Start updating examples to use comet_ml.start

comet-ml · Oct 22, 2024 · ced0900 · ced0900
1 parent 9c88d5d
commit ced0900
Show file tree

Hide file tree

Showing 99 changed files with 1,038 additions and 171,390 deletions.
diff --git a/distributed-optimizer/initialize_optimizer.py b/distributed-optimizer/initialize_optimizer.py
@@ -1,35 +1,30 @@
-import comet_ml
-import sys
+# -*- coding: utf-8 -*-
+from comet_ml import Optimizer
 
-from comet_ml import Experiment, Optimizer
 
 def run():
 
     opt_config = {
-
         # We pick the Bayes algorithm:
         "algorithm": "grid",
-
         # Declare your hyperparameters in the Vizier-inspired format:
         "parameters": {
             "x": {"type": "integer", "min": 1, "max": 5},
         },
-
         # Declare what we will be optimizing, and how:
         "spec": {
-        "metric": "loss",
+            "metric": "loss",
             "objective": "minimize",
-        }
+        },
     }
 
     # initialize the optimizer object
-    opt = Optimizer(
-        config=opt_config
-    )
-
+    opt = Optimizer(config=opt_config)
+
     # print Optimizer id
     optimizer_id = opt.get_id()
     print(optimizer_id)
 
-if __name__ == '__main__':
-    run()
+
+if __name__ == "__main__":
+    run()
diff --git a/distributed-optimizer/run_optimizer.py b/distributed-optimizer/run_optimizer.py
@@ -1,14 +1,14 @@
-import comet_ml
-import sys
+# -*- coding: utf-8 -*-
 import time
 
-from comet_ml import Experiment, Optimizer
+from comet_ml import Optimizer
 
-def run():  
+
+def run():
 
     # access existing Optimizer object using key
-    opt = Optimizer()   
-    
+    opt = Optimizer()
+
     # loop over experiments in Optimizer generator
     for experiment in opt.get_experiments():
         x = experiment.get_parameter("x")
@@ -22,5 +22,5 @@ def run():
         time.sleep(60)
 
 
-if __name__ == '__main__':
-    run()
+if __name__ == "__main__":
+    run()
diff --git a/guides/MPM/end_to_end_example/data_processing/data_processing.py b/guides/MPM/end_to_end_example/data_processing/data_processing.py
@@ -1,68 +1,92 @@
+# -*- coding: utf-8 -*-
+import os
+from io import StringIO
+
 import comet_ml
+
 import pandas as pd
-from io import StringIO
-import os
+
 
 def get_raw_data(workspace_name: str, artifact_name: str):
     """
-    In this function, we will check if the raw data exists in Comet Artifacts. If it does, we will download it from there,
-    if not we will upload it from the local directory.
+    In this function, we will check if the raw data exists in Comet Artifacts. If it
+    does, we will download it from there, if not we will upload it from the local
+    directory.
 
-    Once the file is available locally, we will load it into a pandas dataframe and return it.
+    Once the file is available locally, we will load it into a pandas dataframe and
+    return it.
     """
     exp = comet_ml.get_running_experiment()
 
     try:
         artifact = exp.get_artifact(artifact_name=f"{artifact_name}_raw")
-        
+
         # Download the artifact
         artifact.download(path="./")
     except Exception as e:
         print(f"Error downloading artifact: {e}")
-        artifact = comet_ml.Artifact(name=f"{artifact_name}_raw", artifact_type="dataset")
+        artifact = comet_ml.Artifact(
+            name=f"{artifact_name}_raw", artifact_type="dataset"
+        )
         artifact.add("./credit_scoring_dataset.csv")
         exp.log_artifact(artifact)
-    
+
     df = pd.read_csv("./credit_scoring_dataset.csv")
     return df
 
+
 def preprocess_data(df: pd.DataFrame):
     """
-    In this function, we will preprocess the data to make it ready for the model. We will store the preprocessed data in a 
-    new Comet Artifact.
+    In this function, we will preprocess the data to make it ready for the model. We
+    will store the preprocessed data in a new Comet Artifact.
     """
     # Select the relevant columns
-    df = df.loc[:, ['CustAge', 'CustIncome', 'EmpStatus', 'UtilRate', 'OtherCC', 'ResStatus', 'TmAtAddress', 'TmWBank',
-                    'probdefault']]
-
+    df = df.loc[
+        :,
+        [
+            "CustAge",
+            "CustIncome",
+            "EmpStatus",
+            "UtilRate",
+            "OtherCC",
+            "ResStatus",
+            "TmAtAddress",
+            "TmWBank",
+            "probdefault",
+        ],
+    ]
+
     # Rename the target column
-    df.rename({'probdefault': 'probability_default'}, inplace=True, axis=1)
+    df.rename({"probdefault": "probability_default"}, inplace=True, axis=1)
 
