make release-tag: Merge branch 'master' into stable

csala · csala · commit b3bc6998d52a · 2021-02-24T22:21:52.000+01:00
diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md
diff --git a/.github/ISSUE_TEMPLATE/bug_report.md b/.github/ISSUE_TEMPLATE/bug_report.md
@@ -0,0 +1,33 @@
+---
+name: Bug report
+about: Report an error that you found when using CTGAN
+title: ''
+labels: bug, pending review
+assignees: ''
+
+---
+
+### Environment Details
+
+Please indicate the following details about the environment in which you found the bug:
+
+* CTGAN version:
+* Python version:
+* Operating System:
+
+### Error Description
+
+<!--Replace this text with a description of what you were trying to get done.
+Tell us what happened, what went wrong, and what you expected to happen.-->
+
+### Steps to reproduce
+
+<!--Replace this text with a description of the steps that anyone can follow to
+reproduce the error. If the error happens only on a specific dataset, please
+consider attaching some example data to the issue so that others can use it
+to reproduce the error.-->
+
+```
+Paste the command(s) you ran and the output.
+If there was a crash, please include the traceback here.
+```
diff --git a/.github/ISSUE_TEMPLATE/feature_request.md b/.github/ISSUE_TEMPLATE/feature_request.md
@@ -0,0 +1,24 @@
+---
+name: Feature request
+about: Request a new feature that you would like to see implemented in CTGAN
+title: ''
+labels: new feature, pending review
+assignees: ''
+
+---
+
+### Problem Description
+
+<!--Replace this with a description of the problem that you think CTGAN should be able
+to solve and is not solving already-->
+
+### Expected behavior
+
+<!--Replace this a clear and concise description of what you would expect CTGAN with regards
+with the described problem. If possible, explain how you would like to interact with CTGAN
+and what the outcome of this interaction would be.-->
+
+### Additional context
+
+<!--Please provide any additional context that may be relevant to the issue here. If none,
+please remove this section.-->
diff --git a/.github/ISSUE_TEMPLATE/question.md b/.github/ISSUE_TEMPLATE/question.md
@@ -0,0 +1,33 @@
+---
+name: Question
+about: Doubts about CTGAN usage
+title: ''
+labels: question, pending review
+assignees: ''
+
+---
+
+### Environment details
+
+If you are already running CTGAN, please indicate the following details about the environment in
+which you are running it:
+
+* CTGAN version:
+* Python version:
+* Operating System:
+
+### Problem description
+
+<!--Replace this with a description of the problem that you are trying to solve using CTGAN. If
+possible, describe the data that you are using, or consider attaching some example data
+that others can use to propose a working solution for your problem.-->
+
+### What I already tried
+
+<!--Replace with a description of what you already tried and what is the behavior that you observe.
+If possible, also add below the exact code that you are running.-->
+
+```
+Paste the command(s) you ran and the output.
+If there was a crash, please include the traceback here.
+```
diff --git a/HISTORY.md b/HISTORY.md
@@ -1,5 +1,16 @@
 # History
 
+## v0.4.0 - 2021-02-24
+
+Maintenance relese to upgrade dependencies to ensure compatibility with the rest
+of the SDV libraries.
+
+Also add a validation on the CTGAN `condition_column` and `condition_value` inputs.
+
+### Improvements
+
+* Validate condition_column and condition_value - Issue [#124](https://github.com/sdv-dev/CTGAN/issues/124) by @fealho
+
 ## v0.3.1 - 2021-01-27
 
 ### Improvements
diff --git a/conda/meta.yaml b/conda/meta.yaml
@@ -1,5 +1,5 @@
 {% set name = 'ctgan' %}
-{% set version = '0.3.1' %}
+{% set version = '0.4.0.dev2' %}
 
 package:
   name: "{{ name|lower }}"
@@ -17,35 +17,35 @@ build:
 
