Merge pull request #1140 from kanchanrai7/main

Crop Recommendation Using ML

Machine Learning and Data Science/Intermediate/Crop Recommedation using ML/Models/Gaussian Naive Bayes.ipynb

@@ -0,0 +1,318 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "074109be-9caa-4f91-a3cf-45d8d7c7789a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "from sklearn.metrics import accuracy_score \n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.svm import SVC\n",
+    "from sklearn.preprocessing import MinMaxScaler\n",
+    "from sklearn import metrics\n",
+    "from sklearn.metrics import classification_report,confusion_matrix,ConfusionMatrixDisplay\n",
+    "from sklearn.model_selection import cross_val_score\n",
+    "from sklearn.naive_bayes import GaussianNB"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "d5649b12-bfdc-4013-a112-ee8928d0fb0b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df=pd.read_csv(\"Crop_recommendation.csv\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "33a2b758-7ace-4970-9864-386fed83a88c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "features = df[['N', 'P','K','temperature', 'humidity', 'ph', 'rainfall']]\n",
+    "target = df['label']\n",
+    "#features = df[['temperature', 'humidity', 'ph', 'rainfall']]\n",
+    "labels = df['label']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "98bb3aee-2b27-4e84-934c-65426e1d6f0d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "Xtrain, Xtest, Ytrain, Ytest = train_test_split(features,target,test_size = 0.3,random_state =2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "643cb2a4-22b8-4831-8a3b-b09924df8fe7",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<style>#sk-container-id-1 {color: black;background-color: white;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>GaussianNB()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">GaussianNB</label><div class=\"sk-toggleable__content\"><pre>GaussianNB()</pre></div></div></div></div></div>"
+      ],
+      "text/plain": [
+       "GaussianNB()"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "NaiveBayes=GaussianNB()\n",
+    "NaiveBayes.fit(Xtrain,Ytrain)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "a977bbfd-30b2-4ac6-86a8-fbda16112a55",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "predicted_values=NaiveBayes.predict(Xtest)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "fbb637e3-cc3c-4479-8b0f-1077e88d0aae",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Naive Bayes's Accuracy is:  0.9924242424242424\n"
+     ]
+    }
+   ],
+   "source": [
+    "x=metrics.accuracy_score(Ytest,predicted_values)\n",
+    "print(\"Naive Bayes's Accuracy is: \",x)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "518a369d-785b-430e-8525-1b088590a9a6",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "              precision    recall  f1-score   support\n",
+      "\n",
+      "       apple       1.00      1.00      1.00        28\n",
+      "      banana       1.00      1.00      1.00        26\n",
+      "   blackgram       1.00      1.00      1.00        28\n",
+      "    chickpea       1.00      1.00      1.00        29\n",
+      "     coconut       1.00      1.00      1.00        31\n",
+      "      coffee       1.00      1.00      1.00        33\n",
+      "      cotton       1.00      1.00      1.00        31\n",
+      "      grapes       1.00      1.00      1.00        29\n",
+      "        jute       0.89      0.97      0.93        33\n",
+      " kidneybeans       1.00      1.00      1.00        30\n",
+      "      lentil       1.00      1.00      1.00        32\n",
+      "       maize       1.00      1.00      1.00        32\n",
+      "       mango       1.00      1.00      1.00        33\n",
+      "   mothbeans       1.00      1.00      1.00        29\n",
+      "    mungbean       1.00      1.00      1.00        32\n",
+      "   muskmelon       1.00      1.00      1.00        30\n",
+      "      orange       1.00      1.00      1.00        42\n",
+      "      papaya       1.00      1.00      1.00        30\n",
+      "  pigeonpeas       1.00      1.00      1.00        31\n",
+      " pomegranate       1.00      1.00      1.00        19\n",
+      "        rice       0.96      0.87      0.91        30\n",
+      "  watermelon       1.00      1.00      1.00        22\n",
+      "\n",
+      "    accuracy                           0.99       660\n",
+      "   macro avg       0.99      0.99      0.99       660\n",
+      "weighted avg       0.99      0.99      0.99       660\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(classification_report(Ytest,predicted_values))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "341b0753-d59b-48cf-b53f-1907fd1733cf",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([0.99772727, 0.99545455, 0.99545455, 0.99545455, 0.99090909])"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Cross validation score (NaiveBayes)\n",
+    "score = cross_val_score(NaiveBayes,features,target,cv=5)\n",
+    "score"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "9ef017fb-6420-47e6-98b2-b5c17fd46134",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0.9950000000000001\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(score.mean())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "ff557e0b-96a4-45c6-9ef4-76c115018456",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Predicted Crop Label: jute\n",
+      "Predicted Crop Label: mothbeans\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "C:\\Users\\kanch\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\sklearn\\base.py:439: UserWarning: X does not have valid feature names, but GaussianNB was fitted with feature names\n",
+      "  warnings.warn(\n",
+      "C:\\Users\\kanch\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\site-packages\\sklearn\\base.py:439: UserWarning: X does not have valid feature names, but GaussianNB was fitted with feature names\n",
+      "  warnings.warn(\n"
+     ]
+    }
+   ],
+   "source": [
+    "def predict_crop_label(input_features):\n",
+    "    \n",
+    "    \n",
+    "    input_features = np.array(input_features).reshape(1, -1) \n",
+    "    \n",
+    "    # Predict the crop label using the LogReg model\n",
+    "    predicted_label = NaiveBayes.predict(input_features)\n",
+    "    \n",
+    "    return predicted_label[0]  # Return the predicted label\n",
+    "\n",
+    "# Example usage:\n",
+    "user_input = [83, 45, 60, 28, 70.3, 7.0, 150.9]  # Example input features (N, P, K, pH, temperature, humidity, rainfall)\n",
+    "predicted_crop_label = predict_crop_label(user_input)\n",
+    "print(\"Predicted Crop Label:\", predicted_crop_label)\n",
+    "\n",
+    "user_input = [83, 45, 60, 28, 3.3, 2.0, 0.9]  # Example input features (N, P, K, pH, temperature, humidity, rainfall)\n",
+    "predicted_crop_label = predict_crop_label(user_input)\n",
+    "print(\"Predicted Crop Label:\", predicted_crop_label)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "97cfcbf6-4635-4b5d-9131-dcf9c2e2ec2a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "nb_train_accuracy = NaiveBayes.score(Xtrain, Ytrain)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "8ec62797-daba-4365-b225-d83e6f5a37cc",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0.9961038961038962\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(nb_train_accuracy)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "72348713-8497-406b-99bb-258a458c3949",
+   "metadata": {},
+   "source": [
+    "### Training Accuracy: 0.9961\n",
+    "### Cross-Validation Accuracy: 0.9950\n",
+    "### Test Accuracy: 0.9924"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2d16a23f-0b9b-42ae-bb72-8f4cecd70a74",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3f13635b-5f36-4bbf-842b-1957cf7dc028",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": "3.11.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}