Commit 88061537 authored by dasharatha.vamshi's avatar dasharatha.vamshi

mlflow cleanup

parent c33f1b83
# Created by .ignore support plugin (hsz.mobi)
### JetBrains template
# Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio, WebStorm and Rider
# Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839
reports/*.pdf
reports/*.csv
reports/*.xlsx
# User-specific stuff
.idea/**/workspace.xml
.idea/**/tasks.xml
.idea/**/usage.statistics.xml
.idea/**/dictionaries
.idea/**/shelf
.idea
logs
# Generated files
.idea/**/contentModel.xml
# Sensitive or high-churn files
.idea/**/dataSources/
.idea/**/dataSources.ids
.idea/**/dataSources.local.xml
.idea/**/sqlDataSources.xml
.idea/**/dynamic.xml
.idea/**/uiDesigner.xml
.idea/**/dbnavigator.xml
# Gradle
.idea/**/gradle.xml
.idea/**/libraries
# Gradle and Maven with auto-import
# When using Gradle or Maven with auto-import, you should exclude module files,
# since they will be recreated, and may cause churn. Uncomment if using
# auto-import.
# .idea/artifacts
# .idea/compiler.xml
# .idea/jarRepositories.xml
# .idea/modules.xml
# .idea/*.iml
# .idea/modules
# *.iml
# *.ipr
# CMake
cmake-build-*/
# Mongo Explorer plugin
.idea/**/mongoSettings.xml
# File-based project format
*.iws
# IntelliJ
out/
# mpeltonen/sbt-idea plugin
.idea_modules/
# JIRA plugin
atlassian-ide-plugin.xml
# Cursive Clojure plugin
.idea/replstate.xml
# Crashlytics plugin (for Android Studio and IntelliJ)
com_crashlytics_export_strings.xml
crashlytics.properties
crashlytics-build.properties
fabric.properties
# Editor-based Rest Client
.idea/httpRequests
# Android studio 3.1+ serialized cache file
.idea/caches/build_file_checksums.ser
### Python template
# Byte-compiled / optimized / DLL files
__pycache__/
*.py[cod]
