Gopala Krishna
.
cef1747
raw
history blame
2.79 kB
import pandas as pd
from sklearn.metrics.pairwise import cosine_similarity
import gradio as gr
def recommend_items(customer_id_1, customer_id_2):
# Read data source Excel file.
try:
df1 = pd.read_excel("UBCF_Online_Retail.xlsx")
except FileNotFoundError:
return "Error: Excel file not found."
df1a = df1.dropna(subset=['CustomerID'])
# Create CustomerID vs Item (Purchased Items, " 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 User to User similarity matrix.
user_to_user_similarity_matrix = pd.DataFrame(
cosine_similarity(CustomerID_Item_matrix)
)
# Update index to corresponding CustomerID.
user_to_user_similarity_matrix.columns = CustomerID_Item_matrix.index
user_to_user_similarity_matrix['CustomerID'] = CustomerID_Item_matrix.index
user_to_user_similarity_matrix = user_to_user_similarity_matrix.set_index('CustomerID')
# Display CustomerID (customer_id_1) purchased items.
try:
items_purchased_by_X = set(CustomerID_Item_matrix.loc[customer_id_1].iloc[
CustomerID_Item_matrix.loc[customer_id_1].to_numpy().nonzero()].index)
except KeyError:
return pd.DataFrame({"Error": ["Customer ID 1 is invalid. Please enter a valid Customer ID"]})
# Display CustomerID (customer_id_2) purchased items.
try:
items_purchased_by_Y = set(CustomerID_Item_matrix.loc[customer_id_2].iloc[
CustomerID_Item_matrix.loc[customer_id_2].to_numpy().nonzero()].index)
except KeyError:
return pd.DataFrame({"Error": ["Customer ID 2 is invalid. Please enter a valid Customer ID"]})
# Find out items which purchased by X (customer_id_1) but not yet purchased by Y (customer_id_2).
items_to_recommend_to_Y = items_purchased_by_X - items_purchased_by_Y
# Return the list of items recommended for Y (customer_id_2) with item Description.
return df1a.loc[
df1a['StockCode'].isin(items_to_recommend_to_Y),
['StockCode', 'Description']
].drop_duplicates().set_index('StockCode')
# Create a Gradio interface
iface = gr.Interface(
fn=recommend_items,
inputs=[
gr.inputs.Number(label="Customer ID 1",default=12702),
gr.inputs.Number(label="Customer ID 2",default=14608),
],
outputs=gr.outputs.Dataframe(label="Recommended Items for Customer 2",type="pandas"),
allow_flagging=False
)
iface.launch()