diff --git a/notebooks/regression/preprocessing_Shivasmi.ipynb b/notebooks/regression/preprocessing_Shivasmi.ipynb
index eeed1201191198a3203eebf942775137665ce6d4..c2a6debc350cea5195d206a9392ba388b0a94ac4 100644
--- a/notebooks/regression/preprocessing_Shivasmi.ipynb
+++ b/notebooks/regression/preprocessing_Shivasmi.ipynb
@@ -455,7 +455,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "df['reopen_count'] = df_original['reopen_count']"
+    "df['reopen_count'] = df_original['reopen_count'] #keeping reopen_count column"
    ]
   },
   {
@@ -1097,14 +1097,12 @@
    "id": "40a56281-553f-4642-85bc-06db28e1017b",
    "metadata": {},
    "source": [
-    "🔍 Key Insights:\n",
+    "##### **Observation: Avg Time to Resolution by Incident State**\n",
     "\n",
-    "🚨 Awaiting Vendor (2800+ hrs) and Awaiting Evidence (3200+ hrs) have the longest average resolution times by far.\n",
-    "This suggests delays when incidents rely on third parties or additional proof.\n",
-    "\n",
-    "🧍 Awaiting User Info and Awaiting Problem also show high resolution times (400–800 hrs), indicating bottlenecks when additional information or problem identification is pending.\n",
-    "\n",
-    "✅ States like Closed, New, Resolved, and Active have much lower average resolution times (mostly below 300 hrs), reflecting standard workflow steps that are resolved quicker."
+    "- **\"Awaiting Vendor\"** and **\"Awaiting Evidence\"** states have the **highest average resolution times** (500–580+ hours), suggesting significant delays when external input or third-party involvement is required.\n",
+    "- **\"Awaiting Problem\"** and **\"Awaiting User Info\"** also show elevated resolution times, reflecting dependencies on internal problem teams or users.\n",
+    "- In contrast, **\"Closed\"**, **\"Resolved\"**, and **\"New\"** states have the **lowest average times** (near or below 150 hours), indicating that these are either completed or just initiated cases.\n",
+    "- **\"Active\"** sits in the middle, reflecting ongoing handling without external blockers."
    ]
   },
   {
@@ -1123,7 +1121,7 @@
    "outputs": [
     {
      "data": {
-      "image/png": "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",
+      "image/png": "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",
       "text/plain": [
        "<Figure size 800x500 with 1 Axes>"
       ]
@@ -1146,14 +1144,12 @@
    "id": "e1c912de-c2a9-49a2-ad51-656c743ef6eb",
    "metadata": {},
    "source": [
-    "🔍 Key Insights:\n",
-    "📈 Peak resolution times are between 11 AM and 4 PM, where average resolution durations are the highest (300+ hours).\n",
-    "\n",
-    "🕔 Early hours (5–6 AM) and late hours (9 PM–3 AM) show lower average resolution times, likely due to fewer complex tickets or auto-closures.\n",
+    "##### **Observation: Avg Time to Resolution by Hour of Day**\n",
     "\n",
-    "🕘 Office hours trend: Resolution time tends to increase during active business hours when more complex tickets are likely submitted.\n",
-    "\n",
-    "📉 Shorter resolution times at night may suggest simpler issues or more efficient auto-resolution mechanisms."
+    "- Resolution times are **highest during working hours** (10:00 to 17:00), peaking around **15:00–16:00** with averages close to 200 hours.\n",
+    "- **Early morning (0:00–6:00)** and **late night (after 20:00)** hours show **significantly lower resolution times**, with the lowest around **2:00 and 21:00**.\n",
+    "- This trend may indicate that tickets created or handled during **peak business hours** tend to be more complex or take longer to resolve.\n",
+    "- Alternatively, tickets logged during **off-hours** may be simpler or resolved faster due to lower system load or automated handling."
    ]
   },
   {
@@ -1172,7 +1168,7 @@
    "outputs": [
     {
      "data": {
-      "image/png": "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",
