DOSUG Intro to google prediction api

Oct 20, 20130 likes1,548 views

Gabe and Devon present Regression Analysis using Google Prediction API and numpi. These slides are the Google Prediction API portion. For the rest see https://docs.google.com/presentation/d/1Wtivp7IfUOBxr3wWN0lcw97SQiFkWMLBqgQf_bXgJ0c/edit#slide=id.p10 So you want to predict the future? Oh, just some sentiment analysis, spam detection, stock market predictions? In that case the Google Prediction API is for you. Classification problems, Regression problems. This API is a great tool for any software developer and is easily accessible to anyone who is good with spreadsheets.

Regression Analysis & Prediction
Devon Jones
Lead Systems Engineer, Knewton

Gabe Hamilton
Software Engineering Mgr, Revionics

Tech Confluence
For those who work downtown, check out our
DOSUG inspired group.
meetup.com/TechConfluence
3rd Wednesday of the month
At lunch: 12:30 - 1:30pm

The Plan
1. Regression Analysis

- Devon

2. Google Prediction API - Gabe
3. Applying Regression

- Devon

Google Prediction API

{

{

"label": "awesome",
"score": 0.98

},

"label": "lame",
"score": 0.08

}

Gabe Hamilton

What kind of Prediction?
Predict an output value based on some input
values.
Things like:
Sentiment Analysis, Spam Detection, Today's
temperature, GDP Growth

Well, it's Google
Through an intensive breeding program Google has managed to distribute Punxsutawney Phils
throughout its datacenters across the world. Each Phil is kept in a climate controlled enclosure that
mimics the conditions of a perfectly average February 2nd. A full scale digital sundial maps your
problem domain onto the shadow matrix of the enclosure allowing each Phil to fully interact with
your model. The early spring / long winter emergence probability of each Phil is then sorted and
reduced to determine the final result returned by the prediction API.

No Really, How do they do it?
Short Answer:
I have no idea
Long answer:
It's a service, they can
do whatever works,
swap implementations
run multiple
algorithms

Possible Implementations
Regression Analysis
Neural Networks
Support Vector
Machine
Monte Carlo Sim
Decision Trees
Evolutionary
Algorithms

Basically it is

STATISTICS

Types of Prediction you can do
Regression

Classification

How do inputs cause
an output to vary?

Deciding which bucket
some input belongs in

Output is a numeric
value:
Shopping Cart Size
Stock Price

Buckets are text
values: French,
Spanish, English

Classification
●
●
●
●
●
●
●
●

Sentiment analysis
Spam detection
Language categorization
Tagging
Assign priority to bugs
Predict movie ratings
Message routing decisions
<Your brilliant idea here>

Getting Started
Hello World page is great
https://developers.google.com/prediction/docs/hello_world

Time for some cleanup
90% of the
development time is
data cleanup

Good talk on data
driven projects
http://www.slideshare.
net/ryanweald/building-data-drivenproducts-with-ruby-rubyconf-2012

CSV Input file aka Training Set
First column is expected values.
2nd through N columns are input values
"French", "Je pense donc j'essuie", "Paris"

Output

an input

No header columns

more input
250MB max file size

4 Steps to Prediction
1. Create a CSV file of your training data
2. Create a new Project in the Prediction API
a. requires entering billing info

3. Upload your csv file to Google Storage
4. In Prediction API Browser:
a. insert a new training set (the csv file)
b. view your trained set
c. use trainedmodel.predict to make
predictions
See the hello world for details of the method calls

Storage for datasets
https://storage.cloud.google.com

API Explorer
https://developers.google.com/apis-explorer/#s/prediction/v1.6/

This document describes Infer, a predictive scoring tool that analyzes thousands of external signals about leads and contacts to deliver an accurate predictive score. It can be easily implemented through an API connection without any software or hardware. Using Infer provides benefits to both sales and marketing teams by focusing reps on prioritized leads, uncovering hidden opportunities, and identifying qualified leads faster. Testimonials from several companies cite benefits like doubled conversion rates, 6x higher conversion of top-scoring leads, and 95% of closed deals involving leads identified through Infer's scoring.

2.7 other classifiersKrish_ver2

Lazy learning methods store training data and wait until test data is received to perform classification, taking less time to train but more time to predict. Eager learning methods construct a classification model during training. Lazy methods like k-nearest neighbors use a richer hypothesis space while eager methods commit to a single hypothesis. The k-nearest neighbor algorithm classifies new examples based on the labels of its k closest training examples. Case-based reasoning uses a symbolic case database for classification while genetic algorithms evolve rule populations through crossover and mutation to classify data.

T16 multiple regressionkompellark

This document discusses multiple regression as an intermediate prediction method that allows for one continuous dependent variable and two or more usually continuous independent variables. It provides an example of using house feature data like size, bedrooms, bathrooms, etc. to predict house selling prices. It also discusses using multiple regression to determine appropriate advertising budget levels across categories based on sales data from different college campuses. Finally, it presents results from a multiple regression analyzing factors influencing willingness to purchase genetically modified foods for U.S. and U.K. students.

Chapter 2computerangel85

This document discusses rough set theory, which is used to model vagueness and uncertainty when precise definitions of sets are not possible given available information. Key points: 1. Rough sets use upper and lower approximations to represent sets that cannot be precisely defined based on available knowledge. The lower approximation includes all elements that surely belong to the set, while the upper approximation includes elements that possibly belong. 2. Rough sets have properties like boundary regions that characterize their imprecision. Measures like roughness quantify the degree of uncertainty in approximating sets. 3. Membership in a rough set is characterized by upper and lower membership relations. Properties and examples are provided to illustrate rough set concepts.

Predicting crop yield and response to Nutrients from soil spectra at WCSS 201...CIAT

This document presents a study that uses soil spectroscopy to predict crop yields and response to fertilizers in sub-Saharan Africa. The study collected soil spectra and yield data from plots in Tanzania and Malawi. Statistical models like partial least squares regression and random forest were used to determine how much of the variance in yield and response could be explained by soil spectra alone and in combination with other soil, topographic, and weather data. The models were able to explain up to 65% of the variance in yield, with soil spectra and additional data like rainfall and topography each contributing. The study aims to refine yield predictions and help smallholder farmers apply optimal fertilizer levels based on cheap soil spectral analyses.

2010-11 CIARD - Bridging Rural Digital Divide (Brasil) - EnglishCIARD

Ijetcas14 379Iasir Journals

This document discusses a regression model to predict soybean crop prices in the US based on various factors from 1995 to 2005. It analyzes factors like temperature, precipitation, crop yield, population, food supply, crude oil prices, and export/import quantities. The regression model explains over 90% of the variation in crop prices based on just four key factors, showing a strong relationship between observed and predicted values.

T16 multiple regressionkompellark

This document discusses multiple regression as an intermediate prediction method that allows for one continuous dependent variable and two or more usually continuous independent variables. It provides an example of using house feature data like size, bedrooms, bathrooms, lot size, taxes, etc. to predict house selling prices. A linear regression model is proposed with selling price as the dependent variable and house features as independent variables. Coefficients are estimated to represent the marginal effect of each independent variable on selling price. The document also provides another example using data on advertising expenditures and sales at college campuses to determine optimal advertising budgets.

Regression analysisSubin Raj

Regression analysis is a statistical technique used to determine the relationship between variables. It allows one to predict the value of a dependent variable based on the value of one or more independent variables. The dependent variable is the variable being predicted, while the independent variables are what is used to make the predictions. Regression analysis helps establish functional relationships between variables and is used in business, economics, and other fields to model phenomena and make predictions.

Analysis of crop yield prediction using data mining techniqueseSAT Journals

Abstract Agrarian sector in India is facing rigorous problem to maximize the crop productivity. More than 60 percent of the crop still depends on monsoon rainfall. Recent developments in Information Technology for agriculture field has become an interesting research area to predict the crop yield. The problem of yield prediction is a major problem that remains to be solved based on available data. Data Mining techniques are the better choices for this purpose. Different Data Mining techniques are used and evaluated in agriculture for estimating the future year's crop production. This paper presents a brief analysis of crop yield prediction using Multiple Linear Regression (MLR) technique and Density based clustering technique for the selected region i.e. East Godavari district of Andhra Pradesh in India. Keywords: Agrarian Sector, Crop Production, Data Mining, Density based clustering, Information Technology, Multiple Linear Regression, Yield Prediction.

Predicting the future with Google Prediction APIRadu-Sebastian Amarie

Scale Invariant Feature TranformShanker Naik

SIFT extracts distinctive invariant features from images to enable object recognition despite variations in scale, rotation, and illumination. The algorithm involves: 1) Constructing scale-space images from differences of Gaussians to identify keypoints. 2) Detecting stable local extrema across scales as candidate keypoints. 3) Filtering out low contrast keypoints and those poorly localized along edges. 4) Assigning orientations based on local gradient directions. 5) Computing descriptors by sampling gradients around keypoints for matching between images.

Prediction of house price using multiple regressionvinovk

Data miningMeysam Asadi

روش های داده کاوی Class/Concept Description Characterization the mining of frequent patterns, associations, and correlations itemsets subsequences substructures Classification and Regression decision tree classifiers Bayesian classifiers Bayesian Belief Networks classification using frequent patterns rule-based classifiers lazy learners or nstance-based methods Artificial Neural Networks genetic algorithms Rough sets fuzzy logic techniques Associative Classification Discriminative Frequent Pattern–Based Classification IF-THEN Rules Rule Extraction from a Decision Tree Sequential Covering Algorithm k-Nearest-Neighbor Classifiers Case-Based Reasoning A multilayer perceptron (MLP) Radial basis function network(RBF) Classification by Backpropagation Hopfield network support vector machines(SVM) learning vector quantization (LVQ) k-Means: A Centroid-Based Technique k-Medoids: A Representative Object-Based Technique Self-Organizing map(SOM) ID3- C4.5 -CART- CHAID -C SEP- C-SEP AQ, CN2, RIPPER. Data Are Linearly Separable Data Are Linearly Inseparable Cluster Analysis Partitioning methods Hierarchical methods Density-based methods Grid-based methods Competitive neural networks fuzzy logic techniques k-Means: A Centroid-Based Technique k-Medoids: A Representative Object-Based Technique Self-Organizing map(SOM) AGNES- DIANA- BIRCH- Chameleon DBSCAN- OPTICS- DENCLUE STING- CLIQUE domain expert–provided labels their assumptions regarding normal objects versus outliers. Supervised Semi-Supervised Unsupervised Methods Statistical Methods Proximity-Based Methods Clustering-Based Methods Classification-Based Approaches

Data mining in agricultureSibananda Khatai

The document provides an overview of data mining in agriculture. It discusses the history and evolution of data science and defines key concepts like data mining, knowledge discovery in databases (KDD), and techniques used in data mining like statistics, machine learning, neural networks, and decision trees. The document also reviews applications of data mining in agriculture like crop yield estimation, influence of climate on crops, and spatial pattern analysis. It summarizes several research papers that apply techniques like K-means, KNN, and artificial neural networks to problems in agriculture.

