Spaces:
Sleeping
Sleeping
OmPrakashSingh1704
commited on
Commit
•
d6e2b99
1
Parent(s):
d5bcd11
Upload Train_Test.ipynb
Browse files- Train_Test.ipynb +1316 -0
Train_Test.ipynb
ADDED
@@ -0,0 +1,1316 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cells": [
|
3 |
+
{
|
4 |
+
"cell_type": "code",
|
5 |
+
"id": "initial_id",
|
6 |
+
"metadata": {
|
7 |
+
"ExecuteTime": {
|
8 |
+
"end_time": "2024-07-30T12:35:06.718909Z",
|
9 |
+
"start_time": "2024-07-30T12:35:06.081202Z"
|
10 |
+
}
|
11 |
+
},
|
12 |
+
"source": [
|
13 |
+
"import pandas as pd\n",
|
14 |
+
"import numpy as np"
|
15 |
+
],
|
16 |
+
"outputs": [],
|
17 |
+
"execution_count": 1
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"cell_type": "code",
|
21 |
+
"id": "13ad721e84c34936",
|
22 |
+
"metadata": {
|
23 |
+
"ExecuteTime": {
|
24 |
+
"end_time": "2024-07-30T12:35:08.731721Z",
|
25 |
+
"start_time": "2024-07-30T12:35:06.720903Z"
|
26 |
+
}
|
27 |
+
},
|
28 |
+
"source": [
|
29 |
+
"df=pd.read_csv(r'D:\\pynb\\Walmart\\KNN\\archive\\WMT_Grocery_202209.csv')\n",
|
30 |
+
"df"
|
31 |
+
],
|
32 |
+
"outputs": [
|
33 |
+
{
|
34 |
+
"name": "stderr",
|
35 |
+
"output_type": "stream",
|
36 |
+
"text": [
|
37 |
+
"C:\\Users\\thaku\\AppData\\Local\\Temp\\ipykernel_13136\\1153799610.py:1: DtypeWarning: Columns (3) have mixed types. Specify dtype option on import or set low_memory=False.\n",
|
38 |
+
" df=pd.read_csv(r'D:\\pynb\\Walmart\\KNN\\archive\\WMT_Grocery_202209.csv')\n"
|
39 |
+
]
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"data": {
|
43 |
+
"text/plain": [
|
44 |
+
" SHIPPING_LOCATION DEPARTMENT CATEGORY SUBCATEGORY \\\n",
|
45 |
+
"0 79936 Deli Hummus, Dips, & Salsa NaN \n",
|
46 |
+
"1 79936 Deli Hummus, Dips, & Salsa NaN \n",
|
47 |
+
"2 79936 Deli Hummus, Dips, & Salsa NaN \n",
|
48 |
+
"3 79936 Deli Hummus, Dips, & Salsa NaN \n",
|
49 |
+
"4 79936 Deli Hummus, Dips, & Salsa NaN \n",
|
50 |
+
"... ... ... ... ... \n",
|
51 |
+
"568529 70072 Alcohol Wine White Wine \n",
|
52 |
+
"568530 70072 Alcohol Wine White Wine \n",
|
53 |
+
"568531 70072 Alcohol Wine White Wine \n",
|
54 |
+
"568532 70072 Alcohol Wine White Wine \n",
|
55 |
+
"568533 70072 Alcohol Wine White Wine \n",
|
56 |
+
"\n",
|
57 |
+
" BREADCRUMBS SKU \\\n",
|
58 |
+
"0 Deli/Hummus, Dips, & Salsa 110895339 \n",
|
59 |
+
"1 Deli/Hummus, Dips, & Salsa 105455228 \n",
|
60 |
+
"2 Deli/Hummus, Dips, & Salsa 128642379 \n",
|
61 |
+
"3 Deli/Hummus, Dips, & Salsa 366126367 \n",
|
62 |
+
"4 Deli/Hummus, Dips, & Salsa 160090316 \n",
|
63 |
+
"... ... ... \n",
|
64 |
+
"568529 Alcohol/Wine 593600139 \n",
|
65 |
+
"568530 Alcohol/Wine 333403243 \n",
|
66 |
+
"568531 Alcohol/Wine 526588325 \n",
|
67 |
+
"568532 Alcohol/Wine 286992782 \n",
|
68 |
+
"568533 Alcohol/Wine 160015930 \n",
|
69 |
+
"\n",
|
70 |
+
" PRODUCT_URL \\\n",
|
71 |
+
"0 https://www.walmart.com/ip/Marketside-Roasted-... \n",
|
72 |
+
"1 https://www.walmart.com/ip/Marketside-Roasted-... \n",
|
73 |
+
"2 https://www.walmart.com/ip/Marketside-Classic-... \n",
|
74 |
+
"3 https://www.walmart.com/ip/Marketside-Everythi... \n",
|
75 |
+
"4 https://www.walmart.com/ip/Price-s-Jalapeno-Di... \n",
|
76 |
+
"... ... \n",
|
77 |
+
"568529 https://www.walmart.com/ip/Farm-Fresh-Blueberr... \n",
|
78 |
+
"568530 https://www.walmart.com/ip/Farm-Fresh-Peach-Mo... \n",
|
79 |
+
"568531 https://www.walmart.com/ip/Farm-Fresh-Raspberr... \n",
|
80 |
+
"568532 https://www.walmart.com/ip/Farm-Fresh-Mango-Mo... \n",
|
81 |
+
"568533 https://www.walmart.com/ip/Ole-Orleans-Heritag... \n",
|
82 |
+
"\n",
|
83 |
+
" PRODUCT_NAME BRAND \\\n",
|
84 |
+
"0 Marketside Roasted Red Pepper Hummus, 10 Oz Marketside \n",
|
85 |
+
"1 Marketside Roasted Garlic Hummus, 10 Oz Marketside \n",
|
86 |
+
"2 Marketside Classic Hummus, 10 Oz Marketside \n",
|
87 |
+
"3 Marketside Everything Hummus, 10 oz Marketside \n",
|
88 |
+
"4 Price's Jalapeno Dip, 12 Oz. Price's \n",
|
89 |
+
"... ... ... \n",
|
90 |
+
"568529 Farm Fresh Blueberry Moscato 750ml Farm Fresh Wine Company \n",
|
91 |
+
"568530 Farm Fresh Peach Moscato 750 Ml Farm Fresh Wine Company \n",
|
92 |
+
"568531 Farm Fresh Raspberry Moscato 750ml Farm Fresh Wine Company \n",
|
93 |
+
"568532 Farm Fresh Mango Moscato 750ml Farm Fresh Wine Company \n",
|
94 |
+
"568533 Ole Orleans Heritage Riesling 750ml Ole Orleans \n",
|
95 |
+
"\n",
|
96 |
+
" PRICE_RETAIL PRICE_CURRENT PRODUCT_SIZE PROMOTION \\\n",
|
97 |
+
"0 2.67 2.67 10 NaN \n",
|
98 |
+
"1 2.67 2.67 10 NaN \n",
|
99 |
+
"2 2.67 2.67 10 NaN \n",
|
100 |
+
"3 2.67 2.67 10 NaN \n",
|
101 |
+
"4 3.12 3.12 12 NaN \n",
|
102 |
+
"... ... ... ... ... \n",
|
103 |
+
"568529 9.98 9.98 750 NaN \n",
|
104 |
+
"568530 9.98 9.98 750 NaN \n",
|
105 |
+
"568531 9.98 9.98 750 NaN \n",
|
106 |
+
"568532 9.98 9.98 750 NaN \n",
|
107 |
+
"568533 18.98 18.98 750 NaN \n",
|
108 |
+
"\n",
|
109 |
+
" RunDate tid \n",
|
110 |
+
"0 2022-09-11 21:20:04 16163804 \n",
|
111 |
+
"1 2022-09-11 21:20:04 16163805 \n",
|
112 |
+
"2 2022-09-11 21:20:04 16163806 \n",
|
113 |
+
"3 2022-09-11 21:20:04 16163807 \n",
|
114 |
+
"4 2022-09-11 21:20:04 16163808 \n",
|
115 |
+
"... ... ... \n",
|
116 |
+
"568529 2022-09-11 21:20:04 16732333 \n",
|
117 |
+
"568530 2022-09-11 21:20:04 16732334 \n",
|
118 |
+
"568531 2022-09-11 21:20:04 16732335 \n",
|
119 |
+
"568532 2022-09-11 21:20:04 16732336 \n",
|
120 |
+
"568533 2022-09-11 21:20:04 16732337 \n",
|
121 |
+
"\n",
|
122 |
+
"[568534 rows x 15 columns]"
|
123 |
+
],
|
124 |
+
"text/html": [
|
125 |
+
"<div>\n",
|
126 |
+
"<style scoped>\n",
|
127 |
+
" .dataframe tbody tr th:only-of-type {\n",
|
128 |
+
" vertical-align: middle;\n",
|
129 |
+
" }\n",
|
130 |
+
"\n",
|
131 |
+
" .dataframe tbody tr th {\n",
|
132 |
+
" vertical-align: top;\n",
|
133 |
+
" }\n",
|
134 |
+
"\n",
|
135 |
+
" .dataframe thead th {\n",
|
136 |
+
" text-align: right;\n",
|
137 |
+
" }\n",
|
138 |
+
"</style>\n",
|
139 |
+
"<table border=\"1\" class=\"dataframe\">\n",
|
140 |
+
" <thead>\n",
|
141 |
+
" <tr style=\"text-align: right;\">\n",
|
142 |
+
" <th></th>\n",
|
143 |
+
" <th>SHIPPING_LOCATION</th>\n",
|
144 |
+
" <th>DEPARTMENT</th>\n",
|
145 |
+
" <th>CATEGORY</th>\n",
|
146 |
+
" <th>SUBCATEGORY</th>\n",
|
147 |
+
" <th>BREADCRUMBS</th>\n",
|
148 |
+
" <th>SKU</th>\n",
|
149 |
+
" <th>PRODUCT_URL</th>\n",
|
150 |
+
" <th>PRODUCT_NAME</th>\n",
|
151 |
+
" <th>BRAND</th>\n",
|
152 |
+
" <th>PRICE_RETAIL</th>\n",
|
153 |
+
" <th>PRICE_CURRENT</th>\n",
|
154 |
+
" <th>PRODUCT_SIZE</th>\n",
|
155 |
+
" <th>PROMOTION</th>\n",
|
156 |
+
" <th>RunDate</th>\n",
|
157 |
+
" <th>tid</th>\n",
|
158 |
+
" </tr>\n",
|
159 |
+
" </thead>\n",
|
160 |
+
" <tbody>\n",
|
161 |
+
" <tr>\n",
|
162 |
+
" <th>0</th>\n",
|
163 |
+
" <td>79936</td>\n",
|
164 |
+
" <td>Deli</td>\n",
|
165 |
+
" <td>Hummus, Dips, & Salsa</td>\n",
|
166 |
+
" <td>NaN</td>\n",
|
167 |
+
" <td>Deli/Hummus, Dips, & Salsa</td>\n",
|
168 |
+
" <td>110895339</td>\n",
|
169 |
+
" <td>https://www.walmart.com/ip/Marketside-Roasted-...</td>\n",
|
170 |
+
" <td>Marketside Roasted Red Pepper Hummus, 10 Oz</td>\n",
|
171 |
+
" <td>Marketside</td>\n",
|
172 |
+
" <td>2.67</td>\n",
|
173 |
+
" <td>2.67</td>\n",
|
174 |
+
" <td>10</td>\n",
|
175 |
+
" <td>NaN</td>\n",
|
176 |
+
" <td>2022-09-11 21:20:04</td>\n",
|
177 |
+
" <td>16163804</td>\n",
|
178 |
+
" </tr>\n",
|
179 |
+
" <tr>\n",
|
180 |
+
" <th>1</th>\n",
|
181 |
+
" <td>79936</td>\n",
|
182 |
+
" <td>Deli</td>\n",
|
183 |
+
" <td>Hummus, Dips, & Salsa</td>\n",
|
184 |
+
" <td>NaN</td>\n",
|
185 |
+
" <td>Deli/Hummus, Dips, & Salsa</td>\n",
|
186 |
+
" <td>105455228</td>\n",
|
187 |
+
" <td>https://www.walmart.com/ip/Marketside-Roasted-...</td>\n",
|
188 |
+
" <td>Marketside Roasted Garlic Hummus, 10 Oz</td>\n",
|
189 |
+
" <td>Marketside</td>\n",
|
190 |
+
" <td>2.67</td>\n",
|
191 |
+
" <td>2.67</td>\n",
|
192 |
+
" <td>10</td>\n",
|
193 |
+
" <td>NaN</td>\n",
|
194 |
+
" <td>2022-09-11 21:20:04</td>\n",
|
195 |
+
" <td>16163805</td>\n",
|
196 |
+
" </tr>\n",
|
197 |
+
" <tr>\n",
|
198 |
+
" <th>2</th>\n",
|
199 |
+
" <td>79936</td>\n",
|
200 |
+
" <td>Deli</td>\n",
|
201 |
+
" <td>Hummus, Dips, & Salsa</td>\n",
|
202 |
+
" <td>NaN</td>\n",
|
203 |
+
" <td>Deli/Hummus, Dips, & Salsa</td>\n",
|
204 |
+
" <td>128642379</td>\n",
|
205 |
+
" <td>https://www.walmart.com/ip/Marketside-Classic-...</td>\n",
|
206 |
+
" <td>Marketside Classic Hummus, 10 Oz</td>\n",
|
207 |
+
" <td>Marketside</td>\n",
|
208 |
+
" <td>2.67</td>\n",
|
209 |
+
" <td>2.67</td>\n",
|
210 |
+
" <td>10</td>\n",
|
211 |
+
" <td>NaN</td>\n",
|
212 |
+
" <td>2022-09-11 21:20:04</td>\n",
|
213 |
+
" <td>16163806</td>\n",
|
214 |
+
" </tr>\n",
|
215 |
+
" <tr>\n",
|
216 |
+
" <th>3</th>\n",
|
217 |
+
" <td>79936</td>\n",
|
218 |
+
" <td>Deli</td>\n",
|
219 |
+
" <td>Hummus, Dips, & Salsa</td>\n",
|
220 |
+
" <td>NaN</td>\n",
|
221 |
+
" <td>Deli/Hummus, Dips, & Salsa</td>\n",
|
222 |
+
" <td>366126367</td>\n",
|
223 |
+
" <td>https://www.walmart.com/ip/Marketside-Everythi...</td>\n",
|
224 |
+
" <td>Marketside Everything Hummus, 10 oz</td>\n",
|
225 |
+
" <td>Marketside</td>\n",
|
226 |
+
" <td>2.67</td>\n",
|
227 |
+
" <td>2.67</td>\n",
|
228 |
+
" <td>10</td>\n",
|
229 |
+
" <td>NaN</td>\n",
|
230 |
+
" <td>2022-09-11 21:20:04</td>\n",
|
231 |
+
" <td>16163807</td>\n",
|
232 |
+
" </tr>\n",
|
233 |
+
" <tr>\n",
|
234 |
+
" <th>4</th>\n",
|
235 |
+
" <td>79936</td>\n",
|
236 |
+
" <td>Deli</td>\n",
|
237 |
+
" <td>Hummus, Dips, & Salsa</td>\n",
|
238 |
+
" <td>NaN</td>\n",
|
239 |
+
" <td>Deli/Hummus, Dips, & Salsa</td>\n",
|
240 |
+
" <td>160090316</td>\n",
|
241 |
+
" <td>https://www.walmart.com/ip/Price-s-Jalapeno-Di...</td>\n",
|
242 |
+
" <td>Price's Jalapeno Dip, 12 Oz.</td>\n",
|
243 |
+
" <td>Price's</td>\n",
|
244 |
+
" <td>3.12</td>\n",
|
245 |
+
" <td>3.12</td>\n",
|
246 |
+
" <td>12</td>\n",
|
247 |
+
" <td>NaN</td>\n",
|
248 |
+
" <td>2022-09-11 21:20:04</td>\n",
|
249 |
+
" <td>16163808</td>\n",
|
250 |
+
" </tr>\n",
|
251 |
+
" <tr>\n",
|
252 |
+
" <th>...</th>\n",
|
253 |
+
" <td>...</td>\n",
|
254 |
+
" <td>...</td>\n",
|
255 |
+
" <td>...</td>\n",
|
256 |
+
" <td>...</td>\n",
|
257 |
+
" <td>...</td>\n",
|
258 |
+
" <td>...</td>\n",
|
259 |
+
" <td>...</td>\n",
|
260 |
+
" <td>...</td>\n",
|
261 |
+
" <td>...</td>\n",
|
262 |
+
" <td>...</td>\n",
|
263 |
+
" <td>...</td>\n",
|
264 |
+
" <td>...</td>\n",
|
265 |
+
" <td>...</td>\n",
|
266 |
+
" <td>...</td>\n",
|
267 |
+
" <td>...</td>\n",
|
268 |
+
" </tr>\n",
|
269 |
+
" <tr>\n",
|
270 |
+
" <th>568529</th>\n",
|
271 |
+
" <td>70072</td>\n",
|
272 |
+
" <td>Alcohol</td>\n",
|
273 |
+
" <td>Wine</td>\n",
|
274 |
+
" <td>White Wine</td>\n",
|
275 |
+
" <td>Alcohol/Wine</td>\n",
|
276 |
+
" <td>593600139</td>\n",
|
277 |
+
" <td>https://www.walmart.com/ip/Farm-Fresh-Blueberr...</td>\n",
|
278 |
+
" <td>Farm Fresh Blueberry Moscato 750ml</td>\n",
|
279 |
+
" <td>Farm Fresh Wine Company</td>\n",
|
280 |
+
" <td>9.98</td>\n",
|
281 |
+
" <td>9.98</td>\n",
|
282 |
+
" <td>750</td>\n",
|
283 |
+
" <td>NaN</td>\n",
|
284 |
+
" <td>2022-09-11 21:20:04</td>\n",
|
285 |
+
" <td>16732333</td>\n",
|
286 |
+
" </tr>\n",
|
287 |
+
" <tr>\n",
|
288 |
+
" <th>568530</th>\n",
|
289 |
+
" <td>70072</td>\n",
|
290 |
+
" <td>Alcohol</td>\n",
|
291 |
+
" <td>Wine</td>\n",
|
292 |
+
" <td>White Wine</td>\n",
|
293 |
+
" <td>Alcohol/Wine</td>\n",
|
294 |
+
" <td>333403243</td>\n",
|
295 |
+
" <td>https://www.walmart.com/ip/Farm-Fresh-Peach-Mo...</td>\n",
|
296 |
+
" <td>Farm Fresh Peach Moscato 750 Ml</td>\n",
|
297 |
+
" <td>Farm Fresh Wine Company</td>\n",
|
298 |
+
" <td>9.98</td>\n",
|
299 |
+
" <td>9.98</td>\n",
|
300 |
+
" <td>750</td>\n",
|
301 |
+
" <td>NaN</td>\n",
|
302 |
+
" <td>2022-09-11 21:20:04</td>\n",
|
303 |
+
" <td>16732334</td>\n",
|
304 |
+
" </tr>\n",
|
305 |
+
" <tr>\n",
|
306 |
+
" <th>568531</th>\n",
|
307 |
+
" <td>70072</td>\n",
|
308 |
+
" <td>Alcohol</td>\n",
|
309 |
+
" <td>Wine</td>\n",
|
310 |
+
" <td>White Wine</td>\n",
|
311 |
+
" <td>Alcohol/Wine</td>\n",
|
312 |
+
" <td>526588325</td>\n",
|
313 |
+
" <td>https://www.walmart.com/ip/Farm-Fresh-Raspberr...</td>\n",
|
314 |
+
" <td>Farm Fresh Raspberry Moscato 750ml</td>\n",
|
315 |
+
" <td>Farm Fresh Wine Company</td>\n",
|
316 |
+
" <td>9.98</td>\n",
|
317 |
+
" <td>9.98</td>\n",
|
318 |
+
" <td>750</td>\n",
|
319 |
+
" <td>NaN</td>\n",
|
320 |
+
" <td>2022-09-11 21:20:04</td>\n",
|
321 |
+
" <td>16732335</td>\n",
|
322 |
+
" </tr>\n",
|
323 |
+
" <tr>\n",
|
324 |
+
" <th>568532</th>\n",
|
325 |
+
" <td>70072</td>\n",
|
326 |
+
" <td>Alcohol</td>\n",
|
327 |
+
" <td>Wine</td>\n",
|
328 |
+
" <td>White Wine</td>\n",
|
329 |
+
" <td>Alcohol/Wine</td>\n",
|
330 |
+
" <td>286992782</td>\n",
|
331 |
+
" <td>https://www.walmart.com/ip/Farm-Fresh-Mango-Mo...</td>\n",
|
332 |
+
" <td>Farm Fresh Mango Moscato 750ml</td>\n",
|
333 |
+
" <td>Farm Fresh Wine Company</td>\n",
|
334 |
+
" <td>9.98</td>\n",
|
335 |
+
" <td>9.98</td>\n",
|
336 |
+
" <td>750</td>\n",
|
337 |
+
" <td>NaN</td>\n",
|
338 |
+
" <td>2022-09-11 21:20:04</td>\n",
|
339 |
+
" <td>16732336</td>\n",
|
340 |
+
" </tr>\n",
|
341 |
+
" <tr>\n",
|
342 |
+
" <th>568533</th>\n",
|
343 |
+
" <td>70072</td>\n",
|
344 |
+
" <td>Alcohol</td>\n",
|
345 |
+
" <td>Wine</td>\n",
|
346 |
+
" <td>White Wine</td>\n",
|
347 |
+
" <td>Alcohol/Wine</td>\n",
|
348 |
+
" <td>160015930</td>\n",
|
349 |
+
" <td>https://www.walmart.com/ip/Ole-Orleans-Heritag...</td>\n",
|
350 |
+
" <td>Ole Orleans Heritage Riesling 750ml</td>\n",
|
351 |
+
" <td>Ole Orleans</td>\n",
|
352 |
+
" <td>18.98</td>\n",
|
353 |
+
" <td>18.98</td>\n",
|
354 |
+
" <td>750</td>\n",
|
355 |
+
" <td>NaN</td>\n",
|
356 |
+
" <td>2022-09-11 21:20:04</td>\n",
|
357 |
+
" <td>16732337</td>\n",
|
358 |
+
" </tr>\n",
|
359 |
+
" </tbody>\n",
|
360 |
+
"</table>\n",
|
361 |
+
"<p>568534 rows × 15 columns</p>\n",
|
362 |
+
"</div>"
|
363 |
+
]
|
364 |
+
},
|
365 |
+
"execution_count": 2,
|
366 |
+
"metadata": {},
|
367 |
+
"output_type": "execute_result"
|
368 |
+
}
|
369 |
+
],
|
370 |
+
"execution_count": 2
|
371 |
+
},
|
372 |
+
{
|
373 |
+
"cell_type": "code",
|
374 |
+
"id": "e65e1fbd9770b4",
|
375 |
+
"metadata": {
|
376 |
+
"ExecuteTime": {
|
377 |
+
"end_time": "2024-07-30T12:35:08.778596Z",
|
378 |
+
"start_time": "2024-07-30T12:35:08.732718Z"
|
379 |
+
}
|
380 |
+
},
|
381 |
+
"source": [
|
382 |
+
"df=df[['PRODUCT_NAME','DEPARTMENT','CATEGORY','BREADCRUMBS','BRAND']]\n",
|
383 |
+
"df['PRODUCT']=df['PRODUCT_NAME']"
|
384 |
+
],
|
385 |
+
"outputs": [
|
386 |
+
{
|
387 |
+
"name": "stderr",
|
388 |
+
"output_type": "stream",
|
389 |
+
"text": [
|
390 |
+
"C:\\Users\\thaku\\AppData\\Local\\Temp\\ipykernel_13136\\2027505516.py:2: SettingWithCopyWarning: \n",
|
391 |
+
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
|
392 |
+
"Try using .loc[row_indexer,col_indexer] = value instead\n",
|
393 |
+
"\n",
|
394 |
+
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
|
395 |
+
" df['PRODUCT']=df['PRODUCT_NAME']\n"
|
396 |
+
]
|
397 |
+
}
|
398 |
+
],
|
399 |
+
"execution_count": 3
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"metadata": {
|
403 |
+
"ExecuteTime": {
|
404 |
+
"end_time": "2024-07-30T12:35:08.903031Z",
|
405 |
+
"start_time": "2024-07-30T12:35:08.780590Z"
|
406 |
+
}
|
407 |
+
},
|
408 |
+
"cell_type": "code",
|
409 |
+
"source": "df.isnull().sum()",
|
410 |
+
"id": "fa1760637e52808f",
|
411 |
+
"outputs": [
|
412 |
+
{
|
413 |
+
"data": {
|
414 |
+
"text/plain": [
|
415 |
+
"PRODUCT_NAME 0\n",
|
416 |
+
"DEPARTMENT 0\n",
|
417 |
+
"CATEGORY 0\n",
|
418 |
+
"BREADCRUMBS 0\n",
|
419 |
+
"BRAND 27\n",
|
420 |
+
"PRODUCT 0\n",
|
421 |
+
"dtype: int64"
|
422 |
+
]
|
423 |
+
},
|
424 |
+
"execution_count": 4,
|
425 |
+
"metadata": {},
|
426 |
+
"output_type": "execute_result"
|
427 |
+
}
|
428 |
+
],
|
429 |
+
"execution_count": 4
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"metadata": {
|
433 |
+
"ExecuteTime": {
|
434 |
+
"end_time": "2024-07-30T12:35:09.045434Z",
|
435 |
+
"start_time": "2024-07-30T12:35:08.905158Z"
|
436 |
+
}
|
437 |
+
},
|
438 |
+
"cell_type": "code",
|
439 |
+
"source": "df = df[df['BRAND'].apply(lambda x: isinstance(x, str))]",
|
440 |
+
"id": "e33c2a31c09617ba",
|
441 |
+
"outputs": [],
|
442 |
+
"execution_count": 5
|
443 |
+
},
|
444 |
+
{
|
445 |
+
"cell_type": "code",
|
446 |
+
"id": "dc247f93acd769a",
|
447 |
+
"metadata": {
|
448 |
+
"ExecuteTime": {
|
449 |
+
"end_time": "2024-07-30T12:35:09.406463Z",
|
450 |
+
"start_time": "2024-07-30T12:35:09.046431Z"
|
451 |
+
}
|
452 |
+
},
|
453 |
+
"source": [
|
454 |
+
"df.dropna()\n",
|
455 |
+
"def is_string(value):\n",
|
456 |
+
" return isinstance(value, str)\n",
|
457 |
+
"\n",
|
458 |
+
"# Identify rows in 'BRAND' column where the value is not a string\n",
|
459 |
+
"non_string_rows = df[~df['BRAND'].apply(is_string)].index\n",
|
460 |
+
"print(non_string_rows)\n",
|
461 |
+
"# Drop those rows from the DataFrame\n",
|
462 |
+
"df.drop(index=non_string_rows)"
|
463 |
+
],
|
464 |
+
"outputs": [
|
465 |
+
{
|
466 |
+
"name": "stdout",
|
467 |
+
"output_type": "stream",
|
468 |
+
"text": [
|
469 |
+
"Index([], dtype='int64')\n"
|
470 |
+
]
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"data": {
|
474 |
+
"text/plain": [
|
475 |
+
" PRODUCT_NAME DEPARTMENT \\\n",
|
476 |
+
"0 Marketside Roasted Red Pepper Hummus, 10 Oz Deli \n",
|
477 |
+
"1 Marketside Roasted Garlic Hummus, 10 Oz Deli \n",
|
478 |
+
"2 Marketside Classic Hummus, 10 Oz Deli \n",
|
479 |
+
"3 Marketside Everything Hummus, 10 oz Deli \n",
|
480 |
+
"4 Price's Jalapeno Dip, 12 Oz. Deli \n",
|
481 |
+
"... ... ... \n",
|
482 |
+
"568529 Farm Fresh Blueberry Moscato 750ml Alcohol \n",
|
483 |
+
"568530 Farm Fresh Peach Moscato 750 Ml Alcohol \n",
|
484 |
+
"568531 Farm Fresh Raspberry Moscato 750ml Alcohol \n",
|
485 |
+
"568532 Farm Fresh Mango Moscato 750ml Alcohol \n",
|
486 |
+
"568533 Ole Orleans Heritage Riesling 750ml Alcohol \n",
|
487 |
+
"\n",
|
488 |
+
" CATEGORY BREADCRUMBS \\\n",
|
489 |
+
"0 Hummus, Dips, & Salsa Deli/Hummus, Dips, & Salsa \n",
|
490 |
+
"1 Hummus, Dips, & Salsa Deli/Hummus, Dips, & Salsa \n",
|
491 |
+
"2 Hummus, Dips, & Salsa Deli/Hummus, Dips, & Salsa \n",
|
492 |
+
"3 Hummus, Dips, & Salsa Deli/Hummus, Dips, & Salsa \n",
|
493 |
+
"4 Hummus, Dips, & Salsa Deli/Hummus, Dips, & Salsa \n",
|
494 |
+
"... ... ... \n",
|
495 |
+
"568529 Wine Alcohol/Wine \n",
|
496 |
+
"568530 Wine Alcohol/Wine \n",
|
497 |
+
"568531 Wine Alcohol/Wine \n",
|
498 |
+
"568532 Wine Alcohol/Wine \n",
|
499 |
+
"568533 Wine Alcohol/Wine \n",
|
500 |
+
"\n",
|
501 |
+
" BRAND PRODUCT \n",
|
502 |
+
"0 Marketside Marketside Roasted Red Pepper Hummus, 10 Oz \n",
|
503 |
+
"1 Marketside Marketside Roasted Garlic Hummus, 10 Oz \n",
|
504 |
+
"2 Marketside Marketside Classic Hummus, 10 Oz \n",
|
505 |
+
"3 Marketside Marketside Everything Hummus, 10 oz \n",
|
506 |
+
"4 Price's Price's Jalapeno Dip, 12 Oz. \n",
|
507 |
+
"... ... ... \n",
|
508 |
+
"568529 Farm Fresh Wine Company Farm Fresh Blueberry Moscato 750ml \n",
|
509 |
+
"568530 Farm Fresh Wine Company Farm Fresh Peach Moscato 750 Ml \n",
|
510 |
+
"568531 Farm Fresh Wine Company Farm Fresh Raspberry Moscato 750ml \n",
|
511 |
+
"568532 Farm Fresh Wine Company Farm Fresh Mango Moscato 750ml \n",
|
512 |
+
"568533 Ole Orleans Ole Orleans Heritage Riesling 750ml \n",
|
513 |
+
"\n",
|
514 |
+
"[568507 rows x 6 columns]"
|
515 |
+
],
|
516 |
+
"text/html": [
|
517 |
+
"<div>\n",
|
518 |
+
"<style scoped>\n",
|
519 |
+
" .dataframe tbody tr th:only-of-type {\n",
|
520 |
+
" vertical-align: middle;\n",
|
521 |
+
" }\n",
|
522 |
+
"\n",
|
523 |
+
" .dataframe tbody tr th {\n",
|
524 |
+
" vertical-align: top;\n",
|
525 |
+
" }\n",
|
526 |
+
"\n",
|
527 |
+
" .dataframe thead th {\n",
|
528 |
+
" text-align: right;\n",
|
529 |
+
" }\n",
|
530 |
+
"</style>\n",
|
531 |
+
"<table border=\"1\" class=\"dataframe\">\n",
|
532 |
+
" <thead>\n",
|
533 |
+
" <tr style=\"text-align: right;\">\n",
|
534 |
+
" <th></th>\n",
|
535 |
+
" <th>PRODUCT_NAME</th>\n",
|
536 |
+
" <th>DEPARTMENT</th>\n",
|
537 |
+
" <th>CATEGORY</th>\n",
|
538 |
+
" <th>BREADCRUMBS</th>\n",
|
539 |
+
" <th>BRAND</th>\n",
|
540 |
+
" <th>PRODUCT</th>\n",
|
541 |
+
" </tr>\n",
|
542 |
+
" </thead>\n",
|
543 |
+
" <tbody>\n",
|
544 |
+
" <tr>\n",
|
545 |
+
" <th>0</th>\n",
|
546 |
+
" <td>Marketside Roasted Red Pepper Hummus, 10 Oz</td>\n",
|
547 |
+
" <td>Deli</td>\n",
|
548 |
+
" <td>Hummus, Dips, & Salsa</td>\n",
|
549 |
+
" <td>Deli/Hummus, Dips, & Salsa</td>\n",
|
550 |
+
" <td>Marketside</td>\n",
|
551 |
+
" <td>Marketside Roasted Red Pepper Hummus, 10 Oz</td>\n",
|
552 |
+
" </tr>\n",
|
553 |
+
" <tr>\n",
|
554 |
+
" <th>1</th>\n",
|
555 |
+
" <td>Marketside Roasted Garlic Hummus, 10 Oz</td>\n",
|
556 |
+
" <td>Deli</td>\n",
|
557 |
+
" <td>Hummus, Dips, & Salsa</td>\n",
|
558 |
+
" <td>Deli/Hummus, Dips, & Salsa</td>\n",
|
559 |
+
" <td>Marketside</td>\n",
|
560 |
+
" <td>Marketside Roasted Garlic Hummus, 10 Oz</td>\n",
|
561 |
+
" </tr>\n",
|
562 |
+
" <tr>\n",
|
563 |
+
" <th>2</th>\n",
|
564 |
+
" <td>Marketside Classic Hummus, 10 Oz</td>\n",
|
565 |
+
" <td>Deli</td>\n",
|
566 |
+
" <td>Hummus, Dips, & Salsa</td>\n",
|
567 |
+
" <td>Deli/Hummus, Dips, & Salsa</td>\n",
|
568 |
+
" <td>Marketside</td>\n",
|
569 |
+
" <td>Marketside Classic Hummus, 10 Oz</td>\n",
|
570 |
+
" </tr>\n",
|
571 |
+
" <tr>\n",
|
572 |
+
" <th>3</th>\n",
|
573 |
+
" <td>Marketside Everything Hummus, 10 oz</td>\n",
|
574 |
+
" <td>Deli</td>\n",
|
575 |
+
" <td>Hummus, Dips, & Salsa</td>\n",
|
576 |
+
" <td>Deli/Hummus, Dips, & Salsa</td>\n",
|
577 |
+
" <td>Marketside</td>\n",
|
578 |
+
" <td>Marketside Everything Hummus, 10 oz</td>\n",
|
579 |
+
" </tr>\n",
|
580 |
+
" <tr>\n",
|
581 |
+
" <th>4</th>\n",
|
582 |
+
" <td>Price's Jalapeno Dip, 12 Oz.</td>\n",
|
583 |
+
" <td>Deli</td>\n",
|
584 |
+
" <td>Hummus, Dips, & Salsa</td>\n",
|
585 |
+
" <td>Deli/Hummus, Dips, & Salsa</td>\n",
|
586 |
+
" <td>Price's</td>\n",
|
587 |
+
" <td>Price's Jalapeno Dip, 12 Oz.</td>\n",
|
588 |
+
" </tr>\n",
|
589 |
+
" <tr>\n",
|
590 |
+
" <th>...</th>\n",
|
591 |
+
" <td>...</td>\n",
|
592 |
+
" <td>...</td>\n",
|
593 |
+
" <td>...</td>\n",
|
594 |
+
" <td>...</td>\n",
|
595 |
+
" <td>...</td>\n",
|
596 |
+
" <td>...</td>\n",
|
597 |
+
" </tr>\n",
|
598 |
+
" <tr>\n",
|
599 |
+
" <th>568529</th>\n",
|
600 |
+
" <td>Farm Fresh Blueberry Moscato 750ml</td>\n",
|
601 |
+
" <td>Alcohol</td>\n",
|
602 |
+
" <td>Wine</td>\n",
|
603 |
+
" <td>Alcohol/Wine</td>\n",
|
604 |
+
" <td>Farm Fresh Wine Company</td>\n",
|
605 |
+
" <td>Farm Fresh Blueberry Moscato 750ml</td>\n",
|
606 |
+
" </tr>\n",
|
607 |
+
" <tr>\n",
|
608 |
+
" <th>568530</th>\n",
|
609 |
+
" <td>Farm Fresh Peach Moscato 750 Ml</td>\n",
|
610 |
+
" <td>Alcohol</td>\n",
|
611 |
+
" <td>Wine</td>\n",
|
612 |
+
" <td>Alcohol/Wine</td>\n",
|
613 |
+
" <td>Farm Fresh Wine Company</td>\n",
|
614 |
+
" <td>Farm Fresh Peach Moscato 750 Ml</td>\n",
|
615 |
+
" </tr>\n",
|
616 |
+
" <tr>\n",
|
617 |
+
" <th>568531</th>\n",
|
618 |
+
" <td>Farm Fresh Raspberry Moscato 750ml</td>\n",
|
619 |
+
" <td>Alcohol</td>\n",
|
620 |
+
" <td>Wine</td>\n",
|
621 |
+
" <td>Alcohol/Wine</td>\n",
|
622 |
+
" <td>Farm Fresh Wine Company</td>\n",
|
623 |
+
" <td>Farm Fresh Raspberry Moscato 750ml</td>\n",
|
624 |
+
" </tr>\n",
|
625 |
+
" <tr>\n",
|
626 |
+
" <th>568532</th>\n",
|
627 |
+
" <td>Farm Fresh Mango Moscato 750ml</td>\n",
|
628 |
+
" <td>Alcohol</td>\n",
|
629 |
+
" <td>Wine</td>\n",
|
630 |
+
" <td>Alcohol/Wine</td>\n",
|
631 |
+
" <td>Farm Fresh Wine Company</td>\n",
|
632 |
+
" <td>Farm Fresh Mango Moscato 750ml</td>\n",
|
633 |
+
" </tr>\n",
|
634 |
+
" <tr>\n",
|
635 |
+
" <th>568533</th>\n",
|
636 |
+
" <td>Ole Orleans Heritage Riesling 750ml</td>\n",
|
637 |
+
" <td>Alcohol</td>\n",
|
638 |
+
" <td>Wine</td>\n",
|
639 |
+
" <td>Alcohol/Wine</td>\n",
|
640 |
+
" <td>Ole Orleans</td>\n",
|
641 |
+
" <td>Ole Orleans Heritage Riesling 750ml</td>\n",
|
642 |
+
" </tr>\n",
|
643 |
+
" </tbody>\n",
|
644 |
+
"</table>\n",
|
645 |
+
"<p>568507 rows × 6 columns</p>\n",
|
646 |
+
"</div>"
|
647 |
+
]
|
648 |
+
},
|
649 |
+
"execution_count": 6,
|
650 |
+
"metadata": {},
|
651 |
+
"output_type": "execute_result"
|
652 |
+
}
|
653 |
+
],
|
654 |
+
"execution_count": 6
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"cell_type": "code",
|
658 |
+
"id": "3478dbf45d0de013",
|
659 |
+
"metadata": {
|
660 |
+
"ExecuteTime": {
|
661 |
+
"end_time": "2024-07-30T12:35:09.421458Z",
|
662 |
+
"start_time": "2024-07-30T12:35:09.407461Z"
|
663 |
+
}
|
664 |
+
},
|
665 |
+
"source": [
|
666 |
+
"import ast,re\n",
|
667 |
+
"def preprocess_text(text):\n",
|
668 |
+
" # Remove non-alphabet characters and extra spaces\n",
|
669 |
+
" text = re.sub(r'[^a-zA-Z\\s]', '', text)\n",
|
670 |
+
" text = re.sub(r'\\s+', ' ', text).strip()\n",
|
671 |
+
" return text.lower()"
|
672 |
+
],
|
673 |
+
"outputs": [],
|
674 |
+
"execution_count": 7
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"cell_type": "code",
|
678 |
+
"id": "47b4b465b97821bb",
|
679 |
+
"metadata": {
|
680 |
+
"ExecuteTime": {
|
681 |
+
"end_time": "2024-07-30T12:35:17.915264Z",
|
682 |
+
"start_time": "2024-07-30T12:35:09.422456Z"
|
683 |
+
}
|
684 |
+
},
|
685 |
+
"source": [
|
686 |
+
"df['PRODUCT']=df['PRODUCT'].apply(preprocess_text)\n",
|
687 |
+
"df['DEPARTMENT']=df['DEPARTMENT'].apply(preprocess_text)\n",
|
688 |
+
"df['CATEGORY']=df['CATEGORY'].apply(preprocess_text)\n",
|
689 |
+
"df['BREADCRUMBS']=df['BREADCRUMBS'].apply(preprocess_text)\n",
|
690 |
+
"df['BRAND']=df['BRAND'].apply(preprocess_text)"
|
691 |
+
],
|
692 |
+
"outputs": [],
|
693 |
+
"execution_count": 8
|
694 |
+
},
|
695 |
+
{
|
696 |
+
"cell_type": "code",
|
697 |
+
"id": "bca9973bcd761828",
|
698 |
+
"metadata": {
|
699 |
+
"ExecuteTime": {
|
700 |
+
"end_time": "2024-07-30T12:35:21.683604Z",
|
701 |
+
"start_time": "2024-07-30T12:35:17.918253Z"
|
702 |
+
}
|
703 |
+
},
|
704 |
+
"source": [
|
705 |
+
"df['PRODUCT']=df['PRODUCT'].apply(lambda x:x.split())\n",
|
706 |
+
"df['DEPARTMENT']=df['DEPARTMENT'].apply(lambda x:x.split())\n",
|
707 |
+
"df['CATEGORY']=df['CATEGORY'].apply(lambda x:x.split())\n",
|
708 |
+
"df['BREADCRUMBS']=df['BREADCRUMBS'].apply(lambda x:x.split())\n",
|
709 |
+
"df['BRAND']=df['BRAND'].apply(lambda x:x.split())"
|
710 |
+
],
|
711 |
+
"outputs": [],
|
712 |
+
"execution_count": 9
|
713 |
+
},
|
714 |
+
{
|
715 |
+
"cell_type": "code",
|
716 |
+
"id": "8240161bbf8dd746",
|
717 |
+
"metadata": {
|
718 |
+
"ExecuteTime": {
|
719 |
+
"end_time": "2024-07-30T12:35:24.181188Z",
|
720 |
+
"start_time": "2024-07-30T12:35:21.686396Z"
|
721 |
+
}
|
722 |
+
},
|
723 |
+
"source": "df['tags']=df['PRODUCT']+df['DEPARTMENT']+df['CATEGORY']+df['BREADCRUMBS']+df['BRAND']",
|
724 |
+
"outputs": [],
|
725 |
+
"execution_count": 10
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"cell_type": "code",
|
729 |
+
"id": "620840a23eee5d5e",
|
730 |
+
"metadata": {
|
731 |
+
"ExecuteTime": {
|
732 |
+
"end_time": "2024-07-30T12:35:24.212213Z",
|
733 |
+
"start_time": "2024-07-30T12:35:24.182142Z"
|
734 |
+
}
|
735 |
+
},
|
736 |
+
"source": [
|
737 |
+
"df"
|
738 |
+
],
|
739 |
+
"outputs": [
|
740 |
+
{
|
741 |
+
"data": {
|
742 |
+
"text/plain": [
|
743 |
+
" PRODUCT_NAME DEPARTMENT \\\n",
|
744 |
+
"0 Marketside Roasted Red Pepper Hummus, 10 Oz [deli] \n",
|
745 |
+
"1 Marketside Roasted Garlic Hummus, 10 Oz [deli] \n",
|
746 |
+
"2 Marketside Classic Hummus, 10 Oz [deli] \n",
|
747 |
+
"3 Marketside Everything Hummus, 10 oz [deli] \n",
|
748 |
+
"4 Price's Jalapeno Dip, 12 Oz. [deli] \n",
|
749 |
+
"... ... ... \n",
|
750 |
+
"568529 Farm Fresh Blueberry Moscato 750ml [alcohol] \n",
|
751 |
+
"568530 Farm Fresh Peach Moscato 750 Ml [alcohol] \n",
|
752 |
+
"568531 Farm Fresh Raspberry Moscato 750ml [alcohol] \n",
|
753 |
+
"568532 Farm Fresh Mango Moscato 750ml [alcohol] \n",
|
754 |
+
"568533 Ole Orleans Heritage Riesling 750ml [alcohol] \n",
|
755 |
+
"\n",
|
756 |
+
" CATEGORY BREADCRUMBS \\\n",
|
757 |
+
"0 [hummus, dips, salsa] [delihummus, dips, salsa] \n",
|
758 |
+
"1 [hummus, dips, salsa] [delihummus, dips, salsa] \n",
|
759 |
+
"2 [hummus, dips, salsa] [delihummus, dips, salsa] \n",
|
760 |
+
"3 [hummus, dips, salsa] [delihummus, dips, salsa] \n",
|
761 |
+
"4 [hummus, dips, salsa] [delihummus, dips, salsa] \n",
|
762 |
+
"... ... ... \n",
|
763 |
+
"568529 [wine] [alcoholwine] \n",
|
764 |
+
"568530 [wine] [alcoholwine] \n",
|
765 |
+
"568531 [wine] [alcoholwine] \n",
|
766 |
+
"568532 [wine] [alcoholwine] \n",
|
767 |
+
"568533 [wine] [alcoholwine] \n",
|
768 |
+
"\n",
|
769 |
+
" BRAND \\\n",
|
770 |
+
"0 [marketside] \n",
|
771 |
+
"1 [marketside] \n",
|
772 |
+
"2 [marketside] \n",
|
773 |
+
"3 [marketside] \n",
|
774 |
+
"4 [prices] \n",
|
775 |
+
"... ... \n",
|
776 |
+
"568529 [farm, fresh, wine, company] \n",
|
777 |
+
"568530 [farm, fresh, wine, company] \n",
|
778 |
+
"568531 [farm, fresh, wine, company] \n",
|
779 |
+
"568532 [farm, fresh, wine, company] \n",
|
780 |
+
"568533 [ole, orleans] \n",
|
781 |
+
"\n",
|
782 |
+
" PRODUCT \\\n",
|
783 |
+
"0 [marketside, roasted, red, pepper, hummus, oz] \n",
|
784 |
+
"1 [marketside, roasted, garlic, hummus, oz] \n",
|
785 |
+
"2 [marketside, classic, hummus, oz] \n",
|
786 |
+
"3 [marketside, everything, hummus, oz] \n",
|
787 |
+
"4 [prices, jalapeno, dip, oz] \n",
|
788 |
+
"... ... \n",
|
789 |
+
"568529 [farm, fresh, blueberry, moscato, ml] \n",
|
790 |
+
"568530 [farm, fresh, peach, moscato, ml] \n",
|
791 |
+
"568531 [farm, fresh, raspberry, moscato, ml] \n",
|
792 |
+
"568532 [farm, fresh, mango, moscato, ml] \n",
|
793 |
+
"568533 [ole, orleans, heritage, riesling, ml] \n",
|
794 |
+
"\n",
|
795 |
+
" tags \n",
|
796 |
+
"0 [marketside, roasted, red, pepper, hummus, oz,... \n",
|
797 |
+
"1 [marketside, roasted, garlic, hummus, oz, deli... \n",
|
798 |
+
"2 [marketside, classic, hummus, oz, deli, hummus... \n",
|
799 |
+
"3 [marketside, everything, hummus, oz, deli, hum... \n",
|
800 |
+
"4 [prices, jalapeno, dip, oz, deli, hummus, dips... \n",
|
801 |
+
"... ... \n",
|
802 |
+
"568529 [farm, fresh, blueberry, moscato, ml, alcohol,... \n",
|
803 |
+
"568530 [farm, fresh, peach, moscato, ml, alcohol, win... \n",
|
804 |
+
"568531 [farm, fresh, raspberry, moscato, ml, alcohol,... \n",
|
805 |
+
"568532 [farm, fresh, mango, moscato, ml, alcohol, win... \n",
|
806 |
+
"568533 [ole, orleans, heritage, riesling, ml, alcohol... \n",
|
807 |
+
"\n",
|
808 |
+
"[568507 rows x 7 columns]"
|
809 |
+
],
|
810 |
+
"text/html": [
|
811 |
+
"<div>\n",
|
812 |
+
"<style scoped>\n",
|
813 |
+
" .dataframe tbody tr th:only-of-type {\n",
|
814 |
+
" vertical-align: middle;\n",
|
815 |
+
" }\n",
|
816 |
+
"\n",
|
817 |
+
" .dataframe tbody tr th {\n",
|
818 |
+
" vertical-align: top;\n",
|
819 |
+
" }\n",
|
820 |
+
"\n",
|
821 |
+
" .dataframe thead th {\n",
|
822 |
+
" text-align: right;\n",
|
823 |
+
" }\n",
|
824 |
+
"</style>\n",
|
825 |
+
"<table border=\"1\" class=\"dataframe\">\n",
|
826 |
+
" <thead>\n",
|
827 |
+
" <tr style=\"text-align: right;\">\n",
|
828 |
+
" <th></th>\n",
|
829 |
+
" <th>PRODUCT_NAME</th>\n",
|
830 |
+
" <th>DEPARTMENT</th>\n",
|
831 |
+
" <th>CATEGORY</th>\n",
|
832 |
+
" <th>BREADCRUMBS</th>\n",
|
833 |
+
" <th>BRAND</th>\n",
|
834 |
+
" <th>PRODUCT</th>\n",
|
835 |
+
" <th>tags</th>\n",
|
836 |
+
" </tr>\n",
|
837 |
+
" </thead>\n",
|
838 |
+
" <tbody>\n",
|
839 |
+
" <tr>\n",
|
840 |
+
" <th>0</th>\n",
|
841 |
+
" <td>Marketside Roasted Red Pepper Hummus, 10 Oz</td>\n",
|
842 |
+
" <td>[deli]</td>\n",
|
843 |
+
" <td>[hummus, dips, salsa]</td>\n",
|
844 |
+
" <td>[delihummus, dips, salsa]</td>\n",
|
845 |
+
" <td>[marketside]</td>\n",
|
846 |
+
" <td>[marketside, roasted, red, pepper, hummus, oz]</td>\n",
|
847 |
+
" <td>[marketside, roasted, red, pepper, hummus, oz,...</td>\n",
|
848 |
+
" </tr>\n",
|
849 |
+
" <tr>\n",
|
850 |
+
" <th>1</th>\n",
|
851 |
+
" <td>Marketside Roasted Garlic Hummus, 10 Oz</td>\n",
|
852 |
+
" <td>[deli]</td>\n",
|
853 |
+
" <td>[hummus, dips, salsa]</td>\n",
|
854 |
+
" <td>[delihummus, dips, salsa]</td>\n",
|
855 |
+
" <td>[marketside]</td>\n",
|
856 |
+
" <td>[marketside, roasted, garlic, hummus, oz]</td>\n",
|
857 |
+
" <td>[marketside, roasted, garlic, hummus, oz, deli...</td>\n",
|
858 |
+
" </tr>\n",
|
859 |
+
" <tr>\n",
|
860 |
+
" <th>2</th>\n",
|
861 |
+
" <td>Marketside Classic Hummus, 10 Oz</td>\n",
|
862 |
+
" <td>[deli]</td>\n",
|
863 |
+
" <td>[hummus, dips, salsa]</td>\n",
|
864 |
+
" <td>[delihummus, dips, salsa]</td>\n",
|
865 |
+
" <td>[marketside]</td>\n",
|
866 |
+
" <td>[marketside, classic, hummus, oz]</td>\n",
|
867 |
+
" <td>[marketside, classic, hummus, oz, deli, hummus...</td>\n",
|
868 |
+
" </tr>\n",
|
869 |
+
" <tr>\n",
|
870 |
+
" <th>3</th>\n",
|
871 |
+
" <td>Marketside Everything Hummus, 10 oz</td>\n",
|
872 |
+
" <td>[deli]</td>\n",
|
873 |
+
" <td>[hummus, dips, salsa]</td>\n",
|
874 |
+
" <td>[delihummus, dips, salsa]</td>\n",
|
875 |
+
" <td>[marketside]</td>\n",
|
876 |
+
" <td>[marketside, everything, hummus, oz]</td>\n",
|
877 |
+
" <td>[marketside, everything, hummus, oz, deli, hum...</td>\n",
|
878 |
+
" </tr>\n",
|
879 |
+
" <tr>\n",
|
880 |
+
" <th>4</th>\n",
|
881 |
+
" <td>Price's Jalapeno Dip, 12 Oz.</td>\n",
|
882 |
+
" <td>[deli]</td>\n",
|
883 |
+
" <td>[hummus, dips, salsa]</td>\n",
|
884 |
+
" <td>[delihummus, dips, salsa]</td>\n",
|
885 |
+
" <td>[prices]</td>\n",
|
886 |
+
" <td>[prices, jalapeno, dip, oz]</td>\n",
|
887 |
+
" <td>[prices, jalapeno, dip, oz, deli, hummus, dips...</td>\n",
|
888 |
+
" </tr>\n",
|
889 |
+
" <tr>\n",
|
890 |
+
" <th>...</th>\n",
|
891 |
+
" <td>...</td>\n",
|
892 |
+
" <td>...</td>\n",
|
893 |
+
" <td>...</td>\n",
|
894 |
+
" <td>...</td>\n",
|
895 |
+
" <td>...</td>\n",
|
896 |
+
" <td>...</td>\n",
|
897 |
+
" <td>...</td>\n",
|
898 |
+
" </tr>\n",
|
899 |
+
" <tr>\n",
|
900 |
+
" <th>568529</th>\n",
|
901 |
+
" <td>Farm Fresh Blueberry Moscato 750ml</td>\n",
|
902 |
+
" <td>[alcohol]</td>\n",
|
903 |
+
" <td>[wine]</td>\n",
|
904 |
+
" <td>[alcoholwine]</td>\n",
|
905 |
+
" <td>[farm, fresh, wine, company]</td>\n",
|
906 |
+
" <td>[farm, fresh, blueberry, moscato, ml]</td>\n",
|
907 |
+
" <td>[farm, fresh, blueberry, moscato, ml, alcohol,...</td>\n",
|
908 |
+
" </tr>\n",
|
909 |
+
" <tr>\n",
|
910 |
+
" <th>568530</th>\n",
|
911 |
+
" <td>Farm Fresh Peach Moscato 750 Ml</td>\n",
|
912 |
+
" <td>[alcohol]</td>\n",
|
913 |
+
" <td>[wine]</td>\n",
|
914 |
+
" <td>[alcoholwine]</td>\n",
|
915 |
+
" <td>[farm, fresh, wine, company]</td>\n",
|
916 |
+
" <td>[farm, fresh, peach, moscato, ml]</td>\n",
|
917 |
+
" <td>[farm, fresh, peach, moscato, ml, alcohol, win...</td>\n",
|
918 |
+
" </tr>\n",
|
919 |
+
" <tr>\n",
|
920 |
+
" <th>568531</th>\n",
|
921 |
+
" <td>Farm Fresh Raspberry Moscato 750ml</td>\n",
|
922 |
+
" <td>[alcohol]</td>\n",
|
923 |
+
" <td>[wine]</td>\n",
|
924 |
+
" <td>[alcoholwine]</td>\n",
|
925 |
+
" <td>[farm, fresh, wine, company]</td>\n",
|
926 |
+
" <td>[farm, fresh, raspberry, moscato, ml]</td>\n",
|
927 |
+
" <td>[farm, fresh, raspberry, moscato, ml, alcohol,...</td>\n",
|
928 |
+
" </tr>\n",
|
929 |
+
" <tr>\n",
|
930 |
+
" <th>568532</th>\n",
|
931 |
+
" <td>Farm Fresh Mango Moscato 750ml</td>\n",
|
932 |
+
" <td>[alcohol]</td>\n",
|
933 |
+
" <td>[wine]</td>\n",
|
934 |
+
" <td>[alcoholwine]</td>\n",
|
935 |
+
" <td>[farm, fresh, wine, company]</td>\n",
|
936 |
+
" <td>[farm, fresh, mango, moscato, ml]</td>\n",
|
937 |
+
" <td>[farm, fresh, mango, moscato, ml, alcohol, win...</td>\n",
|
938 |
+
" </tr>\n",
|
939 |
+
" <tr>\n",
|
940 |
+
" <th>568533</th>\n",
|
941 |
+
" <td>Ole Orleans Heritage Riesling 750ml</td>\n",
|
942 |
+
" <td>[alcohol]</td>\n",
|
943 |
+
" <td>[wine]</td>\n",
|
944 |
+
" <td>[alcoholwine]</td>\n",
|
945 |
+
" <td>[ole, orleans]</td>\n",
|
946 |
+
" <td>[ole, orleans, heritage, riesling, ml]</td>\n",
|
947 |
+
" <td>[ole, orleans, heritage, riesling, ml, alcohol...</td>\n",
|
948 |
+
" </tr>\n",
|
949 |
+
" </tbody>\n",
|
950 |
+
"</table>\n",
|
951 |
+
"<p>568507 rows × 7 columns</p>\n",
|
952 |
+
"</div>"
|
953 |
+
]
|
954 |
+
},
|
955 |
+
"execution_count": 11,
|
956 |
+
"metadata": {},
|
957 |
+
"output_type": "execute_result"
|
958 |
+
}
|
959 |
+
],
|
960 |
+
"execution_count": 11
|
961 |
+
},
|
962 |
+
{
|
963 |
+
"cell_type": "code",
|
964 |
+
"id": "3a28e095285cd9a",
|
965 |
+
"metadata": {
|
966 |
+
"ExecuteTime": {
|
967 |
+
"end_time": "2024-07-30T12:35:24.243648Z",
|
968 |
+
"start_time": "2024-07-30T12:35:24.213211Z"
|
969 |
+
}
|
970 |
+
},
|
971 |
+
"source": "new_df=df[['PRODUCT_NAME',\"tags\"]]",
|
972 |
+
"outputs": [],
|
973 |
+
"execution_count": 12
|
974 |
+
},
|
975 |
+
{
|
976 |
+
"cell_type": "code",
|
977 |
+
"id": "c672ae1826940651",
|
978 |
+
"metadata": {
|
979 |
+
"ExecuteTime": {
|
980 |
+
"end_time": "2024-07-30T12:35:24.258999Z",
|
981 |
+
"start_time": "2024-07-30T12:35:24.245254Z"
|
982 |
+
}
|
983 |
+
},
|
984 |
+
"source": [
|
985 |
+
"new_df"
|
986 |
+
],
|
987 |
+
"outputs": [
|
988 |
+
{
|
989 |
+
"data": {
|
990 |
+
"text/plain": [
|
991 |
+
" PRODUCT_NAME \\\n",
|
992 |
+
"0 Marketside Roasted Red Pepper Hummus, 10 Oz \n",
|
993 |
+
"1 Marketside Roasted Garlic Hummus, 10 Oz \n",
|
994 |
+
"2 Marketside Classic Hummus, 10 Oz \n",
|
995 |
+
"3 Marketside Everything Hummus, 10 oz \n",
|
996 |
+
"4 Price's Jalapeno Dip, 12 Oz. \n",
|
997 |
+
"... ... \n",
|
998 |
+
"568529 Farm Fresh Blueberry Moscato 750ml \n",
|
999 |
+
"568530 Farm Fresh Peach Moscato 750 Ml \n",
|
1000 |
+
"568531 Farm Fresh Raspberry Moscato 750ml \n",
|
1001 |
+
"568532 Farm Fresh Mango Moscato 750ml \n",
|
1002 |
+
"568533 Ole Orleans Heritage Riesling 750ml \n",
|
1003 |
+
"\n",
|
1004 |
+
" tags \n",
|
1005 |
+
"0 [marketside, roasted, red, pepper, hummus, oz,... \n",
|
1006 |
+
"1 [marketside, roasted, garlic, hummus, oz, deli... \n",
|
1007 |
+
"2 [marketside, classic, hummus, oz, deli, hummus... \n",
|
1008 |
+
"3 [marketside, everything, hummus, oz, deli, hum... \n",
|
1009 |
+
"4 [prices, jalapeno, dip, oz, deli, hummus, dips... \n",
|
1010 |
+
"... ... \n",
|
1011 |
+
"568529 [farm, fresh, blueberry, moscato, ml, alcohol,... \n",
|
1012 |
+
"568530 [farm, fresh, peach, moscato, ml, alcohol, win... \n",
|
1013 |
+
"568531 [farm, fresh, raspberry, moscato, ml, alcohol,... \n",
|
1014 |
+
"568532 [farm, fresh, mango, moscato, ml, alcohol, win... \n",
|
1015 |
+
"568533 [ole, orleans, heritage, riesling, ml, alcohol... \n",
|
1016 |
+
"\n",
|
1017 |
+
"[568507 rows x 2 columns]"
|
1018 |
+
],
|
1019 |
+
"text/html": [
|
1020 |
+
"<div>\n",
|
1021 |
+
"<style scoped>\n",
|
1022 |
+
" .dataframe tbody tr th:only-of-type {\n",
|
1023 |
+
" vertical-align: middle;\n",
|
1024 |
+
" }\n",
|
1025 |
+
"\n",
|
1026 |
+
" .dataframe tbody tr th {\n",
|
1027 |
+
" vertical-align: top;\n",
|
1028 |
+
" }\n",
|
1029 |
+
"\n",
|
1030 |
+
" .dataframe thead th {\n",
|
1031 |
+
" text-align: right;\n",
|
1032 |
+
" }\n",
|
1033 |
+
"</style>\n",
|
1034 |
+
"<table border=\"1\" class=\"dataframe\">\n",
|
1035 |
+
" <thead>\n",
|
1036 |
+
" <tr style=\"text-align: right;\">\n",
|
1037 |
+
" <th></th>\n",
|
1038 |
+
" <th>PRODUCT_NAME</th>\n",
|
1039 |
+
" <th>tags</th>\n",
|
1040 |
+
" </tr>\n",
|
1041 |
+
" </thead>\n",
|
1042 |
+
" <tbody>\n",
|
1043 |
+
" <tr>\n",
|
1044 |
+
" <th>0</th>\n",
|
1045 |
+
" <td>Marketside Roasted Red Pepper Hummus, 10 Oz</td>\n",
|
1046 |
+
" <td>[marketside, roasted, red, pepper, hummus, oz,...</td>\n",
|
1047 |
+
" </tr>\n",
|
1048 |
+
" <tr>\n",
|
1049 |
+
" <th>1</th>\n",
|
1050 |
+
" <td>Marketside Roasted Garlic Hummus, 10 Oz</td>\n",
|
1051 |
+
" <td>[marketside, roasted, garlic, hummus, oz, deli...</td>\n",
|
1052 |
+
" </tr>\n",
|
1053 |
+
" <tr>\n",
|
1054 |
+
" <th>2</th>\n",
|
1055 |
+
" <td>Marketside Classic Hummus, 10 Oz</td>\n",
|
1056 |
+
" <td>[marketside, classic, hummus, oz, deli, hummus...</td>\n",
|
1057 |
+
" </tr>\n",
|
1058 |
+
" <tr>\n",
|
1059 |
+
" <th>3</th>\n",
|
1060 |
+
" <td>Marketside Everything Hummus, 10 oz</td>\n",
|
1061 |
+
" <td>[marketside, everything, hummus, oz, deli, hum...</td>\n",
|
1062 |
+
" </tr>\n",
|
1063 |
+
" <tr>\n",
|
1064 |
+
" <th>4</th>\n",
|
1065 |
+
" <td>Price's Jalapeno Dip, 12 Oz.</td>\n",
|
1066 |
+
" <td>[prices, jalapeno, dip, oz, deli, hummus, dips...</td>\n",
|
1067 |
+
" </tr>\n",
|
1068 |
+
" <tr>\n",
|
1069 |
+
" <th>...</th>\n",
|
1070 |
+
" <td>...</td>\n",
|
1071 |
+
" <td>...</td>\n",
|
1072 |
+
" </tr>\n",
|
1073 |
+
" <tr>\n",
|
1074 |
+
" <th>568529</th>\n",
|
1075 |
+
" <td>Farm Fresh Blueberry Moscato 750ml</td>\n",
|
1076 |
+
" <td>[farm, fresh, blueberry, moscato, ml, alcohol,...</td>\n",
|
1077 |
+
" </tr>\n",
|
1078 |
+
" <tr>\n",
|
1079 |
+
" <th>568530</th>\n",
|
1080 |
+
" <td>Farm Fresh Peach Moscato 750 Ml</td>\n",
|
1081 |
+
" <td>[farm, fresh, peach, moscato, ml, alcohol, win...</td>\n",
|
1082 |
+
" </tr>\n",
|
1083 |
+
" <tr>\n",
|
1084 |
+
" <th>568531</th>\n",
|
1085 |
+
" <td>Farm Fresh Raspberry Moscato 750ml</td>\n",
|
1086 |
+
" <td>[farm, fresh, raspberry, moscato, ml, alcohol,...</td>\n",
|
1087 |
+
" </tr>\n",
|
1088 |
+
" <tr>\n",
|
1089 |
+
" <th>568532</th>\n",
|
1090 |
+
" <td>Farm Fresh Mango Moscato 750ml</td>\n",
|
1091 |
+
" <td>[farm, fresh, mango, moscato, ml, alcohol, win...</td>\n",
|
1092 |
+
" </tr>\n",
|
1093 |
+
" <tr>\n",
|
1094 |
+
" <th>568533</th>\n",
|
1095 |
+
" <td>Ole Orleans Heritage Riesling 750ml</td>\n",
|
1096 |
+
" <td>[ole, orleans, heritage, riesling, ml, alcohol...</td>\n",
|
1097 |
+
" </tr>\n",
|
1098 |
+
" </tbody>\n",
|
1099 |
+
"</table>\n",
|
1100 |
+
"<p>568507 rows × 2 columns</p>\n",
|
1101 |
+
"</div>"
|
1102 |
+
]
|
1103 |
+
},
|
1104 |
+
"execution_count": 13,
|
1105 |
+
"metadata": {},
|
1106 |
+
"output_type": "execute_result"
|
1107 |
+
}
|
1108 |
+
],
|
1109 |
+
"execution_count": 13
|
1110 |
+
},
|
1111 |
+
{
|
1112 |
+
"cell_type": "code",
|
1113 |
+
"id": "9f206d66e3a02e2d",
|
1114 |
+
"metadata": {
|
1115 |
+
"ExecuteTime": {
|
1116 |
+
"end_time": "2024-07-30T12:35:26.205605Z",
|
1117 |
+
"start_time": "2024-07-30T12:35:24.260533Z"
|
1118 |
+
}
|
1119 |
+
},
|
1120 |
+
"source": [
|
1121 |
+
"from sklearn.feature_extraction.text import CountVectorizer\n",
|
1122 |
+
"from nltk.stem.porter import PorterStemmer\n",
|
1123 |
+
"ps=PorterStemmer()\n",
|
1124 |
+
"cv=CountVectorizer(max_features=5000,stop_words='english')"
|
1125 |
+
],
|
1126 |
+
"outputs": [],
|
1127 |
+
"execution_count": 14
|
1128 |
+
},
|
1129 |
+
{
|
1130 |
+
"cell_type": "code",
|
1131 |
+
"id": "179547695cf71375",
|
1132 |
+
"metadata": {
|
1133 |
+
"ExecuteTime": {
|
1134 |
+
"end_time": "2024-07-30T12:35:26.221713Z",
|
1135 |
+
"start_time": "2024-07-30T12:35:26.206601Z"
|
1136 |
+
}
|
1137 |
+
},
|
1138 |
+
"source": [
|
1139 |
+
"def stem(text):\n",
|
1140 |
+
" y=[]\n",
|
1141 |
+
" for i in text:\n",
|
1142 |
+
" y.append(ps.stem(i))\n",
|
1143 |
+
" return \" \".join(y)"
|
1144 |
+
],
|
1145 |
+
"outputs": [],
|
1146 |
+
"execution_count": 15
|
1147 |
+
},
|
1148 |
+
{
|
1149 |
+
"cell_type": "code",
|
1150 |
+
"id": "40e19aacfa32d7f9",
|
1151 |
+
"metadata": {
|
1152 |
+
"ExecuteTime": {
|
1153 |
+
"end_time": "2024-07-30T12:37:14.151419Z",
|
1154 |
+
"start_time": "2024-07-30T12:35:26.222722Z"
|
1155 |
+
}
|
1156 |
+
},
|
1157 |
+
"source": [
|
1158 |
+
"new_df['tags']=new_df['tags'].apply(stem)\n"
|
1159 |
+
],
|
1160 |
+
"outputs": [
|
1161 |
+
{
|
1162 |
+
"name": "stderr",
|
1163 |
+
"output_type": "stream",
|
1164 |
+
"text": [
|
1165 |
+
"C:\\Users\\thaku\\AppData\\Local\\Temp\\ipykernel_13136\\1459480162.py:1: SettingWithCopyWarning: \n",
|
1166 |
+
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
|
1167 |
+
"Try using .loc[row_indexer,col_indexer] = value instead\n",
|
1168 |
+
"\n",
|
1169 |
+
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
|
1170 |
+
" new_df['tags']=new_df['tags'].apply(stem)\n"
|
1171 |
+
]
|
1172 |
+
}
|
1173 |
+
],
|
1174 |
+
"execution_count": 16
|
1175 |
+
},
|
1176 |
+
{
|
1177 |
+
"cell_type": "code",
|
1178 |
+
"id": "24975d8282c44c17",
|
1179 |
+
"metadata": {
|
1180 |
+
"ExecuteTime": {
|
1181 |
+
"end_time": "2024-07-30T12:37:21.969928Z",
|
1182 |
+
"start_time": "2024-07-30T12:37:14.153418Z"
|
1183 |
+
}
|
1184 |
+
},
|
1185 |
+
"source": [
|
1186 |
+
"vectors=cv.fit_transform(new_df['tags']).toarray()"
|
1187 |
+
],
|
1188 |
+
"outputs": [
|
1189 |
+
{
|
1190 |
+
"ename": "MemoryError",
|
1191 |
+
"evalue": "Unable to allocate 21.2 GiB for an array with shape (568507, 5000) and data type int64",
|
1192 |
+
"output_type": "error",
|
1193 |
+
"traceback": [
|
1194 |
+
"\u001B[1;31m---------------------------------------------------------------------------\u001B[0m",
|
1195 |
+
"\u001B[1;31mMemoryError\u001B[0m Traceback (most recent call last)",
|
1196 |
+
"Cell \u001B[1;32mIn[17], line 1\u001B[0m\n\u001B[1;32m----> 1\u001B[0m vectors\u001B[38;5;241m=\u001B[39m\u001B[43mcv\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mfit_transform\u001B[49m\u001B[43m(\u001B[49m\u001B[43mnew_df\u001B[49m\u001B[43m[\u001B[49m\u001B[38;5;124;43m'\u001B[39;49m\u001B[38;5;124;43mtags\u001B[39;49m\u001B[38;5;124;43m'\u001B[39;49m\u001B[43m]\u001B[49m\u001B[43m)\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mtoarray\u001B[49m\u001B[43m(\u001B[49m\u001B[43m)\u001B[49m\n",
|
1197 |
+
"File \u001B[1;32mD:\\pynb\\Walmart\\venv\\lib\\site-packages\\scipy\\sparse\\_compressed.py:1181\u001B[0m, in \u001B[0;36m_cs_matrix.toarray\u001B[1;34m(self, order, out)\u001B[0m\n\u001B[0;32m 1179\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m out \u001B[38;5;129;01mis\u001B[39;00m \u001B[38;5;28;01mNone\u001B[39;00m \u001B[38;5;129;01mand\u001B[39;00m order \u001B[38;5;129;01mis\u001B[39;00m \u001B[38;5;28;01mNone\u001B[39;00m:\n\u001B[0;32m 1180\u001B[0m order \u001B[38;5;241m=\u001B[39m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_swap(\u001B[38;5;124m'\u001B[39m\u001B[38;5;124mcf\u001B[39m\u001B[38;5;124m'\u001B[39m)[\u001B[38;5;241m0\u001B[39m]\n\u001B[1;32m-> 1181\u001B[0m out \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_process_toarray_args\u001B[49m\u001B[43m(\u001B[49m\u001B[43morder\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mout\u001B[49m\u001B[43m)\u001B[49m\n\u001B[0;32m 1182\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;129;01mnot\u001B[39;00m (out\u001B[38;5;241m.\u001B[39mflags\u001B[38;5;241m.\u001B[39mc_contiguous \u001B[38;5;129;01mor\u001B[39;00m out\u001B[38;5;241m.\u001B[39mflags\u001B[38;5;241m.\u001B[39mf_contiguous):\n\u001B[0;32m 1183\u001B[0m \u001B[38;5;28;01mraise\u001B[39;00m \u001B[38;5;167;01mValueError\u001B[39;00m(\u001B[38;5;124m'\u001B[39m\u001B[38;5;124mOutput array must be C or F contiguous\u001B[39m\u001B[38;5;124m'\u001B[39m)\n",
|
1198 |
+
"File \u001B[1;32mD:\\pynb\\Walmart\\venv\\lib\\site-packages\\scipy\\sparse\\_base.py:1301\u001B[0m, in \u001B[0;36m_spbase._process_toarray_args\u001B[1;34m(self, order, out)\u001B[0m\n\u001B[0;32m 1299\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m out\n\u001B[0;32m 1300\u001B[0m \u001B[38;5;28;01melse\u001B[39;00m:\n\u001B[1;32m-> 1301\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[43mnp\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mzeros\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mshape\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mdtype\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mdtype\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43morder\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43morder\u001B[49m\u001B[43m)\u001B[49m\n",
|
1199 |
+
"\u001B[1;31mMemoryError\u001B[0m: Unable to allocate 21.2 GiB for an array with shape (568507, 5000) and data type int64"
|
1200 |
+
]
|
1201 |
+
}
|
1202 |
+
],
|
1203 |
+
"execution_count": 17
|
1204 |
+
},
|
1205 |
+
{
|
1206 |
+
"cell_type": "code",
|
1207 |
+
"id": "84d50839b49ad1ce",
|
1208 |
+
"metadata": {
|
1209 |
+
"ExecuteTime": {
|
1210 |
+
"end_time": "2024-07-30T12:37:21.971885Z",
|
1211 |
+
"start_time": "2024-07-30T12:37:21.971885Z"
|
1212 |
+
}
|
1213 |
+
},
|
1214 |
+
"source": [
|
1215 |
+
"from sklearn.metrics.pairwise import cosine_similarity\n",
|
1216 |
+
"similarity=cosine_similarity(vectors)\n"
|
1217 |
+
],
|
1218 |
+
"outputs": [],
|
1219 |
+
"execution_count": null
|
1220 |
+
},
|
1221 |
+
{
|
1222 |
+
"cell_type": "code",
|
1223 |
+
"id": "9f8b1afa332ca4b7",
|
1224 |
+
"metadata": {},
|
1225 |
+
"source": [
|
1226 |
+
"def recommend(item):\n",
|
1227 |
+
" item_index=new_df[new_df['PRODUCT_NAME']==item].index[0]\n",
|
1228 |
+
" distance=similarity[item_index]\n",
|
1229 |
+
" items_list=sorted(list(enumerate(distance)),reverse=True,key=lambda x:x[1])[1:6]\n",
|
1230 |
+
" \n",
|
1231 |
+
" for i in items_list:\n",
|
1232 |
+
" print(new_df.iloc[i[0]]['PRODUCT_NAME'])\n",
|
1233 |
+
"\n",
|
1234 |
+
"def get_recommendations(user_description, count_vectorizer, count_matrix):\n",
|
1235 |
+
" # Preprocess the user-provided description\n",
|
1236 |
+
" user_description = preprocess_text(user_description)\n",
|
1237 |
+
" \n",
|
1238 |
+
" # Transform the user description into the same feature space\n",
|
1239 |
+
" user_vector = count_vectorizer.transform([user_description])\n",
|
1240 |
+
" \n",
|
1241 |
+
" # Compute cosine similarity between user description and item descriptions\n",
|
1242 |
+
" cosine_similarities = cosine_similarity(user_vector, count_matrix).flatten()\n",
|
1243 |
+
" \n",
|
1244 |
+
" # Get indices of the most similar items\n",
|
1245 |
+
" similar_indices = cosine_similarities.argsort()[::-1]\n",
|
1246 |
+
" \n",
|
1247 |
+
" return similar_indices\n"
|
1248 |
+
],
|
1249 |
+
"outputs": [],
|
1250 |
+
"execution_count": null
|
1251 |
+
},
|
1252 |
+
{
|
1253 |
+
"cell_type": "code",
|
1254 |
+
"id": "72c21ab855a6ba41",
|
1255 |
+
"metadata": {},
|
1256 |
+
"source": [
|
1257 |
+
"recommend(\"THE FIRST YEARS\")"
|
1258 |
+
],
|
1259 |
+
"outputs": [],
|
1260 |
+
"execution_count": null
|
1261 |
+
},
|
1262 |
+
{
|
1263 |
+
"cell_type": "code",
|
1264 |
+
"id": "206cf57c6ce8bbf9",
|
1265 |
+
"metadata": {},
|
1266 |
+
"source": [
|
1267 |
+
"new_df.iloc[get_recommendations('milk', cv, vectors)]"
|
1268 |
+
],
|
1269 |
+
"outputs": [],
|
1270 |
+
"execution_count": null
|
1271 |
+
},
|
1272 |
+
{
|
1273 |
+
"cell_type": "code",
|
1274 |
+
"id": "76143eea-ffb5-4d4c-a700-b0d98de0bb01",
|
1275 |
+
"metadata": {},
|
1276 |
+
"source": [
|
1277 |
+
"import pickle\n",
|
1278 |
+
"with open(\"cv.pkl\",\"wb\") as file:\n",
|
1279 |
+
" pickle.dump(cv,file)\n",
|
1280 |
+
"with open(\"vectors.pkl\",\"wb\")as file:\n",
|
1281 |
+
" pickle.dump(vectors,file)"
|
1282 |
+
],
|
1283 |
+
"outputs": [],
|
1284 |
+
"execution_count": null
|
1285 |
+
},
|
1286 |
+
{
|
1287 |
+
"cell_type": "code",
|
1288 |
+
"id": "c5ee2911-a4bc-4a39-bde9-a8ee8378cc88",
|
1289 |
+
"metadata": {},
|
1290 |
+
"source": [],
|
1291 |
+
"outputs": [],
|
1292 |
+
"execution_count": null
|
1293 |
+
}
|
1294 |
+
],
|
1295 |
+
"metadata": {
|
1296 |
+
"kernelspec": {
|
1297 |
+
"display_name": "Python 3 (ipykernel)",
|
1298 |
+
"language": "python",
|
1299 |
+
"name": "python3"
|
1300 |
+
},
|
1301 |
+
"language_info": {
|
1302 |
+
"codemirror_mode": {
|
1303 |
+
"name": "ipython",
|
1304 |
+
"version": 3
|
1305 |
+
},
|
1306 |
+
"file_extension": ".py",
|
1307 |
+
"mimetype": "text/x-python",
|
1308 |
+
"name": "python",
|
1309 |
+
"nbconvert_exporter": "python",
|
1310 |
+
"pygments_lexer": "ipython3",
|
1311 |
+
"version": "3.8.19"
|
1312 |
+
}
|
1313 |
+
},
|
1314 |
+
"nbformat": 4,
|
1315 |
+
"nbformat_minor": 5
|
1316 |
+
}
|