{ "cells": [ { "cell_type": "code", "execution_count": 17, "id": "36ac21fc", "metadata": {}, "outputs": [], "source": [ "# Import dependencies and packages neededfrom sklearn import datasets\n", "from sklearn.svm import SVC\n", "from sklearn.model_selection import train_test_split\n", "import numpy as np\n", "import pandas as pd\n", "import seaborn as sn\n", "import matplotlib.pyplot as plt" ] }, { "cell_type": "code", "execution_count": 18, "id": "3c07c748", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
PatientIdPregnanciesGlucoseBloodPressureSkinThicknessInsulinBMIDiabetesPedigreeFunctionAgeOutcome
0161487235033.60.627501
121856629026.60.351310
238183640023.30.672321
3418966239428.10.167210
450137403516843.12.288331
\n", "
" ], "text/plain": [ " PatientId Pregnancies Glucose BloodPressure SkinThickness Insulin \\\n", "0 1 6 148 72 35 0 \n", "1 2 1 85 66 29 0 \n", "2 3 8 183 64 0 0 \n", "3 4 1 89 66 23 94 \n", "4 5 0 137 40 35 168 \n", "\n", " BMI DiabetesPedigreeFunction Age Outcome \n", "0 33.6 0.627 50 1 \n", "1 26.6 0.351 31 0 \n", "2 23.3 0.672 32 1 \n", "3 28.1 0.167 21 0 \n", "4 43.1 2.288 33 1 " ] }, "execution_count": 18, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# import the dataset (stored in a variable)\n", "diabetes = pd.read_csv(\"diabetes.csv\")\n", "# Inspect the data(first five rows, or this can be changed by including how many rows within the brackets)\n", "diabetes.head()" ] }, { "cell_type": "code", "execution_count": 19, "id": "f5ce7fbc", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "Index: 614 entries, 60 to 102\n", "Data columns (total 10 columns):\n", " # Column Non-Null Count Dtype \n", "--- ------ -------------- ----- \n", " 0 PatientId 614 non-null int64 \n", " 1 Pregnancies 614 non-null int64 \n", " 2 Glucose 614 non-null int64 \n", " 3 BloodPressure 614 non-null int64 \n", " 4 SkinThickness 614 non-null int64 \n", " 5 Insulin 614 non-null int64 \n", " 6 BMI 614 non-null float64\n", " 7 DiabetesPedigreeFunction 614 non-null float64\n", " 8 Age 614 non-null int64 \n", " 9 Outcome 614 non-null int64 \n", "dtypes: float64(2), int64(8)\n", "memory usage: 52.8 KB\n" ] } ], "source": [ "# split the data into train and test using the SciKitLearn package\n", "from sklearn.model_selection import train_test_split\n", "train,test=train_test_split(diabetes,test_size=0.2,random_state=42)\n", "# view the information\n", "train.info()" ] }, { "cell_type": "code", "execution_count": 20, "id": "9c236d8a", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "Index: 154 entries, 668 to 462\n", "Data columns (total 8 columns):\n", " # Column Non-Null Count Dtype \n", "--- ------ -------------- ----- \n", " 0 Pregnancies 154 non-null int64 \n", " 1 Glucose 154 non-null int64 \n", " 2 BloodPressure 154 non-null int64 \n", " 3 SkinThickness 154 non-null int64 \n", " 4 Insulin 154 non-null int64 \n", " 5 BMI 154 non-null float64\n", " 6 DiabetesPedigreeFunction 154 non-null float64\n", " 7 Age 154 non-null int64 \n", "dtypes: float64(2), int64(6)\n", "memory usage: 10.8 KB\n" ] } ], "source": [ "# Ensure only labels are saved in y variables\n", "y_train=train['Outcome']\n", "y_test=test['Outcome']\n", "#drop the unwanted / irrelevant columns, features are stored in X variables\n", "X_train=train.drop(['PatientId','Outcome'],axis=1)\n", "X_test=test.drop(['PatientId','Outcome'],axis=1)\n", "# view the information\n", "X_test.info()" ] }, { "cell_type": "code", "execution_count": 21, "id": "cf217602", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'C': 1.0,\n", " 'break_ties': False,\n", " 'cache_size': 200,\n", " 'class_weight': None,\n", " 'coef0': 0.0,\n", " 'decision_function_shape': 'ovr',\n", " 'degree': 3,\n", " 'gamma': 'scale',\n", " 'kernel': 'rbf',\n", " 'max_iter': -1,\n", " 'probability': False,\n", " 'random_state': None,\n", " 'shrinking': True,\n", " 'tol': 0.001,\n", " 'verbose': False}" ] }, "execution_count": 21, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# this step is just to demonstrate the adjustable parameters within the algorithm and not a necessary step\n", "SVC().get_params()" ] }, { "cell_type": "code", "execution_count": 22, "id": "3f4c8504", "metadata": {}, "outputs": [], "source": [ "# # this step is just to demonstrate the api methods and not a necessary step\n", "# dir(SVC)" ] }, { "cell_type": "code", "execution_count": 23, "id": "25ec0839", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
SVC()