*$py.class
# C extensions
*.so
# Distribution / packaging
.Python
build/
develop-eggs/
dist/
downloads/
eggs/
.eggs/
lib/
lib64/
parts/
sdist/
var/
wheels/
share/python-wheels/
*.egg-info/
.installed.cfg
*.egg
MANIFEST
# PyInstaller
# Usually these files are written by a python script from a template
# before PyInstaller builds the exe, so as to inject date/other infos into it.
*.manifest
*.spec
# Installer logs
pip-log.txt
pip-delete-this-directory.txt
# Unit test / coverage reports
htmlcov/
.tox/
.nox/
.coverage
.coverage.*
.cache
nosetests.xml
coverage.xml
*.cover
*.py,cover
.hypothesis/
.pytest_cache/
cover/
# Translations
*.mo
*.pot
# Django stuff:
*.log
local_settings.py
db.sqlite3
db.sqlite3-journal
# Flask stuff:
instance/
.webassets-cache
# Scrapy stuff:
.scrapy
# Sphinx documentation
docs/_build/
# PyBuilder
.pybuilder/
target/
# Jupyter Notebook
.ipynb_checkpoints
# IPython
profile_default/
ipython_config.py
# pyenv
# For a library or package, you might want to ignore these files since the code is
# intended to run in multiple environments; otherwise, check them in:
# .python-version
# pipenv
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
# However, in case of collaboration, if having platform-specific dependencies or dependencies
# having no cross-platform support, pipenv may install dependencies that don't work, or not
# install all needed dependencies.
#Pipfile.lock
# PEP 582; used by e.g. github.com/David-OConnor/pyflow
__pypackages__/
# Celery stuff
celerybeat-schedule
celerybeat.pid
# SageMath parsed files
*.sage.py
# Environments
.venv
env/
venv/
ENV/
env.bak/
venv.bak/
# Spyder project settings
.spyderproject
.spyproject
# Rope project settings
.ropeproject
# mkdocs documentation
/site
# mypy
.mypy_cache/
.dmypy.json
dmypy.json
# Pyre type checker
.pyre/
# pytype static type analyzer
.pytype/
# Cython debug symbols
cython_debug/
### VisualStudio template
## Ignore Visual Studio temporary files, build results, and
## files generated by popular Visual Studio add-ons.
##
## Get latest from https://github.com/github/gitignore/blob/master/VisualStudio.gitignore
# User-specific files
*.rsuser
*.suo
*.user
*.userosscache
*.sln.docstates
# User-specific files (MonoDevelop/Xamarin Studio)
*.userprefs
# Mono auto generated files
mono_crash.*
# Build results
[Dd]ebug/
[Dd]ebugPublic/
[Rr]elease/
[Rr]eleases/
x64/
x86/
[Ww][Ii][Nn]32/
[Aa][Rr][Mm]/
[Aa][Rr][Mm]64/
bld/
[Bb]in/
[Oo]bj/
[Ll]og/
[Ll]ogs/
# Visual Studio 2015/2017 cache/options directory
.vs/
# Uncomment if you have tasks that create the project's static files in wwwroot
#wwwroot/
# Visual Studio 2017 auto generated files
Generated\ Files/
# MSTest test Results
[Tt]est[Rr]esult*/
[Bb]uild[Ll]og.*
# NUnit
*.VisualState.xml
TestResult.xml
nunit-*.xml
# Build Results of an ATL Project
[Dd]ebugPS/
[Rr]eleasePS/
dlldata.c
# Benchmark Results
BenchmarkDotNet.Artifacts/
# .NET Core
project.lock.json
project.fragment.lock.json
artifacts/
# ASP.NET Scaffolding
ScaffoldingReadMe.txt
# StyleCop
StyleCopReport.xml
# Files built by Visual Studio
*_i.c
*_p.c
*_h.h
*.ilk
*.meta
*.obj
*.iobj
*.pch
*.pdb
*.ipdb
*.pgc
*.pgd
*.rsp
*.sbr
*.tlb
*.tli
*.tlh
*.tmp
*.tmp_proj
*_wpftmp.csproj
*.vspscc
*.vssscc
.builds
*.pidb
*.svclog
*.scc
# Chutzpah Test files
_Chutzpah*
# Visual C++ cache files
ipch/
*.aps
*.ncb
*.opendb
*.opensdf
*.sdf
*.cachefile
*.VC.db
*.VC.VC.opendb
# Visual Studio profiler
*.psess
*.vsp
*.vspx
*.sap
# Visual Studio Trace Files
*.e2e
# TFS 2012 Local Workspace
$tf/
# Guidance Automation Toolkit
*.gpState
# ReSharper is a .NET coding add-in
_ReSharper*/
*.[Rr]e[Ss]harper
*.DotSettings.user
# TeamCity is a build add-in
_TeamCity*
# DotCover is a Code Coverage Tool
*.dotCover
# AxoCover is a Code Coverage Tool
.axoCover/*
!.axoCover/settings.json
# Coverlet is a free, cross platform Code Coverage Tool
coverage*.json
coverage*.xml
coverage*.info
# Visual Studio code coverage results
*.coverage
*.coveragexml
# NCrunch
_NCrunch_*
.*crunch*.local.xml
nCrunchTemp_*
# MightyMoose
*.mm.*
AutoTest.Net/
# Web workbench (sass)
.sass-cache/
# Installshield output folder
[Ee]xpress/
# DocProject is a documentation generator add-in
DocProject/buildhelp/
DocProject/Help/*.HxT
DocProject/Help/*.HxC
DocProject/Help/*.hhc
DocProject/Help/*.hhk
DocProject/Help/*.hhp
DocProject/Help/Html2
DocProject/Help/html
# Click-Once directory
publish/
# Publish Web Output
*.[Pp]ublish.xml
*.azurePubxml
# Note: Comment the next line if you want to checkin your web deploy settings,
# but database connection strings (with potential passwords) will be unencrypted
*.pubxml
*.publishproj
# Microsoft Azure Web App publish settings. Comment the next line if you want to
# checkin your Azure Web App publish settings, but sensitive information contained
# in these scripts will be unencrypted
PublishScripts/
# NuGet Packages
*.nupkg
# NuGet Symbol Packages
*.snupkg
# The packages folder can be ignored because of Package Restore
**/[Pp]ackages/*
# except build/, which is used as an MSBuild target.
!**/[Pp]ackages/build/
# Uncomment if necessary however generally it will be regenerated when needed
#!**/[Pp]ackages/repositories.config
# NuGet v3's project.json files produces more ignorable files
*.nuget.props
*.nuget.targets
# Microsoft Azure Build Output
csx/
*.build.csdef
# Microsoft Azure Emulator
ecf/
rcf/
# Windows Store app package directories and files
AppPackages/
BundleArtifacts/
Package.StoreAssociation.xml
_pkginfo.txt
*.appx
*.appxbundle
*.appxupload
# Visual Studio cache files
# files ending in .cache can be ignored
*.[Cc]ache
# but keep track of directories ending in .cache
!?*.[Cc]ache/
# Others
ClientBin/
~$*
*~
*.dbmdl
*.dbproj.schemaview
*.jfm
*.pfx
*.publishsettings
orleans.codegen.cs
# Including strong name files can present a security risk
# (https://github.com/github/gitignore/pull/2483#issue-259490424)
#*.snk
# Since there are multiple workflows, uncomment next line to ignore bower_components
# (https://github.com/github/gitignore/pull/1529#issuecomment-104372622)
#bower_components/
# RIA/Silverlight projects
Generated_Code/
# Backup & report files from converting an old project file
# to a newer Visual Studio version. Backup files are not needed,
# because we have git ;-)
_UpgradeReport_Files/
Backup*/
UpgradeLog*.XML
UpgradeLog*.htm
ServiceFabricBackup/
*.rptproj.bak
# SQL Server files
*.mdf
*.ldf
*.ndf
# Business Intelligence projects
*.rdl.data
*.bim.layout
*.bim_*.settings
*.rptproj.rsuser
*- [Bb]ackup.rdl
*- [Bb]ackup ([0-9]).rdl
*- [Bb]ackup ([0-9][0-9]).rdl
# Microsoft Fakes
FakesAssemblies/
# GhostDoc plugin setting file
*.GhostDoc.xml
# Node.js Tools for Visual Studio
.ntvs_analysis.dat
node_modules/
# Visual Studio 6 build log
*.plg
# Visual Studio 6 workspace options file
*.opt
# Visual Studio 6 auto-generated workspace file (contains which files were open etc.)
*.vbw
# Visual Studio LightSwitch build output
**/*.HTMLClient/GeneratedArtifacts
**/*.DesktopClient/GeneratedArtifacts
**/*.DesktopClient/ModelManifest.xml
**/*.Server/GeneratedArtifacts
**/*.Server/ModelManifest.xml
_Pvt_Extensions
# Paket dependency manager
.paket/paket.exe
paket-files/
# FAKE - F# Make
.fake/
# CodeRush personal settings
.cr/personal
# Python Tools for Visual Studio (PTVS)
*.pyc
# Cake - Uncomment if you are using it
# tools/**
# !tools/packages.config
# Tabs Studio
*.tss
# Telerik's JustMock configuration file
*.jmconfig
# BizTalk build output
*.btp.cs
*.btm.cs
*.odx.cs
*.xsd.cs
# OpenCover UI analysis results
OpenCover/
# Azure Stream Analytics local run output
ASALocalRun/
# MSBuild Binary and Structured Log
*.binlog
# NVidia Nsight GPU debugger configuration file
*.nvuser
# MFractors (Xamarin productivity tool) working folder
.mfractor/
# Local History for Visual Studio
.localhistory/
# BeatPulse healthcheck temp database
healthchecksdb
# Backup folder for Package Reference Convert tool in Visual Studio 2017
MigrationBackup/
# Ionide (cross platform F# VS Code tools) working folder
.ionide/
# Fody - auto-generated XML schema
FodyWeavers.xsd
### JupyterNotebooks template
# gitignore template for Jupyter Notebooks
# website: http://jupyter.org/
.env
FROM python:3.8-buster
COPY . /code
WORKDIR /code
RUN pip install -r requirements.txt
CMD [ "python","app.py" ]
\ No newline at end of file
run_id,experiment_id,status,artifact_uri,start_time,end_time,metrics.MAE,metrics.MSE,metrics.R2,metrics.MAPE,metrics.RMSLE,metrics.RMSE,params.max_depth,params.min_samples_split,params.ccp_alpha,params.max_samples,params.min_weight_fraction_leaf,params.criterion,params.oob_score,params.min_samples_leaf,params.warm_start,params.max_leaf_nodes,params.n_estimators,params.verbose,params.min_impurity_decrease,params.bootstrap,params.random_state,params.n_jobs,params.max_features,tags.mlflow.runName,tags.mlflow.user,tags.mlflow.parentRunId,tags.mlflow.source.git.commit,tags.algorithm,tags.mlflow.source.type,tags.mlflow.source.name,tags.mlflow.log-model.history
3eef20e89fb948078ef99847ae4b4bc0,65,FINISHED,wasbs://mlflow-vm-container@azrmlilensqa006382180551.blob.core.windows.net/mlflow_qa/65/3eef20e89fb948078ef99847ae4b4bc0/artifacts,2023-03-20 11:12:56.468000+00:00,2023-03-20 11:14:51.309000+00:00,538.0753,499454.5687,0.1195,0.0855,0.1141,706.721,6,2,0.0,None,0.0,mae,False,2,False,None,10,0,0.05,True,2872,-1,1.0,stately-snake-36,dasharatha.vamshi,839ba85648e04ff79c411ffdce21213f,75c16b31e98f3fb1db70c11a6bd21aade07567d6,RandomForestRegressor,LOCAL,D:/ilens-ai/jubilant/R5/patch/r5-reaction-golden-batch/app.py,"[{""run_id"": ""3eef20e89fb948078ef99847ae4b4bc0"", ""artifact_path"": ""r5_model"", ""utc_time_created"": ""2023-03-20 11:14:46.153233"", ""flavors"": {""python_function"": {""model_path"": ""model.pkl"", ""loader_module"": ""mlflow.sklearn"", ""python_version"": ""3.8.16"", ""env"": ""conda.yaml""}, ""sklearn"": {""pickled_model"": ""model.pkl"", ""sklearn_version"": ""1.1.3"", ""serialization_format"": ""cloudpickle""}}, ""model_uuid"": null}]"
839ba85648e04ff79c411ffdce21213f,65,FINISHED,wasbs://mlflow-vm-container@azrmlilensqa006382180551.blob.core.windows.net/mlflow_qa/65/839ba85648e04ff79c411ffdce21213f/artifacts,2023-03-20 11:12:54.625000+00:00,2023-03-20 11:14:51.646000+00:00,,,,,,,,,,,,,,,,,,,,,,,,r5-golden-batch-test-1,dasharatha.vamshi,,75c16b31e98f3fb1db70c11a6bd21aade07567d6,,LOCAL,D:/ilens-ai/jubilant/R5/patch/r5-reaction-golden-batch/app.py,
14b392b1df58424b98cf47c6e7bfad7e,65,FINISHED,wasbs://mlflow-vm-container@azrmlilensqa006382180551.blob.core.windows.net/mlflow_qa/65/14b392b1df58424b98cf47c6e7bfad7e/artifacts,2023-03-20 11:05:34.682000+00:00,2023-03-20 11:07:24.960000+00:00,566.4853,708495.3303,0.164,0.088,0.1296,841.7216,3,10,0.0,None,0.0,mae,False,3,False,None,220,0,0.3,False,839,-1,log2,hilarious-yak-718,dasharatha.vamshi,b64389f4be80438eac4e87396f52ff96,75c16b31e98f3fb1db70c11a6bd21aade07567d6,RandomForestRegressor,LOCAL,D:/ilens-ai/jubilant/R5/patch/r5-reaction-golden-batch/app.py,"[{""run_id"": ""14b392b1df58424b98cf47c6e7bfad7e"", ""artifact_path"": ""r5_model"", ""utc_time_created"": ""2023-03-20 11:07:19.674442"", ""flavors"": {""python_function"": {""model_path"": ""model.pkl"", ""loader_module"": ""mlflow.sklearn"", ""python_version"": ""3.8.16"", ""env"": ""conda.yaml""}, ""sklearn"": {""pickled_model"": ""model.pkl"", ""sklearn_version"": ""1.1.3"", ""serialization_format"": ""cloudpickle""}}, ""model_uuid"": null}]"
0f35ac4a96fa413b9a15a54fe0b9b905,65,FAILED,wasbs://mlflow-vm-container@azrmlilensqa006382180551.blob.core.windows.net/mlflow_qa/65/0f35ac4a96fa413b9a15a54fe0b9b905/artifacts,2023-03-20 11:04:48.940000+00:00,2023-03-20 11:05:26.504000+00:00,,,,,,,,,,,,,,,,,,,,,,,,treasured-ape-95,dasharatha.vamshi,b64389f4be80438eac4e87396f52ff96,75c16b31e98f3fb1db70c11a6bd21aade07567d6,,LOCAL,D:/ilens-ai/jubilant/R5/patch/r5-reaction-golden-batch/app.py,
63df0f705ff44802aa8ff40a9fe0dd42,65,FINISHED,wasbs://mlflow-vm-container@azrmlilensqa006382180551.blob.core.windows.net/mlflow_qa/65/63df0f705ff44802aa8ff40a9fe0dd42/artifacts,2023-03-20 11:01:50.710000+00:00,2023-03-20 11:03:15.779000+00:00,464.6541,398781.9839,0.3022,0.0686,0.0919,631.4919,4,5,0.0,None,0.0,mse,False,2,False,None,40,0,0.002,True,2588,-1,log2,secretive-hen-994,dasharatha.vamshi,b64389f4be80438eac4e87396f52ff96,75c16b31e98f3fb1db70c11a6bd21aade07567d6,RandomForestRegressor,LOCAL,D:/ilens-ai/jubilant/R5/patch/r5-reaction-golden-batch/app.py,"[{""run_id"": ""63df0f705ff44802aa8ff40a9fe0dd42"", ""artifact_path"": ""r5_model"", ""utc_time_created"": ""2023-03-20 11:03:10.815296"", ""flavors"": {""python_function"": {""model_path"": ""model.pkl"", ""loader_module"": ""mlflow.sklearn"", ""python_version"": ""3.8.16"", ""env"": ""conda.yaml""}, ""sklearn"": {""pickled_model"": ""model.pkl"", ""sklearn_version"": ""1.1.3"", ""serialization_format"": ""cloudpickle""}}, ""model_uuid"": null}]"
8533b5b16bf04d03b9021e4a09df31dd,65,FINISHED,wasbs://mlflow-vm-container@azrmlilensqa006382180551.blob.core.windows.net/mlflow_qa/65/8533b5b16bf04d03b9021e4a09df31dd/artifacts,2023-03-20 10:59:10.251000+00:00,2023-03-20 11:01:36.039000+00:00,564.6727,644844.6845,0.2292,0.0872,0.1219,803.0222,8,10,0.0,None,0.0,mae,False,3,False,None,210,0,0.4,True,2017,-1,log2,rogue-koi-225,dasharatha.vamshi,b64389f4be80438eac4e87396f52ff96,75c16b31e98f3fb1db70c11a6bd21aade07567d6,RandomForestRegressor,LOCAL,D:/ilens-ai/jubilant/R5/patch/r5-reaction-golden-batch/app.py,"[{""run_id"": ""8533b5b16bf04d03b9021e4a09df31dd"", ""artifact_path"": ""r5_model"", ""utc_time_created"": ""2023-03-20 11:01:31.173586"", ""flavors"": {""python_function"": {""model_path"": ""model.pkl"", ""loader_module"": ""mlflow.sklearn"", ""python_version"": ""3.8.16"", ""env"": ""conda.yaml""}, ""sklearn"": {""pickled_model"": ""model.pkl"", ""sklearn_version"": ""1.1.3"", ""serialization_format"": ""cloudpickle""}}, ""model_uuid"": null}]"
b64389f4be80438eac4e87396f52ff96,65,FINISHED,wasbs://mlflow-vm-container@azrmlilensqa006382180551.blob.core.windows.net/mlflow_qa/65/b64389f4be80438eac4e87396f52ff96/artifacts,2023-03-20 10:22:30.234000+00:00,2023-03-20 11:07:25.260000+00:00,,,,,,,,,,,,,,,,,,,,,,,,r5-golden-batch-test,dasharatha.vamshi,,75c16b31e98f3fb1db70c11a6bd21aade07567d6,,LOCAL,D:/ilens-ai/jubilant/R5/patch/r5-reaction-golden-batch/app.py,
from loguru import logger
from scripts.constants.app_configuration import MlflowMetaData
from scripts.core.mlflow_util import MlflowCleanUp
if __name__ == '__main__':
try:
logger.info("Starting the Module...")
experiment_name = MlflowMetaData.EXPERIMENT_NAME
run_name = MlflowMetaData.RUN_NAME
model_name = MlflowMetaData.MODEL_NAME
logger.info(f"Performing cleanup for experiment: {experiment_name}, parent run: {run_name}, "
f"model name: {model_name}")
_mcu_ = MlflowCleanUp(experiment_name, run_name, model_name)
_mcu_.start_cleanup()
except Exception as e:
logger.exception(f"Error cleaning up because of error {e}")
[TIMEZONE]
required_tz=$REQUIRED_TZ
[MLFLOW]
mlflow_tracking_uri=$MLFLOW_TRACKING_URI
mlflow_tracking_username=$MLFLOW_TRACKING_USERNAME
mlflow_tracking_password=$MLFLOW_TRACKING_PASSWORD
azure_storage_connection_string=$AZURE_STORAGE_CONNECTION_STRING
azure_storage_access_key=$AZURE_STORAGE_ACCESS_KEY
experiment_name=$EXPERIMENT_NAME
run_name=$RUN_NAME
model_name=$MODEL_NAME
total_models_needed=$TOTAL_MODELS_NEEDED
\ No newline at end of file
REQUIRED_TZ=Asia/Kolkata
MLFLOW_TRACKING_URI=https://qa.unifytwin.com/mlflow/
MLFLOW_TRACKING_USERNAME=mlflow
MLFLOW_TRACKING_PASSWORD=MlFlOwQA#4321
AZURE_STORAGE_CONNECTION_STRING=DefaultEndpointsProtocol=https;AccountName=azrmlilensqa006382180551;AccountKey=tDGOKfiZ2svfoMvVmS0Fbpf0FTHfTq4wKYuDX7cAxlhve/3991QuzdvJHm9vWc+lo6mtC+x9yPSghWNR4+gacg==;EndpointSuffix=core.windows.net
AZURE_STORAGE_ACCESS_KEY=tDGOKfiZ2svfoMvVmS0Fbpf0FTHfTq4wKYuDX7cAxlhve/3991QuzdvJHm9vWc+lo6mtC+x9yPSghWNR4+gacg==
EXPERIMENT_NAME=Golden Batch Models Test
RUN_NAME=r5-golden-batch-test
MODEL_NAME=r5_model
TOTAL_MODELS_NEEDED=2
\ No newline at end of file
pytz==2021.3
loguru==0.5.3
scipy==1.7.1
numpy==1.21.2
mlflow==1.20.2
scikit-learn
simplejson==3.17.5
requests==2.27.1
pydantic==1.8.2
python-dotenv==0.19.2
PyYAML==6.0
kafka-python==1.4.7
SQLAlchemy==1.4.16
sqlparse==0.4.2
psycopg2==2.9.1
pycaret==3.0.0rc8
python-dateutil~=2.8.2
protobuf==3.20.1
azure-storage-blob==12.14.1
\ No newline at end of file
import os
import sys
from configparser import ConfigParser, BasicInterpolation
from dotenv import load_dotenv
# Configuration File Constants
_application_conf = f"./conf/application.conf"
_default_conf = f"./config.env"
load_dotenv(dotenv_path=_default_conf)
class EnvInterpolation(BasicInterpolation):
"""
Interpolation which expands environment variables in values.
"""
def before_get(self, parser, section, option, value, defaults):
value = super().before_get(parser, section, option, value, defaults)
if not os.path.expandvars(value).startswith("$"):
return os.path.expandvars(value)
else:
return
try:
config = ConfigParser(interpolation=EnvInterpolation())
config.read(_application_conf)
except Exception as e:
print(f"Error while loading the config: {e}")
print("Failed to Load Configuration. Exiting!!!")
sys.exit()
class Logging:
level = config.get("LOGGING", "level", fallback="INFO")
level = level if level else "INFO"
tb_flag = config.getboolean("LOGGING", "traceback", fallback=True)
tb_flag = tb_flag if tb_flag is not None else True
# Configuration Variables
REQUIRED_TZ = config['TIMEZONE']['required_tz']
class MlflowMetaData:
MLFLOW_TRACKING_URI = config['MLFLOW']['mlflow_tracking_uri']
MLFLOW_TRACKING_USERNAME = config['MLFLOW']['mlflow_tracking_username']
MLFLOW_TRACKING_PASSWORD = config['MLFLOW']['mlflow_tracking_password']
AZURE_STORAGE_CONNECTION_STRING = config['MLFLOW']['azure_storage_connection_string']
AZURE_STORAGE_ACCESS_KEY = config['MLFLOW']['azure_storage_access_key']
EXPERIMENT_NAME = config['MLFLOW']['experiment_name']
RUN_NAME = config['MLFLOW']['run_name']
MODEL_NAME = config['MLFLOW']['model_name']
TOTAL_MODELS_NEEDED = config['MLFLOW']['total_models_needed']
MODEL_NAME = 'model.pkl'
import os
import re
from datetime import datetime
import mlflow
import pandas as pd
import pytz
from dateutil import tz
from loguru import logger
from azure.storage.blob import BlobServiceClient
from scripts.constants.app_configuration import REQUIRED_TZ, MlflowMetaData
from scripts.constants.app_constants import MODEL_NAME
mlflow_tracking_uri = MlflowMetaData.MLFLOW_TRACKING_URI
AZURE_STORAGE_CONNECTION_STRING = MlflowMetaData.AZURE_STORAGE_CONNECTION_STRING
AZURE_STORAGE_ACCESS_KEY = MlflowMetaData.AZURE_STORAGE_ACCESS_KEY
os.environ["MLFLOW_TRACKING_USERNAME"] = MlflowMetaData.MLFLOW_TRACKING_USERNAME
os.environ["MLFLOW_TRACKING_PASSWORD"] = MlflowMetaData.MLFLOW_TRACKING_PASSWORD
os.environ["AZURE_STORAGE_CONNECTION_STRING"] = AZURE_STORAGE_CONNECTION_STRING
os.environ["AZURE_STORAGE_ACCESS_KEY"] = AZURE_STORAGE_ACCESS_KEY
mlflow.set_tracking_uri(mlflow_tracking_uri)
mlflow.set_registry_uri(mlflow_tracking_uri)
client = mlflow.tracking.MlflowClient()
class MlFlowUtil:
@staticmethod
def get_last_run_time_diff(run_info):
try:
logger.info(f"Checking the time difference in days")
df_time = run_info.copy()
df_time['end_time'] = pd.to_datetime(df_time['end_time']).dt.tz_convert(REQUIRED_TZ)
to_zone = tz.gettz(REQUIRED_TZ)
df_time["days"] = df_time['end_time'].dt.date
df_time["hours"] = df_time['end_time'].dt.hour
last_model_time = list(df_time['end_time'])[0].to_pydatetime()
today = datetime.now(pytz.utc)
central_current = today.astimezone(to_zone)
time_diff = central_current - last_model_time
return int(time_diff.days)
except Exception as e:
logger.warning(f"Exception while checking the last run time of the model - {e}")
return 0
@staticmethod
def log_model(model, model_name):
try:
mlflow.sklearn.log_model(model, model_name)
logger.info("logged the model")
return True
except Exception as e:
logger.exception(str(e))
@staticmethod
def log_metrics(metrics):
try:
updated_metric = {}
for key, value in metrics.items():
key = re.sub(r"[([{})\]]", "", key)
updated_metric[key] = value
mlflow.log_metrics(updated_metric)
return True
except Exception as e:
logger.exception(str(e))
@staticmethod
def log_hyper_param(hyper_params):
try:
mlflow.log_params(hyper_params)
return True
except Exception as e:
logger.exception(str(e))
@staticmethod
def set_tag(child_run_id, key, value):
try:
client.set_tag(run_id=child_run_id, key=key, value=value)
except Exception as e:
logger.exception(f"Exception while setting the tag - {e}")
@staticmethod
def remove_file_if_exists(path):
if os.path.exists(path):
os.remove(path)
@staticmethod
def delete_artifact(run_id, parent_run_name, artifact_uri, file_path, model_name):
logger.info(f"Deleting artifact for {run_id} under {parent_run_name}")
container_name = artifact_uri.split("//")[-1].split('@')[0]
mlflow_name = artifact_uri.split("//")[-1].split('@')[-1].split('/')[1]
mlflow_id = artifact_uri.split("//")[-1].split('@')[-1].split('/')[2]
path = f'{mlflow_name}/{mlflow_id}/{run_id}/artifacts/{file_path}/{model_name}'
logger.info(f'Deleting artifact from path: {path}')
blob_service_client = BlobServiceClient.from_connection_string(MlflowMetaData.AZURE_STORAGE_CONNECTION_STRING)
container_client = blob_service_client.get_container_client(container_name)
blob_client = container_client.get_blob_client(path)
blob_exists = blob_client.exists()
if blob_exists:
logger.info(f"The blob {path} exists, so deleting it")
blob_client.delete_blob()
else:
logger.info(f"The blob {path} does not exist, which means its already deleted")
class MlflowCleanUp:
def __init__(self, experiment_name, parent_run_name, model_save_name):
self.experiment_name = experiment_name
self.parent_run_name = parent_run_name
self.model_save_name = model_save_name
self._mfu_ = MlFlowUtil()
self.total_models_needed = int(MlflowMetaData.TOTAL_MODELS_NEEDED)
self.model_name = MODEL_NAME
self.model_history_key = 'tags.mlflow.log-model.history'
self.model_parent_run_id_key = 'tags.mlflow.parentRunId'
def check_experiment(self):
experiment_info = mlflow.get_experiment_by_name(self.experiment_name)
if experiment_info is None:
logger.info(f"No experiment found with name {self.experiment_name}")
return None
else:
logger.info(f"Proceeding with existing Experiment {self.experiment_name}")
mlflow.set_experiment(experiment_name=self.experiment_name)
experiment_info = mlflow.get_experiment_by_name(self.experiment_name)
experiment_id = experiment_info.experiment_id
return experiment_id
@staticmethod
def check_runs_data(experiment_id):
runs_df = mlflow.search_runs(experiment_id)
# parent_runs_df.to_csv('all-runs.csv', index=False)
if not runs_df.empty:
return runs_df
else:
logger.info('No runs found for the experiment...')
return None
def delete_run_model_data(self, df, run_name_mapping):
cols = ['run_id', 'artifact_uri', 'start_time', 'end_time', 'tags.mlflow.parentRunId',
'tags.mlflow.log-model.history']
parent_runs = list(set(list(df[self.model_parent_run_id_key])))
for parent_run_id in parent_runs:
logger.info(f'Checking for Run Name {run_name_mapping[parent_run_id]}')
temp_df = df[df[self.model_parent_run_id_key] == parent_run_id]
temp_df = temp_df[temp_df[self.model_history_key].notna()]
if not temp_df.empty:
temp_df = temp_df[cols]
total_models_present = len(temp_df)
logger.info(f'Total models present are {total_models_present}')
temp_df = temp_df.iloc[self.total_models_needed:]
logger.info(f'Total models to cleanup are {len(temp_df)}')
all_records = temp_df.to_dict('records')
if len(all_records) > 0:
for record in all_records:
run_id = record['run_id']
artifact_uri = record['artifact_uri']
self._mfu_.delete_artifact(run_id, run_name_mapping[parent_run_id], artifact_uri,
self.model_save_name, self.model_name)
else:
logger.info(f'No records to cleanup for Run {run_name_mapping[parent_run_id]}')
else:
logger.info(f'Nothing to cleanup for Run {run_name_mapping[parent_run_id]}')
def start_cleanup(self):
experiment_id = self.check_experiment()
if experiment_id is not None:
runs_df = self.check_runs_data(experiment_id)
if runs_df is not None:
run_id_list = list(runs_df['run_id'])
run_name_list = list(runs_df['tags.mlflow.runName'])
run_name_mapping = {}
for i in range(len(run_id_list)):
run_name_mapping[run_id_list[i]] = run_name_list[i]
# getting runs who have a parent-id
df = runs_df[runs_df[self.model_parent_run_id_key].notna()]
# getting runs who have a model logged
f_df = df[df[self.model_history_key].notna()]
self.delete_run_model_data(f_df, run_name_mapping)
else:
logger.info('No runs found for experiment, so no cleanup')
return False
else:
logger.info("Not a valid experiment...")
