スピントロニクスや量子生物学に関係のある面白そうな総説をみつけました。

ツイートをみていたら、量子生物学に関係がある総説がでていたのでリンクを紹介しておきます。オープンアクセスなので誰でも無料でダウンロードできます。
バイオセンサーの開発にも重要なThe chiral(ity)-induced spin selectivity (CISS) effectについての総説です。キラリティの解説からはじまって、生命現象についての考察もされているので興味のある方はどうぞ。弱い磁場によるカエルの卵の発生への影響のプレプリントも参考文献にはいっています。磁場のXenopus laevis (アフリカツメガエル)卵の発生への影響については、日本のリニア新幹線の開発計画の初期段階で調査されていて影響がないとの結論がでていたと聞いたことがあるので、ものすごい弱い磁場の影響があるのかどうかプレプリントを読んでみようと思いました。

Chem. Phys. Rev. 6, 031306 (2025)
Review Article| September 02 2025
https://doi.org/10.1063/5.0244306
Mind the gap: From resolving theoretical foundations of chiral(ity)-induced spin selectivity to pioneering implementations in quantum sensing
Special Collection: Molecular Approaches for Spin-based Technologies
Yan Xi Foo, Aisha Kermiche, Farhan T. Chowdhury, Clarice D. Aiello, and Luke D. Smith

NHKの面白い番組を二つ紹介します。

この前紹介していた夜ドラ『いつか無重力の宙で』が昨夜からはじまりましたね。金曜日に一週間分まとめて再放送されるのでそちらをみるのもよさそうです。

NHKはよいドラマを放送しますね。録画しただけでまだみていませんが、算額について研究しているドイツの方の番組もありました。
https://www.nhk.jp/p/ts/PG7NRXY592/episode/te/GX26NN28J5/
神戸大学の中澤 港先生のツイートをご覧ください。先生のツイートによると、算額の問題をコンピュータで解いているサイトもあるそうです。私も何枚か算額をみたことがありますが、どれも面白そうなサイトです。

湯川秀樹さんが激賞していた日本の思想家 三浦梅園についてのサイトを紹介します。

江戸時代の日本の思想家、哲学者に三浦梅園という人がいます。
私が高校生のころ湯川秀樹さんがテレビや本で、三浦梅園はすごいということをおっしゃっていたので興味はありましたが今まで一度も読んだことはありませんでした。今日は、三浦梅園についてのサイトで面白そうなのをいくつかまとめてみます。

松岡正剛さんのこちらの記事は最初の入門記事として読みやすいと思います。
『松岡正剛の千夜千冊』というサイトの、第993夜です。
三浦梅園の「玄語」というタイトルです。
https://eel-1000ya.sakura.ne.jp/0993.html

この記事に紹介されている『三枝博音著作集』第5巻 (三浦梅園・日本文化論),中央公論社,1972.は国会図書館のデジタルコレクションで読めます。
この著作集はおそらく全巻が個人送信資料で公開されており、日本の哲学、科学の歴史について学ぶのに役立つ著作集だと思います。

『三枝博音著作集』第5巻 (三浦梅園・日本文化論),中央公論社,1972. 国立国会図書館デジタルコレクション https://dl.ndl.go.jp/pid/12283006 (参照 2025-09-08)

著作集の内容については
『三枝博音著作集』別巻 (総索引),中央公論社,1977.7. 国立国会図書館デジタルコレクション https://dl.ndl.go.jp/pid/12285435 (参照 2025-09-08)
で知ることができます。西田哲学とかの解説もあるのでよさそうです。
三枝博音の三浦梅園についての解説記事は、このブログで何度もとりあげている科学図書館
http://www.cam.hi-ho.ne.jp/munehiro/science/scilib.html
にもあります。三浦梅園の著作もデジタル化されている(漢文ですが)ので参考にしてください。
http://www.cam.hi-ho.ne.jp/munehiro/science/scilib.html#miura

ただ科学図書館の本は、リンクがきれているものが多いので、リンクをコピーして
Internet ArchiveのWayback Machine
https://web.archive.org/
にいれてダウンロードするとよいでしょう。たとえば科学図書館の
『三枝博音 三浦梅園の哲学 三浦梅園の哲学を、東西の哲学者の言説と対比して、日本独自の弁証法哲 学であることを解明した力作。』
のリンクは、http://fomalhautpsa.sakura.ne.jp/Science/SaigusaHiroto/miurabaien-no-tetugaku.pdfですが、クリックすると、「アクセスしようとしているサイトをみつけられません」とでてきます。その場合は上のWayback Machineのサイトにいって、このurlをいれるとアーカイブされているデータにアクセスできるので試してみてください。たとえばこの本はこちらからダウンロードできます。
https://web.archive.org/web/20231002090822/http://fomalhautpsa.sakura.ne.jp/Science/SaigusaHiroto/miurabaien-no-tetugaku.pdf

三浦梅園の「玄語」は、中央公論社の日本の名著シリーズに現代語訳(抄訳)が収録されており、デジタルコレクションで読むことができます。
『日本の名著』20,中央公論社,1984.2. 国立国会図書館デジタルコレクション https://dl.ndl.go.jp/pid/12406525 (参照 2025-09-08)

この本の巻頭の山田慶児さんの解説がとても読みやすくて面白そうです。
山田先生は同じタイトルの本も書いておられます。
山田慶児 著『黒い言葉の空間 : 三浦梅園の自然哲学』,中央公論社,1988.4. 国立国会図書館デジタルコレクション https://dl.ndl.go.jp/pid/13260115 (参照 2025-09-08) 梅園の思想の、ライプニッツや二進法・群論などとの関係を指摘して話題になった本です。
梅園の「玄語」の図を集めた本もあります。
三浦梅園 著 ほか『玄語図全影 : 三浦梅園手蹟依據』,梅園研究所,1975. 国立国会図書館デジタルコレクション https://dl.ndl.go.jp/pid/12231178 (参照 2025-09-08) ながめると興味がわくと思います。

無料で自分のパソコンにインストールして使えるGPT-OSSに英語論文執筆の方法についてきいてみた結果です。

昨日インストールしてみたOpenAIのGpt-oss latest版に英語論文を生命科学分野でかくためのbest practiceを挙げてもらいました。今いろいろ質問して遊んでみているのですが、午前中に「日本の現在の総理大臣は誰?」ときいたところ、岸田首相と答えました。知識は昔のものを使っているようです。

以下は昨日出力した英語論文作成のベストプラクティスです。こんな感じで使えるという紹介をかねてペーストしておきます。なかなか参考になると思いますがどうでしょう。

## Best‑Practice Guide for Writing Research Papers in the Biological
Sciences

> *This is a practical, step‑by‑step checklist that can be followed from
the first draft to the final submission. It draws on journal guidelines,
open‑science recommendations, and common pitfalls observed in the field.*

### 1. Before You Write

| Step | Why It Matters | Quick Actions |
|——|—————-|—————-|
| **Define the story** | A manuscript should answer one clear, central
question. | Draft a one‑sentence “story” and a 5‑bullet “take‑home
messages”. |
| **Know your audience & target journal** | Different journals have
different expectations (format, length, emphasis). | Skim 3–5 recent
papers from the target journal. Read “Author Instructions” and the “
Scope & Focus” section. |
| **Plan the structure** | IMRaD (Introduction, Methods, Results, and
Discussion) is the backbone, but sub‑sections vary. | Create a “chapter
outline” with headings & sub‑headings. |
| **Set a timeline** | Drafts, co‑author reviews, figure edits, and
revisions take time. | Use a Gantt‑style sheet: 2 wk draft, 1 wk co‑author
round, 1 wk figure polish, etc. |

