feat- Retail sample data

Data/create_search_resources.py

@@ -0,0 +1,78 @@
+import os
+from dotenv import load_dotenv
+from azure.core.credentials import AzureKeyCredential
+from azure.search.documents.indexes import SearchIndexClient, SearchIndexerClient
+from azure.search.documents.indexes.models import (
+    SearchIndexerDataSourceConnection,
+    SearchIndexer,
+    SearchIndex,
+    SimpleField,
+    SearchableField,
+    SearchFieldDataType
+)
+
+# Load environment variables from .env file
+load_dotenv()
+
+# Retrieve environment variables
+SEARCH_ENDPOINT = os.getenv("SEARCH_ENDPOINT")
+SEARCH_API_KEY = os.getenv("SEARCH_API_KEY")
+BLOB_CONNECTION_STRING = os.getenv("BLOB_CONNECTION_STRING")
+BLOB_CONTAINER_NAME = os.getenv("BLOB_CONTAINER_NAME")
+
+# Validate required environment variables
+required_vars = [SEARCH_ENDPOINT, SEARCH_API_KEY, BLOB_CONNECTION_STRING, BLOB_CONTAINER_NAME]
+if any(var is None for var in required_vars):
+    raise ValueError("One or more required environment variables are missing.")
+
+def create_search_resources():
+    """Create Azure AI Search resources: data source, index, and indexer."""
+    try:
+        # Initialize SearchIndexClient for index operations
+        index_client = SearchIndexClient(
+            endpoint=SEARCH_ENDPOINT,
+            credential=AzureKeyCredential(SEARCH_API_KEY)
+        )
+
+        # Initialize SearchIndexerClient for data source and indexer operations
+        indexer_client = SearchIndexerClient(
+            endpoint=SEARCH_ENDPOINT,
+            credential=AzureKeyCredential(SEARCH_API_KEY)
+        )
+
+        # Define data source connection
+        data_source = SearchIndexerDataSourceConnection(
+            name="macae-blob-datasets",
+            type="azureblob",
+            connection_string=BLOB_CONNECTION_STRING,
+            container={"name": BLOB_CONTAINER_NAME}
+        )
+        indexer_client.create_or_update_data_source_connection(data_source)
+        print("Data source 'macae-blob-datasets' created successfully.")
+
+        # Define index schema
+        index = SearchIndex(
+            name="macae-index",
+            fields=[
+                SimpleField(name="id", type=SearchFieldDataType.String, key=True),
+                SearchableField(name="content", type=SearchFieldDataType.String),
+                SearchableField(name="metadata", type=SearchFieldDataType.String)
+            ]
+        )
+        index_client.create_or_update_index(index)
+        print("Index 'macae-index' created successfully.")
+
+        # Define indexer
+        indexer = SearchIndexer(
+            name="macae-indexer",
+            data_source_name="macae-blob-datasets",
+            target_index_name="macae-index"
+        )
+        indexer_client.create_or_update_indexer(indexer)
+        print("Indexer 'macae-indexer' created successfully.")
+
+    except Exception as e:
+        print(f"An error occurred while creating search resources: {e}")
+
+if __name__ == "__main__":
+    create_search_resources()

Data/data_upload.py

@@ -0,0 +1,21 @@
+from azure.storage.blob import BlobServiceClient
+import os
+from dotenv import load_dotenv
+
+load_dotenv() 
+
+# Retrieve environment variables
+BLOB_CONNECTION_STRING = os.getenv("BLOB_CONNECTION_STRING")
+BLOB_CONTAINER_NAME = os.getenv("BLOB_CONTAINER_NAME")
+local_folder = "./datasets"
+
+blob_service_client = BlobServiceClient.from_connection_string(BLOB_CONNECTION_STRING)
+container_client = blob_service_client.get_container_client(BLOB_CONTAINER_NAME)
+
+for filename in os.listdir(local_folder):
+    file_path = os.path.join(local_folder, filename)
+    if os.path.isfile(file_path):
+        print(f"Uploading {filename}...")
+        with open(file_path, "rb") as data:
+            container_client.upload_blob(name=filename, data=data, overwrite=True)
+print("Upload complete!")

Data/datasets/Competitor_Pricing_Analysis.csv

@@ -0,0 +1,5 @@
+ProductCategory,ContosoAveragePrice,CompetitorAveragePrice
+Dresses,120,100
+Shoes,100,105
+Accessories,60,55
+Sportswear,80,85

Data/datasets/Customer_Churn_Analysis.csv

@@ -0,0 +1,6 @@
+ReasonForCancellation,Percentage
+Service Dissatisfaction,40
+Financial Reasons,3
+Competitor Offer,15
+Moving to a Non-Service Area,5
+Other,37

Data/datasets/Email_Marketing_Engagement.csv

@@ -0,0 +1,6 @@
+Campaign,Opened,Clicked,Unsubscribed
+Summer Sale,Yes,Yes,No
+New Arrivals,Yes,No,No
+Exclusive Member Offers,No,No,No
+Personal Styling Invite,No,No,No
+Autumn Collection Preview,Yes,Yes,No

Data/datasets/Loyalty_Program_Overview.csv

@@ -0,0 +1,2 @@
+TotalPointsEarned,PointsRedeemed,CurrentPointBalance,PointsExpiringNextMonth
+4800,3600,1200,1200

Data/datasets/Subscription_benefits_utilization.csv

@@ -0,0 +1,5 @@
+Benefit,UsageFrequency
+Free Shipping,7
+Early Access to Collections,2
+Exclusive Discounts,1
+Personalized Styling Sessions,0

Data/datasets/Unauthorized_Access_Attempts.csv

@@ -0,0 +1,4 @@
+Date,IPAddress,Location,SuccessfulLogin
+2023-06-20,192.168.1.1,Home Network,Yes
+2023-07-22,203.0.113.45,Unknown,No
+2023-08-15,198.51.100.23,Office Network,Yes

Data/datasets/Warehouse_Incident_Reports.csv

@@ -0,0 +1,4 @@
+Date,IncidentDescription,AffectedOrders
+2023-06-15,Inventory system outage,100
+2023-07-18,Logistics partner strike,250
+2023-08-25,Warehouse flooding due to heavy rain,150

Data/datasets/customer_feedback_surveys.csv

@@ -0,0 +1,3 @@
+SurveyID,Date,SatisfactionRating,Comments
+O5678,2023-03-16,5,"Loved the summer dress! Fast delivery."
+O5970,2023-09-13,4,"Happy with the sportswear. Quick delivery."

Data/datasets/customer_profile.csv

@@ -0,0 +1,2 @@
+CustomerID,Name,Age,MembershipDuration,TotalSpend,AvgMonthlySpend,PreferredCategories
+C1024,Emily Thompson,35,24,4800,200,"Dresses, Shoes, Accessories"

Data/datasets/customer_service_interactions.json

@@ -0,0 +1,3 @@
+{"InteractionID":"1","Channel":"Live Chat","Date":"2023-06-20","Customer":"Emily Thompson","OrderID":"O5789","Content":["Agent: Hello Emily, how can I assist you today?","Emily: Hi, I just received my order O5789, and wanted to swap it for another colour","Agent: Sure, that's fine- feel free to send it back or change it in store.","Emily: Ok, I'll just send it back then","Agent: Certainly. I've initiated the return process. You'll receive an email with the return instructions.","Emily: Thank you."]}
+{"InteractionID":"2","Channel":"Phone Call","Date":"2023-07-25","Customer":"Emily Thompson","OrderID":"O5890","Content":["Agent: Good afternoon, this is Contoso customer service. How may I help you?","Emily: I'm calling about my order O5890. I need the gown for an event this weekend, and just want to make sure it will be delivered on time as it's really important.","Agent: Let me check... it seems like the delivery is on track. It should be there on time.","Emily: Ok thanks."]}
+{"InteractionID":"3","Channel":"Email","Date":"2023-09-15","Customer":"Emily Thompson","OrderID":"","Content":["Subject: Membership Cancellation Request","Body: Hello, I want to cancel my Contoso Plus subscription. The cost is becoming too high for me."]}

Data/datasets/delivery_performance_metrics.csv

@@ -0,0 +1,8 @@
+Month,AverageDeliveryTime,OnTimeDeliveryRate,CustomerComplaints
+March,3,98,15
+April,4,95,20
+May,5,92,30
+June,6,88,50
+July,7,85,70
+August,4,94,25
+September,3,97,10

Data/datasets/product_return_rates.csv

@@ -0,0 +1,6 @@
+Category,ReturnRate
+Dresses,15
+Shoes,10
+Accessories,8
+Outerwear,12
+Sportswear,9

Data/datasets/product_table.csv

@@ -0,0 +1,6 @@
+ProductCategory,ReturnRate,ContosoAveragePrice,CompetitorAveragePrice
+Dresses,15,120,100
+Shoes,10,100,105
+Accessories,8,60,55
+Outerwear,12,,
+Sportswear,9,80,85

Data/datasets/purchase_history.csv

@@ -0,0 +1,8 @@
+OrderID,Date,ItemsPurchased,TotalAmount,DiscountApplied,DateDelivered,ReturnFlag
+O5678,2023-03-15,"Summer Floral Dress, Sun Hat",150,10,2023-03-19,No
+O5721,2023-04-10,"Leather Ankle Boots",120,15,2023-04-13,No
+O5789,2023-05-05,Silk Scarf,80,0,2023-05-25,Yes
+O5832,2023-06-18,Casual Sneakers,90,5,2023-06-21,No
+O5890,2023-07-22,"Evening Gown, Clutch Bag",300,20,2023-08-05,No
+O5935,2023-08-30,Denim Jacket,110,0,2023-09-03,Yes
+O5970,2023-09-12,"Fitness Leggings, Sports Bra",130,25,2023-09-18,No

Data/datasets/social_media_sentiment_analysis.csv

@@ -0,0 +1,8 @@
+Month,PositiveMentions,NegativeMentions,NeutralMentions
+March,500,50,200
+April,480,60,220
+May,450,80,250
+June,400,120,300
+July,350,150,320
+August,480,70,230
+September,510,40,210

Data/datasets/store_visit_history.csv

@@ -0,0 +1,4 @@
+Date,StoreLocation,Purpose,Outcome
+2023-05-12,Downtown Outlet,Browsing,"Purchased a Silk Scarf (O5789)"
+2023-07-20,Uptown Mall,Personal Styling,"Booked a session but didn't attend"
+2023-08-05,Midtown Boutique,Browsing,"No purchase"

Data/datasets/website_activity_log.csv

@@ -0,0 +1,6 @@
+Date,PagesVisited,TimeSpent
+2023-09-10,"Homepage, New Arrivals, Dresses",15
+2023-09-11,"Account Settings, Subscription Details",5
+2023-09-12,"FAQ, Return Policy",3
+2023-09-13,"Careers Page, Company Mission",2
+2023-09-14,"Sale Items, Accessories",10

requirements.txt

@@ -0,0 +1,7 @@
+pyodbc
+sqlalchemy
+pandas
+azure-storage-blob
+azure-search-documents
+langchain
+openai