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" ], "text/plain": [ "SVC()" ] }, "execution_count": 23, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Create a model for Support Vector (Machine) Classifier using default parameters\n", "model = SVC()\n", "# fit the data to the model, both features and labels to train it\n", "model.fit(X_train, y_train)" ] }, { "cell_type": "code", "execution_count": 24, "id": "59cf09a6", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0,\n", " 0, 0, 0, 1, 0, 0, 0, 0, 1, 1, 1, 1, 0, 1, 1, 0, 0, 1, 0, 0, 0, 0,\n", " 0, 1, 0, 0, 0, 1, 0, 1, 1, 0, 0, 0, 1, 0, 0, 1, 1, 0, 0, 0, 0, 1,\n", " 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 1, 0,\n", " 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 0,\n", " 0, 1, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1,\n", " 0, 0, 1, 0, 0, 1, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0],\n", " dtype=int64)" ] }, "execution_count": 24, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# use the model to classify the datapoints within the test set\n", "y_pred2=model.predict(X_test)\n", "# print predicted classifications\n", "y_pred2" ] }, { "cell_type": "code", "execution_count": 25, "id": "606707f8", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "668 0\n", "324 0\n", "624 0\n", "690 0\n", "473 0\n", " ..\n", "355 1\n", "534 0\n", "344 0\n", "296 1\n", "462 0\n", "Name: Outcome, Length: 154, dtype: int64" ] }, "execution_count": 25, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# print test labels (ground truth) that is compared to classifier\n", "y_test" ] }, { "cell_type": "code", "execution_count": 26, "id": "fb8d51eb", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[[87 12]\n", " [24 31]]\n", " precision recall f1-score support\n", "\n", " 0 0.784 0.879 0.829 99\n", " 1 0.721 0.564 0.633 55\n", "\n", " accuracy 0.766 154\n", " macro avg 0.752 0.721 0.731 154\n", "weighted avg 0.761 0.766 0.759 154\n", "\n" ] } ], "source": [ "# display the metrics of the model's classification through confusion matrix and classification report\n", "# (accuracy / precision / recall / f1)\n", "from sklearn import metrics\n", "print(metrics.confusion_matrix(y_test, y_pred2))\n", "\n", "\n", "print(metrics.classification_report(y_test, y_pred2, digits=3))" ] }, { "cell_type": "code", "execution_count": 27, "id": "a1096778", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " Actual Predicted\n", "668 0 0\n", "324 0 0\n", "624 0 0\n", "690 0 0\n", "473 0 0\n", ".. ... ...\n", "355 1 1\n", "534 0 0\n", "344 0 0\n", "296 1 0\n", "462 0 0\n", "\n", "[154 rows x 2 columns]\n" ] } ], "source": [ "# use Pandas to create a dataframe to view the ground truth and classifications side by side\n", "data = {'Actual': y_test,\n", " 'Predicted': y_pred2}\n", "df = pd.DataFrame(data)\n", "print(df)" ] }, { "cell_type": "code", "execution_count": 28, "id": "e5d198fa", "metadata": {}, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ " precision recall f1-score support\n", "\n", " 0 0.784 0.879 0.829 99\n", " 1 0.721 0.564 0.633 55\n", "\n", " accuracy 0.766 154\n", " macro avg 0.752 0.721 0.731 154\n", "weighted avg 0.761 0.766 0.759 154\n", "\n" ] } ], "source": [ "# Use Seaborn to create a confusion matrix heatmap and MatPlotLib to display\n", "confusion_matrix = pd.crosstab(df['Actual'], df['Predicted'], rownames=['Actual'], colnames=['Predicted'])\n", "sn.heatmap(confusion_matrix, annot=True)\n", "plt.show()\n", "print(metrics.classification_report(y_test, y_pred2, digits=3))" ] }, { "cell_type": "code", "execution_count": 67, "id": "1da94641-5613-4ab2-b8dd-3416bf2298ae", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Accuracy: 0.7662337662337663\n" ] } ], "source": [ "from sklearn.metrics import accuracy_score\n", "accuracy_svm = accuracy_score(y_test, y_pred2)\n", "print(f\"Accuracy: {accuracy_svm}\")" ] }, { "cell_type": "markdown", "id": "ef72442e-63bb-4a75-a2ab-dd2aa8df1840", "metadata": {}, "source": [ "## Searching for the Best Hyperparameters with GridSearchCV" ] }, { "cell_type": "code", "execution_count": 54, "id": "fa40302a", "metadata": {}, "outputs": [], "source": [ "# Create an iterative grid search to tune the parameters\n", "import joblib\n", "from sklearn.model_selection import GridSearchCV" ] }, { "cell_type": "code", "execution_count": 55, "id": "275f6db5-7431-4231-a183-5410f7fd6040", "metadata": {}, "outputs": [], "source": [ "svm = SVC()\n", "# Set the parameters to be tuned\n", "parameters = {\n", " 'kernel' : ['linear', 'rbf'],\n", " 'C' : [0.1, 1, 10]\n", "}" ] }, { "cell_type": "code", "execution_count": 56, "id": "8b572a47-6b30-4e74-b3d0-26d2ae8f140a", "metadata": {}, "outputs": [ { "ename": "KeyboardInterrupt", "evalue": "", "output_type": "error", "traceback": [ "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[1;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)", "Cell \u001b[1;32mIn[56], line 2\u001b[0m\n\u001b[0;32m 1\u001b[0m grid_search \u001b[38;5;241m=\u001b[39m GridSearchCV(svm, parameters, cv\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m5\u001b[39m, scoring\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124maccuracy\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[1;32m----> 2\u001b[0m grid_search\u001b[38;5;241m.