add universal for many periods

app.py

@@ -17,8 +17,7 @@ def update_data():
     train_model()
 
 
-def get_eth_inference():
-    """Load model and predict current price."""
+def get_inference(token, period):
     try:
         with open(model_file_path, "rb") as f:
             loaded_model = pickle.load(f)
@@ -27,41 +26,56 @@ def get_eth_inference():
         price_data = pd.read_csv(training_price_data_path)
 
         # Используем последние значения признаков для предсказания
-        X_new = (
-            price_data[
-                [
-                    "timestamp",
-                    "price_diff",
-                    "volatility",
-                    "volume",
-                    "moving_avg_7",
-                    "moving_avg_30",
-                ]
+        last_row = price_data.iloc[-1]
+
+        # Получаем последний timestamp
+        last_timestamp = last_row["timestamp"]
+
+        # Преобразуем период в секунды (пример)
+        period_seconds = convert_period_to_seconds(period)
+
+        # Рассчитываем новый временной штамп на основе периода
+        new_timestamp = last_timestamp + period_seconds
+
+        # timestamp
+        X_new = np.array(
+            [
+                new_timestamp,
+                last_row["price_diff"],
+                last_row["volatility"],
+                last_row["volume"],
+                last_row["moving_avg_7"],
+                last_row["moving_avg_30"],
             ]
-            .iloc[-1]
-            .values.reshape(1, -1)
-        )
+        ).reshape(1, -1)
 
-        # Делаем предсказание
-        current_price_pred = loaded_model.predict(X_new)
+        # Предсказание
+        future_price_pred = loaded_model.predict(X_new)
+
+        return future_price_pred[0]
 
-        return current_price_pred[0]
     except Exception as e:
         print(f"Error during inference: {str(e)}")
         raise
 
 
-@app.route("/inference/<string:token>")
-def generate_inference(token):
-    """Generate inference for given token."""
-    if not token or token != "ETH":
-        error_msg = "Token is required" if not token else "Token not supported"
-        return Response(
-            json.dumps({"error": error_msg}), status=400, mimetype="application/json"
-        )
+def convert_period_to_seconds(period):
+    """Конвертируем период в секунды."""
+    if period.endswith("min"):
+        return int(period[:-3]) * 60
+    elif period.endswith("h"):
+        return int(period[:-1]) * 3600
+    elif period.endswith("d"):
+        return int(period[:-1]) * 86400
+    else:
+        raise ValueError(f"Unknown period format: {period}")
 
+
+@app.route("/inference/<string:token>/<string:period>")
+def generate_inference(token, period):
+    """Generate inference for given token and period."""
     try:
-        inference = get_eth_inference()
+        inference = get_inference(token, period)
         return Response(str(inference), status=200)
     except Exception as e:
         return Response(
@@ -81,4 +95,4 @@ def update():
 
 if __name__ == "__main__":
     update_data()
-    app.run(host="0.0.0.0", port=8000)
+    app.run(host="0.0.0.0", port=8127)

model.py

@@ -1,9 +1,9 @@
 import os
 import pickle
-import numpy as np 
+import numpy as np
 from xgboost import XGBRegressor
 from zipfile import ZipFile
-from datetime import datetime
+from datetime import datetime, timedelta
 import pandas as pd
 from sklearn.model_selection import train_test_split
 from updater import download_binance_monthly_data, download_binance_daily_data
@@ -16,7 +16,7 @@ training_price_data_path = os.path.join(data_base_path, "eth_price_data.csv")
 def download_data():
     cm_or_um = "um"
     symbols = ["ETHUSDT"]
-    intervals = ["1d"]
+    intervals = ["10min"]
     years = ["2020", "2021", "2022", "2023", "2024"]
     months = ["01", "02", "03", "04", "05", "06", "07", "08", "09", "10", "11", "12"]
     download_path = binance_data_path
@@ -104,10 +104,8 @@ def train_model():
     model.fit(x_train, y_train)
     print("Model trained.")
 
-    # create the model's parent directory if it doesn't exist
     os.makedirs(os.path.dirname(model_file_path), exist_ok=True)
 
-    # Save the trained model to a file
     with open(model_file_path, "wb") as f:
         pickle.dump(model, f)
 
@@ -115,4 +113,42 @@ def train_model():
 
     # Optional: Оценка модели
     y_pred = model.predict(x_test)
-    print(f"Mean Absolute Error: {np.mean(np.abs(y_test - y_pred))}")
+    print(f"Mean Absolute Error: {np.mean(np.abs(y_test - y_pred))}")
+
+
+def get_inference_data(token, period):
+    """
+    Генерирует данные для инференса на основе переданного токена и периода.
+    """
+    price_data = pd.read_csv(training_price_data_path)
+
+    # Настроить разницу времени в зависимости от периода
+    time_delta_map = {
+        "1min": timedelta(minutes=1),
+        "5min": timedelta(minutes(5)),
+        "10min": timedelta(minutes(10)),
+        "30min": timedelta(minutes(30)),
+        "1h": timedelta(hours=1),
+        "1d": timedelta(days=1),
+    }
+
+    # Получаем последний таймстамп и вычисляем следующий
+    last_timestamp = pd.to_datetime(price_data["timestamp"].iloc[-1], unit="s")
+    next_timestamp = last_timestamp + time_delta_map.get(period, timedelta(minutes=10))
+
+    # Используем последние значения признаков
+    last_data = price_data.iloc[-1]
+    X_new = np.array(
+        [
+            [
+                next_timestamp.timestamp(),
+                last_data["price_diff"],
+                last_data["volatility"],
+                last_data["volume"],
+                last_data["moving_avg_7"],
+                last_data["moving_avg_30"],
+            ]
+        ]
+    )
+
+    return X_new