Upload 5 files

app.py

@@ -0,0 +1,106 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+import joblib
+
+# Load the trained model
+model_path = 'random_forest_regressor_model.pkl'
+model = joblib.load(model_path)
+
+# Encoding mappings
+rainfall_mapping = {'moderate': 2, 'low': 1, 'high': 0}
+soil_type_mapping = {'sandy': 3, 'silty': 4, 'clay': 0, 'peaty': 2, 'loamy': 1}
+drainage_mapping = {'poor': 2, 'moderate': 1, 'good': 0}
+crop_mapping = {'rice': 2, 'wheat': 4, 'soybean': 3, 'cotton': 0, 'maize': 1}
+growth_stage_mapping = {'flowering': 0, 'fruiting': 1, 'vegetative': 5, 'seedling': 4, 'reproductive': 3, 'maturity': 2}
+
+# Function to preprocess user inputs
+def preprocess_input(data):
+    data['rainfall_pattern'] = rainfall_mapping[data['rainfall_pattern']]
+    data['soil_type'] = soil_type_mapping[data['soil_type']]
+    data['drainage_properties'] = drainage_mapping[data['drainage_properties']]
+    data['crop_type'] = crop_mapping[data['crop_type']]
+    data['growth_stage'] = growth_stage_mapping[data['growth_stage']]
+    return np.array(list(data.values())).reshape(1, -1)
+
+# Streamlit App
+st.title("Optimal Water Requirement Prediction for Agricultural Farms")
+st.write("This application predicts the optimal water requirement for different crops based on environmental and soil properties.")
+
+# User Inputs
+st.sidebar.header("Input Features")
+
+# Numerical inputs
+temperature = st.sidebar.slider("Temperature (°C):", min_value=-10.0, max_value=50.0, value=25.0, step=0.1)
+humidity = st.sidebar.slider("Humidity (%):", min_value=0.0, max_value=100.0, value=50.0, step=0.1)
+wind_speed = st.sidebar.slider("Wind Speed (m/s):", min_value=0.0, max_value=20.0, value=5.0, step=0.1)
+evapotranspiration = st.sidebar.slider("Evapotranspiration (mm/day):", min_value=0.0, max_value=10.0, value=3.0, step=0.1)
+soil_moisture_levels = st.sidebar.slider("Soil Moisture Levels (%):", min_value=0.0, max_value=100.0, value=50.0, step=0.1)
+water_retention_capacity = st.sidebar.slider("Water Retention Capacity (%):", min_value=0.0, max_value=100.0, value=60.0, step=0.1)
+crop_water_requirement = st.sidebar.slider("Actual Water Requirement (mm/day)):", min_value=0.0, max_value=25.0, value=10.0, step=0.1)
+
+# Categorical inputs
+rainfall_pattern = st.sidebar.selectbox("Rainfall Pattern:", list(rainfall_mapping.keys()))
+soil_type = st.sidebar.selectbox("Soil Type:", list(soil_type_mapping.keys()))
+drainage_properties = st.sidebar.selectbox("Drainage Properties:", list(drainage_mapping.keys()))
+crop_type = st.sidebar.selectbox("Crop Type:", list(crop_mapping.keys()))
+growth_stage = st.sidebar.selectbox("Growth Stage:", list(growth_stage_mapping.keys()))
+
+# Prediction
+if st.sidebar.button("Predict Water Requirement"):
+    input_data = {
+        'temperature': temperature,
+        'humidity': humidity,
+        'wind_speed': wind_speed,
+        'evapotranspiration': evapotranspiration,
+        'soil_moisture_levels': soil_moisture_levels,
+        'water_retention_capacity': water_retention_capacity,
+        'rainfall_pattern': rainfall_pattern,
+        'soil_type': soil_type,
+        'drainage_properties': drainage_properties,
+        'crop_type': crop_type,
+        'growth_stage': growth_stage,
+        'crop_water_requirement':crop_water_requirement
+    }
+    processed_data = preprocess_input(input_data)
+    prediction = model.predict(processed_data)[0]
+
+
+    st.write("### Predicted Water Requirement")
+    st.success(f"The predicted water requirement is **{prediction:.2f} mm/day**.")
+
+    st.header("Optimization Suggestions")
+
+    suggestions = []
+
+    # Check soil type
+    if soil_type == "Sandy":
+        suggestions.append("Consider improving soil structure by adding organic matter or compost to enhance water retention.")
+
+    # Check evapotranspiration
+    if evapotranspiration > 8.0:
+        suggestions.append("High evapotranspiration detected. Use mulching to reduce evaporation and conserve soil moisture.")
+
+    # Check soil moisture
+    if soil_moisture_levels < 15.0:
+        suggestions.append("Low soil moisture detected. Ensure proper irrigation scheduling to maintain adequate levels.")
+
+    # Check water retention
+    if water_retention_capacity < 20.0:
+        suggestions.append("Low water retention capacity. Incorporate soil amendments to improve retention.")
+
+    # Check drainage
+    if drainage_properties=='good':
+        suggestions.append("Poor drainage detected. Improve soil aeration or use soil conditioners to balance drainage.")
+
+    # Display suggestions
+    if suggestions:
+        for suggestion in suggestions:
+            st.write(f"- {suggestion}")
+    else:
+        st.write("✅ All parameters are well-balanced for optimal water usage!")
+
+
+# Footer
+st.write("---")
+#st.write("Developed with ❤️ using Streamlit")

main.py

@@ -0,0 +1,53 @@
+#import libraries
+import pandas as pd
+import numpy as np
+import joblib
+import warnings
+warnings.filterwarnings('ignore')
+from sklearn.model_selection import train_test_split, GridSearchCV
+from sklearn.ensemble import RandomForestRegressor
+from sklearn.metrics import mean_squared_error, r2_score
+#importing the dataset
+df= pd.read_csv('clean_water_requirement_data.csv')
+print(df.shape)
+
+#finding the categorical and numerical columns
+categorical_columns = df.select_dtypes(include=['object', 'category']).columns
+numerical_columns = df.select_dtypes(include=['float64', 'int64']).columns
+
+#encoding the categorical variables
+from sklearn.preprocessing import LabelEncoder
+label_encoder = LabelEncoder()
+for col in categorical_columns:
+    df[col] = label_encoder.fit_transform(df[col])
+
+#separating input and target features in dataset
+X = df.drop(columns=['water_requirement']) 
+y=df.iloc[:,-1]
+
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+from sklearn.preprocessing import StandardScaler
+
+# Apply StandardScaler
+scaler = StandardScaler()
+X_train = scaler.fit_transform(X_train)
+X_test = scaler.transform(X_test)
+
+# Initialize the model with the provided best parameters
+model = RandomForestRegressor(max_depth=20, n_estimators=200, random_state=42)
+
+# Fit the model
+model.fit(X_train, y_train)
+
+# Predictions
+y_pred = model.predict(X_test)
+
+# Calculate performance metrics
+mse = mean_squared_error(y_test, y_pred)
+mae = mean_absolute_error(y_test, y_pred)
+r2 = r2_score(y_test, y_pred)
+
+# Save the model as a .pkl file using joblib
+model_filename = 'random_forest_regressor_model.pkl'
+joblib.dump(model, model_filename)

requirements.txt

@@ -0,0 +1,9 @@
+streamlit
+pandas
+numpy
+joblib
+pandas
+numpy
+joblib
+warnings
+sklearn