return False
import os
import re
from datetime import datetime
import mlflow
import pandas as pd
import pytz
from dateutil import tz
from loguru import logger
from azure.storage.blob import BlobServiceClient
from scripts.constants.app_configuration import REQUIRED_TZ, MlflowMetaData
mlflow_tracking_uri = MlflowMetaData.MLFLOW_TRACKING_URI
AZURE_STORAGE_CONNECTION_STRING = MlflowMetaData.AZURE_STORAGE_CONNECTION_STRING
AZURE_STORAGE_ACCESS_KEY = MlflowMetaData.AZURE_STORAGE_ACCESS_KEY
os.environ["MLFLOW_TRACKING_USERNAME"] = MlflowMetaData.MLFLOW_TRACKING_USERNAME
os.environ["MLFLOW_TRACKING_PASSWORD"] = MlflowMetaData.MLFLOW_TRACKING_PASSWORD
os.environ["AZURE_STORAGE_CONNECTION_STRING"] = AZURE_STORAGE_CONNECTION_STRING
os.environ["AZURE_STORAGE_ACCESS_KEY"] = AZURE_STORAGE_ACCESS_KEY
mlflow.set_tracking_uri(mlflow_tracking_uri)
mlflow.set_registry_uri(mlflow_tracking_uri)
client = mlflow.tracking.MlflowClient()
class MlFlowUtil:
@staticmethod
def get_last_run_time_diff(run_info):
try:
logger.info(f"Checking the time difference in days")
df_time = run_info.copy()
df_time['end_time'] = pd.to_datetime(df_time['end_time']).dt.tz_convert(REQUIRED_TZ)
to_zone = tz.gettz(REQUIRED_TZ)
df_time["days"] = df_time['end_time'].dt.date
df_time["hours"] = df_time['end_time'].dt.hour
last_model_time = list(df_time['end_time'])[0].to_pydatetime()
today = datetime.now(pytz.utc)
central_current = today.astimezone(to_zone)
time_diff = central_current - last_model_time
return int(time_diff.days)
except Exception as e:
logger.warning(f"Exception while checking the last run time of the model - {e}")
return 0
@staticmethod
def log_model(model, model_name):
try:
mlflow.sklearn.log_model(model, model_name)
logger.info("logged the model")
return True
except Exception as e:
logger.exception(str(e))
@staticmethod
def log_metrics(metrics):
try:
updated_metric = {}
for key, value in metrics.items():
key = re.sub(r"[([{})\]]", "", key)
updated_metric[key] = value
mlflow.log_metrics(updated_metric)
return True
except Exception as e:
logger.exception(str(e))
@staticmethod
def log_hyper_param(hyper_params):
try:
mlflow.log_params(hyper_params)
return True
except Exception as e:
logger.exception(str(e))
@staticmethod
def set_tag(child_run_id, key, value):
try:
client.set_tag(run_id=child_run_id, key=key, value=value)
except Exception as e:
logger.exception(f"Exception while setting the tag - {e}")
@staticmethod
def remove_file_if_exists(path):
if os.path.exists(path):
os.remove(path)
@staticmethod
def delete_artifact(run_id, artifact_uri, file_path):
container_name = artifact_uri.split("//")[-1].split('@')[0]
mlflow_name = artifact_uri.split("//")[-1].split('@')[-1].split('/')[1]
mlflow_id = artifact_uri.split("//")[-1].split('@')[-1].split('/')[2]
path = f'{mlflow_name}/{mlflow_id}/{run_id}/artifacts/{file_path}/requirements.txt'
logger.info(f'Deleting artifact from path: {path}')
blob_service_client = BlobServiceClient.from_connection_string(MlflowMetaData.AZURE_STORAGE_CONNECTION_STRING)
container_client = blob_service_client.get_container_client(container_name)
blob_client = container_client.get_blob_client(path)
blob_client.delete_blob()
class MlflowCleanUp:
def __init__(self, experiment_name, parent_run_name, model_save_name):
self.experiment_name = experiment_name
self.parent_run_name = parent_run_name
self.model_save_name = model_save_name
self._mfu_ = MlFlowUtil()
self.model_age = int(MlflowMetaData.MODEL_AGE_IN_DAYS)
def check_experiment(self):
experiment_info = mlflow.get_experiment_by_name(self.experiment_name)
if experiment_info is None:
logger.info(f"No experiment found with name {self.experiment_name}")
return None
else:
logger.info(f"Proceeding with existing Experiment {self.experiment_name}")
mlflow.set_experiment(experiment_name=self.experiment_name)
experiment_info = mlflow.get_experiment_by_name(self.experiment_name)
experiment_id = experiment_info.experiment_id
return experiment_id
@staticmethod
def check_parent_run(experiment_id):
parent_runs_df = mlflow.search_runs(experiment_id)
parent_runs_df.to_csv('all-runs.csv',index=False)
all_parent_runs = list(parent_runs_df['tags.mlflow.parentRunId'])
print(all_parent_runs)
if not parent_runs_df.empty:
parent_key = 'tags.mlflow.parentRunId'
parent_runs_df[parent_key].fillna('parent', inplace=True)
df = parent_runs_df[parent_runs_df[parent_key] == 'parent']
if not df.empty:
run_key = 'run_id'
logger.info('Parent runs found for the experiment')
parent_runs = list(df[run_key])
return {'parent_runs': parent_runs, 'df': parent_runs_df}
else:
logger.info('No parent runs found for the experiment')
return None
else:
logger.info('No runs found for the experiment...')
return None
def get_nested_runs(self, exp_id, parent_run_id):
"""
Recursively iterate through all child runs of the specified parent run and return a nested dictionary
with the parent run ID as the key and a dictionary of child run IDs and their nested child runs as the value.
"""
# Recursively get all child runs
child_runs_dict = {}
for child_run_id in mlflow.search_runs([exp_id], f"tags.mlflow.parentRunId = '{parent_run_id}'")["run_id"]:
nested_child_runs = self.get_nested_runs(exp_id, child_run_id)
child_runs_dict[child_run_id] = nested_child_runs if nested_child_runs else None
# Construct the nested dictionary with parent run ID as key and dictionary of child runs as value
return child_runs_dict
def check_under_parent_run(self, experiment_id, parent_run_id, df):
logger.info(f"Getting all runs under parent run {parent_run_id}")
child_runs = self.get_nested_runs(experiment_id, parent_run_id)
print(child_runs)
print(df.columns)
cols = ['run_id', 'artifact_uri', 'start_time', 'end_time', 'tags.mlflow.parentRunId',
'tags.mlflow.log-model.history']
df = df[cols]
print(df.columns)
# for child_run in child_runs:
# temp_df = df[df['run_id'] == child_run]
# artifact_uri = list(temp_df['artifact_uri'])[0]
# self._mfu_.delete_artifact(child_run, artifact_uri, self.model_save_name)
def start_cleanup(self):
experiment_id = self.check_experiment()
if experiment_id is not None:
parent_runs_dict = self.check_parent_run(experiment_id)
if parent_runs_dict is not None:
parent_runs = parent_runs_dict['parent_runs']
df = parent_runs_dict['df']
logger.info(f'Total parent runs found are {len(parent_runs)}')
for run in parent_runs:
self.check_under_parent_run(experiment_id, run, df)
else:
logger.info('No parent runs found for experiment, so no cleanup')
return False
else:
logger.info("Not a valid experiment...")
return False
def check_existing_model_retrain(self, latest_child_run_id, child_run_info, retrain):
"""
If retrain is True, it returns true as retraining is required.
If retrain is False, it checks the time difference between the last child run and the current time and returns
true or false depending on the time difference
:param latest_child_run_id: last child run id
:param child_run_info: last child run info
:param retrain: retrain flag
:return: final retrain flag
"""
if retrain:
logger.info("Retraining Needed...")
return True
else:
logger.info(f"Already trained model is present, checking the age of the existing model of run id "
f"{latest_child_run_id}")
time_diff = self._mfu_.get_last_run_time_diff(child_run_info)
return False
def forming_loading_path(self, latest_run_id):
"""
Creates the path from the child run id
:param latest_run_id: latest child run id
:return: the path to the model
"""
try:
model_name = self.model_save_name
return f"runs:/{latest_run_id}/{model_name}"
except Exception as e:
logger.exception(f"Exception while forming loading path - {e}")
{
"cells": [
{
"cell_type": "code",
"execution_count": 36,
"id": "253d82dd",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": 70,
"id": "12dbfa08",
"metadata": {},
"outputs": [],
"source": [
"df = pd.read_csv(r'D:\\ilens-ai\\Vamshi-git\\mlflow-cleanup\\all-runs.csv')\n",
"df1 = df.copy()"
]
},
{
"cell_type": "code",
"execution_count": 71,
"id": "1712fc79",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>run_id</th>\n",
" <th>experiment_id</th>\n",
" <th>status</th>\n",
" <th>artifact_uri</th>\n",
" <th>start_time</th>\n",
" <th>end_time</th>\n",
" <th>metrics.MAE</th>\n",
" <th>metrics.MSE</th>\n",
" <th>metrics.R2</th>\n",
" <th>metrics.MAPE</th>\n",
" <th>...</th>\n",
" <th>params.n_jobs</th>\n",
" <th>params.max_features</th>\n",
" <th>tags.mlflow.runName</th>\n",
" <th>tags.mlflow.user</th>\n",
" <th>tags.mlflow.parentRunId</th>\n",
" <th>tags.mlflow.source.git.commit</th>\n",
" <th>tags.algorithm</th>\n",
" <th>tags.mlflow.source.type</th>\n",
" <th>tags.mlflow.source.name</th>\n",
" <th>tags.mlflow.log-model.history</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>3eef20e89fb948078ef99847ae4b4bc0</td>\n",
" <td>65</td>\n",
" <td>FINISHED</td>\n",
" <td>wasbs://mlflow-vm-container@azrmlilensqa006382...</td>\n",
" <td>2023-03-20 11:12:56.468000+00:00</td>\n",
" <td>2023-03-20 11:14:51.309000+00:00</td>\n",
" <td>538.0753</td>\n",
" <td>499454.5687</td>\n",
" <td>0.1195</td>\n",
" <td>0.0855</td>\n",
" <td>...</td>\n",
" <td>-1.0</td>\n",
" <td>1.0</td>\n",
" <td>stately-snake-36</td>\n",
" <td>dasharatha.vamshi</td>\n",
" <td>839ba85648e04ff79c411ffdce21213f</td>\n",
" <td>75c16b31e98f3fb1db70c11a6bd21aade07567d6</td>\n",
" <td>RandomForestRegressor</td>\n",
" <td>LOCAL</td>\n",
" <td>D:/ilens-ai/jubilant/R5/patch/r5-reaction-gold...</td>\n",
" <td>[{\"run_id\": \"3eef20e89fb948078ef99847ae4b4bc0\"...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>839ba85648e04ff79c411ffdce21213f</td>\n",
" <td>65</td>\n",
" <td>FINISHED</td>\n",
" <td>wasbs://mlflow-vm-container@azrmlilensqa006382...</td>\n",
" <td>2023-03-20 11:12:54.625000+00:00</td>\n",
" <td>2023-03-20 11:14:51.646000+00:00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>r5-golden-batch-test-1</td>\n",
" <td>dasharatha.vamshi</td>\n",
" <td>NaN</td>\n",
" <td>75c16b31e98f3fb1db70c11a6bd21aade07567d6</td>\n",
" <td>NaN</td>\n",
" <td>LOCAL</td>\n",
" <td>D:/ilens-ai/jubilant/R5/patch/r5-reaction-gold...</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>14b392b1df58424b98cf47c6e7bfad7e</td>\n",
" <td>65</td>\n",
" <td>FINISHED</td>\n",
" <td>wasbs://mlflow-vm-container@azrmlilensqa006382...</td>\n",
" <td>2023-03-20 11:05:34.682000+00:00</td>\n",
" <td>2023-03-20 11:07:24.960000+00:00</td>\n",
" <td>566.4853</td>\n",
" <td>708495.3303</td>\n",
" <td>0.1640</td>\n",
" <td>0.0880</td>\n",
" <td>...</td>\n",
" <td>-1.0</td>\n",
" <td>log2</td>\n",
" <td>hilarious-yak-718</td>\n",
" <td>dasharatha.vamshi</td>\n",
" <td>b64389f4be80438eac4e87396f52ff96</td>\n",
" <td>75c16b31e98f3fb1db70c11a6bd21aade07567d6</td>\n",
" <td>RandomForestRegressor</td>\n",
" <td>LOCAL</td>\n",
" <td>D:/ilens-ai/jubilant/R5/patch/r5-reaction-gold...</td>\n",
" <td>[{\"run_id\": \"14b392b1df58424b98cf47c6e7bfad7e\"...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>0f35ac4a96fa413b9a15a54fe0b9b905</td>\n",
" <td>65</td>\n",
" <td>FAILED</td>\n",
" <td>wasbs://mlflow-vm-container@azrmlilensqa006382...</td>\n",
" <td>2023-03-20 11:04:48.940000+00:00</td>\n",
" <td>2023-03-20 11:05:26.504000+00:00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>treasured-ape-95</td>\n",
" <td>dasharatha.vamshi</td>\n",
" <td>b64389f4be80438eac4e87396f52ff96</td>\n",
" <td>75c16b31e98f3fb1db70c11a6bd21aade07567d6</td>\n",
" <td>NaN</td>\n",
" <td>LOCAL</td>\n",
" <td>D:/ilens-ai/jubilant/R5/patch/r5-reaction-gold...</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>63df0f705ff44802aa8ff40a9fe0dd42</td>\n",
" <td>65</td>\n",
" <td>FINISHED</td>\n",
" <td>wasbs://mlflow-vm-container@azrmlilensqa006382...</td>\n",
" <td>2023-03-20 11:01:50.710000+00:00</td>\n",
" <td>2023-03-20 11:03:15.779000+00:00</td>\n",
" <td>464.6541</td>\n",
" <td>398781.9839</td>\n",
" <td>0.3022</td>\n",
" <td>0.0686</td>\n",
" <td>...</td>\n",
" <td>-1.0</td>\n",
" <td>log2</td>\n",
" <td>secretive-hen-994</td>\n",
" <td>dasharatha.vamshi</td>\n",
" <td>b64389f4be80438eac4e87396f52ff96</td>\n",
" <td>75c16b31e98f3fb1db70c11a6bd21aade07567d6</td>\n",
" <td>RandomForestRegressor</td>\n",
" <td>LOCAL</td>\n",
" <td>D:/ilens-ai/jubilant/R5/patch/r5-reaction-gold...</td>\n",
" <td>[{\"run_id\": \"63df0f705ff44802aa8ff40a9fe0dd42\"...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>8533b5b16bf04d03b9021e4a09df31dd</td>\n",
" <td>65</td>\n",
" <td>FINISHED</td>\n",
" <td>wasbs://mlflow-vm-container@azrmlilensqa006382...</td>\n",
" <td>2023-03-20 10:59:10.251000+00:00</td>\n",
" <td>2023-03-20 11:01:36.039000+00:00</td>\n",
" <td>564.6727</td>\n",
" <td>644844.6845</td>\n",
" <td>0.2292</td>\n",
" <td>0.0872</td>\n",
" <td>...</td>\n",
" <td>-1.0</td>\n",
" <td>log2</td>\n",
" <td>rogue-koi-225</td>\n",
" <td>dasharatha.vamshi</td>\n",
" <td>b64389f4be80438eac4e87396f52ff96</td>\n",
" <td>75c16b31e98f3fb1db70c11a6bd21aade07567d6</td>\n",
" <td>RandomForestRegressor</td>\n",
" <td>LOCAL</td>\n",
" <td>D:/ilens-ai/jubilant/R5/patch/r5-reaction-gold...</td>\n",
" <td>[{\"run_id\": \"8533b5b16bf04d03b9021e4a09df31dd\"...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>b64389f4be80438eac4e87396f52ff96</td>\n",
" <td>65</td>\n",
" <td>FINISHED</td>\n",
" <td>wasbs://mlflow-vm-container@azrmlilensqa006382...</td>\n",
" <td>2023-03-20 10:22:30.234000+00:00</td>\n",
" <td>2023-03-20 11:07:25.260000+00:00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>r5-golden-batch-test</td>\n",
" <td>dasharatha.vamshi</td>\n",
" <td>NaN</td>\n",
" <td>75c16b31e98f3fb1db70c11a6bd21aade07567d6</td>\n",
" <td>NaN</td>\n",
" <td>LOCAL</td>\n",
" <td>D:/ilens-ai/jubilant/R5/patch/r5-reaction-gold...</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>7 rows × 37 columns</p>\n",
"</div>"
],
"text/plain": [
" run_id experiment_id status \\\n",
"0 3eef20e89fb948078ef99847ae4b4bc0 65 FINISHED \n",
"1 839ba85648e04ff79c411ffdce21213f 65 FINISHED \n",
"2 14b392b1df58424b98cf47c6e7bfad7e 65 FINISHED \n",
"3 0f35ac4a96fa413b9a15a54fe0b9b905 65 FAILED \n",
"4 63df0f705ff44802aa8ff40a9fe0dd42 65 FINISHED \n",
"5 8533b5b16bf04d03b9021e4a09df31dd 65 FINISHED \n",
"6 b64389f4be80438eac4e87396f52ff96 65 FINISHED \n",
"\n",
" artifact_uri \\\n",
"0 wasbs://mlflow-vm-container@azrmlilensqa006382... \n",
"1 wasbs://mlflow-vm-container@azrmlilensqa006382... \n",
"2 wasbs://mlflow-vm-container@azrmlilensqa006382... \n",
"3 wasbs://mlflow-vm-container@azrmlilensqa006382... \n",
"4 wasbs://mlflow-vm-container@azrmlilensqa006382... \n",
"5 wasbs://mlflow-vm-container@azrmlilensqa006382... \n",
"6 wasbs://mlflow-vm-container@azrmlilensqa006382... \n",
"\n",
" start_time end_time \\\n",
"0 2023-03-20 11:12:56.468000+00:00 2023-03-20 11:14:51.309000+00:00 \n",
"1 2023-03-20 11:12:54.625000+00:00 2023-03-20 11:14:51.646000+00:00 \n",
"2 2023-03-20 11:05:34.682000+00:00 2023-03-20 11:07:24.960000+00:00 \n",
"3 2023-03-20 11:04:48.940000+00:00 2023-03-20 11:05:26.504000+00:00 \n",
"4 2023-03-20 11:01:50.710000+00:00 2023-03-20 11:03:15.779000+00:00 \n",
"5 2023-03-20 10:59:10.251000+00:00 2023-03-20 11:01:36.039000+00:00 \n",
"6 2023-03-20 10:22:30.234000+00:00 2023-03-20 11:07:25.260000+00:00 \n",
"\n",
" metrics.MAE metrics.MSE metrics.R2 metrics.MAPE ... params.n_jobs \\\n",
"0 538.0753 499454.5687 0.1195 0.0855 ... -1.0 \n",
"1 NaN NaN NaN NaN ... NaN \n",
"2 566.4853 708495.3303 0.1640 0.0880 ... -1.0 \n",
"3 NaN NaN NaN NaN ... NaN \n",
"4 464.6541 398781.9839 0.3022 0.0686 ... -1.0 \n",
"5 564.6727 644844.6845 0.2292 0.0872 ... -1.0 \n",
"6 NaN NaN NaN NaN ... NaN \n",
"\n",
" params.max_features tags.mlflow.runName tags.mlflow.user \\\n",
"0 1.0 stately-snake-36 dasharatha.vamshi \n",
"1 NaN r5-golden-batch-test-1 dasharatha.vamshi \n",
"2 log2 hilarious-yak-718 dasharatha.vamshi \n",
"3 NaN treasured-ape-95 dasharatha.vamshi \n",
"4 log2 secretive-hen-994 dasharatha.vamshi \n",
"5 log2 rogue-koi-225 dasharatha.vamshi \n",
"6 NaN r5-golden-batch-test dasharatha.vamshi \n",
"\n",
" tags.mlflow.parentRunId tags.mlflow.source.git.commit \\\n",
"0 839ba85648e04ff79c411ffdce21213f 75c16b31e98f3fb1db70c11a6bd21aade07567d6 \n",
"1 NaN 75c16b31e98f3fb1db70c11a6bd21aade07567d6 \n",
"2 b64389f4be80438eac4e87396f52ff96 75c16b31e98f3fb1db70c11a6bd21aade07567d6 \n",
"3 b64389f4be80438eac4e87396f52ff96 75c16b31e98f3fb1db70c11a6bd21aade07567d6 \n",
"4 b64389f4be80438eac4e87396f52ff96 75c16b31e98f3fb1db70c11a6bd21aade07567d6 \n",
"5 b64389f4be80438eac4e87396f52ff96 75c16b31e98f3fb1db70c11a6bd21aade07567d6 \n",
"6 NaN 75c16b31e98f3fb1db70c11a6bd21aade07567d6 \n",
"\n",
" tags.algorithm tags.mlflow.source.type \\\n",
"0 RandomForestRegressor LOCAL \n",
"1 NaN LOCAL \n",
"2 RandomForestRegressor LOCAL \n",
"3 NaN LOCAL \n",
"4 RandomForestRegressor LOCAL \n",
"5 RandomForestRegressor LOCAL \n",
"6 NaN LOCAL \n",
"\n",
" tags.mlflow.source.name \\\n",
"0 D:/ilens-ai/jubilant/R5/patch/r5-reaction-gold... \n",
"1 D:/ilens-ai/jubilant/R5/patch/r5-reaction-gold... \n",
"2 D:/ilens-ai/jubilant/R5/patch/r5-reaction-gold... \n",
"3 D:/ilens-ai/jubilant/R5/patch/r5-reaction-gold... \n",
"4 D:/ilens-ai/jubilant/R5/patch/r5-reaction-gold... \n",
"5 D:/ilens-ai/jubilant/R5/patch/r5-reaction-gold... \n",
"6 D:/ilens-ai/jubilant/R5/patch/r5-reaction-gold... \n",
"\n",
" tags.mlflow.log-model.history \n",
"0 [{\"run_id\": \"3eef20e89fb948078ef99847ae4b4bc0\"... \n",
"1 NaN \n",
"2 [{\"run_id\": \"14b392b1df58424b98cf47c6e7bfad7e\"... \n",
"3 NaN \n",
"4 [{\"run_id\": \"63df0f705ff44802aa8ff40a9fe0dd42\"... \n",
"5 [{\"run_id\": \"8533b5b16bf04d03b9021e4a09df31dd\"... \n",
"6 NaN \n",
"\n",
"[7 rows x 37 columns]"
]
},
"execution_count": 71,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": 72,
"id": "a16a4a83",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Index(['run_id', 'experiment_id', 'status', 'artifact_uri', 'start_time',\n",
" 'end_time', 'metrics.MAE', 'metrics.MSE', 'metrics.R2', 'metrics.MAPE',\n",
" 'metrics.RMSLE', 'metrics.RMSE', 'params.max_depth',\n",
" 'params.min_samples_split', 'params.ccp_alpha', 'params.max_samples',\n",
