Template Contents
The following is the directory structure for this template:
- Data This contains Data for scoring. Other data is downloaded during the solution workflow
- R This contains the R code to prepare training/testing/evaluation set, train the multi-class classifier and evaluate the model.
- Python This contains the Python code to prepare training/testing/evaluation set, train the multi-class classifier and evaluate the model.
- SQLR Stored procedures in SQL implement the model training workflow with R code.
- SQLPy Stored procedures in SQL implement the model training workflow with Python code.
- Resources This directory contains other resources for the solution package.
Data
Data for training and testing will also be downloaded and added to this directory, so more files will be present once the solution has been run once.
File | Description |
News_To_Score | Text file containing new data for scoring. |
Model Development in R
File | Description |
TextClassificationR.ipynb | Create features on the fly for the training and testing set, train model, make predictions, and evaluate the model in Jupyter notebook. |
run_modeling_main.R | Create features on the fly for the training and testing set, train model, make predictions, and evaluate the model. |
Operationalize in SQL R
Stored procedures in SQL implement the model training workflow with R code.
File | Description |
Load_Data.ps1 | Loads all data for the solution if you'd like to create a second instance of the solution on the same server |
execute_yourself.sql | Runs through all the steps of the solution |
step0_create_tables.sql | Create data tables, invoked in Load_Data.ps1 |
step1_create_features_train.sql | Create features on the fly and train model |
step2_score.sql | Scores data with model created in step1 |
step3_evaluate.sql | Evaluates model created in step1 |
Model Development in Python
File | Description |
TextClassificationR.ipynb | Create features on the fly for the training and testing set, train model, make predictions, and evaluate the model in Jupyter notebook. |
run_modeling_main.py | Create features on the fly for the training and testing set, train model, make predictions, and evaluate the model. |
Operationalize in SQL Python
Stored procedures in SQL implement the model training workflow with Python code.
File | Description |
Load_Data.ps1 | Loads all data for the solution if you'd like to create a second instance of the solution on the same server |
execute_yourself.sql | Runs through all the steps of the solution |
step0_create_tables.sql | Create data tables, invoked in Load_Data.ps1 |
step1_create_features_train.sql | Create features on the fly and train model |
step2_score.sql | Scores data with model created in step1 |
step3_evaluate.sql | Evaluates model created in step1 |
Resources for the Solution Package
File | Description |
.\Resources\ActionScripts\ConfigureSQL.ps1 | Configures SQL, called from SetupVM.ps1 |
.\Resources\ActionScripts\CreateDatabase.sql | Creates the database for this solution, called from ConfigureSQL.ps1 |
.\Resources\ActionScripts\CreateSQLObjectsPy.sql | Creates the tables and stored procedures for this solution, called from ConfigureSQL.ps1 |
.\Resources\ActionScripts\CreateSQLObjectsR.sql | Creates the tables and stored procedures for this solution, called from ConfigureSQL.ps1 |
.\Resources\ActionScripts\TextClassificationSetup.ps1 | Configures SQL, creates and populates database |
.\Resources\ActionScripts\SolutionHelp.url | URL to the help page |
< Home