calkit-python 0.2.1__tar.gz → 0.3.0__tar.gz

{calkit_python-0.2.1 → calkit_python-0.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: calkit-python
-Version: 0.2.1
+Version: 0.3.0
 Summary: Reproducibility simplified.
 Project-URL: Homepage, https://github.com/calkit/calkit
 Project-URL: Issues, https://github.com/calkit/calkit/issues
@@ -10,17 +10,21 @@ Classifier: License :: OSI Approved :: MIT License
 Classifier: Operating System :: OS Independent
 Classifier: Programming Language :: Python :: 3
 Requires-Python: >=3.8
+Requires-Dist: docx2pdf
 Requires-Dist: dvc
 Requires-Dist: eval-type-backport; python_version < '3.10'
 Requires-Dist: fastapi
 Requires-Dist: gitpython
 Requires-Dist: keyring
 Requires-Dist: nbconvert
+Requires-Dist: pillow
 Requires-Dist: pydantic-settings
 Requires-Dist: pydantic[email]
 Requires-Dist: pyjwt
+Requires-Dist: pywin32; platform_system == 'Windows'
 Requires-Dist: requests
 Requires-Dist: typer
+Requires-Dist: uvicorn
 Provides-Extra: data
 Requires-Dist: pandas; extra == 'data'
 Requires-Dist: polars; extra == 'data'
@@ -31,10 +35,14 @@ Description-Content-Type: text/markdown
 [Calkit](https://calkit.io) simplifies reproducibility,
 acting as a layer on top of
 [Git](https://git-scm.com/), [DVC](https://dvc.org/),
-[Zenodo](https://zenodo.org), and more,
+[Docker](https://docker.com), and more,
 such that all all aspects of the research process can be fully described in a
 single repository.
 
+## Tutorials
+
+- [Reproducible OpenFOAM simulations](https://petebachant.me/reproducible-openfoam/)
+
 ## Why does reproducibility matter?
 
 If your work is reproducible, that means that someone else can "run" it and
@@ -55,7 +63,7 @@ community:
 
 ## Why another tool/platform?
 
-Git, GitHub, DVC, Zenodo et al. are amazing tools/platforms, but their
+Git, GitHub, DVC, Docker et al. are amazing tools/platforms, but their
 use involves multiple fairly difficult learning curves.
 Our goal is to provide a single tool and platform to unify all of these so
 that there is a single, gentle learning curve.

{calkit_python-0.2.1 → calkit_python-0.3.0}/README.md

@@ -3,10 +3,14 @@
 [Calkit](https://calkit.io) simplifies reproducibility,
 acting as a layer on top of
 [Git](https://git-scm.com/), [DVC](https://dvc.org/),
-[Zenodo](https://zenodo.org), and more,
+[Docker](https://docker.com), and more,
 such that all all aspects of the research process can be fully described in a
 single repository.
 
+## Tutorials
+
+- [Reproducible OpenFOAM simulations](https://petebachant.me/reproducible-openfoam/)
+
 ## Why does reproducibility matter?
 
 If your work is reproducible, that means that someone else can "run" it and
@@ -27,7 +31,7 @@ community:
 
 ## Why another tool/platform?
 
-Git, GitHub, DVC, Zenodo et al. are amazing tools/platforms, but their
+Git, GitHub, DVC, Docker et al. are amazing tools/platforms, but their
 use involves multiple fairly difficult learning curves.
 Our goal is to provide a single tool and platform to unify all of these so
 that there is a single, gentle learning curve.

{calkit_python-0.2.1 → calkit_python-0.3.0}/calkit/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "0.2.1"
+__version__ = "0.3.0"
 
 from .core import *
 from . import git
@@ -7,3 +7,4 @@ from . import cloud
 from . import jupyter
 from . import config
 from . import models
+from . import office

{calkit_python-0.2.1 → calkit_python-0.3.0}/calkit/cli/__init__.py

@@ -3,4 +3,5 @@ from .core import *
 
 def run() -> None:
     from .main import app
+
     app()

{calkit_python-0.2.1 → calkit_python-0.3.0}/calkit/cli/main.py

@@ -19,6 +19,7 @@ from calkit.cli.import_ import import_app
 from calkit.cli.list import list_app
 from calkit.cli.new import new_app
 from calkit.cli.notebooks import notebooks_app
+from calkit.cli.office import office_app
 
 app = typer.Typer(
     invoke_without_command=True,
@@ -36,6 +37,7 @@ app.add_typer(
 app.add_typer(notebooks_app, name="nb", help="Work with Jupyter notebooks.")
 app.add_typer(list_app, name="list", help="List Calkit objects.")
 app.add_typer(import_app, name="import", help="Import objects.")
+app.add_typer(office_app, name="office", help="Work with Microsoft Office.")
 