\u001b[39mfit(X_train, y_train)\n\u001b[0;32m 4\u001b[0m \u001b[38;5;66;03m# 最优参数和得分\u001b[39;00m\n\u001b[0;32m 5\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mBest parameters:\u001b[39m\u001b[38;5;124m\"\u001b[39m, grid_search\u001b[38;5;241m.\u001b[39mbest_params_)\n", "File \u001b[1;32mD:\\anaconda\\Lib\\site-packages\\sklearn\\base.py:1473\u001b[0m, in \u001b[0;36m_fit_context..decorator..wrapper\u001b[1;34m(estimator, *args, **kwargs)\u001b[0m\n\u001b[0;32m 1466\u001b[0m estimator\u001b[38;5;241m.\u001b[39m_validate_params()\n\u001b[0;32m 1468\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m config_context(\n\u001b[0;32m 1469\u001b[0m skip_parameter_validation\u001b[38;5;241m=\u001b[39m(\n\u001b[0;32m 1470\u001b[0m prefer_skip_nested_validation \u001b[38;5;129;01mor\u001b[39;00m global_skip_validation\n\u001b[0;32m 1471\u001b[0m )\n\u001b[0;32m 1472\u001b[0m ):\n\u001b[1;32m-> 1473\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m fit_method(estimator, \u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n", "File \u001b[1;32mD:\\anaconda\\Lib\\site-packages\\sklearn\\model_selection\\_search.py:1018\u001b[0m, in \u001b[0;36mBaseSearchCV.fit\u001b[1;34m(self, X, y, **params)\u001b[0m\n\u001b[0;32m 1012\u001b[0m results \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_format_results(\n\u001b[0;32m 1013\u001b[0m all_candidate_params, n_splits, all_out, all_more_results\n\u001b[0;32m 1014\u001b[0m )\n\u001b[0;32m 1016\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m results\n\u001b[1;32m-> 1018\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_run_search(evaluate_candidates)\n\u001b[0;32m 1020\u001b[0m \u001b[38;5;66;03m# multimetric is determined here because in the case of a callable\u001b[39;00m\n\u001b[0;32m 1021\u001b[0m \u001b[38;5;66;03m# self.scoring the return type is only known after calling\u001b[39;00m\n\u001b[0;32m 1022\u001b[0m first_test_score \u001b[38;5;241m=\u001b[39m all_out[\u001b[38;5;241m0\u001b[39m][\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtest_scores\u001b[39m\u001b[38;5;124m\"\u001b[39m]\n", "File \u001b[1;32mD:\\anaconda\\Lib\\site-packages\\sklearn\\model_selection\\_search.py:1572\u001b[0m, in \u001b[0;36mGridSearchCV._run_search\u001b[1;34m(self, evaluate_candidates)\u001b[0m\n\u001b[0;32m 1570\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_run_search\u001b[39m(\u001b[38;5;28mself\u001b[39m, evaluate_candidates):\n\u001b[0;32m 1571\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"Search all candidates in param_grid\"\"\"\u001b[39;00m\n\u001b[1;32m-> 1572\u001b[0m evaluate_candidates(ParameterGrid(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mparam_grid))\n", "File \u001b[1;32mD:\\anaconda\\Lib\\site-packages\\sklearn\\model_selection\\_search.py:964\u001b[0m, in \u001b[0;36mBaseSearchCV.fit..evaluate_candidates\u001b[1;34m(candidate_params, cv, more_results)\u001b[0m\n\u001b[0;32m 956\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mverbose \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m0\u001b[39m:\n\u001b[0;32m 957\u001b[0m \u001b[38;5;28mprint\u001b[39m(\n\u001b[0;32m 958\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mFitting \u001b[39m\u001b[38;5;132;01m{0}\u001b[39;00m\u001b[38;5;124m folds for each of \u001b[39m\u001b[38;5;132;01m{1}\u001b[39;00m\u001b[38;5;124m candidates,\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 959\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m totalling \u001b[39m\u001b[38;5;132;01m{2}\u001b[39;00m\u001b[38;5;124m fits\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;241m.\u001b[39mformat(\n\u001b[0;32m 960\u001b[0m n_splits, n_candidates, n_candidates \u001b[38;5;241m*\u001b[39m n_splits\n\u001b[0;32m 961\u001b[0m )\n\u001b[0;32m 962\u001b[0m )\n\u001b[1;32m--> 964\u001b[0m out \u001b[38;5;241m=\u001b[39m parallel(\n\u001b[0;32m 965\u001b[0m delayed(_fit_and_score)(\n\u001b[0;32m 966\u001b[0m clone(base_estimator),\n\u001b[0;32m 967\u001b[0m X,\n\u001b[0;32m 968\u001b[0m y,\n\u001b[0;32m 969\u001b[0m train\u001b[38;5;241m=\u001b[39mtrain,\n\u001b[0;32m 970\u001b[0m test\u001b[38;5;241m=\u001b[39mtest,\n\u001b[0;32m 971\u001b[0m parameters\u001b[38;5;241m=\u001b[39mparameters,\n\u001b[0;32m 972\u001b[0m split_progress\u001b[38;5;241m=\u001b[39m(split_idx, n_splits),\n\u001b[0;32m 973\u001b[0m candidate_progress\u001b[38;5;241m=\u001b[39m(cand_idx, n_candidates),\n\u001b[0;32m 974\u001b[0m \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mfit_and_score_kwargs,\n\u001b[0;32m 975\u001b[0m )\n\u001b[0;32m 976\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m (cand_idx, parameters), (split_idx, (train, test)) \u001b[38;5;129;01min\u001b[39;00m product(\n\u001b[0;32m 977\u001b[0m \u001b[38;5;28menumerate\u001b[39m(candidate_params),\n\u001b[0;32m 978\u001b[0m \u001b[38;5;28menumerate\u001b[39m(cv\u001b[38;5;241m.