\n",
- "Int64Index: 2946 entries, 1591 to 6131\n",
- "Data columns (total 4 columns):\n",
- " # Column Non-Null Count Dtype \n",
- "--- ------ -------------- ----- \n",
- " 0 tweet_id 2946 non-null object \n",
- " 1 safe_text 2946 non-null object \n",
- " 2 label 2946 non-null float64\n",
- " 3 agreement 2946 non-null float64\n",
- "dtypes: float64(2), object(2)\n",
- "memory usage: 115.1+ KB\n"
- ]
- }
- ]
- },
- {
- "cell_type": "code",
- "source": [
- "# Save splitted subsets\n",
- "\n",
- "# Define file path\n",
- "\n",
- "file_path = '/content/drive/MyDrive/LP5/Career_Accelerator_P5-NLP'\n",
- "\n",
- "#\"/content/drive/MyDrive/LP5/Career_Accelerator_P5-NLP\"\n",
- "\n",
- "train.to_csv(os.path.join(file_path, \"train_subset.csv\"), index=False)\n",
- "eval.to_csv(os.path.join(file_path, \"eval_subset.csv\"), index=False)"
- ],
- "metadata": {
- "id": "dX7PPpfWYYEH"
- },
- "execution_count": null,
- "outputs": []
- },
- {
- "cell_type": "code",
- "source": [
- "# Load the CSV files into a dataset\n",
- "\n",
- "dataset = load_dataset('csv', data_files={\n",
- " 'train': '/content/drive/MyDrive/LP5/Career_Accelerator_P5-NLP/train_subset.csv',\n",
- " 'eval': '/content/drive/MyDrive/LP5/Career_Accelerator_P5-NLP/eval_subset.csv'\n",
- "}, encoding='ISO-8859-1')"
- ],
- "metadata": {
- "colab": {
- "base_uri": "https://localhost:8080/",
- "height": 145,
- "referenced_widgets": [
- "8317af457cae42a1abc4e51f51005024",
- "2f69dfb451ef4d299ab8426fa13d9cc9",
- "cee8221d7b604daaa0410fa43a7e02c6",
- "93e0888ab59c431788bde53b47c9f1a7",
- "5d6e06ad7a404ebe9989eac1ad8088b8",
- "15c30df19dc34bfd838a8dab09ffc539",
- "a4f9f99512df4b0e855255b723bb9a32",
- "452164c70ad74ba9ba5d7a051511e7a4",
- "a945817118b2490981c8c2523c0d14b7",
- "39afc12f9f79453e825dc53ce47f430d",
- "29290f8590e046419de099ef06f161e7",
- "695b654db12041a585e86db828de5d95",
- "c41e5e6cec324f5db130622308cde314",
- "322b85b8208645f4985f8e9c2c49ad3f",
- "c1efaccf258c4e289f18fa95163506d8",
- "2e30f2e5d1a44a08b03b96afbb9f13ef",
- "75246d3c183a466d9568801d029e83e4",
- "fa5b047a367242b3b5752f9341075e38",
- "ed2608efb1984c1da3b16a5e6a8cd721",
- "288e22fe04324ce1a58f90d0eb20c364",
- "404ff5cd99824b19ad9ab92259a16f6c",
- "cd733dfbddad4cd897ff4de0ac59d159",
- "6eb746d967ac4f8eb177ba7993195dfa",
- "d34d49386cd44fccb961612f3e6927f4",
- "9a43b8a0d1de4071bd5ad07e03f38ec8",
- "360864a297ef455db7119b09eaf6187d",
- "b3ae9602ed824d0d9404e685866b781b",
- "1b54675ca28b42d0b9392d01aae335b4",
- "2a42963e11534bab9a4e589afd48b088",
- "ea67b81733974c20920b2f980e30fb7c",
- "0b9cc75ee18e471792adb2c9cff89c84",
- "d9109a472e8d47e7a3a703307dce6206",
- "6e5d529bf7274b4ea671ff62c16c0b65",
- "71c83f53f66a4d7c9fe937679a4e53cf",
- "d0a9d85156f34ca98c39b52ddbc13fb6",
- "cdd36713dac848afbfeeb32c0c77056b",
- "95ea838a1cb74ab2aba597fe5360fe06",
- "2ce24f7ad8724307b64f279113fb6141",
- "04ae3b6e5f0b484ab742dc68f7012adc",
- "74681abc93d24b538f95bb9da0d2771e",
- "fd101d83e06a42ad842994c03dd5daff",
- "8ff9991cd97c402694894100d7be585e",
- "a5a4f8535b2e4e638260acfe5ba1dbc8",
- "7fbc9531f78144bb91272299fd03fc10"
- ]
- },
- "id": "ENDoL3ObY1H6",
- "outputId": "378a8c0d-2634-4f8e-de51-2b8c870d0bec"
- },
- "execution_count": null,
- "outputs": [
- {
- "output_type": "display_data",
- "data": {
- "text/plain": [
- "Downloading data files: 0%| | 0/2 [00:00\n",
- " \n",
- " \n",
- " [406/552 39:47 < 14:22, 0.17 it/s, Epoch 2.20/3]\n",
- " \n",
- " \n",
- " \n",
- " \n",
- " | Step | \n",
- " Training Loss | \n",
- " Validation Loss | \n",
- "
\n",
- " \n",
- " \n",
- " \n",
- "
"
- ],
- "text/plain": [
- ""
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- },
- {
- "output_type": "display_data",
- "data": {
- "text/plain": [
- ""
- ],
- "text/html": [
- "\n",
- " \n",
- " \n",
- "
\n",
- " [458/552 44:56 < 09:15, 0.17 it/s, Epoch 2.48/3]\n",
- "
\n",
- " \n",
- " \n",
- " | Step | \n",
- " Training Loss | \n",
- " Validation Loss | \n",
- "
\n",
- " \n",
- " \n",