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAxYAAAHqCAYAAACZcdjsAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjAsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvlHJYcgAAAAlwSFlzAAAPYQAAD2EBqD+naQAARaNJREFUeJzt3QmcTfUf//HPmDGDwdgaY+z7vo4MyRYRJaKS9LPkR/wtISm/X4QWoqSkXaRI2igVSZZkJ4kkpGxjX4aRscz9Pz7f///c372zmXHuzL1z7+v5eJzmnnPP3Pu959zReZ/vFuRwOBwCAAAAADbksvPLAAAAAKAIFgAAAABsI1gAAAAAsI1gAQAAAMA2ggUAAAAA2wgWAAAAAGwjWAAAAACwjWABAAAAwDaCBQAAAADbCBYAcrzevXtLuXLlvF2MgDd79mwJCgqSv/76y6Ov27JlS7N46/Ns3rw52987p9m0aZPccsstEh4ebo7Ztm3bJCfgHAOeRbAAkKrXX3/d/A83NjbWK++v752RZeXKleJrfvvtNxk3bpzHL7CtiyBrCQkJkZIlS5pgdfjwYcnJsuqY5QR6/lzPa/78+aVChQpy7733ymeffSZJSUniy65cuSL33XefnD59Wl5++WX54IMPpGzZsin227hxo/l8uk9ynTp1Ms/NmjUrxXPNmzc333MAvi/E2wUA4Jvmzp1ragH0YmDv3r1SqVKlbH1/vThxNWfOHFm2bFmK7dWrV5d33nnHpy6+9CJ5/Pjx5i57VtSkTJgwQcqXLy+XLl2S9evXm8CxZs0a2bFjh+TJk0dyovSO2XfffSf+LiwsTN59913z+J9//pG///5bvvrqKxMu9JgsWrRIChYsKL5o3759prz6d/jvf/87zf0aNGgg+fLlM9/V4cOHuz23du1aE5R/+ukn6dOnj3P75cuXTW1Ix44ds/QzAPAMggWAFPbv32/+R//555/LI488YkLG008/na1leOihh9zW9QJag0Xy7YGoffv20rBhQ/NYL+SKFSsmL7zwgnz55Zdy//33i78JDQ0Vf6cX1cm/288++6xMmjRJRo8eLf369ZOPP/5YfNHx48fNz0KFCl33M2oNqIYHV7t375aTJ0/Kgw8+aEKHqy1btpgAfeutt2ZByQF4Gk2hAKSgQaJw4cJy5513mjumuu7a7KFIkSJudxUt8fHx5o75yJEjndv0Tubdd99t2l5HRkaaO5VLly71aDOm5H0stDmNvv6LL74oM2bMMM1K9E5p27Zt5eDBg+JwOOSZZ56RUqVKSd68eU0zDG3Gkdy3334rzZo1M2UvUKCAOR47d+5Mtyxae6DNQlSrVq1SbbKlzcxq1qxp7lJHR0fLoEGD5OzZszf8+bWM1p1jV7///rs5f3q+9LxoGNHw4UrPp9YUVK5c2exTtGhRcxGnIc7VDz/84DwWegGpx2zXrl3XLZt+dm3ilJyeLz1vGTlmqfWx0IvZvn37SvHixU2569atK++//77bPq7fg7ffflsqVqxojvnNN99s7oJn1MWLF03A1mOjtQY9e/aUM2fOOJ/v1auXCXd6LJPT71zVqlXlRj355JPmNT755BP5448/nNu1BkO/j/r90c+kn02/09euXXPuozcDcufOLSdOnEjxuv379zfnUS/a03O9867nsEWLFuaxnkM93un1h9Hv1rFjx0wtqEWDhh5XLZMVMlyfs34vs3+XGfn+p0bPbaNGjcy/D1oeABlHsACQggaJLl26mDvF3bt3lz179jgvxPRC5Z577pGFCxeaZgqudFtiYqI88MADZj0hIUFuu+02+f7772Xo0KHy3//+19SEPPHEE9n2OfQifsiQIfLYY4/JqlWrzB39p556SpYsWWLKoRcz2uTENQwpbXKlFyza3l1rA8aMGWOa6+gFTnr9ALQ9uH5W9Z///Me8ji7aZEvpRbYGCb0gfOmll6Rr167y1ltvmYvH1C5MM8Iqj4ZBi15oNW7c2FwE6sWpvpdeiHXu3Fm++OIL535aHg0WekH/2muvmXNUpkwZ2bp1q3MfPX/t2rUzF/O6/4gRI8x5bNq0qUf6RFzvmCWnTYX04lX36dGjh0yZMkUiIiLMRe4rr7ySYv958+aZfTQcaC2Allm/3xk93oMHDzbHUT+7hgr9Xulx1ICq/vWvf8mpU6dMYHZ19OhRc2Fut5ZNX1/fyzXsaRjT76aeC/3MMTExMnbsWHOuXX/v6tWrKWo69O/2008/Nd+99JrOZeS86zHVc6b0HOo50e9QWqyA4FozoeFBv6tam6H/vuh7uD6n4UGDY2b+LjP6/U9OQ43+m6XhR/+9sBMKgYDkAAAXmzdv1qslx7Jly8x6UlKSo1SpUo5HH33Uuc/SpUvNPl999ZXb73bo0MFRoUIF5/pLL71k9lu4cKFz2z///OOoVq2a2b5ixYoMl2vQoEHmd1LTq1cvR9myZZ3r+/fvN/vedNNNjrNnzzq3jx492myvW7eu48qVK87t3bt3d4SGhjouXbpk1s+fP+8oVKiQo1+/fm7vc/ToUUdERESK7cl98sknqX6+48ePm/dp27at49q1a87tr732mtn/vffeS/d1Z82aZfb7/vvvHSdOnHAcPHjQ8emnn5rPGRYWZtYtrVu3dtSuXdv5maxzecsttzgqV67s3KbH4s4770z3fevVq+eIjIx0nDp1yrntl19+ceTKlcvRs2fPFOXT42/R9aeffjrFa+r50vN2vWOmWrRoYRbLtGnTzL4ffvihc9vly5cdTZo0ceTPn98RHx/v9j0oWrSo4/Tp0859Fy1alOr3Nznr88TExJjXt0yePNls19dRei71b6Rbt25uvz916lRHUFCQ488//0z3ffQ4hIeHp/n8zz//bN5v+PDhzm0XL15Msd8jjzziyJcvn9s512MSGxvrtt/nn3+eob+/jJ53fR19PT2H16PnJjg42NG3b1/ntqpVqzrGjx9vHjdq1Mjx+OOPO5/T7/btt9+e6b/LjH7/rXO8adMmR1xcnKNmzZrm37C//vrrup8FQErUWABwo3djtXmJ3sFW2rShW7duMn/+fGczC72jp00/XO+EavMBvaOq+1q0VkBHc9GmUBa9Q6rtxbODNs3QO9kWa4QrvYOs7b1dt+tdXGtkJf0c2jRJa2v0Dqa1BAcHm31XrFhxQ+XRO8D6PsOGDZNcuf73z68eD20K8vXXX2foddq0aSM33XSTlC5d2jT10Dux2sRDm24obdald8q1dub8+fPO8utddb0DrTVQ1mfV5i16d1e3pSYuLs4MHaq1AdqkxFKnTh25/fbb5ZtvvpHspu8ZFRVlzo9F73TrHfMLFy6YO82u9DvpWptjNR37888/M/R+Wqulr28ZOHCg+f5Yn13Ppdac6DnQ4+36t6RDsGpHezv07rxyfW1twmexzrF+Lm22pU2ALFrDsmHDBrdmclou/e5YTZiy87xr7YO+hlVjoeXW5kZ6nJTWhljNn7Tplzbjsmo5Mvp3mZnvv+XQoUPmeGgt1urVq1Md1QrA9REsADhpcNAAoaFCO3BrO2hd9H/a2jRg+fLlZj+9qNJmFNrOW5s+Ke3orf9Tdg0W2r9C235rOHGVXSNMaZMeV1bI0Iuq1LZb7eati2wNUHoB77roCEVWZ9XM0uOhkjev0CZn2g/Eev56tN+IXmRpc5YOHTqYiyZtZ2/Rc6aVBdpMJHn5rU741mfQEab0Yq1KlSpSu3Ztefzxx2X79u3XLbPSpkr63trkLTtpmbRPiGs4s8pjPZ/e98AKGa79JNKj75X8Qr9EiRJuTW/0Al6baFnNbPRiWTsea3MkuzQsWRflFg2D2iRRv7saSvXcWk2uzp0759xP/x71u2H1k9LnFi9ebIJQ8r9LV1l53jUoWH0ptNmTBgNttqQ0YOhx039XkvevyOjfZWa+/xY9T7pNQylD2wI3jlGhADjpXT69U6nhQpfk9OJE+wIo7UehfQO0I6W2W16wYIFUq1bN2RbaF+gFS2a2W23mraFrtT233hlPzrW2wxu0Y6k1KpQee73w0hF19GJNL3qt8mu/Eb1Dmxor3Gn/Br2brSFRL850yFOdZ+DNN99Md+hQu1w7GWe1651vT6hRo4bp5/Dhhx+akKE/NTB6YpQuHUbY9ZxpENS76xooNBhqeNeaQO0Xo/2GXIde1hB11113mb9d7YOhYVQv2r05upp+X6dPn26CgwYLDbRWrYwGCy2f9unSWg39W7NCR0b/LjPz/bdonxsd0lr7q0ycONHDnxgIHAQLAE568aEjN+kd8eS0RkLvxuoFpzbD0AtSvWurzaH0QkFDSfJOm9qcQDtW6gWc691R1xFhfJFeqCk9FtrsKLPSuhNsNa/QAKA1FBZtHqU1RDfyXnrRrBdCVudr7ahqvbY238nIa1qjfOmid8f13GpnXQ0WrmVOTpvcaJM4bYqVFr2wTT7ilX5eDbCu0rt7npyWSWtV9ALStdbCagLk6WYseqfcahqo9Bhp+bW2yJUGCu3grM9ph3HtZOzaBOtG6YW0Hh9tgqR0tCxt1qN/k3quLPodSo2WS0dz0ot1/RuvX7++GZUsPXbPe3pcO3CvW7fONH+y6KAG+t4aOnTRsuqIbpn5u8zs91/pAA8aNjR8aS2Qayd4ABlHUygAhjbj0AsVvbup7faTLzoyjrZXtoZr1As63a4jKumFj44+49oMSundQm3L7DrEow5vqRNp+TItt94Nfv7551MdOSi14TtdWRdcyS+o9SJH72K/+uqrbnfLZ86caZqo6IXojdARkrQWY9q0aeb46oWXbtMapeQX8MnLrxeorvTOsV5gWU3cNDzWq1fPDOXq+nn0LrrWcCS/uE5OLwa1zborHfo1eY1FWscsNfqeOuKSax8f/f7pXXAtf3p9B26Eltf1e/DGG2+Y99P5RFxp238NAI8++qjpv+GJWgGdx0KPs/5tWU2yrBoY1++QhjUdAS01Wk5rrhNt6pORctk97+nR8KD9TrRp5ebNm539Kyy6riPMaahxHWY2o3+Xmfn+u9KmU1rLofOG6DkGkHnUWAAwrI6nrh2tXWlzBG2jrHc8rQChP/ViTtsta3OG5MOD6lCUehddL7j0YksvVvT3rSEuM3OXOjvpxYteWGi7a50tWJt96Wc/cOCA6WCtd1j1c6VFL8j04k8v5DQwaBt3bReuFzx60aLDu95xxx3mWOvFk14Q6twKdi5EtW+EdlbXYUgHDBhgap30okzPi3YO17u42k9G7xBrR9VffvnF2YRHL8K0GY/WXOiFnjaX0SBp0aFa9eK0SZMmZu4IDaF63vXObmpzVLjSWg8tj/bJ0Tvu+r46LKte6Gb0mKXWmVovGrVjsbbH1zkxtMx6h1vDlWtfBE/Qi/bWrVubZk3W+dJjm/xvRb8jel51zgntFJ+ZoKhBRZtPKQ2H2sdB/ya1ZkZrSzTcuF54a02Izp+hHdb170jDfVpNu/TOvX6H9Turx9i103t67Jz369Hjp2VWrjUW1uf76KOPnPvdyN9lRr//qX1m/f7pkND6PWJCTiCTUhkpCkAA6tixoyNPnjyOhISENPfp3bu3I3fu3I6TJ086h28sXbq0Ga7x2WefTfV3dKhNHc40b968ZujIxx57zPHZZ5+Z31m/fn2WDjc7ZcoUt/3SGhbTdcjJ5Pu3a9fODGWpx6ZixYrmGOiQvNfzzjvvmGErdWjN5EN76vCyOuSuHsvixYs7Bg4c6Dhz5sx1XzOtclpDnmr5dLl69arZtm/fPjMsaFRUlHmvkiVLOu666y4zRK1Fz5sO8anDeOo50nI999xzbsOrKh3itmnTpmafggULmu/Lb7/9lmr5XIeb1XI98cQTjmLFipmhUPV47t27N8Vws+kds+TDzapjx445+vTpY15Xh/DVoUX1/V2l9T1Ibxjc1D7PqlWrHP3793cULlzYDGfbo0cPtyFYXS1YsMD8ju6fUXoc9HesRY9TuXLlHF27djXnynVoYstPP/3kaNy4sTkf0dHRjlGjRjmHgU5tGNmNGzea53So48zIyHnPzHCzlrfeesv8jn4nk9u6davzWOh5Ti6jf5cZ+f6n9jelx1uHoA4JCXEbKhvA9QXpfzIbRgDADr2rrDNw651DRmCBP9FO8NqhXpt/WcPa+gK9Q6+1QtpB2RMjVQFAaggWALKUNp9wHXNfm3loh0xtY6/j1AP+RPso6WzPOkCBLzX106Zt2l9C+6bcaKdrALge+lgAyFI6jKPOI6B3S7XtsrYj11FlrHH1AX+gwzNrfwht669DlvpKqNDBFXRkNu2joeGCUAEgK1FjASDLmz3p3Ag6mZjWUmhn4VGjRqUYQQrIyTRI6IhU+r3WIZm9PdeJRTu2a6dlHVFJO0t7umM7ALgiWAAAAACwjXksAAAAANhGsAAAAABgm280AvWypKQkOXLkiGl76isd7gAAAABv014TOoFudHS05MqVfp0EwULEhIrSpUt7uxgAAACATzp48KCUKlUq3X0IFiLOUTL0gBUsWNDbxQEAAAB8Qnx8vLkBn5FR5QgW/3+YQKWhgmABAAAAuMtIdwE6bwMAAACwjWABAAAAwDaCBQAAAADbCBYAAAAAbCNYAAAAALCNYAEAAADANoIFAAAAANsIFgAAAABsI1gAAAAAsI1gAQAAAMA2ggUAAAAA2wgWAAAAAGwjWAAAAACwjWABAAAAwDaCBQAAAADbQuy/BAAA8GcOh0MSEhKc6+Hh4RIUFOTVMgHwPQQLAACQLg0VnTp1cq4vWrRI8ufP79UyAfA9BAsAAYk7sAAAeBbBAkBA4g4sAACeRedtAAAAALYRLAAAAADYRrAAAAAAYBt9LAAAPoNO9QCQcxEsAAA+I5A71cc8Pkd8VdDVyxLhst5yzHxxhISKL9oypae3iwAELIIFgCzDhZJncKEEAMgJ6GMBAAAAwDaCBQAAAADbCBYAAAAAbCNYAAAAALCNztsAEGDoVO8ZdKoHAHcECwAAkC5HcG45V6e72zoAJEewAAAA6QsK8tmaIwC+g2ABICBxBxYAAD/qvL169Wrp2LGjREdHS1BQkCxcuNDted2W2jJlyhTnPuXKlUvx/KRJk7zwaQDkxDuw1qLrAAAghwaLhIQEqVu3rsyYMSPV5+Pi4tyW9957zwSHrl27uu03YcIEt/2GDBmSTZ8AAAAAgNebQrVv394saYmKinJbX7RokbRq1UoqVKjgtr1AgQIp9gUAAACQfXLMPBbHjh2Tr7/+Wvr27ZviOW36VLRoUalfv75pJnX16tV0XysxMVHi4+PdFgCA7/R9sRb6vgBAzpFjOm+///77pmaiS5cubtuHDh0qDRo0kCJFisjatWtl9OjRpjnU1KlT03ytiRMnyvjx47Oh1ACATGH0IQDIsXJMsND+FT169JA8efK4bR8xYoTzcZ06dSQ0NFQeeeQREx7CwsJSfS0NH66/pzUWpUuXzsLSAwAAAP4tRwSLH3/8UXbv3i0ff/zxdfeNjY01TaH++usvqVq1aqr7aOBIK3QAAAAA8NM+FjNnzpSYmBgzgtT1bNu2TXLlyiWRkZHZUjYAAAAAXq6xuHDhguzdu9e5vn//fhMMtL9EmTJlnM2UPvnkE3nppZdS/P66detkw4YNZqQo7X+h68OHD5eHHnpIChcunK2fBQAAAAhkXg0WmzdvNqHAYvV76NWrl8yePds8nj9/vjgcDune/X8z5Fq0OZM+P27cODPSU/ny5U2wcO0/AQAAAMDPg0XLli1NaEhP//79zZIaHQ1q/fr1WVQ6AAAAAH7VxwIAAACAbyNYAAAAALCNYAEAAADANoIFAAAAANsIFgAAAABsI1gAAAAAsI1gAQAAAMA2ggUAAAAA2wgWAAAAAGwjWAAAAACwLcT+SwBIj8PhkISEBOd6eHi4BAUFebVMAAAAnkawALKYhopOnTo51xctWiT58+f3apkAAAA8jaZQAAAAAGwjWAAAAACwjWABAAAAwDaCBQAAAADbCBYAAAAAbGNUKPiFmMfniK8KunpZIlzWW46ZL46QUPFFW6b09HYRAABADkWNBQAAAADbCBYAAAAAbCNYAAAAALCNYAEAAADANoIFAAAAANsIFgAAAABsY7hZIIs5gnPLuTrd3dYBAAD8DcECyGpBQT47bwUAAICn0BQKAAAAgG3UWPgRh8MhCQkJzvXw8HAJCgryapkAAAAQGAgWfkRDRadOnZzrixYtkvz583u1TAAAAAgMNIUCAAAAYBvBAgAAAIBtBAsAAAAAthEsAAAAANhGsAAAAABgG6NCZVLM43PEVwVdvSwRLustx8z3yYnZtkzp6e0iAAAAwMOosQAAAABgG8ECAAAAgG0ECwAAAAC2ESwAAAAA2EawAAAAAGAbwQIAAABAzg4Wq1evlo4dO0p0dLQEBQXJwoUL3Z7v3bu32e663HHHHW77nD59Wnr06CEFCxaUQoUKSd++feXChQsSiBzBueVcne7ORdcBAAAAvw8WCQkJUrduXZkxY0aa+2iQiIuLcy4fffSR2/MaKnbu3CnLli2TxYsXm7DSv39/CUhBQWbeCmvRdQAAAMDvJ8hr3769WdITFhYmUVFRqT63a9cuWbJkiWzatEkaNmxotk2fPl06dOggL774oqkJAQAAAJD1fL6PxcqVKyUyMlKqVq0qAwcOlFOnTjmfW7dunWn+ZIUK1aZNG8mVK5ds2LAhzddMTEyU+Ph4twUAAACAnwYLbQY1Z84cWb58ubzwwguyatUqU8Nx7do18/zRo0dN6HAVEhIiRYoUMc+lZeLEiRIREeFcSpcuneWfBQAAAPBnXm0KdT0PPPCA83Ht2rWlTp06UrFiRVOL0bp16xt+3dGjR8uIESOc61pjQbgAAAAA/LTGIrkKFSpIsWLFZO/evWZd+14cP37cbZ+rV6+akaLS6pdh9dvQUaRcFwAAAAABEiwOHTpk+liUKFHCrDdp0kTOnj0rW7Zsce7zww8/SFJSksTGxnqxpAAAAEBg8WpTKJ1vwqp9UPv375dt27aZPhK6jB8/Xrp27WpqH/bt2yejRo2SSpUqSbt27cz+1atXN/0w+vXrJ2+++aZcuXJFBg8ebJpQMSIUAAAAECA1Fps3b5b69eubRWm/B308duxYCQ4Olu3bt8vdd98tVapUMRPfxcTEyI8//miaMlnmzp0r1apVM30udJjZW2+9Vd5++20vfioAAAAg8Hi1xqJly5bicDjSfH7p0qXXfQ2t2Zg3b56HSwYAAADAb/tYAAAAAPBNBAsAAAAAthEsAAAAANhGsAAAAABgG8ECAAAAgG0ECwAAAAC2ESwAAAAA2EawAAAAAGAbwQIAAACAbQQLAAAAALYRLAAAAADYRrAAAAAAYBvBAgAAAIBtBAsAAAAAthEsAAAAANhGsAAAAABgG8ECAAAAgG0ECwAAAAC2ESwAAAAA2EawAAAAAGAbwQIAAACAbQQLAAAAALYRLAAAAADYRrAAAAAAYBvBAgAAAIBtBAsAAAAAthEsAAAAANhGsAAAAABgG8ECAAAAgG0ECwAAAAC2ESwAAAAA2EawAAAAAGAbwQIAAACAbQQLAAAAAN4LFnv37pWlS5fKP//8Y9YdDof90gAAAAAIjGBx6tQpadOmjVSpUkU6dOggcXFxZnvfvn3lsccey4oyAgAAAPC3YDF8+HAJCQmRAwcOSL58+Zzbu3XrJkuWLPF0+QAAAADkACGZ/YXvvvvONIEqVaqU2/bKlSvL33//7cmyAQAAAPDXGouEhAS3mgrL6dOnJSwszFPlAgAAAODPwaJZs2YyZ84c53pQUJAkJSXJ5MmTpVWrVp4uHwAAAAB/bAqlAaJ169ayefNmuXz5sowaNUp27txpaix++umnrCklAAAAAP+qsahVq5b88ccfcuutt0qnTp1M06guXbrIzz//LBUrVszUa61evVo6duwo0dHRpuZj4cKFzueuXLkiTzzxhNSuXVvCw8PNPj179pQjR464vUa5cuXM77oukyZNyuzHAgAAAJCdNRYqIiJC/vvf/4pdGkrq1q0rDz/8sAknri5evChbt26VMWPGmH3OnDkjjz76qNx9992mtsTVhAkTpF+/fs71AgUK2C4bAAAAgCwOFpcuXZLt27fL8ePHTf8KV3rhn1Ht27c3S1rhZdmyZW7bXnvtNWnUqJEZ6rZMmTJuQSIqKirTnwMAAACAl4KFzlWhTZJOnjyZ4jlthnTt2jXJKufOnTPvUahQIbft2vTpmWeeMWHjwQcfdM61kZbExESzWOLj47OszAAAAEAgyHQfiyFDhsh9991nZtzW2grXJStDhdaSaJ+L7t27S8GCBZ3bhw4dKvPnz5cVK1bII488Is8//7zpUJ6eiRMnmhoRayldunSWlRsAAAAIBJmusTh27JiMGDFCihcvLtlFO3Lff//94nA45I033nB7TstiqVOnjoSGhpqAoeEhrXk1Ro8e7fZ7WmNBuAAAAACyscbi3nvvlZUrV0p2hwqd1Vv7XLjWVqQmNjZWrl69Kn/99Vea+2jg0NdxXQAAAABkY42FdqDWplA//vijGQo2d+7cbs9r0yRPh4o9e/aYpk5Fixa97u9s27ZNcuXKJZGRkR4rBwAAAAAPB4uPPvpIvvvuO8mTJ4+pudDO1BZ9nJlgceHCBdm7d69zff/+/SYYFClSREqUKGFqR3TI2cWLF5v+G0ePHjX76fPa5GndunWyYcMGM+O3jgyl69px+6GHHpLChQtn9qMBAAAAyK5gofNXjB8/Xp588klTM2CHzkehocBi9Xvo1auXjBs3Tr788kuzXq9ePbff09qLli1bmiZN2nFb99VRnsqXL2+ChWv/CQAAAAA+GCwuX74s3bp1sx0qlIYD7ZCdlvSeUw0aNJD169fbLgcAAAAAezKdDrQ24eOPP7b5tgAAAAACusZC+zpMnjxZli5daoZ3Td55e+rUqZ4sHwAAAAB/DBa//vqr1K9f3zzesWOH23OuHbkBAAAABI5MBwvtOA0AAAAAruz3wAYAAAAQ8DJUY9GlSxeZPXu2maFaH6fn888/91TZAAAAAPhTsIiIiHD2n9DHAAAAAJDpYDFr1iyZMGGCjBw50jwGAAAAgBvqY6GzbV+4cCGjuwMAAAAIIBkOFtebBRsAAABA4MrUqFDMUwEAAADA9jwWVapUuW64OH36dGZeEgAAAECgBQvtZ8GoUAAAAABsBYsHHnhAIiMjM/MrAAAAAAJAhvtY0L8CAAAAQFoYFQoAAABA9jWFSkpKsv9uAAAAAPxSpoabBQAAAIDUECwAAAAA2EawAAAAAGAbwQIAAABA9s5jYdmzZ4+sWLFCjh8/nqJT99ixY+2XCgAAAIB/B4t33nlHBg4cKMWKFZOoqCi3+S30McECAAAACDyZDhbPPvusPPfcc/LEE09kTYkAAAAA+H+wOHPmjNx3331ZUxoAAABkePLihIQE53p4eLhbSxLA5ztva6j47rvvsqY0AAAAyBANFZ06dXIuriEDyBE1FpUqVZIxY8bI+vXrpXbt2pI7d26354cOHerJ8gEAAADwx2Dx9ttvS/78+WXVqlVmcaXVbwQLAAAAIPBkOljs378/a0oCAAAAIDAnyNNOQ7oAAAAACGw3FCzmzJlj+lfkzZvXLHXq1JEPPvjA86UDAAAA4J9NoaZOnWo6bw8ePFiaNm1qtq1Zs0YGDBggJ0+elOHDh2dFOQEAAAD4U7CYPn26vPHGG9KzZ0/ntrvvvltq1qwp48aNI1gAAAAAASjTTaHi4uLklltuSbFdt+lzAAAAAAJPrhuZx2LBggUptn/88cdSuXJlT5ULAAAAgD83hRo/frx069ZNVq9e7exj8dNPP8ny5ctTDRwAAAAA/F+mayy6du0qGzZskGLFisnChQvNoo83btwo99xzT9aUEgAAAIB/1ViomJgY+fDDDz1fGgAAAB8S8/gc8VVBVy9LhMt6yzHzxRESKr5oy5T/DfqDAA8W8fHxUrBgQefj9Fj7AQAAAAgcGQoWhQsXNiM+RUZGSqFChSQoKCjFPjoDt26/du1aVpQTAAAAQE4PFj/88IMUKVLEPF6xYkVWlwkAAACAP3bebtGihYSE/L8MUr58eWnevLnZ5rroNn0uM3RkqY4dO0p0dLSp7dCO4MlrQcaOHSslSpSQvHnzSps2bWTPnj1u+5w+fVp69OhhmmBpbUrfvn3lwoULmSoHAAAAgGweFUrDw4kTJ1Js1wv8zAaLhIQEqVu3rsyYMSPV5ydPniyvvvqqvPnmm2YkqvDwcGnXrp1cunTJuY+Gip07d8qyZctk8eLFJqz0798/sx8LAAAAQHaOCmX1pUhOawny5MmTqddq3769WdJ6n2nTpslTTz0lnTp1MtvmzJkjxYsXNzUbDzzwgOzatUuWLFkimzZtkoYNG5p9pk+fLh06dJAXX3zR1IQAAAAA8KFgMWLECPNTQ8WYMWMkX758zue0w7bWKNSrV89jBdu/f78cPXrUNH+yRERESGxsrKxbt84EC/2pzZ+sUKF0/1y5cpnypDWvRmJiolks1xvpCgAAAICHgsXPP//srEn49ddfJTT0f+Mk62Nt0jRy5EiPFUxDhdIaCle6bj2nP3WkKlfaF0Q7mlv7pGbixIlmBnEAAAAA2RwsrNGg+vTpI6+88kqOnq9i9OjRzhoYq8aidOnSXi0TAAAAEFB9LGbNmiXZISoqyvw8duyYGRXKoutWkyvd5/jx426/d/XqVdOR3Pr91ISFhZkFAAAAgJeCxW233XbdOS88QUeY0nCwfPlyZ5DQmgXtOzFw4ECz3qRJEzl79qxs2bJFYmJinO+flJRk+mIAAAAA8NFgoX0pXF25ckW2bdsmO3bskF69emXqtXQkqb1797p12NbX0j4SZcqUkWHDhsmzzz4rlStXNkFDO43rSE+dO3c2+1evXl3uuOMO6devnxmSVssyePBg07GbEaEAAIA/cwTnlnN1urutAzkqWLz88supbh83blymJ6bbvHmztGrVyrlu9XvQgDJ79mwZNWqUmetC56XQmolbb73VDC/rOqzt3LlzTZho3bq1GQ2qa9euZu4LAAAAvxYUJI6Q/w2mA+S4YJGWhx56SBo1amTmj8ioli1bmlGm0qJD206YMMEsadHajXnz5mW6vAAAAAC8OPN2WnROicxOkAcAAAAgQGssunTp4rauNQ5xcXGmWZP2gQAAAAAClcPhME35LeHh4aYVTiDIdLDQ2a9dab+GqlWrmuZKbdu29WTZAAAAgBwlISFBOnXq5FxftGiR5M+fXwKBz85jAQAAACAA+1gAAAAACFwZqrEoXLhwhtuG6azXAAAAAAJLhoLFtGnTsr4kAAAAAPw7WGR2Rm0AAAAAgeWGJsi7du2aLFy4UHbt2mXWa9asKXfffbcEBwd7unwAAAAA/DFY7N27Vzp06CCHDx82w8yqiRMnSunSpeXrr7+WihUrZkU5AQAAAPjTqFBDhw414eHgwYOydetWsxw4cEDKly9vngMAAAAQeDJdY7Fq1SpZv369FClSxLmtaNGiMmnSJGnatKmnywcAAADAH2sswsLC5Pz58ym2X7hwQUJDQz1VLgAAAAD+XGNx1113Sf/+/WXmzJnSqFEjs23Dhg0yYMAA04EbAAAAyEoxj88RXxV09bJEuKy3HDNfHCG+efN9y5Se3q2xePXVV00fiyZNmkiePHnMok2gKlWqJK+88opHCwcAAADAT2ssChUqJIsWLTKjQ1nDzVavXt0ECwAAAACB6YbmsVAaJHTROS1+/fVXOXPmjBQuXNizpQMAAACQI2S6KdSwYcNM/wqloaJFixbSoEEDM4/FypUrs6KMAAAAAPwtWHz66adSt25d8/irr76SP//8U37//XcZPny4/Pe//82KMgIAAADwt2Bx8uRJiYqKMo+/+eYbuf/++6VKlSry8MMPmyZRAAAAAAJPpoNF8eLF5bfffjPNoJYsWSK333672X7x4kUJDg7OijICAAAA8LfO23369DG1FCVKlJCgoCBp06aNcy6LatWqZUUZAQAAAPhbsBg3bpzUqlVLDh48KPfdd5+ZiVtpbcWTTz6ZFWUEAAAA4I/Dzd57773m56VLl5zbevXq5blSAQAAAPDvPhbat+KZZ56RkiVLSv78+c2oUGrMmDHOYWgBAAAABJZMB4vnnntOZs+eLZMnT5bQ0FDndm0e9e6773q6fAAAAECO4QjOLefqdHcuuh4oMh0s5syZI2+//bb06NHDbRQondtC57MAAAAAAlZQkDhCQp2LrgeKTAeLw4cPS6VKlVJsT0pKkitXrniqXAAAAAD8OVjUqFFDfvzxx1Rn5K5fv76nygUAAADAn0eFGjt2rBkBSmsutJbi888/l927d5smUosXL86aUgIAAADwrxqLTp06yVdffSXff/+9hIeHm6Cxa9cus82ahRsAAABAYLmheSyaNWsmy5YtS7F98+bN0rBhQ0+UCwAAAIA/11hcuHBB/vnnH7dt27Ztk44dO0psbKwnywYAAADA34LFwYMHpUmTJhIREWGWESNGyMWLF6Vnz54mUGizqLVr12ZtaQEAAADk7KZQjz/+uFy6dEleeeUV02Fbf+roUBoq9u3bJ6VKlcrakgIAAADI+cFi9erVJlA0btxY7r//fomKijKT5A0bNixrSwgAAADAf5pCHTt2TMqXL28eR0ZGSr58+aR9+/ZZWTYAAAAA/th5O1euXG6PQ0NDs6JMAAAAAPy1KZTD4ZAqVapIUFCQc3QonWnbNWyo06dPe76UAAAAAPwjWMyaNStrSwIAAADA/4NFr169srYkAAAAAAJngrzsVq5cOdP8KvkyaNAg83zLli1TPDdgwABvFxsAAAAIKBmusfCWTZs2ybVr15zrO3bskNtvv13uu+8+57Z+/frJhAkTnOs6YhUAAACA7OPzweKmm25yW580aZJUrFhRWrRo4RYkdF4NAAAAAN7h802hXF2+fFk+/PBDefjhh52jU6m5c+dKsWLFpFatWjJ69Gi5ePFiuq+TmJgo8fHxbgsAAAAAP66xcLVw4UI5e/as9O7d27ntwQcflLJly0p0dLRs375dnnjiCdm9e7eZJTwtEydOlPHjx2dTqQEAAAD/l+lgMWLEiFS3aw1Cnjx5pFKlStKpUycpUqSIeNrMmTPNbN8aIiz9+/d3Pq5du7aUKFFCWrduLfv27TNNplKjtRqun0NrLEqXLu3x8gIAAACBItPB4ueff5atW7eaDtVVq1Y12/744w8JDg6WatWqyeuvvy6PPfaYrFmzRmrUqOGxgv7999/y/fffp1sToWJjY83PvXv3phkswsLCzAIAAADAS30stDaiTZs2cuTIEdmyZYtZDh06ZEZq6t69uxw+fFiaN28uw4cPF0/SCfoiIyPlzjvvTHe/bdu2mZ9acwEAAADAR2sspkyZIsuWLZOCBQs6t0VERMi4ceOkbdu28uijj8rYsWPNY09JSkoywUIn6QsJ+V+RtbnTvHnzpEOHDlK0aFHTx0IDjQabOnXqeOz9AQAAAHi4xuLcuXNy/PjxFNtPnDjhHF2pUKFCZgQnT9EmUAcOHDCjQbkKDQ01z2mI0WZY2gSra9eu8tVXX3nsvQEAAABkQY2FNoXSC/yXXnpJbr75ZuckdiNHjpTOnTub9Y0bN0qVKlXEUzQ4OByOFNu1w/WqVas89j4AAAAAsilYvPXWW6a50QMPPCBXr179fy8SEmKaKb388stmXWsP3n333RssEgAAAAC/Dxb58+eXd955x4SIP//802yrUKGC2W6pV6+eZ0sJAAAAwL/6WOjM1zqztQYJ7SCti2uoAAAAABB4Mh0stBmUDvuqM15/8803Zj4LAAAAAIEt08EiLi5O5s+fb2bavv/++818EYMGDZK1a9dmTQkBAAAA+F+w0I7ad911l8ydO9cMO6t9Lf766y9p1apVmjNdAwAAAPBvme687SpfvnzSrl07OXPmjPz999+ya9cuz5UMAAAAgP/WWCjtvK01FjrjdcmSJWXatGlyzz33yM6dOz1fQgAAAAD+V2Oh81csXrzY1FZoH4sxY8ZIkyZNsqZ0AAAAAPwzWAQHB8uCBQtMEyh97GrHjh1Sq1YtT5YPAAAAgD8GC20C5er8+fPy0UcfmZm2t2zZwvCzAAAAQAC6oT4WavXq1dKrVy8z3OyLL74ot912m6xfv96zpQMAAADgfzUWR48eldmzZ8vMmTMlPj7e9LFITEyUhQsXSo0aNbKulAAAAAD8o8aiY8eOUrVqVdm+fbsZBerIkSMyffr0rC0dAAAAAP+qsfj2229l6NChMnDgQKlcuXLWlgoAAACAf9ZYrFmzxnTUjomJkdjYWHnttdfk5MmTWVs6AAAAAP4VLBo3bizvvPOOxMXFySOPPCLz58+X6OhoSUpKkmXLlpnQAQAAACAwZXpUqPDwcHn44YdNDcavv/4qjz32mEyaNEkiIyPl7rvvzppSAgAAAPDP4WaVduaePHmyHDp0yMxlAQAAACAw2QoWFp2Bu3PnzvLll1964uUAAAAABGKwAAAAABDYCBYAAAAAbCNYAAAAALCNYAEAAADANoIFAAAAANsIFgAAAABsI1gAAAAAsI1gAQAAAMA2ggUAAAAA2wgWAAAAAGwjWAAAAACwjWABAAAAwDaCBQAAAADbCBYAAAAAbCNYAAAAALCNYAEAAADANoIFAAAAANsIFgAAAABsI1gAAAAAsI1gAQAAAMA2ggUAAAAA/w4W48aNk6CgILelWrVqzucvXbokgwYNkqJFi0r+/Pmla9eucuzYMa+WGQAAAAhEPh0sVM2aNSUuLs65rFmzxvnc8OHD5auvvpJPPvlEVq1aJUeOHJEuXbp4tbwAAABAIAoRHxcSEiJRUVEptp87d05mzpwp8+bNk9tuu81smzVrllSvXl3Wr18vjRs39kJpAQAAgMDk8zUWe/bskejoaKlQoYL06NFDDhw4YLZv2bJFrly5Im3atHHuq82kypQpI+vWrfNiiQEAAIDA49M1FrGxsTJ79mypWrWqaQY1fvx4adasmezYsUOOHj0qoaGhUqhQIbffKV68uHkuPYmJiWaxxMfHZ9lnAAAAAAKBTweL9u3bOx/XqVPHBI2yZcvKggULJG/evDf8uhMnTjQhBQAAAECANIVypbUTVapUkb1795p+F5cvX5azZ8+67aOjQqXWJ8PV6NGjTR8Nazl48GAWlxwAAADwbzkqWFy4cEH27dsnJUqUkJiYGMmdO7csX77c+fzu3btNH4wmTZqk+zphYWFSsGBBtwUAAACAnzaFGjlypHTs2NE0f9KhZJ9++mkJDg6W7t27S0REhPTt21dGjBghRYoUMeFgyJAhJlQwIhQAAACQvXw6WBw6dMiEiFOnTslNN90kt956qxlKVh+rl19+WXLlymUmxtPO2O3atZPXX3/d28UGAAAAAo5PB4v58+en+3yePHlkxowZZgEAAADgPTmqjwUAAAAA30SwAAAAAGAbwQIAAACAbQQLAAAAALYRLAAAAADYRrAAAAAAYBvBAgAAAIBtBAsAAAAAthEsAAAAANhGsAAAAABgG8ECAAAAgG0ECwAAAAC2ESwAAAAA2EawAAAAAGAbwQIAAACAbQQLAAAAALYRLAAAAADYRrAAAAAAYBvBAgAAAIBtBAsAAAAAthEsAAAAANhGsAAAAABgG8ECAAAAgG0ECwAAAAC2ESwAAAAA2EawAAAAAGAbwQIAAACAbQQLAAAAALYRLAAAAADYRrAAAAAAYBvBAgAAAIBtBAsAAAAAthEsAAAAANhGsAAAAABgG8ECAAAAgG0ECwAAAAC2ESwAAAAA2EawAAAAAGAbwQIAAACAbQQLAAAAALYRLAAAAAD4d7CYOHGi3HzzzVKgQAGJjIyUzp07y+7du932admypQQFBbktAwYM8FqZAQAAgEDk08Fi1apVMmjQIFm/fr0sW7ZMrly5Im3btpWEhAS3/fr16ydxcXHOZfLkyV4rMwAAABCIQsSHLVmyxG199uzZpuZiy5Yt0rx5c+f2fPnySVRUlBdKCAAAAMDnayySO3funPlZpEgRt+1z586VYsWKSa1atWT06NFy8eJFL5UQAAAACEw+XWPhKikpSYYNGyZNmzY1AcLy4IMPStmyZSU6Olq2b98uTzzxhOmH8fnnn6f5WomJiWaxxMfHZ3n5AQAAAH+WY4KF9rXYsWOHrFmzxm17//79nY9r164tJUqUkNatW8u+ffukYsWKaXYKHz9+fJaXGQAAAAgUOaIp1ODBg2Xx4sWyYsUKKVWqVLr7xsbGmp979+5Ncx9tLqXNqqzl4MGDHi8zAAAAEEh8usbC4XDIkCFD5IsvvpCVK1dK+fLlr/s727ZtMz+15iItYWFhZgEAAAAQAMFCmz/NmzdPFi1aZOayOHr0qNkeEREhefPmNc2d9PkOHTpI0aJFTR+L4cOHmxGj6tSp4+3iAwAAAAHDp4PFG2+84ZwEz9WsWbOkd+/eEhoaKt9//71MmzbNzG1RunRp6dq1qzz11FNeKjEAAAAQmHy+KVR6NEjoJHoAAAAAvCtHdN4GAAAA4NsIFgAAAABsI1gAAAAAsI1gAQAAAMA2ggUAAAAA2wgWAAAAAGwjWAAAAACwjWABAAAAwDaCBQAAAADbCBYAAAAAbCNYAAAAALCNYAEAAADANoIFAAAAANsIFgAAAABsI1gAAAAAsI1gAQAAAMA2ggUAAAAA2wgWAAAAAGwjWAAAAACwjWABAAAAwDaCBQAAAADbCBYAAAAAbCNYAAAAALCNYAEAAADANoIFAAAAANsIFgAAAABsI1gAAAAAsI1gAQAAAMA2ggUAAAAA2wgWAAAAAGwjWAAAAACwjWABAAAAwDaCBQAAAADbCBYAAAAAbCNYAAAAALCNYAEAAADANoIFAAAAANsIFgAAAABsI1gAAAAAsI1gAQAAAMA2ggUAAAAA2/wmWMyYMUPKlSsnefLkkdjYWNm4caO3iwQAAAAEDL8IFh9//LGMGDFCnn76adm6davUrVtX2rVrJ8ePH/d20QAAAICA4BfBYurUqdKvXz/p06eP1KhRQ958803Jly+fvPfee94uGgAAABAQcnywuHz5smzZskXatGnj3JYrVy6zvm7dOq+WDQAAAAgUIZLDnTx5Uq5duybFixd3267rv//+e6q/k5iYaBbLuXPnzM/4+Pjrvt+1xH9slznQZeQ4ZxbnxTfPDefFMzgvvonz4ps4L76J85Jzz4u1j8PhuO6+QY6M7OXDjhw5IiVLlpS1a9dKkyZNnNtHjRolq1atkg0bNqT4nXHjxsn48eOzuaQAAABAznTw4EEpVaqUf9dYFCtWTIKDg+XYsWNu23U9Kioq1d8ZPXq06extSUpKktOnT0vRokUlKChIcjJNlaVLlzYnv2DBgt4uDv4/zotv4rz4Js6Lb+K8+CbOi2+K96PzonUQ58+fl+jo6Ovum+ODRWhoqMTExMjy5culc+fOzqCg64MHD071d8LCwsziqlChQuJP9Euc07/I/ojz4ps4L76J8+KbOC++ifPimwr6yXmJiIjI0H45PlgorX3o1auXNGzYUBo1aiTTpk2ThIQEM0oUAAAAgKznF8GiW7ducuLECRk7dqwcPXpU6tWrJ0uWLEnRoRsAAABA1vCLYKG02VNaTZ8CiTbx0okCkzf1gndxXnwT58U3cV58E+fFN3FefFNYgJ6XHD8qFAAAAADvy/ET5AEAAADwPoIFAAAAANsIFgAAAABsI1j4kRkzZki5cuUkT548EhsbKxs3bvR2kQLe6tWrpWPHjmZSGZ18ceHChd4uUsCbOHGi3HzzzVKgQAGJjIw089/s3r3b28WCiLzxxhtSp04d57jvTZo0kW+//dbbxYKLSZMmmX/Lhg0b5u2iBLxx48aZc+G6VKtWzdvFgogcPnxYHnroITPxct68eaV27dqyefNmCQQECz/x8ccfm/k8dASCrVu3St26daVdu3Zy/PhxbxctoOl8KnouNPTBN6xatUoGDRok69evl2XLlsmVK1ekbdu25lzBu0qVKmUuXLds2WL+J3zbbbdJp06dZOfOnd4uGkRk06ZN8tZbb5nwB99Qs2ZNiYuLcy5r1qzxdpEC3pkzZ6Rp06aSO3duc2Pkt99+k5deekkKFy4sgYBRofyE1lDoXdjXXnvNOfu4TiU/ZMgQefLJJ71dPOgfW1CQfPHFF84Z4uEbdA4crbnQwNG8eXNvFwfJFClSRKZMmSJ9+/b1dlEC2oULF6RBgwby+uuvy7PPPmvmi9LJaOHdGgutBd+2bZu3iwIXTz75pPz000/y448/SiCixsIPXL582dzha9OmjXNbrly5zPq6deu8WjbA1507d855AQvfce3aNZk/f76pSdImUfAureW788473f4/A+/bs2ePaWpboUIF6dGjhxw4cMDbRQp4X375pTRs2FDuu+8+c9Oqfv368s4770igIFj4gZMnT5r/CSefaVzXdSZyAKnTmj1tK67V1rVq1fJ2cSAiv/76q+TPn99MKjVgwABTy1ejRg1vFyugacDTJrbaPwm+1VJh9uzZsmTJEtM/af/+/dKsWTM5f/68t4sW0P78809zPipXrixLly6VgQMHytChQ+X999+XQOA3M28DwI3chd2xYwftkn1I1apVTdMOrUn69NNPpVevXqaZGuHCOw4ePCiPPvqo6Y+kA4PAd7Rv3975WPu9aNAoW7asLFiwgKaDXr5h1bBhQ3n++efNutZY6P9n3nzzTfPvmb+jxsIPFCtWTIKDg+XYsWNu23U9KirKa+UCfNngwYNl8eLFsmLFCtNpGL4hNDRUKlWqJDExMeYOuQ5+8Morr3i7WAFLm9nqICDavyIkJMQsGvReffVV81hry+EbChUqJFWqVJG9e/d6uygBrUSJEiluhFSvXj1gmqkRLPzkf8T6P+Hly5e7JWZdp20y4E7Hq9BQoU1sfvjhBylfvry3i4R06L9liYmJ3i5GwGrdurVpnqa1SNaid2O1Pb8+1pta8J0O9vv27TMXtvCepk2bphjC/I8//jC1SYGAplB+Qoea1So2/Qe/UaNGZrQO7fTYp08fbxdNAv0fete7R9oGVv9nrB2Fy5Qp49WyBXLzp3nz5smiRYvMXBZWP6SIiAgz3ji8Z/To0aZ5h/5taDtxPU8rV6407ZThHfo3krz/UXh4uBmfn35J3jVy5EgzT5JesB45csQMN69Br3v37t4uWkAbPny43HLLLaYp1P3332/mFHv77bfNEggIFn6iW7duZtjMsWPHmgslHQpQO3Ql79CN7KVj8bdq1cotACoNgdrpDtlPO9Wpli1bum2fNWuW9O7d20ulgtImNz179jTj8WvQ03bjGipuv/12bxcN8DmHDh0yIeLUqVNy0003ya233mrm59HH8J6bb77Z1IjrjZIJEyaYWnG92au1fIGAeSwAAAAA2EYfCwAAAAC2ESwAAAAA2EawAAAAAGAbwQIAAACAbQQLAAAAALYRLAAAAADYRrAAAAAAYBvBAgAAAIBtBAsAQJp0Vt/IyEj566+/vF0Un1CuXDkzi66nnDx50hxfnUUZAHI6ggUA+KjevXtLUFCQWXLnzi3FixeX22+/Xd577z1JSkrKljI899xz0qlTJ3NBbTlw4IDceeedki9fPnNR/Pjjj8vVq1eztBzWcVi/fr3b9sTERClatKh5buXKlZLTFCtWTHr27ClPP/20t4sCALYRLADAh91xxx0SFxdnagy+/fZbadWqlTz66KNy1113ZfnF/MWLF2XmzJnSt29f57Zr166ZUHH58mVZu3atvP/++zJ79mwZO3asZLXSpUvLrFmz3LZ98cUXkj9/fsnJ+vTpI3PnzpXTp097uygAYAvBAgB8WFhYmERFRUnJkiWlQYMG8p///EcWLVpkQoZe0FumTp0qtWvXlvDwcHMB/n/+z/+RCxcumOcSEhKkYMGC8umnn7q99sKFC83+58+fT/W9v/nmG/P+jRs3dm777rvv5LfffpMPP/xQ6tWrJ+3bt5dnnnlGZsyYYcJGVurVq5fMnz9f/vnnH+c2rb3R7cn9+uuvctttt0nevHlNjUb//v2dx8OqDercubO8+OKLUqJECbPPoEGD5MqVK859jh8/Lh07djSvUb58eXPxn5wnjnvNmjUlOjrahCQAyMkIFgCQw+gFc926deXzzz93bsuVK5e8+uqrsnPnTlOL8MMPP8ioUaPMc3oR+8ADD6S426/r9957rxQoUCDV9/nxxx8lJibGbdu6devMhbQ2y7K0a9dO4uPjzXunRS+etWYhrUUDyvVoWbRJ1meffeZskrV69Wr517/+5bafXtBrmQoXLiybNm2STz75RL7//nsZPHiw234rVqyQffv2mZ9WzYtrWNPwcfDgQfO8hoPXX3/dhA1XnjrujRo1MscbAHKyEG8XAACQedWqVZPt27c714cNG+Z8rBffzz77rAwYMMBcDKt///vfcsstt5hmVXqHXi+QtUZCL7jT8vfff5s76a6OHj3qFiqUta7PpUXfy7U2IDmtFciIhx9+2NRSPPTQQyYEdOjQQW666Sa3febNmyeXLl2SOXPmmIt79dprr5nahxdeeMFZXg0euj04ONgcT23itXz5cunXr5/88ccfplZo48aNcvPNN5v9tVlY9erV3d7LU8ddj/PPP/+coWMAAL6KGgsAyIEcDofpsGzRC9XWrVubJlN6J1zv4uuITtpPwrojrrUGelddaVOmsmXLSvPmzdN8D21ylCdPHo+UV9+rUqVKaS5a7ozQQKG1Jn/++acJFho0ktu1a5ep0bFChWratKnp8L57927nNj0eGios1oW/9RohISFuNTYaPgoVKuT2Xp467hqsrN8BgJyKYAEAOZBe+Gq7f6Udu7Uzd506dUwzoS1btpg+D8q134PePbea+mhzHO007BpOUhux6MyZM27btL/HsWPH3LZZ6/pcVjaFUtoXQj+rdijXWomM/l5qdKQtV3osMjPaliePu3bcTl7zAgA5DcECAHIYbcevnZO7du1q1vWCVi+IX3rpJdPRukqVKnLkyJFU7/Zr8ybtE6AdsFPr9Oyqfv36Zj9XTZo0Me/t2tdg2bJlppNyjRo10nwtbf6zbdu2NJd33303w59fayl0aFkdptW1xsGizZV++eUX09fC8tNPP5n+EFWrVs3Qe2jthI66pcfWorUdZ8+eda578rjv2LHDHG8AyMnoYwEAPkznadC+CzrMq9YMLFmyRCZOnGjulOuFtdKmRNp/Yfr06aYfgV5Ev/nmmyleS/sUdOnSxcw70bZtWylVqlS6760doEePHm1qLfR3lf6eBght8jN58mRTtqeeesqMqKQjSKVFm/94cgjeEydOmDCTmh49eph5IfQCfty4cWbfIUOGmDIn7x+SFg0g+j6PPPKIvPHGG6ZZlPancO0L4qnjrk2gNKQ8//zzmT4WAOBLqLEAAB+mQULb/mvHYL3Q1RGK9M63Djlr3a3X/gQ67Kl2TK5Vq5YZFlXDR2q0CZE200mtb0JyOvqTDnG7YMEC5zZ9z8WLF5ufWnuhd+M14EyYMEGyizYj0mZaoaGhqT6vE/ctXbrUNC/Sjtc6ApP2g9CO2pmhzZa0U3WLFi1MMNAha3VCQIunjrueyzJlykizZs0yVT4A8DVBDu0BCAAICB988IEMHz7cNNlJ68Lc1ddff23utGtTHW1KBM8fd21GNXToUHnwwQe9Vj4A8ASaQgFAANDmNjrk6aRJk0zznoyECqVDsO7Zs0cOHz5sJoCDZ4/7yZMnTW1I9+7dvVZGAPAUaiwAIABoX4PnnnvODHOqTW90JCZkPY47gEBCsAAAAABgGw1mAQAAANhGsAAAAABgG8ECAAAAgG0ECwAAAAC2ESwAAAAA2EawAAAAAGAbwQIAAACAbQQLAAAAALYRLAAAAACIXf8XLlleVU+jKRkAAAAASUVORK5CYII=",
       "text/plain": [
        "<Figure size 800x500 with 1 Axes>"
       ]
@@ -1195,18 +1191,12 @@
    "id": "57133d6b-adb1-4a71-8e88-6687e4e043ca",
    "metadata": {},
    "source": [
-    "🔍 Key Insights:\n",
-    "🏢 Weekdays (Monday to Friday / Day 0–4) show significantly higher average resolution times, peaking around Tuesday and Friday (~300+ hours).\n",
-    "\n",
-    "📉 Weekends (Saturday = 5, Sunday = 6) show the lowest resolution times, often around or below 110 hours.\n",
-    "\n",
-    "This could reflect:\n",
     "\n",
-    "Fewer tickets opened on weekends (faster to resolve or auto-closed).\n",
+    "##### **Observation: Avg Time to Resolution by Day of Week**\n",
     "\n",
-    "Less complex issues logged outside business days.\n",
-    "\n",
-    "Lower system or team load."
+    "- Average resolution time is **highest on midweek days** (Tuesday to Friday), peaking around **Day 4 (Thursday)** with values close to **185 hours**.\n",
+    "- **Monday (Day 0)** and **Tuesday (Day 1)** show slightly lower resolution times, though still relatively high.\n",
+    "- A noticeable **drop occurs over the weekend**, with **Saturday (Day 5)** and especially **Sunday (Day 6)** showing the **lowest resolution times** — near or below 100 hours."
    ]
   },
   {
@@ -1299,11 +1289,21 @@
    "id": "e5916c91-40c1-44b5-ad16-670bd6394525",
    "metadata": {},
    "source": [
-    "1. System metadata: sys_created_by, sys_created_at, sys_updated_by, sys_updated_at – not useful for prediction.\n",
+    "1. **System metadata**: sys_created_by, sys_created_at, sys_updated_by, sys_updated_at – not useful for prediction.\n",
+    "\n",
+    "   -sys_created_at and sys_updated_at refer to when the record was inserted/modified in the system, not when the actual incident occurred or was resolved.\n",
+    "\n",
+    "   -These values are technical/logging artifacts that don’t reflect incident complexity, resolution time, or behavior.\n",
+    "\n",
+    "   -Including them can introduce noise or data leakage without improving predictive performance.\n",
+    "\n",
+    "3. **High missing values**: cmdb_ci, problem_id, rfc, vendor, caused_by – over 95% missing or \"Unknown\".\n",
+    "\n",
+    "4. Outcome-related: active, made_sla – could leak target info\n",
     "\n",
-    "2. High missing values: cmdb_ci, problem_id, rfc, vendor, caused_by – over 95% missing or \"Unknown\".\n",
+    "   -These values are often set after the ticket is resolved, meaning they depend on or reflect the target (time_to_resolution).\n",
     "\n",
-    "3. Outcome-related: active, made_sla – could leak target info"
+    "    -Including them would create data leakage, where the model uses future or derived info to make predictions — leading to overfitting and misleading evaluation results."