Day 10 prediction and regressionElih Sutisna Yanto

Michal Erel's SIFT presentationwolf

SIFT is a scale-invariant feature transform algorithm used to detect and describe local features in images. It detects keypoints that are invariant to scale, rotation, and partially invariant to illumination and viewpoint changes. The algorithm involves 4 main steps: (1) scale-space extrema detection, (2) keypoint localization, (3) orientation assignment, and (4) keypoint descriptor generation. SIFT descriptors provide a feature vector for each keypoint that is highly distinctive and partially invariant to remaining variations.

Chapter 4 ClassificationKhalid Elshafie

This document provides an overview of classification techniques. It defines classification as assigning records to predefined classes based on their attribute values. The key steps are building a classification model from training data and then using the model to classify new, unseen records. Decision trees are discussed as a popular classification method that uses a tree structure with internal nodes for attributes and leaf nodes for classes. The document covers decision tree induction, handling overfitting, and performance evaluation methods like holdout validation and cross-validation.

Regression Analysisnadiazaheer

The document provides an overview of regression analysis concepts including: - Regression analysis is used to understand relationships between variables and predict the value of one variable based on another. - A regression model has a dependent variable on the y-axis and an independent variable on the x-axis. - Examples of how to perform regression analysis are provided including creating a scatter plot and calculating parameters like the slope and intercept. - Key concepts for measuring the fit of a linear regression model are defined including variability, correlation coefficient, coefficient of determination, and standard error.

Data mining: Classification and predictionDataminingTools Inc

This document discusses various machine learning techniques for classification and prediction. It covers decision tree induction, tree pruning, Bayesian classification, Bayesian belief networks, backpropagation, association rule mining, and ensemble methods like bagging and boosting. Classification involves predicting categorical labels while prediction predicts continuous values. Key steps for preparing data include cleaning, transformation, and comparing different methods based on accuracy, speed, robustness, scalability, and interpretability.

Correlation and Simple RegressionVenkata Reddy Konasani

This document provides an overview of a data analysis course covering various statistical techniques including correlation, regression, hypothesis testing, clustering, and time series analysis. The course covers descriptive statistics, data exploration, probability distributions, simple and multiple linear regression analysis, logistic regression analysis, and model building for credit risk analysis. Notes are provided on correlation calculation and its properties. Assumptions and interpretations of linear regression are also summarized. The document is intended as a high-level overview of topics covered in the course rather than an in-depth treatment.

B0930610IOSR Journals

This document compares two approaches for handling incomplete data and generating decision rules: 1) Rough set theory, which fills missing values and performs attribute reduction, and 2) Random tree classification in data mining, which ignores missing values. It uses a heart disease dataset with missing values to test the approaches in ROSE2 and WEKA. The results show that random tree classification ignoring missing values produces more accurate decision rules than rough set theory filling missing values.

Regression analysis pptElkana Rorio

The document provides an overview of regression analysis. It defines regression analysis as a technique used to estimate the relationship between a dependent variable and one or more independent variables. The key purposes of regression are to estimate relationships between variables, determine the effect of each independent variable on the dependent variable, and predict the dependent variable given values of the independent variables. The document also outlines the assumptions of the linear regression model, introduces simple and multiple regression, and describes methods for model building including variable selection procedures.

Multiple linear regressionJames Neill

Correlation and regressionKhalid Aziz

This document provides an introduction to correlation and regression analysis. It defines correlation as a measure of the association between two variables and regression as using one variable to predict another. The key aspects covered are: - Calculating correlation using Pearson's correlation coefficient r to measure the strength and direction of association between variables. - Performing simple linear regression to find the "line of best fit" to predict a dependent variable from an independent variable. - Using a TI-83 calculator to graphically display scatter plots of data and calculate the regression equation and correlation coefficient.

"r" for ROIAndrea Dodet

#rstats lessons for #measureMark Edmondson

More Related Content

Viewers also liked (20)

2010-11 CIARD - Bridging Rural Digital Divide (Brasil) - EnglishCIARD

Ijetcas14 379Iasir Journals

T16 multiple regressionkompellark

This document discusses multiple regression as an intermediate prediction method that allows for one continuous dependent variable and two or more usually continuous independent variables. It provides an example of using house feature data like size, bedrooms, bathrooms, lot size, taxes, etc. to predict house selling prices. A linear regression model is proposed with selling price as the dependent variable and house features as independent variables. Coefficients are estimated to represent the marginal effect of each independent variable on selling price. The document also provides another example using data on advertising expenditures and sales at college campuses to determine optimal advertising budgets.

Regression analysisSubin Raj

Analysis of crop yield prediction using data mining techniqueseSAT Journals

Predicting the future with Google Prediction APIRadu-Sebastian Amarie

Scale Invariant Feature TranformShanker Naik

Prediction of house price using multiple regressionvinovk

Data miningMeysam Asadi

Data mining in agricultureSibananda Khatai

Day 10 prediction and regressionElih Sutisna Yanto

Michal Erel's SIFT presentationwolf

Chapter 4 ClassificationKhalid Elshafie

Regression Analysisnadiazaheer

Data mining: Classification and predictionDataminingTools Inc

Correlation and Simple RegressionVenkata Reddy Konasani

B0930610IOSR Journals

Regression analysis pptElkana Rorio

Multiple linear regressionJames Neill

Correlation and regressionKhalid Aziz

2010-11 CIARD - Bridging Rural Digital Divide (Brasil) - EnglishCIARD

Ijetcas14 379Iasir Journals

T16 multiple regressionkompellark

Regression analysisSubin Raj

Analysis of crop yield prediction using data mining techniqueseSAT Journals

Predicting the future with Google Prediction APIRadu-Sebastian Amarie

Scale Invariant Feature TranformShanker Naik

Prediction of house price using multiple regressionvinovk

Data miningMeysam Asadi

Data mining in agricultureSibananda Khatai

Day 10 prediction and regressionElih Sutisna Yanto

Michal Erel's SIFT presentationwolf

Chapter 4 ClassificationKhalid Elshafie

Regression Analysisnadiazaheer

Data mining: Classification and predictionDataminingTools Inc

Correlation and Simple RegressionVenkata Reddy Konasani

B0930610IOSR Journals

Regression analysis pptElkana Rorio

Multiple linear regressionJames Neill

Correlation and regressionKhalid Aziz

Similar to DOSUG Intro to google prediction api (20)

"r" for ROIAndrea Dodet

#rstats lessons for #measureMark Edmondson

The Art of Evolutionary Algorithms ProgrammingJuan J. Merelo

Actminds Outsourcing Summit 07cnetto

The document is a presentation by Actminds about the software development and application management services they offer. It summarizes their key services such as integration, quality and productivity metrics, offshore development centers, and success cases with clients like Johnson & Johnson. It promotes Actminds' ability to reduce costs through a combination of offshore and onshore resources while maintaining quality.

Week 4 Assignment - Software Development PlanScenario-Your team has be.docxestefana2345678

Week 4 Assignment - Software Development Plan Scenario: Your team has been tasked with delivering a Section 508-validated application for U.S. Department of Homeland Security field officers to check potential immigrants for connections to criminal or terrorist behavior. This application must meet these requirements: Â· Conform with Section-508 accessibility guidelines. Â· Allow wireless real-time bidirectional data transfer and database queries with secure servers. Â· Have a secure login and, after two minutes of non-use, have autolocking that reactivates a secure login. Â· Allow for officers working on any day and at any time in offices, from vehicles, and on foot along the U.S. border and in cities across the country. Overview In Week 2, you defined how you will determine user applicability and needs. This week, you will map out a plan for your project. Instructions: Create a 2â€“3-page software development plan for the application you are developing. Include the following: Â· List 8â€“10 steps the project will follow from proposal to post-implementation stages for proper design of the application. Be sure to account for all application constraints in the project planning steps. Â· Explain the outcome, process, and resources involved in accomplishing each step. Incorporate at least 3 credible and relevant resources to support your statements. Â· Create a Gantt chart that includes each step in the process, the resources involved, and the estimated duration of time it will take to complete each step. It is recommended that you use Microsoft Excel to create your chart. You may copy and paste it into your software development plan document or submit a separate file. Â· Remember, your audience is your companyâ€™s IT executive. Your writing should be professional and free of grammar, punctuation, and spelling errors. Figure 1. The evolution of the Waterfall Model (a) and its long development cycles (analysis, design, implementation, test) to the shorter, iterative development cycles within, for example, the Spiral Model (b) to Extreme Programmingâ€™s (c) blending of all these activities, a little at a time, throughout the entire software development process. 0018-9162/99/$10.00 Â© 1999 IEEE70 Computer I n the beginning was the waterfall (Figure 1a). We would get the users to tell us once and for all exactly what they wanted. We would design the system that would deliver those features. We would code it. We would test to make sure the features were delivered. All would be well. All was not well. The users didnâ€™t tell us once and for all exactly what they wanted. They didnâ€™t know. They contradicted themselves. They changed their minds. And the users werenâ€™t the only problem. We programmers could think we were making great progress only to discover three-fourths of the way through that we were one-third of the way through. If long development cycles were bad because they couldnâ€™t adapt to changes, perhaps what we needed was to make shorter.

2013 04 prime guideDroidcon Berlin

This document summarizes a presentation about the Prime Guide TV guide app. It discusses the app's architecture including its use of libraries and backend on Google App Engine. It also reviews the app's initial release, marketing efforts, user feedback, and lessons learned. Key points include a successful beta launch, focus on top requested features like search and reminders, and importance of timely customer support and releasing early for feedback.

