working with Online_Retail 10k

.vs/VSWorkspaceState.json

@@ -0,0 +1,7 @@
+{
+  "ExpandedNodes": [
+    ""
+  ],
+  "SelectedNode": "\\app.py",
+  "PreviewInSolutionExplorer": false
+}

app.py

@@ -0,0 +1,50 @@
+import pandas as pd
+from sklearn.metrics.pairwise import cosine_similarity
+import gradio as gr
+
+def find_similar_items(stock_code):
+    # Read data source Excel files.
+    df1 = pd.read_excel('Online_Retail.xlsx')
+
+    # Check dataframe information.
+    df1a = df1.dropna(subset=['CustomerID'])
+
+    # Create CustomerID vs Item (Purchased Items, by StockCode) matrix by pivot table function.
+    CustomerID_Item_matrix = df1a.pivot_table(
+        index='CustomerID', 
+        columns='StockCode', 
+        values='Quantity',
+        aggfunc='sum'
+    )
+
+    # Update illustration of the matrix, 1 to represent customer have purchased item, 0 to represent customer haven't purchased.
+    CustomerID_Item_matrix = CustomerID_Item_matrix.applymap(lambda x: 1 if x > 0 else 0)
+
+    # Create Item to Item similarity matrix.
+    item_item_similarity_matrix = pd.DataFrame(
+        cosine_similarity(CustomerID_Item_matrix.T)
+    )
+
+    # Update index to corresponding Item Code (StockCode).
+    item_item_similarity_matrix.columns = CustomerID_Item_matrix.T.index
+    item_item_similarity_matrix['StockCode'] = CustomerID_Item_matrix.T.index
+    item_item_similarity_matrix = item_item_similarity_matrix.set_index('StockCode')
+
+    # Randomly pick StockCode (23166) to display the most similar StockCode.
+    top_10_similar_items = list(
+        item_item_similarity_matrix\
+            .loc[22632]\
+            .sort_values(ascending=False)\
+            .iloc[:5]\
+        .index
+    )
+
+    # Display the list of similar items of StockCode (23166) with item Description.
+    results_df = df1a.loc[df1a['StockCode'].isin(top_10_similar_items), ['StockCode', 'Description']].drop_duplicates().set_index('StockCode').loc[top_10_similar_items]
+    return "\n" + results_df.to_string()
+
+# Set up the interface
+stock_code_input = gr.inputs.Textbox(label="Enter Stock Code:")
+output_table = gr.outputs.Textbox(label="Similar Items")
+
+gr.Interface(fn=find_similar_items, inputs=stock_code_input, outputs=output_table, title="Similar Items Recommendation System", description="Enter a stock code to find similar items").launch()

requirements.txt

@@ -0,0 +1 @@
+sklearn