IBM · qpresley · Jul 29, 2020 · Jul 28, 2020 · Jul 28, 2020 · Jul 28, 2020
@@ -0,0 +1,137 @@
+# Instructions
+
+This repository contains notebooks and datasets that will allow Db2 customers build ML models with IBM Db2's in-database machine learning capabilities.
+
+# Table of Contents
+1. [Prerequistes](#Prerequisites)
+2. [Downloading the Dataset](#Downloads)
+3. [Loading the Dataset into a Db2 Table](#Loading)
+4. [Notebook-specific requirements](#Notebook-specific)
+5. [Troubleshooting](#Troubleshooting)
+6. [Other Resources](#Resources)
+
+## 1. Prerequisites <a name="Prerequisites"></a>
+
+You must meet the following requirements to use the machine learning functionality in Db2:
+- Install the `ibm_db` python package
+- Enable IDAX Stored Procedures for ML in your Db2 instance
+
+### 1.1 Installing the ibm_db python package 
+
+Please follow the documentation [here](https://github.com/ibmdb/python-ibmdb#-installation) to install the `ibm_db` python package. This will allow you to connect to and communicate with your Db2 instance.
+
+
+### 1.2 Enable IDAX Stored Proceduces for ML in your Db2 instance
+
+Please follow the documentation [here](https://www.ibm.com/support/knowledgecenter/SSEPGG_11.5.0/com.ibm.db2.luw.ml.doc/doc/ml_prereqs.html) to enable ML functionality in your Db2 instance.
+
+
+## 2. Downloading the Datasets <a name="Downloads"></a>
+### 2.1 Regression with GoSales
+
+Download the file [GoSales.csv](Datasets/GoSales.csv) from the `Datasets` directory
+
+### 2.2 Classification with Titanic
+
+Download the file [Titanic.csv](Datasets/Titanic.csv) from the `Datasets` directory
+
+## 3. Loading the Dataset into a Db2 Table <a name="Loading"></a>
+
+To load the TITANIC dataset into your Db2 table:
+
+```
+db2 start
+db2 connect to <database_name>
+
+CREATE TABLE <table_schema>.<table_name> (
+PASSENGERID INTEGER NOT NULL,
+SURVIVED INTEGER,
+PCLASS INTEGER,
+NAME VARCHAR(255),
+SEX VARCHAR(6),
+AGE DECIMAL(5,2),
+SIBSP INTEGER,
+PARCH INTEGER,
+TICKET VARCHAR(255),
+FARE DECIMAL(30,5),
+CABIN VARCHAR(255),
+EMBARKED VARCHAR(3),
+PRIMARY KEY (PASSENGERID))
+ORGANIZE BY ROW;
+
+db2 IMPORT FROM "<full_path_to_csv>" OF DEL skipcount 1 INSERT INTO 
+<table_schema>.<table_name>(PASSENGERID, SURVIVED, PCLASS, NAME, SEX, AGE, SIBSP, PARCH, TICKET, FARE, CABIN, EMBARKED)
+```
+
+For loading the GO_SALES data you can take the following steps:
+
+```
+db2start
+connect to <database_name>
+
+CREATE TABLE <table_schema>.<table_name> (
+ID INTEGER NOT NULL,
+GENDER VARCHAR(3),
+AGE INTEGER,
+MARITAL_STATUS VARCHAR(30),
+PROFESSION VARCHAR(30),
+IS_TENT INTEGER,
+PRODUCT_LINE VARCHAR(30),
+PURCHASE_AMOUNT DECIMAL(30, 5),
+PRIMARY KEY (ID))
+ORGANIZE BY ROW;
+
+IMPORT FROM "<full_path_to_csv>" OF DEL skipcount 1 INSERT INTO 
+<table_schema>.<table_name>(ID, GENDER, AGE, MARITAL_STATUS, PROFESSION, IS_TENT, PRODUCT_LINE, PURCHASE_AMOUNT)
+```
+
+## 4. Notebook-specific requirements <a name="Notebook-specific"></a>
+### 4.1 Using the Classification Notebook
+To use the [classification demo](Notebooks/Classification_Demo.ipynb) notebook, please ensure that the following Python libraries are installed in your development environment:
+- [Pandas](https://pandas.pydata.org/pandas-docs/stable/getting_started/install.html)
+- [Numpy](https://pypi.org/project/numpy/)
+- [IPython](https://ipython.org/install.html)
+- [Scipy](https://www.scipy.org/install.html)
+- [Itertools](https://docs.python.org/3/library/itertools.html)
+- [Matplotlib](https://matplotlib.org/users/installing.html)
+- [Seaborn](https://pypi.org/project/seaborn/#description)
+
+Once the above prerequisites have been met, ensure that:
+- The parameters in the connection string variable `conn_str` have been changed to your particular Db2 instance (cell 2)
+- The value of the variable `schema` has been changed to the appropriate schema where the ML pipeline will be executed (cell 2)
+- The value `DATA.TITANIC` in cells 8, 11, 14, 17, and 18 is changed to the `<schema_name>.<table_name>` where the csv data was loaded (section 3)
+
+### 4.2 Using the Regression Notebook
+To use the [regression demo](Notebooks/Regression_Demo.ipynb) notebook, please ensure that the following Python libraries are installed in your development environment:
+- [Pandas](https://pandas.pydata.org/pandas-docs/stable/getting_started/install.html)
+- [Numpy](https://pypi.org/project/numpy/)
+- [Matplotlib](https://matplotlib.org/users/installing.html)
+
+Also make sure that you have the [InDBMLModules.py](lib/InDBMLModules.py) file in the same directory as your notebook.
+
+Once the above prerequisites have been met, ensure that:
+- The parameters in the connection string variable `conn_str` have been changed to your particular Db2 instance (cell 3)
+- The value `DATA.GO_SALES` in cells 6,10, and 11 is changed to the `<schema_name>.<table_name>` where the csv data was loaded (section 3)
+
+## 5. Troubleshooting <a name="Troubleshooting"></a>
+
+When using a jupyter notebook, some users may find that they are unable to import a module that has been successfully installed via pip.
+
+Check `sys.executable` to see which Python and environment you're running in, and `sys.path` to see where it looks to import modules:
+
+```
+import sys
+print(sys.executable)
+print(sys.path)
+```
+
+If the path in `sys.executable` is not in `sys.path`, you can add it using the following:
+`sys.path.append('/path/from/sys.executable')`
+
+## 6. Demo Videos <a name="Resources"></a>
+
+Find step-by-step demonstrations here:
+- [Classification with Db2](https://youtu.be/jCgschThiRQ)
+- [Linear Regression with Db2](https://youtu.be/RpX0iHL97dc)
+
+Db2 Machine Learning [Documentation](https://www.ibm.com/support/knowledgecenter/SSEPGG_11.5.0/com.ibm.db2.luw.ml.doc/doc/ml_prereqs.html)
@@ -0,0 +1,42 @@
+<report xmlns="http://developer.cognos.com/schemas/report/15.4/"           expressionLocale="en-us" useStyleVersion="11.5">
+
+				<drillBehavior/>
+				<layouts>
+					<layout>
+						<reportPages>
+							<page name="Page1">
+								<style>
+									<defaultStyles>
+										<defaultStyle refStyle="pg"/>
+									</defaultStyles>
+								</style>
+								<pageBody>
+									<style>
+										<defaultStyles>
+											<defaultStyle refStyle="pb"/>
+										</defaultStyles>
+									<CSS value="padding-top:15px;padding-left:15px"/></style>
+									<contents><table><style><defaultStyles><defaultStyle refStyle="tb"/></defaultStyles><CSS value="border-collapse:collapse;width:100%"/></style><tableRows><tableRow><tableCells><tableCell><contents><textItem><dataSource><staticValue>Gender:</staticValue></dataSource></textItem></contents></tableCell><tableCell colSpan="4"><contents><selectValue parameter="pGender" refQuery="Query2" autoSubmit="true"><useItem refDataItem="GENDER"><displayItem refDataItem="GENDER1"/></useItem><defaultSelections><defaultSimpleSelection>M</defaultSimpleSelection></defaultSelections></selectValue></contents></tableCell></tableCells></tableRow><tableRow><tableCells><tableCell><contents><textItem><dataSource><staticValue>Age:</staticValue></dataSource></textItem></contents><style><CSS value="width:25%"/></style></tableCell><tableCell><contents><textBox parameter="pAge" numbersOnly="true"><defaultSelections><defaultSimpleSelection>33</defaultSimpleSelection></defaultSelections></textBox></contents><style><CSS value="width:25%"/></style></tableCell><tableCell colSpan="2"><contents/><style><CSS value="width:50%;text-align:left;vertical-align:top"/></style></tableCell></tableCells></tableRow><tableRow><tableCells><tableCell><contents><textItem><dataSource><staticValue>Marital Status: </staticValue></dataSource></textItem></contents></tableCell><tableCell colSpan="4"><contents><selectValue parameter="pMaritalStatus" refQuery="Query3" autoSubmit="true"><useItem refDataItem="MARITAL_STATUS"><displayItem refDataItem="MARITAL_STATUS1"/></useItem><defaultSelections><defaultSimpleSelection>Married</defaultSimpleSelection></defaultSelections></selectValue></contents></tableCell></tableCells></tableRow><tableRow><tableCells><tableCell><contents><textItem><dataSource><staticValue>Profession:</staticValue></dataSource></textItem></contents></tableCell><tableCell colSpan="4"><contents><selectValue parameter="pProfession" refQuery="Query4" autoSubmit="true"><useItem refDataItem="PROFESSION"><displayItem refDataItem="PROFESSION1"/></useItem><defaultSelections><defaultSimpleSelection>Professional</defaultSimpleSelection></defaultSelections></selectValue></contents></tableCell></tableCells></tableRow><tableRow><tableCells><tableCell><contents><textItem><dataSource><staticValue>Has purchased tent before:</staticValue></dataSource></textItem></contents></tableCell><tableCell colSpan="4"><contents><selectValue parameter="pIsTent" refQuery="Query5" autoSubmit="true"><useItem refDataItem="IS_TENT"><displayItem refDataItem="IS_TENT1"/></useItem><defaultSelections><defaultSimpleSelection>1</defaultSimpleSelection></defaultSelections></selectValue></contents></tableCell></tableCells></tableRow><tableRow><tableCells><tableCell><contents><textItem><dataSource><staticValue>Product line:</staticValue></dataSource></textItem></contents></tableCell><tableCell><contents><selectValue parameter="pProductLine" refQuery="Query6" autoSubmit="true"><useItem refDataItem="PRODUCT_LINE"><displayItem refDataItem="PRODUCT_LINE1"/></useItem><defaultSelections><defaultSimpleSelection>Camping Equipment</defaultSimpleSelection></defaultSelections></selectValue></contents><style><CSS value="width:33%"/></style></tableCell><tableCell><contents/><style><CSS value="width:33%;text-align:left;vertical-align:top"/></style></tableCell></tableCells></tableRow><tableRow><tableCells><tableCell><contents><table><style><defaultStyles><defaultStyle refStyle="tb"/></defaultStyles><CSS value="border-collapse:collapse;height:100%;width:100%;font-weight:bold;font-style:italic"/></style><tableRows><tableRow><tableCells><tableCell><contents><table><style><defaultStyles><defaultStyle refStyle="tb"/></defaultStyles><CSS value="border-collapse:collapse;width:100%"/></style><tableRows><tableRow><tableCells><tableCell><contents><textItem><dataSource><staticValue>Estimated purchase amount: </staticValue></dataSource></textItem></contents><style><CSS value="text-align:right"/></style></tableCell><tableCell><contents><singleton name="Singleton1" refQuery="Query1">
+			<contents><textItem><dataSource><dataItemValue refDataItem="PURCHASE_AMOUNT"/></dataSource><style><dataFormat><currencyFormat currencyCode="USD" useIntlSymbol="false" decimalDelimiter="." decimalSize="2"/></dataFormat></style></textItem></contents>
+		</singleton></contents><style><CSS value="text-align:left"/></style></tableCell></tableCells></tableRow></tableRows></table></contents><style><CSS value="text-align:left;vertical-align:top;width:50%"/></style></tableCell></tableCells></tableRow></tableRows></table></contents><style><defaultStyles><defaultStyle refStyle="GuidedLayoutTopPadding"/><defaultStyle refStyle="GuidedLayoutRightPadding"/></defaultStyles></style></tableCell><tableCell><contents><promptButton type="reprompt">
+			<contents><textItem><dataSource><staticValue>Estimate</staticValue></dataSource></textItem></contents>
+			<style>
+				<defaultStyles>
+					<defaultStyle refStyle="bp"/>
+				</defaultStyles>
+			</style>
+		</promptButton></contents><style><CSS value="width:20%;text-align:left;vertical-align:top"/></style></tableCell><tableCell><contents/><style><CSS value="text-align:left;vertical-align:top"/></style></tableCell></tableCells></tableRow></tableRows></table></contents>
+								</pageBody>
+							<pageHeader><contents><table><style><CSS value="border-collapse:collapse;width:100%"/><defaultStyles><defaultStyle refStyle="tb"/></defaultStyles></style><tableRows><tableRow><tableCells><tableCell><contents><textItem><dataSource><staticValue>Predict purchase amount</staticValue></dataSource><style><CSS value="font-size:18pt"/></style></textItem></contents></tableCell></tableCells></tableRow><tableRow><tableCells><tableCell><contents/></tableCell></tableCells></tableRow></tableRows></table></contents><style><CSS value="padding-top:15px;padding-left:15px"/></style></pageHeader></page>
+						</reportPages>
+					</layout>
+				</layouts>
+			<queries><query name="Query1"><source><model/></source><selection><dataItem aggregate="total" name="PURCHASE_AMOUNT"><expression>[C].[C_In_DB_ML_Model].[PredictSP].[PURCHASE_AMOUNT]</expression><XMLAttributes><XMLAttribute output="no" name="RS_dataType" value="9"/><XMLAttribute output="no" name="RS_dataUsage" value="2"/></XMLAttributes></dataItem></selection></query><query name="Query2"><source><model/></source><selection><dataItem aggregate="none" name="GENDER"><expression>[C].[C_In_DB_ML_Model].[GO_Sales].[GENDER]</expression></dataItem><dataItem aggregate="none" sort="ascending" name="GENDER1"><expression>case [C].[C_In_DB_ML_Model].[GO_Sales].[GENDER]
+when (&apos;M&apos;) then (&apos;Male&apos;)
+when (&apos;F&apos;) then (&apos;Female&apos;)
+else (null)
+end</expression></dataItem></selection></query><query name="Query5"><source><model/></source><selection><dataItem aggregate="none" name="IS_TENT"><expression>[C].[C_In_DB_ML_Model].[GO_Sales].[IS_TENT]</expression></dataItem><dataItem aggregate="none" sort="ascending" name="IS_TENT1"><expression>case [C].[C_In_DB_ML_Model].[GO_Sales].[IS_TENT] 
+when (1) then(&apos;Yes&apos;) 
+when (0) then (&apos;No&apos;)
+when (null) then (&apos;Not Specified&apos;)
+end</expression></dataItem></selection></query><query name="Query3"><source><model/></source><selection><dataItem aggregate="none" name="MARITAL_STATUS"><expression>[C].[C_In_DB_ML_Model].[GO_Sales].[MARITAL_STATUS]</expression></dataItem><dataItem aggregate="none" sort="ascending" name="MARITAL_STATUS1"><expression>[C].[C_In_DB_ML_Model].[GO_Sales].[MARITAL_STATUS]</expression></dataItem></selection></query><query name="Query4"><source><model/></source><selection><dataItem aggregate="none" name="PROFESSION"><expression>[C].[C_In_DB_ML_Model].[GO_Sales].[PROFESSION]</expression></dataItem><dataItem aggregate="none" sort="ascending" name="PROFESSION1"><expression>[C].[C_In_DB_ML_Model].[GO_Sales].[PROFESSION]</expression></dataItem></selection></query><query name="Query6"><source><model/></source><selection><dataItem aggregate="none" name="PRODUCT_LINE"><expression>[C].[C_In_DB_ML_Model].[GO_Sales].[PRODUCT_LINE]</expression></dataItem><dataItem aggregate="none" sort="ascending" name="PRODUCT_LINE1"><expression>[C].[C_In_DB_ML_Model].[GO_Sales].[PRODUCT_LINE]</expression></dataItem></selection></query></queries><XMLAttributes><XMLAttribute output="no" name="RS_CreateExtendedDataItems" value="true"/><XMLAttribute output="no" name="listSeparator" value=","/><XMLAttribute output="no" name="decimalSeparator" value="."/><XMLAttribute output="no" name="RS_modelModificationTime" value="2020-06-23T14:56:20.507Z"/></XMLAttributes><classStyles><classStyle name="GuidedLayoutLeftPadding"><CSS value="padding-left:5px;border-top-width:1px;border-bottom-width:1px;border-left-width:1px;border-right-width:1px"/></classStyle><classStyle name="GuidedLayoutTopPadding"><CSS value="padding-top:5px;border-top-width:1px;border-bottom-width:1px;border-left-width:1px;border-right-width:1px"/></classStyle><classStyle name="GuidedLayoutRightPadding"><CSS value="padding-right:5px;border-top-width:1px;border-bottom-width:1px;border-left-width:1px;border-right-width:1px"/></classStyle><classStyle name="GuidedLayoutBottomPadding"><CSS value="padding-bottom:5px;border-top-width:1px;border-bottom-width:1px;border-left-width:1px;border-right-width:1px"/></classStyle><classStyle name="GuidedLayoutMargin"><CSS value="margin-bottom:10px"/></classStyle></classStyles><modelPath type="module">CAMID(&quot;BluePages:u:uid=0d5135649,c=ca,ou=bluepages&quot;)/folder[@name=&apos;My Folders&apos;]/folder[@name=&apos;in-DB ML&apos;]/module[@name=&apos;In-DB ML Model&apos;]</modelPath><reportName>GoSales_predict_report</reportName></report>