Sync App files

app.py

@@ -4,6 +4,7 @@ import matplotlib.pyplot as plt
 import numpy as np
 import pandas as pd
 import skops.io as sio
+from io import BytesIO
 
 
 class StockPredictor:
@@ -92,7 +93,10 @@ class StockPredictor:
         # Sort by date
         data.sort_values("date", inplace=True)
 
-        # Feature engineering: create new features such as moving averages
+        # Feature engineering: create new features such as year, month, day, and moving averages
+        data["year"] = data["date"].dt.year
+        data["month"] = data["date"].dt.month
+        data["day"] = data["date"].dt.day
         data["ma_5"] = data["close"].rolling(window=5).mean()
         data["ma_10"] = data["close"].rolling(window=10).mean()
 
@@ -116,55 +120,84 @@ class StockPredictor:
         -------
         tuple
             A tuple containing a DataFrame with dates, actual close values, and predicted close values,
-            and the file path of the generated plot.
+            and the plot as a numpy array.
         """
         model = self.models.get(ticker)
         if model:
             # Load historical stock data
             data = self.load_stock_data(ticker)
 
-            # Take the last 'days' worth of data for prediction
-            data = data.tail(days)
-
             # Define features
-            features = ["open", "high", "low", "ma_5", "ma_10"]
-
-            X = data[features]
+            features = ["year", "month", "day", "ma_5", "ma_10"]
 
-            # Make predictions
-            predictions = model.predict(X)
+            # Use the last available values for features
+            last_date = data["date"].max()
+            next_30_days = pd.date_range(
+                start=last_date + pd.Timedelta(days=1), periods=days
+            )
+            last_values = data[features].iloc[-1].copy()
+            last_5_close = data["close"].iloc[-5:].tolist()
+            last_10_close = data["close"].iloc[-10:].tolist()
+            predictions = []
+
+            for date in next_30_days:
+                last_values["year"] = date.year
+                last_values["month"] = date.month
+                last_values["day"] = date.day
+
+                # Ensure input features are in the correct format
+                prediction_input = pd.DataFrame([last_values], columns=features)
+                prediction = model.predict(prediction_input)[0]
+                predictions.append(prediction)
+
+                # Update the moving averages dynamically
+                last_5_close.append(prediction)
+                last_10_close.append(prediction)
+                if len(last_5_close) > 5:
+                    last_5_close.pop(0)
+                if len(last_10_close) > 10:
+                    last_10_close.pop(0)
+
+                last_values["ma_5"] = np.mean(last_5_close)
+                last_values["ma_10"] = np.mean(last_10_close)
+
+            prediction_df = pd.DataFrame(
+                {"date": next_30_days, "predicted_close": predictions}
+            )
 
-            # Round predictions to 2 decimal places
-            predictions = np.round(predictions, 2)
+            # Concatenate actual and predicted data for plotting
+            actual_df = data[["date", "close"]].iloc[-30:].copy()
+            actual_df.rename(columns={"close": "actual_close"}, inplace=True)
+            plot_data = pd.concat([actual_df, prediction_df], ignore_index=True)
 
-            # Create a DataFrame with dates and predicted close values
-            result_df = pd.DataFrame(
-                {
-                    "date": data["date"],
-                    "actual_close": data["close"],
-                    "predicted_close": predictions,
-                }
+            plt.figure(figsize=(14, 7))
+            plt.plot(
+                plot_data["date"].iloc[:30],
+                plot_data["actual_close"].iloc[:30],
+                label="Actual",
             )
-
-            # Plot the actual and predicted close values
-            plt.figure(figsize=(10, 5))
-            plt.plot(result_df["date"], result_df["actual_close"], label="Actual Close")
             plt.plot(
-                result_df["date"], result_df["predicted_close"], label="Predicted Close"
+                plot_data["date"].iloc[30:],
+                plot_data["predicted_close"].iloc[30:],
+                label="Predicted",
             )
             plt.xlabel("Date")
-            plt.ylabel("Close Price")
-            plt.title(f"{ticker} Stock Price Prediction")
+            plt.ylabel("Stock Price")
+            plt.title(
+                f"Last 30 Days Actual and Next {days} Days Prediction for {ticker}"
+            )
             plt.legend()
             plt.grid(True)
             plt.xticks(rotation=45)
 
-            # Save the plot to a file
-            plot_path = f"{ticker}_prediction_plot.png"
-            plt.savefig(plot_path)
+            # Save the plot to a numpy array
+            buf = BytesIO()
+            plt.savefig(buf, format="png")
+            buf.seek(0)
+            img = np.array(plt.imread(buf))
             plt.close()
 
-            return result_df, plot_path
+            return plot_data, img
         else:
             return pd.DataFrame({"Error": ["Model not found"]}), None
 
@@ -197,7 +230,7 @@ def create_gradio_interface(stock_predictor):
         inputs=[dropdown, slider],
         outputs=[
             gr.DataFrame(headers=["date", "actual_close", "predicted_close"]),
-            gr.Image(),
+            gr.Image(type="numpy"),
         ],
         title="Stock Price Forecasting",
         description="Select a ticker and number of days to forecast stock prices.",