def __init__(self, *args, **kwargs):
super(TestTRECIndexer, self).__init__(*args, **kwargs)
if not pt.started():
pt.init(logging="DEBUG")
# else:
# pt.setup_logging("DEBUG")
self.here = os.path.dirname(os.path.realpath(__file__))
def _pt_init(args):
import pyterrier as pt
if not pt.started():
pt.init(no_download=True, **args)
else:
from warnings import warn
warn("Avoiding reinit of PyTerrier")
def __init__(self, *args, **kwargs):
super(BaseTestCase, self).__init__(*args, **kwargs)
terrier_version = os.environ.get("TERRIER_VERSION", None)
if terrier_version is not None:
print("Testing with Terrier version" + terrier_version)
if not pt.started():
pt.init(version=terrier_version)
self.here = os.path.dirname(os.path.realpath(__file__))
def __init__(self, *args, **kwargs):
super(BaseTestCase, self).__init__(*args, **kwargs)
terrier_version = os.environ.get("TERRIER_VERSION", None)
java_bridge = os.environ.get("JAVA_BRIDGE", "jpype")
print("Using " + java_bridge + " as java bridge")
if terrier_version is not None:
print("Testing with Terrier version " + terrier_version)
if not pt.started():
pt.init(version=terrier_version, java_bridge=java_bridge)
self.here = os.path.dirname(os.path.realpath(__file__))
def _convert_query_and_docs_to_features(self, query_id, query, doc_texts):
query_toks = convert_query_example(query_id, query, self.max_qlen,
self.tokenizer)
features = []
from pyterrier import tqdm, started
assert started()
for (ex_index, example) in enumerate(doc_texts):
feature = convert_single_piece_example(ex_index, query_toks,
example, self.max_dlen,
self.tokenizer)
features.append(feature)
return features
def test_monot5_vaswani(self):
if not pt.started():
pt.init()
bm25 = pt.BatchRetrieve(pt.get_dataset('vaswani').get_index(),
wmodel='BM25')
monoT5 = pyterrier_t5.MonoT5ReRanker()
pipeline = bm25 % 20 >> pt.text.get_text(
pt.get_dataset('irds:vaswani'), 'text') >> monoT5
result = pipeline.search('fluid dynamics')
self.assertEqual(result.iloc[0]['docno'], '11216')
self.assertAlmostEqual(result.iloc[0]['score'], -2.186261, places=4)
self.assertEqual(result.iloc[0]['rank'], 0)
self.assertEqual(result.iloc[1]['docno'], '5299')
self.assertAlmostEqual(result.iloc[1]['score'], -8.078399, places=4)
self.assertEqual(result.iloc[1]['rank'], 1)
self.assertEqual(result.iloc[-1]['docno'], '3442')
self.assertAlmostEqual(result.iloc[-1]['score'], -12.725513, places=4)
self.assertEqual(result.iloc[-1]['rank'], 19)
def test_duot5_vaswani(self):
if not pt.started():
pt.init()
bm25 = pt.BatchRetrieve(pt.get_dataset('vaswani').get_index(),
wmodel='BM25')
duoT5 = pyterrier_t5.DuoT5ReRanker()
pipeline = bm25 % 10 >> pt.text.get_text(
pt.get_dataset('irds:vaswani'), 'text') >> duoT5
result = pipeline.search('fluid dynamics')
self.assertEqual(result.iloc[0]['docno'], '9731')
self.assertAlmostEqual(result.iloc[0]['score'], 44.621585, places=4)
self.assertEqual(result.iloc[0]['rank'], 0)
self.assertEqual(result.iloc[1]['docno'], '7045')
self.assertAlmostEqual(result.iloc[1]['score'], 27.716750, places=4)
self.assertEqual(result.iloc[1]['rank'], 1)
self.assertEqual(result.iloc[-1]['docno'], '4767')
self.assertAlmostEqual(result.iloc[-1]['score'], -9.916206, places=4)
self.assertEqual(result.iloc[-1]['rank'], 9)
def main():
if not pt.started():
pt.init()
# Valid Stemmers: "porter", "snowball" and ""
# Valid Datasets: "vaswani", "trec-deep-learning-docs"
# Args
argv = sys.argv
if( len(argv) < 4 ):
print(" Less than 4 arguements inputted, quiting the program.")
return 1
dataset = argv[1]
index_loc = argv[2]
stemmer = argv[3]
only_retr = argv[4] == 'T'
time_taken, evaluation = conduct_experiment(dataset, index_loc, stemmer, only_retr)
def transform(self, topics_and_res):
import pandas as pd
rtr = []
grouper = topics_and_res.groupby("qid")
from pyterrier import tqdm, started
assert started()
#for each query, get the results, and pass to _for_each_query
for qid, group in tqdm(grouper, desc="BERTQE",
unit="q") if self.verbose else grouper:
query = group["query"].iloc[0]
scores = self._for_each_query(qid, query,
group[["docno", self.body_attr]])
# assigned the scores to the input documents
for i, s in enumerate(scores.tolist()):
rtr.append([qid, query, group.iloc[i]["docno"], s])
# returns the final dataframe
df = pd.DataFrame(rtr, columns=["qid", "query", "docno", "score"])
return add_ranks(df)
def starter(**initargs):
if not pt.started():
print("pt booted")
pt.init(*initargs)
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
if not pt.started():
pt.init()
def __init__(self, *args, **kwargs):
super(TestOperators, self).__init__(*args, **kwargs)
if not pt.started():
pt.init()
def setUp(self):
import pyterrier as pt
if not pt.started():
pt.init()
self.test_dir = tempfile.mkdtemp()
def __init__(self):
if not pt.started():
pt.init()
import pyterrier as pt
import pandas as pd
import csv
import os
import shutil
if not pt.started():
pt.init()
def passages_generator(filepath: str, delimiter: str, verbose: bool = False):
"""
Generator of passages dataset. Generates 1 passage at a time.
Parameters
----------
filepath : str
path of file that contains passages in a csv format
with two fields: [passage_id] and [passage_text].
delimiter : str
delimiter of csv file that contains the passages
verbose: bool, default=False
Whether or not to log progress frequently.
Returns
-------
{'docno': docno, 'text': text}
"""
csv_file = open(filepath)
def main(algorithm=LAMBDAMART,
feat_batch=FEATURES_BATCH_N,
top_n_train=TOP_N_TRAIN,
top_n_validation=TOP_N_TRAIN,
run_id=RUN_ID):
if not pt.started():
pt.init(mem=8000)
################
## INDEX STEP ##
################
dataset = pt.get_dataset("trec-deep-learning-passages")
def msmarco_generate():
with pt.io.autoopen(dataset.get_corpus()[0], 'rt') as corpusfile:
for l in corpusfile:
docno, passage = l.split("\t")
yield {'docno': docno, 'text': passage}
try:
print("Indexing MSMARCO passage ranking dataset")
print(
"If the index has not be constructed yet but the MSMARCO dataset has been downloaded previously, it is recommended to place the collection.tar.gz in the \"/Users/{username}/.pyterrier/corpora/trec-deep-learning-passages\" directory. This will make sure that PyTerrier does not download the corpus of the internet and uses the local file instead. "
)
# Single threaded indexing
# iter_indexer = pt.IterDictIndexer("./passage_index")
# indexref3 = iter_indexer.index(msmarco_generate(), meta=['docno', 'text'], meta_lengths=[20, 4096])
print(
"Performing Multi threaded indexing, if this does not work on your system (probably if it is Windows), then uncomment the two lines above this print statement and comment out the two lines below this statement in the code to make sure it runs on a single thread."
)
# Multi threaded indexing, UNIX-based systems only!!!!!
iter_indexer = pt.IterDictIndexer("./passage_index_8", threads=8)
indexref4 = iter_indexer.index(msmarco_generate(),
meta=['docno', 'text'],
meta_lengths=[20, 4096])
except ValueError as err:
if "Index already exists" in str(err):
print("Index already exists, loading existing one")
indexref4 = "./passage_index_8/data.properties"
pt.logging('WARN')
index = pt.IndexFactory.of(indexref4)
print(index.getCollectionStatistics().toString())
################
## DATA PREP ##
################
# Load topics as df: [qid, query]
# load qrels as df: [qid, docno, label]
def load_qrels_file(path):
df = pd.read_csv(path,
sep='\t',
names=['qid', 'q0', 'docno', 'label'],
dtype={
'qid': str,
'q0': str,
'docno': str,
'label': np.int32
})
del df['q0']
return df
def load_topics_file(path):
df = pd.read_csv(path,
sep='\t',
names=['qid', 'query'],
dtype={
'qid': str,
'query': str
})
exclude = set(string.punctuation)
# Remove punctuation
# print(exclude)
df['query'] = df['query'].apply(
lambda s: ''.join(ch for ch in s if ch not in exclude))
# print(df['query'][:6])
return df
def filter_train_qrels(train_topics_subset, train_qrels):
m = train_qrels.qid.isin(train_topics_subset.qid)
return train_qrels[m]
print('Loading train/validation topics and qrels')
print(
"Looking for the query files in the following directory: collections/msmarco-passage/, make sure to have the query files located there..."
)
train_topics = load_topics_file(
'collections/msmarco-passage/queries.train.tsv')
train_qrels = load_qrels_file(
'collections/msmarco-passage/qrels.train.tsv')
validation_topics = load_topics_file(
'collections/msmarco-passage/queries.dev.small.tsv')
validation_qrels = load_qrels_file(
'collections/msmarco-passage/qrels.dev.small.tsv')
test_topics = load_topics_file(
'collections/msmarco-passage/msmarco-test2019-queries.tsv')
print('Getting first {} train topics and corresponding qrels'.format(
top_n_train))
# TODO: not all queries here have qrels... Maybe filter on first 100 that have qrels?
if int(top_n_train) > 0:
train_sub = train_topics[:top_n_train].copy()
train_qrels_sub = filter_train_qrels(train_sub, train_qrels)
else:
train_sub = train_topics
train_qrels_sub = train_qrels
print('Getting first {} validation topics and corresponding qrels'.format(
top_n_validation))
if int(top_n_validation) > 0:
validation_sub = validation_topics[:top_n_validation].copy()
validation_qrels_sub = filter_train_qrels(validation_sub,
validation_qrels)
else:
validation_sub = validation_topics
validation_qrels_sub = validation_qrels
# print(train_qrels_sub)
##############
## TRAINING ##
##############
print('Setting up FeaturesBatchRetriever')
pipeline = pt.FeaturesBatchRetrieve(
index,
wmodel="BM25",
features=[
"SAMPLE", "WMODEL:Tf", "WMODEL:PL2", "WMODEL:TF_IDF",
"WMODEL:DLH13", "WMODEL:Hiemstra_LM"
]) % feat_batch
#### LAMBDAMART
print('Configuring Ranker...')
# this configures LightGBM as LambdaMART
lmart_l = lgb.LGBMRanker(
task="train",
# min_data_in_leaf=1,
# min_sum_hessian_in_leaf=100,
# max_bin=255,
num_leaves=7,
objective="lambdarank",
metric="ndcg",
# ndcg_eval_at=[1, 3, 5, 10],
learning_rate=.1,
importance_type="gain",
# num_iterations=10,
silent=False,
n_jobs=-1)
# lmart_x = xgb.sklearn.XGBRanker(objective='rank:ndcg',
# learning_rate=0.1,
# gamma=1.0,
# min_child_weight=0.1,
# max_depth=6,
# verbose=2,
# random_state=42)
print('''\n
########################################
###### Training pipeline summary: ######
########################################
Train Topics: {}
Train Qrels: {}
Validation topics: {}
Validation Qrels: {}
Amount of passage samples per query: {}
########################################
'''.format(train_sub.shape[0], train_qrels_sub.shape[0],
validation_sub.shape[0], validation_qrels_sub.shape[0],
FEATURES_BATCH_N))
start = time.time()
print(
"Model output is not rendered to the terminal until after the run is finished..."
)
if algorithm.upper() == LAMBDAMART:
print('Training LambdaMART pipeline')
# ltr_pipeline = pipeline >> pt.ltr.apply_learned_model(lmart_x, form="ltr")
# ltr_pipeline.fit(train_sub, train_qrels_sub, validation_topics, validation_qrels)
ltr_pipeline = pipeline >> pt.ltr.apply_learned_model(lmart_l,
form="ltr")
ltr_pipeline.fit_kwargs = {'verbose': 1}
ltr_pipeline.fit(train_sub, train_qrels_sub, validation_sub,
validation_qrels_sub)
model_name = "LambdaRANK"
elif algorithm.upper() == RANDOM_FOREST:
# RANDOM FOREST
print('Training RandomForest pipeline')
rf_model = RandomForestRegressor(n_jobs=-1, verbose=10)
ltr_pipeline = pipeline >> pt.ltr.apply_learned_model(rf_model)
ltr_pipeline.fit(train_sub, train_qrels_sub, validation_sub,
validation_qrels_sub)
model_name = 'RandomForest'
else:
print("ERROR: passed invalid algorithm as parameters")
sys.exit(1)
### End of training ###
end = time.time()
print('Training finished, time elapsed:', end - start, 'seconds...')
###########################
## RERANKING AND OUTPUT ##
###########################
# Output models to pickle files
# pipeline_filename = '{}_pipeline_{}_{}_{}.p'.format(model_name, train_sub.shape[0], validation_sub.shape[0], run_id)
# print('Exporting learned pipline to:', pipeline_filename)
# pickle.dump(ltr_pipeline, open(pipeline_filename, "wb"))
model_filename = '{}_model_{}_{}_{}.p'.format(model_name,
train_sub.shape[0],
validation_sub.shape[0],
run_id)
print('Exporting l2r model to:', model_filename)
if algorithm.upper() == LAMBDAMART:
pickle.dump(lmart_l, open(model_filename, "wb"))
else:
pickle.dump(rf_model, open(model_filename, "wb"))
print('Running test evaluation...')
# Test on small subset
# res = ltr_pipeline.transform(test_topics[:10].copy())
# Test on entire testset
start = time.time()
res = ltr_pipeline.transform(test_topics)
end = time.time()
print('Test evaluation finished, time elapsed:', end - start, 'seconds...')
print('Writing results...')
output_file_path = './{}_resuls_{}.trec'.format(model_name, str(run_id))
pt.io.write_results(res, output_file_path, format='trec')
print('SUCCES: results can be found at: ', output_file_path)
