Merge from main

.github/scripts/update_version.sh

@@ -10,4 +10,4 @@
 # ----------------------------------------------------------------------------
 #
 
-git describe --tags > VERSION
+git describe --tags > deepchecks/VERSION

.github/workflows/build.yml

@@ -17,7 +17,7 @@ on:
     branches: [ main ]
 
 env:
-  DEEPCHECKS_DISABLE_LATEST: "true"
+  DISABLE_DEEPCHECKS_ANONYMOUS_TELEMETRY: "true"
 
 jobs:
   tests:
@@ -91,7 +91,7 @@ jobs:
       with:
         requirements: 'requirements-all.txt'
         fail: 'Copyleft,Other,Error'
-        exclude: '(pyzmq.*22\.3\.0|debugpy.*1\.6\.0|certifi.*2021\.10\.8|tqdm.*4\.63\.1|webencodings.*0\.5\.1|torch.*1\.10\.2.*|torchaudio.*0\.10\.2.*|torchvision.*0\.11\.3.*)'
+        exclude: '(pyzmq.*22\.3\.0|debugpy.*1\.6\.0|certifi.*2021\.10\.8|tqdm.*4\.64\.0|webencodings.*0\.5\.1|torch.*1\.10\.2.*|torchaudio.*0\.10\.2.*|torchvision.*0\.11\.3.*)'
         # pyzmq is Revised BSD https://github.com/zeromq/pyzmq/blob/main/examples/LICENSE
         # debugpy is MIT https://github.com/microsoft/debugpy/blob/main/LICENSE
         # certifi is MPL-2.0 https://github.com/certifi/python-certifi/blob/master/LICENSE

.github/workflows/docs.yaml

@@ -24,7 +24,7 @@ on:
   workflow_dispatch:
 
 env:
-  DEEPCHECKS_DISABLE_LATEST: "true"
+  DISABLE_DEEPCHECKS_ANONYMOUS_TELEMETRY: "true"
   WANDB_MODE: "offline"
 
 jobs:
@@ -42,7 +42,7 @@ jobs:
       - name: Install pandoc
         run: |
           sudo apt-get update
-          sudo apt-get install pandoc dvisvgm texlive
+          sudo apt-get install pandoc dvisvgm texlive texlive-latex-extra
       - name: Build documentation
         run: make docs
 
@@ -78,4 +78,4 @@ jobs:
           token: ${{ secrets.DEEPCHECKS_CI_TOKEN }}
 
       - name: Push documentation
-        run: deepchecks/.github/scripts/push_docs.sh
+        run: deepchecks/.github/scripts/push_docs.sh

.github/workflows/lint.yml

@@ -16,6 +16,9 @@ on:
   pull_request: 
     branches: [ main ]
 
+env:
+  DISABLE_DEEPCHECKS_ANONYMOUS_TELEMETRY: "true"
+
 jobs:
   pylint:
     runs-on: ubuntu-latest

.github/workflows/pr.yaml

@@ -12,6 +12,10 @@ name: Pull Request
 on:
   pull_request:
     types: [opened, labeled, unlabeled, synchronize]
+
+env:
+  DISABLE_DEEPCHECKS_ANONYMOUS_TELEMETRY: "true"
+
 jobs:
   labels:
     name: Validate Label 

.github/workflows/release.yml

@@ -15,6 +15,9 @@ on:
     tags:
       - "[0-9]+.[0-9]+.[0-9]+"
 
+env:
+  DISABLE_DEEPCHECKS_ANONYMOUS_TELEMETRY: "true"
+
 jobs:
 #  Security-Check:
 #    runs-on: ubuntu-latest

.licenserc_fix.yaml

@@ -18,7 +18,7 @@ header:
     - '**/*.ipynb'
     - '.pylintrc'
     - 'LICENSE'
-    - 'VERSION'
+    - 'deepchecks/VERSION'
     - 'deepchecks.egg-info/PKG-INFO'
     - 'makefile'
     - 'examples/'

MANIFEST.in

@@ -3,7 +3,7 @@ include requirements/vision-requirements.txt
 include requirements/nlp-requirements.txt
 include requirements/dev-requirements.txt
 include LICENSE
-include VERSION
+include deepchecks/VERSION
 include README.rst
 include DESCRIPTION.rst
 recursive-include deepchecks/core/resources *

README.rst

@@ -41,7 +41,7 @@
 .. raw:: html
 
    <h1 align="center">
-      Test Suites for Validating ML Models & Data
+      Testing and Validating ML Models & Data
    </h1>
 
 .. raw:: html
@@ -59,16 +59,35 @@ machine learning models and data with minimal effort. This includes
 checks related to various types of issues, such as model performance,
 data integrity, distribution mismatches, and more.
 
