diff --git a/.gitignore b/.gitignore index e4d334cca..ef4cd4b71 100644 --- a/.gitignore +++ b/.gitignore @@ -21,6 +21,7 @@ assets/css/index.css /.quarto/ **/*.quarto_ipynb +**/_mall_cache/ .env diff --git a/content/blog/libraries-for-python-polars/images/book-signing.jpeg b/content/blog/libraries-for-python-polars/images/book-signing.jpeg new file mode 100644 index 000000000..8e2fcb9f5 Binary files /dev/null and b/content/blog/libraries-for-python-polars/images/book-signing.jpeg differ diff --git a/content/blog/libraries-for-python-polars/images/featured-image.jpg b/content/blog/libraries-for-python-polars/images/featured-image.jpg new file mode 100644 index 000000000..7bbddbc99 Binary files /dev/null and b/content/blog/libraries-for-python-polars/images/featured-image.jpg differ diff --git a/content/blog/libraries-for-python-polars/index.md b/content/blog/libraries-for-python-polars/index.md new file mode 100644 index 000000000..71e293fbe --- /dev/null +++ b/content/blog/libraries-for-python-polars/index.md @@ -0,0 +1,844 @@ +--- +title: Libraries for Your Python Polars Workflows +date: '2026-05-28' +people: + - Isabella Velásquez +description: > + Posit's Python libraries provide excellent support for Polars DataFrames + across your data science workflow. +image: images/featured-image.jpg +image-alt: A polar bear waving in front of a bookshelf filled with colorful books +photo: + url: https://unsplash.com/photos/qQWV91TTBrE + author: Hans-Jurgen Mager +topics: + - Data Wrangling + - Visualization +software: + - great-tables + - pointblank + - plotnine + - mall +languages: + - Python +format: hugo-md +jupyter: python3 +filters: + - strip-html-blank-lines +--- + + + + + + + +We (Emil Hvitfeldt, Jeroen Janssens, Michael Chow, and I) just got back from PyCon US 2026, and there was **so much buzz** around [Polars](https://pola.rs/). What is Polars? Why should I switch to Polars? *How* do I switch to Polars? + +I mean, just check out the line for the book signing of Jeroen's book, [Python Polars: The Definitive Guide](https://polarsguide.com/). + +
+A long line of conference attendees waiting at Jeroen’s book signing booth in PyCon US’ large convention hall + +
+ +If Polars is new to you, it is a library for efficient data manipulation in Python. It's built on Rust, so it's super fast. And a lot of people (including [the creator of Pandas](https://polarsguide.com/praise/)!) like the intuitive way you write Polars code. However, if you work in Python, you might know that different DataFrames have different requirements, so you want to make sure to use libraries that support Polars (I admit, I come from the R world, and this was mind blowing to me). + +And, we're happy to say that we (Posit) have excellent Polars support across our Python libraries for every stage of the data science workflow! In this post, we'll walk through four: + +- [**pointblank**](https://posit-dev.github.io/pointblank/) for data validation and quality checks +- [**Great Tables**](https://posit-dev.github.io/great-tables/articles/intro.html) for creating publication-quality tables +- [**plotnine**](https://plotnine.org/) for ggplot2-style visualizations +- [**mall**](https://mlverse.github.io/mall/) for LLM-powered data analysis + +Let's check them out! + +## Setup + +First, let's install the libraries: + +``` python +pip install polars great_tables pointblank plotnine mlverse-mall +``` + +Now, import what we need: + +``` python +import polars as pl +from great_tables import GT +import pointblank as pb +from plotnine import ( + ggplot, aes, geom_point, geom_line, geom_bar, geom_text, geom_col, + labs, theme_minimal, theme, element_text, scale_fill_manual, + scale_y_continuous, element_rect, element_blank, element_line, + scale_color_manual, position_dodge, annotate +) +import mall +``` + +## The dataset + +We'll demonstrate these tools using `sales_data`, a sample sales dataset: + +``` python +sales_data = pl.DataFrame({ + "date": ["2026-01-15", "2026-01-16", "2026-01-17", "2026-01-18", + "2026-01-19", "2026-01-20", "2026-01-21"], + "region": ["North", "South", "North", "West", "South", "North", "West"], + "product": ["Widget A", "Widget B", "Widget A", "Widget C", + "Widget B", "Widget A", "Widget C"], + "sales": [1200, 1800, 1500, 2100, 1650, 1900, 2300], + "units_sold": [24, 36, 30, 42, 33, 38, 46], + "customer_rating": [4.5, 4.8, 4.6, 4.9, 4.7, 4.8, 4.9] +}).with_columns( + pl.col("date").str.strptime(pl.Date, "%Y-%m-%d") +) + +sales_data +``` + +
+shape: (7, 6) + +| date | region | product | sales | units_sold | customer_rating | +|------------|-----------|--------------|-------|------------|-----------------| +| date | str | str | i64 | i64 | f64 | +| 2026-01-15 | \"North\" | \"Widget A\" | 1200 | 24 | 4.5 | +| 2026-01-16 | \"South\" | \"Widget B\" | 1800 | 36 | 4.8 | +| 2026-01-17 | \"North\" | \"Widget A\" | 1500 | 30 | 4.6 | +| 2026-01-18 | \"West\" | \"Widget C\" | 2100 | 42 | 4.9 | +| 2026-01-19 | \"South\" | \"Widget B\" | 1650 | 33 | 4.7 | +| 2026-01-20 | \"North\" | \"Widget A\" | 1900 | 38 | 4.8 | +| 2026-01-21 | \"West\" | \"Widget C\" | 2300 | 46 | 4.9 | + +
+ +We can confirm that it is, indeed, a Polars DataFrame! + +``` python +isinstance(sales_data, pl.DataFrame) +``` + + True + +## Data validation with pointblank + +Let's now validate our data quality using [**pointblank**](https://posit-dev.github.io/pointblank/): + +``` python +agent = ( + pb.Validate(sales_data) + .col_vals_not_null(columns="date") + .col_vals_between(columns="sales", left=0, right=10000) + .col_vals_between(columns="customer_rating", left=1.0, right=5.0) + .col_vals_in_set(columns="region", set=["North", "South", "East", "West"]) + .interrogate() +) + +agent +``` + +
+ + ++ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
Pointblank Validation
2026-05-29|21:34:38
Polars
STEPCOLUMNSVALUESTBLEVALUNITSPASSFAILWECEXT
#4CA64C1 +
+ + + col_vals_not_null + + + + + + + + + +
+
+
col_vals_not_null()
+
+ 		date— + + + + + + + +✓77
1.00		0
0.00		————
#4CA64C2 +
+ + + col_vals_between + + + + + + + +
+
+
col_vals_between()
+
+ 		sales[0, 10000] + + + + + + + +✓77
1.00		0
0.00		————
#4CA64C3 +
+ + + col_vals_between + + + + + + + +
+
+
col_vals_between()
+
+ 		customer_rating[1.0, 5.0] + + + + + + + +✓77
1.00		0
0.00		————
#4CA64C4 +
+ + + col_vals_in_set + + + + + + + +
+
+
col_vals_in_set()
+
+ 		regionNorth, South, East, West + + + + + + + +✓77
1.00		0
0.00		————
2026-05-29 21:34:38 UTC< 1 s2026-05-29 21:34:38 UTC
+
+ +In natural language, the steps that the agent performs are: + +- Validate the `sales_data` DataFrame +- Make sure that no values in `Date` are null +- Make sure that the values in `sales` are between 0 and 10000 +- Make sure that the values in `customer_rating` are between 1 and 5 +- Make sure that the values in `region` are "North", "South", "East", or "West" +- Now, interrogate! + +The resulting table lets us know for each step what was expected, how many values passed, the percentage of values that passed, and so on. And, the validation agent works directly with Polars DataFrames, no need to convert to pandas! + +Also, about that nifty table that gets output? 👀 **Directly** in this blog post (written in [Quarto](https://quarto.org/))? [That is Great Tables](https://posit-dev.github.io/great-tables/)! But Great Tables isn't just for pointblank... + +## Creating beautiful tables with Great Tables + +Let's summarize some data: + +``` python +daily_summary = ( + sales_data.group_by("date") + .agg( + [ + pl.col("sales").sum().alias("total_sales"), + pl.col("units_sold").sum().alias("total_units"), + pl.col("customer_rating").mean().alias("avg_rating"), + ] + ) + .sort("date") +) + +regional_summary = ( + sales_data.group_by("region") + .agg( + [ + pl.col("sales").sum().alias("total_sales"), + pl.col("sales").mean().alias("avg_sales"), + pl.col("units_sold").sum().alias("total_units"), + pl.col("sales").alias("sales_trend"), + ] + ) + .sort("total_sales", descending=True) +) +``` + +Let's present our regional summary in a ✨publication-quality table✨ using **Great Tables**: + +``` python +from great_tables import loc, style + +( + GT(regional_summary) + .tab_header( + title="Regional Sales Performance", + subtitle="Week of January 15-21, 2026" + ) + .fmt_currency( + columns=["total_sales", "avg_sales"], + currency="USD" + ) + .fmt_number( + columns="total_units", + decimals=0, + sep_mark="," + ) + .fmt_nanoplot( + columns="sales_trend", + plot_type="line", + autoscale=True + ) + .cols_label( + region="Region", + total_sales="Total Sales", + avg_sales="Average Sale", + total_units="Units Sold", + sales_trend="Trend" + ) + .data_color( + columns="total_sales", + palette=["#f0f0f0", "#447099"], + domain=[1000, 5000] + ) + .tab_style( + style=style.text(weight="bold"), + locations=loc.body(columns="region") + ) + .tab_style( + style=style.fill(color="#e8f4f8"), + locations=loc.body(rows=[0]) + ) + .tab_source_note("Data validated with pointblank · Trend shows daily sales pattern") + .tab_options( + table_font_size="14px", + heading_title_font_size="18px", + heading_subtitle_font_size="14px" + ) +) +``` + +
