turi.com
Introduction
1.
Getting started
2.
Working with data
2.1.
Tabular data
2.1.1.
Loading and Saving
2.1.2.
Data Manipulation
2.1.3.
Spark RDDs
2.1.4.
SQL Databases
2.2.
Graph data
2.3.
Time series data
2.4.
Visualization
2.5.
Feature Engineering
2.5.1.
Numeric Features
2.5.1.1.
Quadratic Features
2.5.1.2.
Feature Binning
2.5.1.3.
Numeric Imputer
2.5.2.
Categorical Features
2.5.2.1.
One Hot Encoder
2.5.2.2.
Count Thresholder
2.5.2.3.
Categorical Imputer
2.5.2.4.
Count Featurizer
2.5.3.
Text Features
2.5.3.1.
TF-IDF
2.5.3.2.
Tokenizer
2.5.3.3.
RareWordTrimmer
2.5.3.4.
BM25
2.5.3.5.
PartOfSpeechExtractor
2.5.3.6.
SentenceSplitter
2.5.4.
Image Features
2.5.4.1.
Deep Feature Extractor
2.5.5.
Other Transformations
2.5.5.1.
Hasher
2.5.5.2.
Random Projection
2.5.5.3.
Transformer Chain
2.5.5.4.
Custom Transformer
3.
Modeling data
3.1.
Classification
3.1.1.
Logistic Regression
3.1.2.
Nearest Neighbor Classifier
3.1.3.
SVM
3.1.4.
Decision Tree Classifier
3.1.5.
Random Forest Classifier
3.1.6.
Boosted Trees Classifier
3.1.7.
Neuralnet Classifier
3.2.
Regression
3.2.1.
Linear Regression
3.2.2.
Decision Tree Regression
3.2.3.
Boosted Trees Regression
3.2.4.
Random Forest Regression
3.3.
Advanced Deep Learning with MXNet
3.4.
Graph analytics
3.4.1.
Examples
3.5.
Clustering
3.5.1.
KMeans
3.5.2.
DBSCAN
3.6.
Nearest Neighbors
3.7.
Text analysis
3.7.1.
Processing text
3.7.2.
Topic models
3.8.
Evaluating Models
3.8.1.
Regression Metrics
3.8.2.
Classification Metrics
3.9.
Model parameter search
3.9.1.
Models
3.9.2.
Choosing a search space
3.9.3.
Evaluation functions
3.9.4.
Distributed execution
4.
Applications
4.1.
Recommender systems
4.1.1.
Using trained models
4.1.2.
Choosing a model
4.2.
Data matching
4.2.1.
Record Linker
4.2.2.
Deduplication
4.2.3.
Autotagger
4.2.4.
Similarity Search
4.3.
Lead Scoring
4.4.
Churn prediction
4.4.1.
Using a trained model
4.4.2.
Alternate input formats
4.4.3.
How it works
4.5.
Frequent Pattern Mining
4.6.
Sentiment analysis
4.6.1.
Applying a sentiment classifier
4.6.2.
Product sentiment analysis and review data
4.7.
Anomaly Detection
4.7.1.
Local Outlier Factor
4.7.2.
Moving Z-Score
4.7.3.
Bayesian Changepoints
5.
Turi Distributed
5.1.
Asynchronous Jobs
5.2.
Installing on Hadoop
5.3.
Clusters
5.4.
End-to-End Example
5.5.
Distributed Job Execution
5.6.
Distributed Machine Learning
5.7.
Monitoring Jobs
5.8.
Session Management
5.9.
Dependencies
6.
Turi Predictive Services
7.
Conclusion
8.
Exercises
8.1.
Tabular data
8.2.
Graph data
8.3.
Graph analytics
8.4.
Classification
8.5.
Text analysis
8.6.
Recommender systems
9.
FAQ/Common Problems
10.
Contributing
Published with GitBook
Turi Machine Learning Platform User Guide
Image features
These feature transformations are useful when you have image data.
Deep Feature Extractor