### 2. Manuscript Structure (IMRaD)

| Section | Core Purpose | Practical Tips |
|———|————–|—————-|
| **Title** | Capture the essence; be concise. | 12–15 words, avoid
jargon, include a key result or method if it distinguishes your work. |
| **Abstract** | 150–250 words summarizing the whole paper. | Write it
last. Use the **structured** format: Background, Methods, Results,
Conclusion. |
| **Keywords** | Improve discoverability. | 4–6 terms that capture
methods, system, and outcome. |
| **Introduction** | Frame the problem, highlight gaps, state objectives.
| 3–5 paragraphs. End with a sentence that states the hypothesis or aim.
|
| **Materials & Methods** | Enable reproducibility. | 1–2 paragraphs per
major technique. Include *exact* reagent catalog numbers, software
versions, and statistical tests. |
| **Results** | Tell the story with data. | Follow the narrative flow;
each paragraph links to one figure/table. Use the *Results* title for
every major subsection. |
| **Discussion** | Interpret, place in context, note limitations. | 4–
5 paragraphs: 1 summarizing findings, 1-2 interpreting, 1 discussing
limitations, 1 suggesting future work. |
| **Conclusions** | (Optional) A short statement of impact. | 1–
2 sentences. |
| **Acknowledgements** | Credit support and help. | Funding, technical
assistance, and any non‑author contributions. |
| **Author Contributions** | Clarify roles. | Use the CRediT taxonomy
(Conceptualization, Methodology, Writing‑Original Draft, etc.). |
| **Funding** | Transparency. | Full grant numbers and funding agency
names. |
| **Conflicts of Interest** | Ethical transparency. | Full disclosure; “
None declared” if applicable. |
| **Data Availability** | Open science. | Link to repositories (Dryad,
Figshare, GenBank, etc.) or state “data available upon request” with a
DOI. |
| **Supplementary Information** | Additional data, detailed methods, raw
figures. | Use clear labels (Fig. S1, Table S1). Ensure the supplementary
files are cited in the main text. |

### 3. Writing the Narrative

| Tip | How to Apply |
|—–|————–|
| **Active voice & simple verbs** | “We measured X” instead of “X was
measured.” |
| **Avoid jargon** | Define every acronym the first time. |
| **Be concise** | Aim for 150 word sentences at most. |
| **Logical flow** | Each paragraph begins with a topic sentence that
states the point. |
| **Use linking phrases** | “Consequently,” “Therefore,” “In
contrast,” etc. |
| **Avoid redundant qualifiers** | “The data clearly showed” → “The
data showed.” |
| **Revisions focus** | After each draft, ask: *Does this sentence convey
a new idea?* |

### 4. Figures & Tables

| Element | Best Practice |
|———|—————|
| **Figure legends** | 50–70 words, fully explanatory, no need to refer
to the main text. |
| **Images** | High‑resolution (≥300 dpi), minimal color distortion. Use
consistent color palettes (ColorBrewer, viridis). |
| **Statistical markers** | Indicate sample size (n), p‑values, and exact
test. |
| **Table formatting** | Avoid merging cells where possible; use clear
headers; footnotes for units or abbreviations. |
| **Software** | Inkscape or Adobe Illustrator for vector graphics;
GraphPad Prism for graphs; OriginLab or R (ggplot2) for advanced plots. |
| **Caption structure** | 1) Figure name, 2) Key observations, 3)
Statistical summary. |

### 5. Referencing & Citation

| Consideration | Action |
|————–|——–|
| **Citation style** | Follow the journal’s required format (e.g.,
Vancouver, APA). |
| **Reference manager** | Zotero, EndNote, or Mendeley; use the *Insert
Citation* function to keep in sync. |
| **Avoid over‑citation** | Cite key studies, not every similar paper. |
| **Recent literature** | Include at least 2–3 papers from the last
5 years in the field. |
| **Open access** | Prefer DOIs; if the paper is behind a paywall, note
that. |

### 6. Reproducibility & Transparency

| Requirement | Implementation |
|————-|—————-|
| **Raw data** | Deposit in a public repository; link in the paper. |
| **Code** | Share analysis scripts (GitHub, Zenodo) and include a DOI. |
| **Protocols** | Provide detailed protocols; consider the *STAR*
(Structured, Transparent, Accessible, Reproducible) methods format. |
| **Animal & human ethics** | State the approval number and ethics
committee. |
| **Compliance statements** | Include ARRIVE (for animal work), CONSORT
(for clinical trials), PRISMA (for systematic reviews). |

