random_forest_classifier.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "da68738d",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Basic Workflow\n",
    "\n",
    "# 1. Getting the data ready\n",
    "# 2. Choose rhe right estimator/algorithm for our problems\n",
    "# 3. Fit the model/algorithm and use it to make predictions on our data\n",
    "# 4. Evaluating a model\n",
    "# 5. Improve a model\n",
    "# 6. Save and load a trained model\n",
    "# 7. Putting it all together!!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "9ba6df30",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Importing the libraries "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "73735cbb",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "a0bbbccf",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Importing the data set"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "156f45f2",
   "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>age</th>\n",
       "      <th>sex</th>\n",
       "      <th>cp</th>\n",
       "      <th>trestbps</th>\n",
       "      <th>chol</th>\n",
       "      <th>fbs</th>\n",
       "      <th>restecg</th>\n",
       "      <th>thalach</th>\n",
       "      <th>exang</th>\n",
       "      <th>oldpeak</th>\n",
       "      <th>slope</th>\n",
       "      <th>ca</th>\n",
       "      <th>thal</th>\n",
       "      <th>target</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>63</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>145</td>\n",
       "      <td>233</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>150</td>\n",
       "      <td>0</td>\n",
       "      <td>2.3</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>37</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>130</td>\n",
       "      <td>250</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>187</td>\n",
       "      <td>0</td>\n",
       "      <td>3.5</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>41</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>130</td>\n",
       "      <td>204</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>172</td>\n",
       "      <td>0</td>\n",
       "      <td>1.4</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>56</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>120</td>\n",
       "      <td>236</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>178</td>\n",
       "      <td>0</td>\n",
       "      <td>0.8</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>57</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>120</td>\n",
       "      <td>354</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>163</td>\n",
       "      <td>1</td>\n",
       "      <td>0.6</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>298</th>\n",
       "      <td>57</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>140</td>\n",
       "      <td>241</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>123</td>\n",
       "      <td>1</td>\n",
       "      <td>0.2</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>299</th>\n",
       "      <td>45</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>110</td>\n",
       "      <td>264</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>132</td>\n",
       "      <td>0</td>\n",
       "      <td>1.2</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>300</th>\n",
       "      <td>68</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>144</td>\n",
       "      <td>193</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>141</td>\n",
       "      <td>0</td>\n",
       "      <td>3.4</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>301</th>\n",
       "      <td>57</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>130</td>\n",
       "      <td>131</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>115</td>\n",
       "      <td>1</td>\n",
       "      <td>1.2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>302</th>\n",
       "      <td>57</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>130</td>\n",
       "      <td>236</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>174</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>303 rows × 14 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     age  sex  cp  trestbps  chol  fbs  restecg  thalach  exang  oldpeak  \\\n",
       "0     63    1   3       145   233    1        0      150      0      2.3   \n",
       "1     37    1   2       130   250    0        1      187      0      3.5   \n",
       "2     41    0   1       130   204    0        0      172      0      1.4   \n",
       "3     56    1   1       120   236    0        1      178      0      0.8   \n",
       "4     57    0   0       120   354    0        1      163      1      0.6   \n",
       "..   ...  ...  ..       ...   ...  ...      ...      ...    ...      ...   \n",
       "298   57    0   0       140   241    0        1      123      1      0.2   \n",
       "299   45    1   3       110   264    0        1      132      0      1.2   \n",
