mlflow · Ramyashree-20 · Jul 27, 2025
diff --git a/README.md b/README.md
@@ -1 +1,63 @@
 # Example MLflow project
+This is a simple example ML project that demonstrates how to use [MLflow](https://mlflow.org/) to track machine learning experiments using the Wine Quality dataset.
+
+## 📁 Project Structure
+.
+├── conda.yaml # Conda environment dependencies
+├── LICENSE.txt # License file
+├── MLproject # MLflow project configuration
+├── README.md # Project description (this file)
+├── train.py # Training script
+└── wine-quality.csv # Dataset
+
+## 📦 Requirements
+
+- Python 3.7+
+- MLflow
+- scikit-learn
+- pandas
+- numpy
+
+You can install dependencies using:
+
+```bash
+pip install -r requirements.txt
+Or using the conda.yaml file:
+
+bash
+Copy
+Edit
+conda env create -f conda.yaml
+conda activate mlflow-env
+🧪 Running the Training Script
+To run the training script with MLflow:
+
+bash
+Copy
+Edit
+python train.py 0.5 0.5
+Or with MLflow CLI:
+
+bash
+Copy
+Edit
+mlflow run . -P alpha=0.5 -P l1_ratio=0.5
+📈 Logged Metrics
+This project logs the following metrics:
+
+RMSE (Root Mean Squared Error)
+
+MAE (Mean Absolute Error)
+
+R² (R-squared)
+
+The trained model is also saved and logged with MLflow
+📚 Dataset Info
+The dataset used is the Wine Quality dataset from UCI Machine Learning Repository.
+
+css
+Copy
+Edit
+P. Cortez, A. Cerdeira, F. Almeida, T. Matos and J. Reis.
+"Modeling wine preferences by data mining from physicochemical properties".
+Decision Support Systems, Elsevier, 47(4):547-553, 2009.
diff --git a/mlruns/0/79442e6bb3ff42c5a7ca58e4858e5f62/meta.yaml b/mlruns/0/79442e6bb3ff42c5a7ca58e4858e5f62/meta.yaml
@@ -0,0 +1,14 @@
+artifact_uri: file:///C:/Users/hp/mlflow-example/mlruns/0/79442e6bb3ff42c5a7ca58e4858e5f62/artifacts
+end_time: 1753625116637
+entry_point_name: ''
+experiment_id: '0'
+lifecycle_stage: active
+run_id: 79442e6bb3ff42c5a7ca58e4858e5f62
+run_name: carefree-jay-416
+source_name: ''
+source_type: 4
+source_version: ''
+start_time: 1753625111329
+status: 3
+tags: []
+user_id: hp
diff --git a/mlruns/0/79442e6bb3ff42c5a7ca58e4858e5f62/metrics/mae b/mlruns/0/79442e6bb3ff42c5a7ca58e4858e5f62/metrics/mae
@@ -0,0 +1,2 @@
+1753625111412 0.6278761410160693 0
+1753625111412 0.6278761410160693 0
diff --git a/mlruns/0/79442e6bb3ff42c5a7ca58e4858e5f62/metrics/r2 b/mlruns/0/79442e6bb3ff42c5a7ca58e4858e5f62/metrics/r2
@@ -0,0 +1,2 @@
+1753625111400 0.12678721972772689 0
+1753625111400 0.12678721972772689 0
diff --git a/mlruns/0/79442e6bb3ff42c5a7ca58e4858e5f62/metrics/rmse b/mlruns/0/79442e6bb3ff42c5a7ca58e4858e5f62/metrics/rmse
@@ -0,0 +1,2 @@
+1753625111380 0.82224284975954 0
+1753625111380 0.82224284975954 0
diff --git a/...s/0/79442e6bb3ff42c5a7ca58e4858e5f62/outputs/m-716f80ebde1c4e5bb22cf127c5367bca/meta.yaml b/...s/0/79442e6bb3ff42c5a7ca58e4858e5f62/outputs/m-716f80ebde1c4e5bb22cf127c5367bca/meta.yaml
