updated to Ray 2.7

README.md

@@ -108,6 +108,7 @@ touch .env
 ```bash
 # Inside .env
 GITHUB_USERNAME="CHANGE_THIS_TO_YOUR_USERNAME"  # ← CHANGE THIS
+```
 ```bash
 source .env
 ```
@@ -120,8 +121,6 @@ Now we're ready to clone the repository that has all of our code:
 
 ```bash
 git clone https://github.com/GokuMohandas/Made-With-ML.git .
-git remote set-url origin https://github.com/$GITHUB_USERNAME/Made-With-ML.git  # <-- CHANGE THIS to your username
-git checkout -b dev
 ```
 
 ### Virtual environment
@@ -289,7 +288,6 @@ python madewithml/evaluate.py \
 
 ### Inference
 ```bash
-# Get run ID
 export EXPERIMENT_NAME="llm"
 export RUN_ID=$(python madewithml/predict.py get-best-run-id --experiment-name $EXPERIMENT_NAME --metric val_loss --mode ASC)
 python madewithml/predict.py predict \
@@ -485,17 +483,23 @@ We're not going to manually deploy our application every time we make a change.
   <img src="https://madewithml.com/static/images/mlops/cicd/cicd.png">
 </div>
 
-1. We'll start by adding the necessary credentials to the [`/settings/secrets/actions`](https://github.com/GokuMohandas/Made-With-ML/settings/secrets/actions) page of our GitHub repository.
+1. Create a new github branch to save our changes to and execute CI/CD workloads:
+```bash
+git remote set-url origin https://github.com/$GITHUB_USERNAME/Made-With-ML.git  # <-- CHANGE THIS to your username
+git checkout -b dev
+```
+
+2. We'll start by adding the necessary credentials to the [`/settings/secrets/actions`](https://github.com/GokuMohandas/Made-With-ML/settings/secrets/actions) page of our GitHub repository.
 
 ``` bash
 export ANYSCALE_HOST=https://console.anyscale.com
 export ANYSCALE_CLI_TOKEN=$YOUR_CLI_TOKEN  # retrieved from https://console.anyscale.com/o/madewithml/credentials
 ```
 
-2. Now we can make changes to our code (not on `main` branch) and push them to GitHub. But in order to push our code to GitHub, we'll need to first authenticate with our credentials before pushing to our repository:
+3. Now we can make changes to our code (not on `main` branch) and push them to GitHub. But in order to push our code to GitHub, we'll need to first authenticate with our credentials before pushing to our repository:
 
 ```bash
-git config --global user.name "Your Name"  # <-- CHANGE THIS to your name
+git config --global user.name $GITHUB_USERNAME  # <-- CHANGE THIS to your username
 git config --global user.email you@example.com  # <-- CHANGE THIS to your email
 git add .
 git commit -m ""  # <-- CHANGE THIS to your message
@@ -504,13 +508,13 @@ git push origin dev
 
 Now you will be prompted to enter your username and password (personal access token). Follow these steps to get personal access token: [New GitHub personal access token](https://github.com/settings/tokens/new) → Add a name → Toggle `repo` and `workflow` → Click `Generate token` (scroll down) → Copy the token and paste it when prompted for your password.
 
-3. Now we can start a PR from this branch to our `main` branch and this will trigger the [workloads workflow](/.github/workflows/workloads.yaml). If the workflow (Anyscale Jobs) succeeds, this will produce comments with the training and evaluation results directly on the PR.
+4. Now we can start a PR from this branch to our `main` branch and this will trigger the [workloads workflow](/.github/workflows/workloads.yaml). If the workflow (Anyscale Jobs) succeeds, this will produce comments with the training and evaluation results directly on the PR.
 
 <div align="center">
   <img src="https://madewithml.com/static/images/mlops/cicd/comments.png">
 </div>
 
-4. If we like the results, we can merge the PR into the `main` branch. This will trigger the [serve workflow](/.github/workflows/serve.yaml) which will rollout our new service to production!
+5. If we like the results, we can merge the PR into the `main` branch. This will trigger the [serve workflow](/.github/workflows/serve.yaml) which will rollout our new service to production!
 
 ### Continual learning
 

madewithml/config.py

@@ -5,7 +5,6 @@
 from pathlib import Path
 
 import mlflow
-import pretty_errors  # NOQA: F401 (imported but unused)
 
 # Directories
 ROOT_DIR = Path(__file__).parent.parent.absolute()

madewithml/data.py

@@ -5,7 +5,6 @@
 import pandas as pd
 import ray
 from ray.data import Dataset
-from ray.data.preprocessor import Preprocessor
 from sklearn.model_selection import train_test_split
 from transformers import BertTokenizer
 
@@ -135,13 +134,18 @@ def preprocess(df: pd.DataFrame, class_to_index: Dict) -> Dict:
     return outputs
 
 
-class CustomPreprocessor(Preprocessor):
+class CustomPreprocessor:
     """Custom preprocessor class."""
 
-    def _fit(self, ds):
+    def __init__(self, class_to_index={}):
+        self.class_to_index = class_to_index or {}  # mutable defaults
+        self.index_to_class = {v: k for k, v in self.class_to_index.items()}
+
+    def fit(self, ds):
         tags = ds.unique(column="tag")
         self.class_to_index = {tag: i for i, tag in enumerate(tags)}
         self.index_to_class = {v: k for k, v in self.class_to_index.items()}
+        return self
 
-    def _transform_pandas(self, batch):  # could also do _transform_numpy
-        return preprocess(batch, class_to_index=self.class_to_index)
+    def transform(self, ds):
+        return ds.map_batches(preprocess, fn_kwargs={"class_to_index": self.class_to_index}, batch_format="pandas")

madewithml/evaluate.py

@@ -8,13 +8,13 @@
 import ray.train.torch  # NOQA: F401 (imported but unused)
 import typer
 from ray.data import Dataset
-from ray.train.torch.torch_predictor import TorchPredictor
 from sklearn.metrics import precision_recall_fscore_support
 from snorkel.slicing import PandasSFApplier, slicing_function
 from typing_extensions import Annotated
 
 from madewithml import predict, utils
 from madewithml.config import logger
+from madewithml.predict import TorchPredictor
 
 # Initialize Typer CLI app
 app = typer.Typer()
@@ -133,8 +133,8 @@ def evaluate(
     y_true = np.stack([item["targets"] for item in values])
 
     # y_pred
-    z = predictor.predict(data=ds.to_pandas())["predictions"]
-    y_pred = np.stack(z).argmax(1)
+    predictions = preprocessed_ds.map_batches(predictor).take_all()
+    y_pred = np.array([d["output"] for d in predictions])
 
     # Metrics
     metrics = {

madewithml/models.py

@@ -1,13 +1,20 @@
+import json
+import os
+from pathlib import Path
+
 import torch
 import torch.nn as nn
+import torch.nn.functional as F
+from transformers import BertModel
 
 
-class FinetunedLLM(nn.Module):  # pragma: no cover, torch model
-    """Model architecture for a Large Language Model (LLM) that we will fine-tune."""
-
+class FinetunedLLM(nn.Module):
     def __init__(self, llm, dropout_p, embedding_dim, num_classes):
         super(FinetunedLLM, self).__init__()
         self.llm = llm
+        self.dropout_p = dropout_p
+        self.embedding_dim = embedding_dim
+        self.num_classes = num_classes
         self.dropout = torch.nn.Dropout(dropout_p)
         self.fc1 = torch.nn.Linear(embedding_dim, num_classes)
 
@@ -17,3 +24,36 @@ def forward(self, batch):
         z = self.dropout(pool)
         z = self.fc1(z)
         return z
+
+    @torch.inference_mode()
+    def predict(self, batch):
+        self.eval()
+        z = self(batch)
+        y_pred = torch.argmax(z, dim=1).cpu().numpy()
+        return y_pred
+
+    @torch.inference_mode()
+    def predict_proba(self, batch):
+        self.eval()
+        z = self(batch)
+        y_probs = F.softmax(z, dim=1).cpu().numpy()
+        return y_probs
+
+    def save(self, dp):
+        with open(Path(dp, "args.json"), "w") as fp:
+            contents = {
+                "dropout_p": self.dropout_p,
+                "embedding_dim": self.embedding_dim,
+                "num_classes": self.num_classes,
+            }
