Via Native json

Define a “pretty print” function pprint for dict objects and dataframes.

import json 
pprint = lambda x: print(json.dumps(x, indent=2)) if isinstance(x, dict) else display(x)

Load Review Samples

file = "review_categories/All_Beauty.jsonl"

with open(file, 'r') as fp:
    for line in fp:
        pprint(json.loads(line.strip()))
        break

{
  "rating": 5.0,
  "title": "Such a lovely scent but not overpowering.",
  "text": "This spray is really nice. It smells really good, goes on really fine, and does the trick. I will say it feels like you need a lot of it though to get the texture I want. I have a lot of hair, medium thickness. I am comparing to other brands with yucky chemicals so I'm gonna stick with this. Try it!",
  "images": [],
  "asin": "B00YQ6X8EO",
  "parent_asin": "B00YQ6X8EO",
  "user_id": "AGKHLEW2SOWHNMFQIJGBECAF7INQ",
  "timestamp": 1588687728923,
  "helpful_vote": 0,
  "verified_purchase": true
}

Load Item Metadata

file = "meta_categories/meta_All_Beauty.jsonl"

with open(file, 'r') as fp:
    for line in fp:
        pprint(json.loads(line.strip()))
        break

{
  "main_category": "All Beauty",
  "title": "Howard LC0008 Leather Conditioner, 8-Ounce (4-Pack)",
  "average_rating": 4.8,
  "rating_number": 10,
  "features": [],
  "description": [],
  "price": null,
  "images": [
    {
      "thumb": "https://m.media-amazon.com/images/I/41qfjSfqNyL._SS40_.jpg",
      "large": "https://m.media-amazon.com/images/I/41qfjSfqNyL.jpg",
      "variant": "MAIN",
      "hi_res": null
    },
    {
      "thumb": "https://m.media-amazon.com/images/I/41w2yznfuZL._SS40_.jpg",
      "large": "https://m.media-amazon.com/images/I/41w2yznfuZL.jpg",
      "variant": "PT01",
      "hi_res": "https://m.media-amazon.com/images/I/71i77AuI9xL._SL1500_.jpg"
    }
  ],
  "videos": [],
  "store": "Howard Products",
  "categories": [],
  "details": {
    "Package Dimensions": "7.1 x 5.5 x 3 inches; 2.38 Pounds",
    "UPC": "617390882781"
  },
  "parent_asin": "B01CUPMQZE",
  "bought_together": null
}

Load Pure IDs Files (Before Splitting)

file = "rating_only/All_Beauty.csv"

import pandas as pd

df = pd.read_csv(file)
pprint(df.head())

	user_id	parent_asin	rating	timestamp
0	AGKHLEW2SOWHNMFQIJGBECAF7INQ	B081TJ8YS3	4.0	1588615855070
1	AGKHLEW2SOWHNMFQIJGBECAF7INQ	B00YQ6X8EO	5.0	1588687728923
2	AE74DYR3QUGVPZJ3P7RFWBGIX7XQ	B097R46CSY	5.0	1589665266052
3	AFQLNQNQYFWQZPJQZS6V3NZU4QBQ	B08BZ63GMJ	5.0	1609322563534
4	AFQLNQNQYFWQZPJQZS6V3NZU4QBQ	B09JS339BZ	1.0	1643393630220

Load Pure IDs Files (After Splitting)

file = "timestamp_split/All_Beauty.{}.csv"

Only need (user, item) interactions:

for split in ['train', 'valid', 'test']:
    df = pd.read_csv(
        file.format(split), 
        usecols=[0,1,2,3],
    )
    pprint(f"split: {split}")
    pprint(df.head())

'split: train'

	user_id	parent_asin	rating	timestamp
0	AGKHLEW2SOWHNMFQIJGBECAF7INQ	B081TJ8YS3	4.0	1588615855070
1	AGKHLEW2SOWHNMFQIJGBECAF7INQ	B00YQ6X8EO	5.0	1588687728923
2	AE74DYR3QUGVPZJ3P7RFWBGIX7XQ	B097R46CSY	5.0	1589665266052
3	AFQLNQNQYFWQZPJQZS6V3NZU4QBQ	B08BZ63GMJ	5.0	1609322563534
4	AGMJ3EMDVL6OWBJF7CA5RGJLXN5A	B00R8DXL44	4.0	1598567408138

