Ubuntu
commited on
Commit
•
7bd8341
1
Parent(s):
fca1cc4
created the dataset for categorical classification
Browse files
data_categories/Final_Category_Data_With_Labels.csv
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c2ba96d90a437a017a25af64364a58c7e2954ca1519a5fce27d0e55addae8da
|
3 |
+
size 1810529
|
research/08_organizing_the_entire_datacategories.ipynb
ADDED
@@ -0,0 +1,919 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cells": [
|
3 |
+
{
|
4 |
+
"cell_type": "code",
|
5 |
+
"execution_count": 1,
|
6 |
+
"metadata": {},
|
7 |
+
"outputs": [],
|
8 |
+
"source": [
|
9 |
+
"import os; os.chdir('..');"
|
10 |
+
]
|
11 |
+
},
|
12 |
+
{
|
13 |
+
"cell_type": "code",
|
14 |
+
"execution_count": 2,
|
15 |
+
"metadata": {},
|
16 |
+
"outputs": [],
|
17 |
+
"source": [
|
18 |
+
"import json"
|
19 |
+
]
|
20 |
+
},
|
21 |
+
{
|
22 |
+
"cell_type": "code",
|
23 |
+
"execution_count": 3,
|
24 |
+
"metadata": {},
|
25 |
+
"outputs": [
|
26 |
+
{
|
27 |
+
"data": {
|
28 |
+
"text/plain": [
|
29 |
+
"{'Beauty_and_Fitness': 0,\n",
|
30 |
+
" 'People_and_Society': 1,\n",
|
31 |
+
" 'Travel_and_Transportation': 2,\n",
|
32 |
+
" 'Shopping': 3,\n",
|
33 |
+
" 'Adult': 4,\n",
|
34 |
+
" 'Sports': 5,\n",
|
35 |
+
" 'Science': 6,\n",
|
36 |
+
" 'Food_and_Drink': 7,\n",
|
37 |
+
" 'News': 8,\n",
|
38 |
+
" 'Sensitive Subjects': 9,\n",
|
39 |
+
" 'Autos_and_Vehicles': 10,\n",
|
40 |
+
" 'Law_and_Government': 11,\n",
|
41 |
+
" 'Business_and_Industrial': 12,\n",
|
42 |
+
" 'Health': 13,\n",
|
43 |
+
" 'Real Estate': 14,\n",
|
44 |
+
" 'Books_and_Literature': 15,\n",
|
45 |
+
" 'Computers_and_Electronics': 16,\n",
|
46 |
+
" 'Internet_and_Telecom': 17,\n",
|
47 |
+
" 'Home_and_Garden': 18,\n",
|
48 |
+
" 'Jobs_and_Education': 19,\n",
|
49 |
+
" 'Online Communities': 20,\n",
|
50 |
+
" 'Finance': 21,\n",
|
51 |
+
" 'Arts_and_Entertainment': 22,\n",
|
52 |
+
" 'Games': 23,\n",
|
53 |
+
" 'Hobbies_and_Leisure': 24,\n",
|
54 |
+
" 'Reference': 25,\n",
|
55 |
+
" 'Pets_and_Animals': 26}"
|
56 |
+
]
|
57 |
+
},
|
58 |
+
"execution_count": 3,
|
59 |
+
"metadata": {},
|
60 |
+
"output_type": "execute_result"
|
61 |
+
}
|
62 |
+
],
|
63 |
+
"source": [
|
64 |
+
"data_cat_dict= json.load(\n",
|
65 |
+
" open('data/categories_refined.json', 'r')\n",
|
66 |
+
")\n",
|
67 |
+
"data_cat_dict"
|
68 |
+
]
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"cell_type": "code",
|
72 |
+
"execution_count": 5,
|
73 |
+
"metadata": {},
|
74 |
+
"outputs": [
|
75 |
+
{
|
76 |
+
"data": {
|
77 |
+
"text/plain": [
|
78 |
+
"{0: 'Beauty_and_Fitness',\n",
|
79 |
+
" 1: 'People_and_Society',\n",
|
80 |
+
" 2: 'Travel_and_Transportation',\n",
|
81 |
+
" 3: 'Shopping',\n",
|
82 |
+
" 4: 'Adult',\n",
|
83 |
+
" 5: 'Sports',\n",
|
84 |
+
" 6: 'Science',\n",
|
85 |
+
" 7: 'Food_and_Drink',\n",
|
86 |
+
" 8: 'News',\n",
|
87 |
+
" 9: 'Sensitive Subjects',\n",
|
88 |
+
" 10: 'Autos_and_Vehicles',\n",
|
89 |
+
" 11: 'Law_and_Government',\n",
|
90 |
+
" 12: 'Business_and_Industrial',\n",
|
91 |
+
" 13: 'Health',\n",
|
92 |
+
" 14: 'Real Estate',\n",
|
93 |
+
" 15: 'Books_and_Literature',\n",
|
94 |
+
" 16: 'Computers_and_Electronics',\n",
|
95 |
+
" 17: 'Internet_and_Telecom',\n",
|
96 |
+
" 18: 'Home_and_Garden',\n",
|
97 |
+
" 19: 'Jobs_and_Education',\n",
|
98 |
+
" 20: 'Online Communities',\n",
|
99 |
+
" 21: 'Finance',\n",
|
100 |
+
" 22: 'Arts_and_Entertainment',\n",
|
101 |
+
" 23: 'Games',\n",
|
102 |
+
" 24: 'Hobbies_and_Leisure',\n",
|
103 |
+
" 25: 'Reference',\n",
|
104 |
+
" 26: 'Pets_and_Animals'}"
|
105 |
+
]
|
106 |
+
},
|
107 |
+
"execution_count": 5,
|
108 |
+
"metadata": {},
|
109 |
+
"output_type": "execute_result"
|
110 |
+
}
|
111 |
+
],
|
112 |
+
"source": [
|
113 |
+
"data_cat_dict_rev= {}\n",
|
114 |
+
"for key in data_cat_dict.keys():\n",
|
115 |
+
