Metadata-Version: 2.4
Name: valentine
Version: 1.0.0
Summary: Valentine: find relationships between columns of different tabular datasets
Author-email: Delft Data <delftdatasystems@gmail.com>
Maintainer-email: Delft Data <delftdatasystems@gmail.com>
License:                                  Apache License
                                   Version 2.0, January 2004
                                http://www.apache.org/licenses/
        
           TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
        
           1. Definitions.
        
              "License" shall mean the terms and conditions for use, reproduction,
              and distribution as defined by Sections 1 through 9 of this document.
        
              "Licensor" shall mean the copyright owner or entity authorized by
              the copyright owner that is granting the License.
        
              "Legal Entity" shall mean the union of the acting entity and all
              other entities that control, are controlled by, or are under common
              control with that entity. For the purposes of this definition,
              "control" means (i) the power, direct or indirect, to cause the
              direction or management of such entity, whether by contract or
              otherwise, or (ii) ownership of fifty percent (50%) or more of the
              outstanding shares, or (iii) beneficial ownership of such entity.
        
              "You" (or "Your") shall mean an individual or Legal Entity
              exercising permissions granted by this License.
        
              "Source" form shall mean the preferred form for making modifications,
              including but not limited to software source code, documentation
              source, and configuration files.
        
              "Object" form shall mean any form resulting from mechanical
              transformation or translation of a Source form, including but
              not limited to compiled object code, generated documentation,
              and conversions to other media types.
        
              "Work" shall mean the work of authorship, whether in Source or
              Object form, made available under the License, as indicated by a
              copyright notice that is included in or attached to the work
              (an example is provided in the Appendix below).
        
              "Derivative Works" shall mean any work, whether in Source or Object
              form, that is based on (or derived from) the Work and for which the
              editorial revisions, annotations, elaborations, or other modifications
              represent, as a whole, an original work of authorship. For the purposes
              of this License, Derivative Works shall not include works that remain
              separable from, or merely link (or bind by name) to the interfaces of,
              the Work and Derivative Works thereof.
        
              "Contribution" shall mean any work of authorship, including
              the original version of the Work and any modifications or additions
              to that Work or Derivative Works thereof, that is intentionally
              submitted to Licensor for inclusion in the Work by the copyright owner
              or by an individual or Legal Entity authorized to submit on behalf of
              the copyright owner. For the purposes of this definition, "submitted"
              means any form of electronic, verbal, or written communication sent
              to the Licensor or its representatives, including but not limited to
              communication on electronic mailing lists, source code control systems,
              and issue tracking systems that are managed by, or on behalf of, the
              Licensor for the purpose of discussing and improving the Work, but
              excluding communication that is conspicuously marked or otherwise
              designated in writing by the copyright owner as "Not a Contribution."
        
              "Contributor" shall mean Licensor and any individual or Legal Entity
              on behalf of whom a Contribution has been received by Licensor and
              subsequently incorporated within the Work.
        
           2. Grant of Copyright License. Subject to the terms and conditions of
              this License, each Contributor hereby grants to You a perpetual,
              worldwide, non-exclusive, no-charge, royalty-free, irrevocable
              copyright license to reproduce, prepare Derivative Works of,
              publicly display, publicly perform, sublicense, and distribute the
              Work and such Derivative Works in Source or Object form.
        
           3. Grant of Patent License. Subject to the terms and conditions of
              this License, each Contributor hereby grants to You a perpetual,
              worldwide, non-exclusive, no-charge, royalty-free, irrevocable
              (except as stated in this section) patent license to make, have made,
              use, offer to sell, sell, import, and otherwise transfer the Work,
              where such license applies only to those patent claims licensable
              by such Contributor that are necessarily infringed by their
              Contribution(s) alone or by combination of their Contribution(s)
              with the Work to which such Contribution(s) was submitted. If You
              institute patent litigation against any entity (including a
              cross-claim or counterclaim in a lawsuit) alleging that the Work
              or a Contribution incorporated within the Work constitutes direct
              or contributory patent infringement, then any patent licenses
              granted to You under this License for that Work shall terminate
              as of the date such litigation is filed.
        
           4. Redistribution. You may reproduce and distribute copies of the
              Work or Derivative Works thereof in any medium, with or without
              modifications, and in Source or Object form, provided that You
              meet the following conditions:
        
              (a) You must give any other recipients of the Work or
                  Derivative Works a copy of this License; and
        
              (b) You must cause any modified files to carry prominent notices
                  stating that You changed the files; and
        
              (c) You must retain, in the Source form of any Derivative Works
                  that You distribute, all copyright, patent, trademark, and
                  attribution notices from the Source form of the Work,
                  excluding those notices that do not pertain to any part of
                  the Derivative Works; and
        
              (d) If the Work includes a "NOTICE" text file as part of its
                  distribution, then any Derivative Works that You distribute must
                  include a readable copy of the attribution notices contained
                  within such NOTICE file, excluding those notices that do not
                  pertain to any part of the Derivative Works, in at least one
                  of the following places: within a NOTICE text file distributed
                  as part of the Derivative Works; within the Source form or
                  documentation, if provided along with the Derivative Works; or,
                  within a display generated by the Derivative Works, if and
                  wherever such third-party notices normally appear. The contents
                  of the NOTICE file are for informational purposes only and
                  do not modify the License. You may add Your own attribution
                  notices within Derivative Works that You distribute, alongside
                  or as an addendum to the NOTICE text from the Work, provided
                  that such additional attribution notices cannot be construed
                  as modifying the License.
        
              You may add Your own copyright statement to Your modifications and
              may provide additional or different license terms and conditions
              for use, reproduction, or distribution of Your modifications, or
              for any such Derivative Works as a whole, provided Your use,
              reproduction, and distribution of the Work otherwise complies with
              the conditions stated in this License.
        
           5. Submission of Contributions. Unless You explicitly state otherwise,
              any Contribution intentionally submitted for inclusion in the Work
              by You to the Licensor shall be under the terms and conditions of
              this License, without any additional terms or conditions.
              Notwithstanding the above, nothing herein shall supersede or modify
              the terms of any separate license agreement you may have executed
              with Licensor regarding such Contributions.
        
           6. Trademarks. This License does not grant permission to use the trade
              names, trademarks, service marks, or product names of the Licensor,
              except as required for reasonable and customary use in describing the
              origin of the Work and reproducing the content of the NOTICE file.
        
           7. Disclaimer of Warranty. Unless required by applicable law or
              agreed to in writing, Licensor provides the Work (and each
              Contributor provides its Contributions) on an "AS IS" BASIS,
              WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
              implied, including, without limitation, any warranties or conditions
              of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
              PARTICULAR PURPOSE. You are solely responsible for determining the
              appropriateness of using or redistributing the Work and assume any
              risks associated with Your exercise of permissions under this License.
        
           8. Limitation of Liability. In no event and under no legal theory,
              whether in tort (including negligence), contract, or otherwise,
              unless required by applicable law (such as deliberate and grossly
              negligent acts) or agreed to in writing, shall any Contributor be
              liable to You for damages, including any direct, indirect, special,
              incidental, or consequential damages of any character arising as a
              result of this License or out of the use or inability to use the
              Work (including but not limited to damages for loss of goodwill,
              work stoppage, computer failure or malfunction, or any and all
              other commercial damages or losses), even if such Contributor
              has been advised of the possibility of such damages.
        
           9. Accepting Warranty or Additional Liability. While redistributing
              the Work or Derivative Works thereof, You may choose to offer,
              and charge a fee for, acceptance of support, warranty, indemnity,
              or other liability obligations and/or rights consistent with this
              License. However, in accepting such obligations, You may act only
              on Your own behalf and on Your sole responsibility, not on behalf
              of any other Contributor, and only if You agree to indemnify,
              defend, and hold each Contributor harmless for any liability
              incurred by, or claims asserted against, such Contributor by reason
              of your accepting any such warranty or additional liability.
        
           END OF TERMS AND CONDITIONS
        
           APPENDIX: How to apply the Apache License to your work.
        
              To apply the Apache License to your work, attach the following
              boilerplate notice, with the fields enclosed by brackets "[]"
              replaced with your own identifying information. (Don't include
              the brackets!)  The text should be enclosed in the appropriate
              comment syntax for the file format. We also recommend that a
              file or class name and description of purpose be included on the
              same "printed page" as the copyright notice for easier
              identification within third-party archives.
        
           Copyright 2021-2026 Delft University of Technology
        
           Licensed under the Apache License, Version 2.0 (the "License");
           you may not use this file except in compliance with the License.
           You may obtain a copy of the License at
        
               http://www.apache.org/licenses/LICENSE-2.0
        
           Unless required by applicable law or agreed to in writing, software
           distributed under the License is distributed on an "AS IS" BASIS,
           WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
           See the License for the specific language governing permissions and
           limitations under the License.
        
Project-URL: Homepage, https://delftdata.github.io/valentine/
Project-URL: Documentation, https://delftdata.github.io/valentine/
Project-URL: Source, https://github.com/delftdata/valentine
Project-URL: Issues, https://github.com/delftdata/valentine/issues
Project-URL: Changelog, https://github.com/delftdata/valentine/releases
Keywords: matching,valentine,schema matching,dataset discovery,coma,cupid,similarity flooding
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Developers
Classifier: Topic :: Scientific/Engineering :: Information Analysis
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Programming Language :: Python :: 3.14
Classifier: Operating System :: POSIX
Classifier: Operating System :: MacOS :: MacOS X
Classifier: Operating System :: Microsoft :: Windows
Requires-Python: <3.15,>=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: numpy<3.0,>=2.0
Requires-Dist: pandas<4.0,>=2.0
Requires-Dist: nltk<4.0,>=3.9.4
Requires-Dist: anytree<3.0,>=2.9
Requires-Dist: networkx<4.0,>=2.8
Requires-Dist: chardet<8.0,>=7.0
Requires-Dist: rapidfuzz<4.0,>=3.0
Requires-Dist: PuLP<4.0,>=2.5
Requires-Dist: POT<1.0,>=0.9.5
Requires-Dist: scipy<2.0,>=1.12
Requires-Dist: python-dateutil<3.0,>=2.8
Provides-Extra: dev
Requires-Dist: pytest<10.0,>=9.0; extra == "dev"
Requires-Dist: coverage<8.0,>=7.0; extra == "dev"
Requires-Dist: ruff<1.0,>=0.15; extra == "dev"
Provides-Extra: polars
Requires-Dist: polars<2.0,>=1.0; extra == "polars"
Provides-Extra: embeddings
Requires-Dist: sentence-transformers<6.0,>=2.0; extra == "embeddings"
Provides-Extra: docs
Requires-Dist: zensical==0.0.41; extra == "docs"
Dynamic: license-file

<h1 align="center">
  <img src="docs/assets/favicon.png" alt="" width="40" valign="middle">
  Valentine
</h1>
<p align="center"><em>(Schema-) Matching DataFrames Made Easy</em></p>

<p align="center">
  <a href="https://github.com/delftdata/valentine/actions/workflows/build.yml">
    <img src="https://github.com/delftdata/valentine/actions/workflows/build.yml/badge.svg" alt="Build">
  </a>
  <a href="https://codecov.io/gh/delftdata/valentine">
    <img src="https://codecov.io/gh/delftdata/valentine/branch/master/graph/badge.svg?token=4QR0X315CL" alt="codecov">
  </a>
  <a href="https://app.codacy.com/gh/delftdata/valentine/dashboard">
    <img src="https://app.codacy.com/project/badge/Grade/85cfebfc9c6a43359c5b2e56a5fdf3a3" alt="Codacy Badge">
  </a>
  <a href="https://github.com/astral-sh/ruff">
    <img src="https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json" alt="Ruff">
  </a>
  <a href="https://pypi.org/project/valentine/">
    <img src="https://img.shields.io/pypi/v/valentine.svg" alt="PyPI version">
  </a>
  <a href="https://pypi.org/project/valentine/">
    <img src="https://img.shields.io/pypi/pyversions/valentine.svg" alt="Python versions">
  </a>
  <a href="https://pypi.org/project/valentine/">
    <img src="https://img.shields.io/pypi/dm/valentine.svg" alt="PyPI downloads">
  </a>
  <a href="https://github.com/delftdata/valentine/blob/master/LICENSE">
    <img src="https://img.shields.io/github/license/delftdata/valentine.svg" alt="License">
  </a>
  <a href="https://delftdata.github.io/valentine/">
    <img src="https://img.shields.io/badge/docs-GitHub%20Pages-blue.svg" alt="Docs">
  </a>
</p>

---

A Python package for capturing potential relationships among columns of different tabular datasets, given as pandas or Polars DataFrames.
Valentine is based on the paper [**Valentine: Evaluating Matching Techniques for Dataset Discovery**](https://ieeexplore.ieee.org/abstract/document/9458921).

📚 **Full documentation:** <https://delftdata.github.io/valentine/> — getting started, matcher guide, API reference, and migration notes.


## Experimental suite version

The original experimental suite version of Valentine, as first published for the needs of the research paper, can be still found [here](https://github.com/delftdata/valentine/tree/v1.1).

## Installation instructions
### Requirements

*   *Python* >=3.10,<3.15

To install Valentine simply run:

```shell
pip install valentine
```

To enable **Polars** support, install the optional extra:

```shell
pip install valentine[polars]
```

To enable the **sentence-transformer embedding** distance for `JaccardDistanceMatcher` (see below), install:

```shell
pip install valentine[embeddings]
```


## Usage
Valentine can be used to find matches among columns of a given pair of pandas or Polars DataFrames. You can even mix pandas and Polars frames in the same call — Valentine auto-detects the frame type.

### Matching methods
In order to do so, the user can choose one of the following matching methods:

1.   `Coma(int: max_n, bool: use_instances, bool: use_schema, float: delta, float: threshold)` is a pure Python implementation of the [COMA 3.0](https://sourceforge.net/projects/coma-ce/) schema matching algorithm.
     *    **Parameters**:
           *    **max_n**(*int*) - Maximum number of matches to keep per column, 0 means unlimited (default: 0).
           *    **use_instances**(*bool*) - Whether to use TF-IDF instance-based matching on data values (default: False).
           *    **use_schema**(*bool*) - Whether to use schema-based matching on column names, paths, and structure (default: True).
           *    **delta**(*float*) - Fraction from the best score within which matches are kept (default: 0.15).
           *    **threshold**(*float*) - Absolute minimum similarity score to keep a match (default: 0.0).

2.   `Cupid(float: w_struct, float: leaf_w_struct, float: th_accept)` is the python implementation of the paper [Generic Schema Matching with Cupid](https://www.vldb.org/conf/2001/P049.pdf)
     *    **Parameters**:
          *    **w_struct**(*float*) - Structural similarity threshold, default is 0.2.
          *    **leaf_w_struct**(*float*) - Structural similarity threshold, leaf level, default is 0.2.
          *    **th_accept**(*float*) - Accept similarity threshold, default is 0.7.

3.   `DistributionBased(float: threshold1, float: threshold2)` is the python implementation of the paper [Automatic Discovery of Attributes in Relational Databases](https://dl.acm.org/doi/10.1145/1989323.1989336)
     *    **Parameters**:
          *    **threshold1**(*float*) - The threshold for phase 1 of the method, default is 0.15.
          *    **threshold2**(*float*) - The threshold for phase 2 of the method, default is 0.15.

4.   `JaccardDistanceMatcher(...)` is a baseline method that scores column pairs by **Tversky** similarity over their value sets (Jaccard by default). Element equality between values can be decided by a configurable string distance function, including a sentence-transformer **embedding** option for semantic matching.
     *    **Parameters**:
          *    **threshold_dist**(*float*) - Acceptance threshold above which two values are considered equal under the chosen `distance_fun`, default is 0.8. For embeddings, ~0.7 is a typical operating point.
          *    **distance_fun**(*StringDistanceFunction*) - Per-value similarity function. The enumeration class `StringDistanceFunction` can be imported from `valentine.algorithms.jaccard_distance`. Functions currently supported are:
   		       * `StringDistanceFunction.Levenshtein`: [Levenshtein distance](https://en.wikipedia.org/wiki/Levenshtein_distance) (default)
               * `StringDistanceFunction.DamerauLevenshtein`: [Damerau-Levenshtein distance](https://en.wikipedia.org/wiki/Damerau%E2%80%93Levenshtein_distance)
               * `StringDistanceFunction.Hamming`: [Hamming distance](https://en.wikipedia.org/wiki/Hamming_distance)
               * `StringDistanceFunction.Jaro`: [Jaro distance](https://en.wikipedia.org/wiki/Jaro%E2%80%93Winkler_distance)
               * `StringDistanceFunction.JaroWinkler`: [Jaro-Winkler distance](https://en.wikipedia.org/wiki/Jaro%E2%80%93Winkler_distance)
               * `StringDistanceFunction.Exact`: String equality `==`
               * `StringDistanceFunction.Embedding`: cosine similarity on sentence-transformer embeddings (requires the `valentine[embeddings]` extra)
          *    **tversky_alpha**(*float*) / **tversky_beta**(*float*) - Tversky penalty weights for unmatched values on each side (defaults `1.0`, `1.0`). Defaults give Jaccard; `0.5, 0.5` gives Sørensen-Dice; `1.0, 0.0` (or vice versa) gives set containment — useful when one column is expected to be a subset of the other.
          *    **embedding_model**(*str*) - Sentence-transformers model name when `distance_fun=Embedding` (default `"all-MiniLM-L6-v2"`).
          *    **embedding_device**(*str* or *None*) - Device override (`"cpu"`, `"cuda"`, `"mps"`). `None` (default) auto-picks: cuda → mps → cpu.
          *    **embedding_batch_size**(*int* or *None*) - Encode batch size; `None` uses the sentence-transformers default (32). Larger values amortise per-call overhead on capable hardware.

5.   `SimilarityFlooding(Policy: coeff_policy, Formula: formula, StringMatcher: string_matcher)` is the python implementation of the paper [Similarity Flooding: A Versatile Graph Matching Algorithmand its Application to Schema Matching](https://ieeexplore.ieee.org/document/994702)
     * **Parameters**:
        *    **coeff_policy**(*Policy*) - Policy for deciding the weight coefficients of the propagation graph. `Policy.INVERSE_PRODUCT` or `Policy.INVERSE_AVERAGE` (default).
        *    **formula**(*Formula*) - Formula on which iterative fixpoint computation is based. `Formula.BASIC`, `Formula.FORMULA_A`, `Formula.FORMULA_B`, or `Formula.FORMULA_C` (default).
        *    **string_matcher**(*StringMatcher*) - String matching function for the initial similarity mapping. `StringMatcher.PREFIX_SUFFIX` (default), `StringMatcher.PREFIX_SUFFIX_TFIDF`, or `StringMatcher.LEVENSHTEIN`.

### Matching DataFrames

Pass two or more DataFrames as a list (or any iterable) along with a matcher. Valentine will match columns across all unique pairs. Pandas and Polars frames can be freely mixed:

```python
# Match a pair of DataFrames (pandas, Polars, or mixed)
matches = valentine_match([df1, df2], matcher)

# Match multiple DataFrames (computes all N×(N-1)/2 pairs)
matches = valentine_match([df1, df2, df3], matcher, df_names=["sales", "orders", "products"])
```

Optionally provide `df_names` to label each DataFrame (defaults to "aaa", "bbb", etc. — designed to have zero similarity so they don't influence schema-based matchers). Function `valentine_match` returns a `MatcherResults` object, an immutable mapping from `ColumnPair` to similarity scores with convenience methods for filtering, subsetting, and evaluation.


### MatcherResults and ColumnPair

Results are keyed by `ColumnPair` namedtuples with named fields for easy access:

```python
for pair, score in matches.items():
    print(f"{pair.source_column} <-> {pair.target_column}: {score:.3f}")
    # Also available: pair.source_table, pair.target_table
    # Shorthand tuples: pair.source, pair.target
```

`MatcherResults` provides convenience methods for filtering and subsetting:
```python
top_n_matches = matches.take_top_n(5)
top_n_percent_matches = matches.take_top_percent(25)
high_confidence = matches.filter(min_score=0.7)

# One-to-one selectors — three flavours, pick the one that fits your task:
one_to_one_matches = matches.one_to_one_hungarian()           # globally optimal (default)
one_to_one_strict = matches.one_to_one_hungarian(threshold=0.5)
greedy_legacy = matches.one_to_one_greedy()                   # legacy greedy assignment
mutual_only = matches.one_to_one_mutual_top(n=1)              # mutual nearest neighbour
```

`one_to_one_hungarian` (Hungarian assignment via `scipy.optimize.linear_sum_assignment`) is the recommended default and is what `Precision` / `Recall` / `F1Score` apply when their `one_to_one` flag is set. `one_to_one_greedy` preserves the legacy greedy behaviour for backwards compatibility. `one_to_one_mutual_top(n)` keeps a pair only when each side ranks the other in its top-`n` — a high-precision filter that drops one-sided affinities.

### Match details (Coma)

When using the Coma matcher, per-sub-matcher score breakdowns are available via `.details`:

```python
for pair, score in matches.items():
    details = matches.get_details(pair)
    if details:
        print(f"{pair.source_column} <-> {pair.target_column}: {details}")
        # e.g. {'NameCM': 0.72, 'PathCM': 0.65, 'LeavesCM': 0.58, ...}
```


### Measuring effectiveness

```python
metrics = matches.get_metrics(ground_truth)
```

Computes Precision, Recall, F1-score and others as described in the original Valentine paper. The ground truth is a list of `(source_column, target_column)` tuples:

```python
ground_truth = [("emp_id", "employee_number"), ("fname", "first_name"), ...]
```

Custom metrics can be specified, and predefined sets are available:

```python
from valentine.metrics import F1Score, PrecisionTopNPercent, METRICS_PRECISION_INCREASING_N
metrics_custom = matches.get_metrics(ground_truth, metrics={F1Score(one_to_one=False), PrecisionTopNPercent(n=70)})
metrics_predefined_set = matches.get_metrics(ground_truth, metrics=METRICS_PRECISION_INCREASING_N)
```

The 1:1 selection algorithm used when a metric's `one_to_one` flag is `True` can be overridden per call (default `"hungarian"`):

```python
metrics_strict   = matches.get_metrics(ground_truth, metrics={F1Score()}, one_to_one_method="mutual_top")
metrics_legacy   = matches.get_metrics(ground_truth, metrics={F1Score()}, one_to_one_method="greedy")
```

Valid values are `"hungarian"` (default), `"greedy"`, and `"mutual_top"`. Metrics whose `one_to_one` flag is `False` (e.g. `MeanReciprocalRank`, `RecallAtSizeofGroundTruth`) ignore the argument.


### Example
The following block of code shows: 1) how to run a matcher from Valentine on two DataFrames storing information about job candidates, and then 2) how to assess its effectiveness based on a given ground truth. More examples are available in the [`examples/`](https://github.com/delftdata/valentine/tree/master/examples) directory, including a [pandas example](https://github.com/delftdata/valentine/blob/master/examples/valentine_example_pandas.py), a [Polars example](https://github.com/delftdata/valentine/blob/master/examples/valentine_example_polars.py), and a [mixed pandas+Polars example](https://github.com/delftdata/valentine/blob/master/examples/valentine_example_mixed.py).

```python
import pandas as pd
from valentine import valentine_match
from valentine.algorithms import Coma

# Load data using pandas
df1 = pd.read_csv("source_candidates.csv")
df2 = pd.read_csv("target_candidates.csv")

# Instantiate matcher and run
matcher = Coma(use_instances=True)
matches = valentine_match([df1, df2], matcher)

# Iterate over results using ColumnPair named fields
for pair, score in matches.items():
    print(f"{pair.source_column} <-> {pair.target_column}: {score:.3f}")

# If ground truth available valentine could calculate the metrics
ground_truth = [
    ("emp_id", "employee_number"),
    ("fname", "first_name"),
    ("lname", "last_name"),
    ("dept", "department"),
    ("annual_salary", "compensation"),
    ("hire_date", "start_date"),
    ("office_loc", "work_location"),
]

metrics = matches.get_metrics(ground_truth)
print(metrics)
```

## Cite Valentine
```
Original Valentine paper:
@inproceedings{koutras2021valentine,
  title={Valentine: Evaluating Matching Techniques for Dataset Discovery},
  author={Koutras, Christos and Siachamis, George and Ionescu, Andra and Psarakis, Kyriakos and Brons, Jerry and Fragkoulis, Marios and Lofi, Christoph and Bonifati, Angela and Katsifodimos, Asterios},
  booktitle={2021 IEEE 37th International Conference on Data Engineering (ICDE)},
  pages={468--479},
  year={2021},
  organization={IEEE}
}
Demo Paper:
@article{koutras2021demo,
  title={Valentine in Action: Matching Tabular Data at Scale},
  author={Koutras, Christos and Psarakis, Kyriakos and Siachamis, George and Ionescu, Andra and Fragkoulis, Marios and Bonifati, Angela and Katsifodimos, Asterios},
  journal={VLDB},
  volume={14},
  number={12},
  pages={2871--2874},
  year={2021},
  publisher={VLDB Endowment}
}
```