@@ -0,0 +1,6 @@
+destination_id: m-716f80ebde1c4e5bb22cf127c5367bca
+destination_type: MODEL_OUTPUT
+source_id: m-716f80ebde1c4e5bb22cf127c5367bca
+source_type: RUN_OUTPUT
+step: 0
+tags: {}
diff --git a/mlruns/0/79442e6bb3ff42c5a7ca58e4858e5f62/params/alpha b/mlruns/0/79442e6bb3ff42c5a7ca58e4858e5f62/params/alpha
@@ -0,0 +1 @@
+0.5
diff --git a/mlruns/0/79442e6bb3ff42c5a7ca58e4858e5f62/params/l1_ratio b/mlruns/0/79442e6bb3ff42c5a7ca58e4858e5f62/params/l1_ratio
@@ -0,0 +1 @@
+0.5
diff --git a/mlruns/0/79442e6bb3ff42c5a7ca58e4858e5f62/tags/mlflow.runName b/mlruns/0/79442e6bb3ff42c5a7ca58e4858e5f62/tags/mlflow.runName
@@ -0,0 +1 @@
+carefree-jay-416
diff --git a/mlruns/0/79442e6bb3ff42c5a7ca58e4858e5f62/tags/mlflow.source.git.commit b/mlruns/0/79442e6bb3ff42c5a7ca58e4858e5f62/tags/mlflow.source.git.commit
@@ -0,0 +1 @@
+0651d1c962aa35e4dd02608c51a7b0efc2412407
diff --git a/mlruns/0/79442e6bb3ff42c5a7ca58e4858e5f62/tags/mlflow.source.name b/mlruns/0/79442e6bb3ff42c5a7ca58e4858e5f62/tags/mlflow.source.name
@@ -0,0 +1 @@
+train.py
diff --git a/mlruns/0/79442e6bb3ff42c5a7ca58e4858e5f62/tags/mlflow.source.type b/mlruns/0/79442e6bb3ff42c5a7ca58e4858e5f62/tags/mlflow.source.type
@@ -0,0 +1 @@
+LOCAL
diff --git a/mlruns/0/79442e6bb3ff42c5a7ca58e4858e5f62/tags/mlflow.user b/mlruns/0/79442e6bb3ff42c5a7ca58e4858e5f62/tags/mlflow.user
@@ -0,0 +1 @@
+hp
diff --git a/mlruns/0/meta.yaml b/mlruns/0/meta.yaml
@@ -0,0 +1,6 @@
+artifact_location: file:///C:/Users/hp/mlflow-example/mlruns/0
+creation_time: 1753625110390
+experiment_id: '0'
+last_update_time: 1753625110390
+lifecycle_stage: active
+name: Default
diff --git a/mlruns/0/models/m-716f80ebde1c4e5bb22cf127c5367bca/artifacts/MLmodel b/mlruns/0/models/m-716f80ebde1c4e5bb22cf127c5367bca/artifacts/MLmodel
@@ -0,0 +1,22 @@
+artifact_path: file:///C:/Users/hp/mlflow-example/mlruns/0/models/m-716f80ebde1c4e5bb22cf127c5367bca/artifacts
+flavors:
+  python_function:
+    env:
+      conda: conda.yaml
+      virtualenv: python_env.yaml
+    loader_module: mlflow.sklearn
+    model_path: model.pkl
+    predict_fn: predict
+    python_version: 3.10.0
+  sklearn:
+    code: null
+    pickled_model: model.pkl
+    serialization_format: cloudpickle
+    sklearn_version: 1.7.0
+mlflow_version: 3.1.4
+model_id: m-716f80ebde1c4e5bb22cf127c5367bca
+model_size_bytes: 879
+model_uuid: m-716f80ebde1c4e5bb22cf127c5367bca
+prompts: null
+run_id: 79442e6bb3ff42c5a7ca58e4858e5f62
+utc_time_created: '2025-07-27 14:05:11.490711'
diff --git a/mlruns/0/models/m-716f80ebde1c4e5bb22cf127c5367bca/artifacts/conda.yaml b/mlruns/0/models/m-716f80ebde1c4e5bb22cf127c5367bca/artifacts/conda.yaml
@@ -0,0 +1,14 @@
+channels:
+- conda-forge
+dependencies:
+- python=3.10.0
+- pip<=21.2.3
