Added gradient boosting regressor example

scikit-learn/gradient_boosting_regressor/client.py

@@ -0,0 +1,63 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+
+import sys
+import argparse
+import numpy as np
+
+import tritonclient.grpc as grpcclient
+
+from sklearn.datasets import fetch_california_housing
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import mean_squared_error
+
+
+def make_prediction(model_server, model_name, model_version, verbose):
+    try:
+        triton_client = grpcclient.InferenceServerClient(url=model_server, verbose=verbose)
+    except Exception as e:
+        print("channel creation failed: " + str(e))
+        sys.exit(1)
+    # Infer
+    inputs = []
+    outputs = []
+    # Load the California Housing dataset
+    california = fetch_california_housing()
+    X, y = california.data, california.target
+    # Split the dataset into training and testing sets
+    _, X_test, _, y_test = train_test_split(X, y, test_size=0.25, random_state=0)
+    input_data = X_test.astype(np.float32)
+    input_label = y_test.astype(np.float32)
+    print(f'input_data:\n{input_data[0]}')
+    print(f'input_label:\n{input_label[0]}')
+    # input_data = np.expand_dims(input_data, axis=0)
+    # Initialize the data
+    inputs.append(grpcclient.InferInput('float_input', [input_data.shape[0], input_data.shape[1]], "FP32"))
+    inputs[0].set_data_from_numpy(input_data)
+    outputs.append(grpcclient.InferRequestedOutput('variable'))
+    # Test with outputs
+    results = triton_client.infer(model_name=model_name, inputs=inputs, outputs=outputs)
+    # print("response:\n", results.get_response())
+    statistics = triton_client.get_inference_statistics(model_name=model_name)
+    # print("statistics:\n", statistics)
+    if len(statistics.model_stats) != 1:
+        print("FAILED: Inference Statistics")
+        sys.exit(1)
+    # Get the output arrays from the results
+    y_pred = results.as_numpy('variable').squeeze()
+    print(f"y_pred:\n{y_pred[0]}")
+    mse = mean_squared_error(y_test, y_pred)
+    print(f'Mean Squared Error: {mse}')
+
+
+"""
+python client.py --model_server localhost:8001 --model_name gradient_boosting_regressor --model_version 1
+"""
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="Make predictions using a specific model.")
+    parser.add_argument("--model_server", default="localhost:8001", help="The address of the model server.")
+    parser.add_argument("--model_name", default="gradient_boosting_regressor", help="The name of the model to use.")
+    parser.add_argument("--model_version", default="1", help="The version of the model to use.")
+    parser.add_argument("--verbose", action="store_true", required=False, default=False, help='Enable verbose output')
+    args = parser.parse_args()
+    make_prediction(args.model_server, args.model_name, args.model_version, args.verbose)

scikit-learn/gradient_boosting_regressor/convert2onnx.sh

@@ -0,0 +1 @@
+python ../convert2onnx.py california gradient_boosting_regressor.joblib gradient_boosting_regressor.onnx

scikit-learn/gradient_boosting_regressor/gradient_boosting_regressor.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe77c60b969a21089e927061d442b5752cffabf8ac32b522b887928fa1bd585a
+size 1019468

scikit-learn/gradient_boosting_regressor/gradient_boosting_regressor.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b63d719c545722eb97b2f74ff5de0932fc39b46f47f504ed15cddb29c1396e08
+size 411998

scikit-learn/gradient_boosting_regressor/gradient_boosting_regressor.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d17ef5133e1d83847fc1d6efc4067fb9fa790bd8541e6f6d09c1afabe6f59eaf
+size 59217

scikit-learn/gradient_boosting_regressor/gradient_boosting_regressor/1/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b63d719c545722eb97b2f74ff5de0932fc39b46f47f504ed15cddb29c1396e08
+size 411998

scikit-learn/gradient_boosting_regressor/gradient_boosting_regressor/config.pbtxt

@@ -0,0 +1,18 @@
+name: "gradient_boosting_regressor"
+backend: "onnxruntime"
+max_batch_size: 0
+input [
+  {
+    name: "float_input"
+    data_type: TYPE_FP32
+    dims: [ 8 ]
+  }
+]
+output [
+]
+instance_group [
+  {
+    count: 1
+    kind: KIND_CPU
+  }
+]

scikit-learn/gradient_boosting_regressor/model_packaging.sh

@@ -0,0 +1 @@
+python ../model_packaging.py .

scikit-learn/gradient_boosting_regressor/predict.py

@@ -0,0 +1,31 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+
+import joblib
+
+from sklearn.datasets import fetch_california_housing
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import mean_squared_error
+
+# Load the model from disk
+loaded_model = joblib.load('gradient_boosting_regressor.joblib')
+
+# Set the random seed
+random_seed = 0
+
+# Load the dataset
+dataset = fetch_california_housing()
+X, y = dataset.data, dataset.target
+
+# Split the dataset into training and testing sets
+_, X_test, _, y_test = train_test_split(X, y, test_size=0.25, random_state=random_seed)
+print(f'X_test:\n{X_test[0]}')
+print(f'y_test:\n{y_test[0]}')
+
+# Use the model to make predictions on the test data
+y_pred = loaded_model.predict(X_test)
+print(f'y_pred:\n{y_pred[0]}')
+
+# Score the model using mean squared error
+mse = mean_squared_error(y_test, y_pred)
+print(f'Mean Squared Error: {mse}')

scikit-learn/gradient_boosting_regressor/train.py

@@ -0,0 +1,27 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+
+import joblib
+import numpy as np
+
+from sklearn.ensemble import GradientBoostingRegressor
+from sklearn.datasets import fetch_california_housing
+from sklearn.model_selection import train_test_split
+
+# Set the random seed
+random_seed = 0
+np.random.seed(random_seed)
+
+# Load the dataset
+dataset = fetch_california_housing()
+X, y = dataset.data, dataset.target
+
+# Split the dataset into training and testing sets
+X_train, _, y_train, _ = train_test_split(X, y, test_size=0.25, random_state=random_seed)
+
+# Create and train model
+model = GradientBoostingRegressor(n_estimators=100, max_depth=6, random_state=42)
+model.fit(X_train, y_train)
+
+# Save the trained model to disk
+joblib.dump(model, 'gradient_boosting_regressor.joblib')