Update app.py

app.py

@@ -1,14 +1,13 @@
-import streamlit as st
+import gradio as gr
 import pandas as pd
 import numpy as np
 import matplotlib.pyplot as plt
-import seaborn as sns
 from sklearn.preprocessing import MinMaxScaler
 from tensorflow.keras.models import Sequential
 from tensorflow.keras.layers import LSTM, Dense, Dropout
 
 # Load the dataset
-df = pd.read_csv("/content/TEMP_ANNUAL_SEASONAL_MEAN.csv")
+df = pd.read_csv("TEMP_ANNUAL_SEASONAL_MEAN.csv")  # Ensure file is in the repo
 
 # Convert 'YEAR' column to datetime
 df.columns = df.columns.str.upper()  # Ensure column names are uppercase
@@ -55,20 +54,33 @@ model.compile(optimizer='adam', loss='mse')
 # Train the model
 model.fit(X_train, y_train, epochs=50, batch_size=8, validation_data=(X_test, y_test))
 
-# Make predictions
-predictions = model.predict(X_test)
-predictions = scaler.inverse_transform(predictions)  # Convert back to original scale
+# Function to predict temperature
+def predict_temperature(year):
+    try:
+        last_10_years = data_scaled[-sequence_length:]  # Take last 10 years of data
+        last_10_years = last_10_years.reshape(1, sequence_length, 1)
 
-# Streamlit UI
-st.title("India Climate Change Forecast")
+        pred_scaled = model.predict(last_10_years)
+        pred_temp = scaler.inverse_transform(pred_scaled)[0][0]
 
-st.write("### Actual vs Predicted Annual Mean Temperature")
+        # Plot actual vs predicted
+        fig, ax = plt.subplots(figsize=(8, 4))
+        ax.plot(df.index[-len(y_test):], scaler.inverse_transform(y_test.reshape(-1, 1)), label="Actual")
+        ax.plot(df.index[-len(y_test):], scaler.inverse_transform(model.predict(X_test)), label="Predicted", linestyle='dashed')
+        ax.set_xlabel("Year")
+        ax.set_ylabel("Temperature (°C)")
+        ax.set_title("Actual vs Predicted Annual Mean Temperature")
+        ax.legend()
+        
+        return pred_temp, fig
+    except Exception as e:
+        return f"Error: {str(e)}"
 
-fig, ax = plt.subplots(figsize=(12, 6))
-ax.plot(df.index[-len(y_test):], scaler.inverse_transform(y_test.reshape(-1, 1)), label="Actual")
-ax.plot(df.index[-len(y_test):], predictions, label="Predicted", linestyle='dashed')
-ax.set_xlabel("Year")
-ax.set_ylabel("Temperature (°C)")
-ax.set_title("Actual vs Predicted Annual Mean Temperature in India")
-ax.legend()
-st.pyplot(fig)
+# Gradio Interface
+iface = gr.Interface(
+    fn=predict_temperature,
+    inputs=gr.Number(label="Enter Year (e.g., 2027)"),
+    outputs=[gr.Textbox(label="Predicted Temperature (°C)"), gr.Plot(label="Actual vs Predicted")]
+)
+
+iface.launch()