dataframe-toolkit 0.12.0__tar.gz → 0.13.0__tar.gz

{dataframe_toolkit-0.12.0 → dataframe_toolkit-0.13.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: dataframe-toolkit
-Version: 0.12.0
+Version: 0.13.0
 Summary: A command-line toolkit for DataFrame analysis and manipulation
 Keywords: dataframe,statistics,data analysis,CLI,TSV,pandas
 Author: Gunnar Pálsson
@@ -416,6 +416,20 @@ dftk print <(grep -v '^#' data.tsv)          # the same, as a filename
 With `--backend duckdb`, a whole-line `#` comment below the header is an
 error, and `#` lines above the header are skipped.
 
+### Files without a header
+
+`--noheader` reads the first line as data and names the columns `V1`,
+`V2`, …. It only describes the input: the output gets a header (`V1 V2 …`)
+unless you add `--removeheader`. Name the columns with `--move`:
+
+```bash
+dftk print data.txt --noheader --move V1:chr V2:begin V3:end -o named.tsv
+dftk eval data.txt --noheader -f "len = V3 - V2" --removeheader   # no header out
+```
+
+Parquet always has column names, so `--removeheader` with `-o` and
+`--noheader` on parquet input do nothing (dftk warns).
+
 Standard output options (available on all tabular commands):
 
 - `-o` / `--output` — controls where output goes; takes an *optional* value:
@@ -427,6 +441,8 @@ Standard output options (available on all tabular commands):
 - `--drop col1 col2 …` — remove these columns
 - `--round N` — round numeric output
 - `--postquery EXPR` — filter output rows after processing
+- `--move OLD:NEW …` — rename columns
+- `--removeheader` — leave out the header row in TSV output
 - `--meta KEY=VALUE` — embed provenance metadata in parquet output (repeatable)
 
 ### Provenance annotations

{dataframe_toolkit-0.12.0 → dataframe_toolkit-0.13.0}/README.md

@@ -386,6 +386,20 @@ dftk print <(grep -v '^#' data.tsv)          # the same, as a filename
 With `--backend duckdb`, a whole-line `#` comment below the header is an
 error, and `#` lines above the header are skipped.
 
+### Files without a header
+
+`--noheader` reads the first line as data and names the columns `V1`,
+`V2`, …. It only describes the input: the output gets a header (`V1 V2 …`)
+unless you add `--removeheader`. Name the columns with `--move`:
+
+```bash
+dftk print data.txt --noheader --move V1:chr V2:begin V3:end -o named.tsv
+dftk eval data.txt --noheader -f "len = V3 - V2" --removeheader   # no header out
+```
+
+Parquet always has column names, so `--removeheader` with `-o` and
+`--noheader` on parquet input do nothing (dftk warns).
+
 Standard output options (available on all tabular commands):
 
 - `-o` / `--output` — controls where output goes; takes an *optional* value:
@@ -397,6 +411,8 @@ Standard output options (available on all tabular commands):
 - `--drop col1 col2 …` — remove these columns
 - `--round N` — round numeric output
 - `--postquery EXPR` — filter output rows after processing
+- `--move OLD:NEW …` — rename columns
+- `--removeheader` — leave out the header row in TSV output
 - `--meta KEY=VALUE` — embed provenance metadata in parquet output (repeatable)
 
 ### Provenance annotations

{dataframe_toolkit-0.12.0 → dataframe_toolkit-0.13.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "dataframe-toolkit"
-version = "0.12.0"
+version = "0.13.0"
 description = "A command-line toolkit for DataFrame analysis and manipulation"
 readme = "README.md"
 keywords = [

{dataframe_toolkit-0.12.0 → dataframe_toolkit-0.13.0}/pyproject.toml.orig

@@ -1,6 +1,6 @@
 [project]
 name = "dataframe-toolkit"
-version = "0.12.0"
+version = "0.13.0"
 description = "A command-line toolkit for DataFrame analysis and manipulation"
 readme = "README.md"
 authors = [

{dataframe_toolkit-0.12.0 → dataframe_toolkit-0.13.0}/src/dftk/commands/eval_cmd.py

@@ -44,6 +44,12 @@ methods are under .str (name.str.lower(), not name.lower() or tolower()):
 
   x = x.abs()   x = x.round(1)   x = x.clip(lower=0)   y = name.str.upper()
 
+A regular expression test gives True/False; fullmatch checks the whole value
+(match only its start). Here: exactly 7 ASCII letters, empty cells False:
+
+  dftk dataset diamonds -o \\
+      | dftk eval -f "is7 = cut.str.fullmatch('[A-Za-z]{7}')"
+
 
 FILLING MISSING VALUES (-f)
 ---------------------------

{dataframe_toolkit-0.12.0 → dataframe_toolkit-0.13.0}/src/dftk/commands/print_cmd.py