+            json.dump(contents, fp, indent=4, sort_keys=False)
+        torch.save(self.state_dict(), os.path.join(dp, "model.pt"))
+
+    @classmethod
+    def load(cls, args_fp, state_dict_fp):
+        with open(args_fp, "r") as fp:
+            kwargs = json.load(fp=fp)
+        llm = BertModel.from_pretrained("allenai/scibert_scivocab_uncased", return_dict=False)
+        model = cls(llm=llm, **kwargs)
+        model.load_state_dict(torch.load(state_dict_fp, map_location=torch.device("cpu")))
+        return model

madewithml/predict.py

@@ -1,19 +1,20 @@
 import json
+from pathlib import Path
 from typing import Any, Dict, Iterable, List
 from urllib.parse import urlparse
 
 import numpy as np
-import pandas as pd
 import ray
-import torch
 import typer
 from numpyencoder import NumpyEncoder
 from ray.air import Result
-from ray.train.torch import TorchPredictor
 from ray.train.torch.torch_checkpoint import TorchCheckpoint
 from typing_extensions import Annotated
 
 from madewithml.config import logger, mlflow
+from madewithml.data import CustomPreprocessor
+from madewithml.models import FinetunedLLM
+from madewithml.utils import collate_fn
 
 # Initialize Typer CLI app
 app = typer.Typer()
@@ -48,25 +49,51 @@ def format_prob(prob: Iterable, index_to_class: Dict) -> Dict:
     return d
 
 
-def predict_with_proba(
-    df: pd.DataFrame,
-    predictor: ray.train.torch.torch_predictor.TorchPredictor,
+class TorchPredictor:
+    def __init__(self, preprocessor, model):
+        self.preprocessor = preprocessor
+        self.model = model
+        self.model.eval()
+
+    def __call__(self, batch):
+        results = self.model.predict(collate_fn(batch))
+        return {"output": results}
+
+    def predict_proba(self, batch):
+        results = self.model.predict_proba(collate_fn(batch))
+        return {"output": results}
+
+    def get_preprocessor(self):
+        return self.preprocessor
+
+    @classmethod
+    def from_checkpoint(cls, checkpoint):
+        metadata = checkpoint.get_metadata()
+        preprocessor = CustomPreprocessor(class_to_index=metadata["class_to_index"])
+        model = FinetunedLLM.load(Path(checkpoint.path, "args.json"), Path(checkpoint.path, "model.pt"))
+        return cls(preprocessor=preprocessor, model=model)
+
+
+def predict_proba(
+    ds: ray.data.dataset.Dataset,
+    predictor: TorchPredictor,
 ) -> List:  # pragma: no cover, tested with inference workload
     """Predict tags (with probabilities) for input data from a dataframe.
 
     Args:
         df (pd.DataFrame): dataframe with input features.
-        predictor (ray.train.torch.torch_predictor.TorchPredictor): loaded predictor from a checkpoint.
+        predictor (TorchPredictor): loaded predictor from a checkpoint.
 
     Returns:
         List: list of predicted labels.
     """
     preprocessor = predictor.get_preprocessor()
-    z = predictor.predict(data=df)["predictions"]
-    y_prob = torch.tensor(np.stack(z)).softmax(dim=1).numpy()
+    preprocessed_ds = preprocessor.transform(ds)
+    outputs = preprocessed_ds.map_batches(predictor.predict_proba)
+    y_prob = np.array([d["output"] for d in outputs.take_all()])
     results = []
     for i, prob in enumerate(y_prob):
-        tag = decode([z[i].argmax()], preprocessor.index_to_class)[0]
+        tag = preprocessor.index_to_class[prob.argmax()]
         results.append({"prediction": tag, "probabilities": format_prob(prob, preprocessor.index_to_class)})
     return results
 
@@ -125,11 +152,10 @@ def predict(
     # Load components
     best_checkpoint = get_best_checkpoint(run_id=run_id)
     predictor = TorchPredictor.from_checkpoint(best_checkpoint)
-    # preprocessor = predictor.get_preprocessor()
 
     # Predict
-    sample_df = pd.DataFrame([{"title": title, "description": description, "tag": "other"}])
-    results = predict_with_proba(df=sample_df, predictor=predictor)
+    sample_ds = ray.data.from_items([{"title": title, "description": description, "tag": "other"}])
+    results = predict_proba(ds=sample_ds, predictor=predictor)
     logger.info(json.dumps(results, cls=NumpyEncoder, indent=2))
     return results
 

madewithml/serve.py

@@ -3,11 +3,9 @@
 from http import HTTPStatus
 from typing import Dict
 
-import pandas as pd
 import ray
 from fastapi import FastAPI
 from ray import serve
-from ray.train.torch import TorchPredictor
 from starlette.requests import Request
 
 from madewithml import evaluate, predict
@@ -21,7 +19,7 @@
 )
 
 
-@serve.deployment(route_prefix="/", num_replicas="1", ray_actor_options={"num_cpus": 8, "num_gpus": 0})
+@serve.deployment(num_replicas="1", ray_actor_options={"num_cpus": 8, "num_gpus": 0})
 @serve.ingress(app)
 class ModelDeployment:
     def __init__(self, run_id: str, threshold: int = 0.9):
@@ -30,8 +28,7 @@ def __init__(self, run_id: str, threshold: int = 0.9):
         self.threshold = threshold
         mlflow.set_tracking_uri(MLFLOW_TRACKING_URI)  # so workers have access to model registry
         best_checkpoint = predict.get_best_checkpoint(run_id=run_id)
-        self.predictor = TorchPredictor.from_checkpoint(best_checkpoint)
-        self.preprocessor = self.predictor.get_preprocessor()
+        self.predictor = predict.TorchPredictor.from_checkpoint(best_checkpoint)
 
     @app.get("/")
     def _index(self) -> Dict:
@@ -55,11 +52,10 @@ async def _evaluate(self, request: Request) -> Dict:
         return {"results": results}
 
     @app.post("/predict/")
-    async def _predict(self, request: Request) -> Dict:
-        # Get prediction
+    async def _predict(self, request: Request):
         data = await request.json()
-        df = pd.DataFrame([{"title": data.get("title", ""), "description": data.get("description", ""), "tag": ""}])
-        results = predict.predict_with_proba(df=df, predictor=self.predictor)
+        sample_ds = ray.data.from_items([{"title": data.get("title", ""), "description": data.get("description", ""), "tag": ""}])
+        results = predict.predict_proba(ds=sample_ds, predictor=self.predictor)
 
         # Apply custom logic
         for i, result in enumerate(results):