docs: use the new AnalyzeText API in docs(#2126)

microsoft · Nov 10, 2023 · 90ded80 · 90ded80
1 parent 5cd78c9
commit 90ded80
Show file tree

Hide file tree

Showing 3 changed files with 13 additions and 21 deletions.
diff --git a/docs/Explore Algorithms/AI Services/Advanced Usage - Async, Batching, and Multi-Key.ipynb b/docs/Explore Algorithms/AI Services/Advanced Usage - Async, Batching, and Multi-Key.ipynb
@@ -301,7 +301,7 @@
    },
    "outputs": [],
    "source": [
-    "from synapse.ml.services.text import TextSentiment\n",
+    "from synapse.ml.services.language import AnalyzeText\n",
     "\n",
     "# Create a dataframe\n",
     "text_df = spark.createDataFrame(\n",
@@ -314,7 +314,8 @@
     ")\n",
     "\n",
     "sentiment = (\n",
-    "    TextSentiment()\n",
+    "    AnalyzeText()\n",
+    "    .setKind(\"SentimentAnalysis\")\n",
     "    .setTextCol(\"text\")\n",
     "    .setLocation(service_loc)\n",
     "    .setSubscriptionKey(service_key)\n",
@@ -324,7 +325,7 @@
     ")\n",
     "\n",
     "# Show the results of your text query\n",
-    "display(sentiment.transform(text_df).select(\"text\", \"sentiment.document.sentiment\"))"
+    "display(sentiment.transform(text_df).select(\"text\", \"sentiment.documents.sentiment\"))"
    ]
   },
   {
@@ -356,7 +357,6 @@
    },
    "outputs": [],
    "source": [
-    "from synapse.ml.services.text import TextSentiment\n",
     "from pyspark.sql.functions import udf\n",
     "import random\n",
     "\n",

diff --git a/docs/Explore Algorithms/AI Services/Overview.ipynb b/docs/Explore Algorithms/AI Services/Overview.ipynb
@@ -61,7 +61,7 @@
     "\n",
     "\n",
     "### Language\n",
-    "[**Text Analytics**](https://azure.microsoft.com/services/cognitive-services/text-analytics/)\n",
+    "[**AI Language**](https://azure.microsoft.com/products/ai-services/ai-language)\n",
     "- Language detection: detects language of the input text ([Scala](https://mmlspark.blob.core.windows.net/docs/1.0.1/scala/com/microsoft/azure/synapse/ml/services/text/LanguageDetector.html), [Python](https://mmlspark.blob.core.windows.net/docs/1.0.1/pyspark/synapse.ml.services.text.html#module-synapse.ml.services.text.LanguageDetector))\n",
     "- Key phrase extraction: identifies the key talking points in the input text ([Scala](https://mmlspark.blob.core.windows.net/docs/1.0.1/scala/com/microsoft/azure/synapse/ml/services/text/KeyPhraseExtractor.html), [Python](https://mmlspark.blob.core.windows.net/docs/1.0.1/pyspark/synapse.ml.services.text.html#module-synapse.ml.services.text.KeyPhraseExtractor))\n",
     "- Named entity recognition: identifies known entities and general named entities in the input text ([Scala](https://mmlspark.blob.core.windows.net/docs/1.0.1/scala/com/microsoft/azure/synapse/ml/services/text/NER.html), [Python](https://mmlspark.blob.core.windows.net/docs/1.0.1/pyspark/synapse.ml.services.text.html#module-synapse.ml.services.text.NER))\n",
@@ -194,7 +194,7 @@
    "source": [
     "## Perform sentiment analysis on text\n",
     "\n",
-    "The [Text Analytics](https://azure.microsoft.com/services/ai-services/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."
+    "The [AI Language](https://azure.microsoft.com/products/ai-services/ai-language/) 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."
    ]
   },
   {
@@ -215,7 +215,8 @@
     "\n",
     "# Run the Text Analytics service with options\n",
     "sentiment = (\n",
-    "    TextSentiment()\n",
+    "    AnalyzeText()\n",
+    "    .setKind(\"SentimentAnalysis\")\n",
     "    .setTextCol(\"text\")\n",
     "    .setLocation(service_loc)\n",
     "    .setSubscriptionKey(service_key)\n",
@@ -227,7 +228,7 @@
     "# Show the results of your text query in a table format\n",
     "display(\n",
     "    sentiment.transform(df).select(\n",
-    "        \"text\", col(\"sentiment.document.sentiment\").alias(\"sentiment\")\n",
+    "        \"text\", col(\"sentiment.documents.sentiment\").alias(\"sentiment\")\n",
     "    )\n",
     ")"
    ]

diff --git a/docs/Get Started/Quickstart - Your First Models.ipynb b/docs/Get Started/Quickstart - Your First Models.ipynb
@@ -147,25 +147,16 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {
-    "application/vnd.databricks.v1+cell": {
-     "inputWidgets": {},
-     "nuid": "f22b1c1a-b0c9-43e9-bcb0-b29624b4a76a",
-     "showTitle": false,
-     "title": ""
-    },
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
-    "from synapse.ml.services.text import TextSentiment\n",
+    "from synapse.ml.services.language import AnalyzeText\n",
     "from synapse.ml.core.platform import find_secret\n",
     "\n",
-    "model = TextSentiment(\n",
+    "model = AnalyzeText(\n",
     "    textCol=\"text\",\n",
     "    outputCol=\"sentiment\",\n",
+    "    kind=\"SentimentAnalysis\",\n",
     "    subscriptionKey=find_secret(\n",
     "        secret_name=\"ai-services-api-key\", keyvault=\"mmlspark-build-keys\"\n",
     "    ),  # Replace the call to find_secret with your key as a python string.\n",