+- pip:
+  - mlflow==3.1.4
+  - cloudpickle==3.1.1
+  - numpy==2.2.6
+  - pandas==2.3.0
+  - psutil==7.0.0
+  - scikit-learn==1.7.0
+  - scipy==1.15.3
+name: mlflow-env
diff --git a/mlruns/0/models/m-716f80ebde1c4e5bb22cf127c5367bca/artifacts/model.pkl b/mlruns/0/models/m-716f80ebde1c4e5bb22cf127c5367bca/artifacts/model.pkl
diff --git a/mlruns/0/models/m-716f80ebde1c4e5bb22cf127c5367bca/artifacts/python_env.yaml b/mlruns/0/models/m-716f80ebde1c4e5bb22cf127c5367bca/artifacts/python_env.yaml
@@ -0,0 +1,7 @@
+python: 3.10.0
+build_dependencies:
+- pip==21.2.3
+- setuptools==57.4.0
+- wheel
+dependencies:
+- -r requirements.txt
diff --git a/mlruns/0/models/m-716f80ebde1c4e5bb22cf127c5367bca/artifacts/requirements.txt b/mlruns/0/models/m-716f80ebde1c4e5bb22cf127c5367bca/artifacts/requirements.txt
@@ -0,0 +1,7 @@
+mlflow==3.1.4
+cloudpickle==3.1.1
+numpy==2.2.6
+pandas==2.3.0
+psutil==7.0.0
+scikit-learn==1.7.0
+scipy==1.15.3
diff --git a/mlruns/0/models/m-716f80ebde1c4e5bb22cf127c5367bca/meta.yaml b/mlruns/0/models/m-716f80ebde1c4e5bb22cf127c5367bca/meta.yaml
@@ -0,0 +1,10 @@
+artifact_location: file:///C:/Users/hp/mlflow-example/mlruns/0/models/m-716f80ebde1c4e5bb22cf127c5367bca/artifacts
+creation_timestamp: 1753625111456
+experiment_id: '0'
+last_updated_timestamp: 1753625116628
+model_id: m-716f80ebde1c4e5bb22cf127c5367bca
+model_type: null
+name: model
+source_run_id: 79442e6bb3ff42c5a7ca58e4858e5f62
+status: 2
+status_message: null
diff --git a/mlruns/0/models/m-716f80ebde1c4e5bb22cf127c5367bca/metrics/mae b/mlruns/0/models/m-716f80ebde1c4e5bb22cf127c5367bca/metrics/mae
@@ -0,0 +1 @@
+1753625111412 0.6278761410160693 0 79442e6bb3ff42c5a7ca58e4858e5f62
diff --git a/mlruns/0/models/m-716f80ebde1c4e5bb22cf127c5367bca/metrics/r2 b/mlruns/0/models/m-716f80ebde1c4e5bb22cf127c5367bca/metrics/r2
@@ -0,0 +1 @@
+1753625111400 0.12678721972772689 0 79442e6bb3ff42c5a7ca58e4858e5f62
diff --git a/mlruns/0/models/m-716f80ebde1c4e5bb22cf127c5367bca/metrics/rmse b/mlruns/0/models/m-716f80ebde1c4e5bb22cf127c5367bca/metrics/rmse
@@ -0,0 +1 @@
+1753625111380 0.82224284975954 0 79442e6bb3ff42c5a7ca58e4858e5f62
diff --git a/mlruns/0/models/m-716f80ebde1c4e5bb22cf127c5367bca/params/alpha b/mlruns/0/models/m-716f80ebde1c4e5bb22cf127c5367bca/params/alpha
@@ -0,0 +1 @@
+0.5
diff --git a/mlruns/0/models/m-716f80ebde1c4e5bb22cf127c5367bca/params/l1_ratio b/mlruns/0/models/m-716f80ebde1c4e5bb22cf127c5367bca/params/l1_ratio
@@ -0,0 +1 @@
+0.5
diff --git a/mlruns/0/models/m-716f80ebde1c4e5bb22cf127c5367bca/tags/mlflow.source.git.commit b/mlruns/0/models/m-716f80ebde1c4e5bb22cf127c5367bca/tags/mlflow.source.git.commit
@@ -0,0 +1 @@
+0651d1c962aa35e4dd02608c51a7b0efc2412407
diff --git a/mlruns/0/models/m-716f80ebde1c4e5bb22cf127c5367bca/tags/mlflow.source.name b/mlruns/0/models/m-716f80ebde1c4e5bb22cf127c5367bca/tags/mlflow.source.name
