Skip to main content
Version: 0.11.1

First Example


Get started

To get started, import and configurate service keys.

from import *
from notebookutils import mssparkutils

# A general Cognitive Services key for Text Analytics and Computer Vision (or use separate keys that belong to each service)
cognitive_service_key = mssparkutils.credentials.getSecret("ADD_YOUR_KEY_VAULT_NAME", "ADD_YOUR_SERVICE_KEY","ADD_YOUR_KEY_VAULT_LINKED_SERVICE_NAME")
# A Bing Search v7 subscription key
bingsearch_service_key = mssparkutils.credentials.getSecret("ADD_YOUR_KEY_VAULT_NAME", "ADD_YOUR_BING_SEARCH_KEY","ADD_YOUR_KEY_VAULT_LINKED_SERVICE_NAME")
# An Anomaly Dectector subscription key
anomalydetector_key = mssparkutils.credentials.getSecret("ADD_YOUR_KEY_VAULT_NAME", "ADD_YOUR_ANOMALY_KEY","ADD_YOUR_KEY_VAULT_LINKED_SERVICE_NAME")

Text analytics sample

The Text Analytics service provides several algorithms for extracting intelligent insights from text. For example, we can find the sentiment of given input text. The service will return a score between 0.0 and 1.0 where low scores indicate negative sentiment and high score indicates positive sentiment. This sample uses three simple sentences and returns the sentiment for each.

from pyspark.sql.functions import col

# Create a dataframe that's tied to it's column names
df_sentences = spark.createDataFrame([
("I'm so happy today, it's sunny!", "en-US"),
("this is a dog", "en-US"),s
("I'm frustrated by this rush hour traffic!", "en-US")
], ["text", "language"])

# Run the Text Analytics service with options
sentiment = (TextSentiment()
.setLocation("eastasia") # Set the location of your cognitive service

# Show the results of your text query in a table format

display(sentiment.transform(df_sentences).select("text", col("sentiment")[0].getItem("sentiment").alias("sentiment")))

Expected results

I'm frustrated by this rush hour traffic!negative
this is a dogneutral
I'm so happy today, it's sunny!positive