{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"! pip install scikit-llm","metadata":{"execution":{"iopub.status.busy":"2023-09-10T15:25:34.002995Z","iopub.execute_input":"2023-09-10T15:25:34.003492Z","iopub.status.idle":"2023-09-10T15:25:57.536073Z","shell.execute_reply.started":"2023-09-10T15:25:34.003463Z","shell.execute_reply":"2023-09-10T15:25:57.534952Z"},"collapsed":true,"jupyter":{"outputs_hidden":true},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2023-09-10T15:28:26.596844Z","iopub.execute_input":"2023-09-10T15:28:26.597457Z","iopub.status.idle":"2023-09-10T15:28:26.606759Z","shell.execute_reply.started":"2023-09-10T15:28:26.597423Z","shell.execute_reply":"2023-09-10T15:28:26.605730Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df = pd.read_csv(\"/kaggle/input/quora-insincere-questions-classification/train.csv\")\nX_train = df['question_text'].to_list()\ny_train = df['target'].to_list()","metadata":{"execution":{"iopub.status.busy":"2023-09-10T15:35:56.542482Z","iopub.execute_input":"2023-09-10T15:35:56.542837Z","iopub.status.idle":"2023-09-10T15:35:59.284034Z","shell.execute_reply.started":"2023-09-10T15:35:56.542808Z","shell.execute_reply":"2023-09-10T15:35:59.283054Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_test = pd.read_csv(\"/kaggle/input/quora-insincere-questions-classification/test.csv\")\nX_test = X_test['question_text'].to_list()","metadata":{"execution":{"iopub.status.busy":"2023-09-10T15:38:53.341959Z","iopub.execute_input":"2023-09-10T15:38:53.342403Z","iopub.status.idle":"2023-09-10T15:38:54.350030Z","shell.execute_reply.started":"2023-09-10T15:38:53.342368Z","shell.execute_reply":"2023-09-10T15:38:54.349062Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from skllm.config import SKLLMConfig\n\nSKLLMConfig.set_openai_key(\"sk-xxx\")\nSKLLMConfig.set_openai_org(\"org-xxx\")","metadata":{"execution":{"iopub.status.busy":"2023-09-10T16:01:07.542248Z","iopub.execute_input":"2023-09-10T16:01:07.542636Z","iopub.status.idle":"2023-09-10T16:01:07.547882Z","shell.execute_reply.started":"2023-09-10T16:01:07.542605Z","shell.execute_reply":"2023-09-10T16:01:07.546591Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from skllm.models.gpt import GPTClassifier\n\nclf = GPTClassifier(\n        base_model = \"gpt-3.5-turbo-0613\",\n        n_epochs = None, # int or None. When None, will be determined automatically by OpenAI\n        default_label = \"Random\", # optional\n)\n\nclf.fit(X_train, y_train) # y_train is a list of labels\nlabels = clf.predict(X_test)","metadata":{},"execution_count":null,"outputs":[]}],"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}}