Droidcon thessaloniki 2015Raymond Chenon

Data Analytic s (Unit -1).pRESENTATION .PPTGayathriShiva4

Meet a 100% R-based CRO - The summary of a 5-year journeyAdrian Olszewski

This document summarizes a 5-year journey of using R as the sole statistical analysis software at a CRO. Some key points: - Initially there were questions around whether R would be sufficient, what hidden costs there may be to using open source software, how to validate and organize the working environment, and which packages would be needed. - After 5 years of experience, the CRO found that R mostly sufficed for their work but using open source "is not free" as time must be spent collecting tools, validating them, dealing with package failures, and reporting issues. This amounts to costs equivalent to commercial software licenses. - The CRO developed a simple, automated, template-based workflow

Meet a 100% R-based CRO. The summary of a 5-year journeyAdrian Olszewski

This document summarizes a 5-year journey of using R as the sole statistical programming language at a CRO. It discusses initial concerns about relying entirely on open-source R, the hidden costs of using free software, and how over 230 packages were eventually incorporated into the CRO's library. The automated, template-based workflow developed organizes analysis into regular R files with conventions for data, analysis, and report generation. Defining analysis tasks helped identify necessary tools and packages. Though challenges were faced, determination to improve R and flexibility of the software led to the decision to remain fully R-based.

Big dataarchitecturesandecosystem+nosqlKhanderao Kand

This document provides an overview of big data architecture, the Hadoop ecosystem, and NoSQL databases. It discusses common big data use cases, characteristics, and tools. It describes the typical 3-tier traditional architecture compared to the big data architecture using Hadoop. Key components of Hadoop like HDFS, MapReduce, Hive, Pig, Avro/Thrift, HBase are explained. The document also discusses stream processing tools like Storm, Spark and real-time query with Impala. It notes how NoSQL databases can integrate with Hadoop/MapReduce for both batch and real-time processing.

Introduction to Google Cloud platform technologiesChris Schalk

Continuous DeploymentBrian Henerey

Continuous Deployment involves shipping code as frequently as possible, even multiple times per day. It allows for smaller changes with less risk, faster feedback, and a competitive advantage. To achieve this, companies optimize their deployment process, automate testing and deployments, and measure everything to learn and improve continuously. This approach is enabled by technologies like cloud computing and embraced by companies like Google, Amazon, and Facebook.

DA 592 - Term Project Report - Berker Kozan Can KokluCan Köklü

This document summarizes a data analytics project done by students for a Kaggle contest to perform demand prediction for Grupo Bimbo. Python and the XGBoost library were used to perform feature engineering, training, and predictions on a large dataset. The team achieved a top 17% score on the competition by optimizing hyperparameters and selecting important features. Challenges included analyzing a large dataset, which was overcome through data type reductions and cloud computing resources.

Dataiku productive application to production - pap is may 2015 Dataiku

This document discusses the development of predictive applications and outlines a vision for a platform called "Blue Box" that could help address many of the challenges in building and deploying these applications at scale. It notes that building predictive applications currently requires integrating multiple separate components. The document then describes desired features for the Blue Box platform, such as data cleansing, external data integration, model updating, decision logic, auditing, and serving predictions in real-time. It poses questions about how such a platform could be created, whether through open source or a commercial offering.

Cómo programar en c++ 9th Edition Harvey Deitelvrtoviuostas90

The Testing Planet Issue 7Rosie Sherry

This document discusses how mobile technology has become integrated into the restaurant dining experience. It provides a list of common activities people engage in using their mobile devices at restaurants, such as searching for nearby restaurants, reading reviews, getting directions, checking in on social media, taking photos of food and sharing on social networks, and posting reviews of the dining experience. The document suggests that mobile devices have become people's main connection to online applications, services and their social lives, and that this is shifting people's focus away from the food, company and atmosphere at restaurants and more towards interacting with applications on their mobile devices.

2014-10-10-SBC361-Reproducible researchYannick Wurm

This document discusses best practices for organizing computational biology projects. It recommends creating a directory structure with folders for source code, data, documentation, results and binaries/executables. Data folders should include README files explaining where the data came from. Version control is important to track changes over time. Comments and documentation will help others understand the project and allow researchers to revisit past work without reconstructing their experiments from scratch. Organizing and documenting projects thoroughly makes computational experiments more reproducible, understandable and useful to both the original researchers and others in the future.

The Google Analytics API and Analytics CanvasnModal Solutions Inc.

Maximizing Big Data ROI via Best of Breed Technology Patterns and Practices -...DigiMarCon - Digital Marketing, Media and Advertising Conferences & Exhibitions

Not long ago the question was whether your organization had big data. Did you have the volume, the velocity, the technology. Now those basics are largely given for most of the people attending this event. The path to success is still fuzzy, however, with so many technologies to choose from – and so many ways to use them. This presentation triangulates in a holistic manner on the modern business dilemma: how can we leverage technology to improve revenue, profit, market share, and numerous other success criteria. That said, this is not about the analytics or KPIs -- although it is about measurable improvement. It’s about lining up the right technologies and using them in effective, proven ways to maximize Return on Investment (ROI). Since the slant here is holistic, we’ll show how to blend infrastructure, tools, methods, and talent to avoid and constantly trim technical debt… and to produce success stories that are consistently repeatable, not a byproduct of individual heroics.

