![\"Open](\"https://colab.research.google.com/assets/colab-badge.svg\"){kind=icon}
"
11 | ]
12 | },
13 | {
14 | "cell_type": "markdown",
15 | "metadata": {
16 | "id": "zSX7qCPx7_sx"
17 | },
18 | "source": [
19 | "# **deep learning model**\n",
20 | "# ***Attention- based Seq2Seq Model***"
21 | ]
22 | },
23 | {
24 | "cell_type": "markdown",
25 | "metadata": {
26 | "id": "K2kzzVhv798W"
27 | },
28 | "source": [
29 | "# bidirectional LSTM encoder :phase 1"
30 | ]
31 | },
32 | {
33 | "cell_type": "code",
34 | "execution_count": null,
35 | "metadata": {
36 | "id": "iHVUIrKpLb74"
37 | },
38 | "outputs": [],
39 | "source": [
40 | "import pandas as pd\n",
41 | "import numpy as np\n",
42 | "import tensorflow as tf\n",
43 | "from gensim.models import Word2Vec\n",
44 | "from keras.preprocessing.text import Tokenizer\n",
45 | "from tensorflow.keras.preprocessing.sequence import pad_sequences\n",
46 | "from keras.layers import Embedding, LSTM, Dense, Bidirectional\n",
47 | "from keras.models import Sequential"
48 | ]
49 | },
50 | {
51 | "cell_type": "code",
52 | "execution_count": null,
53 | "metadata": {
54 | "id": "O1fqausTUEgS"
55 | },
56 | "outputs": [],
57 | "source": [
58 | "from keras.layers import *\n",
59 | "from keras.models import *\n",
60 | "from keras import backend as K"
61 | ]
62 | },
63 | {
64 | "cell_type": "code",
65 | "execution_count": null,
66 | "metadata": {
67 | "id": "wVEC5-LN-LcZ"
68 | },
69 | "outputs": [],
70 | "source": [
71 | "df_train = pd.read_csv(\"/content/drive/MyDrive/ATS- gigadata/model_gigadata_new.csv\")"
72 | ]
73 | },
74 | {
75 | "cell_type": "code",
76 | "execution_count": null,
77 | "metadata": {
78 | "id": "dxx3V4PKHsqP"
79 | },
80 | "outputs": [],
81 | "source": [
82 | "i=0\n",
83 | "tokens ,art_summer=[] , []\n",
84 | "\n",
85 | "while i<1000000:\n",
86 | " art_summer.append(df_train['article'][i])\n",
87 | " art_summer.append(df_train['summery'][i])\n",
88 | " tokens.append(art_summer)\n",
89 | " art_summer = []\n",
90 | " i+=1"
91 | ]
92 | },
93 | {
94 | "cell_type": "code",
95 | "execution_count": null,
96 | "metadata": {
97 | "id": "43IOaAcqH5dr"
98 | },
99 | "outputs": [],
100 | "source": [
101 | "embed_model = Word2Vec(tokens, size = 100, window = 5 , min_count = 1)"
102 | ]
103 | },
104 | {
105 | "cell_type": "code",
106 | "execution_count": null,
107 | "metadata": {
108 | "id": "-gECaaYdptlL"
109 | },
110 | "outputs": [],
111 | "source": [
112 | "embed_model.save(\"w2v.model\")"
113 | ]
114 | },
115 | {
116 | "cell_type": "code",
117 | "execution_count": null,
118 | "metadata": {
119 | "id": "qrgGvyNVMiFD"
120 | },
121 | "outputs": [],
122 | "source": [
123 | "embedding_weights = embed_model.wv.vectors"
124 | ]
125 | },
126 | {
127 | "cell_type": "code",
128 | "execution_count": null,
129 | "metadata": {
130 | "colab": {
131 | "base_uri": "https://localhost:8080/"
132 | },
133 | "id": "9zhyhs9oZJvl",
134 | "outputId": "1745bd34-4933-4d26-9803-d95c45947db0"
135 | },
136 | "outputs": [
137 | {
138 | "data": {
139 | "text/plain": [
140 | "(1498136, 100)"
141 | ]
142 | },
143 | "execution_count": 8,
144 | "metadata": {},
145 | "output_type": "execute_result"
146 | }
147 | ],
148 | "source": [
149 | "embedding_weights.shape"
150 | ]
151 | },
152 | {
153 | "cell_type": "code",
154 | "execution_count": null,
155 | "metadata": {
156 | "colab": {
157 | "background_save": true
158 | },
159 | "id": "Jm6K3keWShtb"
160 | },
161 | "outputs": [],
162 | "source": [
163 | "x , y = [],[]\n",
164 | "i=0\n",
165 | "while i