    ]
   },
   {
@@ -2975,17 +2975,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 45,
+   "execution_count": 44,
    "id": "5a8cef41-a520-4778-af96-79f95eb7235a",
    "metadata": {},
    "outputs": [],
    "source": [
-    "df.drop(columns=[\"time_bin\"], inplace=True)  "
+    "df.drop(columns=[\"time_bin\" , \"reassignment_count_log\", \"sys_mod_count_log\"], inplace=True)  "
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 46,
+   "execution_count": 45,
    "id": "1a70d5ca-9a2b-47a1-98cc-f09e467b8c85",
    "metadata": {},
    "outputs": [
@@ -2995,42 +2995,40 @@
      "text": [
       "<class 'pandas.core.frame.DataFrame'>\n",
       "Index: 138566 entries, 0 to 141711\n",
-      "Data columns (total 31 columns):\n",
+      "Data columns (total 29 columns):\n",
       " #   Column                             Non-Null Count   Dtype  \n",
       "---  ------                             --------------   -----  \n",
       " 0   reassignment_count                 138566 non-null  int64  \n",
       " 1   reopen_count                       138566 non-null  int64  \n",
       " 2   sys_mod_count                      138566 non-null  float64\n",
       " 3   priority                           138566 non-null  int8   \n",
-      " 4   reassignment_count_log             138566 non-null  float64\n",
-      " 5   sys_mod_count_log                  138566 non-null  float64\n",
-      " 6   time_to_resolution_log             138566 non-null  float64\n",
-      " 7   opened_hour                        138566 non-null  int32  \n",
-      " 8   opened_dayofweek                   138566 non-null  int32  \n",
-      " 9   opened_month                       138566 non-null  int32  \n",
-      " 10  opened_weekend                     138566 non-null  int64  \n",
-      " 11  caller_avg_resolution              138566 non-null  float64\n",
-      " 12  opened_by_avg_resolution           138566 non-null  float64\n",
-      " 13  resolved_by_avg_resolution         138566 non-null  float64\n",
-      " 14  symptom_avg_resolution             138566 non-null  float64\n",
-      " 15  closed_code_avg_resolution         138566 non-null  float64\n",
-      " 16  location_avg_resolution            138566 non-null  float64\n",
-      " 17  category_avg_resolution            138566 non-null  float64\n",
-      " 18  subcategory_avg_resolution         138566 non-null  float64\n",
-      " 19  assignment_group_avg_resolution    138566 non-null  float64\n",
-      " 20  incident_state_Awaiting Evidence   138566 non-null  int64  \n",
-      " 21  incident_state_Awaiting Problem    138566 non-null  int64  \n",
-      " 22  incident_state_Awaiting User Info  138566 non-null  int64  \n",
-      " 23  incident_state_Awaiting Vendor     138566 non-null  int64  \n",
-      " 24  incident_state_Closed              138566 non-null  int64  \n",
-      " 25  incident_state_New                 138566 non-null  int64  \n",
-      " 26  incident_state_Resolved            138566 non-null  int64  \n",
-      " 27  contact_type_Email                 138566 non-null  int64  \n",
-      " 28  contact_type_Phone                 138566 non-null  int64  \n",
-      " 29  contact_type_Self service          138566 non-null  int64  \n",
-      " 30  notify_Send Email                  138566 non-null  int64  \n",
-      "dtypes: float64(13), int32(3), int64(14), int8(1)\n",
-      "memory usage: 31.3 MB\n"
+      " 4   time_to_resolution_log             138566 non-null  float64\n",
+      " 5   opened_hour                        138566 non-null  int32  \n",
+      " 6   opened_dayofweek                   138566 non-null  int32  \n",
+      " 7   opened_month                       138566 non-null  int32  \n",
+      " 8   opened_weekend                     138566 non-null  int64  \n",
+      " 9   caller_avg_resolution              138566 non-null  float64\n",
+      " 10  opened_by_avg_resolution           138566 non-null  float64\n",
+      " 11  resolved_by_avg_resolution         138566 non-null  float64\n",
+      " 12  symptom_avg_resolution             138566 non-null  float64\n",
+      " 13  closed_code_avg_resolution         138566 non-null  float64\n",
+      " 14  location_avg_resolution            138566 non-null  float64\n",
+      " 15  category_avg_resolution            138566 non-null  float64\n",
+      " 16  subcategory_avg_resolution         138566 non-null  float64\n",
+      " 17  assignment_group_avg_resolution    138566 non-null  float64\n",
+      " 18  incident_state_Awaiting Evidence   138566 non-null  int64  \n",
+      " 19  incident_state_Awaiting Problem    138566 non-null  int64  \n",
+      " 20  incident_state_Awaiting User Info  138566 non-null  int64  \n",
+      " 21  incident_state_Awaiting Vendor     138566 non-null  int64  \n",
+      " 22  incident_state_Closed              138566 non-null  int64  \n",
+      " 23  incident_state_New                 138566 non-null  int64  \n",
+      " 24  incident_state_Resolved            138566 non-null  int64  \n",
+      " 25  contact_type_Email                 138566 non-null  int64  \n",
+      " 26  contact_type_Phone                 138566 non-null  int64  \n",
+      " 27  contact_type_Self service          138566 non-null  int64  \n",
+      " 28  notify_Send Email                  138566 non-null  int64  \n",
+      "dtypes: float64(11), int32(3), int64(14), int8(1)\n",
+      "memory usage: 29.2 MB\n"
      ]
     }
    ],
@@ -3038,31 +3036,61 @@
     "df.info()"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 46,
+   "id": "f140e55f-87a4-4c31-be9c-98932127cd8b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.to_csv(\"preprocessed_data.csv\", index=False)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "aa126145-5cb5-4a70-848a-5270002928be",
    "metadata": {},
    "source": [
-    "#### Pre-processing Takeaways\n",
-    "1. Outliers were handled using IQR-based capping to reduce skew without removing valuable data.\n",
+    "### Pre-processing Takeaways\n",
     "\n",
-    "2. Log transformation was applied to time_to_resolution to normalize their distributions.\n",
+    "1. **Datetime Conversion & Feature Creation**  \n",
+    "   - Datetime columns like `opened_at` and `resolved_at` were parsed correctly.  \n",
+    "   - A new feature, `time_to_resolution`, was created by calculating the duration (in hours) between `opened_at` and `resolved_at`.\n",
     "\n",
-    "3. Datetime parsing was done early to extract useful temporal features.\n",
+    "2. **Outlier Detection and Treatment**  \n",
+    "   - Outliers in numerical features (`time_to_resolution`, `sys_mod_count`, and `reassignment_count`) were detected using the IQR method.  \n",
+    "   - **Capping** was applied to limit extreme values instead of removing them, preserving all data.  \n",
+    "   - The `reopen_count` feature was **excluded from capping** as high values were meaningful (e.g., repeated unresolved issues).\n",
     "\n",
-    "4. Missing values were detected and imputed to ensure data completeness.\n",
+    "3. **Log Transformation**  \n",
+    "   - **Only `time_to_resolution`** was log-transformed using `np.log1p()` to normalize its skewed distribution.  \n",
+    "   - This helps improve regression performance by stabilizing variance and compressing long tails.  \n",
+    "   - The log-transformed column `time_to_resolution_log` was used for modeling and encoding.\n",
     "\n",
-    "5. Target encoding used the log-transformed target for consistency with modeling.\n",
+    "4. **Missing Value Handling**  \n",
+    "   - Missing values were detected and filled based on the type of feature (mean/mode or group-based filling).  \n",
+    "   - This ensured consistency and avoided dropping potentially valuable rows.\n",
     "\n",
-    "6. Highly correlated features (r > 0.70) were dropped to reduce redundancy and multicollinearity.\n",
+    "5. **Target Encoding (Mean Encoding)**  \n",
+    "   - Categorical features with high cardinality were encoded using the **mean of the log-transformed target** (`time_to_resolution_log`).  \n",
+    "   - A global average fallback was used for unseen categories during inference.\n",
     "\n",
-    "7. Chi-Square tests confirmed strong associations between categorical features and resolution time using binned time_to_resolution values.\n",
+    "6. **Correlation Analysis & Feature Reduction**  \n",
+    "   - Correlation heatmaps were used to identify feature pairs with **correlation > 0.70**.  \n",
+    "   - From each highly correlated pair, one feature was dropped to reduce multicollinearity and redundancy.\n",
     "\n",
-    "8. One-hot encoding was used for nominal categorical variables with few unique values.\n",
+    "7. **Categorical Relevance Analysis (Chi-Square Test)**  \n",
+    "   - The `time_to_resolution` column was binned into `Low`, `Medium`, and `High`.  \n",
+    "   - Chi-Square tests were run between these bins and categorical features like `incident_state`, `contact_type`, and `notify`, all showing strong statistical significance (p < 0.001).\n",
     "\n",
-    "9. Label encoding was applied where ordinal relationships existed or for use in tree-based models.\n",
+    "8. **Categorical Encoding**  \n",
+    "   - **One-hot encoding** was used for nominal features with low cardinality.  \n",
+    "   - **Label encoding** was applied to ordinal features or when used with tree-based models.  \n",
+    "   - **Boolean encoding** was applied to binary variables (e.g., `notify`) to convert them into 0/1 form.\n",
     "\n",
-    "10. Boolean encoding was used for binary features like notify to simplify categorical representation.\n",
+    "9. **Final Cleanup**  \n",
+    "   - Dropped redundant columns, including original versions of features that had been encoded or log-transformed.  \n",
+    "   - The cleaned dataset is now ready for model training with well-prepared numerical and categorical features.\n",
     "\n"
    ]
   }