"r" for ROIAndrea Dodet

#rstats lessons for #measureMark Edmondson

The Art of Evolutionary Algorithms ProgrammingJuan J. Merelo

Actminds Outsourcing Summit 07cnetto

Week 4 Assignment - Software Development PlanScenario-Your team has be.docxestefana2345678

2013 04 prime guideDroidcon Berlin

Droidcon thessaloniki 2015Raymond Chenon

Data Analytic s (Unit -1).pRESENTATION .PPTGayathriShiva4

Meet a 100% R-based CRO - The summary of a 5-year journeyAdrian Olszewski

Meet a 100% R-based CRO. The summary of a 5-year journeyAdrian Olszewski

Big dataarchitecturesandecosystem+nosqlKhanderao Kand

Introduction to Google Cloud platform technologiesChris Schalk

Continuous DeploymentBrian Henerey

DA 592 - Term Project Report - Berker Kozan Can KokluCan Köklü

Dataiku productive application to production - pap is may 2015 Dataiku

Cómo programar en c++ 9th Edition Harvey Deitelvrtoviuostas90

The Testing Planet Issue 7Rosie Sherry

2014-10-10-SBC361-Reproducible researchYannick Wurm

The Google Analytics API and Analytics CanvasnModal Solutions Inc.

Maximizing Big Data ROI via Best of Breed Technology Patterns and Practices -...DigiMarCon - Digital Marketing, Media and Advertising Conferences & Exhibitions

More from Gabriel Hamilton (14)

Javascript Smart Contracts on NEARGabriel Hamilton

Smart ContractsGabriel Hamilton

The document discusses smart contracts and their potential uses and drawbacks. It defines smart contracts as programs run under the economic rules of a blockchain. Some potential uses of smart contracts mentioned include creating markets, electronic voting systems, fractional ownership of assets, and distributed computation. Drawbacks discussed include issues with privacy, immutability of mistakes, and slow performance relative to traditional databases. The document aims to explore smart contracts and discuss where they may or may not be better options than traditional approaches.

Web NextGabriel Hamilton

The document discusses potential future directions for web pages, including making them more spatial and three-dimensional. It presents examples of how web pages could be immersive environments for browsing, shopping, editing, gaming, collaboration and education. Key applications mentioned include using virtual and augmented reality to make pages feel more like 3D spaces where users can navigate and interact visually, auditorily and kinetically. The document suggests these types of "spatial websites" could be built using technologies like WebGL, WebAssembly, Unity and WebXR.

Beyond Agile SoftwareGabriel Hamilton

Natural language processing: feature extractionGabriel Hamilton

This document discusses natural language processing (NLP) and feature extraction. It explains that NLP can be used for applications like search, translation, and question answering. The document then discusses extracting features from text like paragraphs, sentences, words, parts of speech, entities, sentiment, topics, and assertions. Specific features discussed in more detail include frequency, relationships between words, language features, supervised machine learning, classifiers, encoding words, word vectors, and parse trees. Tools mentioned for NLP include Google Cloud NLP, Spacy, OpenNLP, and Stanford Core NLP.

Software engineering for CEOsGabriel Hamilton

This document discusses challenges with software projects from the perspective of CEOs and managers. It uses construction and airport projects as metaphors to illustrate how custom software systems are complex and unique like large infrastructure projects. Planning for software is difficult as initial plans often prove wrong, so failures need to be planned for through feature slip deadlines and time slip requirements. Software complexity grows exponentially with team size due to communication overhead, but techniques like pair programming can help manage this. Ultimately, prioritizing speed and features over quality will undermine the business, so an iterative approach focusing on delivering working software regularly is recommended.

Adaptive software engineeringGabriel Hamilton

The TensorFlow dance crazeGabriel Hamilton

The document introduces TensorFlow, a machine learning library. It discusses how TensorFlow uses multi-dimensional arrays called tensors to represent data and models. An example regression problem is demonstrated where TensorFlow is used to fit a line to sample data points by iteratively updating the slope and offset values to minimize loss. The document promotes TensorFlow by noting its ability to distribute operations across processors and optimize entire graphs.

DataFlow & BeamGabriel Hamilton

Software engineering for CEOs ch1Gabriel Hamilton

How BigQuery broke my heartGabriel Hamilton

How to present lots of information on a screenGabriel Hamilton

Dojo: Beautiful Web Apps, FastGabriel Hamilton

Dojo: Getting Started TodayGabriel Hamilton

Javascript Smart Contracts on NEARGabriel Hamilton

Smart ContractsGabriel Hamilton

Web NextGabriel Hamilton

Beyond Agile SoftwareGabriel Hamilton

Natural language processing: feature extractionGabriel Hamilton

Software engineering for CEOsGabriel Hamilton

Adaptive software engineeringGabriel Hamilton

The TensorFlow dance crazeGabriel Hamilton

DataFlow & BeamGabriel Hamilton

Software engineering for CEOs ch1Gabriel Hamilton

How BigQuery broke my heartGabriel Hamilton

How to present lots of information on a screenGabriel Hamilton

Dojo: Beautiful Web Apps, FastGabriel Hamilton

Dojo: Getting Started TodayGabriel Hamilton

Recently uploaded (20)