+ + + +++++++ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
Regional Sales Performance
Week of January 15-21, 2026
RegionTotal SalesAverage SaleUnits SoldTrend
North$4,600.00$1,533.3392
+ +2.30K1.20K1.20K1.50K1.90K + +
West$4,400.00$2,200.0088
+ +2.30K1.20K2.10K2.30K + +
South$3,450.00$1,725.0069
+ +2.30K1.20K1.80K1.65K + +
Data validated with pointblank · Trend shows daily sales pattern
+ +
+ +In this example, Great Tables: + +- Adds a title using `tab_header` +- Formats currency using `fmt_currency` +- Formats numbers using `fmt_number` +- Creates a nanoplot (a miniature line chart) using `fmt_nanoplot` +- Labels the columns using `cols_label` +- Edit color, styling, and font sizes with `data_color`, `tab_style`, and `tab_options` +- Add a source note using `tab_source_note` + +All with full Polars support! In fact, Great Tables is the [default way to style Polars DataFrames](https://docs.pola.rs/user-guide/misc/styling/), using `df.style`. + +## Visualizations with plotnine + +For visualizations, [**plotnine**](https://plotnine.org/) brings the [grammar of graphics](https://en.wikipedia.org/wiki/Wilkinson%27s_Grammar_of_Graphics) to Python. Let's create some nice-looking plots: + +### Daily sales trend + +``` python +( + ggplot(daily_summary, aes(x="date", y="total_sales")) + + geom_line(color="#447099", size=1.5) + + geom_point(color="#447099", size=4, fill="white", stroke=1.5) + + geom_text( + aes(label="total_sales"), + va="bottom", + nudge_y=100, + size=9, + color="#333333", + format_string="${:,.0f}" + ) + + scale_y_continuous( + labels=lambda l: [f"${x:,.0f}" for x in l], + limits=(1000, 2600), + expand=(0, 0) + ) + + labs( + title="Daily Sales Trend", + subtitle="Week of January 15-21, 2026 • Total revenue trending upward", + x="", + y="" + ) + + theme_minimal() + + theme( + plot_title=element_text(size=16, weight="bold", color="#2c3e50"), + plot_subtitle=element_text(size=11, color="#7f8c8d", margin={"b": 15}), + axis_title_y=element_blank(), + axis_text_y=element_text(size=10, color="#666666"), + axis_text_x=element_text(size=10, color="#666666"), + panel_grid_major_x=element_blank(), + panel_grid_minor=element_blank(), + panel_grid_major_y=element_line(color="#e0e0e0", size=0.5), + plot_background=element_rect(fill="white"), + panel_background=element_rect(fill="white"), + figure_size=(8, 6) + ) +) +``` + + + +### Sales by region and product + +``` python +# Custom color palette with Posit-inspired colors +product_colors = { + "Widget A": "#447099", # Blue + "Widget B": "#72994e", # Green + "Widget C": "#c65d47", # Rust +} + +( + ggplot(sales_data, aes(x="region", y="sales", fill="product")) + + geom_col(position=position_dodge(width=0.8), width=0.7) + + scale_fill_manual(values=product_colors) + + scale_y_continuous( + labels=lambda l: [f"${x:,.0f}" for x in l], + limits=(0, 2500), + breaks=range(0, 2501, 500), + expand=(0, 0), + ) + + labs( + title="Sales Performance by Region", + subtitle="Product comparison across geographic markets", + x="", + y="", + fill="", + ) + + theme_minimal() + + theme( + plot_title=element_text(size=16, weight="bold", color="#2c3e50"), + plot_subtitle=element_text(size=11, color="#7f8c8d", margin={"b": 15}), + axis_title=element_blank(), + axis_text_y=element_text(size=10, color="#666666"), + axis_text_x=element_text(size=11, color="#333333", weight="bold"), + legend_position="top", + legend_title=element_blank(), + legend_text=element_text(size=10), + legend_box_margin=0, + panel_grid_major_x=element_blank(), + panel_grid_minor=element_blank(), + panel_grid_major_y=element_line(color="#e0e0e0", size=0.5), + plot_background=element_rect(fill="white"), + panel_background=element_rect(fill="white"), + figure_size=(8, 6), + ) +) +``` + + + +Plotnine works seamlessly with Polars DataFrames, no conversion needed! These visualizations can include: + +- Values displayed directly on points for easy reading with `geom_text` +- Currency labels, appropriate limits, and controlled breaks with `scale_y_continuous` +- Larger, bolder titles with subtle subtitle styling with `theme` +- Pure white backgrounds with subtle gray gridlines with `theme_minimal` (my favorite built-in theme) + +Again, with full Polars support. There's more about it in the [Polars documentation for visualization](https://docs.pola.rs/user-guide/misc/visualization/). + +## AI-powered insights with mall + +Finally, let's use [**mall**](https://mlverse.github.io/mall/) to