Merge branch 'main' of github.com:CITCOM-project/CausalTestingFramework into metamorphic_testing

Author: jmafoster1

.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,38 @@
+---
+name: Bug report
+about: Create a report to help us improve
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+**Describe the bug**
+A clear and concise description of what the bug is.
+
+**To Reproduce**
+Steps to reproduce the behavior:
+1. Go to '...'
+2. Click on '....'
+3. Scroll down to '....'
+4. See error
+
+**Expected behavior**
+A clear and concise description of what you expected to happen.
+
+**Screenshots**
+If applicable, add screenshots to help explain your problem.
+
+**Desktop (please complete the following information):**
+ - OS: [e.g. iOS]
+ - Browser [e.g. chrome, safari]
+ - Version [e.g. 22]
+
+**Smartphone (please complete the following information):**
+ - Device: [e.g. iPhone6]
+ - OS: [e.g. iOS8.1]
+ - Browser [e.g. stock browser, safari]
+ - Version [e.g. 22]
+
+**Additional context**
+Add any other context about the problem here.

.github/ISSUE_TEMPLATE/feature_request.md

@@ -0,0 +1,20 @@
+---
+name: Feature request
+about: Suggest an idea for this project
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+**Is your feature request related to a problem? Please describe.**
+A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
+
+**Describe the solution you'd like**
+A clear and concise description of what you want to happen.
+
+**Describe alternatives you've considered**
+A clear and concise description of any alternative solutions or features you've considered.
+
+**Additional context**
+Add any other context or screenshots about the feature request here.

.github/workflows/publish-to-pypi.yaml

@@ -0,0 +1,33 @@
+name: Publish python PyPI
+
+on:
+  push:
+    tags:
+      - v*
+
+jobs:
+  build-release:
+    name: Build and publish PyPI
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+      - name: Set up Python
+        uses: actions/setup-python@v3
+        with:
+          python-version: 3.9
+      - name: Installing package
+        run: |
+          pip3 install .
+          pip3 install .[pypi]
+          pip3 install build
+          pip3 install setuptools --upgrade
+          pip3 install setuptools_scm
+      - name: Build Package
+        run: |
+          python -m build --no-isolation
+      - name: Publish package to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          password: ${{ secrets.PYPI_API_TOKEN }}

.pylintrc

@@ -152,6 +152,8 @@ disable=raw-checker-failed,
         useless-suppression,
         deprecated-pragma,
         use-symbolic-message-instead,
+        logging-fstring-interpolation,
+        import-error,
 
 # Enable the message, report, category or checker with the given id(s). You can
 # either give multiple identifier separated by comma (,) or put this option
@@ -239,7 +241,9 @@ good-names=i,
            j,
            k,
            ex,
+           df,
            Run,
+           z3,
            _
 
 # Good variable names regexes, separated by a comma. If names match any regex,

README.md

@@ -31,7 +31,7 @@ Here are some explanations for the causal inference terminology used above.
 
 ## Installation
 
-To use the causal testing framework, clone the repository, `cd` into the root directory, and run `pip install -e .`. More detailled installation instructions can be found in the [online documentation](https://causal-testing-framework.readthedocs.io/en/latest/installation.html).
+See the readthedocs site for installation instructions](https://causal-testing-framework.readthedocs.io/en/latest/installation.html).
 
 ## Usage
 

causal_testing/__init__.py

@@ -1,3 +1,13 @@
+"""
+This is the CausalTestingFramework Module
+It contains 5 subpackages:
+data_collection
+generation
+json_front
+specification
+testing
+"""
+
 import logging
 
 logger = logging.getLogger(__name__)

causal_testing/data_collection/data_collector.py

@@ -1,5 +1,9 @@
+"""This module contains the DataCollector abstract class, as well as its concrete extensions: ExperimentalDataCollector
+and ObservationalDataCollector"""
+
 import logging
 from abc import ABC, abstractmethod
+from enum import Enum
 
 import pandas as pd
 import z3
@@ -34,11 +38,15 @@ def filter_valid_data(self, data: pd.DataFrame, check_pos: bool = True) -> pd.Da
         """
 
         # Check positivity
-        scenario_variables = set(self.scenario.variables)
+        scenario_variables = set(self.scenario.variables) - {x.name for x in self.scenario.hidden_variables()}
 
-        if check_pos and not scenario_variables.issubset(data.columns):
+        if check_pos and not (scenario_variables - {x.name for x in self.scenario.hidden_variables()}).issubset(
+            set(data.columns)
+        ):
             missing_variables = scenario_variables - set(data.columns)
-            raise IndexError(f"Positivity violation: missing data for variables {missing_variables}.")
+            raise IndexError(
+                f"Missing columns: missing data for variables {missing_variables}. Should they be marked as hidden?"
+            )
 
         # For each row, does it satisfy the constraints?
         solver = z3.Solver()
@@ -53,6 +61,7 @@ def filter_valid_data(self, data: pd.DataFrame, check_pos: bool = True) -> pd.Da
                 self.scenario.variables[var].z3
                 == self.scenario.variables[var].z3_val(self.scenario.variables[var].z3, row[var])
                 for var in self.scenario.variables
+                if var in row
             ]
             for c in model:
                 solver.assert_and_track(c, f"model: {c}")
@@ -72,10 +81,7 @@ def filter_valid_data(self, data: pd.DataFrame, check_pos: bool = True) -> pd.Da
         size_diff = len(data) - len(satisfying_data)
         if size_diff > 0:
             logger.warning(
-                "Discarded %s/%s values due to constraint violations.\n" "For example%s",
-                size_diff,
-                len(data),
-                unsat_core,
+                f"Discarded {size_diff}/{len(data)} values due to constraint violations.\n For example {unsat_core}",
             )
         return satisfying_data
 
@@ -123,23 +129,27 @@ def run_system_with_input_configuration(self, input_configuration: dict) -> pd.D
 
 
 class ObservationalDataCollector(DataCollector):
-    """A data collector that extracts data that is relevant to the specified scenario from a csv of execution data."""
+    """A data collector that extracts data that is relevant to the specified scenario from a dataframe of execution
+    data."""
 
-    def __init__(self, scenario: Scenario, csv_path: str):
+    def __init__(self, scenario: Scenario, data: pd.DataFrame):
         super().__init__(scenario)
-        self.csv_path = csv_path
+        self.data = data
 
     def collect_data(self, **kwargs) -> pd.DataFrame:
-        """Read a csv containing execution data for the system-under-test into a pandas dataframe and filter to remove
+        """Read a pandas dataframe and filter to remove
         any data which is invalid for the scenario-under-test.
 
         Data is invalid if it does not meet the constraints outlined in the scenario-under-test (Scenario).
 
         :return: A pandas dataframe containing execution data that is valid for the scenario-under-test.
         """
 
-        execution_data_df = pd.read_csv(self.csv_path, **kwargs)
+        execution_data_df = self.data
         for meta in self.scenario.metas():
             meta.populate(execution_data_df)
         scenario_execution_data_df = self.filter_valid_data(execution_data_df)
+        for var_name, var in self.scenario.variables.items():
+            if issubclass(var.datatype, Enum):
+                scenario_execution_data_df[var_name] = [var.datatype(x) for x in scenario_execution_data_df[var_name]]
         return scenario_execution_data_df