ibc789/pipeline

PipelineAI: End-to-End ML and AI Platform for Real-time Spark and Tensorflow Data Pipelines

PipelineAI Home

PipelineAI Products

Community Edition

Standalone Edition

Enterprise Edition

PipelineAI Resources

PipelineAI Open Source

PipelineAI + Kubernetes

PipelineAI 24x7 Global Support

TensorFlow + Spark + GPU Workshop

AWS + GPU

Google Cloud + GPU

PipelineAI Core Features

Consistent, Immutable, Reproducible Model Runtimes

Each model is built into a separate Docker image with the appropriate Python, C++, and Java/Scala Runtime Libraries for training or prediction.

Use the same Docker Image from Local Laptop to Production to avoid dependency surprises.

Supported Model Types

scikit, tensorflow, python, keras, pmml, spark, java, xgboost, R

More model samples coming soon (ie. R).

Pre-Requisites

Docker

• Install Docker

Python3 (Conda is Optional)

• Install Miniconda with Python3 Support

Install PipelineCLI

Note: This command line interface requires Python3 and Docker as detailed above.

pip install cli-pipeline==1.3.10 --ignore-installed --no-cache -U

Verify Successful PipelineCLI Installation

pipeline version

### EXPECTED OUTPUT ###
cli_version: 1.3.10     <-- MAKE SURE YOU ARE ON THIS VERSION OR BAD THINGS MAY HAPPEN!
api_version: v1

capabilities_enabled: ['predict_server', 'predict', 'version']
capabilities_disabled: ['predict_cluster', 'train_cluster', 'train_server', 'optimize', 'experiment']

Email `[email protected]` to enable the advanced capabilities.

Review CLI Functionality

pipeline

### EXPECTED OUTPUT ###
Usage:       pipeline                             <-- This List of CLI Commands

(Enterprise) pipeline experiment-add              <-- Add Cluster to Experiment
             pipeline experiment-start            <-- Start Experiment
             pipeline experiment-status           <-- Experiment Status (ie. Bandit-based Rewards)
             pipeline experiment-stop             <-- Stop Experiment
             pipeline experiment-update           <-- Update Experiment (ie. Bandit-based % Traffic Router)

(Standalone) pipeline optimize                    <-- Perform Model and Runtime Hyper-Parameter Tuning

(Community)  pipeline predict                     <-- Predict with Model Server or Cluster
             
(Enterprise) pipeline predict-cluster-connect     <-- Create Secure Tunnel to Prediction Cluster 
             pipeline predict-cluster-describe    <-- Describe Prediction Cluster
             pipeline predict-cluster-logs        <-- View Prediction Cluster Logs 
             pipeline predict-cluster-scale       <-- Scale Prediction Cluster
             pipeline predict-cluster-shell       <-- Shell into Prediction Cluster
             pipeline predict-cluster-start       <-- Start Prediction Cluster from Docker Registry
             pipeline predict-cluster-status      <-- Status of Predidction Cluster
             pipeline predict-cluster-stop        <-- Stop Prediction Cluster
             
(Community)  pipeline predict-server-build        <-- Build Prediction Server
             pipeline predict-server-logs         <-- View Prediction Server Logs
             pipeline predict-server-pull         <-- Pull Prediction Server from Docker Registry
             pipeline predict-server-push         <-- Push Prediction Server to Docker Registry
             pipeline predict-server-shell        <-- Shell into Prediction Server (Debugging)
             pipeline predict-server-start        <-- Start Prediction Server
             pipeline predict-server-stop         <-- Stop Prediction Server

(Enterprise) pipeline train-cluster-connect       <-- Create Secure Tunnel to Training Cluster
             pipeline train-cluster-describe      <-- Describe Training Cluster
             pipeline train-cluster-logs          <-- View Training Cluster Logs
             pipeline train-cluster-scale         <-- Scale Training Cluster
             pipeline train-cluster-shell         <-- Shell into Training Cluster
             pipeline train-cluster-start         <-- Start Training Cluster from Docker Registry
             pipeline train-cluster-status        <-- Status of Training Cluster
             pipeline train-cluster-stop          <-- Stop Traininhg Cluster

(Standalone) pipeline train-server-build          <-- Build Prediction Server
             pipeline train-server-logs           <-- View Prediction Server Logs
             pipeline train-server-pull           <-- Pull Prediction Server from Docker Registry
             pipeline train-server-push           <-- Push Prediction Server to Docker Registry
             pipeline train-server-shell          <-- Shell into Prediction Server (Debugging)
             pipeline train-server-start          <-- Start Prediction Server
             pipeline train-server-stop           <-- Stop Prediction Server
             
(Community)  pipeline version                     <-- View This CLI Version

Prepare Model Samples

Clone the PipelineAI Predict Repo

git clone https://github.com/PipelineAI/predict

Change into predict Directory

cd predict 

Switch to Latest Release Branch (r1.3)

git checkout r1.3

Model Predictions

Inspect Model Directory

ls -l ./models/tensorflow/mnist

### EXPECTED OUTPUT ###
pipeline_conda_environment.yml     <-- Required.  Sets up the conda environment
pipeline_predict.py                <-- Required.  `predict(request: bytes) -> bytes` is required
versions/                          <-- Optional.  If directory exists, we start TensorFlow Serving

Inspect PipelineAI Predict Module ./models/tensorflow/mnist/pipeline_predict.py

Note: Only the predict() method is required. Everything else is optional.

cat ./models/tensorflow/mnist/pipeline_predict.py

### EXPECTED OUTPUT ###
import os
import logging
from pipeline_model import TensorFlowServingModel             <-- Optional.  Wraps TensorFlow Serving
from pipeline_monitor import prometheus_monitor as monitor    <-- Optional.  Monitor runtime metrics
from pipeline_logger import log                               <-- Optional.  Log to console, file, kafka

...

__all__ = ['predict']                                         <-- Optional.  Being a good Python citizen.

...

def _initialize_upon_import() -> TensorFlowServingModel:      <-- Optional.  Called once at server startup
    return TensorFlowServingModel(host='localhost',           <-- Optional.  Wraps TensorFlow Serving
                                  port=9000,
                                  model_name=os.environ['PIPELINE_MODEL_NAME'],
                                  inputs_name='inputs',       <-- Optional.  TensorFlow SignatureDef inputs
                                  outputs_name='outputs',     <-- Optional.  TensorFlow SignatureDef outputs
                                  timeout=100)                <-- Optional.  TensorFlow Serving timeout

_model = _initialize_upon_import()                            <-- Optional.  Called once upon server startup

_labels = {'model_type': os.environ['PIPELINE_MODEL_TYPE'],   <-- Optional.  Tag metrics
           'model_name': os.environ['PIPELINE_MODEL_NAME'],
           'model_tag': os.environ['PIPELINE_MODEL_TAG']}

_logger = logging.getLogger('predict-logger')                 <-- Optional.  Standard Python logging

@log(labels=_labels, logger=_logger)                          <-- Optional.  Sample and compare predictions
def predict(request: bytes) -> bytes:                         <-- Required.  Called on every prediction

    with monitor(labels=_labels, name="transform_request"):   <-- Optional.  Expose fine-grained metrics
        transformed_request = _transform_request(request)     <-- Optional.  Transform input (json) into TensorFlow (tensor)

    with monitor(labels=_labels, name="predict"):
        predictions = _model.predict(transformed_request)       <-- Optional.  Calls _model.predict()

    with monitor(labels=_labels, name="transform_response"):
        transformed_response = _transform_response(predictions) <-- Optional.  Transform TensorFlow (tensor) into output (json)

    return transformed_response                                 <-- Required.  Returns the predicted value(s)
...

Build the Model into a Runnable Docker Image

This command bundles the TensorFlow runtime with the model.

pipeline predict-server-build --model-type=tensorflow --model-name=mnist --model-tag="v1" --model-path=./models/tensorflow/mnist

model-path must be a relative path.

Start the Model Server

pipeline predict-server-start --model-type=tensorflow --model-name=mnist --model-tag="v1" --memory-limit=2G

If the port is already allocated, run docker ps, then docker rm -f <container-id>.

Monitor Runtime Logs

Wait for the model runtime to settle...

pipeline predict-server-logs --model-type=tensorflow --model-name=mnist --model-tag="v1"

### EXPECTED OUTPUT ###
...
2017-10-10 03:56:00.695  INFO 121 --- [     run-main-0] i.p.predict.jvm.PredictionServiceMain$   : Started PredictionServiceMain. in 7.566 seconds (JVM running for 20.739)
[debug] 	Thread run-main-0 exited.
[debug] Waiting for thread container-0 to terminate.
...
INFO[0050] Completed initial partial maintenance sweep through 4 in-memory fingerprints in 40.002264633s.  source="storage.go:1398"
...