add LLM-powered analysis to our workflow. I used [Ollama](https://ollama.com/) [^1] with a local model, but mall works with OpenAI, Anthropic, and other providers through the [chatlas](https://github.com/cpsievert/chatlas) package. + +Mall extends Polars DataFrames with an `.llm` accessor that provides natural language operations. We can use mall to add natural language descriptions to our sales data, rating the performance of each row as "low", "medium", or "high": + +``` python +sales_data.llm.use("ollama", "llama3.2") + +sales_with_performance = sales_data.llm.classify( + "sales", + ["high", "medium", "low"], + pred_name="performance", +) + +sales_with_performance.select( + ["date", "region", "product", "sales", "performance"] +) +``` + +
+shape: (7, 5) + +| date | region | product | sales | performance | +|------------|-----------|--------------|-------|-------------| +| date | str | str | i64 | str | +| 2026-01-15 | \"North\" | \"Widget A\" | 1200 | \"low\" | +| 2026-01-16 | \"South\" | \"Widget B\" | 1800 | \"low\" | +| 2026-01-17 | \"North\" | \"Widget A\" | 1500 | \"low\" | +| 2026-01-18 | \"West\" | \"Widget C\" | 2100 | \"low\" | +| 2026-01-19 | \"South\" | \"Widget B\" | 1650 | \"low\" | +| 2026-01-20 | \"North\" | \"Widget A\" | 1900 | \"low\" | +| 2026-01-21 | \"West\" | \"Widget C\" | 2300 | \"low\" | + +
+ +Or we can generate custom descriptions for each product: + +``` python +sales_with_description = sales_data.llm.custom( + "product", + pred_name="description", + prompt="Create a brief, compelling marketing description for this product in 10 words or less", +) + +with pl.Config(fmt_str_lengths=200): + print(sales_with_description.select(["product", "description"])) +``` + + shape: (7, 2) + ┌──────────┬───────────────────────────────────────────────────────────────────────┐ + │ product ┆ description │ + │ --- ┆ --- │ + │ str ┆ str │ + ╞══════════╪═══════════════════════════════════════════════════════════════════════╡ + │ Widget A ┆ "Unlock innovative performance with Widget A - Simplify Your Space." │ + │ Widget B ┆ "Unlock the Power of Widget B: Revolutionizing Your World." │ + │ Widget A ┆ "Unlock innovative performance with Widget A - Simplify Your Space." │ + │ Widget C ┆ "Unlock innovative possibilities with Widget C, designed to elevate." │ + │ Widget B ┆ "Unlock the Power of Widget B: Revolutionizing Your World." │ + │ Widget A ┆ "Unlock innovative performance with Widget A - Simplify Your Space." │ + │ Widget C ┆ "Unlock innovative possibilities with Widget C, designed to elevate." │ + └──────────┴───────────────────────────────────────────────────────────────────────┘ + +Mall has a bunch of other powerful operations you can use: + +- `.llm.classify()` --- Categorize data into predefined labels +- `.llm.sentiment()` --- Analyze sentiment (positive/negative/neutral) +- `.llm.summarize()` --- Condense text columns to key points +- `.llm.extract()` --- Pull specific information from text +- `.llm.translate()` --- Convert text to another language +- `.llm.verify()` --- Check if statements are supported by data + +And not surprisingly, mall keeps everything in Polars format, which means fast, AI-enhanced data operations that fit naturally into your Polars pipelines. + +## Wrapping up + +The Python data ecosystem has embraced Polars, and so has Posit! These four libraries show how we can build complete data workflows without ever leaving the Polars DataFrame format: + +- **pointblank** --- Ensure your data quality before analysis begins +- **Great Tables** --- Create publication-ready tables with rich formatting options +- **plotnine** --- Build beautiful, reproducible visualizations with the grammar of graphics +- **mall** --- Integrate LLM capabilities directly into your data pipelines + +All of these libraries work seamlessly with Polars, so you can stay in the fast, efficient world of Polars from start to finish. Hope you check them out! + +## Learn more + +- [pointblank documentation](https://posit-dev.github.io/pointblank/) +- [Great Tables documentation](https://posit-dev.github.io/great-tables/) +- [plotnine documentation](https://plotnine.org/) +- [mall documentation](https://mlverse.github.io/mall/) + +[^1]: For instructions, please review the [Setting up local LLMs for R and Python](https://posit.co/blog/setting-up-local-llms-for-r-and-python) blog post. diff --git a/content/blog/libraries-for-python-polars/index.qmd b/content/blog/libraries-for-python-polars/index.qmd new file mode 100644 index 