Use ai.classify with pandas

The ai.classify function categorizes each input row by using the labels you provide.

Note

Overview

The ai.classify function extends the pandas Series class. To assign user-provided labels to each input row, call the function on a text column of a pandas DataFrame.

The function returns a pandas Series that contains classification labels, which can be stored in a new DataFrame column.

Tip

We recommend using the ai.classify function with at least two input labels.

Syntax

df["classification"] = df["input"].ai.classify("category1", "category2", "category3")

Parameters

Name Description
labels
Required		 One or more strings that represent the set of classification labels to match to input text values.

Returns

The function returns a pandas Series that contains a classification label for each input text row. If a text value can't be classified, the corresponding label is null.

Example

# This code uses AI. Always review output for mistakes.

df = pd.DataFrame([
        "This duvet, lovingly hand-crafted from all-natural fabric, is perfect for a good night's sleep.",
        "Tired of friends judging your baking? With these handy-dandy measuring cups, you'll create culinary delights.",
        "Enjoy this *BRAND NEW CAR!* A compact SUV perfect for the professional commuter!"
    ], columns=["descriptions"])

df["category"] = df['descriptions'].ai.classify("kitchen", "bedroom", "garage", "other")
display(df)

Output:

Screenshot of a data frame with 'descriptions' and 'category' columns. The 'category' column lists each description’s category name.

Multimodal input

To classify images, PDFs, or text files, set column_type="path" when the input column contains file path strings. For supported file types and setup, see Use multimodal input with AI Functions.

# This code uses AI. Always review output for mistakes.

file_path_series = aifunc.list_file_paths("/lakehouse/default/Files")
custom_df = pd.DataFrame({"file_path": file_path_series})

custom_df["highest_degree"] = custom_df["file_path"].ai.classify(
    "Master", "PhD", "Bachelor", "Other",
)
display(custom_df)

Note

When you use aifunc.list_file_paths() to create your file path column, the returned yarl.URL objects are automatically detected as file paths. You only need to specify column_type="path" when your column contains plain string URLs.

You can also use aifunc.load to ingest files into a DataFrame, then classify the file-path column:

# This code uses AI. Always review output for mistakes.

df, schema = aifunc.load("/lakehouse/default/Files")
df["category"] = df["file_path"].ai.classify("Master", "PhD", "Bachelor", "Other")
display(df)

When you use aifunc.load, the file-path column contains yarl.URL objects that are automatically detected. For plain string URLs, set column_type="path".

Related content

  • Last updated on