calkit-python 0.0.2__py3-none-any.whl → 0.0.4__py3-none-any.whl

calkit/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "0.0.2"
+__version__ = "0.0.4"
 
 from .core import *
 from . import git

calkit/cli.py

@@ -7,17 +7,20 @@ import pty
 import subprocess
 import sys
 
+import git
 import typer
 from typing_extensions import Annotated, Optional
 
-import calkit
+from calkit.core import ryaml
 
 from . import config
 from .dvc import configure_remote, set_remote_auth
 
 app = typer.Typer()
 config_app = typer.Typer()
+new_app = typer.Typer()
 app.add_typer(config_app, name="config", help="Configure Calkit.")
+app.add_typer(new_app, name="new", help="Add new Calkit object.")
 
 
 @config_app.command(name="set")
@@ -57,19 +60,26 @@ def get_status():
     """Get a unified Git and DVC status."""
 
     def print_sep(name: str):
-        print(f"------------ {name} ------------")
+        width = 66
+        txt_width = len(name) + 2
+        buffer_width = (width - txt_width) // 2
+        buffer = "-" * buffer_width
+        typer.echo(f"{buffer} {name} {buffer}")
 
-    print_sep("Code")
-    if os.name == "nt":
-        subprocess.call(["git", "status"])
-        print()
-        print_sep("data")
-        subprocess.call(["dvc", "status"])
-    else:
-        pty.spawn(["git", "status"], lambda fd: os.read(fd, 1024))
-        print()
-        print_sep("Data")
-        pty.spawn(["dvc", "status"], lambda fd: os.read(fd, 1024))
+    def run_cmd(cmd: list[str]):
+        if os.name == "nt":
+            subprocess.call(cmd)
+        else:
+            pty.spawn(cmd, lambda fd: os.read(fd, 1024))
+
+    print_sep("Code (Git)")
+    run_cmd(["git", "status"])
+    typer.echo()
+    print_sep("Data (DVC)")
+    run_cmd(["dvc", "data", "status"])
+    typer.echo()
+    print_sep("Pipeline (DVC)")
+    run_cmd(["dvc", "status"])
 
 
 @app.command(name="add")
@@ -102,7 +112,78 @@ def commit(
     raise NotImplementedError
 
 
-@app.command(name="server")
+@app.command(name="pull", help="Pull with both Git and DVC.")
+def pull():
+    typer.echo("Git pulling")
+    subprocess.call(["git", "pull"])
+    typer.echo("DVC pulling")
+    subprocess.call(["dvc", "pull"])
+
+
+@app.command(name="push", help="Push with both Git and DVC.")
+def push():
+    typer.echo("Pushing to Git remote")
+    subprocess.call(["git", "push"])
+    typer.echo("Pushing to DVC remote")
+    subprocess.call(["dvc", "push"])
+
+
+@new_app.command(name="figure")
+def new_figure(
+    path: str,
+    title: Annotated[str, typer.Option("--title")],
+    description: Annotated[str, typer.Option("--desc")] = None,
+    commit: Annotated[bool, typer.Option("--commit")] = False,
+):
+    """Add a new figure to ``calkit.yaml``."""
+    if os.path.isfile("calkit.yaml"):
+        with open("calkit.yaml") as f:
+            ck_info = ryaml.load(f)
+    else:
+        ck_info = {}
+    figures = ck_info.get("figures", [])
+    paths = [f.get("path") for f in figures]
+    if path in paths:
+        raise ValueError(f"Figure at path {path} already exists")
+    obj = dict(path=path, title=title)
+    if description is not None:
+        obj["description"] = description
+    figures.append(obj)
+    ck_info["figures"] = figures
+    with open("calkit.yaml", "w") as f:
+        ryaml.dump(ck_info, f)
+    if commit:
+        repo = git.Repo()
+        repo.git.add("calkit.yaml")
+        repo.git.commit(["-m", f"Add figure {path}"])
+
+
+@new_app.command("question")
+def new_question(
+    question: str,
+    commit: Annotated[bool, typer.Option("--commit")] = False,
+):
+    if os.path.isfile("calkit.yaml"):
+        with open("calkit.yaml") as f:
+            ck_info = ryaml.load(f)
+    else:
+        ck_info = {}
+    questions = ck_info.get("questions", [])
+    if question in questions:
+        raise ValueError("Question already exists")
+    if not question.endswith("?"):
+        raise ValueError("Questions must end with a question mark")
+    questions.append(question)
+    ck_info["questions"] = questions
+    with open("calkit.yaml", "w") as f:
+        ryaml.dump(ck_info, f)
+    if commit:
+        repo = git.Repo()
+        repo.git.add("calkit.yaml")
+        repo.git.commit(["-m", "Add question"])
+
+
+@app.command(name="server", help="Run the local server.")
 def run_server():
     import uvicorn
 
@@ -115,5 +196,72 @@ def run_server():
     )
 
 
+@app.command(
+    name="run",
+    add_help_option=False,
+    help="Run DVC pipeline (a wrapper for `dvc repro`).",
+)
+def run_dvc_repro(
+    targets: Optional[list[str]] = typer.Argument(default=None),
+    help: Annotated[bool, typer.Option("-h", "--help")] = False,
+    quiet: Annotated[bool, typer.Option("-q", "--quiet")] = False,
+    verbose: Annotated[bool, typer.Option("-v", "--verbose")] = False,
+    force: Annotated[bool, typer.Option("-f", "--force")] = False,
+    interactive: Annotated[bool, typer.Option("-i", "--interactive")] = False,
+    single_item: Annotated[bool, typer.Option("-s", "--single-item")] = False,
+    pipeline: Annotated[
+        Optional[str], typer.Option("-p", "--pipeline")
+    ] = None,
+    all_pipelines: Annotated[
+        bool, typer.Option("-P", "--all-pipelines")
+    ] = False,
+    recursive: Annotated[bool, typer.Option("-R", "--recursive")] = False,
+    downstream: Annotated[
+        Optional[list[str]], typer.Option("--downstream")
+    ] = None,
+    force_downstream: Annotated[
+        bool, typer.Option("--force-downstream")
+    ] = False,
+    pull: Annotated[bool, typer.Option("--pull")] = False,
+    allow_missing: Annotated[bool, typer.Option("--allow-missing")] = False,
+    dry: Annotated[bool, typer.Option("--dry")] = False,
+    keep_going: Annotated[bool, typer.Option("--keep-going", "-k")] = False,
+    ignore_errors: Annotated[bool, typer.Option("--ignore-errors")] = False,
+    glob: Annotated[bool, typer.Option("--glob")] = False,
+    no_commit: Annotated[bool, typer.Option("--no-commit")] = False,
+    no_run_cache: Annotated[bool, typer.Option("--no-run-cache")] = False,
+):
+    """A simple wrapper for ``dvc repro``."""
+    if targets is None:
+        targets = []
+    args = targets
+    # Extract any boolean args
+    for name in [
+        "help",
+        "quiet",
+        "verbose",
+        "force",
+        "interactive",
+        "single-item",
+        "all-pipelines",
+        "recursive",
+        "pull",
+        "allow-missing",
+        "dry",
+        "keep-going",
+        "force-downstream",
+        "glob",
+        "no-commit",
+        "no-run-cache",
+    ]:
+        if locals()[name.replace("-", "_")]:
+            args.append("--" + name)
+    if pipeline is not None:
+        args += ["--pipeline", pipeline]
+    if downstream is not None:
+        args += downstream
+    subprocess.call(["dvc", "repro"] + args)
+
+
 def run() -> None:
     app()

calkit/core.py

@@ -3,11 +3,21 @@
 from __future__ import annotations
 
 import glob
+import logging
 import os
 
+import ruamel.yaml
 from git import Repo
 from git.exc import InvalidGitRepositoryError
 
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__package__)
+
+ryaml = ruamel.yaml.YAML()
+ryaml.indent(mapping=2, sequence=4, offset=2)
+ryaml.preserve_quotes = True
+ryaml.width = 70
+
 
 def find_project_dirs(relative=False, max_depth=3) -> list[str]:
     """Find all Calkit project directories."""

calkit/data.py

@@ -1,4 +1,9 @@
-"""Functionality for working with datasets."""
+"""Functionality for working with datasets.
+
+Since the dependencies here are optional, we need to ensure this isn't imported
+by default, or otherwise ensure ``import calkit`` works when the data
+dependencies are not installed.
+"""
 
 from __future__ import annotations
 

calkit/models.py

@@ -0,0 +1,81 @@
+"""Data models."""
+
+from typing import Literal
+
+from pydantic import BaseModel
+
+
+class _ImportedFrom(BaseModel):
+    project: str
+    path: str = None
+
+
+class _CalkitObject(BaseModel):
+    path: str
+    title: str
+    description: str
+    stage: str | None = None
+
+
+class Dataset(_CalkitObject):
+    pass
+
+
+class Figure(_CalkitObject):
+    pass
+
+
+class Publication(_CalkitObject):
+    kind: Literal[
+        "journal-article",
+        "conference-paper",
+        "presentation",
+        "poster",
+        "report",
+        "blog",
+    ]
+    is_published: bool = False
+    doi: str = None
+
+
+class ReferenceFile(BaseModel):
+    path: str
+    key: str
+
+
+class ReferenceCollection(BaseModel):
+    path: str
+    files: list[ReferenceFile] = []
+
+
+class Environment(BaseModel):
+    name: str
+    kind: Literal["conda", "docker", "pip", "poetry", "npm", "yarn"]
+    path: str
+
+
+class Software(BaseModel):
+    title: str
+    path: str
+    description: str
+
+
+class Notebook(_CalkitObject):
+    """A Jupyter notebook."""
+
+    pass
+
+
+class ProjectInfo(BaseModel):
+    """All of the project's information or metadata, written to the
+    ``calkit.yaml`` file.
+    """
+
+    questions: list[str] = []
+    datasets: list[Dataset] = []
+    figures: list[Figure] = []
+    publications: list[Publication] = []
+    references: list[ReferenceCollection] = []
+    environments: list[Environment] = []
+    software: list[Software] = []
+    notebooks: list[Notebook] = []

{calkit_python-0.0.2.dist-info → calkit_python-0.0.4.dist-info}/METADATA

@@ -1,7 +1,7 @@
 Metadata-Version: 2.3
 Name: calkit-python
-Version: 0.0.2
-Summary: Reproducibility made easy.
+Version: 0.0.4
+Summary: Reproducibility simplified.
 Project-URL: Homepage, https://github.com/calkit/calkit
 Project-URL: Issues, https://github.com/calkit/calkit/issues
 Author-email: Pete Bachant <petebachant@gmail.com>
@@ -15,23 +15,56 @@ Requires-Dist: eval-type-backport; python_version < '3.10'
 Requires-Dist: fastapi
 Requires-Dist: gitpython
 Requires-Dist: keyring
-Requires-Dist: pandas
-Requires-Dist: polars
+Requires-Dist: nbconvert
 Requires-Dist: pydantic-settings
 Requires-Dist: pydantic[email]
 Requires-Dist: pyjwt
 Requires-Dist: requests
 Requires-Dist: typer
+Provides-Extra: data
+Requires-Dist: pandas; extra == 'data'
+Requires-Dist: polars; extra == 'data'
 Description-Content-Type: text/markdown
 
 # Calkit
 
-[Calkit](https://calkit.io) makes reproducible research easy,
+[Calkit](https://calkit.io) simplifies reproducibility,
 acting as a layer on top of
-[Git](https://git-scm.com/) and [DVC](https://dvc.org/), such that all
-all materials involved in the research process can be fully described in a
+[Git](https://git-scm.com/), [DVC](https://dvc.org/),
+[Zenodo](https://zenodo.org), and more,
+such that all all aspects of the research process can be fully described in a
 single repository.
 
+## Why does reproducibility matter?
+
+If your work is reproducible, that means that someone else can "run" it and
+get the same results or outputs.
+This is a major step towards addressing
+[the replication crisis](https://en.wikipedia.org/wiki/Replication_crisis)
+and has some major benefits for both you as an individual and the research
+community:
+
+1. You will avoid mistakes caused by, e.g., running an old version of a script
+   and including a figure that wasn't created after fixing a bug in the data
+   processing pipeline.
+2. Since your project is "runnable," it's more likely that someone else will be
+   able to reuse part of your work to run it in a different context, thereby
+   producing a bigger impact and accelerating the pace of discovery.
+   If someone can take what you've done and use it to calculate a
+   prediction, you have just produced truly useful knowledge.
+
+## Why another tool/platform?
+
+Git, GitHub, DVC, Zenodo 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.
+However, it is not our goal to hide or replace these underlying components.
+Advanced users can use them directly, but new users aren't forced to, which
+helps them get up and running with less effort and training.
+Calkit should help users understand what is going on under the hood without
+forcing them to work at that lower level of abstraction.
+
 ## Installation
 
