fix requirements.txt

app.py

@@ -4,7 +4,7 @@ import pandas as pd
 import numpy as np
 from datetime import datetime
 from flask import Flask, jsonify, Response
-from model import download_data, format_data, train_model
+from model import download_data, format_data, train_model, training_price_data_path
 from config import model_file_path
 
 app = Flask(__name__)
@@ -19,14 +19,36 @@ def update_data():
 
 def get_eth_inference():
     """Load model and predict current price."""
+    try:
         with open(model_file_path, "rb") as f:
             loaded_model = pickle.load(f)
 
-    now_timestamp = pd.Timestamp(datetime.now()).timestamp()
+        # Загружаем последние данные из файла
-    X_new = np.array([now_timestamp]).reshape(-1, 1)
+        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",
+                ]
+            ]
+            .iloc[-1]
+            .values.reshape(1, -1)
+        )
+
+        # Делаем предсказание
         current_price_pred = loaded_model.predict(X_new)
 
         return current_price_pred[0]
+    except Exception as e:
+        print(f"Error during inference: {str(e)}")
+        raise
 
 
 @app.route("/inference/<string:token>")
@@ -34,13 +56,17 @@ 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')
+        return Response(
+            json.dumps({"error": error_msg}), status=400, mimetype="application/json"
+        )
 
     try:
         inference = get_eth_inference()
         return Response(str(inference), status=200)
     except Exception as e:
-        return Response(json.dumps({"error": str(e)}), status=500, mimetype='application/json')
+        return Response(
+            json.dumps({"error": str(e)}), status=500, mimetype="application/json"
+        )
 
 
 @app.route("/update")

config.json

@@ -7,7 +7,7 @@
         "gasAdjustment": 1.0,
         "nodeRpc": "###RPC_URL###",
         "maxRetries": 10,
-        "delay": 10,
+        "delay": 30,
         "submitTx": false
     },
     "worker": [

logs_parser.py

@@ -2,7 +2,6 @@ import subprocess
 import json
 import sys
 import time
-import os
 
 def is_json(myjson):
     try:
@@ -11,7 +10,7 @@ def is_json(myjson):
         return False
     return True
 
-def parse_logs():
+def parse_logs(timeout):
     start_time = time.time()
     while True:
         unsuccessful_attempts = 0
@@ -50,26 +49,28 @@ def parse_logs():
                             return False, "Max Retry Reached"
         except Exception as e:
             print(f"Exception occurred: {e}", flush=True)
-        finally:
-            process.stdout.close()
 
         print("Sleeping before next log request...", flush=True)
         time.sleep(30)
 
-        if time.time() - start_time > 30 * 60:
+        if time.time() - start_time > timeout * 60:
-            print("Timeout reached: 30 minutes elapsed without success.", flush=True)
+            print(f"Timeout reached: {timeout} minutes elapsed without success.", flush=True)
-            return False, "Timeout reached: 30 minutes elapsed without success."
+            return False, f"Timeout reached: {timeout} minutes elapsed without success."
 
     return False, "No Success"
 
 if __name__ == "__main__":
     print("Parsing logs...")
-    result = parse_logs()
+    if len(sys.argv) > 1: 
+        timeout = eval(sys.argv[1]) 
+    else: 
+        timeout = 30
+    result = parse_logs(timeout)
     print(result[1])
     if result[0] == False:
         print("Exiting 1...")
-        os._exit(1)
+        sys.exit(1)
     else:
         print("Exiting 0...")
-        os._exit(0)
+        sys.exit(0)
 

model.py

@@ -1,15 +1,14 @@
 import os
 import pickle
+import numpy as np 
+from xgboost import XGBRegressor
 from zipfile import ZipFile
 from datetime import datetime
 import pandas as pd
-import numpy as np
 from sklearn.model_selection import train_test_split
-from sklearn import linear_model
 from updater import download_binance_monthly_data, download_binance_daily_data
 from config import data_base_path, model_file_path
 
-
 binance_data_path = os.path.join(data_base_path, "binance/futures-klines")
 training_price_data_path = os.path.join(data_base_path, "eth_price_data.csv")
 
@@ -35,19 +34,14 @@ def download_data():
 
 
 def format_data():
-    files = sorted([x for x in os.listdir(binance_data_path)])
+    files = sorted([x for x in os.listdir(binance_data_path) if x.endswith(".zip")])
 
-    # No files to process
     if len(files) == 0:
         return
 
     price_df = pd.DataFrame()
     for file in files:
         zip_file_path = os.path.join(binance_data_path, file)
-
-        if not zip_file_path.endswith(".zip"):
-            continue
-
         myzip = ZipFile(zip_file_path)
         with myzip.open(myzip.filelist[0]) as f:
             line = f.readline()
@@ -70,30 +64,43 @@ def format_data():
         df.index.name = "date"
         price_df = pd.concat([price_df, df])
 
+    price_df["timestamp"] = price_df.index.map(pd.Timestamp.timestamp)
+    price_df["price_diff"] = price_df["close"].diff()
+    price_df["volatility"] = (price_df["high"] - price_df["low"]) / price_df["open"]
+    price_df["volume"] = price_df["volume"]
+    price_df["moving_avg_7"] = price_df["close"].rolling(window=7).mean()
+    price_df["moving_avg_30"] = price_df["close"].rolling(window=30).mean()
+
+    # Удаляем строки с NaN значениями
+    price_df.dropna(inplace=True)
+
+    # Сохраняем данные
     price_df.sort_index().to_csv(training_price_data_path)
 
 
 def train_model():
-    # Load the eth price data
     price_data = pd.read_csv(training_price_data_path)
-    df = pd.DataFrame()
 
-    # Convert 'date' to a numerical value (timestamp) we can use for regression
+    # Используем дополнительные признаки
-    df["date"] = pd.to_datetime(price_data["date"])
+    x = price_data[
-    df["date"] = df["date"].map(pd.Timestamp.timestamp)
+        [
+            "timestamp",
+            "price_diff",
+            "volatility",
+            "volume",
+            "moving_avg_7",
+            "moving_avg_30",
+        ]
+    ]
+    y = price_data["close"]
 
-    df["price"] = price_data[["open", "close", "high", "low"]].mean(axis=1)
+    x_train, x_test, y_train, y_test = train_test_split(
-
+        x, y, test_size=0.2, random_state=0
-    # Reshape the data to the shape expected by sklearn
+    )
-    x = df["date"].values.reshape(-1, 1)
-    y = df["price"].values.reshape(-1, 1)
-
-    # Split the data into training set and test set
-    x_train, _, y_train, _ = train_test_split(x, y, test_size=0.2, random_state=0)
 
     # Train the model
     print("Training model...")
-    model = linear_model.Lasso(alpha=0.1)
+    model = XGBRegressor()
     model.fit(x_train, y_train)
     print("Model trained.")
 
@@ -105,3 +112,7 @@ def train_model():
         pickle.dump(model, f)
 
     print(f"Trained model saved to {model_file_path}")
+
+    # Optional: Оценка модели
+    y_pred = model.predict(x_test)
+    print(f"Mean Absolute Error: {np.mean(np.abs(y_test - y_pred))}")

requirements.txt

@@ -5,3 +5,12 @@ pandas==2.1.3
 Requests==2.32.0
 scikit_learn==1.3.2
 werkzeug>=3.0.3 # not directly required, pinned by Snyk to avoid a vulnerability
+itsdangerous
+Jinja2
+MarkupSafe
+python-dateutil
+pytz
+scipy
+six
+scikit-learn
+xgboost