|
87 | 87 | }, |
88 | 88 | { |
89 | 89 | "cell_type": "code", |
90 | | - "execution_count": 4, |
| 90 | + "execution_count": 2, |
91 | 91 | "metadata": {}, |
92 | 92 | "outputs": [ |
93 | 93 | { |
94 | 94 | "name": "stderr", |
95 | 95 | "output_type": "stream", |
96 | 96 | "text": [ |
97 | | - "2022-01-05 20:26:31 INFO: Load pretrained SentenceTransformer: allenai-specter\n", |
98 | | - "2022-01-05 20:26:49 INFO: Use pytorch device: cuda\n", |
99 | | - "2022-01-05 20:26:49 INFO: Missing data detected. Dropping them\n", |
100 | | - "2022-01-05 20:26:49 INFO: ========== Step1: Calculating Embeddings ==========\n", |
101 | | - "Batches: 100%|██████████| 3/3 [00:02<00:00, 1.43it/s]\n", |
102 | | - "2022-01-05 20:26:52 INFO: ========== Step2: Topic modeling ==========\n", |
103 | | - "2022-01-05 20:26:52 INFO: Initializing the topic model\n", |
104 | | - "2022-01-05 20:26:52 INFO: Training the topic model\n", |
105 | | - "2022-01-05 20:26:54,313 - BERTopic - Reduced dimensionality with UMAP\n", |
106 | | - "2022-01-05 20:26:54,324 - BERTopic - Clustered UMAP embeddings with HDBSCAN\n", |
107 | | - "2022-01-05 20:26:54 INFO: Populating Topic Results\n", |
108 | | - "2022-01-05 20:26:54 INFO: ========== Step3: STriP Network ==========\n", |
109 | | - "2022-01-05 20:26:54 INFO: Cosine similarity\n", |
110 | | - "2022-01-05 20:26:54 INFO: Calculating optimal threshold\n", |
111 | | - "2022-01-05 20:26:54 INFO: Number of connections: 126\n", |
112 | | - "2022-01-05 20:26:54 INFO: Calculating Network Plot\n", |
113 | | - "2022-01-05 20:26:54 INFO: ========== Model Fit Successfully! ==========\n" |
| 97 | + "2022-01-05 20:42:12 INFO: Load pretrained SentenceTransformer: allenai-specter\n", |
| 98 | + "2022-01-05 20:42:36 INFO: Use pytorch device: cuda\n", |
| 99 | + "2022-01-05 20:42:36 INFO: Missing data detected. Dropping them\n", |
| 100 | + "2022-01-05 20:42:36 INFO: ========== Step1: Calculating Embeddings ==========\n", |
| 101 | + "Batches: 100%|██████████| 3/3 [00:02<00:00, 1.17it/s]\n", |
| 102 | + "2022-01-05 20:42:41 INFO: ========== Step2: Topic modeling ==========\n", |
| 103 | + "2022-01-05 20:42:41 INFO: Initializing the topic model\n", |
| 104 | + "2022-01-05 20:42:41 INFO: Training the topic model\n", |
| 105 | + "2022-01-05 20:42:50,425 - BERTopic - Reduced dimensionality with UMAP\n", |
| 106 | + "2022-01-05 20:42:50,437 - BERTopic - Clustered UMAP embeddings with HDBSCAN\n", |
| 107 | + "2022-01-05 20:42:50 INFO: Populating Topic Results\n", |
| 108 | + "2022-01-05 20:42:50 INFO: ========== Step3: STriP Network ==========\n", |
| 109 | + "2022-01-05 20:42:50 INFO: Cosine similarity\n", |
| 110 | + "2022-01-05 20:42:50 INFO: Calculating optimal threshold\n", |
| 111 | + "2022-01-05 20:42:50 INFO: Number of connections: 126\n", |
| 112 | + "2022-01-05 20:42:50 INFO: Calculating Network Plot\n", |
| 113 | + "2022-01-05 20:42:50 INFO: ========== Model Fit Successfully! ==========\n" |
114 | 114 | ] |
115 | 115 | }, |
116 | 116 | { |
|
1141 | 1141 | "stripnet.most_important()" |
1142 | 1142 | ] |
1143 | 1143 | }, |
| 1144 | + { |
| 1145 | + "cell_type": "code", |
| 1146 | + "execution_count": 3, |
| 1147 | + "metadata": {}, |
| 1148 | + "outputs": [ |
| 1149 | + { |
| 1150 | + "data": { |
| 1151 | + "text/plain": [ |
| 1152 | + "['bertopic==0.9.4',\n", |
| 1153 | + " 'networkx==2.6.3',\n", |
| 1154 | + " 'numpy==1.22.0',\n", |
| 1155 | + " 'pandas==1.3.5',\n", |
| 1156 | + " 'plotly==5.5.0',\n", |
| 1157 | + " 'pyvis==0.1.9',\n", |
| 1158 | + " 'scikit_learn==1.0.2',\n", |
| 1159 | + " 'sentence_transformers==2.1.0',\n", |
| 1160 | + " 'setuptools==58.0.4']" |
| 1161 | + ] |
| 1162 | + }, |
| 1163 | + "execution_count": 3, |
| 1164 | + "metadata": {}, |
| 1165 | + "output_type": "execute_result" |
| 1166 | + } |
| 1167 | + ], |
| 1168 | + "source": [ |
| 1169 | + "import pathlib\n", |
| 1170 | + "pathlib.Path(\"../requirements.txt\").read_text().splitlines()" |
| 1171 | + ] |
| 1172 | + }, |
1144 | 1173 | { |
1145 | 1174 | "cell_type": "code", |
1146 | 1175 | "execution_count": null, |
|
0 commit comments