Created
December 17, 2023 17:55
-
-
Save Clivern/c35182fd192120d1c1377010fc45174e to your computer and use it in GitHub Desktop.
Supervised Learning With scikit-learn
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| {"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"},"kaggle":{"accelerator":"none","dataSources":[],"dockerImageVersionId":30626,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"!pip3 install numpy scipy matplotlib ipython scikit-learn pandas ","metadata":{"execution":{"iopub.status.busy":"2023-12-16T22:57:07.279424Z","iopub.execute_input":"2023-12-16T22:57:07.280252Z","iopub.status.idle":"2023-12-16T22:57:23.325605Z","shell.execute_reply.started":"2023-12-16T22:57:07.280213Z","shell.execute_reply":"2023-12-16T22:57:23.324046Z"},"trusted":true},"execution_count":1,"outputs":[{"name":"stdout","text":"Requirement already satisfied: numpy in /opt/conda/lib/python3.10/site-packages (1.24.3)\nRequirement already satisfied: scipy in /opt/conda/lib/python3.10/site-packages (1.11.4)\nRequirement already satisfied: matplotlib in /opt/conda/lib/python3.10/site-packages (3.7.4)\nRequirement already satisfied: ipython in /opt/conda/lib/python3.10/site-packages (8.14.0)\nRequirement already satisfied: scikit-learn in /opt/conda/lib/python3.10/site-packages (1.2.2)\nRequirement already satisfied: pandas in /opt/conda/lib/python3.10/site-packages (2.0.3)\nRequirement already satisfied: contourpy>=1.0.1 in /opt/conda/lib/python3.10/site-packages (from matplotlib) (1.1.0)\nRequirement already satisfied: cycler>=0.10 in /opt/conda/lib/python3.10/site-packages (from matplotlib) (0.11.0)\nRequirement already satisfied: fonttools>=4.22.0 in /opt/conda/lib/python3.10/site-packages (from matplotlib) (4.42.1)\nRequirement already satisfied: kiwisolver>=1.0.1 in /opt/conda/lib/python3.10/site-packages (from matplotlib) (1.4.4)\nRequirement already satisfied: packaging>=20.0 in /opt/conda/lib/python3.10/site-packages (from matplotlib) (21.3)\nRequirement already satisfied: pillow>=6.2.0 in /opt/conda/lib/python3.10/site-packages (from matplotlib) (10.1.0)\nRequirement already satisfied: pyparsing>=2.3.1 in /opt/conda/lib/python3.10/site-packages (from matplotlib) (3.0.9)\nRequirement already satisfied: python-dateutil>=2.7 in /opt/conda/lib/python3.10/site-packages (from matplotlib) (2.8.2)\nRequirement already satisfied: backcall in /opt/conda/lib/python3.10/site-packages (from ipython) (0.2.0)\nRequirement already satisfied: decorator in /opt/conda/lib/python3.10/site-packages (from ipython) (5.1.1)\nRequirement already satisfied: jedi>=0.16 in /opt/conda/lib/python3.10/site-packages (from ipython) (0.19.0)\nRequirement already satisfied: matplotlib-inline in /opt/conda/lib/python3.10/site-packages (from ipython) (0.1.6)\nRequirement already satisfied: pickleshare in /opt/conda/lib/python3.10/site-packages (from ipython) (0.7.5)\nRequirement already satisfied: prompt-toolkit!=3.0.37,<3.1.0,>=3.0.30 in /opt/conda/lib/python3.10/site-packages (from ipython) (3.0.39)\nRequirement already satisfied: pygments>=2.4.0 in /opt/conda/lib/python3.10/site-packages (from ipython) (2.16.1)\nRequirement already satisfied: stack-data in /opt/conda/lib/python3.10/site-packages (from ipython) (0.6.2)\nRequirement already satisfied: traitlets>=5 in /opt/conda/lib/python3.10/site-packages (from ipython) (5.9.0)\nRequirement already satisfied: pexpect>4.3 in /opt/conda/lib/python3.10/site-packages (from ipython) (4.8.0)\nRequirement already satisfied: joblib>=1.1.1 in /opt/conda/lib/python3.10/site-packages (from scikit-learn) (1.3.2)\nRequirement already satisfied: threadpoolctl>=2.0.0 in /opt/conda/lib/python3.10/site-packages (from scikit-learn) (3.2.0)\nRequirement already satisfied: pytz>=2020.1 in /opt/conda/lib/python3.10/site-packages (from pandas) (2023.3)\nRequirement already satisfied: tzdata>=2022.1 in /opt/conda/lib/python3.10/site-packages (from pandas) (2023.3)\nRequirement already satisfied: parso<0.9.0,>=0.8.3 in /opt/conda/lib/python3.10/site-packages (from jedi>=0.16->ipython) (0.8.3)\nRequirement already satisfied: ptyprocess>=0.5 in /opt/conda/lib/python3.10/site-packages (from pexpect>4.3->ipython) (0.7.0)\nRequirement already satisfied: wcwidth in /opt/conda/lib/python3.10/site-packages (from prompt-toolkit!=3.0.37,<3.1.0,>=3.0.30->ipython) (0.2.6)\nRequirement already satisfied: six>=1.5 in /opt/conda/lib/python3.10/site-packages (from python-dateutil>=2.7->matplotlib) (1.16.0)\nRequirement already satisfied: executing>=1.2.0 in /opt/conda/lib/python3.10/site-packages (from stack-data->ipython) (1.2.0)\nRequirement already satisfied: asttokens>=2.1.0 in /opt/conda/lib/python3.10/site-packages (from stack-data->ipython) (2.2.1)\nRequirement already satisfied: pure-eval in /opt/conda/lib/python3.10/site-packages (from stack-data->ipython) (0.2.2)\n","output_type":"stream"}]},{"cell_type":"code","source":"from sklearn.linear_model import LogisticRegression\nfrom sklearn.model_selection import train_test_split\n\ndata = [\n {\n 'age': 66,\n 'num_of_cars': 1,\n 'owns_house': 'yes',\n 'num_of_childs': 2,\n 'marital_status': 'widowed',\n 'owns_dog': 'no',\n 'bought_boat': 'yes'\n },\n {\n 'age': 52,\n 'num_of_cars': 2,\n 'owns_house': 'yes',\n 'num_of_childs': 3,\n 'marital_status': 'married',\n 'owns_dog': 'no',\n 'bought_boat': 'yes'\n },\n {\n 'age': 22,\n 'num_of_cars': 0,\n 'owns_house': 'no',\n 'num_of_childs': 0,\n 'marital_status': 'married',\n 'owns_dog': 'yes',\n 'bought_boat': 'no'\n },\n {\n 'age': 25,\n 'num_of_cars': 1,\n 'owns_house': 'no',\n 'num_of_childs': 1,\n 'marital_status': 'single',\n 'owns_dog': 'no',\n 'bought_boat': 'no'\n },\n {\n 'age': 44,\n 'num_of_cars': 0,\n 'owns_house': 'no',\n 'num_of_childs': 2,\n 'marital_status': 'divorced',\n 'owns_dog': 'yes',\n 'bought_boat': 'no'\n },\n {\n 'age': 39,\n 'num_of_cars': 1,\n 'owns_house': 'yes',\n 'num_of_childs': 2,\n 'marital_status': 'married',\n 'owns_dog': 'yes',\n 'bought_boat': 'no'\n },\n {\n 'age': 26,\n 'num_of_cars': 1,\n 'owns_house': 'no',\n 'num_of_childs': 2,\n 'marital_status': 'single',\n 'owns_dog': 'no',\n 'bought_boat': 'no'\n },\n {\n 'age': 40,\n 'num_of_cars': 3,\n 'owns_house': 'yes',\n 'num_of_childs': 1,\n 'marital_status': 'married',\n 'owns_dog': 'yes',\n 'bought_boat': 'no'\n },\n {\n 'age': 53,\n 'num_of_cars': 2,\n 'owns_house': 'yes',\n 'num_of_childs': 2,\n 'marital_status': 'divorced',\n 'owns_dog': 'no',\n 'bought_boat': 'no'\n },\n {\n 'age': 64,\n 'num_of_cars': 2,\n 'owns_house': 'yes',\n 'num_of_childs': 3,\n 'marital_status': 'divorced',\n 'owns_dog': 'no',\n 'bought_boat': 'no'\n },\n {\n 'age': 58,\n 'num_of_cars': 2,\n 'owns_house': 'yes',\n 'num_of_childs': 2,\n 'marital_status': 'married',\n 'owns_dog': 'yes',\n 'bought_boat': 'yes'\n },\n {\n 'age': 33,\n 'num_of_cars': 1,\n 'owns_house': 'no',\n 'num_of_childs': 1,\n 'marital_status': 'single',\n 'owns_dog': 'no',\n 'bought_boat': 'no'\n }\n]\n\nflags = {\n 'single': 1,\n 'married': 2,\n 'divorced': 3,\n 'widowed': 4,\n 'no': 0,\n 