From 070432d5055ade6bdfd6916a4fc63651ea5cef9d Mon Sep 17 00:00:00 2001
From: root <cjzhong2014@hotmail.com>
Date: Thu, 19 Jun 2025 08:49:28 +0000
Subject: [PATCH] new test.py

---
 .gitignore |  2 ++
 test.py    | 76 +++++++++++++++++++++++++++++++++++++++++++++++++++---
 2 files changed, 75 insertions(+), 3 deletions(-)
 create mode 100644 .gitignore

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..ff7e2b7
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,2 @@
+mlruns/
+
diff --git a/test.py b/test.py
index 3230ca8..6408136 100644
--- a/test.py
+++ b/test.py
@@ -1,6 +1,76 @@
-import torch
+# The data set used in this example is from http://archive.ics.uci.edu/ml/datasets/Wine+Quality
+# P. Cortez, A. Cerdeira, F. Almeida, T. Matos and J. Reis.
+# Modeling wine preferences by data mining from physicochemical properties. In Decision Support Systems, Elsevier, 47(4):547-553, 2009.
 
-print(torch.__version__)
+import os
+import warnings
+import sys
 
-print("hello")
+import pandas as pd
+import numpy as np
+from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import ElasticNet
+
+import mlflow
+import mlflow.sklearn
+
+import logging
+logging.basicConfig(level=logging.WARN)
+logger = logging.getLogger(__name__)
+
+
+def eval_metrics(actual, pred):
+    rmse = np.sqrt(mean_squared_error(actual, pred))
+    mae = mean_absolute_error(actual, pred)
+    r2 = r2_score(actual, pred)
+    return rmse, mae, r2
+
+
+
+if __name__ == "__main__":
+    warnings.filterwarnings("ignore")
+    np.random.seed(40)
+
+    # Read the wine-quality csv file from the URL
+    csv_url =\
+        'http://archive.ics.uci.edu/ml/machine-learning-databases/wine-quality/winequality-red.csv'
+    try:
+        data = pd.read_csv(csv_url, sep=';')
+    except Exception as e:
+        logger.exception(
+            "Unable to download training & test CSV, check your internet connection. Error: %s", e)
+
+    # Split the data into training and test sets. (0.75, 0.25) split.
+    train, test = train_test_split(data)
+
+    # The predicted column is "quality" which is a scalar from [3, 9]
+    train_x = train.drop(["quality"], axis=1)
+    test_x = test.drop(["quality"], axis=1)
+    train_y = train[["quality"]]
+    test_y = test[["quality"]]
+
+    alpha = float(sys.argv[1]) if len(sys.argv) > 1 else 0.5
+    l1_ratio = float(sys.argv[2]) if len(sys.argv) > 2 else 0.5
+
+    with mlflow.start_run():
+        lr = ElasticNet(alpha=alpha, l1_ratio=l1_ratio, random_state=42)
+        lr.fit(train_x, train_y)
+
+        predicted_qualities = lr.predict(test_x)
+
+        (rmse, mae, r2) = eval_metrics(test_y, predicted_qualities)
+
+        print("Elasticnet model (alpha=%f, l1_ratio=%f):" % (alpha, l1_ratio))
+        print("  RMSE: %s" % rmse)
+        print("  MAE: %s" % mae)
+        print("  R2: %s" % r2)
+
+        mlflow.log_param("alpha", alpha)
+        mlflow.log_param("l1_ratio", l1_ratio)
+        mlflow.log_metric("rmse", rmse)
+        mlflow.log_metric("r2", r2)
+        mlflow.log_metric("mae", mae)
+
+        mlflow.sklearn.log_model(lr, "model")