time  in_transit_qty  forecast_3_month  \\\n",
       "0  1888279           117        NaN               0                 0   \n",
       "1  1870557             7        2.0               0                 0   \n",
       "2  1475481           258       15.0              10                10   \n",
       "3  1758220            46        2.0               0                 0   \n",
       "\n",
       "   forecast_6_month  forecast_9_month  sales_1_month  sales_3_month  \\\n",
       "0                 0                 0              0              0   \n",
       "1                 0                 0              0              0   \n",
       "2                77               184             46            132   \n",
       "3                 0                 0              1              2   \n",
       "\n",
       "   sales_6_month  ...  pieces_past_due  perf_6_month_avg perf_12_month_avg  \\\n",
       "0             15  ...                0            -99.00            -99.00   \n",
       "1              0  ...                0              0.50              0.28   \n",
       "2            256  ...                0              0.54              0.70   \n",
       "3              6  ...                0              0.75              0.90   \n",
       "\n",
       "   local_bo_qty  deck_risk  oe_constraint  ppap_risk stop_auto_buy rev_stop  \\\n",
       "0             0         No             No        Yes           Yes       No   \n",
       "1             0        Yes             No         No           Yes       No   \n",
       "2             0         No             No         No           Yes       No   \n",
       "3             0        Yes             No         No           Yes       No   \n",
       "\n",
       "  went_on_backorder  \n",
       "0                No  \n",
       "1                No  \n",
       "2                No  \n",
       "3                No  \n",
       "\n",
       "[4 rows x 23 columns]"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "orders = pd.read_csv('BackOrders.csv')\n",
    "\n",
    "orders.head(4)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "a0ce2f36-0875-432c-8e9c-2a5dec9f908d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(61589, 23)"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "orders.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "7cada021-5822-4754-9195-2af60b28db30",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 61589 entries, 0 to 61588\n",
      "Data columns (total 23 columns):\n",
      " #   Column             Non-Null Count  Dtype  \n",
      "---  ------             --------------  -----  \n",
      " 0   sku                61589 non-null  int64  \n",
      " 1   national_inv       61589 non-null  int64  \n",
      " 2   lead_time          58186 non-null  float64\n",
      " 3   in_transit_qty     61589 non-null  int64  \n",
      " 4   forecast_3_month   61589 non-null  int64  \n",
      " 5   forecast_6_month   61589 non-null  int64  \n",
      " 6   forecast_9_month   61589 non-null  int64  \n",
      " 7   sales_1_month      61589 non-null  int64  \n",
      " 8   sales_3_month      61589 non-null  int64  \n",
      " 9   sales_6_month      61589 non-null  int64  \n",
      " 10  sales_9_month      61589 non-null  int64  \n",
      " 11  min_bank           61589 non-null  int64  \n",
      " 12  potential_issue    61589 non-null  object \n",
      " 13  pieces_past_due    61589 non-null  int64  \n",
      " 14  perf_6_month_avg   61589 non-null  float64\n",
      " 15  perf_12_month_avg  61589 non-null  float64\n",
      " 16  local_bo_qty       61589 non-null  int64  \n",
      " 17  deck_risk          61589 non-null  object \n",
      " 18  oe_constraint      61589 non-null  object \n",
      " 19  ppap_risk          61589 non-null  object \n",
      " 20  stop_auto_buy      61589 non-null  object \n",
      " 21  rev_stop           61589 non-null  object \n",
      " 22  went_on_backorder  61589 non-null  object \n",
      "dtypes: float64(3), int64(13), object(7)\n",
      "memory usage: 10.8+ MB\n"
     ]
    }
   ],
   "source": [
    "orders.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "b6c8cc41-49bf-4e08-9f4f-f89a87616da7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "sku                     0\n",
       "national_inv            0\n",
       "lead_time            3403\n",
       "in_transit_qty          0\n",
       "forecast_3_month        0\n",
       "forecast_6_month        0\n",
       "forecast_9_month        0\n",
       "sales_1_month           0\n",
       "sales_3_month           0\n",
       "sales_6_month           0\n",
       "sales_9_month           0\n",
       "min_bank                0\n",
       "potential_issue         0\n",
       "pieces_past_due         0\n",
       "perf_6_month_avg        0\n",
       "perf_12_month_avg       0\n",
       "local_bo_qty            0\n",
       "deck_risk               0\n",
       "oe_constraint           0\n",
       "ppap_risk               0\n",
       "stop_auto_buy           0\n",
       "rev_stop                0\n",
       "went_on_backorder       0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "orders.isnull().sum(axis=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "7e380cde-5dce-4d7d-a70d-796e98c9e79f",
   "metadata": {},
   "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>sku</th>\n",
       "      <th>national_inv</th>\n",
       "      <th>lead_time</th>\n",
       "      <th>in_transit_qty</th>\n",
       "      <th>forecast_3_month</th>\n",
       "      <th>forecast_6_month</th>\n",
       "      <th>forecast_9_month</th>\n",
       "      <th>sales_1_month</th>\n",
       "      <th>sales_3_month</th>\n",
       "      <th>sales_6_month</th>\n",
       "      <th>sales_9_month</th>\n",
       "      <th>min_bank</th>\n",
       "      <th>pieces_past_due</th>\n",
       "      <th>perf_6_month_avg</th>\n",
       "      <th>perf_12_month_avg</th>\n",
       "      <th>local_bo_qty</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>6.158900e+04</td>\n",
       "      <td>61589.000000</td>\n",
       "      <td>58186.000000</td>\n",
       "      <td>61589.000000</td>\n",
       "      <td>6.158900e+04</td>\n",
       "      <td>6.158900e+04</td>\n",
       "      <td>6.158900e+04</td>\n",
       "      <td>61589.000000</td>\n",
       "      <td>61589.000000</td>\n",
       "      <td>6.158900e+04</td>\n",
       "      <td>6.158900e+04</td>\n",
       "      <td>61589.000000</td>\n",
       "      <td>61589.000000</td>\n",
       "      <td>61589.000000</td>\n",
       "      <td>61589.000000</td>\n",
       "      <td>61589.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>2.037188e+06</td>\n",
       "      <td>287.721882</td>\n",
       "      <td>7.559619</td>\n",
       "      <td>30.192843</td>\n",
       "      <td>1.692728e+02</td>\n",
       "      <td>3.150413e+02</td>\n",
       "      <td>4.535760e+02</td>\n",
       "      <td>44.742957</td>\n",
       "      <td>150.732631</td>\n",
       "      <td>2.835465e+02</td>\n",
       "      <td>4.196427e+02</td>\n",
       "      <td>43.087256</td>\n",
       "      <td>1.605400</td>\n",
       "      <td>-6.264182</td>\n",
       "      <td>-5.863664</td>\n",
       "      <td>1.205361</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>6.564178e+05</td>\n",
       "      <td>4233.906931</td>\n",
       "      <td>6.498952</td>\n",
       "      <td>792.869253</td>\n",
       "      <td>5.286742e+03</td>\n",
       "      <td>9.774362e+03</td>\n",
       "      <td>1.420201e+04</td>\n",
       "      <td>1373.805831</td>\n",
       "      <td>5224.959649</td>\n",
       "      <td>8.872270e+03</td>\n",
       "      <td>1.269858e+04</td>\n",
       "      <td>959.614135</td>\n",
       "      <td>42.309229</td>\n",
       "      <td>25.537906</td>\n",
       "      <td>24.844514</td>\n",
       "      <td>29.981155</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>1.068628e+06</td>\n",
       "      <td>-2999.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>-99.000000</td>\n",
       "      <td>-99.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>1.498574e+06</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.620000</td>\n",
       "      <td>0.640000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>1.898033e+06</td>\n",
       "      <td>10.000000</td>\n",
       "      <td>8.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>4.000000e+00</td>\n",
       "      <td>6.000000e+00</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.820000</td>\n",
       "      <td>0.800000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>2.314826e+06</td>\n",
       "      <td>57.000000</td>\n",
       "      <td>8.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.200000e+01</td>\n",
       "      <td>2.500000e+01</td>\n",
       "      <td>3.600000e+01</td>\n",
       "      <td>6.000000</td>\n",
       "      <td>17.000000</td>\n",
       "      <td>3.400000e+01</td>\n",
       "      <td>5.100000e+01</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.960000</td>\n",
       "      <td>0.950000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>3.284895e+06</td>\n",
       "      <td>673445.000000</td>\n",
       "      <td>52.000000</td>\n",
       "      <td>170976.000000</td>\n",
       "      <td>1.126656e+06</td>\n",
       "      <td>2.094336e+06</td>\n",
       "      <td>3.062016e+06</td>\n",
       "      <td>295197.000000</td>\n",
