{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": []
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
}
},
"cells": [
{
"cell_type": "code",
"source": [
"!pip install -U scikit-learn"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "yBUpTF0liOBf",
"outputId": "e71b2db0-5438-400e-891c-53ee35c10e4f"
},
"execution_count": 3,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Requirement already satisfied: scikit-learn in /usr/local/lib/python3.10/dist-packages (1.4.2)\n",
"Requirement already satisfied: numpy>=1.19.5 in /usr/local/lib/python3.10/dist-packages (from scikit-learn) (1.25.2)\n",
"Requirement already satisfied: scipy>=1.6.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn) (1.11.4)\n",
"Requirement already satisfied: joblib>=1.2.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn) (1.4.0)\n",
"Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn) (3.5.0)\n"
]
}
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "QhegGo_LT4a_",
"outputId": "59e8d839-82e5-41ab-ca92-35721dcd69a0"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
" N P K temperature humidity ph rainfall Total_Nutrients \\\n",
"0 90 42 43 20.879744 82.002744 6.502985 202.935536 175 \n",
"1 85 58 41 21.770462 80.319644 7.038096 226.655537 184 \n",
"2 60 55 44 23.004459 82.320763 7.840207 263.964248 159 \n",
"3 74 35 40 26.491096 80.158363 6.980401 242.864034 149 \n",
"4 78 42 42 20.130175 81.604873 7.628473 262.717340 162 \n",
"\n",
" Temperature_Humidity Log_Rainfall Label Label_Encoded \n",
"0 1712.196283 5.317804 wheat 0 \n",
"1 1748.595734 5.427834 wheat 0 \n",
"2 1893.744627 5.579595 wheat 0 \n",
"3 2123.482908 5.496611 wheat 0 \n",
"4 1642.720357 5.574878 wheat 0 \n",
"<class 'pandas.core.frame.DataFrame'>\n",
"RangeIndex: 2200 entries, 0 to 2199\n",
"Data columns (total 12 columns):\n",
" # Column Non-Null Count Dtype \n",
"--- ------ -------------- ----- \n",
" 0 N 2200 non-null int64 \n",
" 1 P 2200 non-null int64 \n",
" 2 K 2200 non-null int64 \n",
" 3 temperature 2200 non-null float64\n",
" 4 humidity 2200 non-null float64\n",
" 5 ph 2200 non-null float64\n",
" 6 rainfall 2200 non-null float64\n",
" 7 Total_Nutrients 2200 non-null int64 \n",
" 8 Temperature_Humidity 2200 non-null float64\n",
" 9 Log_Rainfall 2200 non-null float64\n",
" 10 Label 2200 non-null object \n",
" 11 Label_Encoded 2200 non-null int64 \n",
"dtypes: float64(6), int64(5), object(1)\n",
"memory usage: 206.4+ KB\n",
"None\n"
]
}
],
"source": [
"import pandas as pd\n",
"\n",
"# Load the dataset\n",
"data = pd.read_csv('/content/Crop_Dataset.csv')\n",
"\n",
"# Display the first few rows and the data info\n",
"print(data.head())\n",
"print(data.info())\n"
]
},
{
"cell_type": "code",
"source": [
"from sklearn.preprocessing import LabelEncoder, StandardScaler\n",
"\n",
"# Assuming 'Label' is the column with categorical data\n",
"if data['Label'].dtype == 'object':\n",
" encoder = LabelEncoder()\n",
" data['Label_Encoded'] = encoder.fit_transform(data['Label'])\n",
" y = data['Label_Encoded']\n",
"else:\n",
" y = data['Label']\n",
"\n",
"# Exclude the label column from numeric operations\n",
"numeric_features = data.select_dtypes(include=['int64', 'float64'])\n",
"X = numeric_features.drop(['Label_Encoded'], axis=1, errors='ignore')\n",
"\n",
"# Scaling numeric features\n",
"scaler = StandardScaler()\n",
"X_scaled = scaler.fit_transform(X)"
],
"metadata": {
"id": "8YDm7cLGVAdC"
},
"execution_count": 5,
"outputs": []
},
{
"cell_type": "code",
"source": [
"print(X.head())"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "bxlFqxemUwVN",
"outputId": "8b0006fe-4fe9-4b98-8d8f-f66bdb4c9b0e"
},
"execution_count": 6,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
