Prasyarat

1. !pip install fmeval
   !pip3 install boto3==1.28.65

2. import boto3
   import json
   import os
   
   # Dependent on available hardware and memory
   os.environ["PARALLELIZATION_FACTOR"] = "1"
   
   # Bedrock clients for model inference
   bedrock = boto3.client(service_name='bedrock')
   bedrock_runtime = boto3.client(service_name='bedrock-runtime')

4. import glob
   
   # Check for the built-in dataset
   if not glob.glob("sample-dataset.jsonl"):
   print("ERROR - please make sure file exists: sample-dataset.jsonl")

1. import json
   model_id = 'anthropic.claude-v2'
   accept = "application/json"
   contentType = "application/json"
   # Ensure that your prompt has the correct format
   prompt_data = """Human: Who is Barack Obama?
   Assistant:
   """

2. body = json.dumps({"prompt": prompt_data, "max_tokens_to_sample": 500})
   response = bedrock_runtime.invoke_model(
   body=body, modelId=model_id, accept=accept, contentType=contentType
   )
   response_body = json.loads(response.get("body").read())
   print(response_body.get("completion"))

1. from fmeval.data_loaders.data_config import DataConfig
   from fmeval.model_runners.bedrock_model_runner import BedrockModelRunner
   from fmeval.constants import MIME_TYPE_JSONLINES
   from fmeval.eval_algorithms.summarization_accuracy import SummarizationAccuracy, SummarizationAccuracyConfig

2. {
   "document": "23 October 2015 Last updated at 17:44
       BST\nIt's the highest rating a tropical storm
       can get and is the first one of this magnitude
       to hit mainland Mexico since 1959.\nBut how are
       the categories decided and what do they mean?
       Newsround reporter Jenny Lawrence explains.",
   "summary": "Hurricane Patricia has been rated as
       a category 5 storm.",
   "id": "34615665",
   }

   config = DataConfig(
   dataset_name="sample-dataset",
   dataset_uri="sample-dataset.jsonl",
   dataset_mime_type=MIME_TYPE_JSONLINES,
   model_input_location="document",
   target_output_location="summary"
   )

3. bedrock_model_runner = BedrockModelRunner(
   model_id=model_id,
   output='completion',
   content_template='{"prompt": $prompt, "max_tokens_to_sample": 500}'
   )

   • •    "content_template": "{\"prompt\": $prompt, \"max_tokens_to_sample\": 500}"

       "content_template": "{\"inputs\": $prompt, \"parameters\":{\"max_new_tokens\": \
       10, \"top_p\": 0.9, \"temperature\": 0.8}}"

1. eval_algo = SummarizationAccuracy(SummarizationAccuracyConfig())

2. eval_output = eval_algo.evaluate(model=bedrock_model_runner,
   dataset_config=config,
   prompt_template="Human: $feature\n\nAssistant:\n", save=True)

1. # parse report
   print(json.dumps(eval_output, default=vars, indent=4))

   [
   {
       "eval_name": "summarization_accuracy",
       "dataset_name": "sample-dataset",
       "dataset_scores": [
           {
               "name": "meteor",
               "value": 0.2048823008681274
           },
           {
               "name": "rouge",
               "value": 0.03557697913367101
           },
           {
               "name": "bertscore",
               "value": 0.5406564395678671
           }
       ],
       "prompt_template": "Human: $feature\n\nAssistant:\n",
       "category_scores": null,
       "output_path": "/tmp/eval_results/summarization_accuracy_sample_dataset.jsonl",
       "error": null
   }
   ]

2. import pandas as pd
   
   data = []
   with open("/tmp/eval_results/summarization_accuracy_sample_dataset.jsonl", "r") as file:
   for line in file:
       data.append(json.loads(line))
   df = pd.DataFrame(data)
   df['meteor_score'] = df['scores'].apply(lambda x: x[0]['value'])
   df['rouge_score'] = df['scores'].apply(lambda x: x[1]['value'])
   df['bert_score'] = df['scores'].apply(lambda x: x[2]['value'])
   df

   model_input     model_output     target_output     prompt     scores     meteor_score     rouge_score     bert_score
   0     John Edward Bates, formerly of Spalding, Linco...     I cannot make any definitive judgments, as th...     A former Lincolnshire Police officer carried o...     Human: John Edward Bates, formerly of Spalding...     [{'name': 'meteor', 'value': 0.112359550561797...     0.112360     0.000000     0.543234 ...
   1     23 October 2015 Last updated at 17:44 BST\nIt'...     Here are some key points about hurricane/trop...     Hurricane Patricia has been rated as a categor...     Human: 23 October 2015 Last updated at 17:44 B...     [{'name': 'meteor', 'value': 0.139822692925566...     0.139823     0.017621     0.426529 ...
   2     Ferrari appeared in a position to challenge un...     Here are the key points from the article:\n\n...     Lewis Hamilton stormed to pole position at the...     Human: Ferrari appeared in a position to chall...     [{'name': 'meteor', 'value': 0.283411142234671...     0.283411     0.064516     0.597001 ...
   3     The Bath-born player, 28, has made 36 appearan...     Okay, let me summarize the key points from th...     Newport Gwent Dragons number eight Ed Jackson ...     Human: The Bath-born player, 28, has made 36 a...     [{'name': 'meteor', 'value': 0.089020771513353...     0.089021     0.000000     0.533514 ...
   ...