File size: 1,802 Bytes
8c3633d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 |
import pandas as pd
from sklearn.metrics.pairwise import cosine_similarity
# Read data source Excel files.
df1 = pd.read_excel('Online_Retail.xlsx')
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 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 (12702) purchased items.
items_purchased_by_X = set(CustomerID_Item_matrix.loc[12702.0].iloc[
CustomerID_Item_matrix.loc[12702.0].to_numpy().nonzero()].index)
# Display CustomerID (14608) purchased items.
items_purchased_by_Y = set(CustomerID_Item_matrix.loc[14608.0].iloc[
CustomerID_Item_matrix.loc[14608.0].to_numpy().nonzero()].index)
# Find out items which purchased by X (12702) but not yet purchased by Y (14608).
items_to_recommend_to_Y = items_purchased_by_X - items_purchased_by_Y
# Display the list of items recommended for Y (14608) with item Description.
print(df1a.loc[
df1a['StockCode'].isin(items_to_recommend_to_Y),
['StockCode', 'Description']
].drop_duplicates().set_index('StockCode'))
|