" N P K temperature humidity ph rainfall Total_Nutrients \\\n",
"0 90 42 43 20.879744 82.002744 6.502985 202.935536 175 \n",
"1 85 58 41 21.770462 80.319644 7.038096 226.655537 184 \n",
"2 60 55 44 23.004459 82.320763 7.840207 263.964248 159 \n",
"3 74 35 40 26.491096 80.158363 6.980401 242.864034 149 \n",
"4 78 42 42 20.130175 81.604873 7.628473 262.717340 162 \n",
"\n",
" Temperature_Humidity Log_Rainfall \n",
"0 1712.196283 5.317804 \n",
"1 1748.595734 5.427834 \n",
"2 1893.744627 5.579595 \n",
"3 2123.482908 5.496611 \n",
"4 1642.720357 5.574878 \n"
]
}
]
},
{
"cell_type": "code",
"source": [
"print(y.head())\n"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "Xfyef1ZHVlv9",
"outputId": "1124a98a-7088-4beb-c99f-fc99695bce26"
},
"execution_count": 7,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"0 21\n",
"1 21\n",
"2 21\n",
"3 21\n",
"4 21\n",
"Name: Label_Encoded, dtype: int64\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"from sklearn.model_selection import train_test_split\n",
"\n",
"# Split the dataset into training and testing sets\n",
"X_train, X_test, y_train, y_test = train_test_split(X_scaled, y, test_size=0.2, random_state=42)\n",
"X_train, X_test, y_train, y_test\n"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "qeet3FQuWMYa",
"outputId": "3134ee1c-da4a-49c9-b23a-a2824087bce7"
},
"execution_count": 8,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"(array([[-0.90904306, -1.13294593, -0.67439784, ..., -1.31493084,\n",
" -0.49027085, 0.24780902],\n",
" [-0.36716896, 0.77739624, -0.57565467, ..., -0.21356106,\n",
" 0.07991257, -0.46657409],\n",
" [-1.17998011, 0.59545889, -0.45716288, ..., -0.58902803,\n",
" -0.16692839, -1.2389468 ],\n",
" ...,\n",
" [-1.07160529, -0.5264881 , -0.33867109, ..., -0.9269483 ,\n",
" -0.5842483 , 0.199803 ],\n",
" [-1.07160529, 2.14192637, 3.07784228, ..., 2.33961433,\n",
" -1.1140468 , -0.41541788],\n",
" [-0.50263749, 0.74707335, -0.51640878, ..., -0.25110776,\n",
" -0.51417889, -0.93933906]]),\n",
" array([[ 1.36682815, -1.10262304, -0.02269297, ..., 0.16190591,\n",
" 1.34399451, -2.20354942],\n",
" [ 1.28554704, -1.37552907, 0.05630155, ..., 0.06178138,\n",
" 0.58762688, -1.07859766],\n",
" [ 0.22889255, 0.26190709, 0.01680429, ..., 0.22448374,\n",
" 3.13720326, 0.44554626],\n",
" ...,\n",
" [ 1.90870225, -0.19293629, -0.63490057, ..., 0.39970166,\n",
" 0.02516414, -0.38782438],\n",
" [ 1.77323373, -0.04132183, -0.57565467, ..., 0.43724835,\n",
" -0.17876826, -0.5282515 ],\n",
" [-1.23416752, 0.44384444, -0.55590604, ..., -0.73921482,\n",
" -1.75019501, 0.99674145]]),\n",
" 1656 4\n",
" 752 2\n",
" 892 12\n",
" 1041 7\n",
" 1179 3\n",
" ..\n",
" 1638 4\n",
" 1095 7\n",
" 1130 3\n",
" 1294 9\n",
" 860 12\n",
" Name: Label_Encoded, Length: 1760, dtype: int64,\n",
" 1451 16\n",
" 1334 13\n",
" 1761 18\n",
" 1735 18\n",
" 1576 11\n",
" ..\n",
" 59 21\n",
" 71 21\n",
" 1908 14\n",
" 1958 14\n",
" 482 8\n",
" Name: Label_Encoded, Length: 440, dtype: int64)"
]
},
"metadata": {},
"execution_count": 8
}
]
},
{
"cell_type": "code",
"source": [
"from sklearn.tree import DecisionTreeClassifier\n",
"from sklearn.ensemble import RandomForestClassifier, GradientBoostingClassifier\n",
"from sklearn.svm import SVC\n",
"from sklearn.neighbors import KNeighborsClassifier\n",
"from sklearn.metrics import accuracy_score\n",
"import joblib\n",
"\n",
"\n",
"# Define the models\n",
"models = {\n",
" 'Decision Tree': DecisionTreeClassifier(random_state=42),\n",
" 'Random Forest': RandomForestClassifier(random_state=42),\n",
" 'SVM': SVC(kernel='rbf', random_state=42),\n",
" 'KNN': KNeighborsClassifier(),\n",
" 'Gradient Boosting': GradientBoostingClassifier(random_state=42)\n",
"}\n",
"\n",
"# Train each model and evaluate on the training set\n",
"train_accuracies = {}\n",
"for name, model in models.items():\n",
" model.fit(X_train, y_train)\n",
" y_train_pred = model.predict(X_train)\n",
" train_accuracy = accuracy_score(y_train, y_train_pred)\n",
" train_accuracies[name] = train_accuracy\n",
" print(f\"{name} training accuracy: {train_accuracy:.4f}\")\n",
"\n",
" # Save the model\n",
" model_filename = f'{name.replace(\" \", \"_\").lower()}_model.joblib'\n",
" joblib.dump(model, model_filename)\n",
" print(f\"Saved {name} model as {model_filename}\")\n"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "TsmaeAEYbj6Y",
"outputId": "0b6e493c-9421-4d88-8e97-0591713968e3"
},
"execution_count": 9,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Decision Tree training accuracy: 1.0000\n",
"Saved Decision Tree model as decision_tree_model.joblib\n",
"Random Forest training accuracy: 1.0000\n",
"Saved Random Forest model as random_forest_model.joblib\n",
"SVM training accuracy: 0.9875\n",
"Saved SVM model as svm_model.joblib\n",
"KNN training accuracy: 0.9881\n",
"Saved KNN model as knn_model.joblib\n",
"Gradient Boosting training accuracy: 1.0000\n",
"Saved Gradient Boosting model as gradient_boosting_model.joblib\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"# Example new data for prediction\n",
"new_data = [[129,\t43,\t16, 25.5503704,\t77.85055621,\t6.73210948,\t78.58488484,\t188,\t1989.110547,\t4.376824186]] # Adjust these values as necessary\n",
"new_data_scaled = scaler.transform(new_data) # Assuming 'scaler' is already fitted and saved/loaded similarly\n",
"\n",
"# Load models and make predictions\n",
"predictions = {}\n",
"for name in models.keys():\n",
" model_filename = f'{name.replace(\" \", \"_\").lower()}_model.joblib'\n",
" loaded_model = joblib.load(model_filename)\n",
" prediction = loaded_model.predict(new_data_scaled)\n",
" predictions[name] = prediction\n",
"\n",
" # Assuming you have loaded your LabelEncoder as 'encoder'\n",
" decoded_prediction = encoder.inverse_transform(prediction)\n",
" print(f\"{name} prediction: {decoded_prediction}\")\n"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "448K06w7cT6d",
"outputId": "9263c1d3-228a-4e45-95c0-87b5d2f7c0b9"
},
"execution_count": 10,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Decision Tree prediction: ['potatoes']\n",
"Random Forest prediction: ['potatoes']\n",
"SVM prediction: ['potatoes']\n",
"KNN prediction: ['potatoes']\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"/usr/local/lib/python3.10/dist-packages/sklearn/base.py:493: UserWarning: X does not have valid feature names, but StandardScaler was fitted with feature names\n",
" warnings.warn(\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"Gradient Boosting prediction: ['potatoes']\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"# Save the scaler to a file\n",
"joblib.dump(scaler, 'base_feature_scaler.joblib')"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "ByINvSM1gSHN",
"outputId": "6bbfe644-762c-4502-a07d-05dbcf26fd4b"
},
"execution_count": 11,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"['base_feature_scaler.joblib']"
]
},
"metadata": {},
"execution_count": 11
}
]
},
{
"cell_type": "code",
"source": [
"# Save the LabelEncoder to a file\n",
"joblib.dump(encoder, 'label_encoder.joblib')"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "c9Uu7lsPgSk7",
"outputId": "d3bade81-25b7-47a6-e9c0-c14d2ea39339"
},
"execution_count": 12,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"['label_encoder.joblib']"
]
},
"metadata": {},
"execution_count": 12
}
]
}
]
}