Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

New In-Db2 ML Demo Content #35

Merged
merged 3 commits into from
Mar 9, 2021
Merged

New In-Db2 ML Demo Content #35

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
3e5777c
ML Pipeline Deployment Demo
adrianmahjour Mar 5, 2021
d1c48ed
ML Pipeline Deployment Demo
adrianmahjour Mar 5, 2021
bbc6ad8
ML Pipeline Deployment Demo
adrianmahjour Mar 5, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1,001 changes: 1,001 additions & 0 deletions ...k for Data Trained ML Pipeline/Cloud Pak for Data Assets/customer_full_summary_latest.csv
View file
Open in desktop

Large diffs are not rendered by default.

312 changes: 312 additions & 0 deletions ... Pak for Data Trained ML Pipeline/Cloud Pak for Data Assets/customer_segmentation_prep.py
View file
Open in desktop

Large diffs are not rendered by default.

Binary file added ... Cloud Pak for Data Trained ML Pipeline/Cloud Pak for Data Assets/original_csv_dtypes.pkl
View file
Open in desktop
Binary file not shown.
10,001 changes: 10,001 additions & 0 deletions ...with a Cloud Pak for Data Trained ML Pipeline/Cloud Pak for Data Assets/test_data_10K.csv
View file
Open in desktop

Large diffs are not rendered by default.

285 changes: 285 additions & 0 deletions ...b2 Scoring with a Cloud Pak for Data Trained ML Pipeline/Notebooks/Dataset Creation.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,285 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "97aed183-c9b5-488c-958e-0a38f1a0e88e"
},
"source": [
"# Inserting Training and Test Data into a Db2 Table"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "856ae9ae-ff30-4599-aa8a-2734cfca6d1b"
},
"outputs": [],
"source": [
"#Establishing Connection to Database\n",
"\n",
"import pandas as pd\n",
"import ibm_db_dbi\n",
"import ibm_db\n",
"from project_lib import Project \n",
"\n",
"# Define connection string and connect to database\n",
"project = Project.access()\n",
"LocalDB2_credentials = project.get_connection(name = \"CSSDB3\")\n",
"\n",
"bluedb_connection = ibm_db.connect(\"DATABASE={};HOSTNAME={};PORT={};PROTOCOL=TCPIP;UID={};PWD={}\".format(LocalDB2_credentials['database'],\n",
" LocalDB2_credentials['host'],\n",
" LocalDB2_credentials['port'],\n",
" LocalDB2_credentials['username'],\n",
" LocalDB2_credentials['password']),\"\",\"\")\n",
"dbi_bluedb_connection = ibm_db_dbi.Connection(bluedb_connection)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Insert Training Data"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "47cc7326-94cb-4b7e-98e0-efbf37c4973f"
},
"outputs": [],
"source": [
"#Reading in CSV file with raw data and preparing to write to DB2 \n",
"\n",
"train_data = pd.read_csv('/project_data/data_asset/customer_full_summary_latest.csv')\n",
"\n",
"train_data = test_data.where(pd.notnull(train_data),None)\n",
"\n",
"tuple_of_tuples = tuple([tuple(x) for x in train_data.values])"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "19ae6527-d3f8-4622-b8e8-3acdcb617f3e"
},
"outputs": [],
"source": [
"#Creating string concatenations for sql query to write data \n",
"\n",
"type_mapping = {'int64': 'DOUBLE',\n",
" 'float64': 'DOUBLE',\n",
" 'object': 'VARCHAR(90)',\n",
" 'datetime64[ns]': 'VARCHAR(90)'\n",
" }\n",
"\n",
"value_string = ', '.join(['?' for i in range(len(train_data.columns))])\n",
"dtype_mapping_4table = [type_mapping[str(x)] for x in list(train_data.dtypes)]\n",
"table_creation_column_string = ', '.join('{0} {1} '.format(str(x),str(y)) for x,y in zip(train_data.columns,dtype_mapping_4table))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "48fde0cb-e315-4727-9f8a-11656d7deef2"
},
"outputs": [],
"source": [
"sql = 'CREATE TABLE DSE.CUST_SEG_DATA_TRAIN({});'.format(table_creation_column_string)\n",
"\n",
"stmt = ibm_db.prepare(bluedb_connection, sql)\n",
"\n",
"ibm_db.execute(stmt)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "e6a427d2-dfd3-47ab-ac33-339b5025bc53"
},
"outputs": [],
"source": [
"value_string = ', '.join(['?' for i in range(len(train_data.columns))])\n",
"\n",
"sql = \"INSERT INTO DSE.CUST_SEG_DATA_TRAIN VALUES({})\".format(value_string)\n",
"\n",
"stmt = ibm_db.prepare(bluedb_connection, sql)\n",
"\n",
"ibm_db.execute_many(stmt, tuple_of_tuples)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "eb225a5b-30c8-4e30-abc0-ae2dd7e8e4fa"
},
"outputs": [],
"source": [
"# Validate successful data import\n",
"input_df = pd.read_sql('select * from DSE.CUST_SEG_DATA_TRAIN',con = dbi_bluedb_connection)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "3f87eb38-020b-4d04-9d7a-77040c9e6e71",
"scrolled": true
},
"outputs": [],
"source": [
"input_df.shape"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "cceef222-6910-4a37-8452-84acf385295b",
"scrolled": true
},
"outputs": [],
"source": [
"input_df.head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Insert Test Data"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "47cc7326-94cb-4b7e-98e0-efbf37c4973f"
},
"outputs": [],
"source": [
"#Reading in CSV file with raw data and preparing to write to DB2 \n",
"\n",
"test_data = pd.read_csv('/project_data/data_asset/test_data_10K.csv')\n",
"\n",
"test_data = test_data.where(pd.notnull(test_data),None)\n",
"\n",
"tuple_of_tuples = tuple([tuple(x) for x in test_data.values])"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "19ae6527-d3f8-4622-b8e8-3acdcb617f3e"
},
"outputs": [],
"source": [
"#Creating string concatenations for sql query to write data \n",
"\n",
"type_mapping = {'int64': 'DOUBLE',\n",
" 'float64': 'DOUBLE',\n",
" 'object': 'VARCHAR(90)',\n",
" 'datetime64[ns]': 'VARCHAR(90)'\n",
" }\n",
"\n",
"value_string = ', '.join(['?' for i in range(len(test_data.columns))])\n",
"dtype_mapping_4table = [type_mapping[str(x)] for x in list(test_data.dtypes)]\n",
"table_creation_column_string = ', '.join('{0} {1} '.format(str(x),str(y)) for x,y in zip(test_data.columns,dtype_mapping_4table))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "48fde0cb-e315-4727-9f8a-11656d7deef2"
},
"outputs": [],
"source": [
"sql = 'CREATE TABLE DSE.CUST_SEG_DATA_TEST({});'.format(table_creation_column_string)\n",
"\n",
"stmt = ibm_db.prepare(bluedb_connection, sql)\n",
"\n",
"ibm_db.execute(stmt)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "e6a427d2-dfd3-47ab-ac33-339b5025bc53"
},
"outputs": [],
"source": [
"value_string = ', '.join(['?' for i in range(len(test_data.columns))])\n",
"\n",
"sql = \"INSERT INTO DSE.CUST_SEG_DATA_TEST VALUES({})\".format(value_string)\n",
"\n",
"stmt = ibm_db.prepare(bluedb_connection, sql)\n",
"\n",
"ibm_db.execute_many(stmt, tuple_of_tuples)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "eb225a5b-30c8-4e30-abc0-ae2dd7e8e4fa"
},
"outputs": [],
"source": [
"# Validate successful data import\n",
"input_df = pd.read_sql('select * from DSE.CUST_SEG_DATA_TEST',con = dbi_bluedb_connection)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "3f87eb38-020b-4d04-9d7a-77040c9e6e71"
},
"outputs": [],
"source": [
"input_df.shape"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "cceef222-6910-4a37-8452-84acf385295b"
},
"outputs": [],
"source": [
"input_df.head()"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"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": "3.9.0"
}
},
"nbformat": 4,
"nbformat_minor": 1
}
Loading