'split: valid'

	user_id	parent_asin	rating	timestamp
0	AFQLNQNQYFWQZPJQZS6V3NZU4QBQ	B09JS339BZ	1.0	1643393630220
1	AHREXOGQPZDA6354MHH4ETSF3MCQ	B099DRHW5V	5.0	1631885519443
2	AEYORY2AVPMCPDV57CE337YU5LXA	B08BBQ29N5	3.0	1634275259292
3	AFETVW7S5M4LVJ7GTWPCKT7S3YBQ	B01M5KNSQN	1.0	1649634131604
4	AGVVUU3QRQBHNASSGI5YQLPYOI2Q	B09FF97RHL	1.0	1648824907536

'split: test'

	user_id	parent_asin	rating	timestamp
0	AFZUK3MTBIBEDQOPAK3OATUOUKLA	B0BFR5WF1R	1.0	1675826333052
1	AHV6QCNBJNSGLATP56JAWJ3C4G2A	B0B4JPGX8P	4.0	1660417672640
2	AHV6QCNBJNSGLATP56JAWJ3C4G2A	B0B4JP5YD9	5.0	1660417831321
3	AHV6QCNBJNSGLATP56JAWJ3C4G2A	B0B8DZ7H5F	4.0	1663163956007
4	AEZ26WGWJ3EOQ4KWSHG77HJAG4EA	B0B7RBK4NJ	1.0	1662827578220

Need additional user historical interactions:

for split in ['train', 'valid', 'test']:
    df = pd.read_csv(
        file.format(split), 
    )
    pprint(f"split: {split}")
    pprint(df.head())

'split: train'

	user_id	parent_asin	rating	timestamp	history
0	AGKHLEW2SOWHNMFQIJGBECAF7INQ	B081TJ8YS3	4.0	1588615855070	NaN
1	AGKHLEW2SOWHNMFQIJGBECAF7INQ	B00YQ6X8EO	5.0	1588687728923	B081TJ8YS3
2	AE74DYR3QUGVPZJ3P7RFWBGIX7XQ	B097R46CSY	5.0	1589665266052	NaN
3	AFQLNQNQYFWQZPJQZS6V3NZU4QBQ	B08BZ63GMJ	5.0	1609322563534	NaN
4	AGMJ3EMDVL6OWBJF7CA5RGJLXN5A	B00R8DXL44	4.0	1598567408138	NaN

'split: valid'

	user_id	parent_asin	rating	timestamp	history
0	AFQLNQNQYFWQZPJQZS6V3NZU4QBQ	B09JS339BZ	1.0	1643393630220	B08BZ63GMJ
1	AHREXOGQPZDA6354MHH4ETSF3MCQ	B099DRHW5V	5.0	1631885519443	NaN
2	AEYORY2AVPMCPDV57CE337YU5LXA	B08BBQ29N5	3.0	1634275259292	NaN
3	AFETVW7S5M4LVJ7GTWPCKT7S3YBQ	B01M5KNSQN	1.0	1649634131604	NaN
4	AGVVUU3QRQBHNASSGI5YQLPYOI2Q	B09FF97RHL	1.0	1648824907536	NaN

'split: test'

	user_id	parent_asin	rating	timestamp	history
0	AFZUK3MTBIBEDQOPAK3OATUOUKLA	B0BFR5WF1R	1.0	1675826333052	B0020MKBNW B082FLP15V B00946HGLW
1	AHV6QCNBJNSGLATP56JAWJ3C4G2A	B0B4JPGX8P	4.0	1660417672640	B00N6WHTRG B00NNKWDI6 B00MDKICPK B010B0S67C B0...
2	AHV6QCNBJNSGLATP56JAWJ3C4G2A	B0B4JP5YD9	5.0	1660417831321	B00N6WHTRG B00NNKWDI6 B00MDKICPK B010B0S67C B0...
3	AHV6QCNBJNSGLATP56JAWJ3C4G2A	B0B8DZ7H5F	4.0	1663163956007	B00N6WHTRG B00NNKWDI6 B00MDKICPK B010B0S67C B0...
4	AEZ26WGWJ3EOQ4KWSHG77HJAG4EA	B0B7RBK4NJ	1.0	1662827578220	NaN