yujunjun/haystack
1
0
Fork 0
mirror of https://github.com/deepset-ai/haystack.git synced 2026-01-06 20:17:14 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix document id missing in farm inference output (#174)

Browse Source
This commit is contained in:
Timo Moeller 2020-06-26 11:01:10 +02:00 committed by GitHub
parent 44f89c94ab
commit c53aaddb78
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 92 additions and 63 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
haystack/finder.py
View File

@ -358,3 +358,39 @@ class Finder:
}
return results
@staticmethod
def print_eval_results(finder_eval_results: Dict):
print("\n___Retriever Metrics in Finder___")
print(f"Retriever Recall : {finder_eval_results['retriever_recall']:.3f}")
print(f"Retriever Mean Avg Precision: {finder_eval_results['retriever_map']:.3f}")
# Reader is only evaluated with those questions, where the correct document is among the retrieved ones
print("\n___Reader Metrics in Finder___")
print("Top-k accuracy")
print(f"Reader Top-1 accuracy : {finder_eval_results['reader_top1_accuracy']:.3f}")
print(f"Reader Top-1 accuracy (has answer): {finder_eval_results['reader_top1_accuracy_has_answer']:.3f}")
print(f"Reader Top-k accuracy : {finder_eval_results['reader_top_k_accuracy']:.3f}")
print(f"Reader Top-k accuracy (has answer): {finder_eval_results['reader_topk_accuracy_has_answer']:.3f}")
print("Exact Match")
print(f"Reader Top-1 EM : {finder_eval_results['reader_top1_em']:.3f}")
print(f"Reader Top-1 EM (has answer) : {finder_eval_results['reader_top1_em_has_answer']:.3f}")
print(f"Reader Top-k EM : {finder_eval_results['reader_topk_em']:.3f}")
print(f"Reader Top-k EM (has answer) : {finder_eval_results['reader_topk_em_has_answer']:.3f}")
print("F1 score")
print(f"Reader Top-1 F1 : {finder_eval_results['reader_top1_f1']:.3f}")
print(f"Reader Top-1 F1 (has answer) : {finder_eval_results['reader_top1_f1_has_answer']:.3f}")
print(f"Reader Top-k F1 : {finder_eval_results['reader_topk_f1']:.3f}")
print(f"Reader Top-k F1 (has answer) : {finder_eval_results['reader_topk_f1_has_answer']:.3f}")
print("No Answer")
print(f"Reader Top-1 no-answer accuracy : {finder_eval_results['reader_top1_no_answer_accuracy']:.3f}")
print(f"Reader Top-k no-answer accuracy : {finder_eval_results['reader_topk_no_answer_accuracy']:.3f}")
# Time measurements
print("\n___Time Measurements___")
print(f"Total retrieve time : {finder_eval_results['total_retrieve_time']:.3f}")
print(f"Avg retrieve time per question: {finder_eval_results['avg_retrieve_time']:.3f}")
print(f"Total reader timer : {finder_eval_results['total_reader_time']:.3f}")
print(f"Avg read time per question : {finder_eval_results['avg_reader_time']:.3f}")
print(f"Total Finder time : {finder_eval_results['total_finder_time']:.3f}")

