AI 功能：利用大型語言模型大規模轉換資料

# Required imports
import synapse.ml.aifunc as aifunc
import pandas as pd

import synapse.ml.spark.aifunc as aifunc

# SparkSession with accessor `spark` in PySpark environments is pre-setup and available for use

你不需要初始化。

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

df = pd.DataFrame([
        "The cleaning spray permanently stained my beautiful kitchen counter. Never again!",
        "I used this sunscreen on my vacation to Florida, and I didn't get burned at all. Would recommend.",
        "I'm torn about this speaker system. The sound was high quality, though it didn't connect to my roommate's phone.",
        "The umbrella is OK, I guess."
    ], columns=["reviews"])

df["sentiment"] = df["reviews"].ai.analyze_sentiment()
display(df)

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

df = spark.createDataFrame([
        ("The cleaning spray permanently stained my beautiful kitchen counter. Never again!",),
        ("I used this sunscreen on my vacation to Florida, and I didn't get burned at all. Would recommend.",),
        ("I'm torn about this speaker system. The sound was high quality, though it didn't connect to my roommate's phone.",),
        ("The umbrella is OK, I guess.",)
    ], ["reviews"])

sentiment = df.ai.analyze_sentiment(input_col="reviews", output_col="sentiment")
display(sentiment)

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

WITH df AS (
    SELECT *
    FROM ( VALUES
        ('The cleaning spray permanently stained my beautiful kitchen counter. Never again!'),
        ('I used this sunscreen on my vacation to Florida, and I didn''t get burned at all. Would recommend.'),
        ('I''m torn about this speaker system. The sound was high quality, though it didn''t connect to my roommate''s phone.'),
        ('The umbrella is OK, I guess.')
    ) AS df(reviews)
)
SELECT 
    reviews,
    ai_analyze_sentiment(reviews) AS sentiment
FROM df;

# 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)

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

df = spark.createDataFrame([
        ("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!",)
    ], ["descriptions"])
    
categories = df.ai.classify(labels=["kitchen", "bedroom", "garage", "other"], input_col="descriptions", output_col="categories")
display(categories)

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

WITH df AS (
    SELECT *
    FROM ( VALUES
        ('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!')
    ) AS df(descriptions)
)
SELECT 
    descriptions,
    ai_classify(descriptions, 'kitchen', 'bedroom', 'garage', 'other') AS categories
FROM df

# 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["embed"] = df["descriptions"].ai.embed()
display(df)

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

df = spark.createDataFrame([
        ("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!",) 
    ], ["descriptions"])

embed = df.ai.embed(input_col="descriptions", output_col="embed")
display(embed)

AI_EMBED() T-SQL 中沒有。

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

df = pd.DataFrame([
        "MJ Lee lives in Tucson, AZ, and works as a software engineer for Microsoft.",
        "Kris Turner, a nurse at NYU Langone, is a resident of Jersey City, New Jersey."
    ], columns=["descriptions"])

df_entities = df["descriptions"].ai.extract("name", "profession", "city")
display(df_entities)

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

df = spark.createDataFrame([
        ("MJ Lee lives in Tucson, AZ, and works as a software engineer for Microsoft.",),
        ("Kris Turner, a nurse at NYU Langone, is a resident of Jersey City, New Jersey.",)
    ], ["descriptions"])

df_entities = df.ai.extract(labels=["name", "profession", "city"], input_col="descriptions")
display(df_entities)

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

WITH df AS (
    SELECT *
    FROM ( VALUES
        ('MJ Lee lives in Tuscon, AZ, and works as a software engineer for Microsoft.'),
        ('Kris Turner, a nurse at NYU Langone, is a resident of Jersey City, New Jersey.')
    ) AS df(descriptions)
)
SELECT 
    descriptions,
    ai_extract(descriptions, 'name', 'profession', 'city') AS properties
FROM df;

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

df = pd.DataFrame([
        "There are an error here.",
        "She and me go weigh back. We used to hang out every weeks.",
        "The big picture are right, but you're details is all wrong."
    ], columns=["text"])

df["corrections"] = df["text"].ai.fix_grammar()
display(df)

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

df = spark.createDataFrame([
        ("There are an error here.",),
        ("She and me go weigh back. We used to hang out every weeks.",),
        ("The big picture are right, but you're details is all wrong.",)
    ], ["text"])

corrections = df.ai.fix_grammar(input_col="text", output_col="corrections")
display(corrections)

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

WITH df AS (
    SELECT *
    FROM ( VALUES
        ('There are an error here.'),
        ('She and me go weigh back. We used to hang out every weeks.'),
        ('The big picture are right, but you''re details is all wrong.')
    ) AS df(text)
)
SELECT 
    text,
    ai_fix_grammar(text) AS corrections
FROM df;