### 7. Ethical and Legal Aspects

| Topic | Checklist |
|——-|———–|
| **Authorship** | All authors meet the International Committee of Medical
Journal Editors (ICMJE) criteria. |
| **Consent** | Obtain written consent for any human tissue or data. |
| **Data privacy** | Anonymize patient data; use a secure database. |
| **Intellectual property** | Check patents or proprietary data that might
limit sharing. |
| **Conflict of Interest** | Disclose all financial ties or affiliations.
|

### 8. Submission & Peer Review

| Step | What to do |
|——|————|
| **Choose the right journal** | Match scope, readership, and impact
factor. |
| **Read “Author Guidelines”** | Format, length limits, figure file
types, and supplementary file policies. |
| **Cover letter** | 150–200 words; state why the manuscript is a good
fit and any special points. |
| **Track changes** | Use track‑changes or a version‑control system (Git)
for transparency. |
| **Address reviewers** | Use a response letter; list each comment,
provide exact line numbers where changes were made. |
| **Revise and resubmit** | Polish for clarity; double‑check all figures,
tables, and references. |
| **Consider preprint** | Upload to bioRxiv or arXiv to get early feedback
and establish precedence. |

### 9. Common Pitfalls and How to Avoid Them

| Pitfall | Why It Happens | Prevention |
|———|—————-|————|
| **Over‑long introduction** | Trying to cover all background. | Keep it
focused on the gap your study addresses. |
| **Insufficient method detail** | Time constraints; fear of “word limit.”
| Use supplemental methods or reference a detailed protocol. |
| **Inconsistent figure styles** | Multiple authors produce figures
independently. | Standardize figure templates early. |
| **Statistical misuse** | Misunderstanding tests or p‑value thresholds. |
Verify with a statistician or use software that auto‑checks assumptions. |
| **Poor sentence structure** | Drafting in one language or rushing. |
Proofread, use grammar checkers (Grammarly, Hemingway), or have a
colleague edit. |
| **Citation overload** | Trying to “cover all bases.” | Cite only the
most relevant and recent work. |
| **Neglecting data deposition** | Forgetting or underestimating the
effort. | Schedule data deposition early; use persistent identifiers
(DOIs). |
| **Skipping peer feedback** | Belief that you know best. | Arrange
internal peer review (lab mates, mentors) before submission. |

### 10. Resources & Templates

| Resource | What it Provides |
|———-|—————–|
| **PLOS “Guide to Authors”** | Step‑by‑step, journal‑agnostic guidance.
|
| **Nature “Author Guidelines”** | Example of high‑impact journal
expectations. |
| **ARRIVE 2.0** | Standards for reporting animal studies. |
| **CONSORT** | Reporting guidelines for randomized trials. |
| **PRISMA** | Reporting checklist for systematic reviews. |
| **STAR Methods** | A structured format widely used in Cell Press
journals. |
| **GitHub + Zenodo** | Code and data sharing with DOI. |
| **Figshare / Dryad** | Generic data repositories. |
| **BioRxiv** | Preprint server with rapid feedback. |

## Quick‑Start Checklist

1. **Draft the story** (one sentence + 5 bullets).
2. **Outline the manuscript** (IMRaD + sub‑sections).
3. **Write the methods** in detail first (ensures reproducibility).
4. **Collect & analyze data**; generate figures early.
5. **Write Results** to match figures; keep narrative tight.
6. **Write Introduction & Discussion** using the story map.
7. **Polish Abstract & Title** last.
8. **Prepare tables, legends, and supplementary files**.
9. **Run a full checklist** (authorship, ethics, data availability).
10. **Submit** with a concise cover letter.

> *Remember: the key to a great paper is clarity, transparency, and a
compelling narrative that invites readers to follow the logic of your
science.*

ローカルでLLMをインストールして使えるOllamaを早速インストールしてGPT-OSSを使ってみました。

昨日の記事で書いたOllamaをUbuntu で動いているPCにインストールして使ってみました。メモリ32G ByteでNVIDIAは470という、古いPCですが、OpenAIのgpt-oss:20b モデルがちゃんと動きました。

OllamaのLinux版のダウンロードページ
https://ollama.com/download/linux
にいって、Ubuntuのコマンドラインでサイトに書いてある一行のコマンド
curl -fsSL https://ollama.com/install.sh | sh
を実行するだけで、自動でインストールが行われます。
マニュアルインストールもできますが、いろいろめんどうらしいので上のコマンドを実行すると、一発でインストールが完了しました。私のPCにはcudaやnividiaの純正ドライバもインストール済みなので簡単に終わったのだと思います。Ollamaをインストールしただけなので、LLMはまだインストールされてません。そこでこちらからよさそうなLLMのモデルを選びます。
https://ollama.com/models
いっぱいモデルがあります。今回はOpenAIのGPT-OSS latestを選びました。https://ollama.com/library/gpt-oss
LLMモデルのインストールはコマンドラインで
ollama run gpt-oss
とうつだけです。自分のPCに適合したモデルが自動でインストールされます。何もせずにただ待っているだけで14G ほどのモデルがダウンロードされて起動しました。gpt-oss 20bモデル(これは16Gのメモリーがあれば使えるそうです)が起動してプロンプトを受け付ける状態になりました。このLLMはテキストを入力して、テキストで返事してくるというモデルなのでプロンプトにテキストを入力してエンターを押します。すると思考過程を出力しながら、回答を考えて、テキストで回答してきます。

試しに、生命科学分野の論文を書くためのBest Practiceを教えてと英語でいれると、大変実用的な論文の書き方指南書を出力してきました。明日、どんなのかはお見せしたいと思います。日本語を入力して英語にするのもできましたし、ネットにでていた「空が青いのは何故かを、物理学の観点から説明してください」というプロンプトにも、ちゃんとレーリー散乱の解説をまじえて回答してきました。ローカルでいろいろ使えそうで面白かったです。

あっけなくローカルでLLMが使えるようになって、驚いています。皆さんも試してみると楽しいと思います。また導入でわからないことがあった場合は、こちらの記事が参考になります。

『無料でGPT-OSSを使う:Ollama導入ガイド』
https://apidog.com/jp/blog/run-gpt-oss-using-ollama-jp/

ローカルでLLMを動かす方法についての記事があるのを知りました。

ローカルでAIを動かせる時代がやってきています。プライバシーについての配慮や仕事の性質上、ローカルで動くLLMが必要なことがあると思います。そういう目的にピッタリのソフトがあるそうです。

この記事です。原文はこちらで、
“I tried running a chatbot on my old computer hardware and it actually worked”
https://www.makeuseof.com/i-tried-running-ai-on-my-old-gtx-1070-and-it-actually-worked/
翻訳版はこちらにあります。

『古いPCを「ローカルAI専用機」にしてみた。10年近く前のマシンでも、まだいけるぞ』
https://www.lifehacker.jp/article/2509-i-tried-running-ai-on-my-old-gtx-1070-and-it-actually-worked/

面白そうなのでやってみたいと思い検索すると、いろいろ記事がみつかりました。

『LM Studioの使い方完全ガイド|ローカルPCでGPT-OSSを安全に動かす方法と特徴』
https://digeon.co/blog/lm-studio-local-llm-gpt-oss
LM studioはオープンソースではないのですが無料で利用できます。完全オープンソースのOllamaもあって、こちらを使うのもよさそうです。比較はこちらの記事にわかりやすくまとめられていました。

『Ollama vs LM Studio ローカルLLMツールの特徴・使いやすさ・選び方ガイド』
https://ensou.app/blog/local-llm-ollama-lm-studio-comparison/

面白そうなAIや宇宙、量子に関する日本語動画を紹介します。

福岡は今日は涼しい一日でした。クーラーもあまり使わずにすごせました。
昨日紹介したExcel VBAのマクロを使って作成したマクロ有効ブック10個に、必要なデータ操作用のマクロを一挙にいれるというマクロを使って、10個ほどのデータ解析をやっていました。私はエクセルのマクロなどまったく知らなかったのですが、ChatGPTのおかげで解析がおどろくほど自由になりました。感動です。
ということで一日とても忙しかったので簡単な動画の紹介をしておきます。

面白そうなYouTube動画(日本)を3つ紹介します。一般向けの理解しやすい動画です。

夏休みの宿題ってAIでやるのアリ?ナシ?/AI時代における学びの価値とは?/AIだからこそできる教育
https://youtu.be/UxWsc_Tev2c?

大阪・関西万博「エンタングル・モーメント展」ステージイベント:見えない世界を知るために―量子・宇宙
https://youtu.be/9557cpVTVrk?

東京大学理学部オープンキャンパス2025 講演「機械学習研究のこれまでとこれから」杉山将教授
https://youtu.be/O5nqAXlA8QI?

Excelで複数のCSVファイルをマクロ有効ブック(.xlsm)へ変換する方法

今日、たくさんのcsvファイルを一つずつ開いて、マクロ有効ブック.xlsmとして保存する作業をはじめました。大変手間がかかることがわかったので、エクセルのVBAマクロで一括変換できないかChatGPTに相談してみました。結果は、

VBAでフォルダ内の複数CSVを一括で.xlsm(マクロ有効ブック)に変換できます。」ということで、VBAマクロを作ってくれたので紹介します。

マクロの使い方は以下のとおりです(概要)
1)Excelで空ブックを開く → Alt + F11 → 「挿入」→「標準モジュール」。
2)下のコードを貼り付けて保存(このブックは .xlsm で保存します)。
3)Alt + F8 → BatchConvertCsvToXlsm (マクロの名)を実行。
4)ダイアログで変換元フォルダ(CSVがあるフォルダ:新規にフォルダを作成するのがおすすめです)をきいてくるので指定します。
5)次に、出力先フォルダ(.xlsmを書き出すフォルダ:新規に作成するのがおすすめです)をきいてくるので指定します。
しばらくまっていると、すべてのCSVファイルが.xlsmファイルになって出力先フォルダにできあがります。これは便利なマクロです。

マクロは以下のとおりです。


Option Explicit

Sub BatchConvertCsvToXlsm()
Dim srcFolder As String, dstFolder As String
Dim fd As FileDialog
Dim fso As Object, f As Object, folder As Object
Dim wb As Workbook
Dim baseName As String, outPath As String
Dim cntOk As Long, cntNg As Long

‘ フォルダ選択(変換元)
Set fd = Application.FileDialog(msoFileDialogFolderPicker)
With fd
.Title = “CSVのあるフォルダを選んでください”
If .Show <> -1 Then Exit Sub
srcFolder = .SelectedItems(1)
End With

‘ フォルダ選択(出力先)
With fd
.Title = “出力先フォルダ(.xlsm)を選んでください”
If .Show <> -1 Then Exit Sub
dstFolder = .SelectedItems(1)
End With

If Right$(srcFolder, 1) <> “\” Then srcFolder = srcFolder & “\”
If Right$(dstFolder, 1) <> “\” Then dstFolder = dstFolder & “\”

Set fso = CreateObject(“Scripting.FileSystemObject”)
If Not fso.FolderExists(srcFolder) Then
MsgBox “変換元フォルダが見つかりません: ” & srcFolder, vbExclamation
Exit Sub
End If
If Not fso.FolderExists(dstFolder) Then
MsgBox “出力先フォルダが見つかりません: ” & dstFolder, vbExclamation
Exit Sub
End If

Set folder = fso.GetFolder(srcFolder)

‘ 高速化
Dim prevScr As Boolean, prevDisp As Boolean, prevCalc As XlCalculation, prevEvt As Boolean
prevScr = Application.ScreenUpdating
prevDisp = Application.DisplayAlerts
prevCalc = Application.Calculation
prevEvt = Application.EnableEvents
Application.ScreenUpdating = False
Application.DisplayAlerts = False
Application.Calculation = xlCalculationManual
Application.EnableEvents = False

On Error GoTo CLEANUP

Dim ext As String
For Each f In folder.Files
ext = LCase$(fso.GetExtensionName(f.Path))
If ext = “csv” Then
On Error Resume Next

‘ ★基本は自動判定で開く(UTF-8/BOM付き等はExcelが自動解釈することが多い)
Set wb = Workbooks.Open(Filename:=f.Path)