       "300   68    1   0       144   193    1        1      141      0      3.4   \n",
       "301   57    1   0       130   131    0        1      115      1      1.2   \n",
       "302   57    0   1       130   236    0        0      174      0      0.0   \n",
       "\n",
       "     slope  ca  thal  target  \n",
       "0        0   0     1       1  \n",
       "1        0   0     2       1  \n",
       "2        2   0     2       1  \n",
       "3        2   0     2       1  \n",
       "4        2   0     2       1  \n",
       "..     ...  ..   ...     ...  \n",
       "298      1   0     3       0  \n",
       "299      1   0     3       0  \n",
       "300      1   2     3       0  \n",
       "301      1   1     3       0  \n",
       "302      1   1     2       0  \n",
       "\n",
       "[303 rows x 14 columns]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "heart_disease = pd.read_csv(\"data\\heart-disease.csv\")\n",
    "heart_disease"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "9327e637",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Creating the data set"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "c8b198f4",
   "metadata": {},
   "outputs": [],
   "source": [
    "x = heart_disease.drop(\"target\", axis = 1)\n",
    "y = heart_disease[\"target\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "02ee9cf9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'bootstrap': True,\n",
       " 'ccp_alpha': 0.0,\n",
       " 'class_weight': None,\n",
       " 'criterion': 'gini',\n",
       " 'max_depth': None,\n",
       " 'max_features': 'auto',\n",
       " 'max_leaf_nodes': None,\n",
       " 'max_samples': None,\n",
       " 'min_impurity_decrease': 0.0,\n",
       " 'min_impurity_split': None,\n",
       " 'min_samples_leaf': 1,\n",
       " 'min_samples_split': 2,\n",
       " 'min_weight_fraction_leaf': 0.0,\n",
       " 'n_estimators': 100,\n",
       " 'n_jobs': None,\n",
       " 'oob_score': False,\n",
       " 'random_state': None,\n",
       " 'verbose': 0,\n",
       " 'warm_start': False}"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.ensemble import RandomForestClassifier\n",
    "\n",
    "model = RandomForestClassifier()\n",
    "\n",
    "model.get_params()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "bca20ce9",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Creating the training and test set\n",
    "\n",
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "x_train, x_test, y_train, y_test = train_test_split(x,y,test_size = 0.3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "a2a11ca0",
   "metadata": {},
   "outputs": [],
   "source": [
    "#Training the data\n",
    "\n",
    "model.fit(x_train,y_train);"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "16719661",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 1, 1, 0, 1, 0, 1, 0, 0, 1, 0, 1, 0, 1, 1, 1, 1, 1, 0, 1, 0, 1,\n",
       "       0, 1, 1, 0, 1, 1, 0, 1, 0, 1, 0, 0, 1, 0, 0, 1, 0, 0, 1, 1, 0, 1,\n",
       "       1, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 1, 1, 0, 1, 0, 1, 1, 1,\n",
       "       1, 1, 1, 0, 0, 0, 1, 0, 1, 0, 1, 0, 0, 0, 1, 1, 1, 0, 1, 1, 1, 1,\n",
       "       1, 1, 0], dtype=int64)"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Making predictions\n",
    "\n",
    "y_preds = model.predict(x_test)\n",
    "y_preds"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "34b0663e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1.0"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Evaluating the model\n",
    "\n",
    "model.score(x_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "45f986dc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.8571428571428571"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.score(x_test,y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "142e77d5",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.90      0.80      0.85        46\n",
      "           1       0.82      0.91      0.86        45\n",
      "\n",
      "    accuracy                           0.86        91\n",
      "   macro avg       0.86      0.86      0.86        91\n",
      "weighted avg       0.86      0.86      0.86        91\n",
      "\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import classification_report, confusion_matrix, accuracy_score\n",
    "\n",
    "print(classification_report(y_test,y_preds))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "35064a59",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[37,  9],\n",
       "       [ 4, 41]], dtype=int64)"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "confusion_matrix(y_test,y_preds)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "c92c6c70",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.8571428571428571"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "accuracy_score(y_test,y_preds)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "6270b372",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Improving the model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "6c112859",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Trying model with 10 estimators\n",