 requirements:
   host:
-    - numpy <2,>=1.17.4
-    - pandas <1.1.5,>=0.24
     - pip
-    - python
-    - rdt >=0.2.7,<0.3
-    - scikit-learn <0.24,>=0.21
-    - pytorch <2,>=1.0
-    - torchvision <1,>=0.4.2
-    - packaging
     - pytest-runner
+    - packaging
+    - python >=3.6,<3.9
+    - numpy >=1.18.0,<2
+    - pandas >=1.1,<1.1.5
+    - scikit-learn >=0.23,<1
+    - pytorch >=1.4,<2
+    - torchvision >=0.5.0,<1
+    - rdt >=0.4.0,<0.5
   run:
-    - numpy <2,>=1.17.4
-    - pandas <1.1.5,>=0.24
-    - python
-    - rdt >=0.2.7,<0.3
-    - scikit-learn <0.24,>=0.21
-    - pytorch <2,>=1.0
-    - torchvision <1,>=0.4.2
     - packaging
+    - python >=3.6,<3.9
+    - numpy >=1.18.0,<2
+    - pandas >=1.1,<1.1.5
+    - scikit-learn >=0.23,<1
+    - pytorch >=1.4,<2
+    - torchvision >=0.5.0,<1
+    - rdt >=0.4.0,<0.5
 
 about:
   home: "https://github.com/sdv-dev/CTGAN"
   license: MIT
   license_family: MIT
-  license_file: 
+  license_file:
   summary: "Conditional GAN for Tabular Data"
-  doc_url: 
-  dev_url: 
+  doc_url:
+  dev_url:
 
 extra:
   recipe-maintainers:
-    - sdv-dev
+    - sdv-dev
diff --git a/ctgan/__init__.py b/ctgan/__init__.py
@@ -4,7 +4,7 @@
 
 __author__ = 'MIT Data To AI Lab'
 __email__ = 'dailabmit@gmail.com'
-__version__ = '0.3.1'
+__version__ = '0.4.0.dev2'
 
 from ctgan.demo import load_demo
 from ctgan.synthesizers.ctgan import CTGANSynthesizer
diff --git a/ctgan/data_transformer.py b/ctgan/data_transformer.py
@@ -212,10 +212,18 @@ def convert_column_name_value_to_id(self, column_name, value):
                 break
             if column_transform_info.column_type == "discrete":
                 discrete_counter += 1
+
             column_id += 1
 
+        else:
+            raise ValueError(f"The column_name `{column_name}` doesn't exist in the data.")
+
+        one_hot = column_transform_info.transform.transform(np.array([value]))[0]
+        if sum(one_hot) == 0:
+            raise ValueError(f"The value `{value}` doesn't exist in the column `{column_name}`.")
+
         return {
             "discrete_column_id": discrete_counter,
             "column_id": column_id,
-            "value_id": np.argmax(column_transform_info.transform.transform(np.array([value]))[0])
+            "value_id": np.argmax(one_hot)
         }
diff --git a/setup.cfg b/setup.cfg
@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.3.1
+current_version = 0.4.0.dev2
 commit = True
 tag = True
 parse = (?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(\.(?P<release>[a-z]+)(?P<candidate>\d+))?
diff --git a/setup.py b/setup.py
@@ -12,13 +12,13 @@
     history = history_file.read()
 
 install_requires = [
-    'torch<2,>=1.0',
-    'torchvision<1,>=0.4.2',
-    'scikit-learn<0.24,>=0.21',
-    'numpy<2,>=1.17.4',
-    'pandas<1.1.5,>=0.24',
-    'rdt>=0.2.7,<0.4',
     'packaging',
+    'numpy>=1.18.0,<2',
+    'pandas>=1.1,<1.1.5',
+    'scikit-learn>=0.23,<1',
+    'torch>=1.4,<2',
+    'torchvision>=0.5.0,<1',
+    'rdt>=0.4.0,<0.5',
 ]
 
 setup_requires = [
@@ -99,6 +99,6 @@
     test_suite='tests',
     tests_require=tests_require,
     url='https://github.com/sdv-dev/CTGAN',
-    version='0.3.1',
+    version='0.4.0.dev2',
     zip_safe=False,
 )
diff --git a/tests/integration/test_ctgan.py b/tests/integration/test_ctgan.py
@@ -69,7 +69,6 @@ def test_ctgan_numpy():
 