IEDM 2024 Tutorial2_Advances in CMOS Technologies and Future Directions for C...organizerofv

Semantic Cultivators : The Critical Future Role to Enable AIartmondano

Special Meetup Edition - TDX Bengaluru Meetup #52.pptxshyamraj55

Electronic_Mail_Attacks-1-35.pdf by xploitniftliyevhuseyn

Heap, Types of Heap, Insertion and DeletionJaydeep Kale

Cyber Awareness overview for 2025 month of securityriccardosl1

Role of Data Annotation Services in AI-Powered ManufacturingAndrew Leo

Generative Artificial Intelligence (GenAI) in BusinessDr. Tathagat Varma

Noah Loul Shares 5 Steps to Implement AI Agents for Maximum Business Efficien...Noah Loul

Artificial intelligence is changing how businesses operate. Companies are using AI agents to automate tasks, reduce time spent on repetitive work, and focus more on high-value activities. Noah Loul, an AI strategist and entrepreneur, has helped dozens of companies streamline their operations using smart automation. He believes AI agents aren't just tools—they're workers that take on repeatable tasks so your human team can focus on what matters. If you want to reduce time waste and increase output, AI agents are the next move.

MINDCTI revenue release Quarter 1 2025 PRMIND CTI

tecnologias de las primeras civilizaciones.pdffjgm517

Linux Professional Institute LPIC-1 Exam.pdfRHCSA Guru

Into The Box Conference Keynote Day 1 (ITB2025)Ortus Solutions, Corp

Transcript: #StandardsGoals for 2025: Standards & certification roundup - Tec...BookNet Canada

Book industry standards are evolving rapidly. In the first part of this session, we’ll share an overview of key developments from 2024 and the early months of 2025. Then, BookNet’s resident standards expert, Tom Richardson, and CEO, Lauren Stewart, have a forward-looking conversation about what’s next. Link to recording, presentation slides, and accompanying resource: https://bnctechforum.ca/sessions/standardsgoals-for-2025-standards-certification-roundup/ Presented by BookNet Canada on May 6, 2025 with support from the Department of Canadian Heritage.

Vaibhav Gupta BAML: AI work flows without Hallucinationsjohn409870

Shipping Agents Vaibhav Gupta Cofounder @ Boundary in/vaigup boundaryml/baml Imagine if every API call you made failed only 5% of the time boundaryml/baml Imagine if every LLM call you made failed only 5% of the time boundaryml/baml Imagine if every LLM call you made failed only 5% of the time boundaryml/baml Fault tolerant systems are hard but now everything must be fault tolerant boundaryml/baml We need to change how we think about these systems Aaron Villalpando Cofounder @ Boundary Boundary Combinator boundaryml/baml We used to write websites like this: boundaryml/baml But now we do this: boundaryml/baml Problems web dev had: boundaryml/baml Problems web dev had: Strings. Strings everywhere. boundaryml/baml Problems web dev had: Strings. Strings everywhere. State management was impossible. boundaryml/baml Problems web dev had: Strings. Strings everywhere. State management was impossible. Dynamic components? forget about it. boundaryml/baml Problems web dev had: Strings. Strings everywhere. State management was impossible. Dynamic components? forget about it. Reuse components? Good luck. boundaryml/baml Problems web dev had: Strings. Strings everywhere. State management was impossible. Dynamic components? forget about it. Reuse components? Good luck. Iteration loops took minutes. boundaryml/baml Problems web dev had: Strings. Strings everywhere. State management was impossible. Dynamic components? forget about it. Reuse components? Good luck. Iteration loops took minutes. Low engineering rigor boundaryml/baml React added engineering rigor boundaryml/baml The syntax we use changes how we think about problems boundaryml/baml We used to write agents like this: boundaryml/baml Problems agents have: boundaryml/baml Problems agents have: Strings. Strings everywhere. Context management is impossible. Changing one thing breaks another. New models come out all the time. Iteration loops take minutes. boundaryml/baml Problems agents have: Strings. Strings everywhere. Context management is impossible. Changing one thing breaks another. New models come out all the time. Iteration loops take minutes. Low engineering rigor boundaryml/baml Agents need the expressiveness of English, but the structure of code F*** You, Show Me The Prompt. boundaryml/baml <show don’t tell> Less prompting + More engineering = Reliability + Maintainability BAML Sam Greg Antonio Chris turned down openai to join ex-founder, one of the earliest BAML users MIT PhD 20+ years in compilers made his own database, 400k+ youtube views Vaibhav Gupta in/vaigup [email protected] boundaryml/baml Thank you!

The Evolution of Meme Coins A New Era for Digital Currency ppt.pdfAbi john

SAP Modernization: Maximizing the Value of Your SAP S/4HANA Migration.pdfPrecisely

Procurement Insights Cost To Value Guide.pptxJon Hansen

TrsLabs - Fintech Product & Business ConsultingTrs Labs

Hybrid Growth Mandate Model with TrsLabs Strategic Investments, Inorganic Growth, Business Model Pivoting are critical activities that business don't do/change everyday. In cases like this, it may benefit your business to choose a temporary external consultant. An unbiased plan driven by clearcut deliverables, market dynamics and without the influence of your internal office equations empower business leaders to make right choices. Getting things done within a budget within a timeframe is key to Growing Business - No matter whether you are a start-up or a big company Talk to us & Unlock the competitive advantage

Mastering Advance Window Functions in SQL.pdfSpiral Mantra

IEDM 2024 Tutorial2_Advances in CMOS Technologies and Future Directions for C...organizerofv

Semantic Cultivators : The Critical Future Role to Enable AIartmondano

Special Meetup Edition - TDX Bengaluru Meetup #52.pptxshyamraj55

Electronic_Mail_Attacks-1-35.pdf by xploitniftliyevhuseyn

Heap, Types of Heap, Insertion and DeletionJaydeep Kale

Cyber Awareness overview for 2025 month of securityriccardosl1

Role of Data Annotation Services in AI-Powered ManufacturingAndrew Leo

Generative Artificial Intelligence (GenAI) in BusinessDr. Tathagat Varma

Noah Loul Shares 5 Steps to Implement AI Agents for Maximum Business Efficien...Noah Loul

MINDCTI revenue release Quarter 1 2025 PRMIND CTI

tecnologias de las primeras civilizaciones.pdffjgm517

Linux Professional Institute LPIC-1 Exam.pdfRHCSA Guru

Into The Box Conference Keynote Day 1 (ITB2025)Ortus Solutions, Corp

Transcript: #StandardsGoals for 2025: Standards & certification roundup - Tec...BookNet Canada

Vaibhav Gupta BAML: AI work flows without Hallucinationsjohn409870

The Evolution of Meme Coins A New Era for Digital Currency ppt.pdfAbi john

SAP Modernization: Maximizing the Value of Your SAP S/4HANA Migration.pdfPrecisely

Procurement Insights Cost To Value Guide.pptxJon Hansen

TrsLabs - Fintech Product & Business ConsultingTrs Labs

Mastering Advance Window Functions in SQL.pdfSpiral Mantra

DOSUG Intro to google prediction api

1. Regression Analysis & Prediction Devon Jones Lead Systems Engineer, Knewton Gabe Hamilton Software Engineering Mgr, Revionics

2. Tech Confluence For those who work downtown, check out our DOSUG inspired group. meetup.com/TechConfluence 3rd Wednesday of the month At lunch: 12:30 - 1:30pm

3. The Plan 1. Regression Analysis - Devon 2. Google Prediction API - Gabe 3. Applying Regression - Devon

4. Google Prediction API { { "label": "awesome", "score": 0.98 }, "label": "lame", "score": 0.08 } Gabe Hamilton

5. What kind of Prediction? Predict an output value based on some input values. Things like: Sentiment Analysis, Spam Detection, Today's temperature, GDP Growth

7. How does Google predict things?

8. Well, it's Google Through an intensive breeding program Google has managed to distribute Punxsutawney Phils throughout its datacenters across the world. Each Phil is kept in a climate controlled enclosure that mimics the conditions of a perfectly average February 2nd. A full scale digital sundial maps your problem domain onto the shadow matrix of the enclosure allowing each Phil to fully interact with your model. The early spring / long winter emergence probability of each Phil is then sorted and reduced to determine the final result returned by the prediction API.

9. No Really, How do they do it? Short Answer: I have no idea Long answer: It's a service, they can do whatever works, swap implementations run multiple algorithms

10. Possible Implementations Regression Analysis Neural Networks Support Vector Machine Monte Carlo Sim Decision Trees Evolutionary Algorithms Basically it is STATISTICS

11. Types of Prediction you can do Regression Classification How do inputs cause an output to vary? Deciding which bucket some input belongs in Output is a numeric value: Shopping Cart Size Stock Price Buckets are text values: French, Spanish, English

12. What is Classification good for?

13. Classification ● ● ● ● ● ● ● ● Sentiment analysis Spam detection Language categorization Tagging Assign priority to bugs Predict movie ratings Message routing decisions <Your brilliant idea here>

14. Getting Started Hello World page is great https://developers.google.com/prediction/docs/hello_world

15. So you have a big pile of data

16. Time for some cleanup 90% of the development time is data cleanup Good talk on data driven projects http://www.slideshare. net/ryanweald/building-data-drivenproducts-with-ruby-rubyconf-2012

17. CSV Input file aka Training Set First column is expected values. 2nd through N columns are input values "French", "Je pense donc j'essuie", "Paris" Output an input No header columns more input 250MB max file size

18. 4 Steps to Prediction 1. Create a CSV file of your training data 2. Create a new Project in the Prediction API a. requires entering billing info 3. Upload your csv file to Google Storage 4. In Prediction API Browser: a. insert a new training set (the csv file) b. view your trained set c. use trainedmodel.predict to make predictions See the hello world for details of the method calls

19. Let's make some predictions...

20. Live demo screenshots: List Models

21. Live demo screens: Analyze Model

22. Live demo: Predict Model Category

23. Live demo: Predict Model Numeric

24. Storage for datasets https://storage.cloud.google.com API Explorer https://developers.google.com/apis-explorer/#s/prediction/v1.6/

DOSUG Intro to google prediction api

Recommended

More Related Content

Viewers also liked (20)

Similar to DOSUG Intro to google prediction api (20)

More from Gabriel Hamilton (14)

Recently uploaded (20)

DOSUG Intro to google prediction api