stock_price_predict_basic_v0.1

README .md

@@ -0,0 +1,128 @@
+
+# Real-Time Stock Market Data Prediction API and Flutter App
+
+## Overview
+This project combines a real-time stock market data prediction API built using FastAPI and an accompanying Flutter frontend application. The API processes stock ticker data to predict future stock prices using an LSTM (Long Short-Term Memory) neural network, and the Flutter app provides an interface for users to interact with the API.
+
+## Prerequisites
+
+### Backend (FastAPI)
+- Python 3.7 or higher
+- Conda or virtualenv for environment management
+- FastAPI
+- Uvicorn
+- TensorFlow
+- Scikit-learn
+- yfinance
+
+### Frontend (Flutter)
+- Flutter SDK
+- A text editor or IDE (e.g., Visual Studio Code, Android Studio)
+
+## Setup Instructions
+
+### Backend Setup
+
+1. **Clone the repository:**
+   ```bash
+   git clone <repository_url>
+   cd <repository_name>
+   ```
+
+2. **Create a virtual environment:**
+   - Using Conda:
+     ```bash
+     conda create --name stock-prediction python=3.8
+     conda activate stock-prediction
+     ```
+   - Or using virtualenv:
+     ```bash
+     python3 -m venv env
+     source env/bin/activate  # On Windows use `env\Scriptsctivate`
+     ```
+
+3. **Install dependencies:**
+   ```bash
+   pip install -r requirements.txt
+   ```
+
+4. **Run the API server:**
+   ```bash
+   uvicorn main:app --reload
+   ```
+
+   The API will be available at `http://127.0.0.1:8000/`.
+
+### Frontend Setup
+
+1. **Install Flutter SDK:**
+   Follow the instructions on the official [Flutter installation guide](https://flutter.dev/docs/get-started/install) to set up Flutter on your system.
+
+2. **Create a new Flutter project:**
+   ```bash
+   flutter create stock_prediction_app
+   cd stock_prediction_app
+   ```
+
+3. **Replace the `main.dart` and `pubspec.yaml`:**
+   Replace the `lib/main.dart` file in your Flutter project with the `main.dart` provided in this repository. Similarly, replace the `pubspec.yaml` file with the one provided.
+
+4. **Install Flutter dependencies:**
+   In the root of your Flutter project directory, run:
+   ```bash
+   flutter pub get
+   ```
+
+5. **Run the Flutter app:**
+   Connect a device or start an emulator, then run:
+   ```bash
+   flutter run
+   ```
+
+   The Flutter app will connect to the FastAPI backend to display real-time stock predictions.
+
+## Project Structure
+
+### Backend
+- **`main.py`**: The FastAPI application that handles incoming requests and routes them to the stock prediction function.
+- **`predictor.py`**: Contains the logic for data preprocessing, model training, and stock price prediction.
+- **`requirements.txt`**: Lists the dependencies required for the backend.
+
+### Frontend
+- **`lib/main.dart`**: The main Dart file for the Flutter app, responsible for the UI and API integration.
+- **`pubspec.yaml`**: Specifies the dependencies required for the Flutter app.
+
+## Detailed Functionality
+
+### API Endpoint
+- **POST `/stock/{ticker}`**: Predicts future stock prices for a given ticker symbol over a specified period. The prediction includes:
+  - Current stock price
+  - Predicted prices for the forecasting period
+  - Historical prices
+  - Mean Squared Error (MSE) and Root Mean Squared Error (RMSE)
+  - A prediction label (`CALL` or `SELL`)
+
+### Prediction Methodology
+- The `predictor.py` script fetches historical stock data using the `yfinance` library.
+- Data is preprocessed using scaling techniques to normalize the stock prices.
+- The LSTM model is trained on the historical data to learn patterns.
+- The model predicts future prices based on the last known data.
+- Predictions are scaled back to the original price range, and the results are evaluated for accuracy.
+
+### Model Architecture
+- The LSTM network is designed with two LSTM layers followed by dropout layers to prevent overfitting.
+- The final Dense layer outputs the predicted stock price.
+
+## Example Usage
+
+Once both the API server and the Flutter app are running, you can interact with the app to select a stock ticker and view the predicted prices.
+
+## Future Scope
+
+- **Attention Mechanism**: Implementing an attention mechanism to improve the accuracy of predictions by focusing on more critical time steps.
+- **Extended UI**: Enhancing the Flutter frontend to provide more interactive features and better visualizations.
+- **Additional Models**: Experimenting with other machine learning models to compare performance and accuracy.
+
+## Conclusion
+
+This project demonstrates the application of LSTM neural networks in stock market prediction, providing users with valuable insights into potential future stock prices through an intuitive Flutter frontend. The API is built to be scalable and easy to use, with future improvements planned to enhance prediction accuracy and user experience.

backend/main.py

@@ -0,0 +1,14 @@
+from fastapi import FastAPI, Query
+from stock_predictor.predictor import get_stock_prediction
+
+app = FastAPI()
+
+@app.post("/stock/{ticker}")
+async def stock_prediction(ticker: str, forecasting_period: int = Query(30)):
+    # Call the synchronous function directly
+    result = get_stock_prediction(ticker, forecasting_period)
+    return result
+
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=8000)

backend/requirements.txt

@@ -0,0 +1,6 @@
+yfinance
+numpy 
+pandas
+matplotlib
+scikit-learn
+tensorflow

backend/stock_predictor/predictor.py

@@ -0,0 +1,86 @@
+import numpy as np
+import pandas as pd
+import yfinance as yf
+from sklearn.preprocessing import MinMaxScaler, RobustScaler
+from sklearn.metrics import mean_squared_error
+from tensorflow.keras.models import Sequential
+from tensorflow.keras.layers import LSTM, Dense, Dropout, Input
+from tensorflow.keras.callbacks import EarlyStopping, ReduceLROnPlateau
+
+def get_stock_prediction(ticker: str, forecasting_period: int):
+    data = yf.download(ticker, start='2010-01-01')
+
+    if data.empty:
+        raise ValueError(f"No data found for ticker {ticker}")
+
+    data = data[['Close']]
+    data = data.fillna(method='ffill')
+
+    if data.isnull().values.any():
+        raise ValueError("Data contains NaN values even after forward fill")
+
+    training_data_len = int(np.ceil(len(data) * 0.8))
+    train_data = data[:training_data_len]
+    test_data = data[training_data_len:]
+
+    scaler = RobustScaler()
+    scaled_train_data = scaler.fit_transform(train_data)
+    scaled_test_data = scaler.transform(test_data)
+
+    def create_sequences(data, seq_length):
+        xs, ys = [], []
+        for i in range(len(data) - seq_length):
+            x = data[i:i + seq_length]
+            y = data[i + seq_length]
+            xs.append(x)
+            ys.append(y)
+        return np.array(xs), np.array(ys)
+
+    SEQ_LENGTH = 60
+    X_train, y_train = create_sequences(scaled_train_data, SEQ_LENGTH)
+    X_test, y_test = create_sequences(scaled_test_data, SEQ_LENGTH)
+
+    model = Sequential([
+        Input(shape=(SEQ_LENGTH, 1)),
+        LSTM(50, return_sequences=True),
+        Dropout(0.2),
+        LSTM(50),
+        Dropout(0.2),
+        Dense(1)
+    ])
+
+    model.compile(optimizer='adam', loss='mean_squared_error')
+
+    early_stopping = EarlyStopping(monitor='val_loss', patience=10, restore_best_weights=True)
+    reduce_lr = ReduceLROnPlateau(monitor='val_loss', factor=0.5, patience=5, min_lr=0.0001)
+
+    model.fit(X_train, y_train, epochs=50, batch_size=32, validation_split=0.1, verbose=1,
+              callbacks=[early_stopping, reduce_lr])
+
+    predictions = []
+    last_sequence = X_test[-1]
+
+    for _ in range(forecasting_period):
+        prediction = model.predict(last_sequence.reshape(1, SEQ_LENGTH, 1))
+        predictions.append(prediction[0][0])
+        last_sequence = np.append(last_sequence[1:], prediction, axis=0)
+
+    predictions = np.array(predictions).reshape(-1, 1)
+    predictions = scaler.inverse_transform(predictions)
+    current_price = scaler.inverse_transform(y_test[-1].reshape(-1, 1))[0][0]
+
+    mse = mean_squared_error(y_test, model.predict(X_test))
+    rmse = np.sqrt(mse)
+
+    predictions = predictions.flatten().tolist()
+    mse = float(mse)
+    rmse = float(rmse)
+
+    return {
+        'current_price': current_price,
+        'predicted_prices': predictions,
+        'mse': mse,
+        'rmse': rmse,
+        'historical_prices': data['Close'].values[-SEQ_LENGTH:].tolist(),
+        'prediction': 'CALL' if predictions[-1] > current_price else 'SELL'
+    }

frontend_complete/.gitignore

@@ -0,0 +1,43 @@
+# Miscellaneous
+*.class
+*.log
+*.pyc
+*.swp
+.DS_Store
+.atom/
+.buildlog/
+.history
+.svn/
+migrate_working_dir/
+
+# IntelliJ related
+*.iml
+*.ipr
+*.iws
+.idea/
+
+# The .vscode folder contains launch configuration and tasks you configure in
+# VS Code which you may wish to be included in version control, so this line
+# is commented out by default.
+#.vscode/
+
+# Flutter/Dart/Pub related
+**/doc/api/
+**/ios/Flutter/.last_build_id
+.dart_tool/
+.flutter-plugins
+.flutter-plugins-dependencies
+.pub-cache/
+.pub/
+/build/
+
+# Symbolication related
+app.*.symbols
+
+# Obfuscation related
+app.*.map.json
+
+# Android Studio will place build artifacts here
+/android/app/debug
+/android/app/profile
+/android/app/release

frontend_complete/.metadata

@@ -0,0 +1,45 @@
+# This file tracks properties of this Flutter project.
+# Used by Flutter tool to assess capabilities and perform upgrades etc.
+#
+# This file should be version controlled and should not be manually edited.
+
+version:
+  revision: "a14f74ff3a1cbd521163c5f03d68113d50af93d3"
+  channel: "stable"
+
+project_type: app
+
+# Tracks metadata for the flutter migrate command
+migration:
+  platforms:
+    - platform: root
+      create_revision: a14f74ff3a1cbd521163c5f03d68113d50af93d3
+      base_revision: a14f74ff3a1cbd521163c5f03d68113d50af93d3
+    - platform: android
+      create_revision: a14f74ff3a1cbd521163c5f03d68113d50af93d3
+      base_revision: a14f74ff3a1cbd521163c5f03d68113d50af93d3
+    - platform: ios
+      create_revision: a14f74ff3a1cbd521163c5f03d68113d50af93d3
+      base_revision: a14f74ff3a1cbd521163c5f03d68113d50af93d3
+    - platform: linux
+      create_revision: a14f74ff3a1cbd521163c5f03d68113d50af93d3
+      base_revision: a14f74ff3a1cbd521163c5f03d68113d50af93d3
+    - platform: macos
+      create_revision: a14f74ff3a1cbd521163c5f03d68113d50af93d3
+      base_revision: a14f74ff3a1cbd521163c5f03d68113d50af93d3
+    - platform: web
+      create_revision: a14f74ff3a1cbd521163c5f03d68113d50af93d3
+      base_revision: a14f74ff3a1cbd521163c5f03d68113d50af93d3
+    - platform: windows
+      create_revision: a14f74ff3a1cbd521163c5f03d68113d50af93d3
+      base_revision: a14f74ff3a1cbd521163c5f03d68113d50af93d3
+
+  # User provided section
+
+  # List of Local paths (relative to this file) that should be
+  # ignored by the migrate tool.
+  #
+  # Files that are not part of the templates will be ignored by default.
+  unmanaged_files:
+    - 'lib/main.dart'
+    - 'ios/Runner.xcodeproj/project.pbxproj'

frontend_complete/README.md

@@ -0,0 +1,16 @@
+# app
+
+A new Flutter project.
+
+## Getting Started
+
+This project is a starting point for a Flutter application.
+
+A few resources to get you started if this is your first Flutter project:
+
+- [Lab: Write your first Flutter app](https://docs.flutter.dev/get-started/codelab)
+- [Cookbook: Useful Flutter samples](https://docs.flutter.dev/cookbook)
+
+For help getting started with Flutter development, view the
+[online documentation](https://docs.flutter.dev/), which offers tutorials,
+samples, guidance on mobile development, and a full API reference.

frontend_complete/analysis_options.yaml

@@ -0,0 +1,28 @@
+# This file configures the analyzer, which statically analyzes Dart code to
+# check for errors, warnings, and lints.
+#
+# The issues identified by the analyzer are surfaced in the UI of Dart-enabled
+# IDEs (https://dart.dev/tools#ides-and-editors). The analyzer can also be
+# invoked from the command line by running `flutter analyze`.
+
+# The following line activates a set of recommended lints for Flutter apps,
+# packages, and plugins designed to encourage good coding practices.
+include: package:flutter_lints/flutter.yaml
+
+linter:
+  # The lint rules applied to this project can be customized in the
+  # section below to disable rules from the `package:flutter_lints/flutter.yaml`
+  # included above or to enable additional rules. A list of all available lints
+  # and their documentation is published at https://dart.dev/lints.
+  #
+  # Instead of disabling a lint rule for the entire project in the
+  # section below, it can also be suppressed for a single line of code
+  # or a specific dart file by using the `// ignore: name_of_lint` and
+  # `// ignore_for_file: name_of_lint` syntax on the line or in the file
+  # producing the lint.
+  rules:
+    # avoid_print: false  # Uncomment to disable the `avoid_print` rule
+    # prefer_single_quotes: true  # Uncomment to enable the `prefer_single_quotes` rule
+
+# Additional information about this file can be found at
+# https://dart.dev/guides/language/analysis-options

frontend_complete/android/.gitignore

@@ -0,0 +1,13 @@
+gradle-wrapper.jar
+/.gradle
+/captures/
+/gradlew
+/gradlew.bat
+/local.properties
+GeneratedPluginRegistrant.java
+
+# Remember to never publicly share your keystore.
+# See https://flutter.dev/docs/deployment/android#reference-the-keystore-from-the-app
+key.properties
+**/*.keystore
+**/*.jks