Setup dotnet wrapper around Python AI project for UI

WebServer/AIPython/database.py

@@ -0,0 +1,27 @@
+import sqlite3
+
+class DataBase:
+
+    def __init__(self):
+        # Initilize SqLite
+        self.conn = sqlite3.connect("./data/appdata.db")
+        self.cursor = self.conn.cursor()
+
+        # Create keystore table if it doesnt exist already
+        self.cursor.execute('''
+        CREATE TABLE IF NOT EXISTS keystore (
+            key TEXT PRIMARY KEY,
+            value TEXT
+        )
+        ''')
+
+    # Set a key in the keystore
+    def SetKey(self, Key, Value):
+        self.cursor.execute('INSERT OR REPLACE INTO keystore (key, value) VALUES (?, ?)', (Key, Value))
+        self.conn.commit()
+
+    # Get a key from the keystore
+    def GetKey(self, Key):
+        self.cursor.execute('SELECT value FROM keystore WHERE key = ?', (Key, ))
+        result = self.cursor.fetchone()
+        return result[0] if result else None

WebServer/AIPython/datapuller.py

@@ -0,0 +1,53 @@
+import yfinance as yf
+import pandas as pd
+
+class DataPuller:
+
+    @staticmethod
+    def pull():
+        # Import the S&P 500 symbols
+        symbols = pd.read_excel("./data/stock_symbols.xlsx")
+        symbols.columns = symbols.columns.str.strip()
+        tickers = symbols['Symbol'].tolist()
+
+        # Scrape the data
+        all_data = []
+        for i, symbol in enumerate(tickers): # Try first 20
+            print(f"Processing: {i} of {len(tickers)}")
+            df = yf.download(symbol, period="max", auto_adjust=True)
+            if not df.empty:
+                # Remove the ticker column
+                df.columns = df.columns.get_level_values(0)
+                
+                # Make sure Date is actually a Date Object
+                df = df.reset_index()
+                df['Date'] = pd.to_datetime(df['Date'], format="%Y-%m-%d")
+                df.set_index('Date', inplace=True)
+
+                # Add the Symbol column for tracking
+                df['Symbol'] = symbol
+            
+                # Add feature Spread
+                df['Spread'] = abs( df['High'] - df['Low'] )
+
+                # Add feature for Returns
+                df['Return'] = df['Close'].pct_change()
+
+                # Add feature for volitility last 5
+                df['Volatility_5'] = df['Return'].transform(lambda x: x.rolling(5).std())
+
+                # Add feature for volitility last 20
+                df['Volatility_20'] = df['Return'].transform(lambda x: x.rolling(20).std())
+
+                all_data.append(df)
+
+        # Concatinate into a combined list and cache
+        print("Processing data")
+        final_df = pd.concat(all_data)
+
+        # Drop rows with null values
+        final_df.dropna(inplace=True)
+
+        print("Writing data to file")
+        final_df.to_parquet("./data/stocks.parquet")
+        final_df.head(200).to_csv("./data/stocks_preview.csv")

WebServer/AIPython/main.py

@@ -0,0 +1,39 @@
+from datetime import date, datetime
+from datapuller import DataPuller
+from database import DataBase
+
+def main():
+
+    # Load the database object
+    db = DataBase()
+
+    # If we havent already pulled the stock data today
+    if db.GetKey("LastRun") != str(date.today()):
+        # Update the data store in the data folder
+        DataPuller.pull()
+        # Update the last run to today
+        db.SetKey("LastRun", str(date.today()))
+
+    # Lazy Load in the AI algorithms so yfinance works properly
+    import tensorflow as tf
+    import keras
+    from keras.layers import Dense, Flatten, Conv2D
+    from keras import Model
+
+    mnist = keras.datasets.mnist
+
+    (x_train, y_train), (x_test, y_test) = mnist.load_data()
+    x_train, x_test = x_train / 255.0, x_test / 255.0
+
+    # Add a channels dimension
+    x_train = x_train[..., tf.newaxis].astype("float32")
+    x_test = x_test[..., tf.newaxis].astype("float32")
+
+    # batch and shuffle the dataset
+    train_ds = tf.data.Dataset.from_tensor_slices(
+        (x_train, y_train)).shuffle(10000).batch(32)
+
+    test_ds = tf.data.Dataset.from_tensor_slices((x_test, y_test)).batch(32)
+
+if __name__ == "__main__":
+    main()