" data_cat_dict_rev[data_cat_dict[key]] = key\n",
|
116 |
+
" \n",
|
117 |
+
"data_cat_dict_rev"
|
118 |
+
]
|
119 |
+
},
|
120 |
+
{
|
121 |
+
"cell_type": "code",
|
122 |
+
"execution_count": 8,
|
123 |
+
"metadata": {},
|
124 |
+
"outputs": [
|
125 |
+
{
|
126 |
+
"name": "stdout",
|
127 |
+
"output_type": "stream",
|
128 |
+
"text": [
|
129 |
+
"data_categories/Beauty_and_Fitness.csv: True\n",
|
130 |
+
"data_categories/People_and_Society.csv: True\n",
|
131 |
+
"data_categories/Travel_and_Transportation.csv: True\n",
|
132 |
+
"data_categories/Shopping.csv: True\n",
|
133 |
+
"data_categories/Adult.csv: True\n",
|
134 |
+
"data_categories/Sports.csv: True\n",
|
135 |
+
"data_categories/Science.csv: True\n",
|
136 |
+
"data_categories/Food_and_Drink.csv: True\n",
|
137 |
+
"data_categories/News.csv: True\n",
|
138 |
+
"data_categories/Sensitive Subjects.csv: True\n",
|
139 |
+
"data_categories/Autos_and_Vehicles.csv: True\n",
|
140 |
+
"data_categories/Law_and_Government.csv: True\n",
|
141 |
+
"data_categories/Business_and_Industrial.csv: True\n",
|
142 |
+
"data_categories/Health.csv: True\n",
|
143 |
+
"data_categories/Real Estate.csv: True\n",
|
144 |
+
"data_categories/Books_and_Literature.csv: True\n",
|
145 |
+
"data_categories/Computers_and_Electronics.csv: True\n",
|
146 |
+
"data_categories/Internet_and_Telecom.csv: True\n",
|
147 |
+
"data_categories/Home_and_Garden.csv: True\n",
|
148 |
+
"data_categories/Jobs_and_Education.csv: True\n",
|
149 |
+
"data_categories/Online Communities.csv: True\n",
|
150 |
+
"data_categories/Finance.csv: True\n",
|
151 |
+
"data_categories/Arts_and_Entertainment.csv: True\n",
|
152 |
+
"data_categories/Games.csv: True\n",
|
153 |
+
"data_categories/Hobbies_and_Leisure.csv: True\n",
|
154 |
+
"data_categories/Reference.csv: True\n",
|
155 |
+
"data_categories/Pets_and_Animals.csv: True\n"
|
156 |
+
]
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"data": {
|
160 |
+
"text/plain": [
|
161 |
+
"27"
|
162 |
+
]
|
163 |
+
},
|
164 |
+
"execution_count": 8,
|
165 |
+
"metadata": {},
|
166 |
+
"output_type": "execute_result"
|
167 |
+
}
|
168 |
+
],
|
169 |
+
"source": [
|
170 |
+
"path_list= []\n",
|
171 |
+
"for i in data_cat_dict.keys():\n",
|
172 |
+
" path= os.path.join(\"data_categories\", f'{i}.csv')\n",
|
173 |
+
" print(f\"{path}: {os.path.exists(path)}\")\n",
|
174 |
+
" path_list.append(path)\n",
|
175 |
+
" \n",
|
176 |
+
"len(path_list)"
|
177 |
+
]
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"cell_type": "code",
|
181 |
+
"execution_count": 9,
|
182 |
+
"metadata": {},
|
183 |
+
"outputs": [],
|
184 |
+
"source": [
|
185 |
+
"import pandas as pd"
|
186 |
+
]
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"cell_type": "code",
|
190 |
+
"execution_count": 24,
|
191 |
+
"metadata": {},
|
192 |
+
"outputs": [
|
193 |
+
{
|
194 |
+
"data": {
|
195 |
+
"text/html": [
|
196 |
+
"<div>\n",
|
197 |
+
"<style scoped>\n",
|
198 |
+
" .dataframe tbody tr th:only-of-type {\n",
|
199 |
+
" vertical-align: middle;\n",
|
200 |
+
" }\n",
|
201 |
+
"\n",
|
202 |
+
" .dataframe tbody tr th {\n",
|
203 |
+
" vertical-align: top;\n",
|
204 |
+
" }\n",
|
205 |
+
"\n",
|
206 |
+
" .dataframe thead th {\n",
|
207 |
+
" text-align: right;\n",
|
208 |
+
" }\n",
|
209 |
+
"</style>\n",
|
210 |
+
"<table border=\"1\" class=\"dataframe\">\n",
|
211 |
+
" <thead>\n",
|
212 |
+
" <tr style=\"text-align: right;\">\n",
|
213 |
+
" <th></th>\n",
|
214 |
+
" <th>category</th>\n",
|
215 |
+
" <th>label</th>\n",
|
216 |
+
" <th>label_id</th>\n",
|
217 |
+
" </tr>\n",
|
218 |
+
" </thead>\n",
|
219 |
+
" <tbody>\n",
|
220 |
+
" <tr>\n",
|
221 |
+
" <th>0</th>\n",
|
222 |
+
" <td>Makeup tutorials</td>\n",
|
223 |
+
" <td>Beauty_and_Fitness</td>\n",
|
224 |
+
" <td>0</td>\n",
|
225 |
+
" </tr>\n",
|
226 |
+