\u001b[39msplit(X, y, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mrouted_params\u001b[38;5;241m.\u001b[39msplitter\u001b[38;5;241m.\u001b[39msplit)),\n\u001b[0;32m 979\u001b[0m )\n\u001b[0;32m 980\u001b[0m )\n\u001b[0;32m 982\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(out) \u001b[38;5;241m<\u001b[39m \u001b[38;5;241m1\u001b[39m:\n\u001b[0;32m 983\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[0;32m 984\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mNo fits were performed. \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 985\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mWas the CV iterator empty? \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 986\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mWere there no candidates?\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 987\u001b[0m )\n", "File \u001b[1;32mD:\\anaconda\\Lib\\site-packages\\sklearn\\utils\\parallel.py:74\u001b[0m, in \u001b[0;36mParallel.__call__\u001b[1;34m(self, iterable)\u001b[0m\n\u001b[0;32m 69\u001b[0m config \u001b[38;5;241m=\u001b[39m get_config()\n\u001b[0;32m 70\u001b[0m iterable_with_config \u001b[38;5;241m=\u001b[39m (\n\u001b[0;32m 71\u001b[0m (_with_config(delayed_func, config), args, kwargs)\n\u001b[0;32m 72\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m delayed_func, args, kwargs \u001b[38;5;129;01min\u001b[39;00m iterable\n\u001b[0;32m 73\u001b[0m )\n\u001b[1;32m---> 74\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28msuper\u001b[39m()\u001b[38;5;241m.\u001b[39m\u001b[38;5;21m__call__\u001b[39m(iterable_with_config)\n", "File \u001b[1;32mD:\\anaconda\\Lib\\site-packages\\joblib\\parallel.py:1918\u001b[0m, in \u001b[0;36mParallel.__call__\u001b[1;34m(self, iterable)\u001b[0m\n\u001b[0;32m 1916\u001b[0m output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_get_sequential_output(iterable)\n\u001b[0;32m 1917\u001b[0m \u001b[38;5;28mnext\u001b[39m(output)\n\u001b[1;32m-> 1918\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m output \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mreturn_generator \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28mlist\u001b[39m(output)\n\u001b[0;32m 1920\u001b[0m \u001b[38;5;66;03m# Let's create an ID that uniquely identifies the current call. If the\u001b[39;00m\n\u001b[0;32m 1921\u001b[0m \u001b[38;5;66;03m# call is interrupted early and that the same instance is immediately\u001b[39;00m\n\u001b[0;32m 1922\u001b[0m \u001b[38;5;66;03m# re-used, this id will be used to prevent workers that were\u001b[39;00m\n\u001b[0;32m 1923\u001b[0m \u001b[38;5;66;03m# concurrently finalizing a task from the previous call to run the\u001b[39;00m\n\u001b[0;32m 1924\u001b[0m \u001b[38;5;66;03m# callback.\u001b[39;00m\n\u001b[0;32m 1925\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_lock:\n", "File \u001b[1;32mD:\\anaconda\\Lib\\site-packages\\joblib\\parallel.py:1847\u001b[0m, in \u001b[0;36mParallel._get_sequential_output\u001b[1;34m(self, iterable)\u001b[0m\n\u001b[0;32m 1845\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mn_dispatched_batches \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;241m1\u001b[39m\n\u001b[0;32m 1846\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mn_dispatched_tasks \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;241m1\u001b[39m\n\u001b[1;32m-> 1847\u001b[0m res \u001b[38;5;241m=\u001b[39m func(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[0;32m 1848\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mn_completed_tasks \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;241m1\u001b[39m\n\u001b[0;32m 1849\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mprint_progress()\n", "File \u001b[1;32mD:\\anaconda\\Lib\\site-packages\\sklearn\\utils\\parallel.py:136\u001b[0m, in \u001b[0;36m_FuncWrapper.__call__\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m 134\u001b[0m config \u001b[38;5;241m=\u001b[39m {}\n\u001b[0;32m 135\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m config_context(\u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mconfig):\n\u001b[1;32m--> 136\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfunction(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n", "File \u001b[1;32mD:\\anaconda\\Lib\\site-packages\\sklearn\\model_selection\\_validation.py:888\u001b[0m, in \u001b[0;36m_fit_and_score\u001b[1;34m(estimator, X, y, scorer, train, test, verbose, parameters, fit_params, score_params, return_train_score, return_parameters, return_n_test_samples, return_times, return_estimator, split_progress, candidate_progress, error_score)\u001b[0m\n\u001b[0;32m 886\u001b[0m estimator\u001b[38;5;241m.