dataframe-toolkit 0.4.1__tar.gz → 0.5.0__tar.gz

{dataframe_toolkit-0.4.1 → dataframe_toolkit-0.5.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: dataframe-toolkit
-Version: 0.4.1
+Version: 0.5.0
 Summary: A command-line toolkit for DataFrame analysis and manipulation
 Keywords: dataframe,statistics,data analysis,CLI,TSV,pandas
 Author: Gunnar Pálsson

{dataframe_toolkit-0.4.1 → dataframe_toolkit-0.5.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "dataframe-toolkit"
-version = "0.4.1"
+version = "0.5.0"
 description = "A command-line toolkit for DataFrame analysis and manipulation"
 readme = "README.md"
 authors = [

{dataframe_toolkit-0.4.1 → dataframe_toolkit-0.5.0}/src/dftk/commands/__init__.py

@@ -18,6 +18,7 @@ from dftk.commands.fit_cmd import FitCommand
 from dftk.commands.func_cmd import FuncCommand
 from dftk.commands.help import HelpCommand
 from dftk.commands.hist_cmd import HistCommand
+from dftk.commands.info_cmd import InfoCommand
 from dftk.commands.interp_cmd import InterpCommand
 from dftk.commands.line_cmd import LineCommand
 from dftk.commands.melt_cmd import MeltCommand
@@ -29,15 +30,14 @@ from dftk.commands.randvar_cmd import RandvarCommand
 from dftk.commands.sample_cmd import SampleCommand
 from dftk.commands.scale_cmd import ScaleCommand
 from dftk.commands.scat_cmd import ScatCommand
+from dftk.commands.segid_cmd import SegidCommand
 from dftk.commands.split_cmd import SplitCommand
 from dftk.commands.stat_cmd import StatCommand
 from dftk.commands.test_cmd import TestCommand
+from dftk.commands.transpose_cmd import TransposeCommand
 from dftk.commands.wstat_cmd import WstatCommand
 
 # Ported subcommands — uncomment as each one is added:
-# from dftk.commands.segid     import SegidCommand
-# from dftk.commands.info      import InfoCommand
-# from dftk.commands.transpose import TransposeCommand
 # from dftk.commands.color     import ColorCommand
 # from dftk.commands.wavelet   import WaveletCommand
 # from dftk.commands.fisher    import FisherCommand  # superseded by eval's
@@ -57,6 +57,8 @@ COMMAND_GROUPS: list[tuple[str, list]] = [
             ScaleCommand(),
             InterpCommand(),
             BinxCommand(),
+            TransposeCommand(),
+            SegidCommand(),
         ],
     ),
     (
@@ -68,6 +70,7 @@ COMMAND_GROUPS: list[tuple[str, list]] = [
             TestCommand(),
             CorrCommand(),
             DescribeCommand(),
+            InfoCommand(),
             RandvarCommand(),
         ],
     ),

dataframe_toolkit-0.5.0/src/dftk/commands/info_cmd.py

@@ -0,0 +1,74 @@
+"""
+dftk.commands.info_cmd — dftk info subcommand.
+
+Lightweight structural overview of a DataFrame: per-column dtype, null
+counts, and memory usage. Complements `describe`, which profiles
+statistical distributions and quality flags instead.
+
+Example
+-------
+    dftk info data.tsv
+    dftk info data.tsv --summary
+"""
+
+import argparse
+import sys
+
+import pandas as pd
+
+from dftk.commands.base import BaseCommand
+from dftk.common.io import io
+
+
+def _info(df: pd.DataFrame) -> pd.DataFrame:
+    mem = df.memory_usage(deep=True, index=False)
+    return pd.DataFrame(
+        [
+            dict(
+                name=col,
+                dtype=str(df[col].dtype),
+                non_null=int(df[col].notna().sum()),
+                null=int(df[col].isna().sum()),
+                memory_bytes=int(mem[col]),
+            )
+            for col in df.columns
+        ]
+    )
+
+
+def _summary_line(df: pd.DataFrame) -> str:
+    n_rows, n_cols = df.shape
+    total_mem = int(df.memory_usage(deep=True).sum())
+    n_dupes = int(df.duplicated().sum())
+    return (
+        f"Dataset: {n_rows} rows x {n_cols} columns, "
+        f"{total_mem} bytes, {n_dupes} duplicated row(s)"
+    )
+
+
+class InfoCommand(BaseCommand):
+    @property
+    def name(self) -> str:
+        return "info"
+
+    @property
+    def help(self) -> str:
+        return "Structural overview: per-column dtype, null counts, memory usage"
+
+    def add_arguments(self, parser: argparse.ArgumentParser) -> None:
+        self.add_io_arguments(parser)
+
+        g = parser.add_argument_group("info options")
+        g.add_argument(
+            "--summary",
+            action="store_true",
+            help="Print dataset totals (shape, memory, duplicate rows) to stderr.",
+        )
+
+    def execute(self, args: argparse.Namespace) -> None:
+        df = io.read(args)
+
+        if getattr(args, "summary", False):
+            print(_summary_line(df), file=sys.stderr)
+
+        io.printdf(_info(df), args)

dataframe_toolkit-0.5.0/src/dftk/commands/segid_cmd.py

@@ -0,0 +1,118 @@
+"""
+dftk.commands.segid_cmd — dftk segid subcommand.
+
+Port of dfsegid.py: assign a segment ID that increments each time the
+value in a column changes, useful for grouping contiguous runs of
+identical values (e.g. constant-value stretches in a sorted column).
+
+Rows matching --ignore are excluded from the run comparison and always get
+segid 0; they don't break a run spanning across them. Redesigned from the
+legacy script's magic sentinel default ('1415926535', digits of pi) to a
+plain optional flag — omit --ignore to include every row.
+"""
+
+import argparse
+
+import pandas as pd
+
+from dftk.commands.base import BaseCommand
+from dftk.common.io import check_cols, io
+
+_EPILOG = """\
+EXAMPLE
+-------
+  col
+  A
+  A
+  B
+  B
+  A
+
+  dftk segid data.tsv -c col
+
+  col  segid
+  A    1
+  A    1
+  B    2
+  B    2
+  A    3
+
+With --ignore X, rows where col == X get segid 0 and are skipped when
+detecting value changes, so a run continues across them:
+
+  col
+  A
+  X
+  A
+  B
+
+  dftk segid data.tsv -c col --ignore X
+
+  col  segid
+  A    1
+  X    0
+  A    1
+  B    2
+"""
+
+
+def _segid(df: pd.DataFrame, args: argparse.Namespace) -> pd.DataFrame:
+    col = args.col
+    dest = args.destcol
+
+    df[dest] = 0
+
+    if args.ignore is not None:
+        ignore_value = pd.Series([args.ignore]).astype(df[col].dtype).iloc[0]
+        mask = df[col] != ignore_value
+    else:
+        mask = pd.Series(True, index=df.index)
+
+    subseries = df.loc[mask, col]
+    df.loc[mask, dest] = subseries.ne(subseries.shift()).cumsum()
+    return df
+
+
+class SegidCommand(BaseCommand):
+    @property
+    def name(self) -> str:
+        return "segid"
+
+    @property
+    def help(self) -> str:
+        return "Assign a segment ID that increments on each value change"
+
+    def add_arguments(self, parser: argparse.ArgumentParser) -> None:
+        parser.formatter_class = argparse.RawDescriptionHelpFormatter
+        parser.epilog = _EPILOG
+
+        self.add_io_arguments(parser)
+
+        g = parser.add_argument_group("segid options")
+        g.add_argument(
+            "-c",
+            "--col",
+            required=True,
+            metavar="COL",
+            help="Column whose value changes define segment boundaries.",
+        )
+        g.add_argument(
+            "-d",
+            "--destcol",
+            default="segid",
+            metavar="DESTCOL",
+            help="Name of the output segment-ID column (default: segid).",
+        )
+        g.add_argument(
+            "--ignore",
+            default=None,
+            metavar="VALUE",
+            help="Column value to exclude from segmenting (gets segid 0, "
+            "doesn't break a run spanning across it). Default: none.",
+        )
+
+    def execute(self, args: argparse.Namespace) -> None:
+        df = io.read(args)
+        check_cols(df, [args.col], "-c/--col")
+        result = _segid(df, args)
+        io.printdf(result, args)

dataframe_toolkit-0.5.0/src/dftk/commands/transpose_cmd.py

@@ -0,0 +1,57 @@
+"""
+dftk.commands.transpose_cmd — dftk transpose subcommand.
+
+Port of dftpos.py: flips rows and columns. Original column names become
+values in a new key column (default name: "column"); original row
+positions become the new column headers.
+
+Example
+-------
+Input:
+
+  sample  x  y
+  s1      1  2
+  s2      3  4
+
+  dftk transpose data.tsv
+
+Output:
+
+  column  0  1
+  sample  s1 s2
+  x       1  3
+  y       2  4
+"""
+
+import argparse
+
+from dftk.commands.base import BaseCommand
+from dftk.common.io import io
+
+
+class TransposeCommand(BaseCommand):
+    @property
+    def name(self) -> str:
+        return "transpose"
+
+    @property
+    def help(self) -> str:
+        return "Transpose rows and columns"
+
+    def add_arguments(self, parser: argparse.ArgumentParser) -> None:
+        self.add_io_arguments(parser)
+
+        g = parser.add_argument_group("transpose options")
+        g.add_argument(
+            "--keycol",
+            default="column",
+            metavar="NAME",
+            help="Name for the new column holding the original column names "
+            "(default: column).",
+        )
+
+    def execute(self, args: argparse.Namespace) -> None:
+        df = io.read(args)
+        result = df.transpose().reset_index(names=args.keycol)
+        result.columns = [str(c) for c in result.columns]
+        io.printdf(result, args)