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

df = pd.DataFrame([
        ("Scarves"),
        ("Snow pants"),
        ("Ski goggles")
    ], columns=["product"])

df["response"] = df.ai.generate_response("Write a short, punchy email subject line for a winter sale.")
display(df)

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

df = spark.createDataFrame([
        ("Scarves",),
        ("Snow pants",),
        ("Ski goggles",)
    ], ["product"])

responses = df.ai.generate_response(prompt="Write a short, punchy email subject line for a winter sale.", output_col="response")
display(responses)

WITH df AS (
    SELECT *
    FROM (VALUES
        ('Scarves'),
        ('Snow pants'),
        ('Ski goggles')
    ) AS df(product)
)
SELECT 
    product,
    ai_generate_response('Write a short, punchy email subject line for a winter sale for product ', product) as response
FROM df;

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

df = pd.DataFrame([ 
        ("Bill Gates", "Technology"), 
        ("Satya Nadella", "Healthcare"), 
        ("Joan of Arc", "Agriculture") 
    ], columns=["names", "industries"])
    
df["similarity"] = df["names"].ai.similarity(df["industries"])
display(df)

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

df = spark.createDataFrame([
        ("Bill Gates", "Technology"), 
        ("Satya Nadella", "Healthcare"), 
        ("Joan of Arc", "Agriculture")
    ], ["names", "industries"])

similarity = df.ai.similarity(input_col="names", other_col="industries", output_col="similarity")
display(similarity)

AI_SIMILARITY() T-SQL 中沒有。

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

df= pd.DataFrame([
        ("Microsoft Teams", "2017",
        """
        The ultimate messaging app for your organization—a workspace for real-time 
        collaboration and communication, meetings, file and app sharing, and even the 
        occasional emoji! All in one place, all in the open, all accessible to everyone.
        """),
        ("Microsoft Fabric", "2023",
        """
        An enterprise-ready, end-to-end analytics platform that unifies data movement, 
        data processing, ingestion, transformation, and report building into a seamless, 
        user-friendly SaaS experience. Transform raw data into actionable insights.
        """)
    ], columns=["product", "release_year", "description"])

df["summaries"] = df["description"].ai.summarize()
display(df)

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

df = spark.createDataFrame([
        ("Microsoft Teams", "2017",
        """
        The ultimate messaging app for your organization—a workspace for real-time 
        collaboration and communication, meetings, file and app sharing, and even the 
        occasional emoji! All in one place, all in the open, all accessible to everyone.
        """,),
        ("Microsoft Fabric", "2023",
        """
        An enterprise-ready, end-to-end analytics platform that unifies data movement, 
        data processing, ingestion, transformation, and report building into a seamless, 
        user-friendly SaaS experience. Transform raw data into actionable insights.
        """,)
    ], ["product", "release_year", "description"])

summaries = df.ai.summarize(input_col="description", output_col="summary")
display(summaries)

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

WITH df AS (
    SELECT *
    FROM ( VALUES
        ('Microsoft Teams', '2017', 
        'The ultimate messaging app for your organization—a workspace for real-time collaboration and communication, meetings, file and app sharing, and even the occasional emoji! All in one place, all in the open, all accessible to everyone.'),        
        ('Microsoft Fabric', '2023', 
        'An enterprise-ready, end-to-end analytics platform that unifies data movement, data processing, ingestion, transformation, and report building into a seamless, user-friendly SaaS experience. Transform raw data into actionable insights.')
    ) AS df(product, release_year, description)
)
SELECT 
    product,
    release_year,
    description,
    ai_summarize(description) AS summary
FROM df;

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

df = pd.DataFrame([
        "Hello! How are you doing today?", 
        "Tell me what you'd like to know, and I'll do my best to help.", 
        "The only thing we have to fear is fear itself."
    ], columns=["text"])

df["translations"] = df["text"].ai.translate("spanish")
display(df)

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

df = spark.createDataFrame([
        ("Hello! How are you doing today?",),
        ("Tell me what you'd like to know, and I'll do my best to help.",),
        ("The only thing we have to fear is fear itself.",),
    ], ["text"])

translations = df.ai.translate(to_lang="spanish", input_col="text", output_col="translations")
display(translations)

-- This code uses AI. Always review output for mistakes. 
-- Read terms: https://azure.microsoft.com/support/legal/preview-supplemental-terms/

WITH df AS (
    SELECT *
    FROM ( VALUES
       ('Hello! How are you doing today?'),
        ('Tell me what you''d like to know, and I''ll do my best to help.'),
        ('The only thing we have to fear is fear itself.')
    ) AS df([text])
)
SELECT 
    [text],
    ai_translate([text], 'es') AS translations
FROM df;