File size: 6,940 Bytes
dfe58cd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "import json\n",
    "import csv\n",
    "import ast"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "csv_file_path = \"aug_rev.csv\"  # Path of the CSV\n",
    "json_file_path = \"aug_rev.json\"  # Path of the JSON"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                                               Reviews  is_positive?\n",
      "0    Their team was incredibly knowledgeable about ...             1\n",
      "1    Their team was incredibly knowledgeable about ...             1\n",
      "2                             I stayed here overnight.             1\n",
      "3                             Its okay and affordable.             1\n",
      "4                         Best here is their Sinigang.             1\n",
      "..                                                 ...           ...\n",
      "275   I recommend this hotel to all people who want...             1\n",
      "276  iodine commend this hotel to all people World_...             1\n",
      "277  They have bars restaurant coffee shop spa cent...             1\n",
      "278  They have bars restaurant coffee shop spa etc ...             1\n",
      "279  They are the best agents to contact if you are...             1\n",
      "\n",
      "[280 rows x 2 columns]\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\Ayooo\\AppData\\Local\\Temp\\ipykernel_1904\\2765031854.py:14: FutureWarning: The default value of regex will change from True to False in a future version.\n",
      "  df['Reviews'] = df['Reviews'].str.replace(r\"[\\\"\\',\\[\\]]\", \"\")\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "\n",
    "# Read the CSV file into a pandas DataFrame\n",
    "df = pd.read_csv('aug_rev.csv')\n",
    "\n",
    "\n",
    "# Separate the reviews by splitting the string at the ', ' separator\n",
    "df['Reviews'] = df['Reviews'].apply(lambda x: x.split(\"', \"))\n",
    "\n",
    "# Explode the \"Reviews\" column to separate each review into its own row\n",
    "df = df.explode('Reviews')\n",
    "\n",
    "# Remove quotation marks and square brackets from the reviews\n",
    "df['Reviews'] = df['Reviews'].str.replace(r\"[\\\"\\',\\[\\]]\", \"\")\n",
    "\n",
    "# Reset the index\n",
    "df.reset_index(drop=True, inplace=True)\n",
    "\n",
    "# Print the updated DataFrame\n",
    "print(df)\n",
    "\n",
    "# Save the updated DataFrame as a new CSV file\n",
    "df.to_csv('aug_rev.csv', index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "rows = []\n",
    "\n",
    "# Read the CSV file and preprocess the data\n",
    "with open(csv_file_path, newline='') as csv_file:\n",
    "    reader = csv.DictReader(csv_file)\n",
    "    for row in reader:\n",
    "        row[\"is_positive?\"] = int(row[\"is_positive?\"])\n",
    "        rows.append(row)\n",
    "\n",
    "# Convert the preprocessed data to JSON\n",
    "with open(json_file_path, 'w') as json_file:\n",
    "    json.dump(rows, json_file, indent=4)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import nltk\n",
    "import random\n",
    "\n",
    "nltk.download('punkt')\n",
    "\n",
    "# Define augmentation parameters\n",
    "synonym_replacement_prob = 0.1\n",
    "random_insertion_prob = 0.1\n",
    "random_deletion_prob = 0.1\n",
    "\n",
    "# Initialize NLTK's WordNet for synonym replacement\n",
    "nltk.download('wordnet')\n",
    "from nltk.corpus import wordnet\n",
    "\n",
    "# Function to replace a word with a random synonym\n",
    "def replace_with_synonym(word):\n",
    "    synsets = wordnet.synsets(word)\n",
    "    if synsets:\n",
    "        synonyms = [syn.lemmas()[0].name() for syn in synsets]\n",
    "        return random.choice(synonyms)\n",
    "    else:\n",
    "        return word\n",
    "\n",
    "augmented_sentences = []\n",
    "augmented_labels = []\n",
    "\n",
    "for sentence, label in zip(sentences, labels):\n",
    "    augmented_sentences.append(sentence)\n",
    "    augmented_labels.append(label)\n",
    "    \n",
    "    # Perform synonym replacement\n",
    "    if random.random() < synonym_replacement_prob:\n",
    "        words = nltk.word_tokenize(sentence)\n",
    "        words = [replace_with_synonym(word) for word in words]\n",
    "        augmented_sentences.append(' '.join(words))\n",
    "        augmented_labels.append(label)\n",
    "    \n",
    "    # Perform random insertion\n",
    "    if random.random() < random_insertion_prob:\n",
    "        words = nltk.word_tokenize(sentence)\n",
    "        random_word = random.choice(words)\n",
    "        words.insert(random.randint(0, len(words) - 1), random_word)\n",
    "        augmented_sentences.append(' '.join(words))\n",
    "        augmented_labels.append(label)\n",
    "    \n",
    "    # Perform random deletion\n",
    "    if random.random() < random_deletion_prob:\n",
    "        words = nltk.word_tokenize(sentence)\n",
    "        if len(words) > 1:\n",
    "            random_word_idx = random.randint(0, len(words) - 1)\n",
    "            words.pop(random_word_idx)\n",
    "            augmented_sentences.append(' '.join(words))\n",
    "            augmented_labels.append(label)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Define the output file path\n",
    "output_file = \"augmented_dataset.csv\"\n",
    "\n",
    "# Combine augmented sentences and labels into a list of tuples\n",
    "augmented_data = list(zip(augmented_sentences, augmented_labels))\n",
    "\n",
    "# Write the augmented data to a CSV file\n",
    "with open(output_file, 'w', newline='') as csvfile:\n",
    "    writer = csv.writer(csvfile)\n",
    "    \n",
    "    # Write the header\n",
    "    writer.writerow(['Sentence', 'Label'])\n",
    "    \n",
    "    # Write each augmented sentence and label as a row in the CSV file\n",
    "    writer.writerows(augmented_data)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.2"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}