Predicting Lending & Loan Repayment Using ML.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "import pickle\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.model_selection import KFold\n",
    "from sklearn.model_selection import GridSearchCV\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "from sklearn import neighbors\n",
    "from sklearn import datasets\n",
    "from sklearn import metrics\n",
    "from sklearn import tree\n",
    "from sklearn import svm"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "ofname=open('IDSgithub/files/ch05/dataset_small.pkl','rb')\n",
    "(x,y)=pickle.load(ofname,encoding='latin1')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Dims: 15, Samples:  4140\n"
     ]
    }
   ],
   "source": [
    "dims=x.shape[1]\n",
    "N=x.shape[0]\n",
    "print('Dims: '+str(dims)+', Samples: ',str(N))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Predicted Value: -1.0 , Real Target: -1.0\n"
     ]
    }
   ],
   "source": [
    "knn=neighbors.KNeighborsClassifier(n_neighbors=11)\n",
    "knn.fit(x,y)\n",
    "yhat=knn.predict(x)\n",
    "print('Predicted Value: '+str(yhat[-1]),', Real Target: '+str(y[-1]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.8316425120772947"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "knn.score(x,y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 504x504 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.pie(np.c_[np.sum(np.where(y==1,1,0)),np.sum(np.where(y==-1,1,0))][0],labels=['Not fully funded','Full amount'],colors=['r','g'],shadow=False,autopct='%.2f')\n",
    "plt.gcf().set_size_inches((7,7))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "TP:  3370\n",
      "FP:  690\n",
      "TN:  73\n",
      "FN:  7\n"
     ]
    }
   ],
   "source": [
    "yhat=knn.predict(x)\n",
    "TP=np.sum(np.logical_and(yhat==-1,y==-1))\n",
    "TN=np.sum(np.logical_and(yhat==1,y==1))\n",
    "FP=np.sum(np.logical_and(yhat==-1,y==1))\n",
    "FN=np.sum(np.logical_and(yhat==1,y==-1))\n",
    "print('TP: ',str(TP))\n",
    "print('FP: ',str(FP))\n",
    "print('TN: ',str(TN))\n",
    "print('FN: ',str(FN))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[3370,  690],\n",
       "       [   7,   73]])"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "metrics.confusion_matrix(yhat,y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Score:  1.0\n",
      "Classification Accuracy (Accuracy Score):  1.0\n",
      "Confusion Matrix: \n",
      " [[3377    0]\n",
      " [   0  763]]\n"
     ]
    }
   ],
   "source": [
    "knn=neighbors.KNeighborsClassifier(n_neighbors=1)\n",
    "knn.fit(x,y)\n",
    "yhat=knn.predict(x)\n",
    "print('Score: ',knn.score(x,y))\n",
    "print('Classification Accuracy (Accuracy Score): ',str(metrics.accuracy_score(yhat,y)))\n",
    "print('Confusion Matrix: \\n',str(metrics.confusion_matrix(yhat,y)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Training Shape:  (2898, 15) , Training Targets Shape:  (2898,)\n",
      "Testing Shape:  (1242, 15) , Testing Targets Shape (1242,)\n"
     ]
    }
   ],
   "source": [
    "perm=np.random.permutation(y.size)\n",
    "PRC=0.7\n",
    "split_point=int(np.ceil(y.shape[0]*PRC))\n",
    "X_train=x[perm[:split_point].ravel(),:]\n",
