| # |
| # Licensed to the Apache Software Foundation (ASF) under one or more |
| # contributor license agreements. See the NOTICE file distributed with |
| # this work for additional information regarding copyright ownership. |
| # The ASF licenses this file to You under the Apache License, Version 2.0 |
| # (the "License"); you may not use this file except in compliance with |
| # the License. You may obtain a copy of the License at |
| # |
| # http://www.apache.org/licenses/LICENSE-2.0 |
| # |
| # Unless required by applicable law or agreed to in writing, software |
| # distributed under the License is distributed on an "AS IS" BASIS, |
| # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
| # See the License for the specific language governing permissions and |
| # limitations under the License. |
| # |
| |
| """ |
| Import sample data for similar product engine |
| """ |
| |
| import predictionio |
| import argparse |
| import random |
| |
| SEED = 3 |
| |
| def import_events(client): |
| random.seed(SEED) |
| count = 0 |
| print(client.get_status()) |
| print("Importing data...") |
| |
| # generate 10 users, with user ids u1,u2,....,u10 |
| user_ids = ["u%s" % i for i in range(1, 11)] |
| for user_id in user_ids: |
| print("Set user", user_id) |
| client.create_event( |
| event="$set", |
| entity_type="user", |
| entity_id=user_id |
| ) |
| count += 1 |
| |
| # generate 50 items, with item ids i1,i2,....,i50 |
| # random assign 1 to 4 categories among c1-c6 to items |
| categories = ["c%s" % i for i in range(1, 7)] |
| item_ids = ["i%s" % i for i in range(1, 51)] |
| for item_id in item_ids: |
| print("Set item", item_id) |
| client.create_event( |
| event="$set", |
| entity_type="item", |
| entity_id=item_id, |
| properties={ |
| "categories" : random.sample(categories, random.randint(1, 4)) |
| } |
| ) |
| count += 1 |
| |
| # each user randomly viewed 10 items |
| for user_id in user_ids: |
| for viewed_item in random.sample(item_ids, 10): |
| print("User", user_id ,"views item", viewed_item) |
| client.create_event( |
| event="view", |
| entity_type="user", |
| entity_id=user_id, |
| target_entity_type="item", |
| target_entity_id=viewed_item |
| ) |
| count += 1 |
| |
| # each user randomly liked/disliked 10 items |
| for user_id in user_ids: |
| for viewed_item in random.sample(item_ids, 10): |
| if random.choice((False, True)) : |
| print "User", user_id ,"likes item", viewed_item |
| client.create_event( |
| event="like", |
| entity_type="user", |
| entity_id=user_id, |
| target_entity_type="item", |
| target_entity_id=viewed_item |
| ) |
| else: |
| print "User", user_id ,"dislikes item", viewed_item |
| client.create_event( |
| event="dislike", |
| entity_type="user", |
| entity_id=user_id, |
| target_entity_type="item", |
| target_entity_id=viewed_item |
| ) |
| count += 1 |
| |
| print("%s events are imported." % count) |
| |
| if __name__ == '__main__': |
| parser = argparse.ArgumentParser( |
| description="Import sample data for similar product engine") |
| parser.add_argument('--access_key', default='invald_access_key') |
| parser.add_argument('--url', default="http://localhost:7070") |
| |
| args = parser.parse_args() |
| print(args) |
| |
| client = predictionio.EventClient( |
| access_key=args.access_key, |
| url=args.url, |
| threads=5, |
| qsize=500) |
| import_events(client) |