- " \n",
- "
"
- ]
- },
- "metadata": {}
- }
- ]
- },
- {
- "cell_type": "code",
- "source": [
- "# Evaluate the model\n",
- "eval_results = trainer_ROBERTA.evaluate()\n",
- "\n",
- "# Create a dictionary of the evaluation results\n",
- "results_dict = {\n",
- " \"Model\": \"roberta-base\",\n",
- " \"Loss\": eval_results[\"eval_loss\"],\n",
- " \"RMSE\": eval_results[\"eval_rmse\"],\n",
- " \"Runtime\": eval_results[\"eval_runtime\"],\n",
- " \"Samples Per Second\": eval_results[\"eval_samples_per_second\"],\n",
- " \"Steps Per Second\": eval_results[\"eval_steps_per_second\"],\n",
- " \"Epoch\": eval_results[\"epoch\"]\n",
- "}\n",
- "\n",
- "# Create a pandas DataFrame from the dictionary\n",
- "results_df = pd.DataFrame([results_dict])\n",
- "\n",
- "# Sort the results by \"eval_rmse\" in ascending order and get the name and state dict of the best model\n",
- "best_model = results_df.loc[results_df['f1_macro'].idxmin()]\n",
- "\n",
- "print(best_model)"
- ],
- "metadata": {
- "id": "xrjdNpstawTP",
- "colab": {
- "base_uri": "https://localhost:8080/",
- "height": 235
- },
- "outputId": "06812a13-e52a-4a6b-9c9e-539f385e5a75"
- },
- "execution_count": null,
- "outputs": [
- {
- "output_type": "error",
- "ename": "NameError",
- "evalue": "ignored",
- "traceback": [
- "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
- "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
- "\u001b[0;32m\u001b[0m in \u001b[0;36m| \u001b[0;34m()\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0;31m# Evaluate the model\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0meval_results\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtrainer_ROBERTA\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mevaluate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 3\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 4\u001b[0m \u001b[0;31m# Create a dictionary of the evaluation results\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 5\u001b[0m results_dict = {\n",
- "\u001b[0;31mNameError\u001b[0m: name 'trainer_ROBERTA' is not defined"
- ]
- }
- ]
- },
- {
- "cell_type": "code",
- "source": [
- "# Push the final fine-tuned model to the Hugging Face model hub\n",
- "\n",
- "trainer_ROBERTA.push_to_hub (\"MissChloe/PQ_Roberta_Model\")"
- ],
- "metadata": {
- "id": "hCOqdoteg0aB"
- },
- "execution_count": null,
- "outputs": []
- },
- {
- "cell_type": "code",
- "source": [
- "tokenizer_ROBERTA.push_to_hub (\"MissChloe/PQ_Roberta_Model\")"
- ],
- "metadata": {
- "id": "k_uAB3cXkJnK"
- },
- "execution_count": null,
- "outputs": []
- },
- {
- "cell_type": "code",
- "source": [
- "model_ROBERTA.push_to_hub(\"MissChloe/PQ_Roberta_Model\")"
- ],
- "metadata": {
- "id": "n7IzT4d6kUsm"
- },
- "execution_count": null,
- "outputs": []
- },
- {
- "cell_type": "code",
- "source": [
- "# Load the tokenizer\n",
- "tokenizer = tokenizer_ROBERTA.from_pretrained(\"slickdata/finetuned-Sentiment-classfication-ROBERTA-model\")\n",
- "\n",
- "# Load the fine-tuned model\n",
- "model = pipeline(\"text-classification\", model=\"MissChloe/PQ_Roberta_Model\", tokenizer=tokenizer)"
- ],
- "metadata": {
- "id": "9gwaLN2hkcQd"
- },
- "execution_count": null,
- "outputs": []
- },
- {
- "cell_type": "code",
- "source": [
- "label_map = {0: \"negative\", 1: \"neutral\", 2: \"positive\"}\n",
- "\n",
- "# Make predictions on some example text\n",
- "result = model(\"I love these covid vaccines.\")\n",
- "\n",
- "# Map the numerical label to the corresponding class name\n",
- "result[0][\"label\"] = label_map[int(result[0][\"label\"].split(\"_\")[1])]\n",
- "\n",
- "# Print the predicted label and score\n",
- "print(result)"
- ],
- "metadata": {
- "id": "13tRokU8kv4S"
- },
- "execution_count": null,
- "outputs": []
- },
- {
- "cell_type": "code",
- "source": [
- "!pip freeze >"
- ],
- "metadata": {
- "id": "5dwzpHGlk08E"
- },
- "execution_count": null,
- "outputs": []
- }
- ]
-}
\ No newline at end of file
|