If Err.Number <> 0 Or wb Is Nothing Then
‘ 開けなかった場合は明示的区切り指定(カンマ)で再トライ
Err.Clear
On Error GoTo 0
Workbooks.OpenText _
Filename:=f.Path, _
DataType:=xlDelimited, _
Comma:=True, _
Local:=True ‘ ローカル区切り/エンコーディングの助け
Set wb = ActiveWorkbook
Else
On Error GoTo 0
End If

If Not wb Is Nothing Then
baseName = fso.GetBaseName(f.Path)
outPath = dstFolder & baseName & “.xlsm”

‘ 既存があれば上書き(DisplayAlerts=Falseのため確認なし)
wb.SaveAs Filename:=outPath, FileFormat:=xlOpenXMLWorkbookMacroEnabled
wb.Close SaveChanges:=False
cntOk = cntOk + 1
Else
cntNg = cntNg + 1
End If
End If
Next f

CLEANUP:
Application.ScreenUpdating = prevScr
Application.DisplayAlerts = prevDisp
Application.Calculation = prevCalc
Application.EnableEvents = prevEvt

If Err.Number <> 0 Then
MsgBox “処理中にエラーが発生しました: ” & Err.Description & vbCrLf & _
“成功: ” & cntOk & ” 件 / 失敗: ” & cntNg & ” 件”, vbExclamation
Else
MsgBox “変換完了” & vbCrLf & _
“成功: ” & cntOk & ” 件 / 失敗: ” & cntNg & ” 件”, vbInformation
End If
End Sub


上のコードをコピペするだけで動くと思います。動かないときはChatGPTにコードをいれてきいてみてください。ChatGPTが書いてきた注意点もペーストしておきます。

注意点:
・区切り文字がタブやセミコロンのCSV/TSVの場合は、Workbooks.OpenText の引数を変更してください(例:Tab:=True、Semicolon:=True)。

・文字化け対策:UTF-8(BOMなし)などで文字化けする場合は、OpenText に Origin:=65001 を追加して試してください。

英語学習用のChatGPTプロンプト、ハーバード大学の学部向け機械学習入門教科書の紹介です。

英語学習のためのChatGPTのプロンプトの紹介です。
以前から紹介している京都大学の柳瀬陽介先生のサイト
https://yanase-yosuke.blogspot.com/
にあるものは有用ですが、こちらのツイートのプロンプトも学習用には貴重だと思います。ためしてみてください。


話はかわりますが、こんな機械学習の教材(英語版)もダウンロードして読むことができます。
Textbook created for Harvard’s undergraduate course in Machine Learning, CS181
ハーバード大学の学部生向けの機械学習の教科書だそうです。
https://github.com/harvard-ml-courses/cs181-textbook/blob/master/README.md
pdfへのリンクをクリックすると、次のエラーが出ると思います。

“Error rendering embedded code

Invalid PDF”

これは気にせず、3.59MBとある行の鉛筆マークの左にあるダウンロードボタンを押すとpdfがブラウザで表示されますのでダウンロードしてみてください。

久保さんの緑本『データ解析のための統計モデリング入門』を読むための動画やサイトを紹介します。

岩波書店から出ている久保 拓弥さんの本は緑本とよばれて読まれている名著です。
確率と情報の科学シリーズの一冊です。岩波書店のサイトへのリンクをのせておきます。
『データ解析のための統計モデリング入門
一般化線形モデル・階層ベイズモデル・MCMC』
https://www.iwanami.co.jp/book/b257893.html

久保さんの講義が公開」されているのをうかつにも今日まで知りませんでした。次のツイートにある講義は緑本を読む前に学ぶととても良いと思います。私も勉強させてもらおう糖思います。

動画リンクはこちらです。
https://www.ism.ac.jp/lectures/leadingdat/2022/free_movie.html
いろんな動画がありますが一番下に久保さんの動画へのリンクがあります。
埋め込んでおきます。
https://youtu.be/Hq4K2Kk3lbU?

https://youtu.be/lj77dMmw98E?

こちらのサイトも緑本を読むのに参考になりそうです。
「データ解析のための統計モデリング入門」 読書メモ一覧
https://stern-bow.hatenablog.com/entry/2024/12/30/180000