Upload 3 files

app.py

@@ -0,0 +1,39 @@
+import streamlit as st
+import joblib
+import pandas as pd
+
+model = joblib.load('selector.h5')
+
+prices = pd.read_csv("crop_prices.csv")
+
+st.title("Crop Selection App")
+
+st.header("Input Soil Data:")
+nitrogen = st.number_input("Nitrogen", min_value=0, max_value=100, value=50)
+phosphorus = st.number_input("Phosphorus", min_value=0, max_value=100, value=50)
+potassium = st.number_input("Potassium", min_value=0, max_value=100, value=50)
+temperature = st.number_input("Temperature", min_value=0.0, max_value=100.0, value=25.0,step=1.,format="%.4f")
+humidity = st.number_input("Humidity", min_value=0.0, max_value=100.0, value=50.0,step=1.,format="%.4f")
+ph = st.number_input("pH", min_value=0.0, max_value=14.0, value=7.0,step=1.,format="%.4f")
+rainfall = st.number_input("Rainfall", min_value=0.0, max_value=1000.0, value=500.0,step=1.,format="%.4f")
+
+user_input = [[nitrogen, phosphorus, potassium, temperature, humidity, ph, rainfall]]
+
+if st.button("Predict"):
+    predicted_crop = model.predict_proba(user_input)
+
+    crop_probabilities = list(zip(model.classes_, predicted_crop[0]))
+
+    # Sort crops based on probability estimates
+    sorted_crops = sorted(crop_probabilities, key=lambda x: x[1], reverse=True)
+
+    # Display the sorted crops
+    st.header("Top 3 Crops to grow:")
+    for i, (crop, probability) in enumerate(sorted_crops[:3]):
+        prob_percent = probability*100
+        #st.write(f"{i+1}. {crop}: {prob_percent:.2f}%")
+        average_price = prices.loc[prices['CROP'] == crop, 'AVG PRICES'].values[0]
+        
+        st.write(f"{i+1}. {crop}: {prob_percent:.2f}% || Average Price: Rs.{average_price} / Quintal")
+
+st.text("Created by Analytical Aces")

selector.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7feea986c37dd5b44b1149825352a28c2843a761e2893b65f75227e95555ed70
+size 4887

