Merge fix-ci-tests branch into main

This merge includes fixes for:
- Python 3.9 compatibility with typing_extensions.Self
- include_counts parameter default changed to False for backward compatibility
- Parameter naming consistency (coef_lasso_shift → scale_coeff_lasso_shift)
- Doctest floating point zero representation using .replace(-0.0, 0.0)

All CI tests now pass across Python 3.9-3.11 on Ubuntu and macOS.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <[email protected]>

Author: jgallowa07

multidms/biophysical.py

@@ -354,7 +354,7 @@ def proximal_box_constraints(params, hyperparameters, *args, **kwargs):
 def proximal_objective(Dop, params, hyperparameters, scaling=1.0):
     """ADMM generalized lasso optimization."""
     (
-        coef_lasso_shift,
+        scale_coeff_lasso_shift,
         admm_niter,
         admm_tau,
         admm_mu,
@@ -368,7 +368,7 @@ def proximal_objective(Dop, params, hyperparameters, scaling=1.0):
     # see https://pyproximal.readthedocs.io/en/stable/index.html
     beta_ravel, shift_ravel = pyproximal.optimization.primal.LinearizedADMM(
         pyproximal.L2(b=beta_ravel),
-        pyproximal.L1(sigma=scaling * coef_lasso_shift),
+        pyproximal.L1(sigma=scaling * scale_coeff_lasso_shift),
         Dop,
         niter=admm_niter,
         tau=admm_tau,

multidms/data.py

@@ -100,9 +100,9 @@ class notes.
         a unique name based upon the number of data objects
         instantiated.
     include_counts : bool
-        If True (default), expects 'pre_count' and 'post_count' columns in the
-        input DataFrame and includes them in the data arrays. If False, these
-        columns are not required and count data will not be available.
+        If True, expects 'pre_count' and 'post_count' columns in the
+        input DataFrame and includes them in the data arrays. If False (default),
+        these columns are not required and count data will not be available.
 
     Example
     -------
@@ -197,7 +197,7 @@ def __init__(
         assert_site_integrity=False,
         verbose=False,
         name=None,
-        include_counts=True,
+        include_counts=False,
     ):
         """See main class docstring."""
         # Check and initialize conditions attribute

multidms/model.py

@@ -146,13 +146,13 @@ class Model:
     features included. These are automatically updated each time you
     request the property.
 
-    >>> model.get_mutations_df()  # doctest: +NORMALIZE_WHITESPACE
+    >>> model.get_mutations_df().replace(-0.0, 0.0)  # doctest: +NORMALIZE_WHITESPACE
              wts  sites muts  times_seen_a  times_seen_b  beta_a  beta_b  shift_b  \
     mutation
     M1E        M      1    E             1             3     0.0     0.0      0.0
-    M1W        M      1    W             1             0     0.0    -0.0      0.0
-    G3P        G      3    P             1             4    -0.0    -0.0     -0.0
-    G3R        G      3    R             1             2    -0.0     0.0     -0.0
+    M1W        M      1    W             1             0     0.0     0.0      0.0
+    G3P        G      3    P             1             4     0.0     0.0      0.0
+    G3R        G      3    R             1             2     0.0     0.0      0.0
     <BLANKLINE>
               predicted_func_score_a  predicted_func_score_b
     mutation
@@ -202,8 +202,8 @@ class Model:
     Next, we fit the model with some chosen hyperparameters.
 
     >>> model.fit(maxiter=10, lasso_shift=1e-5, warn_unconverged=False)
-    >>> model.loss
-    0.3483478119356665
+    >>> model.loss  # doctest: +ELLIPSIS
+    0.348347811935666...
 
     The model tunes its parameters in place, and the subsequent call to retrieve
     the loss reflects our models loss given its updated parameters.

multidms/model_collection.py

@@ -37,7 +37,7 @@
 
 
 PARAMETER_NAMES_FOR_PLOTTING = {
-    "coef_lasso_shift": "Lasso Penalty",
+    "scale_coeff_lasso_shift": "Lasso Penalty",
 }
 
 
@@ -350,7 +350,7 @@ def all_mutations(self) -> tuple:
     @lru_cache(maxsize=10)
     def split_apply_combine_muts(
         self,
-        groupby=("dataset_name", "coef_lasso_shift"),
+        groupby=("dataset_name", "scale_coeff_lasso_shift"),
         aggregate_func="mean",
         inner_merge_dataset_muts=True,
         query=None,
@@ -374,7 +374,7 @@ def split_apply_combine_muts(
         groupby : str or tuple of str or None, optional
             The attributes to group the fits by. If None, then group by all
             attributes except for the model, data, and step_loss attributes.
-            The default is ("dataset_name", "coef_lasso_shift").
+            The default is ("dataset_name", "scale_coeff_lasso_shift").
         aggregate_func : str or callable, optional
             The function to aggregate the mutational dataframes within each group.
             The default is "mean".
@@ -524,7 +524,7 @@ def add_validation_loss(self, test_data, overwrite=False):
     def get_conditional_loss_df(self, query=None):
         """
         Return a long form dataframe with columns
-        "dataset_name", "coef_lasso_shift",
+        "dataset_name", "scale_coeff_lasso_shift",
         "split" ("training" or "validation"),
         "loss" (actual value), and "condition".
 
@@ -541,7 +541,7 @@ def get_conditional_loss_df(self, query=None):
         if len(queried_fits) == 0:
             raise ValueError("invalid query, no fits returned")
 
-        id_vars = ["dataset_name", "coef_lasso_shift"]
+        id_vars = ["dataset_name", "scale_coeff_lasso_shift"]
         value_vars = [
             c for c in queried_fits.columns if "loss" in c and c != "step_loss"
         ]
@@ -559,7 +559,7 @@ def get_conditional_loss_df(self, query=None):
     def convergence_trajectory_df(
         self,
         query=None,
-        id_vars=("dataset_name", "coef_lasso_shift"),
+        id_vars=("dataset_name", "scale_coeff_lasso_shift"),
     ):
         """
         Combine the converence trajectory dataframes of
@@ -776,7 +776,7 @@ def mut_param_traceplot(
         self,
         mutations,
         mut_param="shift",
-        x="coef_lasso_shift",
+        x="scale_coeff_lasso_shift",
         width_scalar=100,
         height_scalar=100,
         **kwargs,
@@ -821,7 +821,7 @@ def mut_param_traceplot(
         muts_df = muts_df.query("mutation.isin(@mutations)")
 
         # check that we have multiple lasso penalty weights
-        if len(muts_df.coef_lasso_shift.unique()) <= 1:
+        if len(muts_df.scale_coeff_lasso_shift.unique()) <= 1:
             raise ValueError(
                 "invalid kwargs, must specify a subset of fits with "
                 "multiple lasso penalty weights"
@@ -834,7 +834,7 @@ def mut_type(mut):
         muts_df = muts_df.assign(mut_type=muts_df.mutation.apply(mut_type))
 
         # melt conditions and stats cols, beta is already "tall"
-        # id_cols = ["coef_lasso_shift", "mutation", "is_stop"]
+        # id_cols = ["scale_coeff_lasso_shift", "mutation", "is_stop"]
         id_cols = ["dataset_name", x, "mut_type", "mutation"]
         stat_cols_to_keep = [c for c in muts_df.columns if c.startswith(mut_param)]
         if mut_param == "beta":
@@ -891,7 +891,7 @@ def mut_type(mut):
 
     def shift_sparsity(
         self,
-        x="coef_lasso_shift",
+        x="scale_coeff_lasso_shift",
         width_scalar=100,
         height_scalar=100,
         return_data=False,
@@ -952,7 +952,7 @@ def mut_type(mut):
             alt.Chart(sparsity_df)
             .encode(
                 x=alt.X(
-                    "coef_lasso_shift",
+                    "scale_coeff_lasso_shift",
                     type="nominal",
                     title=(
                         PARAMETER_NAMES_FOR_PLOTTING[x]
@@ -967,7 +967,7 @@ def mut_type(mut):
                 ),
                 color=alt.Color("mut_type", type="nominal", title="Mutation type"),
                 tooltip=[
-                    "coef_lasso_shift",
+                    "scale_coeff_lasso_shift",
                     "sparsity",
                     "mut_type",
                 ],
@@ -995,7 +995,7 @@ def mut_type(mut):
 
     def mut_param_dataset_correlation(
         self,
-        x="coef_lasso_shift",
+        x="scale_coeff_lasso_shift",
         width_scalar=200,
         height=200,
         return_data=False,
@@ -1012,7 +1012,7 @@ def mut_param_dataset_correlation(
         ----------
         x : str, optional
             The parameter to plot on the x-axis.
-            The default is "coef_lasso_shift".
+            The default is "scale_coeff_lasso_shift".
         width_scalar : int, optional
             The width of the chart. The default is 150.
         height : int, optional