Update projects/conda.md

projects/conda.md

@@ -1,3 +1,251 @@
+Great! Let's update the project to use conda for creating the Python environment and pip for package management. Here's the updated project structure and instructions:
+
+Project Structure:
+```
+stock_prediction/
+├── data/
+│   └── stock_data.db
+├── scripts/
+│   ├── fetch_stock_data.py
+│   └── verify_data.py
+├── app/
+│   └── stock_prediction_app.py
+├── environment.yml
+└── requirements.txt
+```
+
+1. `stock_prediction/data/stock_data.db`:
+   - This is the SQLite database file that will store the historical stock data.
+
+2. `stock_prediction/scripts/fetch_stock_data.py`:
+   - The content of this file remains the same as in the previous response.
+
+3. `stock_prediction/scripts/verify_data.py`:
+   - The content of this file remains the same as in the previous response.
+
+4. `stock_prediction/app/stock_prediction_app.py`:
+   - The content of this file remains the same as in the previous response.
+
+5. `stock_prediction/environment.yml`:
+```yaml
+name: stock_prediction
+channels:
+  - defaults
+dependencies:
+  - python=3.9
+  - pip
+  - pip:
+    - -r requirements.txt
+```
+
+6. `stock_prediction/requirements.txt`:
+```
+dash
+pandas
+numpy
+yfinance
+scikit-learn
+tensorflow
+keras
+plotly
+```
+
+To run the project:
+
+1. Create a conda environment using the `environment.yml` file:
+   ```
+   conda env create -f environment.yml
+   ```
+
+2. Activate the conda environment:
+   ```
+   conda activate stock_prediction
+   ```
+
+3. Fetch historical stock data:
+   ```
+   python scripts/fetch_stock_data.py --symbol ^GSPC --start_date 2000-01-01 --end_date 2023-05-31
+   ```
+   You can change the stock symbol and date range as needed.
+
+4. Verify the stored data (optional):
+   ```
+   python scripts/verify_data.py
+   ```
+
+5. Run the Dash application:
+   ```
+   python app/stock_prediction_app.py
+   ```
+
+6. Open a web browser and go to `http://localhost:8050` to access the application.
+
+7. Select a stock symbol from the dropdown menu to see the actual and predicted stock prices on the graph.
+
+The `environment.yml` file defines the conda environment named `stock_prediction` and specifies the Python version as 3.9. It also includes the `pip` package manager and instructs conda to install the packages listed in the `requirements.txt` file using pip.
+
+The `requirements.txt` file remains the same and lists the required Python packages for the project.
+
+By using conda for environment management and pip for package management, you can ensure a consistent and reproducible environment for your project.
+
+Remember to activate the conda environment before running the scripts or the Dash application.
+
+---
+
+Project Structure:
+```
+stock_prediction/
+├── data/
+│   └── stock_data.db
+├── scripts/
+│   ├── fetch_stock_data.py
+│   └── verify_data.py
+├── app/
+│   └── stock_prediction_app.py
+└── requirements.txt
+```
+
+1. `stock_prediction/data/stock_data.db`:
+   - This is the SQLite database file that will store the historical stock data.
+
+2. `stock_prediction/scripts/fetch_stock_data.py`:
+```python
+import argparse
+import yfinance as yf
+import pandas as pd
+import sqlite3
+
+parser = argparse.ArgumentParser(description="Fetch historical stock data from Yahoo Finance.")
+parser.add_argument("--symbol", type=str, default="^GSPC", help="Stock symbol (default: ^GSPC)")
+parser.add_argument("--start_date", type=str, default="2000-01-01", help="Start date (default: 2000-01-01)")
+parser.add_argument("--end_date", type=str, default="2023-05-31", help="End date (default: 2023-05-31)")
+args = parser.parse_args()
+
+symbol = args.symbol
+start_date = args.start_date
+end_date = args.end_date
+
+conn = sqlite3.connect("../data/stock_data.db")
+
+data = yf.download(symbol, start=start_date, end=end_date)
