change data validation mixins to class methods

Author: drbenvincent

causalpy/data_validation.py

@@ -23,14 +23,14 @@
 from patsy import dmatrices
 from sklearn.linear_model import LinearRegression as sk_lin_reg
 
-from causalpy.data_validation import PropensityDataValidator
+from causalpy.custom_exceptions import DataException
 from causalpy.experiments import ExperimentalDesign
 
 # from causalpy.pymc_models import PyMCModel
 # from causalpy.utils import round_num
 
 
-class InversePropensityWeighting(ExperimentalDesign, PropensityDataValidator):
+class InversePropensityWeighting(ExperimentalDesign):
     """
     A class to analyse inverse propensity weighting experiments.
 
@@ -97,6 +97,28 @@ def __init__(
         self.coords = COORDS
         self.model.fit(X=self.X, t=self.t, coords=COORDS)
 
+    def _input_validation(self):
+        """Validate the input data and model formula for correctness"""
+        treatment = self.formula.split("~")[0]
+        test = treatment.strip() in self.data.columns
+        test = test & (self.outcome_variable in self.data.columns)
+        if not test:
+            raise DataException(
+                f"""
+                The treatment variable:
+                {treatment} must appear in the data to be used
+                as an outcome variable. And {self.outcome_variable}
+                must also be available in the data to be re-weighted
+                """
+            )
+        T = self.data[treatment.strip()]
+        check_binary = len(np.unique(T)) > 2
+        if check_binary:
+            raise DataException(
+                """Warning. The treatment variable is not 0-1 Binary.
+                """
+            )
+
     def make_robust_adjustments(self, ps):
         """This estimator is discussed in Aronow
         and Miller's book as being related to the

causalpy/exp_inverse_propensity_weighting.py

@@ -19,14 +19,17 @@
 import pandas as pd
 from patsy import build_design_matrices, dmatrices
 
-from causalpy.data_validation import DiDDataValidator
+from causalpy.custom_exceptions import (
+    DataException,
+    FormulaException,
+)
 from causalpy.experiments import ExperimentalDesign
 from causalpy.pymc_models import PyMCModel
 from causalpy.skl_models import ScikitLearnModel
-from causalpy.utils import convert_to_string
+from causalpy.utils import _is_variable_dummy_coded, convert_to_string
 
 
-class DifferenceInDifferences(ExperimentalDesign, DiDDataValidator):
+class DifferenceInDifferences(ExperimentalDesign):
     """A class to analyse data from Difference in Difference settings.
 
     .. note::
@@ -174,6 +177,29 @@ def __init__(
         else:
             raise ValueError("Model type not recognized")
 
+    def _input_validation(self):
+        """Validate the input data and model formula for correctness"""
+        if "post_treatment" not in self.formula:
+            raise FormulaException(
+                "A predictor called `post_treatment` should be in the formula"
+            )
+
+        if "post_treatment" not in self.data.columns:
+            raise DataException(
+                "Require a boolean column labelling observations which are `treated`"
+            )
+
+        if "unit" not in self.data.columns:
+            raise DataException(
+                "Require a `unit` column to label unique units. This is used for plotting purposes"  # noqa: E501
+            )
+
+        if _is_variable_dummy_coded(self.data[self.group_variable_name]) is False:
+            raise DataException(
+                f"""The grouping variable {self.group_variable_name} should be dummy
+                coded. Consisting of 0's and 1's only."""
+            )
+
     def plot(self, round_to=None):
         """
         Plot the results

causalpy/expt_diff_in_diff.py

@@ -15,19 +15,21 @@
 Instrumental variable regression
 """
 
+import warnings  # noqa: I001
+
 import numpy as np
 import pandas as pd
 from patsy import dmatrices
 from sklearn.linear_model import LinearRegression as sk_lin_reg
 
-from causalpy.data_validation import IVDataValidator
+from causalpy.custom_exceptions import DataException
 from causalpy.experiments import ExperimentalDesign
 
 # from causalpy.pymc_models import PyMCModel
 # from causalpy.utils import round_num
 
 
-class InstrumentalVariable(ExperimentalDesign, IVDataValidator):
+class InstrumentalVariable(ExperimentalDesign):
     """
     A class to analyse instrumental variable style experiments.
 
@@ -140,6 +142,29 @@ def __init__(
             X=self.X, Z=self.Z, y=self.y, t=self.t, coords=COORDS, priors=self.priors
         )
 
+    def _input_validation(self):
+        """Validate the input data and model formula for correctness"""
+        treatment = self.instruments_formula.split("~")[0]
+        test = treatment.strip() in self.instruments_data.columns
+        test = test & (treatment.strip() in self.data.columns)
+        if not test:
+            raise DataException(
+                f"""
+                The treatment variable:
+                {treatment} must appear in the instrument_data to be used
+                as an outcome variable and in the data object to be used as a covariate.
+                """
+            )
+        Z = self.data[treatment.strip()]
+        check_binary = len(np.unique(Z)) > 2
+        if check_binary:
+            warnings.warn(
+                """Warning. The treatment variable is not Binary.
+                This is not necessarily a problem but it violates
+                the assumption of a simple IV experiment.
+                The coefficients should be interpreted appropriately."""
+            )
+
     def get_2SLS_fit(self):
         """
         Two Stage Least Squares Fit

causalpy/expt_instrumental_variable.py

@@ -21,13 +21,13 @@
 import pandas as pd
 from patsy import build_design_matrices, dmatrices
 
-from causalpy.data_validation import PrePostFitDataValidator
+from causalpy.custom_exceptions import BadIndexException
 from causalpy.experiments import ExperimentalDesign
 from causalpy.pymc_models import PyMCModel
 from causalpy.skl_models import ScikitLearnModel
 
 
-class PrePostFit(ExperimentalDesign, PrePostFitDataValidator):
+class PrePostFit(ExperimentalDesign):
     """
     A base class for quasi-experimental designs where parameter estimation is based on
     just pre-intervention data. This class is not directly invoked by the user.
@@ -91,6 +91,21 @@ def __init__(
             self.post_impact
         )
 
+    def _input_validation(self, data, treatment_time):
+        """Validate the input data and model formula for correctness"""
+        if isinstance(data.index, pd.DatetimeIndex) and not isinstance(
+            treatment_time, pd.Timestamp
+        ):
+            raise BadIndexException(
+                "If data.index is DatetimeIndex, treatment_time must be pd.Timestamp."
+            )
+        if not isinstance(data.index, pd.DatetimeIndex) and isinstance(
+            treatment_time, pd.Timestamp
+        ):
+            raise BadIndexException(
+                "If data.index is not DatetimeIndex, treatment_time must be pd.Timestamp."  # noqa: E501
+            )
+
     def plot(self):
         """
         Plot the results