You need to ctrl-c out of the log viewing before proceeding.

PipelineAI Prediction CLI

Perform Prediction

You may see 502 Bad Gateway if you predict too quickly. Let the server startup completely, then predict again.

The first call takes 10-20x longer than subsequent calls for lazy initialization and warm-up. Predict again if you see a "fallback" message.

Before proceeding, make sure you hit ctrl-c after viewing the logs in the previous step.

pipeline predict --model-type=tensorflow --model-name=mnist --model-tag="v1" --predict-server-url=http://localhost:6969 --test-request-path=./models/tensorflow/mnist/data/test_request.json

### Expected Output ###
{"outputs": [0.0022526539396494627, 2.63791100074684e-10, 0.4638307988643646, 0.21909376978874207, 3.2985670372909226e-07, 0.29357224702835083, 0.00019597385835368186, 5.230629176367074e-05, 0.020996594801545143, 5.426473762781825e-06]}

### Formatted Output ###
Digit  Confidence
=====  ==========
0      0.0022526539396494627
1      2.63791100074684e-10
2      0.4638307988643646      <-- Prediction
3      0.21909376978874207
4      3.2985670372909226e-07
5      0.29357224702835083 
6      0.00019597385835368186
7      5.230629176367074e-05
8      0.020996594801545143
9      5.426473762781825e-06

Perform 100 Predictions in Parallel (Mini Load Test)

pipeline predict --model-type=tensorflow --model-name=mnist --model-tag="v1" --predict-server-url=http://localhost:6969 --test-request-path=./models/tensorflow/mnist/data/test_request.json --test-request-concurrency=100

PipelineAI Prediction REST API

Use the REST API to POST a JSON document representing the number 2.

curl -X POST -H "Content-Type: application/json" \
  -d '{"image": [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.05098039656877518, 0.529411792755127, 0.3960784673690796, 0.572549045085907, 0.572549045085907, 0.847058892250061, 0.8156863451004028, 0.9960784912109375, 1.0, 1.0, 0.9960784912109375, 0.5960784554481506, 0.027450982481241226, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.32156863808631897, 0.9921569228172302, 0.9921569228172302, 0.9921569228172302, 0.9921569228172302, 0.9921569228172302, 0.9921569228172302, 0.9921569228172302, 0.9921569228172302, 0.9921569228172302, 0.9921569228172302, 0.7882353663444519, 0.11764706671237946, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.32156863808631897, 0.9921569228172302, 0.988235354423523, 0.7921569347381592, 0.9450981020927429, 0.545098066329956, 0.21568629145622253, 0.3450980484485626, 0.45098042488098145, 0.125490203499794, 0.125490203499794, 0.03921568766236305, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.32156863808631897, 0.9921569228172302, 0.803921639919281, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.6352941393852234, 0.9921569228172302, 0.803921639919281, 0.24705883860588074, 0.3490196168422699, 0.6509804129600525, 0.32156863808631897, 0.32156863808631897, 0.1098039299249649, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.007843137718737125, 0.7529412508010864, 0.9921569228172302, 0.9725490808486938, 0.9686275124549866, 0.9921569228172302, 0.9921569228172302, 0.9921569228172302, 0.9921569228172302, 0.8274510502815247, 0.29019609093666077, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.2549019753932953, 0.9921569228172302, 0.9921569228172302, 0.9921569228172302, 0.9921569228172302, 0.9921569228172302, 0.9921569228172302, 0.9921569228172302, 0.9921569228172302, 0.9921569228172302, 0.847058892250061, 0.027450982481241226, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.5921568870544434, 0.9921569228172302, 0.9921569228172302, 0.9921569228172302, 0.7333333492279053, 0.44705885648727417, 0.23137256503105164, 0.23137256503105164, 0.4784314036369324, 0.9921569228172302, 0.9921569228172302, 0.03921568766236305, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.5568627715110779, 0.9568628072738647, 0.7098039388656616, 0.08235294371843338, 0.019607843831181526, 0.0, 0.0, 0.0, 0.08627451211214066, 0.9921569228172302, 0.9921569228172302, 0.43137258291244507, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.15294118225574493, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.08627451211214066, 0.9921569228172302, 0.9921569228172302, 0.46666669845581055, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.08627451211214066, 0.9921569228172302, 0.9921569228172302, 0.46666669845581055, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.08627451211214066, 0.9921569228172302, 0.9921569228172302, 0.46666669845581055, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.1882353127002716, 0.9921569228172302, 0.9921569228172302, 0.46666669845581055, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.6705882549285889, 0.9921569228172302, 0.9921569228172302, 0.12156863510608673, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.2392157018184662, 0.9647059440612793, 0.9921569228172302, 0.6274510025978088, 0.003921568859368563, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.08235294371843338, 0.44705885648727417, 0.16470588743686676, 0.0, 0.0, 0.2549019753932953, 0.9294118285179138, 0.9921569228172302, 0.9333333969116211, 0.27450981736183167, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.4941176772117615, 0.9529412388801575, 0.0, 0.0, 0.5803921818733215, 0.9333333969116211, 0.9921569228172302, 0.9921569228172302, 0.4078431725502014, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.7411764860153198, 0.9764706492424011, 0.5529412031173706, 0.8784314393997192, 0.9921569228172302, 0.9921569228172302, 0.9490196704864502, 0.43529415130615234, 0.007843137718737125, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.6235294342041016, 0.9921569228172302, 0.9921569228172302, 0.9921569228172302, 0.9764706492424011, 0.6274510025978088, 0.1882353127002716, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.18431372940540314, 0.5882353186607361, 0.729411780834198, 0.5686274766921997, 0.3529411852359772, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0]}' \
  http://localhost:6969/api/v1/model/predict/tensorflow/mnist/v1 \
  -w "\n\n"

### Expected Output ###
{"outputs": [0.0022526539396494627, 2.63791100074684e-10, 0.4638307988643646, 0.21909376978874207, 3.2985670372909226e-07, 0.29357224702835083, 0.00019597385835368186, 5.230629176367074e-05, 0.020996594801545143, 5.426473762781825e-06]}

### Formatted Output
Digit  Confidence
=====  ==========
0      0.0022526539396494627
1      2.63791100074684e-10
2      0.4638307988643646      <-- Prediction
3      0.21909376978874207
4      3.2985670372909226e-07
5      0.29357224702835083 
6      0.00019597385835368186
7      5.230629176367074e-05
8      0.020996594801545143
9      5.426473762781825e-06

Monitor Real-Time Prediction Metrics

Re-run the Prediction REST API while watching the following dashboard URL:

http://localhost:6969/hystrix-dashboard/monitor/monitor.html?streams=%5B%7B%22name%22%3A%22%22%2C%22stream%22%3A%22http%3A%2F%2Flocalhost%3A6969%2Fhystrix.stream%22%2C%22auth%22%3A%22%22%2C%22delay%22%3A%22%22%7D%5D

Monitor Detailed Prediction Metrics

Re-run the Prediction REST API while watching the following detailed metrics dashboard URL:

http://localhost:3000/

Username/Password: admin/admin

Set Type to Prometheues.

Set Url to http://localhost:9090.

Set Access to direct.

Click Save & Test.

Click Dashboards -> Import upper-left menu drop-down.

Copy and Paste THIS raw json file into the paste JSON box.

Select the Prometheus-based data source that you setup above and click Import.

Change the Date Range in the upper right to Last 5m and the Refresh Every to 5s.

Create additional PipelineAI Prediction widgets using THIS guide to the Prometheus Syntax.

Stop Model Server

pipeline predict-server-stop --model-type=tensorflow --model-name=mnist --model-tag="v1"

PipelineAI Standalone and Enterprise Features

Click HERE to compare PipelineAI Products.

Drag N' Drop Model Deploy

Generate Optimize Model Versions Upon Upload

Distributed Model Training and Hyper-Parameter Tuning

Continuously Deploy Models to Clusters of PipelineAI Servers

View Real-Time Prediction Stream

Compare Both Offline (Batch) and Real-Time Model Performance

Compare Response Time, Throughput, and Cost-Per-Prediction

Shift Live Traffic to Maximize Revenue and Minimize Cost

Continuously Fix Borderline Predictions through Crowd Sourcing