     # Convert the categorical columns to category type
-    for c in ['EmpStatus', 'OtherCC', 'ResStatus']:
-        df[c] = df[c].astype('category')
-    
+    for c in ["EmpStatus", "OtherCC", "ResStatus"]:
+        df[c] = df[c].astype("category")
+
     # Save the preprocessed data to a new Comet Artifact
     csv_buffer = StringIO()
     df.to_csv(csv_buffer, index=False)
     csv_buffer.seek(0)
-
-    artifact = comet_ml.Artifact(name=f"{artifact_name}_preprocessed", artifact_type="dataset")
+
+    artifact = comet_ml.Artifact(
+        name=f"{artifact_name}_preprocessed", artifact_type="dataset"
+    )
     artifact.add(local_path_or_data=csv_buffer, logical_path="preprocessed_data.csv")
-    
+
     exp = comet_ml.get_running_experiment()
     exp.log_artifact(artifact)
-    
+
     return df
-
+
+
 if __name__ == "__main__":
     workspace_name = os.environ["COMET_WORKSPACE"]
     project_name = os.environ["COMET_PROJECT_NAME"]
-    artifact_name = os.environ["COMET_PROJECT_NAME"]
+    artifact_name = os.environ["COMET_ARTIFACT_NAME"]
 
-    exp = comet_ml.Experiment(workspace=workspace_name, project_name=project_name)
-    df =  get_raw_data(workspace_name, artifact_name)
+    exp = comet_ml.start(workspace=workspace_name, project_name=project_name)
+    df = get_raw_data(workspace_name, artifact_name)
 
     processed_df = preprocess_data(df)
 
-    print("Data preprocessing complete.")
+    print("Data preprocessing complete.")
diff --git a/guides/MPM/end_to_end_example/training/model_training.py b/guides/MPM/end_to_end_example/training/model_training.py
@@ -1,68 +1,65 @@
+# -*- coding: utf-8 -*-
+import os
+
 import comet_ml
 
-import os
-import pandas as pd
-import numpy as np
 import lightgbm as lgb
+import numpy as np
+import pandas as pd
+
 
 def get_training_data(artifact_name: str) -> pd.DataFrame:
     exp = comet_ml.get_running_experiment()
 
     artifact = exp.get_artifact(artifact_name)
     artifact.download(path="./")
-    
+
     df = pd.read_csv("preprocessed_data.csv")
-    for c in ['EmpStatus', 'OtherCC', 'ResStatus']:
-        df[c] = df[c].astype('category')
+    for c in ["EmpStatus", "OtherCC", "ResStatus"]:
+        df[c] = df[c].astype("category")
 
     return df
 
+
 def train_model(training_data: pd.DataFrame, model_name: str) -> lgb.Booster:
-    exp = comet_ml.get_running_experiment()
-
     # Create training dataset
-    X_train = training_data.drop('probability_default', axis=1)
-    y_train = (training_data['probability_default'] >= 0.5)
+    X_train = training_data.drop("probability_default", axis=1)
+    y_train = training_data["probability_default"] >= 0.5
 
-    training_dataset = lgb.Dataset(data = X_train,
-                                   label = y_train)
+    training_dataset = lgb.Dataset(data=X_train, label=y_train)
 
     # Train model
     params = {
-        'num_iterations': 30,
-        'max_depth': 2,
-        'objective': 'binary',
-        'metric': ['auc', 'average_precision', 'l1', 'l2']
+        "num_iterations": 30,
+        "max_depth": 2,
+        "objective": "binary",
+        "metric": ["auc", "average_precision", "l1", "l2"],
     }
-    model = lgb.train(params = params,
-                      train_set = training_dataset,
-                      valid_sets = training_dataset)
+    model = lgb.train(
+        params=params, train_set=training_dataset, valid_sets=training_dataset
+    )
 