" <tr>\n",
|
227 |
+
" <th>1</th>\n",
|
228 |
+
" <td>Skin care routines</td>\n",
|
229 |
+
" <td>Beauty_and_Fitness</td>\n",
|
230 |
+
" <td>0</td>\n",
|
231 |
+
" </tr>\n",
|
232 |
+
" <tr>\n",
|
233 |
+
" <th>2</th>\n",
|
234 |
+
" <td>Hairstyling tips</td>\n",
|
235 |
+
" <td>Beauty_and_Fitness</td>\n",
|
236 |
+
" <td>0</td>\n",
|
237 |
+
" </tr>\n",
|
238 |
+
" <tr>\n",
|
239 |
+
" <th>3</th>\n",
|
240 |
+
" <td>Weight loss programs</td>\n",
|
241 |
+
" <td>Beauty_and_Fitness</td>\n",
|
242 |
+
" <td>0</td>\n",
|
243 |
+
" </tr>\n",
|
244 |
+
" <tr>\n",
|
245 |
+
" <th>4</th>\n",
|
246 |
+
" <td>Yoga for beginners</td>\n",
|
247 |
+
" <td>Beauty_and_Fitness</td>\n",
|
248 |
+
" <td>0</td>\n",
|
249 |
+
" </tr>\n",
|
250 |
+
" </tbody>\n",
|
251 |
+
"</table>\n",
|
252 |
+
"</div>"
|
253 |
+
],
|
254 |
+
"text/plain": [
|
255 |
+
" category label label_id\n",
|
256 |
+
"0 Makeup tutorials Beauty_and_Fitness 0\n",
|
257 |
+
"1 Skin care routines Beauty_and_Fitness 0\n",
|
258 |
+
"2 Hairstyling tips Beauty_and_Fitness 0\n",
|
259 |
+
"3 Weight loss programs Beauty_and_Fitness 0\n",
|
260 |
+
"4 Yoga for beginners Beauty_and_Fitness 0"
|
261 |
+
]
|
262 |
+
},
|
263 |
+
"execution_count": 24,
|
264 |
+
"metadata": {},
|
265 |
+
"output_type": "execute_result"
|
266 |
+
}
|
267 |
+
],
|
268 |
+
"source": [
|
269 |
+
"df= pd.read_csv(path_list[0])\n",
|
270 |
+
"df['label']= data_cat_dict_rev[0]\n",
|
271 |
+
"df['label_id']= data_cat_dict[data_cat_dict_rev[0]]\n",
|
272 |
+
"df.head()"
|
273 |
+
]
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"cell_type": "code",
|
277 |
+
"execution_count": 25,
|
278 |
+
"metadata": {},
|
279 |
+
"outputs": [
|
280 |
+
{
|
281 |
+
"data": {
|
282 |
+
"text/html": [
|
283 |
+
"<div>\n",
|
284 |
+
"<style scoped>\n",
|
285 |
+
" .dataframe tbody tr th:only-of-type {\n",
|
286 |
+
" vertical-align: middle;\n",
|
287 |
+
" }\n",
|
288 |
+
"\n",
|
289 |
+
" .dataframe tbody tr th {\n",
|
290 |
+
" vertical-align: top;\n",
|
291 |
+
" }\n",
|
292 |
+
"\n",
|
293 |
+
" .dataframe thead th {\n",
|
294 |
+
" text-align: right;\n",
|
295 |
+
" }\n",
|
296 |
+
"</style>\n",
|
297 |
+
"<table border=\"1\" class=\"dataframe\">\n",
|
298 |
+
" <thead>\n",
|
299 |
+
" <tr style=\"text-align: right;\">\n",
|
300 |
+
" <th></th>\n",
|
301 |
+
" <th>category</th>\n",
|
302 |
+
" <th>label</th>\n",
|
303 |
+
" <th>label_id</th>\n",
|
304 |
+
" </tr>\n",
|
305 |
+
" </thead>\n",
|
306 |
+
" <tbody>\n",
|
307 |
+
" <tr>\n",
|
308 |
+
" <th>0</th>\n",
|
309 |
+
" <td>Makeup tutorials</td>\n",
|
310 |
+
" <td>Beauty_and_Fitness</td>\n",
|
311 |
+
" <td>0</td>\n",
|
312 |
+
" </tr>\n",
|
313 |
+
" <tr>\n",
|
314 |
+
" <th>1</th>\n",
|
315 |
+
" <td>Skin care routines</td>\n",
|
316 |
+
" <td>Beauty_and_Fitness</td>\n",
|
317 |
+
" <td>0</td>\n",
|
318 |
+
" </tr>\n",
|
319 |
+
" <tr>\n",
|
320 |
+
" <th>2</th>\n",
|
321 |
+
" <td>Hairstyling tips</td>\n",
|
322 |
+
" <td>Beauty_and_Fitness</td>\n",
|
323 |
+
" <td>0</td>\n",
|
324 |
+
" </tr>\n",
|
325 |
+
" <tr>\n",
|
326 |
+
" <th>3</th>\n",
|
327 |
+
" <td>Weight loss programs</td>\n",
|
328 |
+
" <td>Beauty_and_Fitness</td>\n",
|
329 |
+
" <td>0</td>\n",
|
330 |
+
" </tr>\n",
|
331 |
+
" <tr>\n",
|
332 |
+
" <th>4</th>\n",
|
333 |
+
" <td>Yoga for beginners</td>\n",
|
334 |
+
" <td>Beauty_and_Fitness</td>\n",
|
335 |
+
" <td>0</td>\n",
|
336 |
+
" </tr>\n",
|
337 |
+
" </tbody>\n",
|
338 |
+
"</table>\n",
|
339 |
+
"</div>"
|
340 |
+
],
|
341 |
+
"text/plain": [
|
342 |
+
" category label label_id\n",
|
343 |
+
"0 Makeup tutorials Beauty_and_Fitness 0\n",
|
344 |
+
"1 Skin care routines Beauty_and_Fitness 0\n",
|
345 |
+
"2 Hairstyling tips Beauty_and_Fitness 0\n",
|
346 |
+
"3 Weight loss programs Beauty_and_Fitness 0\n",
|
347 |
+
"4 Yoga for beginners Beauty_and_Fitness 0"
|
348 |
+
]
|
349 |
+
},
|
350 |
+
"execution_count": 25,
|
351 |
+
"metadata": {},
|
352 |
+
"output_type": "execute_result"
|
353 |
+
}
|
354 |
+
],
|
355 |
+
"source": [
|
356 |
+
"concat_df= df.copy()\n",
|
357 |
+
"concat_df.head()"
|
358 |
+
]
|
359 |
+
},
|
360 |
+
{
|
361 |
+
"cell_type": "code",
|
362 |
+
"execution_count": 26,
|
363 |
+
"metadata": {},
|
364 |
+
"outputs": [
|
365 |
+
{
|
366 |
+
"name": "stdout",
|
367 |
+
"output_type": "stream",
|
368 |
+
"text": [
|
369 |
+
"data_categories/People_and_Society.csv\n",
|
370 |
+
"data_categories/Travel_and_Transportation.csv\n",
|
371 |
+
"data_categories/Shopping.csv\n",
|
372 |
+
"data_categories/Adult.csv\n",
|
373 |
+
"data_categories/Sports.csv\n",
|
374 |
+
"data_categories/Science.csv\n",
|
375 |
+
"data_categories/Food_and_Drink.csv\n",
|
376 |
+
"data_categories/News.csv\n",
|
377 |
+
"data_categories/Sensitive Subjects.csv\n",
|
378 |
+
"data_categories/Autos_and_Vehicles.csv\n",
|
379 |
+
"data_categories/Law_and_Government.csv\n",
|
380 |
+
"data_categories/Business_and_Industrial.csv\n",
|
381 |
+
"data_categories/Health.csv\n",
|
382 |
+
"data_categories/Real Estate.csv\n",
|
383 |
+
"data_categories/Books_and_Literature.csv\n",
|
384 |
+
"data_categories/Computers_and_Electronics.csv\n",
|
385 |
+
"data_categories/Internet_and_Telecom.csv\n",
|
386 |
+
"data_categories/Home_and_Garden.csv\n",
|
387 |
+
"data_categories/Jobs_and_Education.csv\n",
|
388 |
+
"data_categories/Online Communities.csv\n",
|
389 |
+
"data_categories/Finance.csv\n",
|
390 |
+
"data_categories/Arts_and_Entertainment.csv\n",
|
391 |
+
"data_categories/Games.csv\n",
|
392 |
+
"data_categories/Hobbies_and_Leisure.csv\n",
|
393 |
+
"data_categories/Reference.csv\n",
|
394 |
+
"data_categories/Pets_and_Animals.csv\n"
|
395 |
+
]
|
396 |
+
}
|
397 |
+
],
|
398 |
+
"source": [
|
399 |
+
"for i in range(1, 27):\n",
|
400 |
+
" print(path_list[i])\n",
|
401 |
+
" df_i= pd.read_csv(path_list[i])\n",
|
402 |
+
" df_i['label']= data_cat_dict_rev[i]\n",
|
403 |
+
" df_i['label_id']= data_cat_dict[data_cat_dict_rev[i]]\n",
|
404 |
+
" concat_df= pd.concat([concat_df, df_i])\n",
|
405 |
+
" "
|
406 |
+
]
|
407 |
+
},
|
408 |
+
{
|
409 |
+
"cell_type": "code",
|
410 |
+
"execution_count": 27,
|
411 |
+
"metadata": {},
|
412 |
+
"outputs": [
|
413 |
+
{
|
414 |
+
"data": {
|
415 |
+
"text/html": [
|
416 |
+
"<div>\n",
|
417 |
+
"<style scoped>\n",
|
418 |
+
" .dataframe tbody tr th:only-of-type {\n",
|
419 |
+
" vertical-align: middle;\n",
|
420 |
+
" }\n",
|
421 |
+
"\n",
|
422 |
+
" .dataframe tbody tr th {\n",
|
423 |
+
" vertical-align: top;\n",
|
424 |
+
" }\n",
|
425 |
+
"\n",
|
426 |
+
" .dataframe thead th {\n",
|
427 |
+
" text-align: right;\n",
|
428 |
+
" }\n",
|
429 |
+
"</style>\n",
|
430 |
+
"<table border=\"1\" class=\"dataframe\">\n",
|
431 |
+
" <thead>\n",
|
432 |
+
" <tr style=\"text-align: right;\">\n",
|
433 |
+
" <th></th>\n",
|
434 |
+
" <th>category</th>\n",
|
435 |
+
" <th>label</th>\n",
|
436 |
+
" <th>label_id</th>\n",
|
437 |
+
" </tr>\n",
|
438 |
+
" </thead>\n",
|
439 |
+
" <tbody>\n",
|
440 |
+
" <tr>\n",
|
441 |
+
" <th>333</th>\n",
|
442 |
+
" <td>collection</td>\n",
|
443 |
+
" <td>Adult</td>\n",
|
444 |
+
" <td>4</td>\n",
|
445 |
+
" </tr>\n",
|
446 |
+
" <tr>\n",
|
447 |
+
" <th>1463</th>\n",
|
448 |
+
" <td>Budget-friendly home decor and decoration</td>\n",
|
449 |
+
" <td>Shopping</td>\n",
|
450 |
+
" <td>3</td>\n",
|
451 |
+
" </tr>\n",
|
452 |
+
" <tr>\n",
|
453 |
+
" <th>556</th>\n",
|
454 |
+
" <td>Hair coloring ideas</td>\n",
|
455 |
+
" <td>Beauty_and_Fitness</td>\n",
|
456 |
+
" <td>0</td>\n",
|
457 |
+
" </tr>\n",
|
458 |
+
" <tr>\n",
|
459 |
+
" <th>723</th>\n",
|
460 |
+
" <td>Makeup for dry skin</td>\n",
|
461 |
+
" <td>Beauty_and_Fitness</td>\n",
|