    "y_train=y[perm[:split_point].ravel()]\n",
    "X_test=x[perm[split_point:].ravel(),:]\n",
    "y_test=y[perm[split_point:].ravel()]\n",
    "print('Training Shape: ',X_train.shape,', Training Targets Shape: ',y_train.shape)\n",
    "print('Testing Shape: ',X_test.shape,', Testing Targets Shape',y_test.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "TRAINING STATS: \n",
      "\n",
      "Score:  1.0\n",
      "Classification Accuracy:  1.0\n",
      "Confusion Matrix: \n",
      " [[2349    0]\n",
      " [   0  549]]\n"
     ]
    }
   ],
   "source": [
    "knn=neighbors.KNeighborsClassifier(n_neighbors=1)\n",
    "knn.fit(X_train,y_train)\n",
    "yhat=knn.predict(X_train)\n",
    "print('TRAINING STATS: \\n')\n",
    "print('Score: ',knn.score(X_train,y_train))\n",
    "print('Classification Accuracy: ',str(metrics.accuracy_score(yhat,y_train)))\n",
    "print('Confusion Matrix: \\n',metrics.confusion_matrix(yhat,y_train))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "TRAINING STATS: \n",
      "\n",
      "Score:  0.9272946859903382\n",
      "Classification Accuracy (Accuracy Score):  0.7576489533011272\n",
      "Confusion Matrix: \n",
      " [[863 136]\n",
      " [165  78]]\n"
     ]
    }
   ],
   "source": [
    "yhat=knn.predict(X_test)\n",
    "print('TRAINING STATS: \\n')\n",
    "print('Score: ',knn.score(x,y))\n",
    "print('Classification Accuracy (Accuracy Score): ',str(metrics.accuracy_score(yhat,y_test)))\n",
    "print('Confusion Matrix: \\n',metrics.confusion_matrix(yhat,y_test))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Mean Expected Error:  0.75829307568438\n"
     ]
    }
   ],
   "source": [
    "PRC=0.3\n",
    "acc=np.zeros((10,))\n",
    "for i in range(10):\n",
    "    X_train,X_test,y_train,y_test=train_test_split(x,y,test_size=PRC)\n",
    "    knn=neighbors.KNeighborsClassifier(n_neighbors=1)\n",
    "    knn.fit(X_train,y_train)\n",
    "    yhat=knn.predict(X_test)\n",
    "    acc[i]=metrics.accuracy_score(yhat,y_test)\n",
    "acc.shape=(1,10)\n",
    "print('Mean Expected Error: ',str(np.mean(acc[0])))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[0.77536232 0.77777778 0.81884058 0.76570048]\n",
      " [0.73188406 0.78743961 0.81884058 0.79951691]\n",
      " [0.78502415 0.78985507 0.83816425 0.7705314 ]\n",
      " [0.78502415 0.81400966 0.81642512 0.77536232]\n",
      " [0.75845411 0.7705314  0.8115942  0.76811594]\n",
      " [0.76570048 0.81400966 0.83333333 0.75362319]\n",
      " [0.7826087  0.79468599 0.81884058 0.7826087 ]\n",
      " [0.74396135 0.76086957 0.82125604 0.76570048]\n",
      " [0.7294686  0.77777778 0.8115942  0.79468599]\n",
      " [0.73913043 0.77294686 0.81400966 0.77777778]]\n"
     ]
    }
   ],
   "source": [
    "PRC=0.1\n",
    "acc_r=np.zeros((10,4))\n",
    "for i in range(10):\n",
    "    X_train,X_test,y_train,y_test=train_test_split(x,y,test_size=PRC)\n",
    "    nn1=neighbors.KNeighborsClassifier(n_neighbors=1)\n",
    "    nn3=neighbors.KNeighborsClassifier(n_neighbors=3)\n",
    "    svc=svm.SVC()\n",
    "    dt=tree.DecisionTreeClassifier()\n",
    "    nn1.fit(X_train,y_train)\n",
    "    nn3.fit(X_train,y_train)\n",
    "    svc.fit(X_train,y_train)\n",
    "    dt.fit(X_train,y_train)\n",
    "    yhat_nn1=nn1.predict(X_test)\n",
    "    yhat_nn3=nn3.predict(X_test)\n",
    "    yhat_svc=svc.predict(X_test)\n",
    "    yhat_dt=dt.predict(X_test)\n",
    "    acc_r[i][0]=metrics.accuracy_score(yhat_nn1,y_test)\n",
    "    acc_r[i][1]=metrics.accuracy_score(yhat_nn3,y_test)\n",
    "    acc_r[i][2]=metrics.accuracy_score(yhat_svc,y_test)\n",
    "    acc_r[i][3]=metrics.accuracy_score(yhat_dt,y_test)\n",
    "print(acc_r)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[0.81884058 0.8236715  0.83091787 0.83333333 0.83091787 0.82850242\n",
      "  0.81884058 0.8236715  0.81400966 0.82608696 0.8236715  0.82125604\n",
      "  0.8115942  0.80193237 0.80676329 0.79951691 0.79710145 0.80676329]\n",
      " [0.77777778 0.77777778 0.77777778 0.79710145 0.80193237 0.79227053\n",
      "  0.79951691 0.79710145 0.79227053 0.78743961 0.78019324 0.77536232\n",
      "  0.76811594 0.76811594 0.76570048 0.78502415 0.77294686 0.77536232]\n",
      " [0.84057971 0.84299517 0.86231884 0.85024155 0.852657   0.84782609\n",
      "  0.84299517 0.83816425 0.84057971 0.84782609 0.83574879 0.83333333\n",
      "  0.83333333 0.82608696 0.82850242 0.8236715  0.81642512 0.79951691]\n",
      " [0.81884058 0.82125604 0.82125604 0.82608696 0.81884058 0.82125604\n",
      "  0.81884058 0.80917874 0.81642512 0.8115942  0.81642512 0.81884058\n",
      "  0.80193237 0.77777778 0.79227053 0.79710145 0.77294686 0.77294686]\n",
      " [0.81400966 0.81400966 0.82608696 0.82850242 0.83333333 0.83333333\n",
      "  0.82125604 0.82125604 0.81884058 0.8115942  0.82125604 0.79951691\n",
      "  0.80917874 0.7826087  0.79227053 0.78985507 0.78019324 0.76328502]\n",
      " [0.85990338 0.85990338 0.8647343  0.86714976 0.86231884 0.85990338\n",
      "  0.852657   0.85024155 0.83091787 0.81400966 0.81642512 0.80917874\n",
      "  0.80917874 0.8115942  0.78019324 0.78985507 0.75362319 0.77777778]\n",
      " [0.81884058 0.81884058 0.81884058 0.83333333 0.83091787 0.8236715\n",
      "  0.82125604 0.81400966 0.80434783 0.80193237 0.80676329 0.80193237\n",
      "  0.79951691 0.77777778 0.78743961 0.76811594 0.76811594 0.76328502]\n",
      " [0.83333333 0.83333333 0.84057971 0.83091787 0.83333333 0.83816425\n",
      "  0.83816425 0.84057971 0.83574879 0.83091787 0.81642512 0.81400966\n",
      "  0.8236715  0.81884058 0.79951691 0.78502415 0.79227053 0.78743961]\n",
      " [0.81884058 0.81884058 0.8236715  0.82850242 0.83333333 0.83091787\n",
      "  0.82850242 0.8236715  0.82125604 0.81642512 0.80676329 0.81400966\n",
      "  0.80917874 0.79468599 0.81400966 0.79951691 0.79710145 0.79227053]\n",
      " [0.852657   0.852657   0.852657   0.84541063 0.85748792 0.85507246\n",
      "  0.84541063 0.84057971 0.852657   0.84057971 0.82125604 0.81642512\n",
      "  0.80676329 0.79227053 0.80193237 0.77294686 0.76086957 0.76086957]]\n"
     ]
    }
   ],
   "source": [
    "kf=KFold(n_splits=10,shuffle=True,random_state=0)\n",
    "C=np.arange(2,20,)\n",
    "acc=np.zeros((10,18))\n",
    "i=0\n",
    "for train_index,val_index in kf.split(x):\n",
    "    X_train,X_val=x[train_index],x[val_index]\n",
    "    y_train,y_val=y[train_index],y[val_index]\n",
    "    j=0\n",
    "    for c in C:\n",
    "        dt=tree.DecisionTreeClassifier(min_samples_leaf=1,max_depth=c)\n",
    "        dt.fit(X_train,y_train)\n",
    "        yhat=dt.predict(X_val)\n",
    "        acc[i][j]=metrics.accuracy_score(yhat,y_val)\n",
    "        j=j+1\n",
    "    i=i+1\n",
    "print(acc)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Mean Accuracy:  [0.82577349 0.82607469 0.82728133 0.82365595 0.830004   0.82245022\n",
      " 0.82667892 0.82003422 0.81852637 0.8182279  0.81158501 0.80765843\n",
      " 0.80675117 0.79829924 0.79135151 0.78712736 0.78561952 0.77807029]\n",
      "Selected Model Index:  4\n"
     ]
    }
   ],
   "source": [
    "X_train,X_test,y_train,y_test=train_test_split(x,y,test_size=0.20)\n",
    "kf=KFold(n_splits=10,shuffle=True,random_state=0)\n",
    "C=np.arange(2,20,)\n",
    "acc=np.zeros((10,18))\n",
    "i=0\n",
    "for train_index,val_index in kf.split(X_train):\n",
    "    X_t,X_val=X_train[train_index],X_train[val_index]\n",
    "    y_t,y_val=y_train[train_index],y_train[val_index]\n",
    "    j=0\n",
    "    for c in C:\n",
    "        dt=tree.DecisionTreeClassifier(min_samples_leaf=1,max_depth=c)\n",
    "        dt.fit(X_t,y_t)\n",
    "        yhat=dt.predict(X_val)\n",
    "        acc[i][j]=metrics.accuracy_score(yhat,y_val)\n",
    "        j=j+1\n",
    "    i=i+1\n",
    "print('Mean Accuracy: ',str(np.mean(acc,axis=0)))\n",
    "print('Selected Model Index: ',np.argmax(np.mean(acc,axis=0)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Test accuracy:  0.8055555555555556\n"
     ]
    }
   ],
   "source": [
    "dt=tree.DecisionTreeClassifier(min_samples_leaf=1,max_depth=C[np.argmax(np.mean(acc,axis=0))])\n",
    "dt.fit(X_train,y_train)\n",
    "yhat=dt.predict(X_test)\n",
    "print('Test accuracy: ',metrics.accuracy_score(yhat,y_test))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=6,\n",
       "            max_features=None, max_leaf_nodes=None,\n",
       "            min_impurity_decrease=0.0, min_impurity_split=None,\n",
       "            min_samples_leaf=1, min_samples_split=2,\n",
       "            min_weight_fraction_leaf=0.0, presort=False, random_state=None,\n",
       "            splitter='best')"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dt=tree.DecisionTreeClassifier(min_samples_leaf=1,max_depth=C[np.argmax(np.mean(acc,axis=0))])\n",
    "dt.fit(x,y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "parameters={'C':[1e4,1e5,1e6],'gamma':[1e-5,1e-4,1e-3]}\n",
    "N_splits=5\n",
    "kf=KFold(n_splits=N_splits,shuffle=True,random_state=0)\n",
    "acc=np.zeros((N_splits,))\n",
    "i=0\n",
    "yhat=y.copy()\n",
    "for train_index,test_index in kf.split(x):\n",
    "    X_train,X_test=x[train_index,:],x[test_index,:]\n",
    "    y_train,y_test=y[train_index],y[test_index]\n",
    "    scaler=StandardScaler()\n",
    "    X_train=scaler.fit_transform(X_train)\n",
    "    clf=svm.SVC(kernel='rbf')\n",
    "    clf=GridSearchCV(clf,parameters,cv=3)\n",
    "    clf.fit(X_train,y_train.ravel())\n",
    "    X_test=scaler.transform(X_test)\n",
    "    yhat[test_index]=clf.predict(X_test)\n",
    "    i=i+1\n",
    "print(metrics.confusion_matrix(yhat,y))\n",
    "print(metrics.confusion_matrix(yhat,y))"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.7.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}