'yes': 1\n}","metadata":{"execution":{"iopub.status.busy":"2023-12-16T22:58:01.940716Z","iopub.execute_input":"2023-12-16T22:58:01.941156Z","iopub.status.idle":"2023-12-16T22:58:02.757730Z","shell.execute_reply.started":"2023-12-16T22:58:01.941121Z","shell.execute_reply":"2023-12-16T22:58:02.756457Z"},"trusted":true},"execution_count":2,"outputs":[]},{"cell_type":"code","source":"def transform_data(data):\n out = {'x': [], 'y': []}\n for item in data:\n out['x'].append([\n item['age'],\n item['num_of_cars'],\n 1 if item['owns_house'] == 'yes' else 0,\n item['num_of_childs'],\n flags[item['marital_status']],\n 1 if item['owns_dog'] == 'yes' else 0\n ])\n out['y'].append(1 if item['bought_boat'] == 'yes' else 0)\n return out\n\n_data = transform_data(data)\nprint(_data)","metadata":{"execution":{"iopub.status.busy":"2023-12-16T22:58:06.524914Z","iopub.execute_input":"2023-12-16T22:58:06.526058Z","iopub.status.idle":"2023-12-16T22:58:06.535429Z","shell.execute_reply.started":"2023-12-16T22:58:06.526016Z","shell.execute_reply":"2023-12-16T22:58:06.533918Z"},"trusted":true},"execution_count":3,"outputs":[{"name":"stdout","text":"{'x': [[66, 1, 1, 2, 4, 0], [52, 2, 1, 3, 2, 0], [22, 0, 0, 0, 2, 1], [25, 1, 0, 1, 1, 0], [44, 0, 0, 2, 3, 1], [39, 1, 1, 2, 2, 1], [26, 1, 0, 2, 1, 0], [40, 3, 1, 1, 2, 1], [53, 2, 1, 2, 3, 0], [64, 2, 1, 3, 3, 0], [58, 2, 1, 2, 2, 1], [33, 1, 0, 1, 1, 0]], 'y': [1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0]}\n","output_type":"stream"}]},{"cell_type":"code","source":"X_train, X_test, y_train, y_test = train_test_split(_data['x'], _data['y'])\n\n# Train the model\nmodel = LogisticRegression()\nmodel.fit(X_train, y_train)\n\naccuracy = model.score(X_test, y_test)\n\nprint(accuracy)","metadata":{"execution":{"iopub.status.busy":"2023-12-16T22:58:56.442791Z","iopub.execute_input":"2023-12-16T22:58:56.443190Z","iopub.status.idle":"2023-12-16T22:58:56.467709Z","shell.execute_reply.started":"2023-12-16T22:58:56.443158Z","shell.execute_reply":"2023-12-16T22:58:56.466561Z"},"trusted":true},"execution_count":13,"outputs":[{"name":"stdout","text":"0.6666666666666666\n","output_type":"stream"}]},{"cell_type":"code","source":"inputs = [\n {\n 'age': 58,\n 'num_of_cars': 2,\n 'owns_house': 'yes',\n 'num_of_childs': 2,\n 'marital_status': 'married',\n 'owns_dog': 'yes'\n },\n {\n 'age': 33,\n 'num_of_cars': 1,\n 'owns_house': 'no',\n 'num_of_childs': 1,\n 'marital_status': 'single',\n 'owns_dog': 'no'\n }\n]\n\ndef transform_inputs(inputs):\n ins = []\n for inp in inputs:\n ins.append([\n inp['age'],\n inp['num_of_cars'],\n 1 if inp['owns_house'] == 'yes' else 0,\n inp['num_of_childs'],\n flags[inp['marital_status']],\n 1 if inp['owns_dog'] == 'yes' else 0\n ])\n return ins\n\ndef transform_prediction(predictions):\n out = []\n for prediction in predictions:\n out.append({\"buys_boat\": True} if prediction == 1 else {\"buys_boat\": False})\n return out\n\nprediction = model.predict(transform_inputs(inputs))\nprint(transform_prediction(prediction))","metadata":{"execution":{"iopub.status.busy":"2023-12-16T22:58:58.379727Z","iopub.execute_input":"2023-12-16T22:58:58.381033Z","iopub.status.idle":"2023-12-16T22:58:58.392885Z","shell.execute_reply.started":"2023-12-16T22:58:58.380964Z","shell.execute_reply":"2023-12-16T22:58:58.391697Z"},"trusted":true},"execution_count":14,"outputs":[{"name":"stdout","text":"[{'buys_boat': True}, {'buys_boat': False}]\n","output_type":"stream"}]}]} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment