|
| 1 | +# Copyright 2024 Google LLC |
| 2 | +# |
| 3 | +# Licensed under the Apache License, Version 2.0 (the "License"); |
| 4 | +# you may not use this file except in compliance with the License. |
| 5 | +# You may obtain a copy of the License at |
| 6 | +# |
| 7 | +# https://www.apache.org/licenses/LICENSE-2.0 |
| 8 | +# |
| 9 | +# Unless required by applicable law or agreed to in writing, software |
| 10 | +# distributed under the License is distributed on an "AS IS" BASIS, |
| 11 | +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
| 12 | +# See the License for the specific language governing permissions and |
| 13 | +# limitations under the License. |
| 14 | +import os |
| 15 | + |
| 16 | +from vertexai.preview.evaluation import EvalResult |
| 17 | + |
| 18 | +PROJECT_ID = os.getenv("GOOGLE_CLOUD_PROJECT") |
| 19 | + |
| 20 | + |
| 21 | +def get_rouge_score() -> EvalResult: |
| 22 | + # [START generativeaionvertexai_evaluation_get_rouge_score] |
| 23 | + import pandas as pd |
| 24 | + |
| 25 | + import vertexai |
| 26 | + from vertexai.preview.evaluation import EvalTask |
| 27 | + |
| 28 | + # TODO(developer): Update & uncomment line below |
| 29 | + # PROJECT_ID = "your-project-id" |
| 30 | + vertexai.init(project=PROJECT_ID, location="us-central1") |
| 31 | + |
| 32 | + text_to_summarize = """ |
| 33 | + The Great Barrier Reef, located off the coast of Queensland in northeastern |
| 34 | + Australia, is the world's largest coral reef system. Stretching over 2,300 |
| 35 | + kilometers, it is composed of over 2,900 individual reefs and 900 islands. |
| 36 | + The reef is home to a wide variety of marine life, including many endangered |
| 37 | + species. However, climate change, ocean acidification, and coral bleaching |
| 38 | + pose significant threats to its ecosystem.""" |
| 39 | + |
| 40 | + prompt = f"Summarize the following text:\n\n{text_to_summarize}" |
| 41 | + |
| 42 | + reference_summarization = """ |
| 43 | + The Great Barrier Reef, the world's largest coral reef system, is |
| 44 | + located off the coast of Queensland, Australia. It's a vast |
| 45 | + ecosystem spanning over 2,300 kilometers with thousands of reefs |
| 46 | + and islands. While it harbors an incredible diversity of marine |
| 47 | + life, including endangered species, it faces serious threats from |
| 48 | + climate change, ocean acidification, and coral bleaching.""" |
| 49 | + |
| 50 | + # Use pre-generated model responses to compare different summarization outputs |
| 51 | + # against a consistent reference. |
| 52 | + eval_dataset = pd.DataFrame( |
| 53 | + { |
| 54 | + "prompt": [prompt] * 3, |
| 55 | + "response": [ |
| 56 | + """The Great Barrier Reef, the world's largest coral reef system located |
| 57 | + in Australia, is a vast and diverse ecosystem. However, it faces serious |
| 58 | + threats from climate change, ocean acidification, and coral bleaching, |
| 59 | + endangering its rich marine life.""", |
| 60 | + """The Great Barrier Reef, a vast coral reef system off the coast of |
| 61 | + Queensland, Australia, is the world's largest. It's a complex ecosystem |
| 62 | + supporting diverse marine life, including endangered species. However, |
| 63 | + climate change, ocean acidification, and coral bleaching are serious |
| 64 | + threats to its survival.""", |
| 65 | + """The Great Barrier Reef, the world's largest coral reef system off the |
| 66 | + coast of Australia, is a vast and diverse ecosystem with thousands of |
| 67 | + reefs and islands. It is home to a multitude of marine life, including |
| 68 | + endangered species, but faces serious threats from climate change, ocean |
| 69 | + acidification, and coral bleaching.""", |
| 70 | + ], |
| 71 | + "reference": [reference_summarization] * 3, |
| 72 | + } |
| 73 | + ) |
| 74 | + |
| 75 | + eval_task = EvalTask( |
| 76 | + dataset=eval_dataset, |
| 77 | + metrics=[ |
| 78 | + "rouge_1", |
| 79 | + "rouge_2", |
| 80 | + "rouge_l", |
| 81 | + "rouge_l_sum", |
| 82 | + ], |
| 83 | + ) |
| 84 | + result = eval_task.evaluate() |
| 85 | + |
| 86 | + print("Summary Metrics:\n") |
| 87 | + |
| 88 | + for key, value in result.summary_metrics.items(): |
| 89 | + print(f"{key}: \t{value}") |
| 90 | + |
| 91 | + print("\n\nMetrics Table:\n") |
| 92 | + print(result.metrics_table) |
| 93 | + # Example response: |
| 94 | + # prompt ... rouge_1/score rouge_2/score ... |
| 95 | + # 0 Summarize the following text:\n\n\n ... 0.659794 0.484211 ... |
| 96 | + # 1 Summarize the following text:\n\n\n ... 0.704762 0.524272 ... |
| 97 | + # ... |
| 98 | + |
| 99 | + # [END generativeaionvertexai_evaluation_get_rouge_score] |
| 100 | + return result |
| 101 | + |
| 102 | + |
| 103 | +if __name__ == "__main__": |
| 104 | + get_rouge_score() |
0 commit comments