     # Evaluate model
     y_pred = np.where(model.predict(X_train) > 0.5, 1, 0)
-    experiment.log_confusion_matrix(
-        y_true=y_train,
-        y_predicted=y_pred
-    )
+    experiment.log_confusion_matrix(y_true=y_train, y_predicted=y_pred)
 
     # Save model and log to Comet
-    model.save_model('./model.txt')
-    experiment.log_model(model_name, './model.txt')
-    os.remove('./model.txt')
+    model.save_model("./model.txt")
+    experiment.log_model(model_name, "./model.txt")
+    os.remove("./model.txt")
 
     return model
-
 
-if __name__ == '__main__':
+
+if __name__ == "__main__":
     ARTIFACT_NAME = os.environ["COMET_PROJECT_NAME"]
     WORKSPACE = os.environ["COMET_WORKSPACE"]
     MODEL_REGISTRY_NAME = os.environ["COMET_MODEL_REGISTRY_NAME"]
-    
+
     # Model training script
-    experiment = comet_ml.Experiment()
+    experiment = comet_ml.start()
+
+    training_data = get_training_data(artifact_name=f"{ARTIFACT_NAME}_preprocessed")
+    model = train_model(training_data, model_name=MODEL_REGISTRY_NAME)
 
-    training_data = get_training_data(artifact_name = f"{ARTIFACT_NAME}_preprocessed")
-    model = train_model(training_data, model_name = MODEL_REGISTRY_NAME)
-
-
-    experiment.register_model(MODEL_REGISTRY_NAME)
+    experiment.register_model(MODEL_REGISTRY_NAME)
diff --git a/guides/advanced/Running_Offline_Experiments.ipynb b/guides/advanced/Running_Offline_Experiments.ipynb
@@ -59,7 +59,7 @@
    },
    "outputs": [],
    "source": [
-    "experiment = comet_ml.OfflineExperiment()\n",
+    "experiment = comet_ml.start(online=False)\n",
     "experiment.log_metrics({\"accuracy\": 0.5, \"loss\": 0.001})\n",
     "experiment.end()"
    ]
@@ -92,29 +92,30 @@
    "source": [
     "!comet upload /content/.cometml-runs/*.zip"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "id": "lxMv2erXgLtD"
-   },
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
   "colab": {
    "provenance": []
   },
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
    "name": "python3"
   },
   "language_info": {
-   "name": "python"
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 0
+ "nbformat_minor": 4
 }
diff --git a/guides/computer_vision/Computer_Vision_with_Comet.ipynb b/guides/computer_vision/Computer_Vision_with_Comet.ipynb
@@ -89,7 +89,7 @@
     "comet_ml.login(project_name=\"comet-example-pytorch-image-classification-svhn\")\n",
     "\n",
     "# Create the Comet Experiment for logging\n",
-    "experiment = comet_ml.Experiment()"
+    "experiment = comet_ml.start()"
    ]
   },
   {

diff --git a/guides/get-started/Comet_Quickstart.ipynb b/guides/get-started/Comet_Quickstart.ipynb
@@ -138,7 +138,7 @@
    },
    "outputs": [],
    "source": [
-    "experiment = comet_ml.Experiment()"
+    "experiment = comet_ml.start()"
    ]
   },
   {
@@ -304,7 +304,7 @@
     "from tqdm import tqdm\n",
     "\n",
     "# Create an Experiment\n",
-    "experiment = comet_ml.Experiment()\n",
+    "experiment = comet_ml.start()\n",
     "\n",
     "hyper_params = {\"batch_size\": 100, \"num_epochs\": 2, \"learning_rate\": 0.01}\n",
     "experiment.log_parameters(hyper_params)\n",
@@ -571,7 +571,7 @@
     "\n",
     "from tensorflow import keras\n",
     "\n",
-    "experiment = comet_ml.Experiment(\n",
+    "experiment = comet_ml.start(\n",
     "    auto_histogram_weight_logging=True,\n",
     "    auto_histogram_gradient_logging=True,\n",
     "    auto_histogram_activation_logging=True,\n",

diff --git a/guides/get-started/Comet_Quickstart.py b/guides/get-started/Comet_Quickstart.py
@@ -13,7 +13,7 @@
 # A Comet Experiment is a unit of measurable research that defines a single
 # run with some data/parameters/code/metrics.
 
-experiment = comet_ml.Experiment()
+experiment = comet_ml.start()
 
 
 # Comet supports logging metrics, parameters, source code, system information,