\u001b[39mfit(X_train, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mfit_params)\n\u001b[0;32m 887\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m--> 888\u001b[0m estimator\u001b[38;5;241m.\u001b[39mfit(X_train, y_train, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mfit_params)\n\u001b[0;32m 890\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m:\n\u001b[0;32m 891\u001b[0m \u001b[38;5;66;03m# Note fit time as time until error\u001b[39;00m\n\u001b[0;32m 892\u001b[0m fit_time \u001b[38;5;241m=\u001b[39m time\u001b[38;5;241m.\u001b[39mtime() \u001b[38;5;241m-\u001b[39m start_time\n", "File \u001b[1;32mD:\\anaconda\\Lib\\site-packages\\sklearn\\base.py:1473\u001b[0m, in \u001b[0;36m_fit_context..decorator..wrapper\u001b[1;34m(estimator, *args, **kwargs)\u001b[0m\n\u001b[0;32m 1466\u001b[0m estimator\u001b[38;5;241m.\u001b[39m_validate_params()\n\u001b[0;32m 1468\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m config_context(\n\u001b[0;32m 1469\u001b[0m skip_parameter_validation\u001b[38;5;241m=\u001b[39m(\n\u001b[0;32m 1470\u001b[0m prefer_skip_nested_validation \u001b[38;5;129;01mor\u001b[39;00m global_skip_validation\n\u001b[0;32m 1471\u001b[0m )\n\u001b[0;32m 1472\u001b[0m ):\n\u001b[1;32m-> 1473\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m fit_method(estimator, \u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n", "File \u001b[1;32mD:\\anaconda\\Lib\\site-packages\\sklearn\\svm\\_base.py:250\u001b[0m, in \u001b[0;36mBaseLibSVM.fit\u001b[1;34m(self, X, y, sample_weight)\u001b[0m\n\u001b[0;32m 247\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m[LibSVM]\u001b[39m\u001b[38;5;124m\"\u001b[39m, end\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m 249\u001b[0m seed \u001b[38;5;241m=\u001b[39m rnd\u001b[38;5;241m.\u001b[39mrandint(np\u001b[38;5;241m.\u001b[39miinfo(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mi\u001b[39m\u001b[38;5;124m\"\u001b[39m)\u001b[38;5;241m.\u001b[39mmax)\n\u001b[1;32m--> 250\u001b[0m fit(X, y, sample_weight, solver_type, kernel, random_seed\u001b[38;5;241m=\u001b[39mseed)\n\u001b[0;32m 251\u001b[0m \u001b[38;5;66;03m# see comment on the other call to np.iinfo in this file\u001b[39;00m\n\u001b[0;32m 253\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mshape_fit_ \u001b[38;5;241m=\u001b[39m X\u001b[38;5;241m.\u001b[39mshape \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mhasattr\u001b[39m(X, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mshape\u001b[39m\u001b[38;5;124m\"\u001b[39m) \u001b[38;5;28;01melse\u001b[39;00m (n_samples,)\n", "File \u001b[1;32mD:\\anaconda\\Lib\\site-packages\\sklearn\\svm\\_base.py:328\u001b[0m, in \u001b[0;36mBaseLibSVM._dense_fit\u001b[1;34m(self, X, y, sample_weight, solver_type, kernel, random_seed)\u001b[0m\n\u001b[0;32m 314\u001b[0m libsvm\u001b[38;5;241m.\u001b[39mset_verbosity_wrap(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mverbose)\n\u001b[0;32m 316\u001b[0m \u001b[38;5;66;03m# we don't pass **self.get_params() to allow subclasses to\u001b[39;00m\n\u001b[0;32m 317\u001b[0m \u001b[38;5;66;03m# add other parameters to __init__\u001b[39;00m\n\u001b[0;32m 318\u001b[0m (\n\u001b[0;32m 319\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msupport_,\n\u001b[0;32m 320\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msupport_vectors_,\n\u001b[0;32m 321\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_n_support,\n\u001b[0;32m 322\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdual_coef_,\n\u001b[0;32m 323\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mintercept_,\n\u001b[0;32m 324\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_probA,\n\u001b[0;32m 325\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_probB,\n\u001b[0;32m 326\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfit_status_,\n\u001b[0;32m 327\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_num_iter,\n\u001b[1;32m--> 328\u001b[0m ) \u001b[38;5;241m=\u001b[39m libsvm\u001b[38;5;241m.\u001b[39mfit(\n\u001b[0;32m 329\u001b[0m X,\n\u001b[0;32m 330\u001b[0m y,\n\u001b[0;32m 331\u001b[0m svm_type\u001b[38;5;241m=\u001b[39msolver_type,\n\u001b[0;32m 332\u001b[0m sample_weight\u001b[38;5;241m=\u001b[39msample_weight,\n\u001b[0;32m 333\u001b[0m class_weight\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mgetattr\u001b[39m(\u001b[38;5;28mself\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mclass_weight_\u001b[39m\u001b[38;5;124m\"\u001b[39m, np\u001b[38;5;241m.