Add models and interfaces

Author: OlivieFranklova

.pylintrc

@@ -68,7 +68,7 @@ ignored-modules=
 
 # Python code to execute, usually for sys.path manipulation such as
 # pygtk.require().
-#init-hook=
+init-hook='import sys; sys.path.append("./similarity"); sys.path.append("./similarityRunner")'
 
 # Use multiple processes to speed up Pylint. Specifying 0 will auto-detect the
 # number of processors available to use, and will cap the count on Windows to

requirements.txt

@@ -1,21 +1,34 @@
+altair==5.4.1
+annotated-types==0.7.0
 astroid==3.2.4
+attrs==24.2.0
 black==24.8.0
+blinker==1.8.2
+cachetools==5.5.0
 certifi==2024.8.30
 charset-normalizer==3.3.2
 click==8.1.7
+coverage==7.6.1
 dill==0.3.8
 filelock==3.16.0
 fsspec==2024.9.0
+gitdb==4.0.11
+GitPython==3.1.43
 huggingface-hub==0.24.7
 idna==3.10
 iniconfig==2.0.0
 isort==5.13.2
 Jinja2==3.1.4
 joblib==1.4.2
+jsonschema==4.23.0
+jsonschema-specifications==2023.12.1
+markdown-it-py==3.0.0
 MarkupSafe==2.1.5
 mccabe==0.7.0
+mdurl==0.1.2
 mpmath==1.3.0
 mypy-extensions==1.0.0
+narwhals==1.8.1
 networkx==3.3
 numpy==1.26.4
 packaging==24.1
@@ -25,24 +38,37 @@ pillow==10.4.0
 platformdirs==4.3.3
 plotly==5.24.1
 pluggy==1.5.0
+protobuf==5.28.1
+pyarrow==17.0.0
+pydantic==2.9.2
+pydantic_core==2.23.4
+pydeck==0.9.1
+Pygments==2.18.0
 pylint==3.2.7
 pytest==8.3.3
 python-dateutil==2.9.0.post0
 pytz==2024.2
 PyYAML==6.0.2
+referencing==0.35.1
 regex==2024.9.11
 requests==2.32.3
+rich==13.8.1
+rpds-py==0.20.0
 safetensors==0.4.5
 scikit-learn==1.5.2
 scipy==1.14.1
 sentence-transformers==3.1.0
 six==1.16.0
+smmap==5.0.1
+streamlit==1.38.0
 sympy==1.13.2
 tenacity==9.0.0
 threadpoolctl==3.5.0
 tokenizers==0.19.1
+toml==0.10.2
 tomlkit==0.13.2
 torch==2.4.1
+tornado==6.4.1
 tqdm==4.66.5
 transformers==4.44.2
 typing_extensions==4.12.2

similarity/README.md

@@ -1,5 +1,7 @@
 # Structure
-- folder [comparing_all_tables](comparing_all_tables) 
+- folder [comparing_all_tables](comparing_all_tables)
+- folder [interfaces](interfaces)
+- folder [models](models)
 - file [Comparator](Comparator.py)
 - file [ComparatorByColumns](ComparatorByColumn.py)
 - file [Types](Types.py)
@@ -15,6 +17,10 @@ we do not recommend to use it.
 
 File `categorical.ipynb` shows usage of `comparing.py`.
 
+## folder interfaces
+This folder contains two files: `ConnectorInterface.py` and `UserInterface.py`.
+## folder models
+Contains all models that are used for interfaces.
 ## file Comparator.py
 File contains Comparator class, ComparatorType classes and DistanceFunction
 Comparator is part of the pipeline that is shown below

similarityRunner/interfaces/ConnectorInterface.py

@@ -0,0 +1,32 @@
+"""
+File contains Connector interface
+"""
+import abc
+
+from models.connector_models import ConnectorSettings, Output, ConnectorOutput
+
+
+class ConnectorInterface(metaclass=abc.ABCMeta):
+    """
+    ConnectorInterface class is an abstract class that defines
+     the methods that must be implemented by the concrete connector classes.
+    """
+
+    @abc.abstractmethod
+    def _connect_and_load_data_source(self, settings: ConnectorSettings) -> ConnectorOutput:
+        """Load in the data set
+        :param settings: ConnectorSettings
+        this is a protected method"""
+        raise NotImplementedError
+
+    @abc.abstractmethod
+    def _format_data(self, data: ConnectorOutput) -> Output:
+        """Format loaded data
+        this is a protected method"""
+        raise NotImplementedError
+
+    def get_data(self, settings: ConnectorSettings) -> Output:
+        """Get formated data from the loaded data source
+        :return: data"""
+        data = self._connect_and_load_data_source(settings)
+        return self._format_data(data)

similarityRunner/interfaces/UserInterface.py

@@ -0,0 +1,28 @@
+"""
+File contains UserInterface interface
+"""
+import abc
+
+from models.user_models import SimilarityOutput
+from models.connector_models import ConnectorSettings
+
+
+class UserInterface(metaclass=abc.ABCMeta):
+    """
+    UserInterface is an abstract class that defines the methods
+     that must be implemented by any class that inherits from it.
+    """
+
+    @abc.abstractmethod
+    def get_user_input(self) -> ConnectorSettings:
+        """
+        Get user input and returns it as ConnectorSettings object
+        """
+        raise NotImplementedError
+
+    @abc.abstractmethod
+    def display_output(self, output: SimilarityOutput) -> None:
+        """
+        Display output to the user
+        """
+        raise NotImplementedError

similarityRunner/interfaces/__init__.py

@@ -0,0 +1,23 @@
+"""
+Connector models module contains:
+ - the base class for connector settings and derived classes.
+ - the base class for connector output and derived classes.
+"""
+import pandas as pd
+from pydantic import BaseModel
+
+Output = pd.DataFrame
+
+
+class ConnectorSettings(BaseModel):
+    """
+    ConnectorSettings class is a base class for connector settings.
+    """
+    # here will be common fields for all connectors
+
+
+class ConnectorOutput(BaseModel):
+    """
+    ConnectorOutput class is a base class for connector output.
+    """
+    # here will be common fields for all connectors

similarityRunner/models/__init__.py

@@ -0,0 +1,13 @@
+"""
+This module contains the user models
+"""
+from pydantic import BaseModel
+
+
+class SimilarityOutput(BaseModel):
+    """
+    SimilarityOutput class isclass containing similarity output.
+    """
+    # here will be common fields for all similarity models
+    table_names: list[str]
+    distances: dict[(str, str),float]