000000000..d7b35c346 --- /dev/null +++ b/content/blog/libraries-for-python-polars/index.qmd @@ -0,0 +1,392 @@ +--- +title: "Libraries for Your Python Polars Workflows" +date: "2026-05-28" +people: + - Isabella Velásquez +description: > + Posit's Python libraries provide excellent support for Polars DataFrames across your data science workflow. +image: "images/featured-image.jpg" +image-alt: "A polar bear waving in front of a bookshelf filled with colorful books" +photo: + url: https://unsplash.com/photos/qQWV91TTBrE + author: Hans-Jurgen Mager +topics: + - Data Wrangling + - Visualization +software: + - great-tables + - pointblank + - plotnine + - mall +languages: + - Python +format: hugo-md +jupyter: python3 +filters: + - strip-html-blank-lines +--- + +We (Emil Hvitfeldt, Jeroen Janssens, Michael Chow, and I) just got back from PyCon US 2026, and there was **so much buzz** around [Polars](https://pola.rs/). What is Polars? Why should I switch to Polars? _How_ do I switch to Polars? + +I mean, just check out the line for the book signing of Jeroen's book, [Python Polars: The Definitive Guide](https://polarsguide.com/). + +![A long line of conference attendees waiting at Jeroen's book signing booth in PyCon US' large convention hall](images/book-signing.jpeg) + +If Polars is new to you, it is a library for efficient data manipulation in Python. It's built on Rust, so it's super fast. And a lot of people (including [the creator of Pandas](https://polarsguide.com/praise/)!) like the intuitive way you write Polars code. However, if you work in Python, you might know that different DataFrames have different requirements, so you want to make sure to use libraries that support Polars (I admit, I come from the R world, and this was mind blowing to me). + +And, we're happy to say that we (Posit) have excellent Polars support across our Python libraries for every stage of the data science workflow! In this post, we'll walk through four: + +- [**pointblank**](https://posit-dev.github.io/pointblank/) for data validation and quality checks +- [**Great Tables**](https://posit-dev.github.io/great-tables/articles/intro.html) for creating publication-quality tables +- [**plotnine**](https://plotnine.org/) for ggplot2-style visualizations +- [**mall**](https://mlverse.github.io/mall/) for LLM-powered data analysis + +Let's check them out! + +## Setup + +First, let's install the libraries: + +```{python} +#| eval: false +pip install polars great_tables pointblank plotnine mlverse-mall +``` + +Now, import what we need: + +```{python} +import polars as pl +from great_tables import GT +import pointblank as pb +from plotnine import ( + ggplot, aes, geom_point, geom_line, geom_bar, geom_text, geom_col, + labs, theme_minimal, theme, element_text, scale_fill_manual, + scale_y_continuous, element_rect, element_blank, element_line, + scale_color_manual, position_dodge, annotate +) +import mall +``` + +## The dataset + +We'll demonstrate these tools using `sales_data`, a sample sales dataset: + +```{python} +sales_data = pl.DataFrame({ + "date": ["2026-01-15", "2026-01-16", "2026-01-17", "2026-01-18", + "2026-01-19", "2026-01-20", "2026-01-21"], + "region": ["North", "South", "North", "West", "South", "North", "West"], + "product": ["Widget A", "Widget B", "Widget A", "Widget C", + "Widget B", "Widget A", "Widget C"], + "sales": [1200, 1800, 1500, 2100, 1650, 1900, 2300], + "units_sold": [24, 36, 30, 42, 33, 38, 46], + "customer_rating": [4.5, 4.8, 4.6, 4.9, 4.7, 4.8, 4.9] +}).with_columns( + pl.col("date").str.strptime(pl.Date, "%Y-%m-%d") +) + +sales_data +``` + +We can confirm that it is, indeed, a Polars DataFrame! + +```{python} +isinstance(sales_data, pl.DataFrame) +``` + +## Data validation with pointblank + +Let's now validate our data quality using [**pointblank**](https://posit-dev.github.io/pointblank/): + +```{python} +agent = ( + pb.Validate(sales_data) + .col_vals_not_null(columns="date") + .col_vals_between(columns="sales", left=0, right=10000) + .col_vals_between(columns="customer_rating", left=1.0, right=5.0) + .col_vals_in_set(columns="region", set=["North", "South", "East", "West"]) + .interrogate() +) + +agent +``` + +In natural language, the steps that the agent performs are: + +- Validate the `sales_data` DataFrame +- Make sure that no values in `Date` are null +- Make sure that the values in `sales` are between 0 and 10000 +- Make sure that the values in `customer_rating` are between 1 and 5 +- Make sure that the values in `region` are "North", "South", "East", or "West" +- Now, interrogate! + +The resulting table lets us know for each step what was expected, how many values passed, the percentage of values that passed, and so on. And, the validation agent works directly with Polars DataFrames, no need to convert to pandas! + +Also, about that nifty table that gets output? 👀 **Directly** in this blog post (written in [Quarto](https://quarto.org/))? [That is Great Tables](https://posit-dev.github.io/great-tables/)! But Great Tables isn't just for pointblank... + +## Creating beautiful tables with Great Tables + +Let's summarize some data: + +```{python} +daily_summary = ( + sales_data.group_by("date") + .agg( + [ + pl.col("sales").sum().alias("total_sales"), + pl.col("units_sold").sum().alias("total_units"), + pl.col("customer_rating").mean().alias("avg_rating"), + ] + ) + .sort("date") +) + +regional_summary = ( + sales_data.group_by("region") + .agg( + [ + pl.col("sales").sum().alias("total_sales"), + pl.col("sales").mean().alias("avg_sales"), + pl.col("units_sold").sum().alias("total_units"), + pl.col("sales").alias("sales_trend"), + ] + ) + .sort("total_sales", descending=True) +) +``` + +Let's present our regional summary in a ✨publication-quality table✨ using **Great Tables**: + +```{python} +from great_tables import loc, style + +( + GT(regional_summary) + .tab_header( + title="Regional Sales Performance", + subtitle="Week of January 15-21, 2026" + ) + .fmt_currency( + columns=["total_sales", "avg_sales"], + currency="USD" + ) + .fmt_number( + columns="total_units", + decimals=0, + sep_mark="," + ) + .fmt_nanoplot( + columns="sales_trend", + plot_type="line", + autoscale=True + ) + .cols_label( + region="Region", + total_sales="Total Sales", + avg_sales="Average Sale", + total_units="Units Sold", + sales_trend="Trend" + ) + .data_color( + columns="total_sales", + palette=["#f0f0f0", "#447099"], + domain=[1000, 5000] + ) + .tab_style( + style=style.text(weight="bold"), + locations=loc.body(columns="region") + ) + .tab_style( + style=style.fill(color="#e8f4f8"), + locations=loc.body(rows=[0]) + ) + .tab_source_note("Data validated with pointblank · Trend shows daily sales pattern") + .tab_options( + table_font_size="14px", + heading_title_font_size="18px", + heading_subtitle_font_size="14px" + ) +) +``` + +In this example, Great Tables: + +- Adds a title using `tab_header` +- Formats currency using `fmt_currency` +- Formats numbers using `fmt_number` +- Creates a nanoplot (a miniature line chart) using `fmt_nanoplot` +- Labels the columns using `cols_label` +- Edit color, styling, and font sizes with `data_color`, `tab_style`, and `tab_options` +- Add a source note using `tab_source_note` + +All with full Polars support! In fact, Great Tables is the [default way to style Polars DataFrames](https://docs.pola.rs/user-guide/misc/styling/), using `df.style`. + +## Visualizations with plotnine + +For visualizations, [**plotnine**](https://plotnine.org/) brings the [grammar of graphics](https://en.wikipedia.org/wiki/Wilkinson%27s_Grammar_of_Graphics) to Python. Let's create some nice-looking plots: + +### Daily sales trend + +```{python} +#| fig-alt: "Line chart showing daily sales from January 15-21, 2026. Sales increase from around $1,900 to $2,300 over the week, with values labeled on each data point." +( + ggplot(daily_summary, aes(x="date", y="total_sales")) + + geom_line(color="#447099", size=1.5) + + geom_point(color="#447099", size=4, fill="white", stroke=1.5) + + geom_text( + aes(label="total_sales"), + va="bottom", + nudge_y=100, + size=9, + color="#333333", + format_string="${:,.0f}" + ) + + scale_y_continuous( + labels=lambda l: [f"${x:,.0f}" for x in l], + limits=(1000, 2600), + expand=(0, 0) + ) + + labs( + title="Daily Sales Trend", + subtitle="Week of January 15-21, 2026 • Total revenue trending upward", + x="", + y="" + ) + + theme_minimal() + + theme( + plot_title=element_text(size=16, weight="bold", color="#2c3e50"), + plot_subtitle=element_text(size=11, color="#7f8c8d", margin={"b": 15}), + axis_title_y=element_blank(), + axis_text_y=element_text(size=10, color="#666666"), + axis_text_x=element_text(size=10, color="#666666"), + panel_grid_major_x=element_blank(), + panel_grid_minor=element_blank(), + panel_grid_major_y=element_line(color="#e0e0e0", size=0.5), + plot_background=element_rect(fill="white"), + panel_background=element_rect(fill="white"), + figure_size=(8, 6) + ) +) +``` + +### Sales by region and product + +```{python} +#| fig-alt: "Grouped bar chart showing sales performance by region (North, South, West) and product (Widget A, B, C). Bars are color-coded by product with Widget A in blue, Widget B in green, and Widget C in rust. West region shows highest sales, particularly for Widget C at approximately $2,300." +# Custom color palette with Posit-inspired colors +product_colors = { + "Widget A": "#447099", # Blue + "Widget B": "#72994e", # Green + "Widget C": "#c65d47", # Rust +} + +( + ggplot(sales_data, aes(x="region", y="sales", fill="product")) + + geom_col(position=position_dodge(width=0.8), width=0.7) + + scale_fill_manual(values=product_colors) + + scale_y_continuous( + labels=lambda l: [f"${x:,.0f}" for x in l], + limits=(0, 2500), + breaks=range(0, 2501, 500), + expand=(0, 0), + ) + + labs( + title="Sales Performance by Region", + subtitle="Product comparison across geographic markets", + x="", + y="", + fill="", + ) + + theme_minimal() + + theme( + plot_title=element_text(size=16, weight="bold", color="#2c3e50"), + plot_subtitle=element_text(size=11, color="#7f8c8d", margin={"b": 15}), + axis_title=element_blank(), + axis_text_y=element_text(size=10, color="#666666"), + axis_text_x=element_text(size=11, color="#333333", weight="bold"), + legend_position="top", + legend_title=element_blank(), + legend_text=element_text(size=10), + legend_box_margin=0, + panel_grid_major_x=element_blank(), + panel_grid_minor=element_blank(), + panel_grid_major_y=element_line(color="#e0e0e0", size=0.5), + plot_background=element_rect(fill="white"), + panel_background=element_rect(fill="white"), + figure_size=(8, 6), + ) +) +``` + +Plotnine works seamlessly with Polars DataFrames, no conversion needed! These visualizations can include: + +- Values displayed directly on points for easy reading with `geom_text` +- Currency labels, appropriate limits, and controlled breaks with `scale_y_continuous` +- Larger, bolder titles with subtle subtitle styling with `theme` +- Pure white backgrounds with subtle gray gridlines with `theme_minimal` (my favorite built-in theme) + +Again, with full Polars support. There's more about it in the [Polars documentation for visualization](https://docs.pola.rs/user-guide/misc/visualization/). + +## AI-powered insights with mall + +Finally, let's use [**mall**](https://mlverse.github.io/mall/) to add LLM-powered analysis to our workflow. I used [Ollama](https://ollama.com/) [^1] with a local model, but mall works with OpenAI, Anthropic, and other providers through the [chatlas](https://github.com/cpsievert/chatlas) package. + +[^1]: For instructions, please review the [Setting up local LLMs for R and Python](https://posit.co/blog/setting-up-local-llms-for-r-and-python) blog post. + +Mall extends Polars DataFrames with an `.llm` accessor that provides natural language operations. We can use mall to add natural language descriptions to our sales data, rating the performance of each row as "low", "medium", or "high": + +```{python} +sales_data.llm.use("ollama", "llama3.2") + +sales_with_performance = sales_data.llm.classify( + "sales", + ["high", "medium", "low"], + pred_name="performance", +) + +sales_with_performance.select( + ["date", "region", "product", "sales", "performance"] +) +``` + +Or we can generate custom descriptions for each product: + +```{python} +sales_with_description = sales_data.llm.custom( + "product", + pred_name="description", + prompt="Create a brief, compelling marketing description for this product in 10 words or less", +) + +with pl.Config(fmt_str_lengths=200): + print(sales_with_description.select(["product", "description"])) +``` + +Mall has a bunch of other powerful operations you can use: + +- `.llm.classify()` — Categorize data into predefined labels +- `.llm.sentiment()` — Analyze sentiment (positive/negative/neutral) +- `.llm.summarize()` — Condense text columns to key points +- `.llm.extract()` — Pull specific information from text +- `.llm.translate()` — Convert text to another language +- `.llm.verify()` — Check if statements are supported by data + +And not surprisingly, mall keeps everything in Polars format, which means fast, AI-enhanced data operations that fit naturally into your Polars pipelines. + +## Wrapping up + +The Python data ecosystem has embraced Polars, and so has Posit! These four libraries show how we can build complete data workflows without ever leaving the Polars DataFrame format: + +- **pointblank** — Ensure your data quality before analysis begins +- **Great Tables** — Create publication-ready tables with rich formatting