--- title: How I Actually Use AI for Data Science in Python | daily.dev description: A practical walkthrough of using AI assistance for data science workflows in Python, with emphasis on verification over blind trust. Covers loading CSV and... canonical: https://daily.dev/posts/how-i-actually-use-ai-for-data-science-in-python-jak0mlpfh twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: How I Actually Use AI for Data Science in Python | daily.dev og:description: A practical walkthrough of using AI assistance for data science workflows in Python, with emphasis on verification over blind trust. Covers loading CSV and... og:url: https://daily.dev/posts/how-i-actually-use-ai-for-data-science-in-python-jak0mlpfh og:image: https://api.daily.dev/og/posts/jak0MlpFH.png og:image:alt: How I Actually Use AI for Data Science in Python og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # How I Actually Use AI for Data Science in Python **[Tech With Tim](https://daily.dev/sources/TechWithTim)** · 18 min read · 1 upvotes · 0 comments ## Summary A practical walkthrough of using AI assistance for data science workflows in Python, with emphasis on verification over blind trust. Covers loading CSV and SQLite data into Jupyter notebooks inside PyCharm, using AI chat to suggest data transformations (e.g., fixing mixed US/European currency formats), and critically verifying AI-generated code using PyCharm's built-in data viewer, column statistics, and Data Wrangler. Also covers setting up AI skills/rules to encode project conventions, running SQL queries that auto-save to dataframes, and using AI to generate matplotlib visualizations. The core message: AI is useful for writing transformation code, but the hard part is validating correctness using proper data visualization tools. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How can I get AI to fix mixed currency formats like US and European number styles in a pandas revenue column? Ask the AI assistant to inspect the raw values in the column before converting, since a naive fix (stripping dollar signs and commas) will corrupt European-formatted numbers like 9.537,48 by misreading them as 9.537 instead of 9537.48. Prompting the assistant to first verify whether multiple formats exist in the column, rather than immediately applying a transformation, avoids silently losing correct values. _daily.dev surfaces workflow tips like this for developers pairing AI assistants with real data cleanup tasks._ ### Why shouldn't I trust AI-generated pandas code for data cleaning without checking it? AI can propose transformations that look reasonable but silently corrupt data, such as misparsing mixed currency formats or dropping outliers incorrectly. The recommended safeguard is inspecting dataframes with visualization tools (column statistics, data viewers) before and after each AI-suggested change, and cross-checking results against the source database rather than assuming correctness. _Developers weighing how much to trust AI-generated code often compare notes on daily.dev._ ## Similar posts on daily.dev - [How AI Is Changing the Daily Work of Data Analysts \(And Why That’s Good News\)](https://daily.dev/posts/how-ai-is-changing-the-daily-work-of-data-analysts-and-why-that-s-good-news--qgftnhazs) · Medium · 1 upvotes · 0 comments --- Tags: [#python](https://daily.dev/tags/python), [#data-science](https://daily.dev/tags/data-science), [#devtools](https://daily.dev/tags/devtools), [#pandas](https://daily.dev/tags/pandas), [#jupyter](https://daily.dev/tags/jupyter) [View this post on daily.dev](https://daily.dev/posts/how-i-actually-use-ai-for-data-science-in-python-jak0mlpfh) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"How I Actually Use AI for Data Science in Python","url":"https://daily.dev/posts/how-i-actually-use-ai-for-data-science-in-python-jak0mlpfh","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/how-i-actually-use-ai-for-data-science-in-python-jak0mlpfh"},"datePublished":"2026-07-20T14:05:17.485Z","dateModified":"2026-09-13T20:54:24.173Z","description":"A practical walkthrough of using AI assistance for data science workflows in Python, with emphasis on verification over blind trust. Covers loading CSV and...","image":"https://i.ytimg.com/vi/bFVa-lLlGYA/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/bFVa-lLlGYA/sddefault.jpg","isAccessibleForFree":true,"articleSection":"Tech With Tim","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Tech With Tim","logo":"https://media.daily.dev/image/upload/s--6vVIDfU0--/f_auto/v1711726146/logos/TechWithTim","url":"https://daily.dev/sources/TechWithTim"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/how-i-actually-use-ai-for-data-science-in-python-jak0mlpfh","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"python,data-science,devtools,pandas,jupyter","timeRequired":"PT18M","video":{"@type":"VideoObject","name":"How I Actually Use AI for Data Science in Python","description":"A practical walkthrough of using AI assistance for data science workflows in Python, with emphasis on verification over blind trust. Covers loading CSV and...","thumbnailUrl":"https://i.ytimg.com/vi/bFVa-lLlGYA/sddefault.jpg","uploadDate":"2026-07-20T14:05:17.485Z","duration":"PT18M","url":"https://api.daily.dev/r/jak0MlpFH","embedUrl":"https://www.youtube.com/embed/bFVa-lLlGYA"}} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Tech With Tim","item":"https://daily.dev/sources/TechWithTim"},{"@type":"ListItem","position":3,"name":"How I Actually Use AI for Data Science in Python"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/how-i-actually-use-ai-for-data-science-in-python-jak0mlpfh#faq","mainEntity":[{"@type":"Question","name":"How can I get AI to fix mixed currency formats like US and European number styles in a pandas revenue column?","acceptedAnswer":{"@type":"Answer","text":"Ask the AI assistant to inspect the raw values in the column before converting, since a naive fix (stripping dollar signs and commas) will corrupt European-formatted numbers like 9.537,48 by misreading them as 9.537 instead of 9537.48. Prompting the assistant to first verify whether multiple formats exist in the column, rather than immediately applying a transformation, avoids silently losing correct values. daily.dev surfaces workflow tips like this for developers pairing AI assistants with real data cleanup tasks."}},{"@type":"Question","name":"Why shouldn't I trust AI-generated pandas code for data cleaning without checking it?","acceptedAnswer":{"@type":"Answer","text":"AI can propose transformations that look reasonable but silently corrupt data, such as misparsing mixed currency formats or dropping outliers incorrectly. The recommended safeguard is inspecting dataframes with visualization tools (column statistics, data viewers) before and after each AI-suggested change, and cross-checking results against the source database rather than assuming correctness. Developers weighing how much to trust AI-generated code often compare notes on daily.dev."}}]} ```