Klasifikasi teks

Pengantar Generative AI di Snowflake

James Cha-Earley

Senior Developer Advocate, Snowflake

Tantangan mengklasifikasikan teks

Masalahnya

Ulasan bisa memuat informasi apa pun

Kategorisasi manual memakan waktu dan tidak skalabel

Solusinya

Otomatiskan dengan Snowflake Cortex!

classify_text()

Menetapkan kategori

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

Mengklasifikasikan teks

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"  
}

Mengonversi keluaran ke dictionary

print(type(category))

<class 'str'>

import json

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

<class 'dict'>

Menskalakan alur kerja

Pipeline klasifikasi untuk mengategorikan ulasan pada bulan tertentu

# Python code
month = 5

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

Menerapkan 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"]

Menerapkan 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

Analisis sentimen

Hanya tertarik pada sentimen ulasan

AI_SENTIMENT in a SQL cell

Analisis sentimen

AI_SENTIMENT - mengekstrak sentimen

Sentimen yang tersedia: positive, negative, neutral, mixed, dan unknown

Ayo berlatih!

Pengantar Generative AI di Snowflake