ModelTraining.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Bank Note Authentication"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Data were extracted from images that were taken from genuine and forged banknote-like specimens. For digitization, an industrial camera usually used for print inspection was used. The final images have 400x 400 pixels. Due to the object lens and distance to the investigated object gray-scale pictures with a resolution of about 660 dpi were gained. Wavelet Transform tool were used to extract features from images."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "##Dataset Link: https://www.kaggle.com/ritesaluja/bank-note-authentication-uci-data\n",
    "import pandas as pd\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "df=pd.read_csv('BankNote_Authentication.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "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>variance</th>\n",
       "      <th>skewness</th>\n",
       "      <th>curtosis</th>\n",
       "      <th>entropy</th>\n",
       "      <th>class</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>3.62160</td>\n",
       "      <td>8.66610</td>\n",
       "      <td>-2.8073</td>\n",
       "      <td>-0.44699</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4.54590</td>\n",
       "      <td>8.16740</td>\n",
       "      <td>-2.4586</td>\n",
       "      <td>-1.46210</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3.86600</td>\n",
       "      <td>-2.63830</td>\n",
       "      <td>1.9242</td>\n",
       "      <td>0.10645</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3.45660</td>\n",
       "      <td>9.52280</td>\n",
       "      <td>-4.0112</td>\n",
       "      <td>-3.59440</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.32924</td>\n",
       "      <td>-4.45520</td>\n",
       "      <td>4.5718</td>\n",
       "      <td>-0.98880</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1367</th>\n",
       "      <td>0.40614</td>\n",
       "      <td>1.34920</td>\n",
       "      <td>-1.4501</td>\n",
       "      <td>-0.55949</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1368</th>\n",
       "      <td>-1.38870</td>\n",
       "      <td>-4.87730</td>\n",
       "      <td>6.4774</td>\n",
       "      <td>0.34179</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1369</th>\n",
       "      <td>-3.75030</td>\n",
       "      <td>-13.45860</td>\n",
       "      <td>17.5932</td>\n",
       "      <td>-2.77710</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1370</th>\n",
       "      <td>-3.56370</td>\n",
       "      <td>-8.38270</td>\n",
       "      <td>12.3930</td>\n",
       "      <td>-1.28230</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1371</th>\n",
       "      <td>-2.54190</td>\n",
       "      <td>-0.65804</td>\n",
       "      <td>2.6842</td>\n",
       "      <td>1.19520</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1372 rows × 5 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      variance  skewness  curtosis  entropy  class\n",
       "0      3.62160   8.66610   -2.8073 -0.44699      0\n",
       "1      4.54590   8.16740   -2.4586 -1.46210      0\n",
       "2      3.86600  -2.63830    1.9242  0.10645      0\n",
       "3      3.45660   9.52280   -4.0112 -3.59440      0\n",
       "4      0.32924  -4.45520    4.5718 -0.98880      0\n",
       "...        ...       ...       ...      ...    ...\n",
       "1367   0.40614   1.34920   -1.4501 -0.55949      1\n",
       "1368  -1.38870  -4.87730    6.4774  0.34179      1\n",
       "1369  -3.75030 -13.45860   17.5932 -2.77710      1\n",
       "1370  -3.56370  -8.38270   12.3930 -1.28230      1\n",
       "1371  -2.54190  -0.65804    2.6842  1.19520      1\n",
       "\n",
       "[1372 rows x 5 columns]"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "### Independent and Dependent features\n",
    "X=df.iloc[:,:-1]\n",
    "y=df.iloc[:,-1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "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>variance</th>\n",
       "      <th>skewness</th>\n",
       "      <th>curtosis</th>\n",
       "      <th>entropy</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>3.62160</td>\n",
       "      <td>8.6661</td>\n",
       "      <td>-2.8073</td>\n",
       "      <td>-0.44699</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4.54590</td>\n",
       "      <td>8.1674</td>\n",
       "      <td>-2.4586</td>\n",
       "      <td>-1.46210</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3.86600</td>\n",
       "      <td>-2.6383</td>\n",
       "      <td>1.9242</td>\n",
       "      <td>0.10645</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3.45660</td>\n",
       "      <td>9.5228</td>\n",
       "      <td>-4.0112</td>\n",
       "      <td>-3.59440</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.32924</td>\n",
       "      <td>-4.4552</td>\n",
       "      <td>4.5718</td>\n",
       "      <td>-0.98880</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   variance  skewness  curtosis  entropy\n",
       "0   3.62160    8.6661   -2.8073 -0.44699\n",
       "1   4.54590    8.1674   -2.4586 -1.46210\n",
       "2   3.86600   -2.6383    1.9242  0.10645\n",
       "3   3.45660    9.5228   -4.0112 -3.59440\n",
       "4   0.32924   -4.4552    4.5718 -0.98880"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0     0\n",
       "1     0\n",
       "2     0\n",
       "3     0\n",
       "4     0\n",
       "5     0\n",
       "6     0\n",
       "7     0\n",
       "8     0\n",
       "9     0\n",
       "10    0\n",
       "11    0\n",
       "12    0\n",
       "13    0\n",
       "14    0\n",
       "15    0\n",
       "16    0\n",
       "17    0\n",
       "18    0\n",
       "19    0\n",
       "Name: class, dtype: int64"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y.head(20)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "### Train Test Split\n",
    "from sklearn.model_selection import train_test_split"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.3,random_state=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight=None,\n",
       "                       criterion='gini', max_depth=None, max_features='auto',\n",
       "                       max_leaf_nodes=None, max_samples=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, n_estimators=100,\n",
       "                       n_jobs=None, oob_score=False, random_state=None,\n",
       "                       verbose=0, warm_start=False)"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "### Implement Random Forest classifier\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "classifier=RandomForestClassifier()\n",
    "classifier.fit(X_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "## Prediction\n",
    "y_pred=classifier.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "### Check Accuracy\n",
    "from sklearn.metrics import accuracy_score\n",
    "score=accuracy_score(y_test,y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9902912621359223"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "### Create a Pickle file using serialization \n",
    "import pickle\n",
    "pickle_out = open(\"classifier.pkl\",\"wb\")\n",
    "pickle.dump(classifier, pickle_out)\n",
    "pickle_out.close()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0], dtype=int64)"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "classifier.predict([[2,3,4,1]])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.7.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}