Create app.py

app.py

@@ -0,0 +1,87 @@
+import pandas as pd
+import numpy as np
+from sklearn.preprocessing import StandardScaler, LabelEncoder
+from sklearn.model_selection import train_test_split
+from sklearn.ensemble import RandomForestRegressor
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import gradio as gr
+
+# -------------------------------
+# 1. Load and Preprocess Data
+# -------------------------------
+file_path = "path_to_your_csv_file.csv"  # Replace with your actual file path
+df = pd.read_csv(file_path)
+
+# Handle Categorical Columns
+label_encoders = {}
+for col in ['Seed_Variety', 'Irrigation_Schedule']:
+    label_encoders[col] = LabelEncoder()
+    df[col] = label_encoders[col].fit_transform(df[col])
+
+# Normalize Numerical Columns
+scaler = StandardScaler()
+numerical_cols = ['Soil_Quality', 'Fertilizer_Amount_kg_per_hectare', 'Sunny_Days', 'Rainfall_mm']
+df[numerical_cols] = scaler.fit_transform(df[numerical_cols])
+
+# Split Dataset
+X = df.drop(columns=['Yield_kg_per_hectare'])
+y = df['Yield_kg_per_hectare']
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+# -------------------------------
+# 2. Train Model
+# -------------------------------
+model = RandomForestRegressor(n_estimators=100, random_state=42)
+model.fit(X_train, y_train)
+
+# -------------------------------
+# 3. Prediction Function
+# -------------------------------
+def predict_yield(soil_quality, seed_variety, fertilizer_amount, sunny_days, rainfall, irrigation_schedule):
+    # Preprocess Inputs
+    input_data = pd.DataFrame({
+        'Soil_Quality': [soil_quality],
+        'Seed_Variety': [label_encoders['Seed_Variety'].transform([seed_variety])[0]],
+        'Fertilizer_Amount_kg_per_hectare': [fertilizer_amount],
+        'Sunny_Days': [sunny_days],
+        'Rainfall_mm': [rainfall],
+        'Irrigation_Schedule': [label_encoders['Irrigation_Schedule'].transform([irrigation_schedule])[0]],
+    })
+    input_data[numerical_cols] = scaler.transform(input_data[numerical_cols])
+    
+    # Prediction
+    predicted_yield = model.predict(input_data)[0]
+    
+    # Insights (Static Example)
+    insight = (
+        f"To optimize yield, maintain fertilizer levels around {fertilizer_amount * 1.1:.2f} kg/hectare "
+        f"and ensure consistent irrigation on {irrigation_schedule} schedule."
+    )
+    
+    return f"""
+- **Predicted Yield:** {predicted_yield:.2f} kg/hectare  
+- **Optimal Fertilizer Usage:** {fertilizer_amount * 1.1:.2f} kg/hectare  
+- **Insight:** {insight}
+"""
+
+# -------------------------------
+# 4. User Interface (Gradio)
+# -------------------------------
+interface = gr.Interface(
+    fn=predict_yield,
+    inputs=[
+        gr.Number(label="Soil Quality (0-1 normalized)"),
+        gr.Textbox(label="Seed Variety"),
+        gr.Number(label="Fertilizer Amount (kg/hectare)"),
+        gr.Number(label="Sunny Days"),
+        gr.Number(label="Rainfall (mm)"),
+        gr.Textbox(label="Irrigation Schedule"),
+    ],
+    outputs="text",
+    title="Crop Yield Prediction App",
+    description="Enter crop parameters to predict yield and get professional agricultural insights."
+)
+
+# Launch App
+if __name__ == "__main__":
+    interface.launch()