dataframe-toolkit 0.7.1__tar.gz → 0.7.2__tar.gz

{dataframe_toolkit-0.7.1 → dataframe_toolkit-0.7.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: dataframe-toolkit
-Version: 0.7.1
+Version: 0.7.2
 Summary: A command-line toolkit for DataFrame analysis and manipulation
 Keywords: dataframe,statistics,data analysis,CLI,TSV,pandas
 Author: Gunnar Pálsson
@@ -17,6 +17,7 @@ Requires-Dist: numpy>=1.24
 Requires-Dist: pyarrow>=12.0
 Requires-Dist: scipy>=1.10
 Requires-Dist: statsmodels>=0.14
+Requires-Dist: patsy>=0.5.6
 Requires-Dist: duckdb>=0.8
 Requires-Dist: matplotlib>=3.7
 Requires-Dist: seaborn>=0.12
@@ -73,6 +74,20 @@ cd dataframe-toolkit
 uv tool install .
 ```
 
+### Skill for coding agents
+
+`skills/dftk/` is an agent skill: a short guide that coding agents such as
+Codex and Claude Code load when a task involves dftk. It covers the piping
+conventions, which command to use for what, and patterns for Snakemake and
+Make. Copy it into your agent's skills directory, for example:
+
+```bash
+cp -r skills/dftk ~/.codex/skills/     # Codex
+cp -r skills/dftk ~/.claude/skills/    # Claude Code
+```
+
+Copy it again after upgrading dftk so it matches the installed version.
+
 ## Quick example
 
 ```bash

{dataframe_toolkit-0.7.1 → dataframe_toolkit-0.7.2}/README.md

@@ -45,6 +45,20 @@ cd dataframe-toolkit
 uv tool install .
 ```
 
+### Skill for coding agents
+
+`skills/dftk/` is an agent skill: a short guide that coding agents such as
+Codex and Claude Code load when a task involves dftk. It covers the piping
+conventions, which command to use for what, and patterns for Snakemake and
+Make. Copy it into your agent's skills directory, for example:
+
+```bash
+cp -r skills/dftk ~/.codex/skills/     # Codex
+cp -r skills/dftk ~/.claude/skills/    # Claude Code
+```
+
+Copy it again after upgrading dftk so it matches the installed version.
+
 ## Quick example
 
 ```bash

{dataframe_toolkit-0.7.1 → dataframe_toolkit-0.7.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "dataframe-toolkit"
-version = "0.7.1"
+version = "0.7.2"
 description = "A command-line toolkit for DataFrame analysis and manipulation"
 readme = "README.md"
 keywords = [
@@ -26,6 +26,7 @@ dependencies = [
     "pyarrow>=12.0",
     "scipy>=1.10",
     "statsmodels>=0.14",
+    "patsy>=0.5.6",
     "duckdb>=0.8",
     "matplotlib>=3.7",
     "seaborn>=0.12",

{dataframe_toolkit-0.7.1 → dataframe_toolkit-0.7.2}/pyproject.toml.orig

@@ -1,6 +1,6 @@
 [project]
 name = "dataframe-toolkit"
-version = "0.7.1"
+version = "0.7.2"
 description = "A command-line toolkit for DataFrame analysis and manipulation"
 readme = "README.md"
 authors = [
@@ -23,6 +23,7 @@ dependencies = [
     "pyarrow>=12.0",
     "scipy>=1.10",
     "statsmodels>=0.14",
+    "patsy>=0.5.6",
     "duckdb>=0.8",
     "matplotlib>=3.7",
     "seaborn>=0.12",

{dataframe_toolkit-0.7.1 → dataframe_toolkit-0.7.2}/src/dftk/commands/concat_cmd.py

@@ -40,6 +40,8 @@ COLUMN ALIGNMENT
 ----------------
   Columns present in all files are aligned by name.
   Columns missing from some files are filled with NaN (or --fill value).
+  --fill applies only to those missing columns: a cell that is empty within
+  a file stays empty.
   Use --select to enforce a fixed output column set.
 
 EXAMPLES
@@ -79,7 +81,8 @@ Mismatched columns are outer-joined and filled (NaN by default, or --fill):
             metavar="VALUE",
             help=(
                 "Fill value for columns absent in some files "
-                "(default: NaN).  Use 0 or '' for numeric/string defaults."
+                "(default: NaN).  Use 0 or '' for numeric/string defaults.  "
+                "Cells that are empty within a file stay empty."
             ),
         )
 
@@ -152,8 +155,6 @@ Mismatched columns are outer-joined and filled (NaN by default, or --fill):
         if not dfs:
             raise ValueError("concat: no data read from any input file")
 
-        result = pd.concat(dfs, ignore_index=True)
-
         if args.fill is not None:
             fill: int | float | str
             try:
@@ -163,6 +164,14 @@ Mismatched columns are outer-joined and filled (NaN by default, or --fill):
                     fill = float(args.fill)
                 except ValueError:
                     fill = args.fill
-            result = result.fillna(fill)
+            # Add each file's missing columns before stacking, so --fill
+            # touches only those, not cells that were already empty in a file.
+            columns = list(dict.fromkeys(c for df in dfs for c in df.columns))
+            dfs = [
+                df.assign(**{c: fill for c in columns if c not in df.columns})[columns]
+                for df in dfs
+            ]
+
+        result = pd.concat(dfs, ignore_index=True)
 
         io.printdf(result, args)

{dataframe_toolkit-0.7.1 → dataframe_toolkit-0.7.2}/src/dftk/commands/fit_cmd.py

@@ -34,10 +34,12 @@ tidy coefficient tables into one output dataframe.
 import argparse
 import logging
 
+import numpy as np  # noqa: F401 — for formulas such as "np.log(y) ~ x", see below
 import pandas as pd
 import statsmodels.api as sm
 import statsmodels.formula.api as smf
 import statsmodels.stats.anova as sa
+from patsy import PatsyError
 
 from dftk.commands.base import BaseCommand
 from dftk.common.io import check_cols, io
@@ -50,6 +52,11 @@ logger = logging.getLogger(__name__)
 # ---------------------------------------------------------------------------
 
 
+# Formulas are evaluated in the namespace of the function that builds the
+# model (statsmodels' default eval_env), i.e. this module's globals — which
+# is why numpy is imported above as np.
+
+
 def standard_model(df: pd.DataFrame, args: argparse.Namespace):
     """Return an OLS or RLM (robust) model, not yet fitted."""
     if getattr(args, "robust", False):
@@ -67,11 +74,18 @@ def weighted_model(df: pd.DataFrame, args: argparse.Namespace):
 
 
 def regress_it(df: pd.DataFrame, args: argparse.Namespace):
-    """Fit the appropriate model and return the fitted result object."""
-    if getattr(args, "weights", None) is not None:
-        mod = weighted_model(df, args)
-    else:
-        mod = standard_model(df, args)
+    """Fit the appropriate model and return the fitted result object.
+
+    A formula that cannot be evaluated (unknown column or function) raises
+    ValueError, which the CLI reports as an input error.
+    """
+    try:
+        if getattr(args, "weights", None) is not None:
+            mod = weighted_model(df, args)
+        else:
+            mod = standard_model(df, args)
+    except PatsyError as exc:
+        raise ValueError(f"cannot evaluate formula {args.formula!r}: {exc}") from None
     return mod.fit()
 
 

{dataframe_toolkit-0.7.1 → dataframe_toolkit-0.7.2}/src/dftk/commands/stat_cmd.py

@@ -132,6 +132,9 @@ def _compute_stats(df: pd.DataFrame, args: argparse.Namespace) -> pd.DataFrame:
         stats = (
             df[cols].agg(agg_funcs).T.reset_index().rename(columns={"index": "name"})
         )
+        # Before the transpose each column held count and the float stats
+        # together, so count came out as float; a count is never missing.
+        stats["count"] = stats["count"].astype("int64")
         return stats[["name"] + _STAT_NAMES]
 
     else: