Merge pull request #1 from petebachant/main

petebachant · web-flow · commit 05369f90322d · 2024-09-24T13:14:39.000-07:00
Add content
diff --git a/.dvc/.gitignore b/.dvc/.gitignore
@@ -0,0 +1,3 @@
+/config.local
+/tmp
+/cache
diff --git a/.dvc/config b/.dvc/config
@@ -0,0 +1,5 @@
+[core]
+    remote = calkit
+['remote "calkit"']
+    url = https://api.calkit.io/projects/petebachant/example-basic/dvc
+    auth = custom
diff --git a/.dvcignore b/.dvcignore
@@ -0,0 +1,3 @@
+# Add patterns of files dvc should ignore, which could improve
+# the performance. Learn more at
+# https://dvc.org/doc/user-guide/dvcignore
diff --git a/README.md b/README.md
@@ -1,2 +1,14 @@
-# example-basic
-A basic Calkit example.
+# Basic Calkit example
+
+## How this was setup
+
+1. Created a repo on GitHub.
+2. Imported into [Calkit](https://calkit.io).
+3. Ran `dvc init` and committed changes.
+4. Ran `calkit new question "Can we make reproducibility simple?" --commit`.
+5. `dvc stage add -n collect-data -o data/raw/data.csv -d scripts/collect-data.py`
+6. Ran `dvc repro`, then `git add .` and `git commit -m ...` and `dvc push`
+   to get everything up to the cloud.
+6. Added a script and DVC stage to create a figure, similar to the two steps
+   above.
+7. Added the figure to `calkit.yaml` by editing the `figures` section manually.
diff --git a/calkit.yaml b/calkit.yaml
@@ -0,0 +1,14 @@
+questions:
+  - Can we make reproducibility simple?
+datasets:
+  - path: data/raw/data.csv
+    title: Raw data
+    description: This is raw voltage data.
+figures:
+  - path: figures/voltage-time-series.png
+    title: Raw voltage time series
+    description: A plot of the raw voltage time series.
+publications:
+  - path: paper/paper.pdf
+    title: The paper
+    description: This is the paper.
diff --git a/data/raw/.gitignore b/data/raw/.gitignore
@@ -0,0 +1 @@
+/data.csv
diff --git a/dvc.lock b/dvc.lock
@@ -0,0 +1,61 @@
+schema: '2.0'
+stages:
+  collect-data:
+    cmd: python scripts/collect-data.py
+    deps:
+    - path: scripts/collect-data.py
+      hash: md5
+      md5: 570acda0f323c18ae0a336583e9d661d
+      size: 424
+    outs:
+    - path: data/raw/data.csv
+      hash: md5
+      md5: 1eec95cacd0a1ad08e06b727d8b701c2
+      size: 43618
+  plot-voltage:
+    cmd: python scripts/plot-voltage.py
+    deps:
+    - path: data/raw/data.csv
+      hash: md5
+      md5: 1eec95cacd0a1ad08e06b727d8b701c2
+      size: 43618
+    - path: scripts/plot-voltage.py
+      hash: md5
+      md5: 087a567a0c0f6199a908399013d564a1
+      size: 297
+    outs:
+    - path: figures/voltage-time-series.png
+      hash: md5
+      md5: a4fc5ebee750a839c23baee1e58bf94a
+      size: 45123
+  copy-figures-to-paper-dir:
+    cmd: cp -r figures paper/figures
+    deps:
+    - path: figures
+      hash: md5
+      md5: d6fd2418e3b774996ddd0f26715c36ac.dir
+      size: 45148
+      nfiles: 2
+    outs:
+    - path: paper/figures
+      hash: md5
+      md5: d6fd2418e3b774996ddd0f26715c36ac.dir
+      size: 45148
+      nfiles: 2
+  build-paper:
+    cmd: latexmk -pdf paper.tex
+    deps:
+    - path: ../figures
+      hash: md5
+      md5: d6fd2418e3b774996ddd0f26715c36ac.dir
+      size: 45148
+      nfiles: 2
+    - path: paper.tex
+      hash: md5
+      md5: f0c474020965d39585a2c0cc99d6cb8f
+      size: 519
+    outs:
+    - path: paper.pdf
+      hash: md5
+      md5: c736dfef6da2768017e4cb293adcaa3e
+      size: 89940
diff --git a/dvc.yaml b/dvc.yaml
@@ -0,0 +1,22 @@
+stages:
+  collect-data:
+    cmd: python scripts/collect-data.py
+    deps:
+      - scripts/collect-data.py
+    outs:
+      - data/raw/data.csv
+  plot-voltage:
+    cmd: python scripts/plot-voltage.py
+    deps:
+      - scripts/plot-voltage.py
+      - data/raw/data.csv
+    outs:
+      - figures/voltage-time-series.png
+  build-paper:
+    cmd: latexmk -pdf paper.tex
+    wdir: paper
+    deps:
+      - ../figures
+      - paper.tex
+    outs:
+      - paper.pdf
diff --git a/figures/.gitignore b/figures/.gitignore
@@ -0,0 +1 @@
+/voltage-time-series.png
diff --git a/paper/.gitignore b/paper/.gitignore
@@ -0,0 +1,6 @@
+figures
+*.aux
+*.dvi
+*.fdb_latexmk
+*.fls
+/paper.pdf
diff --git a/paper/paper.tex b/paper/paper.tex
@@ -0,0 +1,41 @@
+\documentclass[11pt]{article}
+
+\usepackage{sectsty}
+\usepackage{graphicx}
+
+% Margins
+\topmargin=-0.45in
+\evensidemargin=0in
+\oddsidemargin=0in
+\textwidth=6.5in
+\textheight=9.0in
+\headsep=0.25in
+
+\title{This is the paper}
+\author{ Author }
+\date{\today}
+
+\begin{document}
+\maketitle
+\pagebreak
+
+% Optional TOC
+% \tableofcontents
+% \pagebreak
+
+%--Paper--
+
+\section{Section 1}
+
+Lorem Impsum
+
+\includegraphics{../figures/voltage-time-series.png}
+
+
+\pagebreak
+\section{Section 2}
+Lorem Ipsum \\
+
+%--/Paper--
+
+\end{document}
diff --git a/scripts/collect-data.py b/scripts/collect-data.py
@@ -0,0 +1,17 @@
+"""This script collects data."""
+
+import os
+
+import numpy as np
+import pandas as pd
+
+if __name__ == "__main__":
+    df = pd.DataFrame(
+        data={"voltage": np.random.randn(1000)},
+        index=pd.date_range(
+            "2024-08-01", "2024-08-01 00:00:01", freq="ms", inclusive="left"
+        ),
+    )
+    df.index.name = "time"
+    os.makedirs("data/raw", exist_ok=True)
+    df.to_csv("data/raw/data.csv", index=True)
diff --git a/scripts/plot-voltage.py b/scripts/plot-voltage.py
@@ -0,0 +1,12 @@
+"""Plot our raw data."""
+
+import os
+
+import matplotlib.pyplot as plt
+import pandas as pd
+
+if __name__ == "__main__":
+    df = pd.read_csv("data/raw/data.csv").set_index("time")
+    ax = df.voltage.plot()
+    os.makedirs("figures", exist_ok=True)
+    plt.savefig("figures/voltage-time-series.png")

Original file line number	Diff line number	Diff line change
`@@ -0,0 +1,3 @@`
	`1`	`+# Add patterns of files dvc should ignore, which could improve`
	`2`	`+# the performance. Learn more at`
	`3`	`+# https://dvc.org/doc/user-guide/dvcignore`
-Original file line number
+Diff line change
@@ @@ -0,0 +1,6 @@ @@
 +figures
 +*.aux
 +*.dvi
 +*.fdb_latexmk
 +*.fls
 +/paper.pdf