462 |
+
" <td>0</td>\n",
|
463 |
+
" </tr>\n",
|
464 |
+
" <tr>\n",
|
465 |
+
" <th>417</th>\n",
|
466 |
+
" <td>Sports Team Fan Enthusiasm</td>\n",
|
467 |
+
" <td>Sports</td>\n",
|
468 |
+
" <td>5</td>\n",
|
469 |
+
" </tr>\n",
|
470 |
+
" <tr>\n",
|
471 |
+
" <th>1351</th>\n",
|
472 |
+
" <td>Telecommunication industry innovation in healt...</td>\n",
|
473 |
+
" <td>Internet_and_Telecom</td>\n",
|
474 |
+
" <td>17</td>\n",
|
475 |
+
" </tr>\n",
|
476 |
+
" <tr>\n",
|
477 |
+
" <th>284</th>\n",
|
478 |
+
" <td>XXX gay movies</td>\n",
|
479 |
+
" <td>Adult</td>\n",
|
480 |
+
" <td>4</td>\n",
|
481 |
+
" </tr>\n",
|
482 |
+
" <tr>\n",
|
483 |
+
" <th>1150</th>\n",
|
484 |
+
" <td>Bohemian outdoor garden party decor DIY projec...</td>\n",
|
485 |
+
" <td>Home_and_Garden</td>\n",
|
486 |
+
" <td>18</td>\n",
|
487 |
+
" </tr>\n",
|
488 |
+
" <tr>\n",
|
489 |
+
" <th>115</th>\n",
|
490 |
+
" <td>Travel destination skiing</td>\n",
|
491 |
+
" <td>Travel_and_Transportation</td>\n",
|
492 |
+
" <td>2</td>\n",
|
493 |
+
" </tr>\n",
|
494 |
+
" <tr>\n",
|
495 |
+
" <th>411</th>\n",
|
496 |
+
" <td>Citation context accuracy measurement platforms</td>\n",
|
497 |
+
" <td>Reference</td>\n",
|
498 |
+
" <td>25</td>\n",
|
499 |
+
" </tr>\n",
|
500 |
+
" <tr>\n",
|
501 |
+
" <th>285</th>\n",
|
502 |
+
" <td>Art techniques and creative process discussions</td>\n",
|
503 |
+
" <td>Online Communities</td>\n",
|
504 |
+
" <td>20</td>\n",
|
505 |
+
" </tr>\n",
|
506 |
+
" <tr>\n",
|
507 |
+
" <th>1251</th>\n",
|
508 |
+
" <td>Food plating techniques for fine dining</td>\n",
|
509 |
+
" <td>Food_and_Drink</td>\n",
|
510 |
+
" <td>7</td>\n",
|
511 |
+
" </tr>\n",
|
512 |
+
" <tr>\n",
|
513 |
+
" <th>225</th>\n",
|
514 |
+
" <td>Job search for seniors</td>\n",
|
515 |
+
" <td>Jobs_and_Education</td>\n",
|
516 |
+
" <td>19</td>\n",
|
517 |
+
" </tr>\n",
|
518 |
+
" <tr>\n",
|
519 |
+
" <th>979</th>\n",
|
520 |
+
" <td>Beard care for beard grooming</td>\n",
|
521 |
+
" <td>Hobbies_and_Leisure</td>\n",
|
522 |
+
" <td>24</td>\n",
|
523 |
+
" </tr>\n",
|
524 |
+
" <tr>\n",
|
525 |
+
" <th>345</th>\n",
|
526 |
+
" <td>Travel destination local hospitality</td>\n",
|
527 |
+
" <td>Travel_and_Transportation</td>\n",
|
528 |
+
" <td>2</td>\n",
|
529 |
+
" </tr>\n",
|
530 |
+
" <tr>\n",
|
531 |
+
" <th>29</th>\n",
|
532 |
+
" <td>External hard drive</td>\n",
|
533 |
+
" <td>Computers_and_Electronics</td>\n",
|
534 |
+
" <td>16</td>\n",
|
535 |
+
" </tr>\n",
|
536 |
+
" <tr>\n",
|
537 |
+
" <th>556</th>\n",
|
538 |
+
" <td>Real estate contract law</td>\n",
|
539 |
+
" <td>Real Estate</td>\n",
|
540 |
+
" <td>14</td>\n",
|
541 |
+
" </tr>\n",
|
542 |
+
" <tr>\n",
|
543 |
+
" <th>812</th>\n",
|
544 |
+
" <td>Classic literature for historical research and...</td>\n",
|
545 |
+
" <td>Books_and_Literature</td>\n",
|
546 |
+
" <td>15</td>\n",
|
547 |
+
" </tr>\n",
|
548 |
+
" <tr>\n",
|
549 |
+
" <th>489</th>\n",
|
550 |
+
" <td>Theater posters for sale</td>\n",
|
551 |
+
" <td>Arts_and_Entertainment</td>\n",
|
552 |
+
" <td>22</td>\n",
|
553 |
+
" </tr>\n",
|
554 |
+
" <tr>\n",
|
555 |
+
" <th>873</th>\n",
|
556 |
+
" <td>LinkedIn job search for freelancers</td>\n",
|
557 |
+
" <td>Jobs_and_Education</td>\n",
|
558 |
+
" <td>19</td>\n",
|
559 |
+
" </tr>\n",
|
560 |
+
" </tbody>\n",
|
561 |
+
"</table>\n",
|
562 |
+
"</div>"
|
563 |
+
],
|
564 |
+
"text/plain": [
|
565 |
+
" category \\\n",
|
566 |
+
"333 collection \n",
|
567 |
+
"1463 Budget-friendly home decor and decoration \n",
|
568 |
+
"556 Hair coloring ideas \n",
|
569 |
+
"723 Makeup for dry skin \n",
|
570 |
+
"417 Sports Team Fan Enthusiasm \n",
|
571 |
+
"1351 Telecommunication industry innovation in healt... \n",
|
572 |
+
"284 XXX gay movies \n",
|
573 |
+
"1150 Bohemian outdoor garden party decor DIY projec... \n",
|
574 |
+
"115 Travel destination skiing \n",
|
575 |
+
"411 Citation context accuracy measurement platforms \n",
|
576 |
+
"285 Art techniques and creative process discussions \n",
|
577 |
+
"1251 Food plating techniques for fine dining \n",
|
578 |
+
"225 Job search for seniors \n",
|
579 |
+
"979 Beard care for beard grooming \n",
|
580 |
+
"345 Travel destination local hospitality \n",
|
581 |
+
"29 External hard drive \n",
|
582 |
+
"556 Real estate contract law \n",
|
583 |
+
"812 Classic literature for historical research and... \n",
|
584 |
+
"489 Theater posters for sale \n",
|
585 |
+
"873 LinkedIn job search for freelancers \n",
|
586 |
+
"\n",
|
587 |
+
" label label_id \n",
|
588 |
+
"333 Adult 4 \n",
|
589 |
+
"1463 Shopping 3 \n",
|
590 |
+
"556 Beauty_and_Fitness 0 \n",
|
591 |
+
"723 Beauty_and_Fitness 0 \n",
|
592 |
+
"417 Sports 5 \n",
|
593 |
+
"1351 Internet_and_Telecom 17 \n",
|
594 |
+
"284 Adult 4 \n",
|
595 |
+
"1150 Home_and_Garden 18 \n",
|
596 |
+
"115 Travel_and_Transportation 2 \n",
|
597 |
+
"411 Reference 25 \n",
|
598 |
+
"285 Online Communities 20 \n",
|
599 |
+
"1251 Food_and_Drink 7 \n",
|
600 |
+
"225 Jobs_and_Education 19 \n",
|
601 |
+
"979 Hobbies_and_Leisure 24 \n",
|
602 |
+
"345 Travel_and_Transportation 2 \n",
|
603 |
+
"29 Computers_and_Electronics 16 \n",
|
604 |
+
"556 Real Estate 14 \n",
|
605 |
+
"812 Books_and_Literature 15 \n",
|
606 |
+
"489 Arts_and_Entertainment 22 \n",
|
607 |
+
"873 Jobs_and_Education 19 "
|
608 |
+
]
|
609 |
+
},
|
610 |
+
"execution_count": 27,
|
611 |
+
"metadata": {},
|
612 |
+
"output_type": "execute_result"
|
613 |
+
}
|
614 |
+
],
|
615 |
+
"source": [
|
616 |
+
"concat_df.sample(20)"
|
617 |
+
]
|
618 |
+
},
|
619 |
+
{
|
620 |
+
"cell_type": "code",
|
621 |
+
"execution_count": 28,
|
622 |
+
"metadata": {},
|
623 |
+
"outputs": [
|
624 |
+
{
|
625 |
+
"data": {
|
626 |
+
"text/plain": [
|
627 |
+
"label\n",
|
628 |
+
"Shopping 1505\n",
|
629 |
+
"Food_and_Drink 1500\n",
|
630 |
+
"Sports 1399\n",
|
631 |
+
"Travel_and_Transportation 1355\n",
|
632 |
+
"Internet_and_Telecom 1353\n",
|
633 |
+
"Reference 1315\n",
|
634 |
+
"Beauty_and_Fitness 1259\n",
|
635 |
+
"People_and_Society 1250\n",
|
636 |
+
"Pets_and_Animals 1228\n",
|
637 |
+
"Law_and_Government 1226\n",
|
638 |
+
"Home_and_Garden 1200\n",
|
639 |
+
"News 1199\n",
|
640 |
+
"Jobs_and_Education 1188\n",
|
641 |
+
"Arts_and_Entertainment 1162\n",
|
642 |
+
"Business_and_Industrial 1124\n",
|
643 |
+
"Adult 1100\n",
|
644 |
+
"Health 1098\n",
|
645 |
+
"Autos_and_Vehicles 1072\n",
|
646 |
+
"Science 1055\n",
|
647 |
+
"Hobbies_and_Leisure 1049\n",
|
648 |
+
"Computers_and_Electronics 1000\n",
|
649 |
+
"Online Communities 1000\n",
|
650 |
+
"Finance 1000\n",
|
651 |
+
"Books_and_Literature 1000\n",
|
652 |
+
"Real Estate 1000\n",
|
653 |
+
"Games 700\n",
|
654 |
+
"Sensitive Subjects 688\n",
|
655 |
+
"Name: count, dtype: int64"
|
656 |
+
]
|
657 |
+
},
|
658 |
+
"execution_count": 28,
|
659 |
+
"metadata": {},
|
660 |
+
"output_type": "execute_result"
|
661 |
+
}
|
662 |
+
],
|
663 |
+
"source": [
|
664 |
+
"concat_df.label.value_counts()"
|
665 |
+
]
|
666 |
+
},
|
667 |
+
{
|
668 |
+
"cell_type": "code",
|
669 |
+
"execution_count": 29,
|
670 |
+
"metadata": {},
|
671 |
+
"outputs": [
|
672 |
+
{
|
673 |
+
"data": {
|
674 |
+
"text/html": [
|
675 |
+
"<div>\n",
|
676 |
+
"<style scoped>\n",
|
677 |
+
" .dataframe tbody tr th:only-of-type {\n",
|
678 |
+
" vertical-align: middle;\n",
|
679 |
+
" }\n",
|
680 |
+
"\n",
|
681 |
+
" .dataframe tbody tr th {\n",
|
682 |
+
" vertical-align: top;\n",
|
683 |
+
" }\n",
|
684 |
+
"\n",
|
685 |
+
" .dataframe thead th {\n",
|
686 |
+
" text-align: right;\n",
|
687 |
+
" }\n",
|
688 |
+
"</style>\n",
|
689 |
+
"<table border=\"1\" class=\"dataframe\">\n",
|
690 |
+
" <thead>\n",
|
691 |
+
" <tr style=\"text-align: right;\">\n",
|
692 |
+
" <th></th>\n",
|
693 |
+
" <th>category</th>\n",
|
694 |
+
" <th>label</th>\n",
|
695 |
+
" <th>label_id</th>\n",
|
696 |
+
" </tr>\n",
|
697 |
+
" </thead>\n",
|
698 |
+
" <tbody>\n",
|
699 |
+
" <tr>\n",
|
700 |
+
" <th>0</th>\n",
|
701 |
+
" <td>Scientific literature review</td>\n",
|
702 |
+
" <td>Science</td>\n",
|
703 |
+
" <td>6</td>\n",
|
704 |
+
" </tr>\n",
|
705 |
+
" <tr>\n",
|
706 |
+
" <th>1</th>\n",
|
707 |
+
" <td>LGBTQ+ community strategies</td>\n",
|
708 |
+
" <td>People_and_Society</td>\n",
|
709 |
+
" <td>1</td>\n",
|
710 |
+
" </tr>\n",
|
711 |
+
" <tr>\n",
|
712 |
+
" <th>2</th>\n",
|
713 |
+
" <td>Social services for vulnerable populations</td>\n",
|
714 |
+
" <td>People_and_Society</td>\n",
|
715 |
+
" <td>1</td>\n",
|
716 |
+
" </tr>\n",
|
717 |
+
" <tr>\n",
|
718 |
+
" <th>3</th>\n",
|
719 |
+
" <td>Graduate school admissions</td>\n",
|
720 |
+
" <td>Jobs_and_Education</td>\n",
|
721 |
+
" <td>19</td>\n",
|
722 |
+
" </tr>\n",
|
723 |
+
" <tr>\n",
|
724 |
+
" <th>4</th>\n",
|
725 |
+
" <td>Immigrant Health Education</td>\n",
|
726 |
+
" <td>Health</td>\n",
|
727 |
+
" <td>13</td>\n",
|
728 |
+
" </tr>\n",
|
729 |
+
" <tr>\n",
|
730 |
+
" <th>5</th>\n",
|
731 |
+
" <td>Travel deals for beachfront guesthouses</td>\n",
|
732 |
+
" <td>Travel_and_Transportation</td>\n",
|
733 |
+
" <td>2</td>\n",
|
734 |
+
" </tr>\n",
|
735 |
+
" <tr>\n",
|
736 |
+
" <th>6</th>\n",
|
737 |
+
" <td>Book subscription boxes</td>\n",
|
738 |
+
" <td>Books_and_Literature</td>\n",
|
739 |
+
" <td>15</td>\n",
|
740 |
+
" </tr>\n",
|
741 |
+
" <tr>\n",
|
742 |
+
" <th>7</th>\n",
|
743 |
+
" <td>Game streaming community building</td>\n",
|
744 |
+
" <td>Games</td>\n",
|
745 |
+
" <td>23</td>\n",
|
746 |
+
" </tr>\n",
|
747 |
+
" <tr>\n",
|
748 |
+
" <th>8</th>\n",
|
749 |
+
" <td>Retirement healthcare cost planning for health...</td>\n",
|
750 |
+
" <td>Finance</td>\n",
|
751 |
+
" <td>21</td>\n",
|
752 |
+
" </tr>\n",
|
753 |
+
" <tr>\n",
|
754 |
+
" <th>9</th>\n",
|
755 |
+
" <td>Campaign finance laws effectiveness impact</td>\n",
|
756 |
+
" <td>Law_and_Government</td>\n",
|
757 |
+
" <td>11</td>\n",
|
758 |
+
" </tr>\n",
|
759 |
+
" <tr>\n",
|
760 |
+
" <th>10</th>\n",
|
761 |
+
" <td>Vintage and antique furniture and decor items</td>\n",
|
762 |
+
" <td>Shopping</td>\n",
|
763 |
+
" <td>3</td>\n",
|
764 |
+
" </tr>\n",
|
765 |
+
" <tr>\n",
|
766 |
+
" <th>11</th>\n",
|
767 |
+
" <td>Volunteer opportunities near me</td>\n",
|
768 |
+
" <td>People_and_Society</td>\n",
|
769 |
+
" <td>1</td>\n",
|
770 |
+
" </tr>\n",
|
771 |
+
" <tr>\n",
|
772 |
+
" <th>12</th>\n",
|
773 |
+
" <td>Startup success stories</td>\n",
|
774 |
+
" <td>News</td>\n",
|
775 |
+
" <td>8</td>\n",
|
776 |
+
" </tr>\n",
|
777 |
+
" <tr>\n",
|
778 |
+
" <th>13</th>\n",
|
779 |
+
" <td>Internet connectivity solutions for sports org...</td>\n",
|
780 |
+
" <td>Internet_and_Telecom</td>\n",
|
781 |
+
" <td>17</td>\n",
|
782 |
+
" </tr>\n",
|
783 |
+
" <tr>\n",
|
784 |
+
" <th>14</th>\n",
|
785 |
+
" <td>Travel destination local experts</td>\n",
|
786 |
+
" <td>Travel_and_Transportation</td>\n",
|
787 |
+
" <td>2</td>\n",
|
788 |
+
" </tr>\n",
|
789 |
+
" <tr>\n",
|
790 |
+
" <th>15</th>\n",
|
791 |
+
" <td>Industrial revolution history</td>\n",
|
792 |
+
" <td>Business_and_Industrial</td>\n",
|
793 |
+
" <td>12</td>\n",
|
794 |
+
" </tr>\n",
|
795 |
+
" <tr>\n",
|
796 |
+
" <th>16</th>\n",
|
797 |
+
" <td>Backyard pond filtration systems</td>\n",
|
798 |
+
" <td>Home_and_Garden</td>\n",
|
799 |
+
" <td>18</td>\n",
|
800 |
+
" </tr>\n",
|
801 |
+
" <tr>\n",
|
802 |
+
" <th>17</th>\n",
|
803 |
+
" <td>Data center solutions providers list</td>\n",
|
804 |
+
" <td>Internet_and_Telecom</td>\n",
|
805 |
+
" <td>17</td>\n",
|
806 |
+
" </tr>\n",
|
807 |
+
" <tr>\n",
|
808 |
+
" <th>18</th>\n",
|
809 |
+
" <td>Wi-Fi signal optimization for hotels</td>\n",
|
810 |
+
" <td>Internet_and_Telecom</td>\n",
|
811 |
+
" <td>17</td>\n",
|
812 |
+
" </tr>\n",
|
813 |
+
" <tr>\n",
|
814 |
+
" <th>19</th>\n",
|
815 |
+
" <td>Smart home technology trends</td>\n",
|
816 |
+
" <td>Shopping</td>\n",
|
817 |
+
" <td>3</td>\n",
|
818 |
+
" </tr>\n",
|
819 |
+
" </tbody>\n",
|
820 |
+
"</table>\n",
|
821 |
+
"</div>"
|
822 |
+
],
|
823 |
+
"text/plain": [
|
824 |
+
" category \\\n",
|
825 |
+
"0 Scientific literature review \n",
|
826 |
+
"1 LGBTQ+ community strategies \n",
|
827 |
+
"2 Social services for vulnerable populations \n",
|
828 |
+
"3 Graduate school admissions \n",
|
829 |
+
"4 Immigrant Health Education \n",
|
830 |
+
"5 Travel deals for beachfront guesthouses \n",
|
831 |
+
"6 Book subscription boxes \n",
|
832 |
+
"7 Game streaming community building \n",
|
833 |
+
"8 Retirement healthcare cost planning for health... \n",
|
834 |
+
"9 Campaign finance laws effectiveness impact \n",
|
835 |
+
"10 Vintage and antique furniture and decor items \n",
|
836 |
+
"11 Volunteer opportunities near me \n",
|
837 |
+
"12 Startup success stories \n",
|
838 |
+
"13 Internet connectivity solutions for sports org... \n",
|
839 |
+
"14 Travel destination local experts \n",
|
840 |
+
"15 Industrial revolution history \n",
|
841 |
+
"16 Backyard pond filtration systems \n",
|
842 |
+
"17 Data center solutions providers list \n",
|
843 |
+
"18 Wi-Fi signal optimization for hotels \n",
|
844 |
+
"19 Smart home technology trends \n",
|
845 |
+
"\n",
|
846 |
+
" label label_id \n",
|
847 |
+
"0 Science 6 \n",
|
848 |
+
"1 People_and_Society 1 \n",
|
849 |
+
"2 People_and_Society 1 \n",
|
850 |
+
"3 Jobs_and_Education 19 \n",
|
851 |
+
"4 Health 13 \n",
|
852 |
+
"5 Travel_and_Transportation 2 \n",
|
853 |
+
"6 Books_and_Literature 15 \n",
|
854 |
+
"7 Games 23 \n",
|
855 |
+
"8 Finance 21 \n",
|
856 |
+
"9 Law_and_Government 11 \n",
|
857 |
+
"10 Shopping 3 \n",
|
858 |
+
"11 People_and_Society 1 \n",
|
859 |
+
"12 News 8 \n",
|
860 |
+
"13 Internet_and_Telecom 17 \n",
|
861 |
+
"14 Travel_and_Transportation 2 \n",
|
862 |
+
"15 Business_and_Industrial 12 \n",
|
863 |
+
"16 Home_and_Garden 18 \n",
|
864 |
+
"17 Internet_and_Telecom 17 \n",
|
865 |
+
"18 Internet_and_Telecom 17 \n",
|
866 |
+
"19 Shopping 3 "
|
867 |
+
]
|
868 |
+
},
|
869 |
+
"execution_count": 29,
|
870 |
+
"metadata": {},
|
871 |
+
"output_type": "execute_result"
|
872 |
+
}
|
873 |
+
],
|
874 |
+
"source": [
|
875 |
+
"cdf_shffeled= concat_df.sample(frac=1).reset_index(drop=True)\n",
|
876 |
+
"cdf_shffeled.head(20)"
|
877 |
+
]
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"cell_type": "code",
|
881 |
+
"execution_count": 23,
|
882 |
+
"metadata": {},
|
883 |
+
"outputs": [],
|
884 |
+
"source": [
|
885 |
+
"cdf_shffeled.to_csv(\n",
|
886 |
+
" 'data_categories/Final_Category_Data_With_Labels.csv'\n",
|
887 |
+
")"
|
888 |
+
]
|
889 |
+
},
|
890 |
+
{
|
891 |
+
"cell_type": "code",
|
892 |
+
"execution_count": null,
|
893 |
+
"metadata": {},
|
894 |
+
"outputs": [],
|
895 |
+
"source": []
|
896 |
+
}
|
897 |
+
],
|
898 |
+
"metadata": {
|
899 |
+
"kernelspec": {
|
900 |
+
"display_name": "venv",
|
901 |
+
"language": "python",
|
902 |
+
"name": "python3"
|
903 |
+
},
|
904 |
+
"language_info": {
|
905 |
+
"codemirror_mode": {
|
906 |
+
"name": "ipython",
|
907 |
+
"version": 3
|
908 |
+
},
|
909 |
+
"file_extension": ".py",
|
910 |
+
"mimetype": "text/x-python",
|
911 |
+
"name": "python",
|
912 |
+
"nbconvert_exporter": "python",
|
913 |
+
"pygments_lexer": "ipython3",
|
914 |
+
"version": "3.10.12"
|
915 |
+
}
|
916 |
+
},
|
917 |
+
"nbformat": 4,
|
918 |
+
"nbformat_minor": 2
|
919 |
+
}
|