" 'params.min_weight_fraction_leaf', 'params.criterion',\n",
" 'params.oob_score', 'params.min_samples_leaf', 'params.warm_start',\n",
" 'params.max_leaf_nodes', 'params.n_estimators', 'params.verbose',\n",
" 'params.min_impurity_decrease', 'params.bootstrap',\n",
" 'params.random_state', 'params.n_jobs', 'params.max_features',\n",
" 'tags.mlflow.runName', 'tags.mlflow.user', 'tags.mlflow.parentRunId',\n",
" 'tags.mlflow.source.git.commit', 'tags.algorithm',\n",
" 'tags.mlflow.source.type', 'tags.mlflow.source.name',\n",
" 'tags.mlflow.log-model.history'],\n",
" dtype='object')"
]
},
"execution_count": 72,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.columns"
]
},
{
"cell_type": "code",
"execution_count": 74,
"id": "9f996874",
"metadata": {},
"outputs": [],
"source": [
"run_id_list = list(df['run_id'])\n",
"run_name_list = list(df['tags.mlflow.runName'])"
]
},
{
"cell_type": "code",
"execution_count": 78,
"id": "73c90c07",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'3eef20e89fb948078ef99847ae4b4bc0': 'stately-snake-36',\n",
" '839ba85648e04ff79c411ffdce21213f': 'r5-golden-batch-test-1',\n",
" '14b392b1df58424b98cf47c6e7bfad7e': 'hilarious-yak-718',\n",
" '0f35ac4a96fa413b9a15a54fe0b9b905': 'treasured-ape-95',\n",
" '63df0f705ff44802aa8ff40a9fe0dd42': 'secretive-hen-994',\n",
" '8533b5b16bf04d03b9021e4a09df31dd': 'rogue-koi-225',\n",
" 'b64389f4be80438eac4e87396f52ff96': 'r5-golden-batch-test'}"
]
},
"execution_count": 78,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"run_name_mapping = {}\n",
"for i in range(len(run_id_list)):\n",
" run_name_mapping[run_id_list[i]] = run_name_list[i]\n",
"run_name_mapping"
]
},
{
"cell_type": "code",
"execution_count": 39,
"id": "b397c5e1",
"metadata": {},
"outputs": [],
"source": [
"df = df[df['tags.mlflow.parentRunId'].notna()]"
]
},
{
"cell_type": "code",
"execution_count": 40,
"id": "050db45d",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>run_id</th>\n",
" <th>experiment_id</th>\n",
" <th>status</th>\n",
" <th>artifact_uri</th>\n",
" <th>start_time</th>\n",
" <th>end_time</th>\n",
" <th>metrics.MAE</th>\n",
" <th>metrics.MSE</th>\n",
" <th>metrics.R2</th>\n",
" <th>metrics.MAPE</th>\n",
" <th>...</th>\n",
" <th>params.n_jobs</th>\n",
" <th>params.max_features</th>\n",
" <th>tags.mlflow.runName</th>\n",
" <th>tags.mlflow.user</th>\n",
" <th>tags.mlflow.parentRunId</th>\n",
" <th>tags.mlflow.source.git.commit</th>\n",
" <th>tags.algorithm</th>\n",
" <th>tags.mlflow.source.type</th>\n",
" <th>tags.mlflow.source.name</th>\n",
" <th>tags.mlflow.log-model.history</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>3eef20e89fb948078ef99847ae4b4bc0</td>\n",
" <td>65</td>\n",
" <td>FINISHED</td>\n",
" <td>wasbs://mlflow-vm-container@azrmlilensqa006382...</td>\n",
" <td>2023-03-20 11:12:56.468000+00:00</td>\n",
" <td>2023-03-20 11:14:51.309000+00:00</td>\n",
" <td>538.0753</td>\n",
" <td>499454.5687</td>\n",
" <td>0.1195</td>\n",
" <td>0.0855</td>\n",
" <td>...</td>\n",
" <td>-1.0</td>\n",
" <td>1.0</td>\n",
" <td>stately-snake-36</td>\n",
" <td>dasharatha.vamshi</td>\n",
" <td>839ba85648e04ff79c411ffdce21213f</td>\n",
" <td>75c16b31e98f3fb1db70c11a6bd21aade07567d6</td>\n",
" <td>RandomForestRegressor</td>\n",
" <td>LOCAL</td>\n",
" <td>D:/ilens-ai/jubilant/R5/patch/r5-reaction-gold...</td>\n",
" <td>[{\"run_id\": \"3eef20e89fb948078ef99847ae4b4bc0\"...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>14b392b1df58424b98cf47c6e7bfad7e</td>\n",
" <td>65</td>\n",
" <td>FINISHED</td>\n",
" <td>wasbs://mlflow-vm-container@azrmlilensqa006382...</td>\n",
" <td>2023-03-20 11:05:34.682000+00:00</td>\n",
" <td>2023-03-20 11:07:24.960000+00:00</td>\n",
" <td>566.4853</td>\n",
" <td>708495.3303</td>\n",
" <td>0.1640</td>\n",
" <td>0.0880</td>\n",
" <td>...</td>\n",
" <td>-1.0</td>\n",
" <td>log2</td>\n",
" <td>hilarious-yak-718</td>\n",
" <td>dasharatha.vamshi</td>\n",
" <td>b64389f4be80438eac4e87396f52ff96</td>\n",
" <td>75c16b31e98f3fb1db70c11a6bd21aade07567d6</td>\n",
" <td>RandomForestRegressor</td>\n",
" <td>LOCAL</td>\n",
" <td>D:/ilens-ai/jubilant/R5/patch/r5-reaction-gold...</td>\n",
" <td>[{\"run_id\": \"14b392b1df58424b98cf47c6e7bfad7e\"...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>0f35ac4a96fa413b9a15a54fe0b9b905</td>\n",
" <td>65</td>\n",
" <td>FAILED</td>\n",
" <td>wasbs://mlflow-vm-container@azrmlilensqa006382...</td>\n",
" <td>2023-03-20 11:04:48.940000+00:00</td>\n",
" <td>2023-03-20 11:05:26.504000+00:00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>treasured-ape-95</td>\n",
" <td>dasharatha.vamshi</td>\n",
" <td>b64389f4be80438eac4e87396f52ff96</td>\n",
" <td>75c16b31e98f3fb1db70c11a6bd21aade07567d6</td>\n",
" <td>NaN</td>\n",
" <td>LOCAL</td>\n",
" <td>D:/ilens-ai/jubilant/R5/patch/r5-reaction-gold...</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>63df0f705ff44802aa8ff40a9fe0dd42</td>\n",
" <td>65</td>\n",
" <td>FINISHED</td>\n",
" <td>wasbs://mlflow-vm-container@azrmlilensqa006382...</td>\n",
" <td>2023-03-20 11:01:50.710000+00:00</td>\n",
" <td>2023-03-20 11:03:15.779000+00:00</td>\n",
" <td>464.6541</td>\n",
" <td>398781.9839</td>\n",
" <td>0.3022</td>\n",
" <td>0.0686</td>\n",
" <td>...</td>\n",
" <td>-1.0</td>\n",
" <td>log2</td>\n",
" <td>secretive-hen-994</td>\n",
" <td>dasharatha.vamshi</td>\n",
" <td>b64389f4be80438eac4e87396f52ff96</td>\n",
" <td>75c16b31e98f3fb1db70c11a6bd21aade07567d6</td>\n",
" <td>RandomForestRegressor</td>\n",
" <td>LOCAL</td>\n",
" <td>D:/ilens-ai/jubilant/R5/patch/r5-reaction-gold...</td>\n",
" <td>[{\"run_id\": \"63df0f705ff44802aa8ff40a9fe0dd42\"...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>8533b5b16bf04d03b9021e4a09df31dd</td>\n",
" <td>65</td>\n",
" <td>FINISHED</td>\n",
" <td>wasbs://mlflow-vm-container@azrmlilensqa006382...</td>\n",
" <td>2023-03-20 10:59:10.251000+00:00</td>\n",
" <td>2023-03-20 11:01:36.039000+00:00</td>\n",
" <td>564.6727</td>\n",
" <td>644844.6845</td>\n",
" <td>0.2292</td>\n",
" <td>0.0872</td>\n",
" <td>...</td>\n",
" <td>-1.0</td>\n",
" <td>log2</td>\n",
" <td>rogue-koi-225</td>\n",
" <td>dasharatha.vamshi</td>\n",
" <td>b64389f4be80438eac4e87396f52ff96</td>\n",
" <td>75c16b31e98f3fb1db70c11a6bd21aade07567d6</td>\n",
" <td>RandomForestRegressor</td>\n",
" <td>LOCAL</td>\n",
" <td>D:/ilens-ai/jubilant/R5/patch/r5-reaction-gold...</td>\n",
" <td>[{\"run_id\": \"8533b5b16bf04d03b9021e4a09df31dd\"...</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 37 columns</p>\n",
"</div>"
],
"text/plain": [
" run_id experiment_id status \\\n",
"0 3eef20e89fb948078ef99847ae4b4bc0 65 FINISHED \n",
"2 14b392b1df58424b98cf47c6e7bfad7e 65 FINISHED \n",
"3 0f35ac4a96fa413b9a15a54fe0b9b905 65 FAILED \n",
"4 63df0f705ff44802aa8ff40a9fe0dd42 65 FINISHED \n",
"5 8533b5b16bf04d03b9021e4a09df31dd 65 FINISHED \n",
"\n",
" artifact_uri \\\n",
"0 wasbs://mlflow-vm-container@azrmlilensqa006382... \n",
"2 wasbs://mlflow-vm-container@azrmlilensqa006382... \n",
"3 wasbs://mlflow-vm-container@azrmlilensqa006382... \n",
"4 wasbs://mlflow-vm-container@azrmlilensqa006382... \n",
"5 wasbs://mlflow-vm-container@azrmlilensqa006382... \n",
"\n",
" start_time end_time \\\n",
"0 2023-03-20 11:12:56.468000+00:00 2023-03-20 11:14:51.309000+00:00 \n",
"2 2023-03-20 11:05:34.682000+00:00 2023-03-20 11:07:24.960000+00:00 \n",
"3 2023-03-20 11:04:48.940000+00:00 2023-03-20 11:05:26.504000+00:00 \n",
"4 2023-03-20 11:01:50.710000+00:00 2023-03-20 11:03:15.779000+00:00 \n",
"5 2023-03-20 10:59:10.251000+00:00 2023-03-20 11:01:36.039000+00:00 \n",
"\n",
" metrics.MAE metrics.MSE metrics.R2 metrics.MAPE ... params.n_jobs \\\n",
"0 538.0753 499454.5687 0.1195 0.0855 ... -1.0 \n",
"2 566.4853 708495.3303 0.1640 0.0880 ... -1.0 \n",
"3 NaN NaN NaN NaN ... NaN \n",
"4 464.6541 398781.9839 0.3022 0.0686 ... -1.0 \n",
"5 564.6727 644844.6845 0.2292 0.0872 ... -1.0 \n",
"\n",
" params.max_features tags.mlflow.runName tags.mlflow.user \\\n",
"0 1.0 stately-snake-36 dasharatha.vamshi \n",
"2 log2 hilarious-yak-718 dasharatha.vamshi \n",
"3 NaN treasured-ape-95 dasharatha.vamshi \n",
"4 log2 secretive-hen-994 dasharatha.vamshi \n",
"5 log2 rogue-koi-225 dasharatha.vamshi \n",
"\n",
" tags.mlflow.parentRunId tags.mlflow.source.git.commit \\\n",
"0 839ba85648e04ff79c411ffdce21213f 75c16b31e98f3fb1db70c11a6bd21aade07567d6 \n",
"2 b64389f4be80438eac4e87396f52ff96 75c16b31e98f3fb1db70c11a6bd21aade07567d6 \n",
"3 b64389f4be80438eac4e87396f52ff96 75c16b31e98f3fb1db70c11a6bd21aade07567d6 \n",
"4 b64389f4be80438eac4e87396f52ff96 75c16b31e98f3fb1db70c11a6bd21aade07567d6 \n",
"5 b64389f4be80438eac4e87396f52ff96 75c16b31e98f3fb1db70c11a6bd21aade07567d6 \n",
"\n",
" tags.algorithm tags.mlflow.source.type \\\n",
"0 RandomForestRegressor LOCAL \n",
"2 RandomForestRegressor LOCAL \n",
"3 NaN LOCAL \n",
"4 RandomForestRegressor LOCAL \n",
"5 RandomForestRegressor LOCAL \n",
"\n",
" tags.mlflow.source.name \\\n",
"0 D:/ilens-ai/jubilant/R5/patch/r5-reaction-gold... \n",
"2 D:/ilens-ai/jubilant/R5/patch/r5-reaction-gold... \n",
"3 D:/ilens-ai/jubilant/R5/patch/r5-reaction-gold... \n",
"4 D:/ilens-ai/jubilant/R5/patch/r5-reaction-gold... \n",
"5 D:/ilens-ai/jubilant/R5/patch/r5-reaction-gold... \n",
"\n",
" tags.mlflow.log-model.history \n",
"0 [{\"run_id\": \"3eef20e89fb948078ef99847ae4b4bc0\"... \n",
"2 [{\"run_id\": \"14b392b1df58424b98cf47c6e7bfad7e\"... \n",
"3 NaN \n",
"4 [{\"run_id\": \"63df0f705ff44802aa8ff40a9fe0dd42\"... \n",
"5 [{\"run_id\": \"8533b5b16bf04d03b9021e4a09df31dd\"... \n",
"\n",
"[5 rows x 37 columns]"
]
},
"execution_count": 40,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": 41,
"id": "88c94db3",
"metadata": {},
"outputs": [],
"source": [
"df = df[df['tags.mlflow.log-model.history'].notna()]"
]
},
{
"cell_type": "code",
"execution_count": 42,
"id": "d801e437",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>run_id</th>\n",
" <th>experiment_id</th>\n",
" <th>status</th>\n",
" <th>artifact_uri</th>\n",
" <th>start_time</th>\n",
" <th>end_time</th>\n",
" <th>metrics.MAE</th>\n",
" <th>metrics.MSE</th>\n",
" <th>metrics.R2</th>\n",
" <th>metrics.MAPE</th>\n",
" <th>...</th>\n",
" <th>params.n_jobs</th>\n",
" <th>params.max_features</th>\n",
" <th>tags.mlflow.runName</th>\n",
" <th>tags.mlflow.user</th>\n",
" <th>tags.mlflow.parentRunId</th>\n",
" <th>tags.mlflow.source.git.commit</th>\n",
" <th>tags.algorithm</th>\n",
" <th>tags.mlflow.source.type</th>\n",
" <th>tags.mlflow.source.name</th>\n",
" <th>tags.mlflow.log-model.history</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>3eef20e89fb948078ef99847ae4b4bc0</td>\n",
" <td>65</td>\n",
" <td>FINISHED</td>\n",
" <td>wasbs://mlflow-vm-container@azrmlilensqa006382...</td>\n",
" <td>2023-03-20 11:12:56.468000+00:00</td>\n",
" <td>2023-03-20 11:14:51.309000+00:00</td>\n",
" <td>538.0753</td>\n",
" <td>499454.5687</td>\n",
" <td>0.1195</td>\n",
" <td>0.0855</td>\n",
" <td>...</td>\n",
" <td>-1.0</td>\n",
" <td>1.0</td>\n",
" <td>stately-snake-36</td>\n",
" <td>dasharatha.vamshi</td>\n",
" <td>839ba85648e04ff79c411ffdce21213f</td>\n",
" <td>75c16b31e98f3fb1db70c11a6bd21aade07567d6</td>\n",
" <td>RandomForestRegressor</td>\n",
" <td>LOCAL</td>\n",
" <td>D:/ilens-ai/jubilant/R5/patch/r5-reaction-gold...</td>\n",
" <td>[{\"run_id\": \"3eef20e89fb948078ef99847ae4b4bc0\"...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>14b392b1df58424b98cf47c6e7bfad7e</td>\n",
" <td>65</td>\n",
" <td>FINISHED</td>\n",
" <td>wasbs://mlflow-vm-container@azrmlilensqa006382...</td>\n",
" <td>2023-03-20 11:05:34.682000+00:00</td>\n",
" <td>2023-03-20 11:07:24.960000+00:00</td>\n",
" <td>566.4853</td>\n",
" <td>708495.3303</td>\n",
" <td>0.1640</td>\n",
" <td>0.0880</td>\n",
" <td>...</td>\n",
" <td>-1.0</td>\n",
" <td>log2</td>\n",
" <td>hilarious-yak-718</td>\n",
" <td>dasharatha.vamshi</td>\n",
" <td>b64389f4be80438eac4e87396f52ff96</td>\n",
" <td>75c16b31e98f3fb1db70c11a6bd21aade07567d6</td>\n",
" <td>RandomForestRegressor</td>\n",
" <td>LOCAL</td>\n",
" <td>D:/ilens-ai/jubilant/R5/patch/r5-reaction-gold...</td>\n",
" <td>[{\"run_id\": \"14b392b1df58424b98cf47c6e7bfad7e\"...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>63df0f705ff44802aa8ff40a9fe0dd42</td>\n",
" <td>65</td>\n",
" <td>FINISHED</td>\n",
" <td>wasbs://mlflow-vm-container@azrmlilensqa006382...</td>\n",
" <td>2023-03-20 11:01:50.710000+00:00</td>\n",
" <td>2023-03-20 11:03:15.779000+00:00</td>\n",
" <td>464.6541</td>\n",
" <td>398781.9839</td>\n",
" <td>0.3022</td>\n",
" <td>0.0686</td>\n",
" <td>...</td>\n",
" <td>-1.0</td>\n",
" <td>log2</td>\n",
" <td>secretive-hen-994</td>\n",
" <td>dasharatha.vamshi</td>\n",
" <td>b64389f4be80438eac4e87396f52ff96</td>\n",
" <td>75c16b31e98f3fb1db70c11a6bd21aade07567d6</td>\n",
" <td>RandomForestRegressor</td>\n",
" <td>LOCAL</td>\n",
" <td>D:/ilens-ai/jubilant/R5/patch/r5-reaction-gold...</td>\n",
" <td>[{\"run_id\": \"63df0f705ff44802aa8ff40a9fe0dd42\"...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>8533b5b16bf04d03b9021e4a09df31dd</td>\n",
" <td>65</td>\n",
" <td>FINISHED</td>\n",
" <td>wasbs://mlflow-vm-container@azrmlilensqa006382...</td>\n",
" <td>2023-03-20 10:59:10.251000+00:00</td>\n",
" <td>2023-03-20 11:01:36.039000+00:00</td>\n",
" <td>564.6727</td>\n",
" <td>644844.6845</td>\n",
" <td>0.2292</td>\n",
" <td>0.0872</td>\n",
" <td>...</td>\n",
" <td>-1.0</td>\n",
" <td>log2</td>\n",
" <td>rogue-koi-225</td>\n",
" <td>dasharatha.vamshi</td>\n",
" <td>b64389f4be80438eac4e87396f52ff96</td>\n",
" <td>75c16b31e98f3fb1db70c11a6bd21aade07567d6</td>\n",
" <td>RandomForestRegressor</td>\n",
" <td>LOCAL</td>\n",
" <td>D:/ilens-ai/jubilant/R5/patch/r5-reaction-gold...</td>\n",
" <td>[{\"run_id\": \"8533b5b16bf04d03b9021e4a09df31dd\"...</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>4 rows × 37 columns</p>\n",
"</div>"
],
"text/plain": [
" run_id experiment_id status \\\n",
"0 3eef20e89fb948078ef99847ae4b4bc0 65 FINISHED \n",
"2 14b392b1df58424b98cf47c6e7bfad7e 65 FINISHED \n",
"4 63df0f705ff44802aa8ff40a9fe0dd42 65 FINISHED \n",
"5 8533b5b16bf04d03b9021e4a09df31dd 65 FINISHED \n",
"\n",
" artifact_uri \\\n",
"0 wasbs://mlflow-vm-container@azrmlilensqa006382... \n",
"2 wasbs://mlflow-vm-container@azrmlilensqa006382... \n",
"4 wasbs://mlflow-vm-container@azrmlilensqa006382... \n",
"5 wasbs://mlflow-vm-container@azrmlilensqa006382... \n",
"\n",
" start_time end_time \\\n",
"0 2023-03-20 11:12:56.468000+00:00 2023-03-20 11:14:51.309000+00:00 \n",
"2 2023-03-20 11:05:34.682000+00:00 2023-03-20 11:07:24.960000+00:00 \n",
"4 2023-03-20 11:01:50.710000+00:00 2023-03-20 11:03:15.779000+00:00 \n",
"5 2023-03-20 10:59:10.251000+00:00 2023-03-20 11:01:36.039000+00:00 \n",
"\n",
" metrics.MAE metrics.MSE metrics.R2 metrics.MAPE ... params.n_jobs \\\n",
"0 538.0753 499454.5687 0.1195 0.0855 ... -1.0 \n",
"2 566.4853 708495.3303 0.1640 0.0880 ... -1.0 \n",
"4 464.6541 398781.9839 0.3022 0.0686 ... -1.0 \n",
"5 564.6727 644844.6845 0.2292 0.0872 ... -1.0 \n",
"\n",
" params.max_features tags.mlflow.runName tags.mlflow.user \\\n",
"0 1.0 stately-snake-36 dasharatha.vamshi \n",
"2 log2 hilarious-yak-718 dasharatha.vamshi \n",
"4 log2 secretive-hen-994 dasharatha.vamshi \n",
"5 log2 rogue-koi-225 dasharatha.vamshi \n",
"\n",
" tags.mlflow.parentRunId tags.mlflow.source.git.commit \\\n",
"0 839ba85648e04ff79c411ffdce21213f 75c16b31e98f3fb1db70c11a6bd21aade07567d6 \n",
"2 b64389f4be80438eac4e87396f52ff96 75c16b31e98f3fb1db70c11a6bd21aade07567d6 \n",
"4 b64389f4be80438eac4e87396f52ff96 75c16b31e98f3fb1db70c11a6bd21aade07567d6 \n",
"5 b64389f4be80438eac4e87396f52ff96 75c16b31e98f3fb1db70c11a6bd21aade07567d6 \n",
"\n",
" tags.algorithm tags.mlflow.source.type \\\n",
"0 RandomForestRegressor LOCAL \n",
"2 RandomForestRegressor LOCAL \n",
"4 RandomForestRegressor LOCAL \n",
"5 RandomForestRegressor LOCAL \n",
"\n",
" tags.mlflow.source.name \\\n",
"0 D:/ilens-ai/jubilant/R5/patch/r5-reaction-gold... \n",
"2 D:/ilens-ai/jubilant/R5/patch/r5-reaction-gold... \n",
"4 D:/ilens-ai/jubilant/R5/patch/r5-reaction-gold... \n",
"5 D:/ilens-ai/jubilant/R5/patch/r5-reaction-gold... \n",
"\n",
" tags.mlflow.log-model.history \n",
"0 [{\"run_id\": \"3eef20e89fb948078ef99847ae4b4bc0\"... \n",
"2 [{\"run_id\": \"14b392b1df58424b98cf47c6e7bfad7e\"... \n",
"4 [{\"run_id\": \"63df0f705ff44802aa8ff40a9fe0dd42\"... \n",
"5 [{\"run_id\": \"8533b5b16bf04d03b9021e4a09df31dd\"... \n",
"\n",
"[4 rows x 37 columns]"
]
},
"execution_count": 42,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": 52,
"id": "9c160d8c",
"metadata": {},
"outputs": [],
"source": [
"parent_runs = list(set(list(df['tags.mlflow.parentRunId'])))"
]
},
{
"cell_type": "code",
"execution_count": 53,
"id": "0c374845",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['b64389f4be80438eac4e87396f52ff96', '839ba85648e04ff79c411ffdce21213f']"
]
},
"execution_count": 53,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"parent_runs"
]
},
{
"cell_type": "code",
"execution_count": 54,
"id": "08503780",
"metadata": {},
"outputs": [],
"source": [
"cols = ['run_id', 'artifact_uri', 'start_time', 'end_time', 'tags.mlflow.parentRunId',\n",
" 'tags.mlflow.log-model.history']"
]
},
{
"cell_type": "code",
"execution_count": 69,
"id": "d7a097ca",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"3\n",
"['14b392b1df58424b98cf47c6e7bfad7e', '63df0f705ff44802aa8ff40a9fe0dd42', '8533b5b16bf04d03b9021e4a09df31dd']\n",
"{'run_id': '63df0f705ff44802aa8ff40a9fe0dd42', 'artifact_uri': 'wasbs://mlflow-vm-container@azrmlilensqa006382180551.blob.core.windows.net/mlflow_qa/65/63df0f705ff44802aa8ff40a9fe0dd42/artifacts', 'start_time': '2023-03-20 11:01:50.710000+00:00', 'end_time': '2023-03-20 11:03:15.779000+00:00', 'tags.mlflow.parentRunId': 'b64389f4be80438eac4e87396f52ff96', 'tags.mlflow.log-model.history': '[{\"run_id\": \"63df0f705ff44802aa8ff40a9fe0dd42\", \"artifact_path\": \"r5_model\", \"utc_time_created\": \"2023-03-20 11:03:10.815296\", \"flavors\": {\"python_function\": {\"model_path\": \"model.pkl\", \"loader_module\": \"mlflow.sklearn\", \"python_version\": \"3.8.16\", \"env\": \"conda.yaml\"}, \"sklearn\": {\"pickled_model\": \"model.pkl\", \"sklearn_version\": \"1.1.3\", \"serialization_format\": \"cloudpickle\"}}, \"model_uuid\": null}]'}\n",
"{'run_id': '8533b5b16bf04d03b9021e4a09df31dd', 'artifact_uri': 'wasbs://mlflow-vm-container@azrmlilensqa006382180551.blob.core.windows.net/mlflow_qa/65/8533b5b16bf04d03b9021e4a09df31dd/artifacts', 'start_time': '2023-03-20 10:59:10.251000+00:00', 'end_time': '2023-03-20 11:01:36.039000+00:00', 'tags.mlflow.parentRunId': 'b64389f4be80438eac4e87396f52ff96', 'tags.mlflow.log-model.history': '[{\"run_id\": \"8533b5b16bf04d03b9021e4a09df31dd\", \"artifact_path\": \"r5_model\", \"utc_time_created\": \"2023-03-20 11:01:31.173586\", \"flavors\": {\"python_function\": {\"model_path\": \"model.pkl\", \"loader_module\": \"mlflow.sklearn\", \"python_version\": \"3.8.16\", \"env\": \"conda.yaml\"}, \"sklearn\": {\"pickled_model\": \"model.pkl\", \"sklearn_version\": \"1.1.3\", \"serialization_format\": \"cloudpickle\"}}, \"model_uuid\": null}]'}\n",
"1\n",
"['3eef20e89fb948078ef99847ae4b4bc0']\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"C:\\Users\\dasharatha.vamshi\\AppData\\Local\\Temp\\ipykernel_28408\\2128383884.py:9: FutureWarning: Using short name for 'orient' is deprecated. Only the options: ('dict', list, 'series', 'split', 'records', 'index') will be used in a future version. Use one of the above to silence this warning.\n",
" all_records = temp_df.to_dict('r')\n",
"C:\\Users\\dasharatha.vamshi\\AppData\\Local\\Temp\\ipykernel_28408\\2128383884.py:9: FutureWarning: Using short name for 'orient' is deprecated. Only the options: ('dict', list, 'series', 'split', 'records', 'index') will be used in a future version. Use one of the above to silence this warning.\n",
" all_records = temp_df.to_dict('r')\n"
]
}
],
"source": [
"for parent_run_id in parent_runs:\n",
" temp_df = df1[df1['tags.mlflow.parentRunId'] == parent_run_id]\n",
" temp_df = temp_df[temp_df['tags.mlflow.log-model.history'].notna()]\n",
" temp_df = temp_df[cols]\n",
" total_models_present = len(temp_df)\n",
" print(total_models_present)\n",
" print(list(temp_df['run_id']))\n",
" temp_df = temp_df.iloc[1:]\n",
" all_records = temp_df.to_dict('r')\n",
" for i in all_records:\n",
" print(i)"
]
},
{
"cell_type": "code",
"execution_count": 57,
"id": "aa3a2e80",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>run_id</th>\n",
" <th>experiment_id</th>\n",
" <th>status</th>\n",
" <th>artifact_uri</th>\n",
" <th>start_time</th>\n",
" <th>end_time</th>\n",
" <th>metrics.MAE</th>\n",
" <th>metrics.MSE</th>\n",
" <th>metrics.R2</th>\n",
" <th>metrics.MAPE</th>\n",
" <th>...</th>\n",
" <th>params.n_jobs</th>\n",
" <th>params.max_features</th>\n",
" <th>tags.mlflow.runName</th>\n",
" <th>tags.mlflow.user</th>\n",
" <th>tags.mlflow.parentRunId</th>\n",
" <th>tags.mlflow.source.git.commit</th>\n",
" <th>tags.algorithm</th>\n",
" <th>tags.mlflow.source.type</th>\n",
" <th>tags.mlflow.source.name</th>\n",
" <th>tags.mlflow.log-model.history</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>14b392b1df58424b98cf47c6e7bfad7e</td>\n",
" <td>65</td>\n",
" <td>FINISHED</td>\n",
" <td>wasbs://mlflow-vm-container@azrmlilensqa006382...</td>\n",
" <td>2023-03-20 11:05:34.682000+00:00</td>\n",
" <td>2023-03-20 11:07:24.960000+00:00</td>\n",
" <td>566.4853</td>\n",
" <td>708495.3303</td>\n",
" <td>0.1640</td>\n",
" <td>0.0880</td>\n",
" <td>...</td>\n",
" <td>-1.0</td>\n",
" <td>log2</td>\n",
" <td>hilarious-yak-718</td>\n",
" <td>dasharatha.vamshi</td>\n",
" <td>b64389f4be80438eac4e87396f52ff96</td>\n",
" <td>75c16b31e98f3fb1db70c11a6bd21aade07567d6</td>\n",
" <td>RandomForestRegressor</td>\n",
" <td>LOCAL</td>\n",
" <td>D:/ilens-ai/jubilant/R5/patch/r5-reaction-gold...</td>\n",
" <td>[{\"run_id\": \"14b392b1df58424b98cf47c6e7bfad7e\"...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>0f35ac4a96fa413b9a15a54fe0b9b905</td>\n",
" <td>65</td>\n",
" <td>FAILED</td>\n",
" <td>wasbs://mlflow-vm-container@azrmlilensqa006382...</td>\n",
" <td>2023-03-20 11:04:48.940000+00:00</td>\n",
" <td>2023-03-20 11:05:26.504000+00:00</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>treasured-ape-95</td>\n",
" <td>dasharatha.vamshi</td>\n",
" <td>b64389f4be80438eac4e87396f52ff96</td>\n",
" <td>75c16b31e98f3fb1db70c11a6bd21aade07567d6</td>\n",
" <td>NaN</td>\n",
" <td>LOCAL</td>\n",
" <td>D:/ilens-ai/jubilant/R5/patch/r5-reaction-gold...</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>63df0f705ff44802aa8ff40a9fe0dd42</td>\n",
" <td>65</td>\n",
" <td>FINISHED</td>\n",
" <td>wasbs://mlflow-vm-container@azrmlilensqa006382...</td>\n",
" <td>2023-03-20 11:01:50.710000+00:00</td>\n",
" <td>2023-03-20 11:03:15.779000+00:00</td>\n",
" <td>464.6541</td>\n",
" <td>398781.9839</td>\n",
" <td>0.3022</td>\n",
" <td>0.0686</td>\n",
" <td>...</td>\n",
" <td>-1.0</td>\n",
" <td>log2</td>\n",
" <td>secretive-hen-994</td>\n",
" <td>dasharatha.vamshi</td>\n",
" <td>b64389f4be80438eac4e87396f52ff96</td>\n",
" <td>75c16b31e98f3fb1db70c11a6bd21aade07567d6</td>\n",
" <td>RandomForestRegressor</td>\n",
" <td>LOCAL</td>\n",
" <td>D:/ilens-ai/jubilant/R5/patch/r5-reaction-gold...</td>\n",
" <td>[{\"run_id\": \"63df0f705ff44802aa8ff40a9fe0dd42\"...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>8533b5b16bf04d03b9021e4a09df31dd</td>\n",
" <td>65</td>\n",
" <td>FINISHED</td>\n",
" <td>wasbs://mlflow-vm-container@azrmlilensqa006382...</td>\n",
" <td>2023-03-20 10:59:10.251000+00:00</td>\n",
" <td>2023-03-20 11:01:36.039000+00:00</td>\n",
" <td>564.6727</td>\n",
" <td>644844.6845</td>\n",
" <td>0.2292</td>\n",
" <td>0.0872</td>\n",
" <td>...</td>\n",
" <td>-1.0</td>\n",
" <td>log2</td>\n",
" <td>rogue-koi-225</td>\n",
" <td>dasharatha.vamshi</td>\n",
" <td>b64389f4be80438eac4e87396f52ff96</td>\n",
" <td>75c16b31e98f3fb1db70c11a6bd21aade07567d6</td>\n",
" <td>RandomForestRegressor</td>\n",
" <td>LOCAL</td>\n",
" <td>D:/ilens-ai/jubilant/R5/patch/r5-reaction-gold...</td>\n",
" <td>[{\"run_id\": \"8533b5b16bf04d03b9021e4a09df31dd\"...</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>4 rows × 37 columns</p>\n",
"</div>"
],
"text/plain": [
" run_id experiment_id status \\\n",
"2 14b392b1df58424b98cf47c6e7bfad7e 65 FINISHED \n",
"3 0f35ac4a96fa413b9a15a54fe0b9b905 65 FAILED \n",
"4 63df0f705ff44802aa8ff40a9fe0dd42 65 FINISHED \n",
"5 8533b5b16bf04d03b9021e4a09df31dd 65 FINISHED \n",
"\n",
" artifact_uri \\\n",
"2 wasbs://mlflow-vm-container@azrmlilensqa006382... \n",
"3 wasbs://mlflow-vm-container@azrmlilensqa006382... \n",
"4 wasbs://mlflow-vm-container@azrmlilensqa006382... \n",
"5 wasbs://mlflow-vm-container@azrmlilensqa006382... \n",
"\n",
" start_time end_time \\\n",
"2 2023-03-20 11:05:34.682000+00:00 2023-03-20 11:07:24.960000+00:00 \n",
"3 2023-03-20 11:04:48.940000+00:00 2023-03-20 11:05:26.504000+00:00 \n",
"4 2023-03-20 11:01:50.710000+00:00 2023-03-20 11:03:15.779000+00:00 \n",
"5 2023-03-20 10:59:10.251000+00:00 2023-03-20 11:01:36.039000+00:00 \n",
"\n",
" metrics.MAE metrics.MSE metrics.R2 metrics.MAPE ... params.n_jobs \\\n",
"2 566.4853 708495.3303 0.1640 0.0880 ... -1.0 \n",
"3 NaN NaN NaN NaN ... NaN \n",
"4 464.6541 398781.9839 0.3022 0.0686 ... -1.0 \n",
"5 564.6727 644844.6845 0.2292 0.0872 ... -1.0 \n",
"\n",
" params.max_features tags.mlflow.runName tags.mlflow.user \\\n",
"2 log2 hilarious-yak-718 dasharatha.vamshi \n",
"3 NaN treasured-ape-95 dasharatha.vamshi \n",
"4 log2 secretive-hen-994 dasharatha.vamshi \n",
"5 log2 rogue-koi-225 dasharatha.vamshi \n",
"\n",
" tags.mlflow.parentRunId tags.mlflow.source.git.commit \\\n",
"2 b64389f4be80438eac4e87396f52ff96 75c16b31e98f3fb1db70c11a6bd21aade07567d6 \n",
"3 b64389f4be80438eac4e87396f52ff96 75c16b31e98f3fb1db70c11a6bd21aade07567d6 \n",
"4 b64389f4be80438eac4e87396f52ff96 75c16b31e98f3fb1db70c11a6bd21aade07567d6 \n",
"5 b64389f4be80438eac4e87396f52ff96 75c16b31e98f3fb1db70c11a6bd21aade07567d6 \n",
"\n",
" tags.algorithm tags.mlflow.source.type \\\n",
"2 RandomForestRegressor LOCAL \n",
"3 NaN LOCAL \n",
"4 RandomForestRegressor LOCAL \n",
"5 RandomForestRegressor LOCAL \n",
"\n",
" tags.mlflow.source.name \\\n",
"2 D:/ilens-ai/jubilant/R5/patch/r5-reaction-gold... \n",
"3 D:/ilens-ai/jubilant/R5/patch/r5-reaction-gold... \n",
"4 D:/ilens-ai/jubilant/R5/patch/r5-reaction-gold... \n",
"5 D:/ilens-ai/jubilant/R5/patch/r5-reaction-gold... \n",
"\n",
" tags.mlflow.log-model.history \n",
"2 [{\"run_id\": \"14b392b1df58424b98cf47c6e7bfad7e\"... \n",
"3 NaN \n",
"4 [{\"run_id\": \"63df0f705ff44802aa8ff40a9fe0dd42\"... \n",
"5 [{\"run_id\": \"8533b5b16bf04d03b9021e4a09df31dd\"... \n",
"\n",
"[4 rows x 37 columns]"
]
},
"execution_count": 57,
"metadata": {},
"output_type": "execute_result"
}
],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "5c553df4",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.16"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment