Anomaly Detection
Copyright 2025 Google LLC.
Anomaly detection with embeddings
| ⚠️ |
This notebook requires paid tier rate limits to run properly.
|
Overview
This tutorial demonstrates how to use the embeddings from the Gemini API to detect potential outliers in your dataset. You will visualize a subset of the 20 Newsgroup dataset using t-SNE{:.external} and detect outliers outside a particular radius of the central point of each categorical cluster.
For more information on getting started with embeddings generated from the Gemini API, check out the Get Started.
Prerequisites
You can run this quickstart in Google Colab.
To complete this quickstart on your own development environment, ensure that your envirmonement meets the following requirements:
- Python 3.11+
- An installation of
jupyterto run the notebook.
Setup
First, download and install the Gemini API Python library.
Grab an API Key
Before you can use the Gemini API, you must first obtain an API key. If you don't already have one, create a key with one click in Google AI Studio.
In Colab, add the key to the secrets manager under the "🔑" in the left panel. Give it the name GEMINI_API_KEY.
Once you have the API key, pass it to the SDK. You can do this in two ways:
- Put the key in the
GEMINI_API_KEYenvironment variable (the SDK will automatically pick it up from there). - Pass the key to
genai.Client(api_key=...)
Key Point: Next, you will choose a model. Any embedding model will work for this tutorial, but for real applications it's important to choose a specific model and stick with it. The outputs of different models are not compatible with each other.
models/embedding-001 models/text-embedding-004 models/gemini-embedding-exp-03-07 models/gemini-embedding-exp models/gemini-embedding-001
Select the model to be used
Prepare the dataset
The 20 Newsgroups Text Dataset{:.external} contains 18,000 newsgroups posts on 20 topics divided into training and test sets. The split between the training and test datasets are based on messages posted before and after a specific date. This tutorial uses the training subset.
['alt.atheism', , 'comp.graphics', , 'comp.os.ms-windows.misc', , 'comp.sys.ibm.pc.hardware', , 'comp.sys.mac.hardware', , 'comp.windows.x', , 'misc.forsale', , 'rec.autos', , 'rec.motorcycles', , 'rec.sport.baseball', , 'rec.sport.hockey', , 'sci.crypt', , 'sci.electronics', , 'sci.med', , 'sci.space', , 'soc.religion.christian', , 'talk.politics.guns', , 'talk.politics.mideast', , 'talk.politics.misc', , 'talk.religion.misc']
Here is the first example in the training set.
Lines: 15 I was wondering if anyone out there could enlighten me on this car I saw the other day. It was a 2-door sports car, looked to be from the late 60s/ early 70s. It was called a Bricklin. The doors were really small. In addition, the front bumper was separate from the rest of the body. This is all I know. If anyone can tellme a model name, engine specs, years of production, where this car is made, history, or whatever info you have on this funky looking car, please e-mail. Thanks, - IL ---- brought to you by your neighborhood Lerxst ----
Next, sample some of the data by taking 150 data points in the training dataset and choosing a few categories. This tutorial uses the science categories.
/tmp/ipykernel_100019/406673449.py:4: FutureWarning: DataFrameGroupBy.apply operated on the grouping columns. This behavior is deprecated, and in a future version of pandas the grouping columns will be excluded from the operation. Either pass `include_groups=False` to exclude the groupings or explicitly select the grouping columns after groupby to silence this warning. .apply(lambda x: x.sample(SAMPLE_SIZE))
Class Name ,sci.crypt 150 ,sci.electronics 150 ,sci.med 150 ,sci.space 150 ,Name: count, dtype: int64
Generate the embeddings
In this section, you will see how to generate embeddings for the different texts in the dataframe using the embeddings from the Gemini API.
The Gemini embedding model supports several task types, each tailored for a specific goal. Here’s a general overview of the available types and their applications:
| Task Type | Description |
|---|---|
| RETRIEVAL_QUERY | Specifies the given text is a query in a search/retrieval setting. |
| RETRIEVAL_DOCUMENT | Specifies the given text is a document in a search/retrieval setting. |
| SEMANTIC_SIMILARITY | Specifies the given text will be used for Semantic Textual Similarity (STS). |
| CLASSIFICATION | Specifies that the embeddings will be used for classification. |
| CLUSTERING | Specifies that the embeddings will be used for clustering. |
100%|██████████| 600/600 [06:11<00:00, 1.62it/s]
Dimensionality reduction
The dimension of the document embedding vector is 3072. In order to visualize how the embedded documents are grouped together, you will need to apply dimensionality reduction as you can only visualize the embeddings in 2D or 3D space. Contextually similar documents should be closer together in space as opposed to documents that are not as similar.
3072
(600, 3072)
You will apply the t-Distributed Stochastic Neighbor Embedding (t-SNE) approach to perform dimensionality reduction. This technique reduces the number of dimensions, while preserving clusters (points that are close together stay close together). For the original data, the model tries to construct a distribution over which other data points are "neighbors" (e.g., they share a similar meaning). It then optimizes an objective function to keep a similar distribution in the visualization.