@@ -8,10 +8,13 @@ dftk pipeline:
     dftk stat -g grp -s val -o \\
       | dftk pivot -i grp -v val_mean -o \\
       | dftk print
+
+With --noheader and --move it names the columns of a headerless file:
+
+    dftk print data.txt --noheader --move V1:chr V2:begin V3:end
 """
 
 import argparse
-import sys
 
 from dftk.commands.base import BaseCommand
 from dftk.common.io import io
@@ -24,10 +27,9 @@ class PrintCommand(BaseCommand):
     help = "Convert any input (TSV or parquet pipe) to TSV on stdout"
 
     def add_arguments(self, parser: argparse.ArgumentParser) -> None:
-        # Only the read-side arguments — no -o/--output, since the whole
-        # point of this command is to force TSV to stdout.
-        io.parser_read(parser)
+        # The standard output options (--move, --select, --removeheader, …)
+        # work too; with -o FILE print writes there instead of stdout
+        self.add_io_arguments(parser)
 
     def execute(self, args: argparse.Namespace) -> None:
-        df = io.read(args)
-        df.to_csv(sys.stdout, sep="\t", index=False)
+        io.printdf(io.read(args), args)

{dataframe_toolkit-0.12.0 → dataframe_toolkit-0.13.0}/src/dftk/common/io.py

@@ -91,6 +91,13 @@ def _is_temp_pipe_path(path: str) -> bool:
 _MAX_PATH_LINE = 4096
 
 
+def _warn_noheader_parquet(args: argparse.Namespace) -> None:
+    if getattr(args, "noheader", False):
+        logging.warning(
+            "--noheader has no effect on parquet input; parquet always has column names"
+        )
+
+
 def _read_pipe_parquet(path: str) -> pd.DataFrame:
     """Read the parquet file *path* named on stdin; delete it if it's dftk's temp."""
     df = pd.read_parquet(path)
@@ -305,7 +312,11 @@ class io:
         )
         g.add_argument(
             "--noheader",
-            help="File has no header row; columns are named V1, V2, …",
+            help=(
+                "Input has no header row; columns are named V1, V2, … "
+                "(rename with --move V1:NAME).  Output still gets a header "
+                "unless --removeheader."
+            ),
             action="store_true",
         )
         g.add_argument(
@@ -418,6 +429,7 @@ class io:
             if _is_pipe_path(path):
                 rest = stream.read()
                 if not rest.strip():
+                    _warn_noheader_parquet(args)
                     return _read_pipe_parquet(path)
                 stream = _io.BytesIO(rest)
             if backend == "duckdb" and duckdb is not None:
@@ -441,6 +453,7 @@ class io:
                 raise ValueError(
                     f"'...' expects a .parquet path on stdin, got {pipe_path!r}"
                 )
+            _warn_noheader_parquet(args)
             df = _read_pipe_parquet(pipe_path)
 
         elif filename is not None and filename != "-":
@@ -453,6 +466,7 @@ class io:
                     "stdin."
                 )
             if filename.endswith(".parquet"):
+                _warn_noheader_parquet(args)
                 df = pd.read_parquet(filename)
                 df.attrs["_parquet_meta"] = _read_parquet_meta(filename)
             elif os.path.exists(filename) and not os.path.isfile(filename):
@@ -573,7 +587,8 @@ class io:
         )
         g.add_argument(
             "--removeheader",
-            help="Suppress the header row in TSV output.",
+            help="Leave out the header row in TSV output (parquet always "
+            "keeps column names).",
             action="store_true",
         )
         g.add_argument(
@@ -819,10 +834,13 @@ class io:
             except ValueError:
                 logging.warning(f"--meta: expected KEY=VALUE, got {item!r}")
 
-        # Header: suppressed if the input had no header, or --removeheader set
-        header = not getattr(args, "noheader", False)
-        if header and getattr(args, "removeheader", False):
-            header = False
+        # Header: written unless --removeheader (--noheader is about the input)
+        header = not getattr(args, "removeheader", False)
+        if not header and (output == "" or str(output).endswith(".parquet")):
+            logging.warning(
+                "--removeheader has no effect on parquet output (-o); parquet "
+                "always keeps column names"
+            )
 
         if output == "":
             # Pipe mode — write temp parquet, print path

{dataframe_toolkit-0.12.0 → dataframe_toolkit-0.13.0}/src/dftk/skills/dftk/SKILL.md

@@ -75,8 +75,9 @@ left by an interrupted pipe are removed with `dftk clean`.
 ## Options shared by every data command
 
 Input: `--prequery EXPR` (filter rows right after reading), `--noheader`
-(columns become `V1, V2, …`), `--delimiter`, `--readasobject COL…` (keep
-values like IDs as strings).
+(columns become `V1, V2, …`; the output still gets a header unless
+`--removeheader`, and `--move V1:chr …` names them), `--delimiter`,
+`--readasobject COL…` (keep values like IDs as strings).
 
 Output, applied after the command's own work: `--select COL… [+]` (choose
 and order columns; globs allowed; a trailing `+` keeps the remaining