29
haystack/reader/farm.py
View File

@ -250,28 +250,29 @@ class FARMReader(BaseReader):
answers = []
no_ans_gaps = []
best_score_answer = 0
for pred in predictions:
# TODO once FARM returns doc ids again we can revert to using them inside the preds and remove
for pred, inp in zip(predictions, input_dicts):
answers_per_document = []
no_ans_gaps.append(pred["predictions"][0]["no_ans_gap"])
for a in pred["predictions"][0]["answers"]:
for ans in pred["predictions"][0]["answers"]:
# skip "no answers" here
if self._check_no_answer(d=a):
if self._check_no_answer(ans):
pass
else:
cur = {"answer": a["answer"],
"score": a["score"],
cur = {"answer": ans["answer"],
"score": ans["score"],
# just a pseudo prob for now
"probability": float(expit(np.asarray([a["score"]]) / 8)), # type: ignore
"context": a["context"],
"offset_start": a["offset_answer_start"] - a["offset_context_start"],
"offset_end": a["offset_answer_end"] - a["offset_context_start"],
"offset_start_in_doc": a["offset_answer_start"],
"offset_end_in_doc": a["offset_answer_end"],
"document_id": a["document_id"]}
"probability": float(expit(np.asarray([ans["score"]]) / 8)), # type: ignore
"context": ans["context"],
"offset_start": ans["offset_answer_start"] - ans["offset_context_start"],
"offset_end": ans["offset_answer_end"] - ans["offset_context_start"],
"offset_start_in_doc": ans["offset_answer_start"],
"offset_end_in_doc": ans["offset_answer_end"],
"document_id": inp["document_id"]} #TODO revert to ans["docid"] once it is populated
answers_per_document.append(cur)
if a["score"] > best_score_answer:
best_score_answer = a["score"]
if ans["score"] > best_score_answer:
best_score_answer = ans["score"]
# only take n best candidates. Answers coming back from FARM are sorted with decreasing relevance.
answers += answers_per_document[:self.top_k_per_candidate]

