文字分類

Snowflake 生成式 AI 入門

James Cha-Earley

Senior Developer Advocate, Snowflake

文字分類的挑戰

問題

評論內容可能包含各種資訊

人工分類耗時且無法擴充

解法

用 Snowflake Cortex 自動化！

classify_text()

定義分類類別

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

進行文字分類

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"  
}

將輸出轉為字典

print(type(category))

<class 'str'>

import json

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

<class 'dict'>

擴大量化流程

以分類流程為某月份的評論分群

# Python code
month = 5

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

套用 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"]

套用 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

情緒分析

只關心評論的情緒傾向

在 SQL 儲存格中的 AI_SENTIMENT

情緒分析

AI_SENTIMENT－擷取情緒

可用的情緒：positive、negative、neutral、mixed、unknown

一起來練習吧！

Snowflake 生成式 AI 入門