mirror of
https://github.com/deepset-ai/haystack.git
synced 2025-12-30 08:37:20 +00:00
99e924aede
* Add languages and preprocessing pages * add content * address review comments * make link relative * update api ref with latest docstrings * move doc readme and update * add generator API docs * fix example code * design and link fix Co-authored-by: Malte Pietsch <malte.pietsch@deepset.ai> Co-authored-by: PiffPaffM <markuspaff.mp@gmail.com>
94 lines
3.5 KiB
Python
94 lines
3.5 KiB
Python
from utils import get_document_store, index_to_doc_store, get_reader
|
|
from haystack.preprocessor.utils import eval_data_from_file
|
|
from farm.data_handler.utils import _download_extract_downstream_data
|
|
|
|
from pathlib import Path
|
|
import pandas as pd
|
|
from results_to_json import reader as reader_json
|
|
from templates import READER_TEMPLATE
|
|
import json
|
|
import logging
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
reader_models_full = ["deepset/roberta-base-squad2"]
|
|
reader_models_ci = ["deepset/minilm-uncased-squad2"]
|
|
|
|
reader_types = ["farm"]
|
|
data_dir = Path("../../data/squad20")
|
|
filename = "dev-v2.0.json"
|
|
# Note that this number is approximate - it was calculated using Bert Base Cased
|
|
# This number could vary when using a different tokenizer
|
|
n_total_passages = 12350
|
|
n_total_docs = 1204
|
|
|
|
results_file = "reader_results.csv"
|
|
|
|
reader_json_file = "../../docs/_src/benchmarks/reader_performance.json"
|
|
|
|
doc_index = "eval_document"
|
|
label_index = "label"
|
|
|
|
def benchmark_reader(ci=False, update_json=False, save_markdown=False, **kwargs):
|
|
if ci:
|
|
reader_models = reader_models_ci
|
|
max_docs = 100
|
|
# heuristic to estimate num of passages for the reduced num of docs
|
|
n_passages = n_total_passages * (max_docs / n_total_docs)
|
|
else:
|
|
reader_models = reader_models_full
|
|
max_docs = None
|
|
n_passages = n_total_passages
|
|
reader_results = []
|
|
doc_store = get_document_store("elasticsearch")
|
|
# download squad data
|
|
_download_extract_downstream_data(input_file=data_dir/filename)
|
|
docs, labels = eval_data_from_file(data_dir/filename, max_docs)
|
|
|
|
index_to_doc_store(doc_store, docs, None, labels)
|
|
for reader_name in reader_models:
|
|
for reader_type in reader_types:
|
|
logger.info(f"##### Start reader run - model:{reader_name}, type: {reader_type} ##### ")
|
|
try:
|
|
reader = get_reader(reader_name, reader_type)
|
|
results = reader.eval(document_store=doc_store,
|
|
doc_index=doc_index,
|
|
label_index=label_index,
|
|
device="cuda")
|
|
# results = reader.eval_on_file(data_dir, filename, device="cuda")
|
|
print(results)
|
|
results["passages_per_second"] = n_passages / results["reader_time"]
|
|
results["reader"] = reader_name
|
|
results["error"] = ""
|
|
reader_results.append(results)
|
|
except Exception as e:
|
|
results = {'EM': 0.,
|
|
'f1': 0.,
|
|
'top_n_accuracy': 0.,
|
|
'top_n': 0,
|
|
'reader_time': 0.,
|
|
"passages_per_second": 0.,
|
|
"seconds_per_query": 0.,
|
|
'reader': reader_name,
|
|
"error": e}
|
|
reader_results.append(results)
|
|
reader_df = pd.DataFrame.from_records(reader_results)
|
|
reader_df.to_csv(results_file)
|
|
if save_markdown:
|
|
md_file = results_file.replace(".csv", ".md")
|
|
with open(md_file, "w") as f:
|
|
f.write(str(reader_df.to_markdown()))
|
|
if update_json:
|
|
populate_reader_json()
|
|
|
|
|
|
|
|
def populate_reader_json():
|
|
reader_results = reader_json()
|
|
template = READER_TEMPLATE
|
|
template["data"] = reader_results
|
|
json.dump(template, open(reader_json_file, "w"), indent=4)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
benchmark_reader(ci=False, update_json=False, save_markdown=False) |