      "Model accuracy - 82.41758241758241%\n",
      "\n",
      "Trying model with 20 estimators\n",
      "Model accuracy - 83.51648351648352%\n",
      "\n",
      "Trying model with 30 estimators\n",
      "Model accuracy - 87.91208791208791%\n",
      "\n",
      "Trying model with 40 estimators\n",
      "Model accuracy - 89.01098901098901%\n",
      "\n",
      "Trying model with 50 estimators\n",
      "Model accuracy - 86.81318681318682%\n",
      "\n",
      "Trying model with 60 estimators\n",
      "Model accuracy - 86.81318681318682%\n",
      "\n",
      "Trying model with 70 estimators\n",
      "Model accuracy - 86.81318681318682%\n",
      "\n",
      "Trying model with 80 estimators\n",
      "Model accuracy - 87.91208791208791%\n",
      "\n",
      "Trying model with 90 estimators\n",
      "Model accuracy - 89.01098901098901%\n",
      "\n",
      "Trying model with 100 estimators\n",
      "Model accuracy - 87.91208791208791%\n",
      "\n",
      "Trying model with 110 estimators\n",
      "Model accuracy - 85.71428571428571%\n",
      "\n",
      "Trying model with 120 estimators\n",
      "Model accuracy - 86.81318681318682%\n",
      "\n",
      "Trying model with 130 estimators\n",
      "Model accuracy - 86.81318681318682%\n",
      "\n",
      "Trying model with 140 estimators\n",
      "Model accuracy - 87.91208791208791%\n",
      "\n",
      "Trying model with 150 estimators\n",
      "Model accuracy - 89.01098901098901%\n",
      "\n",
      "Trying model with 160 estimators\n",
      "Model accuracy - 87.91208791208791%\n",
      "\n",
      "Trying model with 170 estimators\n",
      "Model accuracy - 87.91208791208791%\n",
      "\n",
      "Trying model with 180 estimators\n",
      "Model accuracy - 87.91208791208791%\n",
      "\n",
      "Trying model with 190 estimators\n",
      "Model accuracy - 87.91208791208791%\n",
      "\n",
      "Trying model with 200 estimators\n",
      "Model accuracy - 86.81318681318682%\n",
      "\n",
      "Trying model with 210 estimators\n",
      "Model accuracy - 86.81318681318682%\n",
      "\n",
      "Trying model with 220 estimators\n",
      "Model accuracy - 86.81318681318682%\n",
      "\n",
      "Trying model with 230 estimators\n",
      "Model accuracy - 89.01098901098901%\n",
      "\n",
      "Trying model with 240 estimators\n",
      "Model accuracy - 86.81318681318682%\n",
      "\n",
      "Trying model with 250 estimators\n",
      "Model accuracy - 87.91208791208791%\n",
      "\n",
      "Trying model with 260 estimators\n",
      "Model accuracy - 87.91208791208791%\n",
      "\n",
      "Trying model with 270 estimators\n",
      "Model accuracy - 87.91208791208791%\n",
      "\n",
      "Trying model with 280 estimators\n",
      "Model accuracy - 87.91208791208791%\n",
      "\n",
      "Trying model with 290 estimators\n",
      "Model accuracy - 90.10989010989012%\n",
      "\n",
      "Trying model with 300 estimators\n",
      "Model accuracy - 86.81318681318682%\n",
      "\n",
      "Trying model with 310 estimators\n",
      "Model accuracy - 86.81318681318682%\n",
      "\n",
      "Trying model with 320 estimators\n",
      "Model accuracy - 86.81318681318682%\n",
      "\n",
      "Trying model with 330 estimators\n",
      "Model accuracy - 87.91208791208791%\n",
      "\n",
      "Trying model with 340 estimators\n",
      "Model accuracy - 87.91208791208791%\n",
      "\n",
      "Trying model with 350 estimators\n",
      "Model accuracy - 86.81318681318682%\n",
      "\n",
      "Trying model with 360 estimators\n",
      "Model accuracy - 89.01098901098901%\n",
      "\n",
      "Trying model with 370 estimators\n",
      "Model accuracy - 87.91208791208791%\n",
      "\n",
      "Trying model with 380 estimators\n",
      "Model accuracy - 86.81318681318682%\n",
      "\n",
      "Trying model with 390 estimators\n",
      "Model accuracy - 86.81318681318682%\n",
      "\n"
     ]
    }
   ],
   "source": [
    "for i in range (10,400,10):\n",
    "    print(f\"Trying model with {i} estimators\")\n",
    "    model = RandomForestClassifier(n_estimators=i)\n",
    "    model.fit(x_train,y_train)\n",
    "    print(f\"Model accuracy - {model.score(x_test,y_test)*100}%\")\n",
    "    print(\"\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "1f762dda",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pickle\n",
    "\n",
    "pickle.dump(model, open(\"random_forest_model.pkl\", \"wb\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "caa45460",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.8681318681318682"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "loaded_model = pickle.load(open(\"random_forest_model.pkl\", \"rb\"))\n",
    "model.score(x_test, y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "4a44d80f",
   "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": "3.8.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}