       "      <td>934593.000000</td>\n",
       "      <td>1.799099e+06</td>\n",
       "      <td>2.631590e+06</td>\n",
       "      <td>192978.000000</td>\n",
       "      <td>7392.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>2999.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                sku   national_inv     lead_time  in_transit_qty  \\\n",
       "count  6.158900e+04   61589.000000  58186.000000    61589.000000   \n",
       "mean   2.037188e+06     287.721882      7.559619       30.192843   \n",
       "std    6.564178e+05    4233.906931      6.498952      792.869253   \n",
       "min    1.068628e+06   -2999.000000      0.000000        0.000000   \n",
       "25%    1.498574e+06       3.000000      4.000000        0.000000   \n",
       "50%    1.898033e+06      10.000000      8.000000        0.000000   \n",
       "75%    2.314826e+06      57.000000      8.000000        0.000000   \n",
       "max    3.284895e+06  673445.000000     52.000000   170976.000000   \n",
       "\n",
       "       forecast_3_month  forecast_6_month  forecast_9_month  sales_1_month  \\\n",
       "count      6.158900e+04      6.158900e+04      6.158900e+04   61589.000000   \n",
       "mean       1.692728e+02      3.150413e+02      4.535760e+02      44.742957   \n",
       "std        5.286742e+03      9.774362e+03      1.420201e+04    1373.805831   \n",
       "min        0.000000e+00      0.000000e+00      0.000000e+00       0.000000   \n",
       "25%        0.000000e+00      0.000000e+00      0.000000e+00       0.000000   \n",
       "50%        0.000000e+00      0.000000e+00      0.000000e+00       0.000000   \n",
       "75%        1.200000e+01      2.500000e+01      3.600000e+01       6.000000   \n",
       "max        1.126656e+06      2.094336e+06      3.062016e+06  295197.000000   \n",
       "\n",
       "       sales_3_month  sales_6_month  sales_9_month       min_bank  \\\n",
       "count   61589.000000   6.158900e+04   6.158900e+04   61589.000000   \n",
       "mean      150.732631   2.835465e+02   4.196427e+02      43.087256   \n",
       "std      5224.959649   8.872270e+03   1.269858e+04     959.614135   \n",
       "min         0.000000   0.000000e+00   0.000000e+00       0.000000   \n",
       "25%         0.000000   0.000000e+00   0.000000e+00       0.000000   \n",
       "50%         2.000000   4.000000e+00   6.000000e+00       0.000000   \n",
       "75%        17.000000   3.400000e+01   5.100000e+01       3.000000   \n",
       "max    934593.000000   1.799099e+06   2.631590e+06  192978.000000   \n",
       "\n",
       "       pieces_past_due  perf_6_month_avg  perf_12_month_avg  local_bo_qty  \n",
       "count     61589.000000      61589.000000       61589.000000  61589.000000  \n",
       "mean          1.605400         -6.264182          -5.863664      1.205361  \n",
       "std          42.309229         25.537906          24.844514     29.981155  \n",
       "min           0.000000        -99.000000         -99.000000      0.000000  \n",
       "25%           0.000000          0.620000           0.640000      0.000000  \n",
       "50%           0.000000          0.820000           0.800000      0.000000  \n",
       "75%           0.000000          0.960000           0.950000      0.000000  \n",
       "max        7392.000000          1.000000           1.000000   2999.000000  "
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "orders.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "f695df27-108b-487a-8cde-e8dbe95200ec",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "sku                  0\n",
       "national_inv         0\n",
       "lead_time            0\n",
       "in_transit_qty       0\n",
       "forecast_3_month     0\n",
       "forecast_6_month     0\n",
       "forecast_9_month     0\n",
       "sales_1_month        0\n",
       "sales_3_month        0\n",
       "sales_6_month        0\n",
       "sales_9_month        0\n",
       "min_bank             0\n",
       "potential_issue      0\n",
       "pieces_past_due      0\n",
       "perf_6_month_avg     0\n",
       "perf_12_month_avg    0\n",
       "local_bo_qty         0\n",
       "deck_risk            0\n",
       "oe_constraint        0\n",
       "ppap_risk            0\n",
       "stop_auto_buy        0\n",
       "rev_stop             0\n",
       "went_on_backorder    0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "orders[\"lead_time\"] = orders[\"lead_time\"].fillna(orders[\"lead_time\"].mean())\n",
    "orders.isnull().sum(axis=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "14247ac6-0ede-45c8-8b2b-b65226ca3983",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.12.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}