 
 def test_log_frequency():
-
     data = pd.DataFrame({
         'continuous': np.random.random(1000),
         'discrete': np.repeat(['a', 'b', 'c'], [950, 25, 25])
@@ -168,3 +167,20 @@ def test_wrong_discrete_columns_numpy():
     ctgan = CTGANSynthesizer(epochs=1)
     with pytest.raises(ValueError):
         ctgan.fit(data.to_numpy(), discrete_columns)
+
+
+def test_wrong_sampling_conditions():
+    data = pd.DataFrame({
+        'continuous': np.random.random(100),
+        'discrete': np.random.choice(['a', 'b', 'c'], 100)
+    })
+    discrete_columns = ['discrete']
+
+    ctgan = CTGANSynthesizer(epochs=1)
+    ctgan.fit(data, discrete_columns)
+
+    with pytest.raises(ValueError):
+        ctgan.sample(1, 'cardinal', "doesn't matter")
+
+    with pytest.raises(ValueError):
+        ctgan.sample(1, 'discrete', "d")
diff --git a/tests/integration/test_tvae.py b/tests/integration/test_tvae.py
@@ -9,76 +9,27 @@
 model are not checked.
 """
 
-import tempfile as tf
-
-import numpy as np
 import pandas as pd
+from sklearn import datasets
 
 from ctgan.synthesizers.tvae import TVAESynthesizer
 
 
-def test_tvae_dataframe():
-    data = pd.DataFrame({
-        'continuous': np.random.random(1000),
-        'discrete': np.random.choice(['a', 'b'], 1000)
-    })
-    discrete_columns = ['discrete']
+def test_tvae(tmpdir):
+    iris = datasets.load_iris()
+    data = pd.DataFrame(iris.data, columns=iris.feature_names)
+    data['class'] = pd.Series(iris.target).map(iris.target_names.__getitem__)
 
     tvae = TVAESynthesizer(epochs=10)
-    tvae.fit(data, discrete_columns)
-
-    sampled = tvae.sample(100)
-
-    assert sampled.shape == (100, 2)
-    assert isinstance(sampled, pd.DataFrame)
-    assert set(sampled.columns) == {'continuous', 'discrete'}
-    assert set(sampled['discrete'].unique()) == {'a', 'b'}
+    tvae.fit(data, ['class'])
 
-
-def test_tvae_numpy():
-    data = pd.DataFrame({
-        'continuous': np.random.random(1000),
-        'discrete': np.random.choice(['a', 'b'], 1000)
-    })
-    discrete_columns = [1]
-
-    tvae = TVAESynthesizer(epochs=10)
-    tvae.fit(data.values, discrete_columns)
+    path = str(tmpdir / 'test_tvae.pkl')
+    tvae.save(path)
+    tvae = TVAESynthesizer.load(path)
 
     sampled = tvae.sample(100)
 
-    assert sampled.shape == (100, 2)
-    assert isinstance(sampled, np.ndarray)
-    assert set(np.unique(sampled[:, 1])) == {'a', 'b'}
-
-
-def test_synthesizer_sample():
-    data = pd.DataFrame({
-        'discrete': np.random.choice(['a', 'b'], 100)
-    })
-    discrete_columns = ['discrete']
-
-    tvae = TVAESynthesizer(epochs=1)
-    tvae.fit(data, discrete_columns)
-
-    samples = tvae.sample(1000)
-    assert isinstance(samples, pd.DataFrame)
-
-
-def test_save_load():
-    data = pd.DataFrame({
-        'continuous': np.random.random(100),
-        'discrete': np.random.choice(['a', 'b'], 100)
-    })
-    discrete_columns = ['discrete']
-
-    tvae = TVAESynthesizer(epochs=10)
-    tvae.fit(data, discrete_columns)
-
-    with tf.TemporaryDirectory() as temporary_directory:
-        tvae.save(temporary_directory + "test_tvae.pkl")
-        tvae = TVAESynthesizer.load(temporary_directory + "test_tvae.pkl")
-
-    sampled = tvae.sample(1000)
-    assert set(sampled.columns) == {'continuous', 'discrete'}
-    assert set(sampled['discrete'].unique()) == {'a', 'b'}
+    assert sampled.shape == (100, 5)
+    assert isinstance(sampled, pd.DataFrame)
+    assert set(sampled.columns) == set(data.columns)
+    assert set(sampled.dtypes) == set(data.dtypes)