+
+🖼️ Computer Vision & 🔢 Tabular Support
+==========================================
+**This README refers to the Tabular version** of deepchecks.
+
+Check out the `Deepchecks for Computer Vision & Images subpackage <deepchecks/vision>`__ for more details about deepchecks for CV, currently in *beta release*.
+
+
 💻 Installation
 =================
 
+
 Using pip
 ----------
 
 .. code:: bash
 
    pip install deepchecks -U --user
 
+.. note::
+
+   To install deepchecks together with the **Computer Vision Submodule** that is currently in *beta release*, replace ``deepchecks`` with ``"deepchecks[vision]"`` as follows.
+
+   .. code:: bash
+   
+      pip install "deepchecks[vision]" -U --user
+   
+   
+
 Using conda
 ------------
 
@@ -83,7 +102,7 @@ Using conda
 Head over to the `Quickstart Notebook <https://docs.deepchecks.com/en/stable/
 examples/guides/quickstart_in_5_minutes.html?
 utm_source=github.com&utm_medium=referral&utm_campaign=readme&utm_content=try_it_out>`__
-and choose the  |binder badge image|  or the  |colab badge image|  to have it up and running, and to then apply it on your own data and models.
+and see deepchecks output on a built-in dataset, or run it yourself to apply it on your own data and models.
 
 
 📊 Usage Examples
@@ -98,7 +117,7 @@ Example for running a suite on given `datasets`_ and with a `supported model`_:
 
 .. code:: python
 
-   from deepchecks.suites import full_suite
+   from deepchecks.tabular.suites import full_suite
    suite = full_suite()
    suite.run(train_dataset=train_dataset, test_dataset=test_dataset, model=model)
 
@@ -150,13 +169,13 @@ can be found in our `API Reference`_.
 
 .. code:: python
 
-   from deepchecks.checks import TrainTestFeatureDrift
+   from deepchecks.tabular.checks import TrainTestFeatureDrift
    import pandas as pd
 
    train_df = pd.read_csv('train_data.csv')
    test_df = pd.read_csv('test_data.csv')
    # Initialize and run desired check
-   TrainTestFeatureDrift().run(train_data, test_data)
+   TrainTestFeatureDrift().run(train_df, test_df)
 
 Will produce output of the type:
 
@@ -210,7 +229,7 @@ return value. An example for adding a condition would be:
 
 .. code:: python
 
-   from deepchecks.checks import BoostingOverfit
+   from deepchecks.tabular.checks import BoostingOverfit
    BoostingOverfit().add_condition_test_score_percent_decline_not_greater_than(threshold=0.05)
 
 which will return a check failure when running it if there is a difference of
@@ -245,17 +264,19 @@ of checks and optional conditions.
 
 
 What Do You Need in Order to Start Validating?
-----------------------------------------------
+==============================================
 
 Environment
-~~~~~~~~~~~~
+-----------
 
 - The deepchecks package installed
 
 - JupyterLab or Jupyter Notebook
 
+
 Data / Model 
-~~~~~~~~~~~~
+------------
+
 
 Depending on your phase and what you wish to validate, you'll need a
 subset of the following:
@@ -269,14 +290,15 @@ subset of the following:
 
 -  A `supported model`_ (e.g. scikit-learn models, XGBoost, any model implementing the `predict` method in the required format)
 
+
 Supported Data Types
-~~~~~~~~~~~~~~~~~~~~
+--------------------
+
+The package currently supports tabular data and is in *beta release* for the computer vision submodule.
 
-Currently the package supports tabular data.
-Stay tuned for the upcoming Computer Vision release.
 