 
 @app.callback()
@@ -157,6 +159,9 @@ def add(
     else:
         dvc_extensions = [
             ".png",
+            ".jpeg",
+            ".jpg",
+            ".gif",
             ".h5",
             ".parquet",
             ".pickle",
@@ -164,6 +169,10 @@ def add(
             ".avi",
             ".webm",
             ".pdf",
+            ".xlsx",
+            ".docx",
+            ".xls",
+            ".doc",
         ]
         dvc_size_thresh_bytes = 1_000_000
         if "." in paths and to is None:
@@ -298,7 +307,7 @@ def run_server():
         port=8866,
         host="localhost",
         reload=True,
-        reload_dirs=[os.path.dirname(__file__)],
+        reload_dirs=[os.path.dirname(os.path.dirname(__file__))],
     )
 
 
@@ -368,7 +377,7 @@ def run_dvc_repro(
         args += ["--pipeline", pipeline]
     if downstream is not None:
         args += downstream
-    subprocess.call(["dvc", "repro"] + args)
+    subprocess.check_call(["dvc", "repro"] + args)
     # Now parse stage metadata for calkit objects
     if not os.path.isfile("dvc.yaml"):
         raise_error("No dvc.yaml file found")
@@ -575,6 +584,7 @@ def build_docker(
         _ = out[0].pop("Id")
         _ = out[0].pop("RepoDigests")
         _ = out[0].pop("Metadata")
+        _ = out[0].pop("DockerVersion")
         return out
 
     typer.echo(f"Checking for existing image with tag {tag}")

{calkit_python-0.2.1 → calkit_python-0.3.0}/calkit/cli/new.py

@@ -21,7 +21,7 @@ new_app = typer.Typer(no_args_is_help=True)
 def new_figure(
     path: str,
     title: Annotated[str, typer.Option("--title")],
-    description: Annotated[str, typer.Option("--description")] = None,
+    description: Annotated[str, typer.Option("--description")],
     stage_name: Annotated[
         str,
         typer.Option(
@@ -71,6 +71,8 @@ def new_figure(
     paths = [f.get("path") for f in figures]
     if not overwrite and path in paths:
         raise_error(f"Figure at path {path} already exists")
+    elif overwrite and path in paths:
+        figures = [fig for fig in figures if fig.get("path") != path]
     if cmd is not None and stage_name is None:
         raise_error("Stage name must be provided if command is specified")
     if (deps or outs or outs_from_stage) and not cmd:
@@ -88,7 +90,13 @@ def new_figure(
             stages = pipeline.get("stages", {})
             if outs_from_stage not in stages:
                 raise_error(f"Stage {outs_from_stage} does not exist")
-            deps += stages[outs_from_stage].get("outs", [])
+            stage = stages[outs_from_stage]
+            if "foreach" in stage:
+                for val in stage["foreach"]:
+                    for out in stage.get("do", {}).get("outs", []):
+                        deps.append(out.replace("${item}", val))
+            else:
+                deps += stage.get("outs", [])
         if path not in outs:
             outs.append(path)
         deps_cmd = []
@@ -99,6 +107,7 @@ def new_figure(
             outs_cmd += ["-o", out]
         subprocess.check_call(
             ["dvc", "stage", "add", "-n", stage_name]
+            + (["-f"] if overwrite else [])
             + deps_cmd
             + outs_cmd
             + [cmd]
@@ -112,7 +121,8 @@ def new_figure(
         repo.git.add("calkit.yaml")
         if cmd:
             repo.git.add("dvc.yaml")
-        repo.git.commit(["-m", f"Add figure {path}"])
+        if repo.git.diff("--staged"):
+            repo.git.commit(["-m", f"Add figure {path}"])
 
 
 @new_app.command("question")
@@ -354,3 +364,111 @@ def new_foreach_stage(
     repo.git.add("dvc.yaml")
     if not no_commit and repo.git.diff("--staged"):
         repo.git.commit(["-m", f"Add foreach stage {name}"])
+
+
+@new_app.command(name="dataset")
+def new_dataset(
+    path: str,
+    title: Annotated[str, typer.Option("--title")],
+    description: Annotated[str, typer.Option("--description")],
+    stage_name: Annotated[
+        str,
+        typer.Option(
+            "--stage",
+            help="Name of the pipeline stage that generates this dataset.",
+        ),
+    ] = None,
+    cmd: Annotated[
+        str,
+        typer.Option(
+            "--cmd", help="Command to add to the stage, if specified."
+        ),
+    ] = None,
+    deps: Annotated[
+        list[str], typer.Option("--dep", help="Path to stage dependency.")
+    ] = [],
+    outs: Annotated[
+        list[str],
+        typer.Option(
+            "--out",
+            help=(
+                "Path to stage output. "
+                "Dataset path will be added automatically."
+            ),
+        ),
+    ] = [],
+    outs_from_stage: Annotated[
+        str,
+        typer.Option(
+            "--deps-from-stage-outs",
+            help="Stage name from which to add outputs as dependencies.",
+        ),
+    ] = None,
+    no_commit: Annotated[bool, typer.Option("--no-commit")] = False,
+    overwrite: Annotated[
+        bool,
+        typer.Option(
+            "--overwrite",
+            "-f",
+            help="Overwrite existing dataset if one exists.",
+        ),
+    ] = False,
+):
+    """Create a new dataset."""
+    ck_info = calkit.load_calkit_info()
+    datasets = ck_info.get("datasets", [])
+    paths = [f.get("path") for f in datasets]
+    if not overwrite and path in paths:
+        raise_error(f"Dataset at path {path} already exists")
+    elif overwrite and path in paths:
+        datasets = [fig for fig in datasets if fig.get("path") != path]
+    if cmd is not None and stage_name is None:
+        raise_error("Stage name must be provided if command is specified")
+    if (deps or outs or outs_from_stage) and not cmd:
+        raise_error("Command must be provided")
+    if (deps or outs or outs_from_stage) and not stage_name:
+        raise_error("Stage name must be provided")
+    obj = dict(path=path, title=title)
+    if description is not None:
+        obj["description"] = description
+    if stage_name is not None:
+        obj["stage"] = stage_name
+    if cmd:
+        if outs_from_stage:
+            pipeline = calkit.dvc.read_pipeline()
+            stages = pipeline.get("stages", {})
+            if outs_from_stage not in stages:
+                raise_error(f"Stage {outs_from_stage} does not exist")
+            stage = stages[outs_from_stage]
+            if "foreach" in stage:
+                for val in stage["foreach"]:
+                    for out in stage.get("do", {}).get("outs", []):
+                        deps.append(out.replace("${item}", val))
+            else:
+                deps += stage.get("outs", [])
+        if path not in outs:
+            outs.append(path)
+        deps_cmd = []
+        for dep in deps:
+            deps_cmd += ["-d", dep]
+        outs_cmd = []
+        for out in outs:
+            outs_cmd += ["-o", out]
+        subprocess.check_call(
+            ["dvc", "stage", "add", "-n", stage_name]
+            + (["-f"] if overwrite else [])
+            + deps_cmd
+            + outs_cmd
+            + [cmd]
+        )
+    datasets.append(obj)
+    ck_info["datasets"] = datasets
+    with open("calkit.yaml", "w") as f:
+        ryaml.dump(ck_info, f)
+    if not no_commit:
+        repo = git.Repo()
+        repo.git.add("calkit.yaml")
+        if cmd:
+            repo.git.add("dvc.yaml")
+        if repo.git.diff("--staged"):
+            repo.git.commit(["-m", f"Add dataset {path}"])

calkit_python-0.3.0/calkit/cli/office.py

@@ -0,0 +1,50 @@
+"""CLI for working with Office."""
+
+from __future__ import annotations
+
+import platform
+
+import docx2pdf
+import typer
+from typing_extensions import Annotated
+
+import calkit
+from calkit.cli import raise_error
+
+office_app = typer.Typer(no_args_is_help=True)
+
+
+@office_app.command(
+    name="excel-chart-to-png",
+    help="Extract a chart from Excel and save to PNG.",
+)
+def excel_chart_to_png(
+    input_fpath: Annotated[str, typer.Argument(help="Input Excel file path.")],
+    output_fpath: Annotated[str, typer.Argument(help="Output PNG file path.")],
+    sheet: Annotated[
+        int, typer.Option("--sheet", help="Sheet in workbook.")
+    ] = 1,
+    chart_index: Annotated[
+        int, typer.Option("--chart-index", help="Chart index.")
+    ] = 0,
+):
+    if platform.system() != "Windows":
+        raise_error("This command is only available on Windows")
+    typer.echo(
+        f"Exporting chart at index {chart_index} from sheet {sheet} "
+        f"in {input_fpath} to {output_fpath}"
+    )
+    calkit.office.excel_chart_to_png(
+        input_fpath=input_fpath,
+        output_fpath=output_fpath,
+        sheet=sheet,
+        chart_index=chart_index,
+    )
+
+
+@office_app.command(name="word-to-pdf", help="Convert a Word document to PDF.")
+def word_to_pdf(
+    input_fpath: Annotated[str, typer.Argument(help="Input Excel file path.")],
+    output_fpath: Annotated[str, typer.Argument(help="Output PNG file path.")],
+):
+    docx2pdf.convert(input_path=input_fpath, output_path=output_fpath)

{calkit_python-0.2.1 → calkit_python-0.3.0}/calkit/config.py

@@ -7,7 +7,7 @@ from typing import Literal
 
 import keyring
 import yaml
-from pydantic import EmailStr, computed_field
+from pydantic import computed_field
 from pydantic_settings import BaseSettings, SettingsConfigDict
 
 
@@ -40,7 +40,7 @@ class Settings(BaseSettings):
         ),
         extra="ignore",
     )
-    username: EmailStr | None = None
+    username: str | None = None
     token: str | None = None
     dvc_token: str | None = None
     dataframe_engine: Literal["pandas", "polars"] = "pandas"

{calkit_python-0.2.1 → calkit_python-0.3.0}/calkit/core.py

@@ -46,8 +46,11 @@ def find_project_dirs(relative=False, max_depth=3) -> list[str]:
     return final_res
 
 
-def load_calkit_info() -> dict:
-    if os.path.isfile("calkit.yaml"):
-        with open("calkit.yaml") as f:
+def load_calkit_info(wdir=None) -> dict:
+    fpath = "calkit.yaml"
+    if wdir is not None:
+        fpath = os.path.join(wdir, fpath)
+    if os.path.isfile(fpath):
+        with open(fpath) as f:
             return ryaml.load(f)
     return {}

calkit_python-0.3.0/calkit/office.py

@@ -0,0 +1,38 @@
+"""Functionality for working with Microsoft Office."""
+
+import os
+
+from PIL import ImageGrab
+
+
+def excel_chart_to_png(
+    input_fpath: str,
+    output_fpath: str,
+    sheet: int = 1,
+    chart_index: int = 0,
+):
+    """Export a chart from an Excel sheet to PNG."""
+    import win32com.client
+
+    # Open the excel application using win32com
+    excel = win32com.client.Dispatch("Excel.Application")
+    # Disable alerts and visibility to the user
+    excel.Visible = 0
+    excel.DisplayAlerts = 0
+    # Open workbook
+    wb = excel.Workbooks.Open(os.path.abspath(input_fpath))
+    factor = 1.0
+    # Extract sheet
+    sheet = excel.Sheets(sheet)
+    shape = sheet.Shapes[chart_index]
+    shape.Copy()
+    image = ImageGrab.grabclipboard()
+    length_x, width_y = image.size
+    size = int(factor * length_x), int(factor * width_y)
+    image_resize = image.resize(size)
+    # Save the image into the existing png file, overwriting if exists
+    image_resize.save(
+        os.path.abspath(output_fpath), "png", quality=95, dpi=(300, 300)
+    )
+    wb.Close(True)
+    excel.Quit()