文本分类

Snowflake 生成式 AI 入门

James Cha-Earley

Senior Developer Advocate, Snowflake

文本分类的挑战

问题

评论可能包含任何信息

手动分类耗时，且无法扩展

解决方案

使用 Snowflake Cortex 自动化！

classify_text()

定义类别

# Define categories
categories = ["overall_experience", "location", "staff", "food_beverages",
              "facilities"]

文本分类

from snowflake.cortex import classify_text


category = classify_text(
    str_input="The check-in was smooth and the staff were very friendly.",
    categories=categories
)


print(category)

{  
  "label": "staff"  
}

将输出转换为字典

print(type(category))

<class 'str'>

import json

category_dict = json.loads(category)
print(type(category_dict))

<class 'dict'>

扩展工作流

针对指定月份对评论进行分类的流水线

# Python code
month = 5

-- SQL query
SELECT *
FROM HOTELS.REVIEWS
WHERE EXTRACT(month FROM date) = '{{month}}'

应用 classify_text()

df = dataframe_1.to_pandas()


def classification(text):
    result = classify_text(
        str_input=text,
        categories=labels
    )
    result_dict = json.loads(result)
    return result_dict["label"]

应用 classify_text()

# Apply classification to the DataFrame
df["category"] = reviews["DESCRIPTION"].apply(classification)


# Print the first row's predicted category
print(df["category"].head(1))

0    overall_experience  
Name: category, dtype: object

情感分析

只需关心评论情感

在 SQL 单元格中使用 AI_SENTIMENT

情感分析

AI_SENTIMENT - 提取情感

可用情感标签：positive、negative、neutral、mixed 和 unknown

让我们一起练习吧！

Snowflake 生成式 AI 入门