+
+table_name = f"{symbol}_prices"
+data.to_sql(name=table_name, con=conn, if_exists="replace")
+
+print(f"Data for {symbol} stored in the database.")
+
+conn.close()
+```
+
+3. `stock_prediction/scripts/verify_data.py`:
+```python
+import sqlite3
+import pandas as pd
+
+conn = sqlite3.connect("../data/stock_data.db")
+
+tables = pd.read_sql_query("SELECT name FROM sqlite_master WHERE type='table'", conn)
+print("Tables in the database:")
+print(tables)
+
+table_name = "^GSPC_prices"
+data = pd.read_sql_query(f"SELECT * FROM {table_name}", conn)
+print(f"\nData from the {table_name} table:")
+print(data.head())
+
+conn.close()
+```
+
+4. `stock_prediction/app/stock_prediction_app.py`:
+```python
+import dash
+import dash_core_components as dcc
+import dash_html_components as html
+from dash.dependencies import Input, Output
+import pandas as pd
+import sqlite3
+import numpy as np
+from sklearn.preprocessing import MinMaxScaler
+from tensorflow.keras.models import Sequential
+from tensorflow.keras.layers import LSTM, Dense
+import plotly.graph_objects as go
+
+app = dash.Dash(__name__)
+
+app.layout = html.Div([
+    html.H1("Stock Price Prediction"),
+    html.Div([
+        html.Label("Select Stock Symbol"),
+        dcc.Dropdown(
+            id="stock-dropdown",
+            options=[{"label": "S&P 500", "value": "^GSPC"},
+                     {"label": "Dow Jones", "value": "^DJI"},
+                     {"label": "Nasdaq", "value": "^IXIC"}],
+            value="^GSPC"
+        )
+    ]),
+    html.Div([
+        dcc.Graph(id="stock-graph")
+    ])
+])
+
+@app.callback(Output("stock-graph", "figure"),
+              [Input("stock-dropdown", "value")])
+def update_graph(stock_symbol):
+    conn = sqlite3.connect("../data/stock_data.db")
+    data = pd.read_sql_query(f"SELECT Date, Close FROM {stock_symbol}_prices", conn)
+    conn.close()
+
+    scaler = MinMaxScaler(feature_range=(0, 1))
+    scaled_data = scaler.fit_transform(data["Close"].values.reshape(-1, 1))
+
+    lookback = 60
+    X, y = [], []
+    for i in range(lookback, len(scaled_data)):
+        X.append(scaled_data[i - lookback:i, 0])
+        y.append(scaled_data[i, 0])
+    X, y = np.array(X), np.array(y)
+    X = np.reshape(X, (X.shape[0], X.shape[1], 1))
+
+    model = Sequential()
+    model.add(LSTM(units=50, return_sequences=True, input_shape=(X.shape[1], 1)))
+    model.add(LSTM(units=50))
+    model.add(Dense(1))
+    model.compile(loss="mean_squared_error", optimizer="adam")
+    model.fit(X, y, epochs=10, batch_size=32)
+
+    last_data = scaled_data[-lookback:]
+    X_test = []
+    for i in range(lookback, len(last_data)):
+        X_test.append(last_data[i - lookback:i, 0])
+    X_test = np.array(X_test)
+    X_test = np.reshape(X_test, (X_test.shape[0], X_test.shape[1], 1))
+    predicted_prices = model.predict(X_test)
+    predicted_prices = scaler.inverse_transform(predicted_prices)
+
+    fig = go.Figure()
+    fig.add_trace(go.Scatter(x=data["Date"], y=data["Close"], name="Actual Price"))
+    fig.add_trace(go.Scatter(x=data["Date"][-len(predicted_prices):], y=predicted_prices.flatten(), name="Predicted Price"))
+    fig.update_layout(title=f"{stock_symbol} Stock Price Prediction", xaxis_title="Date", yaxis_title="Price")
+
+    return fig
+
+if __name__ == "__main__":
+    app.run_server(debug=True)
+```
+
+5. `stock_prediction/requirements.txt`:
+```
+dash
+pandas
+numpy
+yfinance
+scikit-learn
+tensorflow
+keras
+plotly
+```
+
 Certainly! Let's combine Dash, deep learning, and price prediction capabilities into a working project. We'll create a web application using Dash that allows users to select a stock symbol, trains an LSTM model on the historical data, and displays the predicted stock prices.
 
 Here's a step-by-step guide to create the project: