Split RLLib and Ray Tune examples in two separate examples notebooks

.github/workflows/test-examples.yml

@@ -39,6 +39,7 @@ jobs:
           - integrations/model-training/yolov5/notebooks/Comet_and_YOLOv5.ipynb
           - integrations/model-training/yolov8/notebooks/YOLOv8_and_Comet.ipynb
           - integrations/reinforcement-learning/gymnasium/notebooks/comet_gymnasium_example.ipynb
+          - integrations/reinforcement-learning/rllib/notebooks/Comet_and_RLLib.ipynb
           - integrations/workflow-orchestration/metaflow/notebooks/metaflow_hello_world.ipynb
     env:
       NOTEBOOK_TO_TEST: ${{ matrix.notebooks }}

SageMaker/Linear_example.ipynb

@@ -36,9 +36,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "bucket = 'NAME_YOUR_BUCKET'\n",
-    "prefix = 'sagemaker/DEMO-linear-mnist'\n",
-    " \n",
+    "bucket = \"NAME_YOUR_BUCKET\"\n",
+    "prefix = \"sagemaker/DEMO-linear-mnist\"\n",
+    "\n",
     "# Define IAM role\n",
     "import boto3\n",
     "import re\n",
@@ -64,9 +64,11 @@
     "import pickle, gzip, numpy, urllib.request, json\n",
     "\n",
     "# Load the dataset\n",
-    "urllib.request.urlretrieve(\"http://deeplearning.net/data/mnist/mnist.pkl.gz\", \"mnist.pkl.gz\")\n",
-    "with gzip.open('mnist.pkl.gz', 'rb') as f:\n",
-    "    train_set, valid_set, test_set = pickle.load(f, encoding='latin1')"
+    "urllib.request.urlretrieve(\n",
+    "    \"http://deeplearning.net/data/mnist/mnist.pkl.gz\", \"mnist.pkl.gz\"\n",
+    ")\n",
+    "with gzip.open(\"mnist.pkl.gz\", \"rb\") as f:\n",
+    "    train_set, valid_set, test_set = pickle.load(f, encoding=\"latin1\")"
    ]
   },
   {
@@ -84,18 +86,20 @@
    "source": [
     "%matplotlib inline\n",
     "import matplotlib.pyplot as plt\n",
-    "plt.rcParams[\"figure.figsize\"] = (2,10)\n",
+    "\n",
+    "plt.rcParams[\"figure.figsize\"] = (2, 10)\n",
     "\n",
     "\n",
-    "def show_digit(img, caption='', subplot=None):\n",
-    "    if subplot==None:\n",
-    "        _,(subplot)=plt.subplots(1,1)\n",
-    "    imgr=img.reshape((28,28))\n",
-    "    subplot.axis('off')\n",
-    "    subplot.imshow(imgr, cmap='gray')\n",
+    "def show_digit(img, caption=\"\", subplot=None):\n",
+    "    if subplot == None:\n",
+    "        _, (subplot) = plt.subplots(1, 1)\n",
+    "    imgr = img.reshape((28, 28))\n",
+    "    subplot.axis(\"off\")\n",
+    "    subplot.imshow(imgr, cmap=\"gray\")\n",
     "    plt.title(caption)\n",
     "\n",
-    "show_digit(train_set[0][30], 'This is a {}'.format(train_set[1][30]))"
+    "\n",
+    "show_digit(train_set[0][30], \"This is a {}\".format(train_set[1][30]))"
    ]
   },
   {
@@ -115,8 +119,10 @@
     "import numpy as np\n",
     "import sagemaker.amazon.common as smac\n",
     "\n",
-    "vectors = np.array([t.tolist() for t in train_set[0]]).astype('float32')\n",
-    "labels = np.where(np.array([t.tolist() for t in train_set[1]]) == 0, 1, 0).astype('float32')\n",
+    "vectors = np.array([t.tolist() for t in train_set[0]]).astype(\"float32\")\n",
+    "labels = np.where(np.array([t.tolist() for t in train_set[1]]) == 0, 1, 0).astype(\n",
+    "    \"float32\"\n",
+    ")\n",
     "\n",
     "buf = io.BytesIO()\n",
     "smac.write_numpy_to_dense_tensor(buf, vectors, labels)\n",
@@ -139,10 +145,12 @@
     "import boto3\n",
     "import os\n",
     "\n",
-    "key = 'recordio-pb-data'\n",
-    "boto3.resource('s3').Bucket(bucket).Object(os.path.join(prefix, 'train', key)).upload_fileobj(buf)\n",
-    "s3_train_data = 's3://{}/{}/train/{}'.format(bucket, prefix, key)\n",
-    "print('uploaded training data location: {}'.format(s3_train_data))"
+    "key = \"recordio-pb-data\"\n",
+    "boto3.resource(\"s3\").Bucket(bucket).Object(\n",
+    "    os.path.join(prefix, \"train\", key)\n",
+    ").upload_fileobj(buf)\n",
+    "s3_train_data = \"s3://{}/{}/train/{}\".format(bucket, prefix, key)\n",
+    "print(\"uploaded training data location: {}\".format(s3_train_data))"
    ]
   },
   {
@@ -158,8 +166,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "output_location = 's3://{}/{}/output'.format(bucket, prefix)\n",
-    "print('training artifacts will be uploaded to: {}'.format(output_location))"
+    "output_location = \"s3://{}/{}/output\".format(bucket, prefix)\n",
+    "print(\"training artifacts will be uploaded to: {}\".format(output_location))"
    ]
   },
   {
@@ -176,7 +184,8 @@
    "outputs": [],
    "source": [
     "from sagemaker.amazon.amazon_estimator import get_image_uri\n",
-    "container = get_image_uri(boto3.Session().region_name, 'linear-learner')"
+    "\n",
+    "container = get_image_uri(boto3.Session().region_name, \"linear-learner\")"
    ]
   },
   {
@@ -190,17 +199,19 @@
     "\n",
     "sess = sagemaker.Session()\n",
     "\n",
-    "linear = sagemaker.estimator.Estimator(container,\n",
-    "                                       role, \n",
-    "                                       train_instance_count=1, \n",
-    "                                       train_instance_type='ml.c4.xlarge',\n",
-    "                                       output_path=output_location,\n",
-    "                                       sagemaker_session=sess)\n",
-    "linear.set_hyperparameters(feature_dim=784,\n",
-    "                           predictor_type='binary_classifier',\n",
-    "                           mini_batch_size=200)\n",
+    "linear = sagemaker.estimator.Estimator(\n",
+    "    container,\n",
+    "    role,\n",
+    "    train_instance_count=1,\n",
+    "    train_instance_type=\"ml.c4.xlarge\",\n",
+    "    output_path=output_location,\n",
+    "    sagemaker_session=sess,\n",
+    ")\n",
+    "linear.set_hyperparameters(\n",
+    "    feature_dim=784, predictor_type=\"binary_classifier\", mini_batch_size=200\n",
+    ")\n",
     "\n",
-    "linear.fit({'train': s3_train_data})"
+    "linear.fit({\"train\": s3_train_data})"
    ]
   },
   {
@@ -214,7 +225,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Define your Comet [REST API](https://www.comet.ml/docs/rest-api/getting-started/) and your [workspace](https://www.comet.ml/docs/user-interface/#workspaces). See the [configuration documentation](http://docs.comet.ml/python-sdk/advanced/#python-configuration) for info on both specifications."
+    "Define your Comet [REST API](https://www.comet.com/docs/rest-api/getting-started/) and your [workspace](https://www.comet.com/docs/user-interface/#workspaces). See the [configuration documentation](http://docs.comet.ml/python-sdk/advanced/#python-configuration) for info on both specifications."
    ]
   },
   {
@@ -264,7 +275,9 @@
    "source": [
     "# .log_sagemaker_job(regressor/estimator object from Sagemaker SDK, Comet Rest API key (optional, can be taken from usual config source), workspace (comet), project (comet))\n",
     "# I have used the Sagemaker SDK to train a model. I have the estimator/regressor object. I want to log whatever I just trained\n",
-    "experiment = comet_ml_sagemaker.log_sagemaker_job(linear, api_key=COMET_REST_API, workspace=COMET_WORKSPACE, project_name=\"sagemaker\")\n",
+    "experiment = comet_ml_sagemaker.log_sagemaker_job(\n",
+    "    linear, api_key=COMET_REST_API, workspace=COMET_WORKSPACE, project_name=\"sagemaker\"\n",
+    ")\n",
     "print(experiment.url)"
    ]
   },
@@ -290,7 +303,12 @@
     "# I have the name of a completed training job I want to lob\n",
     "# Same as .log_sagemaker_job, except instead of passing the regressor/estimator object, you pass the job name\n",
     "SAGEMAKER_TRAINING_JOB_NAME = \"SAGEMAKER_TRAINING_JOB_NAME\"\n",
-    "experiment = comet_ml_sagemaker.log_sagemaker_job_by_name(SAGEMAKER_TRAINING_JOB_NAME, api_key=COMET_REST_API, workspace=COMET_WORKSPACE, project_name=\"sagemaker\")\n",
+    "experiment = comet_ml_sagemaker.log_sagemaker_job_by_name(\n",
+    "    SAGEMAKER_TRAINING_JOB_NAME,\n",
+    "    api_key=COMET_REST_API,\n",
+    "    workspace=COMET_WORKSPACE,\n",
+    "    project_name=\"sagemaker\",\n",
+    ")\n",
     "print(experiment.url)"
    ]
   },
@@ -313,7 +331,9 @@
    "outputs": [],
    "source": [
     "# Logs the last job for your current Amazon Region / S3\n",
-    "experiment = comet_ml_sagemaker.log_last_sagemaker_job(api_key=COMET_REST_API, workspace=COMET_WORKSPACE, project_name=\"sagemaker\")\n",
+    "experiment = comet_ml_sagemaker.log_last_sagemaker_job(\n",
+    "    api_key=COMET_REST_API, workspace=COMET_WORKSPACE, project_name=\"sagemaker\"\n",
+    ")\n",
     "print(experiment.url)"
    ]
   },

SageMaker/random_forest.ipynb

@@ -41,26 +41,28 @@
     "import sys\n",
     "\n",
     "\n",
-    "bucket = 'NAME_YOUR_BUCKET'   # <--- specify a bucket you have access to\n",
-    "prefix = 'sagemaker/rcf-benchmarks'\n",
+    "bucket = \"NAME_YOUR_BUCKET\"  # <--- specify a bucket you have access to\n",
+    "prefix = \"sagemaker/rcf-benchmarks\"\n",
     "execution_role = sagemaker.get_execution_role()\n",
     "\n",
     "\n",
     "# check if the bucket exists\n",
     "try:\n",
-    "    boto3.Session().client('s3').head_bucket(Bucket=bucket)\n",
+    "    boto3.Session().client(\"s3\").head_bucket(Bucket=bucket)\n",
     "except botocore.exceptions.ParamValidationError as e:\n",
-    "    print('Hey! You either forgot to specify your S3 bucket'\n",
-    "          ' or you gave your bucket an invalid name!')\n",
+    "    print(\n",
+    "        \"Hey! You either forgot to specify your S3 bucket\"\n",
+    "        \" or you gave your bucket an invalid name!\"\n",
+    "    )\n",
     "except botocore.exceptions.ClientError as e:\n",
-    "    if e.response['Error']['Code'] == '403':\n",
+    "    if e.response[\"Error\"][\"Code\"] == \"403\":\n",
     "        print(\"Hey! You don't have permission to access the bucket, {}.\".format(bucket))\n",
-    "    elif e.response['Error']['Code'] == '404':\n",
+    "    elif e.response[\"Error\"][\"Code\"] == \"404\":\n",
     "        print(\"Hey! Your bucket, {}, doesn't exist!\".format(bucket))\n",
     "    else:\n",
     "        raise\n",
     "else:\n",
-    "    print('Training input/output will be stored in: s3://{}/{}'.format(bucket, prefix))"
+    "    print(\"Training input/output will be stored in: s3://{}/{}\".format(bucket, prefix))"
    ]
   },
   {
@@ -81,11 +83,11 @@
     "import pandas as pd\n",
     "import urllib.request\n",
     "\n",
-    "data_filename = 'nyc_taxi.csv'\n",
-    "data_source = 'https://raw.githubusercontent.com/numenta/NAB/master/data/realKnownCause/nyc_taxi.csv'\n",
+    "data_filename = \"nyc_taxi.csv\"\n",
+    "data_source = \"https://raw.githubusercontent.com/numenta/NAB/master/data/realKnownCause/nyc_taxi.csv\"\n",
     "\n",
     "urllib.request.urlretrieve(data_source, data_filename)\n",
-    "taxi_data = pd.read_csv(data_filename, delimiter=',')"
+    "taxi_data = pd.read_csv(data_filename, delimiter=\",\")"
    ]
   },
   {
@@ -108,16 +110,18 @@
     "session = sagemaker.Session()\n",
     "\n",
     "# specify general training job information\n",
-    "rcf = RandomCutForest(role=execution_role,\n",
-    "                      train_instance_count=1,\n",
-    "                      train_instance_type='ml.m4.xlarge',\n",
-    "                      data_location='s3://{}/{}/'.format(bucket, prefix),\n",
-    "                      output_path='s3://{}/{}/output'.format(bucket, prefix),\n",
-    "                      num_samples_per_tree=512,\n",
-    "                      num_trees=50)\n",
+    "rcf = RandomCutForest(\n",
+    "    role=execution_role,\n",
+    "    train_instance_count=1,\n",
+    "    train_instance_type=\"ml.m4.xlarge\",\n",
+    "    data_location=\"s3://{}/{}/\".format(bucket, prefix),\n",
+    "    output_path=\"s3://{}/{}/output\".format(bucket, prefix),\n",
+    "    num_samples_per_tree=512,\n",
+    "    num_trees=50,\n",
+    ")\n",
     "\n",
     "# automatically upload the training data to S3 and run the training job\n",
-    "rcf.fit(rcf.record_set(taxi_data.value.as_matrix().reshape(-1,1)))"
+    "rcf.fit(rcf.record_set(taxi_data.value.as_matrix().reshape(-1, 1)))"
    ]
   },
   {
@@ -131,7 +135,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Define your Comet [REST API](https://www.comet.ml/docs/rest-api/getting-started/) and your [workspace](https://www.comet.ml/docs/user-interface/#workspaces). See the [configuration documentation](http://docs.comet.ml/python-sdk/advanced/#python-configuration) for info on both specifications."
+    "Define your Comet [REST API](https://www.comet.com/docs/rest-api/getting-started/) and your [workspace](https://www.comet.com/docs/user-interface/#workspaces). See the [configuration documentation](http://docs.comet.ml/python-sdk/advanced/#python-configuration) for info on both specifications."
    ]
   },
   {
@@ -181,7 +185,9 @@
    "source": [
     "# .log_sagemaker_job(regressor/estimator object from Sagemaker SDK, Comet Rest API key (optional, can be taken from usual config source), workspace (comet), project (comet))\n",
     "# I have used the Sagemaker SDK to train a model. I have the estimator/regressor object. I want to log whatever I just trained\n",
-    "experiment = comet_ml_sagemaker.log_sagemaker_job(rcf, api_key=COMET_REST_API, workspace=COMET_WORKSPACE, project_name=\"sagemaker\")\n",
+    "experiment = comet_ml_sagemaker.log_sagemaker_job(\n",
+    "    rcf, api_key=COMET_REST_API, workspace=COMET_WORKSPACE, project_name=\"sagemaker\"\n",
+    ")\n",
     "print(experiment.url)\n",
     "experiment.add_tags([\"random_forest\"])"
    ]
@@ -208,7 +214,12 @@
     "# I have the name of a completed training job I want to lob\n",
     "# Same as .log_sagemaker_job, except instead of passing the regressor/estimator object, you pass the job name\n",
     "SAGEMAKER_TRAINING_JOB_NAME = \"SAGEMAKER_TRAINING_JOB_NAME\"\n",
-    "experiment = comet_ml_sagemaker.log_sagemaker_job_by_name(SAGEMAKER_TRAINING_JOB_NAME, api_key=COMET_REST_API, workspace=COMET_WORKSPACE, project_name=\"sagemaker\")\n",
+    "experiment = comet_ml_sagemaker.log_sagemaker_job_by_name(\n",
+    "    SAGEMAKER_TRAINING_JOB_NAME,\n",
+    "    api_key=COMET_REST_API,\n",
+    "    workspace=COMET_WORKSPACE,\n",
+    "    project_name=\"sagemaker\",\n",
+    ")\n",
     "print(experiment.url)"
    ]
   },
@@ -231,7 +242,9 @@
    "outputs": [],
    "source": [
     "# Logs the last job for your current Amazon Region / S3\n",
-    "experiment = comet_ml_sagemaker.log_last_sagemaker_job(api_key=COMET_REST_API, workspace=COMET_WORKSPACE, project_name=\"sagemaker\")\n",
+    "experiment = comet_ml_sagemaker.log_last_sagemaker_job(\n",
+    "    api_key=COMET_REST_API, workspace=COMET_WORKSPACE, project_name=\"sagemaker\"\n",
+    ")\n",
     "print(experiment.url)\n",
     "experiment.add_tags([\"random_forest\"])"
    ]

catalyst/comet_catalyst_example.py

@@ -1,27 +1,33 @@
-import comet_ml
+# coding: utf-8
+
 import os
+
+import comet_ml
+
 from torch import nn, optim
 from torch.utils.data import DataLoader
+
 from catalyst import dl
+from catalyst.contrib.datasets import MNIST
 from catalyst.data import ToTensor
 from catalyst.loggers.comet import CometLogger
-from catalyst.contrib.datasets import MNIST
 
-comet_ml.init()
+comet_ml.login()
 logger = CometLogger(logging_frequency=10)
 
 model = nn.Sequential(nn.Flatten(), nn.Linear(28 * 28, 10))
 criterion = nn.CrossEntropyLoss()
 optimizer = optim.Adam(model.parameters(), lr=0.02)
 
 
-
 loaders = {
     "train": DataLoader(
-        MNIST(os.getcwd(), train=True, download=True, transform=ToTensor()), batch_size=32
+        MNIST(os.getcwd(), train=True, download=True, transform=ToTensor()),
+        batch_size=32,
     ),
     "valid": DataLoader(
-        MNIST(os.getcwd(), train=False, download=True, transform=ToTensor()), batch_size=32
+        MNIST(os.getcwd(), train=False, download=True, transform=ToTensor()),
+        batch_size=32,
     ),
 }
 
@@ -37,14 +43,16 @@
     loaders=loaders,
     num_epochs=1,
     hparams={
-        'lr': 0.02,
-        'betas': (0.9, 0.999),
-        'eps': 1e-08,
-        'weight_decay': 0,
-        'amsgrad': False       
+        "lr": 0.02,
+        "betas": (0.9, 0.999),
+        "eps": 1e-08,
+        "weight_decay": 0,
+        "amsgrad": False,
     },
     callbacks=[
-        dl.AccuracyCallback(input_key="logits", target_key="targets", topk_args=(1, 3, 5)),
+        dl.AccuracyCallback(
+            input_key="logits", target_key="targets", topk_args=(1, 3, 5)
+        ),
         dl.PrecisionRecallF1SupportCallback(
             input_key="logits", target_key="targets", num_classes=10
         ),
@@ -55,7 +63,5 @@
     minimize_valid_metric=True,
     verbose=True,
     load_best_on_end=True,
-    loggers={
-        "comet": logger
-    }
-)
+    loggers={"comet": logger},
+)

guides/manage_data/Introduction_to_Artifacts.ipynb

@@ -534,7 +534,7 @@
         "\n",
         "We hope you enjoyed this introductory guide to Artifacts, a simple, light weight way to version your datasets and models, while providing information about the lineage of your data through your experiments. \n",
         "\n",
-        "Interested in learning more about Artifacts? Check out the [docs](https://www.comet.ml/docs/user-interface/artifacts/?utm_campaign-artifacts-launch&utm_source=colab-example&utm_medium=additional-resources)"
+        "Interested in learning more about Artifacts? Check out the [docs](https://www.comet.com/docs/v2/guides/artifacts/using-artifacts/?utm_campaign-artifacts-launch&utm_source=colab-example&utm_medium=additional-resources)"
       ]
     }
   ],