Text(0, 0.5, 'TSNE2')
Outlier detection
To determine which points are anomalous, you will determine which points are inliers and outliers. Start by finding the centroid, or location that represents the center of the cluster, and use the distance to determine the points that are outliers.
Start by getting the centroid of each category.
Plot each centroid you have found against the rest of the points.
Choose a radius. Anything beyond this bound from the centroid of that category is considered an outlier.
Depending on how sensitive you want your anomaly detector to be, you can choose which radius you would like to use. For now, 0.58 is used, but you can change this value.
Plot the outliers and denote them using a transparent red color.
Text(0, 0.5, 'TSNE2')
Use the index values of the datafames to print a few examples of what outliers can look like in each category. Here, the first data point from each category is printed out. Explore other points in each category to see data that are deemed as outliers, or anomalies.
Electric power line "balls" Article-I.D.: almaden.19930406.142616.248 Lines: 4 Power lines and airplanes don't mix. In areas where lines are strung very high, or where a lot of crop dusting takes place, or where there is danger of airplanes flying into the lines, they place these plastic balls on the lines so they are easier to spot.
LARSONIAN Astronomy and Physics
Organization: University of Wisconsin Eau Claire
Lines: 552
LARSONIAN Astronomy and Physics
Orthodox physicists, astronomers, and astrophysicists
CLAIM to be looking for a "Unified Field Theory" in which all
of the forces of the universe can be explained with a single
set of laws or equations. But they have been systematically
IGNORING or SUPPRESSING an excellent one for 30 years!
The late Physicist Dewey B. Larson's comprehensive
GENERAL UNIFIED Theory of the physical universe, which he
calls the "Reciprocal System", is built on two fundamental
postulates about the physical and mathematical natures of
space and time:
"The physical universe is composed ENTIRELY of ONE
component, MOTION, existing in THREE dimensions, in DISCRETE
UNITS, and in two RECIPROCAL forms, SPACE and TIME."
"The physical universe conforms to the relations of
ORDINARY COMMUTATIVE mathematics, its magnitudes are
ABSOLUTE, and its geometry is EUCLIDEAN."
From these two postulates, Larson developed a COMPLETE
Theoretical Universe, using various combinations of
translational, vibrational, rotational, and vibrational-
rotational MOTIONS, the concepts of IN-ward and OUT-ward
SCALAR MOTIONS, and speeds in relation to the Speed of Light
.
At each step in the development, Larson was able to
MATCH objects in his Theoretical Universe with objects in the
REAL physical universe, , even objects NOT YET
DISCOVERED THEN .
And applying his Theory to his NEW model of the atom,
Larson was able to precisely and accurately CALCULATE inter-
atomic distances in crystals and molecules, compressibility
and thermal expansion of solids, and other properties of
matter.
All of this is described in good detail, with-OUT fancy
complex mathematics, in his books.
BOOKS of Dewey B. Larson
The following is a complete list of the late Physicist
Dewey B. Larson's books about his comprehensive GENERAL
UNIFIED Theory of the physical universe. Some of the early
books are out of print now, but still available through
inter-library loan.
"The Structure of the Physical Universe"
"The Case AGAINST the Nuclear Atom"
"Beyond Newton"
"New Light on Space and Time"
"Quasars and Pulsars"
"NOTHING BUT MOTION"
[A $9.50 SUBSTITUTE for the $8.3 BILLION "Super
Collider".]
[The last four chapters EXPLAIN chemical bonding.]
"The Neglected Facts of Science"
"THE UNIVERSE OF MOTION"
[FINAL SOLUTIONS to most ALL astrophysical
mysteries.]
"BASIC PROPERTIES OF MATTER"
All but the last of these books were published by North
Pacific Publishers, P.O. Box 13255, Portland, OR 97213, and
should be available via inter-library loan if your local
university or public library doesn't have each of them.
Several of them, INCLUDING the last one, are available
from: The International Society of Unified Science ,
1680 E. Atkin Ave., Salt Lake City, Utah 84106. This is the
organization that was started to promote Larson's Theory.
They have other related publications, including the quarterly
journal "RECIPROCITY".
Physicist Dewey B. Larson's Background
Physicist Dewey B. Larson was a retired Engineer
. He was about 91 years old when he
died in May 1989. He had a Bachelor of Science Degree in
Engineering Science from Oregon State University. He
developed his comprehensive GENERAL UNIFIED Theory of the
physical universe while trying to develop a way to COMPUTE
chemical properties based only on the elements used.
Larson's lack of a fancy "PH.D." degree might be one
reason that orthodox physicists are ignoring him, but it is
NOT A VALID REASON. Sometimes it takes a relative outsider
to CLEARLY SEE THE FOREST THROUGH THE TREES. At the same
time, it is clear from his books that he also knew ORTHODOX
physics and astronomy as well as ANY physicist or astronomer,
Next steps
You've now created an anomaly detector using embeddings! Try using your own textual data to visualize them as embeddings, and choose some bound such that you can detect outliers. You can perform dimensionality reduction in order to complete the visualization step. Note that t-SNE is good at clustering inputs, but can take a longer time to converge or might get stuck at local minima.
To learn how to use other services in the Gemini API, see the Get started guide.