 Simply run

{calkit_python-0.0.2.dist-info → calkit_python-0.0.4.dist-info}/RECORD

@@ -1,19 +1,20 @@
-calkit/__init__.py,sha256=5ZyOW3PHimYwnmImfuA_Yqh2Vh1daNTXojMUlAPXeog,142
-calkit/cli.py,sha256=biHONCwIlYFp8Gcj8kl_XPafD0F8jnKQ6m_LUyk07VA,3029
+calkit/__init__.py,sha256=ZhTSlSvcKFHVv921t4q9zBBPNWHaT4h43s3G26KldNo,142
+calkit/cli.py,sha256=FkZGfQNSjWKRjWDX10GMDTh3NM9E7cW9DJch2h_F75Q,7930
 calkit/cloud.py,sha256=CnQKms4mBQo4X8jVLIa-70-3jPDl38zRNFyK5TjiaHM,2209
 calkit/config.py,sha256=NPFRk5inn66Wy44pyx8WppyqvIzkW1sO6VjXwIcCacE,2044
-calkit/core.py,sha256=fB5HAGJg9yDqJESFisFyKImvMB8wO2CpurGg6hfr7qE,990
-calkit/data.py,sha256=DqgrvRj9eI8eidmHZFC-UYHmWc-xmBb_GFYDJP1R0DI,1447
+calkit/core.py,sha256=qLNjBwlECzMitL85pMGIHzne4j7FpQAR9-ukYtdIMig,1225
+calkit/data.py,sha256=DZDkj-BLFWXz56R-A9XZeSKSgXpm3aKtiqD6JstfmnY,1631
 calkit/dvc.py,sha256=tX5172Ahw0mHcuJIrMenz1oGYxCrMzMURJJMHEHenbg,1506
 calkit/git.py,sha256=NLd7A32dPbfVnZLa8xbmviJ-ChGZcdkcd6wcOOnsSKQ,350
 calkit/gui.py,sha256=2UCrMyosc5v4CLlDcHO7oDwW9eLn5_WbNaLaG5bjMTc,23
 calkit/jupyter.py,sha256=S6HUOVafaLQJ7_ZfC1ddBwF3fT5q3GcbouLHdlH-oSo,1034
+calkit/models.py,sha256=ejl032XIrbaCFkO-4VbCaKVQyHqNl7N4WWU20RjeAfc,1447
 calkit/server.py,sha256=gq3643ABKTQu1eVR_OqJ-SdQh2dPLHSFsipmmAK5ttA,5959
 calkit/tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 calkit/tests/test_core.py,sha256=CdRqvYnq3MidyTknvfIbkmmhMfydpyKtTW9hakAvzsc,167
 calkit/tests/test_jupyter.py,sha256=YTL6zI740UM2KUjskSipzvSKxsyQ8rVPFQIX5cb2tMQ,114
-calkit_python-0.0.2.dist-info/METADATA,sha256=QaKWH12fJ1QZ04UT7bgBC8VOW5oVYzsuDk8l8uKgUKs,2393
-calkit_python-0.0.2.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-calkit_python-0.0.2.dist-info/entry_points.txt,sha256=tiPfbDDZNB-YStw5YVO_4Gww0W3Dcdy8Mh6muX_GWnY,42
-calkit_python-0.0.2.dist-info/licenses/LICENSE,sha256=9ZamCaSUTZk9rcrnf-sWFKLOHr3ws-S_dgKMegW4nw8,1056
-calkit_python-0.0.2.dist-info/RECORD,,
+calkit_python-0.0.4.dist-info/METADATA,sha256=yAlvKleBuX6xFXFH3u7UHZVJILjlC-RIOSeQEXcNx8A,4004
+calkit_python-0.0.4.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+calkit_python-0.0.4.dist-info/entry_points.txt,sha256=tiPfbDDZNB-YStw5YVO_4Gww0W3Dcdy8Mh6muX_GWnY,42
+calkit_python-0.0.4.dist-info/licenses/LICENSE,sha256=9ZamCaSUTZk9rcrnf-sWFKLOHr3ws-S_dgKMegW4nw8,1056
+calkit_python-0.0.4.dist-info/RECORD,,