@@ -0,0 +1 @@
+train.py
diff --git a/mlruns/0/models/m-716f80ebde1c4e5bb22cf127c5367bca/tags/mlflow.source.type b/mlruns/0/models/m-716f80ebde1c4e5bb22cf127c5367bca/tags/mlflow.source.type
@@ -0,0 +1 @@
+LOCAL
diff --git a/mlruns/0/models/m-716f80ebde1c4e5bb22cf127c5367bca/tags/mlflow.user b/mlruns/0/models/m-716f80ebde1c4e5bb22cf127c5367bca/tags/mlflow.user
@@ -0,0 +1 @@
+hp
diff --git a/train.py b/train.py
@@ -6,6 +6,7 @@
 import warnings
 import sys
 
+#importing the necessary libraries
 import pandas as pd
 import numpy as np
 from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score
@@ -15,16 +16,15 @@
 import mlflow
 import mlflow.sklearn
 
-
+#define a function to evaluate the metrics
 def eval_metrics(actual, pred):
-    rmse = np.sqrt(mean_squared_error(actual, pred))
-    mae = mean_absolute_error(actual, pred)
-    r2 = r2_score(actual, pred)
+    rmse = np.sqrt(mean_squared_error(actual, pred)) #root mean squared error
+    mae = mean_absolute_error(actual, pred) #mean absolute error
+    r2 = r2_score(actual, pred) #R-squared score
     return rmse, mae, r2
 
-
-
 if __name__ == "__main__":
+    #ignore warnings for clean output
     warnings.filterwarnings("ignore")
     np.random.seed(40)
 
@@ -47,7 +47,7 @@ def eval_metrics(actual, pred):
     with mlflow.start_run():
         lr = ElasticNet(alpha=alpha, l1_ratio=l1_ratio, random_state=42)
         lr.fit(train_x, train_y)
-
+        # Predicting the quality of wine using the trained model
         predicted_qualities = lr.predict(test_x)
 
         (rmse, mae, r2) = eval_metrics(test_y, predicted_qualities)
@@ -56,11 +56,11 @@ def eval_metrics(actual, pred):
         print("  RMSE: %s" % rmse)
         print("  MAE: %s" % mae)
         print("  R2: %s" % r2)
-
+        # Log parameters and metrics to MLflow
         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)
-
+        # save the trained model in MLflow
         mlflow.sklearn.log_model(lr, "model")
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1,2 @@
		1753625111412 0.6278761410160693 0
		1753625111412 0.6278761410160693 0
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1,2 @@
		1753625111400 0.12678721972772689 0
		1753625111400 0.12678721972772689 0
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1,2 @@
		1753625111380 0.82224284975954 0
		1753625111380 0.82224284975954 0
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1 @@
		1753625111412 0.6278761410160693 0 79442e6bb3ff42c5a7ca58e4858e5f62
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1 @@
		1753625111400 0.12678721972772689 0 79442e6bb3ff42c5a7ca58e4858e5f62
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1 @@
		1753625111380 0.82224284975954 0 79442e6bb3ff42c5a7ca58e4858e5f62