 When Should I Run Deepchecks
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+----------------------------
 
 Deepchecks validation accompanies you from the initial phase when you
 have only raw data, through the data splits, and to the final stage of

deepchecks/__init__.py

@@ -13,7 +13,6 @@
 import types
 import os
 import pathlib
-import http.client
 import matplotlib
 import plotly.io as pio
 import warnings
@@ -45,6 +44,7 @@
     ModelComparisonSuite,
 )
 
+from deepchecks.analytics.anonymous_telemetry import send_anonymous_import_event
 
 __all__ = [
     # core
@@ -88,28 +88,16 @@
 
 # Set version info
 try:
-    MODULE_DIR = pathlib.Path(__file__).absolute().parent.parent
+    MODULE_DIR = pathlib.Path(__file__).absolute().parent
     with open(os.path.join(MODULE_DIR, 'VERSION'), 'r', encoding='utf-8') as f:
         __version__ = f.read().strip()
 except:  # pylint: disable=bare-except # noqa
     # If version file can't be found, leave version empty
     __version__ = ''
 
 
-# Check for latest version
-try:
-    disable = os.environ.get('DEEPCHECKS_DISABLE_LATEST', 'false').lower() == 'true'
-    if not disable:
-        conn = http.client.HTTPSConnection('api.deepchecks.com', timeout=3)
-        conn.request('GET', f'/v2/latest?version={__version__}')
-        response = conn.getresponse()
-        result = response.read().decode('utf-8') == 'True'
-        if not result:
-            warnings.warn('Looks like you are using outdated version of deepchecks. consider upgrading using'
-                          ' pip install -U deepchecks')
-except:  # pylint: disable=bare-except # noqa
-    pass
-
+# Send an import event if not disabled
+send_anonymous_import_event()
 
 # ================================================================
 

deepchecks/analytics/__init__.py

@@ -0,0 +1,15 @@
+# ----------------------------------------------------------------------------
+# Copyright (C) 2021-2022 Deepchecks (https://www.deepchecks.com)
+#
+# This file is part of Deepchecks.
+# Deepchecks is distributed under the terms of the GNU Affero General
+# Public License (version 3 or later).
+# You should have received a copy of the GNU Affero General Public License
+# along with Deepchecks.  If not, see <http://www.gnu.org/licenses/>.
+# ----------------------------------------------------------------------------
+#
+"""
+Module for anonymous telemetry.
+
+No credentials, data, personal information or anything private is collected (and will never be).
+"""

deepchecks/analytics/anonymous_telemetry.py

@@ -0,0 +1,42 @@
+# ----------------------------------------------------------------------------
+# Copyright (C) 2021-2022 Deepchecks (https://www.deepchecks.com)
+#
+# This file is part of Deepchecks.
+# Deepchecks is distributed under the terms of the GNU Affero General
+# Public License (version 3 or later).
+# You should have received a copy of the GNU Affero General Public License
+# along with Deepchecks.  If not, see <http://www.gnu.org/licenses/>.
+# ----------------------------------------------------------------------------
+#
+"""
+Module for anonymous telemetry.
+
+No credentials, data, personal information or anything private is collected (and will never be).
+"""
+import http.client
+import os
+import pathlib
+import uuid
+import deepchecks
+
+MODULE_DIR = pathlib.Path(__file__).absolute().parent.parent
+ANALYTICS_DISABLED = os.environ.get('DISABLE_DEEPCHECKS_ANONYMOUS_TELEMETRY', False)
+
+
+def send_anonymous_import_event():
+    """Send an anonymous import event to PostHog."""
+    if not ANALYTICS_DISABLED:
+        try:
+            if os.path.exists(os.path.join(MODULE_DIR, '.user_id')):
+                with open(os.path.join(MODULE_DIR, '.user_id'), 'r', encoding='utf8') as f:
+                    user_id = f.read()
+            else:
+                user_id = str(uuid.uuid4())
+                with open(os.path.join(MODULE_DIR, '.user_id'), 'w', encoding='utf8') as f:
+                    f.write(user_id)
+
+            conn = http.client.HTTPSConnection('api.deepchecks.com', timeout=3)
+            conn.request('GET', f'/metrics?version={deepchecks.__version__}&uuid={user_id}')
+            _ = conn.getresponse()
+        except Exception:  # pylint: disable=broad-except
+            pass