From 065de3f66f744b3574561a6626a871046970a06a Mon Sep 17 00:00:00 2001 From: s487179 Date: Sat, 25 Mar 2023 12:47:22 +0100 Subject: [PATCH] edit notebook --- Zadanie_LAB02.ipynb | 330 +++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 310 insertions(+), 20 deletions(-) diff --git a/Zadanie_LAB02.ipynb b/Zadanie_LAB02.ipynb index 04a25a9..8ce5392 100644 --- a/Zadanie_LAB02.ipynb +++ b/Zadanie_LAB02.ipynb @@ -75,7 +75,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 30, "metadata": {}, "outputs": [ { @@ -123,7 +123,7 @@ "[614 rows x 13 columns]>" ] }, - "execution_count": 7, + "execution_count": 30, "metadata": {}, "output_type": "execute_result" } @@ -137,7 +137,7 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": 31, "metadata": {}, "outputs": [ { @@ -398,7 +398,7 @@ "max 1.000000 NaN NaN " ] }, - "execution_count": 9, + "execution_count": 31, "metadata": {}, "output_type": "execute_result" } @@ -409,7 +409,7 @@ }, { "cell_type": "code", - "execution_count": 12, + "execution_count": 32, "metadata": {}, "outputs": [ { @@ -420,7 +420,7 @@ "Name: Loan_Status, dtype: int64" ] }, - "execution_count": 12, + "execution_count": 32, "metadata": {}, "output_type": "execute_result" } @@ -431,7 +431,7 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": 33, "metadata": {}, "outputs": [ { @@ -440,13 +440,13 @@ "" ] }, - "execution_count": 13, + "execution_count": 33, "metadata": {}, "output_type": "execute_result" }, { "data": { - "image/png": "iVBORw0KGgoAAAANSUhEUgAAAigAAAGZCAYAAACjc8rIAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/bCgiHAAAACXBIWXMAAA9hAAAPYQGoP6dpAAAhu0lEQVR4nO3df2xV9f3H8de1pddSe+9oC/f2hit2sRr1FrcUAzQqBUqhkR8KCWwYhYwZHdCsow1a+MO6Hy3yjYCjGZmGWH7Iyh9adQGRMqSuachKHbNlm8EMtA29drJyb4vNLdbz/WPxZJcCeqFwPy3PR3IS7zmfe+/7JOv65NwfdViWZQkAAMAgt8R7AAAAgIsRKAAAwDgECgAAMA6BAgAAjEOgAAAA4xAoAADAOAQKAAAwTmK8B7gaX3/9tc6cOaPU1FQ5HI54jwMAAL4Dy7LU09Mjn8+nW2658jWSYRkoZ86ckd/vj/cYAADgKrS3t2v8+PFXXDMsAyU1NVXSf0/Q5XLFeRoAAPBdhMNh+f1++/f4lQzLQPnmZR2Xy0WgAAAwzHyXt2fwJlkAAGAcAgUAABiHQAEAAMYhUAAAgHEIFAAAYBwCBQAAGIdAAQAAxiFQAACAcQgUAABgHAIFAAAYh0ABAADGIVAAAIBxCBQAAGAcAgUAABiHQAEAAMZJjPcAiM0dz+2L9wi4gU5veCTeIwBAXHAFBQAAGIdAAQAAxiFQAACAcQgUAABgHAIFAAAYh0ABAADGIVAAAIBxCBQAAGAcAgUAABiHQAEAAMYhUAAAgHEIFAAAYBwCBQAAGOeaAqWqqkoOh0MlJSX2PsuyVFFRIZ/Pp+TkZOXn5+vEiRNR94tEIiouLlZGRoZSUlI0f/58dXR0XMsoAABgBLnqQGlubtYrr7yiiRMnRu3fuHGjNm3apOrqajU3N8vr9WrWrFnq6emx15SUlKiurk61tbVqbGxUb2+v5s6dq4GBgas/EwAAMGJcVaD09vbq8ccf16uvvqoxY8bY+y3L0pYtW7R+/XotXLhQgUBAO3bs0Jdffqk9e/ZIkkKhkLZv366XXnpJBQUF+uEPf6jdu3ertbVVhw4dGpqzAgAAw9pVBcqqVav0yCOPqKCgIGr/qVOnFAwGVVhYaO9zOp2aNm2ampqaJEktLS26cOFC1Bqfz6dAIGCvuVgkElE4HI7aAADAyJUY6x1qa2v14Ycfqrm5edCxYDAoSfJ4PFH7PR6PPv30U3tNUlJS1JWXb9Z8c/+LVVVV6YUXXoh1VAAAMEzFdAWlvb1dP//5z7V7927deuutl13ncDiibluWNWjfxa60pry8XKFQyN7a29tjGRsAAAwzMQVKS0uLurq6lJubq8TERCUmJqqhoUG//e1vlZiYaF85ufhKSFdXl33M6/Wqv79f3d3dl11zMafTKZfLFbUBAICRK6ZAmTlzplpbW3X8+HF7mzRpkh5//HEdP35c3//+9+X1elVfX2/fp7+/Xw0NDcrLy5Mk5ebmatSoUVFrOjs71dbWZq8BAAA3t5jeg5KamqpAIBC1LyUlRenp6fb+kpISVVZWKjs7W9nZ2aqsrNTo0aO1dOlSSZLb7daKFStUWlqq9PR0paWlqaysTDk5OYPedAsAAG5OMb9J9tusXbtWfX19Wrlypbq7uzV58mQdPHhQqamp9prNmzcrMTFRixcvVl9fn2bOnKmamholJCQM9TgAAGAYcliWZcV7iFiFw2G53W6FQqGb7v0odzy3L94j4AY6veGReI8AAEMmlt/f/C0eAABgHAIFAAAYh0ABAADGIVAAAIBxCBQAAGAcAgUAABiHQAEAAMYhUAAAgHEIFAAAYBwCBQAAGIdAAQAAxiFQAACAcQgUAABgHAIFAAAYh0ABAADGIVAAAIBxCBQAAGAcAgUAABiHQAEAAMYhUAAAgHEIFAAAYBwCBQAAGIdAAQAAxiFQAACAcQgUAABgHAIFAAAYh0ABAADGIVAAAIBxCBQAAGAcAgUAABiHQAEAAMaJKVC2bdumiRMnyuVyyeVyaerUqXr33Xft48uXL5fD4YjapkyZEvUYkUhExcXFysjIUEpKiubPn6+Ojo6hORsAADAixBQo48eP14YNG3Ts2DEdO3ZMM2bM0IIFC3TixAl7zZw5c9TZ2Wlv+/fvj3qMkpIS1dXVqba2Vo2Njert7dXcuXM1MDAwNGcEAACGvcRYFs+bNy/q9m9+8xtt27ZNR48e1X333SdJcjqd8nq9l7x/KBTS9u3btWvXLhUUFEiSdu/eLb/fr0OHDmn27NlXcw4AAGCEuer3oAwMDKi2tlbnz5/X1KlT7f1HjhzRuHHjdNddd+mpp55SV1eXfaylpUUXLlxQYWGhvc/n8ykQCKipqemyzxWJRBQOh6M2AAAwcsUcKK2trbrtttvkdDr1zDPPqK6uTvfee68kqaioSK+//roOHz6sl156Sc3NzZoxY4YikYgkKRgMKikpSWPGjIl6TI/Ho2AweNnnrKqqktvttje/3x/r2AAAYBiJ6SUeSbr77rt1/PhxnTt3Tm+88YaWLVumhoYG3XvvvVqyZIm9LhAIaNKkSZowYYL27dunhQsXXvYxLcuSw+G47PHy8nKtWbPGvh0Oh4kUAABGsJgDJSkpSXfeeackadKkSWpubtbLL7+s3//+94PWZmZmasKECTp58qQkyev1qr+/X93d3VFXUbq6upSXl3fZ53Q6nXI6nbGOCgAAhqlr/h4Uy7Lsl3AudvbsWbW3tyszM1OSlJubq1GjRqm+vt5e09nZqba2tisGCgAAuLnEdAVl3bp1Kioqkt/vV09Pj2pra3XkyBEdOHBAvb29qqio0KJFi5SZmanTp09r3bp1ysjI0GOPPSZJcrvdWrFihUpLS5Wenq60tDSVlZUpJyfH/lQPAABATIHy+eef64knnlBnZ6fcbrcmTpyoAwcOaNasWerr61Nra6t27typc+fOKTMzU9OnT9fevXuVmppqP8bmzZuVmJioxYsXq6+vTzNnzlRNTY0SEhKG/OQAAMDw5LAsy4r3ELEKh8Nyu90KhUJyuVzxHueGuuO5ffEeATfQ6Q2PxHsEABgysfz+5m/xAAAA4xAoAADAOAQKAAAwDoECAACMQ6AAAADjECgAAMA4BAoAADAOgQIAAIxDoAAAAOMQKAAAwDgECgAAMA6BAgAAjEOgAAAA4xAoAADAOAQKAAAwDoECAACMQ6AAAADjECgAAMA4BAoAADAOgQIAAIxDoAAAAOMQKAAAwDgECgAAMA6BAgAAjEOgAAAA4xAoAADAOAQKAAAwDoECAACMQ6AAAADjECgAAMA4BAoAADBOTIGybds2TZw4US6XSy6XS1OnTtW7775rH7csSxUVFfL5fEpOTlZ+fr5OnDgR9RiRSETFxcXKyMhQSkqK5s+fr46OjqE5GwAAMCLEFCjjx4/Xhg0bdOzYMR07dkwzZszQggUL7AjZuHGjNm3apOrqajU3N8vr9WrWrFnq6emxH6OkpER1dXWqra1VY2Ojent7NXfuXA0MDAztmQEAgGHLYVmWdS0PkJaWpv/7v//TT37yE/l8PpWUlOjZZ5+V9N+rJR6PRy+++KKefvpphUIhjR07Vrt27dKSJUskSWfOnJHf79f+/fs1e/bs7/Sc4XBYbrdboVBILpfrWsYfdu54bl+8R8ANdHrDI/EeAQCGTCy/v6/6PSgDAwOqra3V+fPnNXXqVJ06dUrBYFCFhYX2GqfTqWnTpqmpqUmS1NLSogsXLkSt8fl8CgQC9ppLiUQiCofDURsAABi5Yg6U1tZW3XbbbXI6nXrmmWdUV1ene++9V8FgUJLk8Xii1ns8HvtYMBhUUlKSxowZc9k1l1JVVSW3221vfr8/1rEBAMAwEnOg3H333Tp+/LiOHj2qn/3sZ1q2bJn+/ve/28cdDkfUesuyBu272LetKS8vVygUsrf29vZYxwYAAMNIzIGSlJSkO++8U5MmTVJVVZXuv/9+vfzyy/J6vZI06EpIV1eXfVXF6/Wqv79f3d3dl11zKU6n0/7k0DcbAAAYua75e1Asy1IkElFWVpa8Xq/q6+vtY/39/WpoaFBeXp4kKTc3V6NGjYpa09nZqba2NnsNAABAYiyL161bp6KiIvn9fvX09Ki2tlZHjhzRgQMH5HA4VFJSosrKSmVnZys7O1uVlZUaPXq0li5dKklyu91asWKFSktLlZ6errS0NJWVlSknJ0cFBQXX5QQBAMDwE1OgfP7553riiSfU2dkpt9utiRMn6sCBA5o1a5Ykae3aterr69PKlSvV3d2tyZMn6+DBg0pNTbUfY/PmzUpMTNTixYvV19enmTNnqqamRgkJCUN7ZgAAYNi65u9BiQe+BwU3C74HBcBIckO+BwUAAOB6IVAAAIBxCBQAAGAcAgUAABiHQAEAAMYhUAAAgHEIFAAAYBwCBQAAGIdAAQAAxiFQAACAcQgUAABgHAIFAAAYh0ABAADGIVAAAIBxCBQAAGAcAgUAABiHQAEAAMYhUAAAgHEIFAAAYBwCBQAAGIdAAQAAxiFQAACAcQgUAABgHAIFAAAYh0ABAADGIVAAAIBxCBQAAGAcAgUAABiHQAEAAMYhUAAAgHEIFAAAYJyYAqWqqkoPPPCAUlNTNW7cOD366KP6+OOPo9YsX75cDocjapsyZUrUmkgkouLiYmVkZCglJUXz589XR0fHtZ8NAAAYEWIKlIaGBq1atUpHjx5VfX29vvrqKxUWFur8+fNR6+bMmaPOzk57279/f9TxkpIS1dXVqba2Vo2Njert7dXcuXM1MDBw7WcEAACGvcRYFh84cCDq9muvvaZx48appaVFDz/8sL3f6XTK6/Ve8jFCoZC2b9+uXbt2qaCgQJK0e/du+f1+HTp0SLNnzx50n0gkokgkYt8Oh8OxjA0AAIaZa3oPSigUkiSlpaVF7T9y5IjGjRunu+66S0899ZS6urrsYy0tLbpw4YIKCwvtfT6fT4FAQE1NTZd8nqqqKrndbnvz+/3XMjYAADDcVQeKZVlas2aNHnzwQQUCAXt/UVGRXn/9dR0+fFgvvfSSmpubNWPGDPsKSDAYVFJSksaMGRP1eB6PR8Fg8JLPVV5erlAoZG/t7e1XOzYAABgGYnqJ53+tXr1aH330kRobG6P2L1myxP7vQCCgSZMmacKECdq3b58WLlx42cezLEsOh+OSx5xOp5xO59WOCgAAhpmruoJSXFysd955R++//77Gjx9/xbWZmZmaMGGCTp48KUnyer3q7+9Xd3d31Lquri55PJ6rGQcAAIwwMQWKZVlavXq13nzzTR0+fFhZWVnfep+zZ8+qvb1dmZmZkqTc3FyNGjVK9fX19prOzk61tbUpLy8vxvEBAMBIFNNLPKtWrdKePXv09ttvKzU11X7PiNvtVnJysnp7e1VRUaFFixYpMzNTp0+f1rp165SRkaHHHnvMXrtixQqVlpYqPT1daWlpKisrU05Ojv2pHgAAcHOLKVC2bdsmScrPz4/a/9prr2n58uVKSEhQa2urdu7cqXPnzikzM1PTp0/X3r17lZqaaq/fvHmzEhMTtXjxYvX19WnmzJmqqalRQkLCtZ8RAAAY9hyWZVnxHiJW4XBYbrdboVBILpcr3uPcUHc8ty/eI+AGOr3hkXiPAABDJpbf3/wtHgAAYBwCBQAAGIdAAQAAxiFQAACAcQgUAABgHAIFAAAYh0ABAADGIVAAAIBxCBQAAGAcAgUAABiHQAEAAMYhUAAAgHEIFAAAYBwCBQAAGIdAAQAAxiFQAACAcQgUAABgHAIFAAAYh0ABAADGIVAAAIBxCBQAAGAcAgUAABiHQAEAAMYhUAAAgHEIFAAAYBwCBQAAGIdAAQAAxiFQAACAcQgUAABgHAIFAAAYJ6ZAqaqq0gMPPKDU1FSNGzdOjz76qD7++OOoNZZlqaKiQj6fT8nJycrPz9eJEyei1kQiERUXFysjI0MpKSmaP3++Ojo6rv1sAADAiBBToDQ0NGjVqlU6evSo6uvr9dVXX6mwsFDnz5+312zcuFGbNm1SdXW1mpub5fV6NWvWLPX09NhrSkpKVFdXp9raWjU2Nqq3t1dz587VwMDA0J0ZAAAYthyWZVlXe+d///vfGjdunBoaGvTwww/Lsiz5fD6VlJTo2WeflfTfqyUej0cvvviinn76aYVCIY0dO1a7du3SkiVLJElnzpyR3+/X/v37NXv27G993nA4LLfbrVAoJJfLdbXjD0t3PLcv3iPgBjq94ZF4jwAAQyaW39/X9B6UUCgkSUpLS5MknTp1SsFgUIWFhfYap9OpadOmqampSZLU0tKiCxcuRK3x+XwKBAL2motFIhGFw+GoDQAAjFxXHSiWZWnNmjV68MEHFQgEJEnBYFCS5PF4otZ6PB77WDAYVFJSksaMGXPZNRerqqqS2+22N7/ff7VjAwCAYeCqA2X16tX66KOP9Ic//GHQMYfDEXXbsqxB+y52pTXl5eUKhUL21t7efrVjAwCAYeCqAqW4uFjvvPOO3n//fY0fP97e7/V6JWnQlZCuri77qorX61V/f7+6u7svu+ZiTqdTLpcragMAACNXTIFiWZZWr16tN998U4cPH1ZWVlbU8aysLHm9XtXX19v7+vv71dDQoLy8PElSbm6uRo0aFbWms7NTbW1t9hoAAHBzS4xl8apVq7Rnzx69/fbbSk1Nta+UuN1uJScny+FwqKSkRJWVlcrOzlZ2drYqKys1evRoLV261F67YsUKlZaWKj09XWlpaSorK1NOTo4KCgqG/gwBAMCwE1OgbNu2TZKUn58ftf+1117T8uXLJUlr165VX1+fVq5cqe7ubk2ePFkHDx5UamqqvX7z5s1KTEzU4sWL1dfXp5kzZ6qmpkYJCQnXdjYAAGBEuKbvQYkXvgcFNwu+BwXASBLL7++YrqAAAK4f/gFyc+EfIFfGHwsEAADGIVAAAIBxCBQAAGAcAgUAABiHQAEAAMYhUAAAgHEIFAAAYBwCBQAAGIdAAQAAxiFQAACAcQgUAABgHAIFAAAYh0ABAADGIVAAAIBxCBQAAGAcAgUAABiHQAEAAMYhUAAAgHEIFAAAYBwCBQAAGIdAAQAAxiFQAACAcQgUAABgHAIFAAAYh0ABAADGIVAAAIBxCBQAAGAcAgUAABiHQAEAAMYhUAAAgHFiDpQPPvhA8+bNk8/nk8Ph0FtvvRV1fPny5XI4HFHblClTotZEIhEVFxcrIyNDKSkpmj9/vjo6Oq7pRAAAwMgRc6CcP39e999/v6qrqy+7Zs6cOers7LS3/fv3Rx0vKSlRXV2damtr1djYqN7eXs2dO1cDAwOxnwEAABhxEmO9Q1FRkYqKiq64xul0yuv1XvJYKBTS9u3btWvXLhUUFEiSdu/eLb/fr0OHDmn27NmxjgQAAEaY6/IelCNHjmjcuHG666679NRTT6mrq8s+1tLSogsXLqiwsNDe5/P5FAgE1NTUdMnHi0QiCofDURsAABi5hjxQioqK9Prrr+vw4cN66aWX1NzcrBkzZigSiUiSgsGgkpKSNGbMmKj7eTweBYPBSz5mVVWV3G63vfn9/qEeGwAAGCTml3i+zZIlS+z/DgQCmjRpkiZMmKB9+/Zp4cKFl72fZVlyOByXPFZeXq41a9bYt8PhMJECAMAIdt0/ZpyZmakJEybo5MmTkiSv16v+/n51d3dHrevq6pLH47nkYzidTrlcrqgNAACMXNc9UM6ePav29nZlZmZKknJzczVq1CjV19fbazo7O9XW1qa8vLzrPQ4AABgGYn6Jp7e3V5988ol9+9SpUzp+/LjS0tKUlpamiooKLVq0SJmZmTp9+rTWrVunjIwMPfbYY5Ikt9utFStWqLS0VOnp6UpLS1NZWZlycnLsT/UAAICbW8yBcuzYMU2fPt2+/c17Q5YtW6Zt27aptbVVO3fu1Llz55SZmanp06dr7969Sk1Nte+zefNmJSYmavHixerr69PMmTNVU1OjhISEITglAAAw3MUcKPn5+bIs67LH33vvvW99jFtvvVVbt27V1q1bY316AABwE+Bv8QAAAOMQKAAAwDgECgAAMA6BAgAAjEOgAAAA4xAoAADAOAQKAAAwDoECAACMQ6AAAADjECgAAMA4BAoAADAOgQIAAIxDoAAAAOMQKAAAwDgECgAAMA6BAgAAjEOgAAAA4xAoAADAOAQKAAAwDoECAACMQ6AAAADjECgAAMA4BAoAADAOgQIAAIxDoAAAAOMQKAAAwDgECgAAMA6BAgAAjEOgAAAA4xAoAADAOAQKAAAwTsyB8sEHH2jevHny+XxyOBx66623oo5blqWKigr5fD4lJycrPz9fJ06ciFoTiURUXFysjIwMpaSkaP78+ero6LimEwEAACNHzIFy/vx53X///aqurr7k8Y0bN2rTpk2qrq5Wc3OzvF6vZs2apZ6eHntNSUmJ6urqVFtbq8bGRvX29mru3LkaGBi4+jMBAAAjRmKsdygqKlJRUdElj1mWpS1btmj9+vVauHChJGnHjh3yeDzas2ePnn76aYVCIW3fvl27du1SQUGBJGn37t3y+/06dOiQZs+ePehxI5GIIpGIfTscDsc6NgAAGEaG9D0op06dUjAYVGFhob3P6XRq2rRpampqkiS1tLTowoULUWt8Pp8CgYC95mJVVVVyu9325vf7h3JsAABgmCENlGAwKEnyeDxR+z0ej30sGAwqKSlJY8aMueyai5WXlysUCtlbe3v7UI4NAAAME/NLPN+Fw+GIum1Z1qB9F7vSGqfTKafTOWTzAQAAsw3pFRSv1ytJg66EdHV12VdVvF6v+vv71d3dfdk1AADg5jakgZKVlSWv16v6+np7X39/vxoaGpSXlydJys3N1ahRo6LWdHZ2qq2tzV4DAABubjG/xNPb26tPPvnEvn3q1CkdP35caWlpuv3221VSUqLKykplZ2crOztblZWVGj16tJYuXSpJcrvdWrFihUpLS5Wenq60tDSVlZUpJyfH/lQPAAC4ucUcKMeOHdP06dPt22vWrJEkLVu2TDU1NVq7dq36+vq0cuVKdXd3a/LkyTp48KBSU1Pt+2zevFmJiYlavHix+vr6NHPmTNXU1CghIWEITgkAAAx3DsuyrHgPEatwOCy3261QKCSXyxXvcW6oO57bF+8RcAOd3vBIvEfADcTP983lZvz5juX3N3+LBwAAGIdAAQAAxiFQAACAcQgUAABgHAIFAAAYh0ABAADGIVAAAIBxCBQAAGAcAgUAABiHQAEAAMYhUAAAgHEIFAAAYBwCBQAAGIdAAQAAxiFQAACAcQgUAABgHAIFAAAYh0ABAADGIVAAAIBxCBQAAGAcAgUAABiHQAEAAMYhUAAAgHEIFAAAYBwCBQAAGIdAAQAAxiFQAACAcQgUAABgHAIFAAAYh0ABAADGGfJAqaiokMPhiNq8Xq993LIsVVRUyOfzKTk5Wfn5+Tpx4sRQjwEAAIax63IF5b777lNnZ6e9tba22sc2btyoTZs2qbq6Ws3NzfJ6vZo1a5Z6enquxygAAGAYui6BkpiYKK/Xa29jx46V9N+rJ1u2bNH69eu1cOFCBQIB7dixQ19++aX27NlzPUYBAADD0HUJlJMnT8rn8ykrK0s/+tGP9K9//UuSdOrUKQWDQRUWFtprnU6npk2bpqampss+XiQSUTgcjtoAAMDINeSBMnnyZO3cuVPvvfeeXn31VQWDQeXl5ens2bMKBoOSJI/HE3Ufj8djH7uUqqoqud1ue/P7/UM9NgAAMMiQB0pRUZEWLVqknJwcFRQUaN++fZKkHTt22GscDkfUfSzLGrTvf5WXlysUCtlbe3v7UI8NAAAMct0/ZpySkqKcnBydPHnS/jTPxVdLurq6Bl1V+V9Op1MulytqAwAAI9d1D5RIJKJ//OMfyszMVFZWlrxer+rr6+3j/f39amhoUF5e3vUeBQAADBOJQ/2AZWVlmjdvnm6//XZ1dXXp17/+tcLhsJYtWyaHw6GSkhJVVlYqOztb2dnZqqys1OjRo7V06dKhHgUAAAxTQx4oHR0d+vGPf6wvvvhCY8eO1ZQpU3T06FFNmDBBkrR27Vr19fVp5cqV6u7u1uTJk3Xw4EGlpqYO9SgAAGCYGvJAqa2tveJxh8OhiooKVVRUDPVTAwCAEYK/xQMAAIxDoAAAAOMQKAAAwDgECgAAMA6BAgAAjEOgAAAA4xAoAADAOAQKAAAwDoECAACMQ6AAAADjECgAAMA4BAoAADAOgQIAAIxDoAAAAOMQKAAAwDgECgAAMA6BAgAAjEOgAAAA4xAoAADAOAQKAAAwDoECAACMQ6AAAADjECgAAMA4BAoAADAOgQIAAIxDoAAAAOMQKAAAwDgECgAAMA6BAgAAjEOgAAAA4xAoAADAOHENlN/97nfKysrSrbfeqtzcXP35z3+O5zgAAMAQcQuUvXv3qqSkROvXr9df//pXPfTQQyoqKtJnn30Wr5EAAIAh4hYomzZt0ooVK/TTn/5U99xzj7Zs2SK/369t27bFayQAAGCIxHg8aX9/v1paWvTcc89F7S8sLFRTU9Og9ZFIRJFIxL4dCoUkSeFw+PoOaqCvI1/GewTcQDfj/8ZvZvx831xuxp/vb87ZsqxvXRuXQPniiy80MDAgj8cTtd/j8SgYDA5aX1VVpRdeeGHQfr/ff91mBEzg3hLvCQBcLzfzz3dPT4/cbvcV18QlUL7hcDiibluWNWifJJWXl2vNmjX27a+//lr/+c9/lJ6efsn1GFnC4bD8fr/a29vlcrniPQ6AIcTP983Fsiz19PTI5/N969q4BEpGRoYSEhIGXS3p6uoadFVFkpxOp5xOZ9S+733ve9dzRBjI5XLxf2DACMXP983j266cfCMub5JNSkpSbm6u6uvro/bX19crLy8vHiMBAACDxO0lnjVr1uiJJ57QpEmTNHXqVL3yyiv67LPP9Mwzz8RrJAAAYIi4BcqSJUt09uxZ/fKXv1RnZ6cCgYD279+vCRMmxGskGMrpdOr5558f9DIfgOGPn29cjsP6Lp/1AQAAuIH4WzwAAMA4BAoAADAOgQIAAIxDoMAYHR0d8R4BAGAIAgXGCAQC2rVrV7zHAAAYgECBMSorK7Vq1SotWrRIZ8+ejfc4AIA4IlBgjJUrV+pvf/uburu7dd999+mdd96J90gAgDjhe1BgpOrqav3iF7/QPffco8TE6O8T/PDDD+M0FYBrdcstt3zrH3l1OBz66quvbtBEMFVc/5oxcCmffvqp3njjDaWlpWnBggWDAgXA8FVXV3fZY01NTdq6dav4dzMkAgWGefXVV1VaWqqCggK1tbVp7Nix8R4JwBBasGDBoH3//Oc/VV5erj/+8Y96/PHH9atf/SoOk8E0BAqMMWfOHP3lL39RdXW1nnzyyXiPA+A6O3PmjJ5//nnt2LFDs2fP1vHjxxUIBOI9FgxBoMAYAwMD+uijjzR+/Ph4jwLgOgqFQqqsrNTWrVv1gx/8QH/605/00EMPxXssGIY3yQIAbpiNGzfqxRdflNfrVWVl5SVf8gEkAgUAcAPdcsstSk5OVkFBgRISEi677s0337yBU8FEvMQDALhhnnzyyW/9mDEgcQUFAAAYiG+SBQAAxiFQAACAcQgUAABgHAIFAAAYh0ABAADGIVAAAIBxCBQAAGCc/wfrkWAyamx1GwAAAABJRU5ErkJggg==", + "image/png": "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", "text/plain": [ "
" ] @@ -461,7 +461,7 @@ }, { "cell_type": "code", - "execution_count": 14, + "execution_count": 34, "metadata": {}, "outputs": [ { @@ -470,13 +470,13 @@ "" ] }, - "execution_count": 14, + "execution_count": 34, "metadata": {}, "output_type": "execute_result" }, { "data": { - "image/png": "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", + "image/png": "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", "text/plain": [ "
" ] @@ -491,16 +491,16 @@ }, { "cell_type": "code", - "execution_count": 15, + "execution_count": 35, "metadata": {}, "outputs": [ { "data": { "text/plain": [ - "" + "" ] }, - "execution_count": 15, + "execution_count": 35, "metadata": {}, "output_type": "execute_result" }, @@ -523,16 +523,16 @@ }, { "cell_type": "code", - "execution_count": 16, + "execution_count": 36, "metadata": {}, "outputs": [ { "data": { "text/plain": [ - "" + "" ] }, - "execution_count": 16, + "execution_count": 36, "metadata": {}, "output_type": "execute_result" }, @@ -553,11 +553,301 @@ }, { "cell_type": "code", - "execution_count": 17, + "execution_count": 37, "metadata": {}, "outputs": [], "source": [ - "from sklearn.model_selection import train_test_split\n" + "from sklearn.model_selection import train_test_split\n", + "home_loan_val_final, home_loan_test_final = train_test_split(home_loan_test, test_size=0.5, random_state=1)\n", + "home_loan_train_final = home_loan_train" + ] + }, + { + "cell_type": "code", + "execution_count": 38, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
Loan_IDGenderMarriedDependentsEducationSelf_EmployedApplicantIncomeCoapplicantIncomeLoanAmountLoan_Amount_TermCredit_HistoryProperty_AreaLoan_Status
1LP001003MaleYes1GraduateNo0.0548300.0361920.1722140.7435901.0RuralN
2LP001005MaleYes0GraduateYes0.0352500.0000000.0824890.7435901.0UrbanY
3LP001006MaleYes0Not GraduateNo0.0300930.0565920.1606370.7435901.0UrbanY
4LP001008MaleNo0GraduateNo0.0723560.0000000.1910270.7435901.0UrbanY
5LP001011MaleYes2GraduateYes0.0651450.1007030.3733720.7435901.0UrbanY
..........................................
609LP002978FemaleNo0GraduateNo0.0340140.0000000.0897250.7435901.0RuralY
610LP002979MaleYes3+GraduateNo0.0489300.0000000.0448630.3589741.0RuralY
611LP002983MaleYes1GraduateNo0.0979840.0057600.3531110.7435901.0UrbanY
612LP002984MaleYes2GraduateNo0.0919360.0000000.2575980.7435901.0UrbanY
613LP002990FemaleNo0GraduateYes0.0548300.0000000.1794500.7435900.0SemiurbanN
\n", + "

480 rows × 13 columns

\n", + "
" + ], + "text/plain": [ + " Loan_ID Gender Married Dependents Education Self_Employed \\\n", + "1 LP001003 Male Yes 1 Graduate No \n", + "2 LP001005 Male Yes 0 Graduate Yes \n", + "3 LP001006 Male Yes 0 Not Graduate No \n", + "4 LP001008 Male No 0 Graduate No \n", + "5 LP001011 Male Yes 2 Graduate Yes \n", + ".. ... ... ... ... ... ... \n", + "609 LP002978 Female No 0 Graduate No \n", + "610 LP002979 Male Yes 3+ Graduate No \n", + "611 LP002983 Male Yes 1 Graduate No \n", + "612 LP002984 Male Yes 2 Graduate No \n", + "613 LP002990 Female No 0 Graduate Yes \n", + "\n", + " ApplicantIncome CoapplicantIncome LoanAmount Loan_Amount_Term \\\n", + "1 0.054830 0.036192 0.172214 0.743590 \n", + "2 0.035250 0.000000 0.082489 0.743590 \n", + "3 0.030093 0.056592 0.160637 0.743590 \n", + "4 0.072356 0.000000 0.191027 0.743590 \n", + "5 0.065145 0.100703 0.373372 0.743590 \n", + ".. ... ... ... ... \n", + "609 0.034014 0.000000 0.089725 0.743590 \n", + "610 0.048930 0.000000 0.044863 0.358974 \n", + "611 0.097984 0.005760 0.353111 0.743590 \n", + "612 0.091936 0.000000 0.257598 0.743590 \n", + "613 0.054830 0.000000 0.179450 0.743590 \n", + "\n", + " Credit_History Property_Area Loan_Status \n", + "1 1.0 Rural N \n", + "2 1.0 Urban Y \n", + "3 1.0 Urban Y \n", + "4 1.0 Urban Y \n", + "5 1.0 Urban Y \n", + ".. ... ... ... \n", + "609 1.0 Rural Y \n", + "610 1.0 Rural Y \n", + "611 1.0 Urban Y \n", + "612 1.0 Urban Y \n", + "613 0.0 Semiurban N \n", + "\n", + "[480 rows x 13 columns]" + ] + }, + "execution_count": 38, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from sklearn.preprocessing import MinMaxScaler\n", + "numeric_cols_train = home_loan_train_final.select_dtypes(include='number').columns\n", + "numeric_cols_test = home_loan_test_final.select_dtypes(include='number').columns\n", + "numeric_cols_val = home_loan_val_final.select_dtypes(include='number').columns\n", + "scaler = MinMaxScaler()\n", + "home_loan_train_final[numeric_cols_train] = scaler.fit_transform(home_loan_train_final[numeric_cols_train])\n", + "home_loan_test_final[numeric_cols_test] = scaler.fit_transform(home_loan_test_final[numeric_cols_test])\n", + "home_loan_val_final[numeric_cols_val] = scaler.fit_transform(home_loan_val_final[numeric_cols_val])\n", + "\n", + "home_loan_train_final = home_loan_train_final.dropna()\n", + "home_loan_test_final = home_loan_test_final.dropna()\n", + "home_loan_val_final = home_loan_val_final.dropna()\n", + "\n", + "home_loan_train_final" ] }, {