selector.ipynb

@@ -0,0 +1,212 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['selector.h5']"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "import streamlit as st\n",
+    "from sklearn.naive_bayes import GaussianNB\n",
+    "import joblib\n",
+    "\n",
+    "prices = pd.read_csv(r\"C:\\Users\\Kush\\Desktop\\hackathons\\IITB\\crop_selector\\crop_prices.csv\")\n",
+    "dataset = pd.read_csv(r\"C:\\Users\\Kush\\Desktop\\hackathons\\IITB\\crop_selector\\Crop_selection.csv\")\n",
+    "\n",
+    "features = dataset[['N', 'P', 'K', 'temperature', 'humidity', 'ph', 'rainfall']]\n",
+    "target = dataset['label']\n",
+    "\n",
+    "model = GaussianNB()\n",
+    "model.fit(features, target)\n",
+    "\n",
+    "joblib.dump(model, 'selector.h5')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Overwriting app.py\n"
+     ]
+    }
+   ],
+   "source": [
+    "%%writefile app.py\n",
+    "import streamlit as st\n",
+    "\n",
+    "model = joblib.load('selector.h5')\n",
+    "\n",
+    "st.title(\"Crop Selection App\")\n",
+    "\n",
+    "st.header(\"Input Soil Data:\")\n",
+    "nitrogen = st.number_input(\"Nitrogen\", min_value=0, max_value=100, value=50)\n",
+    "phosphorus = st.number_input(\"Phosphorus\", min_value=0, max_value=100, value=50)\n",
+    "potassium = st.number_input(\"Potassium\", min_value=0, max_value=100, value=50)\n",
+    "temperature = st.number_input(\"Temperature\", min_value=0.0, max_value=100.0, value=25.0,step=1.,format=\"%.4f\")\n",
+    "humidity = st.number_input(\"Humidity\", min_value=0.0, max_value=100.0, value=50.0,step=1.,format=\"%.4f\")\n",
+    "ph = st.number_input(\"pH\", min_value=0.0, max_value=14.0, value=7.0,step=1.,format=\"%.4f\")\n",
+    "rainfall = st.number_input(\"Rainfall\", min_value=0.0, max_value=1000.0, value=500.0,step=1.,format=\"%.4f\")\n",
+    "\n",
+    "user_input = [[nitrogen, phosphorus, potassium, temperature, humidity, ph, rainfall]]\n",
+    "\n",
+    "if st.button(\"Predict\"):\n",
+    "    predicted_crop = model.predict_proba(user_input)\n",
+    "\n",
+    "    crop_probabilities = list(zip(model.classes_, predicted_crop[0]))\n",
+    "\n",
+    "    # Sort crops based on probability estimates\n",
+    "    sorted_crops = sorted(crop_probabilities, key=lambda x: x[1], reverse=True)\n",
+    "\n",
+    "    # Display the sorted crops\n",
+    "    st.header(\"Top 3 Crops to grow:\")\n",
+    "    for i, (crop, probability) in enumerate(sorted_crops[:3]):\n",
+    "        prob_percent = probability*100\n",
+    "        #st.write(f\"{i+1}. {crop}: {prob_percent:.2f}%\")\n",
+    "        average_price = prices.loc[prices['CROP'] == crop, 'AVG PRICES'].values[0]\n",
+    "        \n",
+    "        st.write(f\"{i+1}. {crop}: {prob_percent:.2f}% || Average Price: Rs.{average_price} / Quintal\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%%writefile app.py\n",
+    "import streamlit as st\n",
+    "import pandas as pd\n",
+    "import joblib\n",
+    "from sklearn.preprocessing import LabelEncoder\n",
+    "\n",
+    "# Load the saved model\n",
+    "best_rf_classifier = joblib.load('moal.h5')\n",
+    "\n",
+    "# Load the label encoder\n",
+    "label_encoder = LabelEncoder()\n",
+    "\n",
+    "# Streamlit App\n",
+    "st.title(\"Loan Approval Prediction App\")\n",
+    "\n",
+    "# Sidebar\n",
+    "st.sidebar.header(\"User Input\")\n",
+    "\n",
+    "# Gender\n",
+    "gender_options = ['Male', 'Female']\n",
+    "gender = st.sidebar.radio(\"Gender\", gender_options)\n",
+    "\n",
+    "# Married\n",
+    "married_options = ['Yes', 'No']\n",
+    "married = st.sidebar.radio(\"Marital Status\", married_options)\n",
+    "\n",
+    "# Dependents\n",
+    "dependents = st.sidebar.selectbox(\"Number of Dependents\", ['0', '1', '2', '3+'])\n",
+    "\n",
+    "# Applicant Income\n",
+    "applicant_income = st.sidebar.number_input(\"Applicant Income\", min_value=0)\n",
+    "\n",
+    "# Coapplicant Income\n",
+    "coapplicant_income = st.sidebar.number_input(\"Coapplicant Income\", min_value=0)\n",
+    "\n",
+    "# Loan Amount\n",
+    "loan_amount = st.sidebar.number_input(\"Loan Amount\", min_value=0)\n",
+    "\n",
+    "# Loan Amount Term\n",
+    "loan_amount_term = st.sidebar.number_input(\"Loan Amount Term\", min_value=0)\n",
+    "\n",
+    "# Land Area\n",
+    "land_area = st.sidebar.number_input(\"Land Area\", min_value=0.0)\n",
+    "\n",
+    "# Crop Type\n",
+    "crop_type_options = ['rabi', 'kharif']\n",
+    "crop_type = st.sidebar.radio(\"Crop Type\", crop_type_options)\n",
+    "\n",
+    "# Land Type\n",
+    "land_type_options = ['irrigated', 'rainfed']\n",
+    "land_type = st.sidebar.radio(\"Land Type\", land_type_options)\n",
+    "\n",
+    "# Irrigation Type\n",
+    "irrigation_type_options = ['drip', 'rainfed', 'sprinkle', 'borewell']\n",
+    "irrigation_type = st.sidebar.selectbox(\"Irrigation Type\", irrigation_type_options)\n",
+    "\n",
+    "# Combine user inputs into a DataFrame\n",
+    "user_inputs = pd.DataFrame({\n",
+    "    'Gender': [gender],\n",
+    "    'Married': [married],\n",
+    "    'Dependents': [dependents],\n",
+    "    'ApplicantIncome': [applicant_income],\n",
+    "    'CoapplicantIncome': [coapplicant_income],\n",
+    "    'LoanAmount': [loan_amount],\n",
+    "    'Loan_Amount_Term': [loan_amount_term],\n",
+    "    'land_area': [land_area],\n",
+    "    'crop_type': [crop_type],\n",
+    "    'land_type': [land_type],\n",
+    "    'irrigation_type': [irrigation_type]\n",
+    "})\n",
+    "\n",
+    "# Encode categorical variables\n",
+    "user_inputs['Gender'] = label_encoder.fit_transform(user_inputs['Gender'])\n",
+    "user_inputs['Married'] = label_encoder.fit_transform(user_inputs['Married'])\n",
+    "user_inputs['crop_type'] = label_encoder.fit_transform(user_inputs['crop_type'])\n",
+    "user_inputs['land_type'] = label_encoder.fit_transform(user_inputs['land_type'])\n",
+    "user_inputs['irrigation_type'] = label_encoder.fit_transform(user_inputs['irrigation_type'])\n",
+    "\n",
+    "# Handle '3+' in 'Dependents' column\n",
+    "user_inputs['Dependents'] = user_inputs['Dependents'].replace('3+', 3)\n",
+    "\n",
+    "if st.sidebar.button(\"Predict\"):\n",
+    "    # Make prediction\n",
+    "    prediction = best_rf_classifier.predict(user_inputs)\n",
+    "\n",
+    "    # Interpret the predicted value directly for binary classification\n",
+    "    predicted_loan_status = \"Approved\" if prediction[0] == 1 else \"Not Approved\"\n",
+    "\n",
+    "    # Display prediction\n",
+    "    st.subheader(\"Prediction Result\")\n",
+    "    st.write(f\"The predicted loan status is: {predicted_loan_status}\")\n",
+    "\n",
+    "\n",
+    "# Credits\n",
+    "st.sidebar.text(\"Created by Analytical Aces\")\n"
+   ]
+  }
+ ],
+ "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": "3.10.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}