90
tutorials/Tutorial5_Evaluation.py
View File

@ -9,9 +9,21 @@ import logging
import subprocess
import time
LAUNCH_ELASTICSEARCH = False
device, n_gpu = initialize_device_settings(use_cuda=True)
logger = logging.getLogger(__name__)
##############################################
# Settings
##############################################
LAUNCH_ELASTICSEARCH = True
eval_retriever_only = False
eval_reader_only = False
eval_both = True
##############################################
# Code
##############################################
device, n_gpu = initialize_device_settings(use_cuda=True)
# Start an Elasticsearch server
# You can start Elasticsearch on your local machine instance using Docker. If Docker is not readily available in
# your environment (eg., in Colab notebooks), then you can manually download and execute Elasticsearch from source.
@ -33,7 +45,11 @@ fetch_archive_from_http(url=s3_url, output_dir=doc_dir)
# Connect to Elasticsearch
document_store = ElasticsearchDocumentStore(host="localhost", username="", password="", index="document", create_index=False)
# Add evaluation data to Elasticsearch database
document_store.add_eval_data("../data/nq/nq_dev_subset.json")
if LAUNCH_ELASTICSEARCH:
document_store.add_eval_data("../data/nq/nq_dev_subset.json")
else:
logger.warning("Since we already have a running ES instance we should not index the same documents again."
"If you still want to do this call: 'document_store.add_eval_data('../data/nq/nq_dev_subset.json')' manually ")
# Initialize Retriever
retriever = ElasticsearchRetriever(document_store=document_store)
@ -44,55 +60,31 @@ reader = FARMReader("deepset/roberta-base-squad2")
# Initialize Finder which sticks together Reader and Retriever
finder = Finder(reader, retriever)
# Evaluate Retriever on its own
retriever_eval_results = retriever.eval()
## Retriever Recall is the proportion of questions for which the correct document containing the answer is
## among the correct documents
print("Retriever Recall:", retriever_eval_results["recall"])
## Retriever Mean Avg Precision rewards retrievers that give relevant documents a higher rank
print("Retriever Mean Avg Precision:", retriever_eval_results["map"])
## Evaluate Retriever on its own
if eval_retriever_only:
retriever_eval_results = retriever.eval()
## Retriever Recall is the proportion of questions for which the correct document containing the answer is
## among the correct documents
print("Retriever Recall:", retriever_eval_results["recall"])
## Retriever Mean Avg Precision rewards retrievers that give relevant documents a higher rank
print("Retriever Mean Avg Precision:", retriever_eval_results["map"])
# Evaluate Reader on its own
reader_eval_results = reader.eval(document_store=document_store, device=device)
# Evaluation of Reader can also be done directly on a SQuAD-formatted file without passing the data to Elasticsearch
#reader_eval_results = reader.eval_on_file("../data/natural_questions", "dev_subset.json", device=device)
if eval_reader_only:
reader_eval_results = reader.eval(document_store=document_store, device=device)
# Evaluation of Reader can also be done directly on a SQuAD-formatted file without passing the data to Elasticsearch
#reader_eval_results = reader.eval_on_file("../data/natural_questions", "dev_subset.json", device=device)
## Reader Top-N-Recall is the proportion of predicted answers that overlap with their corresponding correct answer
print("Reader Top-N-Recall:", reader_eval_results["top_n_recall"])
## Reader Exact Match is the proportion of questions where the predicted answer is exactly the same as the correct answer
print("Reader Exact Match:", reader_eval_results["EM"])
## Reader F1-Score is the average overlap between the predicted answers and the correct answers
print("Reader F1-Score:", reader_eval_results["f1"])
## Reader Top-N-Recall is the proportion of predicted answers that overlap with their corresponding correct answer
print("Reader Top-N-Recall:", reader_eval_results["top_n_recall"])
## Reader Exact Match is the proportion of questions where the predicted answer is exactly the same as the correct answer
print("Reader Exact Match:", reader_eval_results["EM"])
## Reader F1-Score is the average overlap between the predicted answers and the correct answers
print("Reader F1-Score:", reader_eval_results["f1"])
# Evaluate combination of Reader and Retriever through Finder
finder_eval_results = finder.eval()
print("\n___Retriever Metrics in Finder___")
print("Retriever Recall:", finder_eval_results["retriever_recall"])
print("Retriever Mean Avg Precision:", finder_eval_results["retriever_map"])
# Reader is only evaluated with those questions, where the correct document is among the retrieved ones
print("\n___Reader Metrics in Finder___")
print("Reader Top-1 accuracy:", finder_eval_results["reader_top1_accuracy"])
print("Reader Top-1 accuracy (has answer):", finder_eval_results["reader_top1_accuracy_has_answer"])
print("Reader Top-k accuracy:", finder_eval_results["reader_top_k_accuracy"])
print("Reader Top-k accuracy (has answer):", finder_eval_results["reader_topk_accuracy_has_answer"])
print("Reader Top-1 EM:", finder_eval_results["reader_top1_em"])
print("Reader Top-1 EM (has answer):", finder_eval_results["reader_top1_em_has_answer"])
print("Reader Top-k EM:", finder_eval_results["reader_topk_em"])
print("Reader Top-k EM (has answer):", finder_eval_results["reader_topk_em_has_answer"])
print("Reader Top-1 F1:", finder_eval_results["reader_top1_f1"])
print("Reader Top-1 F1 (has answer):", finder_eval_results["reader_top1_f1_has_answer"])
print("Reader Top-k F1:", finder_eval_results["reader_topk_f1"])
print("Reader Top-k F1 (has answer):", finder_eval_results["reader_topk_f1_has_answer"])
print("Reader Top-1 no-answer accuracy:", finder_eval_results["reader_top1_no_answer_accuracy"])
print("Reader Top-k no-answer accuracy:", finder_eval_results["reader_topk_no_answer_accuracy"])
# Time measurements
print("\n___Time Measurements___")
print("Total retrieve time:", finder_eval_results["total_retrieve_time"])
print("Avg retrieve time per question:", finder_eval_results["avg_retrieve_time"])
print("Total reader timer:", finder_eval_results["total_reader_time"])
print("Avg read time per question:", finder_eval_results["avg_reader_time"])
print("Total Finder time:", finder_eval_results["total_finder_time"])
if eval_both:
finder_eval_results = finder.eval(top_k_retriever = 10, top_k_reader = 10)
finder.print_eval_results(finder_eval_results)