options +- **plotnine** — Build beautiful, reproducible visualizations with the grammar of graphics +- **mall** — Integrate LLM capabilities directly into your data pipelines + +All of these libraries work seamlessly with Polars, so you can stay in the fast, efficient world of Polars from start to finish. Hope you check them out! + +## Learn more + +- [pointblank documentation](https://posit-dev.github.io/pointblank/) +- [Great Tables documentation](https://posit-dev.github.io/great-tables/) +- [plotnine documentation](https://plotnine.org/) +- [mall documentation](https://mlverse.github.io/mall/) diff --git a/content/blog/libraries-for-python-polars/index_files/figure-markdown_strict/cell-10-output-1.png b/content/blog/libraries-for-python-polars/index_files/figure-markdown_strict/cell-10-output-1.png new file mode 100644 index 000000000..b7245b065 Binary files /dev/null and b/content/blog/libraries-for-python-polars/index_files/figure-markdown_strict/cell-10-output-1.png differ diff --git a/content/blog/libraries-for-python-polars/index_files/figure-markdown_strict/cell-9-output-1.png b/content/blog/libraries-for-python-polars/index_files/figure-markdown_strict/cell-9-output-1.png new file mode 100644 index 000000000..5b73b01a8 Binary files /dev/null and b/content/blog/libraries-for-python-polars/index_files/figure-markdown_strict/cell-9-output-1.png differ diff --git a/content/blog/libraries-for-python-polars/requirements.txt b/content/blog/libraries-for-python-polars/requirements.txt new file mode 100644 index 000000000..7fad4bc79 --- /dev/null +++ b/content/blog/libraries-for-python-polars/requirements.txt @@ -0,0 +1,149 @@ +annotated-types==0.7.0 +anyio==4.13.0 +appnope==0.1.4 +argon2-cffi==25.1.0 +argon2-cffi-bindings==25.1.0 +arrow==1.4.0 +asttokens==3.0.1 +async-lru==2.3.0 +attrs==26.1.0 +babel==2.18.0 +beautifulsoup4==4.14.3 +bleach==6.3.0 +certifi==2026.5.20 +cffi==2.0.0 +charset-normalizer==3.4.7 +chatlas==0.18.1 +click==8.4.1 +comm==0.2.3 +commonmark==0.9.1 +contourpy==1.3.3 +coverage==7.14.1 +cycler==0.12.1 +debugpy==1.8.20 +decorator==5.2.1 +defusedxml==0.7.1 +distro==1.9.0 +exceptiongroup==1.3.1 +executing==2.2.1 +faicons==0.2.2 +fastjsonschema==2.21.2 +fonttools==4.63.0 +fqdn==1.5.1 +great-tables==0.21.0 +h11==0.16.0 +htmltools==0.7.0 +httpcore==1.0.9 +httpx==0.28.1 +idna==3.16 +importlib_metadata==8.7.1 +importlib_resources==7.1.0 +iniconfig==2.3.0 +ipykernel==6.31.0 +ipython==8.18.1 +ipython_pygments_lexers==1.1.1 +ipywidgets==8.1.8 +isoduration==20.11.0 +jedi==0.19.2 +Jinja2==3.1.6 +jiter==0.15.0 +json5==0.14.0 +jsonpointer==3.1.1 +jsonschema==4.26.0 +jsonschema-specifications==2025.9.1 +jupyter==1.1.1 +jupyter-console==6.6.3 +jupyter-events==0.12.1 +jupyter-lsp==2.3.1 +jupyter_client==8.6.3 +jupyter_core==5.8.1 +jupyter_server==2.18.2 +jupyter_server_terminals==0.5.4 +jupyterlab==4.5.7 +jupyterlab_pygments==0.3.0 +jupyterlab_server==2.28.0 +jupyterlab_widgets==3.0.16 +kiwisolver==1.5.0 +lark==1.3.1 +markdown-it-py==4.2.0 +MarkupSafe==3.0.3 +matplotlib==3.10.9 +matplotlib-inline==0.2.1 +mdurl==0.1.2 +mistune==3.2.1 +mizani==0.14.4 +mlverse-mall==0.2.0 +narwhals==2.21.2 +nbclient==0.10.4 +nbconvert==7.17.1 +nbformat==5.10.4 +nest-asyncio==1.6.0 +notebook==7.5.6 +notebook_shim==0.2.4 +numpy==2.4.6 +ollama==0.6.2 +openai==2.38.0 +orjson==3.11.9 +packaging==26.0 +pandas==3.0.3 +pandocfilters==1.5.1 +parso==0.8.6 +patsy==1.0.2 +pexpect==4.9.0 +pillow==12.2.0 +platformdirs==4.4.0 +plotnine==0.15.4 +pluggy==1.6.0 +pointblank==0.24.0 +polars==1.40.1 +polars-runtime-32==1.40.1 +prometheus_client==0.25.0 +prompt_toolkit==3.0.52 +psutil==7.2.2 +ptyprocess==0.7.0 +pure_eval==0.2.3 +pyarrow==24.0.0 +pycparser==3.0 +pydantic==2.13.4 +pydantic_core==2.46.4 +Pygments==2.20.0 +pyparsing==3.3.2 +pytest==9.0.3 +pytest-cov==7.1.0 +pytest-html==4.2.0 +pytest-metadata==3.1.1 +python-dateutil==2.9.0.post0 +python-json-logger==4.1.0 +PyYAML==6.0.3 +pyzmq==27.1.0 +referencing==0.37.0 +requests==2.34.2 +rfc3339-validator==0.1.4 +rfc3986-validator==0.1.1 +rfc3987-syntax==1.1.0 +rich==15.0.0 +rpds-py==0.30.0 +scipy==1.17.1 +Send2Trash==2.1.0 +setuptools==82.0.1 +six==1.17.0 +sniffio==1.3.1 +soupsieve==2.8.4 +stack-data==0.6.3 +statsmodels==0.14.6 +terminado==0.18.1 +tinycss2==1.4.0 +tornado==6.5.5 +tqdm==4.67.3 +traitlets==5.14.3 +typing-inspection==0.4.2 +typing_extensions==4.15.0 +tzdata==2026.2 +uri-template==1.3.0 +urllib3==2.7.0 +wcwidth==0.6.0 +webcolors==25.10.0 +webencodings==0.5.1 +websocket-client==1.9.0 +widgetsnbextension==4.0.15 +zipp==3.23.0