\u001b[39mempty(\u001b[38;5;241m0\u001b[39m)),\n\u001b[0;32m 334\u001b[0m kernel\u001b[38;5;241m=\u001b[39mkernel,\n\u001b[0;32m 335\u001b[0m C\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mC,\n\u001b[0;32m 336\u001b[0m nu\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mnu,\n\u001b[0;32m 337\u001b[0m probability\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mprobability,\n\u001b[0;32m 338\u001b[0m degree\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdegree,\n\u001b[0;32m 339\u001b[0m shrinking\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mshrinking,\n\u001b[0;32m 340\u001b[0m tol\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtol,\n\u001b[0;32m 341\u001b[0m cache_size\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcache_size,\n\u001b[0;32m 342\u001b[0m coef0\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcoef0,\n\u001b[0;32m 343\u001b[0m gamma\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_gamma,\n\u001b[0;32m 344\u001b[0m epsilon\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mepsilon,\n\u001b[0;32m 345\u001b[0m max_iter\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmax_iter,\n\u001b[0;32m 346\u001b[0m random_seed\u001b[38;5;241m=\u001b[39mrandom_seed,\n\u001b[0;32m 347\u001b[0m )\n\u001b[0;32m 349\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_warn_from_fit_status()\n", "\u001b[1;31mKeyboardInterrupt\u001b[0m: " ] } ], "source": [ "grid_search = GridSearchCV(svm, parameters, cv=5, scoring='accuracy')\n", "grid_search.fit(X_train, y_train)\n", "\n", "# 最优参数和得分\n", "print(\"Best parameters:\", grid_search.best_params_)\n", "print(\"Best accuracy:\", grid_search.best_score_)" ] }, { "cell_type": "code", "execution_count": 57, "id": "06a71bed", "metadata": {}, "outputs": [], "source": [ "# Create a function to show the results of the classifier under different parameter values\n", "def print_results(results):\n", " print('Best Parameters: {}\\n'.format(results.best_params_))\n", " \n", " means = results.cv_results_['mean_test_score']\n", " stds = results.cv_results_['std_test_score']\n", " for mean, std, params in zip(means, stds, results.cv_results_['params']):\n", " print('{} (+/-{}) for {}'.format(round(mean, 3), round(std * 2, 3), params))" ] }, { "cell_type": "code", "execution_count": 58, "id": "5404a42e", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "C:\\Users\\g1986\\AppData\\Local\\Temp\\ipykernel_18444\\3758584095.py:11: FutureWarning: Series.ravel is deprecated. The underlying array is already 1D, so ravel is not necessary. Use `to_numpy()` for conversion to a numpy array instead.\n", " cv.fit(X_train, y_train.ravel())\n" ] }, { "ename": "KeyboardInterrupt", "evalue": "", "output_type": "error", "traceback": [ "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[1;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)", "Cell \u001b[1;32mIn[58], line 11\u001b[0m\n\u001b[0;32m 9\u001b[0m cv \u001b[38;5;241m=\u001b[39m GridSearchCV(svm, parameters, cv\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m5\u001b[39m)\n\u001b[0;32m 10\u001b[0m \u001b[38;5;66;03m# fit the training data to the model\u001b[39;00m\n\u001b[1;32m---> 11\u001b[0m cv\u001b[38;5;241m.\u001b[39mfit(X_train, y_train\u001b[38;5;241m.\u001b[39mravel())\n\u001b[0;32m 12\u001b[0m \u001b[38;5;66;03m# display the model evaluation with the different paramter combination values (C value and kernel)\u001b[39;00m\n\u001b[0;32m 13\u001b[0m print_results(cv)\n", "File \u001b[1;32mD:\\anaconda\\Lib\\site-packages\\sklearn\\base.py:1473\u001b[0m, in \u001b[0;36m_fit_context..decorator..wrapper\u001b[1;34m(estimator, *args, **kwargs)\u001b[0m\n\u001b[0;32m 1466\u001b[0m estimator\u001b[38;5;241m.\u001b[39m_validate_params()\n\u001b[0;32m 1468\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m config_context(\n\u001b[0;32m 1469\u001b[0m skip_parameter_validation\u001b[38;5;241m=\u001b[39m(\n\u001b[0;32m 1470\u001b[0m prefer_skip_nested_validation \u001b[38;5;129;01mor\u001b[39;00m global_skip_validation\n\u001b[0;32m 1471\u001b[0m )\n\u001b[0;32m 1472\u001b[0m ):\n\u001b[1;32m-> 1473\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m fit_method(estimator, \u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n", "File \u001b[1;32mD:\\anaconda\\Lib\\site-packages\\sklearn\\model_selection\\_search.py:1018\u001b[0m, in \u001b[0;36mBaseSearchCV.fit\u001b[1;34m(self, X, y, **params)\u001b[0m\n\u001b[0;32m 1012\u001b[0m results \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_format_results(\n\u001b[0;32m 1013\u001b[0m all_candidate_params, n_splits, all_out, all_more_results\n\u001b[0;32m 1014\u001b[0m )\n\u001b[0;32m 1016\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m results\n\u001b[1;32m-> 1018\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_run_search(evaluate_candidates)\n\u001b[0;32m 1020\u001b[0m \u001b[38;5;66;03m# multimetric is determined here because in the case of a callable\u001b[39;00m\n\u001b[0;32m 1021\u001b[0m \u001b[38;5;66;03m# self.scoring the return type is only known after calling\u001b[39;00m\n\u001b[0;32m 1022\u001b[0m first_test_score \u001b[38;5;241m=\u001b[39m all_out[\u001b[38;5;241m0\u001b[39m][\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtest_scores\u001b[39m\u001b[38;5;124m\"\u001b[39m]\n", "File \u001b[1;32mD:\\anaconda\\Lib\\site-packages\\sklearn\\model_selection\\_search.py:1572\u001b[0m, in \u001b[0;36mGridSearchCV._run_search\u001b[1;34m(self, evaluate_candidates)\u001b[0m\n\u001b[0;32m 1570\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_run_search\u001b[39m(\u001b[38;5;28mself\u001b[39m, evaluate_candidates):\n\u001b[0;32m 1571\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"Search all candidates in param_grid\"\"\"\u001b[39;00m\n\u001b[1;32m-> 1572\u001b[0m evaluate_candidates(ParameterGrid(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mparam_grid))\n", "File \u001b[1;32mD:\\anaconda\\Lib\\site-packages\\sklearn\\model_selection\\_search.py:964\u001b[0m, in \u001b[0;36mBaseSearchCV.fit..evaluate_candidates\u001b[1;34m(candidate_params, cv, more_results)\u001b[0m\n\u001b[0;32m 956\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mverbose \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m0\u001b[39m:\n\u001b[0;32m 957\u001b[0m \u001b[38;5;28mprint\u001b[39m(\n\u001b[0;32m 958\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mFitting \u001b[39m\u001b[38;5;132;01m{0}\u001b[39;00m\u001b[38;5;124m folds for each of \u001b[39m\u001b[38;5;132;01m{1}\u001b[39;00m\u001b[38;5;124m candidates,\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 959\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m totalling \u001b[39m\u001b[38;5;132;01m{2}\u001b[39;00m\u001b[38;5;124m fits\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;241m.\u001b[39mformat(\n\u001b[0;32m 960\u001b[0m n_splits, n_candidates, n_candidates \u001b[38;5;241m*\u001b[39m n_splits\n\u001b[0;32m 961\u001b[0m )\n\u001b[0;32m 962\u001b[0m )\n\u001b[1;32m--> 964\u001b[0m out \u001b[38;5;241m=\u001b[39m parallel(\n\u001b[0;32m 965\u001b[0m delayed(_fit_and_score)(\n\u001b[0;32m 966\u001b[0m clone(base_estimator),\n\u001b[0;32m 967\u001b[0m X,\n\u001b[0;32m 968\u001b[0m y,\n\u001b[0;32m 969\u001b[0m train\u001b[38;5;241m=\u001b[39mtrain,\n\u001b[0;32m 970\u001b[0m test\u001b[38;5;241m=\u001b[39mtest,\n\u001b[0;32m 971\u001b[0m parameters\u001b[38;5;241m=\u001b[39mparameters,\n\u001b[0;32m 972\u001b[0m split_progress\u001b[38;5;241m=\u001b[39m(split_idx, n_splits),\n\u001b[0;32m 973\u001b[0m candidate_progress\u001b[38;5;241m=\u001b[39m(cand_idx, n_candidates),\n\u001b[0;32m 974\u001b[0m \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mfit_and_score_kwargs,\n\u001b[0;32m 975\u001b[0m )\n\u001b[0;32m 976\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m (cand_idx, parameters), (split_idx, (train, test)) \u001b[38;5;129;01min\u001b[39;00m product(\n\u001b[0;32m 977\u001b[0m \u001b[38;5;28menumerate\u001b[39m(candidate_params),\n\u001b[0;32m 978\u001b[0m \u001b[38;5;28menumerate\u001b[39m(cv\u001b[38;5;241m.\u001b[39msplit(X, y, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mrouted_params\u001b[38;5;241m.\u001b[39msplitter\u001b[38;5;241m.\u001b[39msplit)),\n\u001b[0;32m 979\u001b[0m )\n\u001b[0;32m 980\u001b[0m )\n\u001b[0;32m 982\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(out) \u001b[38;5;241m<\u001b[39m \u001b[38;5;241m1\u001b[39m:\n\u001b[0;32m 983\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[0;32m 984\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mNo fits were performed. \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 985\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mWas the CV iterator empty? \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 986\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mWere there no candidates?\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 987\u001b[0m )\n", "File \u001b[1;32mD:\\anaconda\\Lib\\site-packages\\sklearn\\utils\\parallel.py:74\u001b[0m, in \u001b[0;36mParallel.__call__\u001b[1;34m(self, iterable)\u001b[0m\n\u001b[0;32m 69\u001b[0m config \u001b[38;5;241m=\u001b[39m get_config()\n\u001b[0;32m 70\u001b[0m iterable_with_config \u001b[38;5;241m=\u001b[39m (\n\u001b[0;32m 71\u001b[0m (_with_config(delayed_func, config), args, kwargs)\n\u001b[0;32m 72\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m delayed_func, args, kwargs \u001b[38;5;129;01min\u001b[39;00m iterable\n\u001b[0;32m 73\u001b[0m )\n\u001b[1;32m---> 74\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28msuper\u001b[39m()\u001b[38;5;241m.\u001b[39m\u001b[38;5;21m__call__\u001b[39m(iterable_with_config)\n", "File \u001b[1;32mD:\\anaconda\\Lib\\site-packages\\joblib\\parallel.py:1918\u001b[0m, in \u001b[0;36mParallel.__call__\u001b[1;34m(self, iterable)\u001b[0m\n\u001b[0;32m 1916\u001b[0m output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_get_sequential_output(iterable)\n\u001b[0;32m 1917\u001b[0m \u001b[38;5;28mnext\u001b[39m(output)\n\u001b[1;32m-> 1918\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m output \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mreturn_generator \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28mlist\u001b[39m(output)\n\u001b[0;32m 1920\u001b[0m \u001b[38;5;66;03m# Let's create an ID that uniquely identifies the current call. If the\u001b[39;00m\n\u001b[0;32m 1921\u001b[0m \u001b[38;5;66;03m# call is interrupted early and that the same instance is immediately\u001b[39;00m\n\u001b[0;32m 1922\u001b[0m \u001b[38;5;66;03m# re-used, this id will be used to prevent workers that were\u001b[39;00m\n\u001b[0;32m 1923\u001b[0m \u001b[38;5;66;03m# concurrently finalizing a task from the previous call to run the\u001b[39;00m\n\u001b[0;32m 1924\u001b[0m \u001b[38;5;66;03m# callback.\u001b[39;00m\n\u001b[0;32m 1925\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_lock:\n", "File \u001b[1;32mD:\\anaconda\\Lib\\site-packages\\joblib\\parallel.py:1847\u001b[0m, in \u001b[0;36mParallel._get_sequential_output\u001b[1;34m(self, iterable)\u001b[0m\n\u001b[0;32m 1845\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mn_dispatched_batches \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;241m1\u001b[39m\n\u001b[0;32m 1846\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mn_dispatched_tasks \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;241m1\u001b[39m\n\u001b[1;32m-> 1847\u001b[0m res \u001b[38;5;241m=\u001b[39m func(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[0;32m 1848\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mn_completed_tasks \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;241m1\u001b[39m\n\u001b[0;32m 1849\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mprint_progress()\n", "File \u001b[1;32mD:\\anaconda\\Lib\\site-packages\\sklearn\\utils\\parallel.py:136\u001b[0m, in \u001b[0;36m_FuncWrapper.__call__\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m 134\u001b[0m config \u001b[38;5;241m=\u001b[39m {}\n\u001b[0;32m 135\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m config_context(\u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mconfig):\n\u001b[1;32m--> 136\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfunction(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n", "File \u001b[1;32mD:\\anaconda\\Lib\\site-packages\\sklearn\\model_selection\\_validation.py:888\u001b[0m, in \u001b[0;36m_fit_and_score\u001b[1;34m(estimator, X, y, scorer, train, test, verbose, parameters, fit_params, score_params, return_train_score, return_parameters, return_n_test_samples, return_times, return_estimator, split_progress, candidate_progress, error_score)\u001b[0m\n\u001b[0;32m 886\u001b[0m estimator\u001b[38;5;241m.\u001b[39mfit(X_train, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mfit_params)\n\u001b[0;32m 887\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m--> 888\u001b[0m estimator\u001b[38;5;241m.\u001b[39mfit(X_train, y_train, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mfit_params)\n\u001b[0;32m 890\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m:\n\u001b[0;32m 891\u001b[0m \u001b[38;5;66;03m# Note fit time as time until error\u001b[39;00m\n\u001b[0;32m 892\u001b[0m fit_time \u001b[38;5;241m=\u001b[39m time\u001b[38;5;241m.\u001b[39mtime() \u001b[38;5;241m-\u001b[39m start_time\n", "File \u001b[1;32mD:\\anaconda\\Lib\\site-packages\\sklearn\\base.py:1473\u001b[0m, in \u001b[0;36m_fit_context..decorator..wrapper\u001b[1;34m(estimator, *args, **kwargs)\u001b[0m\n\u001b[0;32m 1466\u001b[0m estimator\u001b[38;5;241m.\u001b[39m_validate_params()\n\u001b[0;32m 1468\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m config_context(\n\u001b[0;32m 1469\u001b[0m skip_parameter_validation\u001b[38;5;241m=\u001b[39m(\n\u001b[0;32m 1470\u001b[0m prefer_skip_nested_validation \u001b[38;5;129;01mor\u001b[39;00m global_skip_validation\n\u001b[0;32m 1471\u001b[0m )\n\u001b[0;32m 1472\u001b[0m ):\n\u001b[1;32m-> 1473\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m fit_method(estimator, \u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n", "File \u001b[1;32mD:\\anaconda\\Lib\\site-packages\\sklearn\\svm\\_base.py:250\u001b[0m, in \u001b[0;36mBaseLibSVM.fit\u001b[1;34m(self, X, y, sample_weight)\u001b[0m\n\u001b[0;32m 247\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m[LibSVM]\u001b[39m\u001b[38;5;124m\"\u001b[39m, end\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m 249\u001b[0m seed \u001b[38;5;241m=\u001b[39m rnd\u001b[38;5;241m.\u001b[39mrandint(np\u001b[38;5;241m.\u001b[39miinfo(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mi\u001b[39m\u001b[38;5;124m\"\u001b[39m)\u001b[38;5;241m.\u001b[39mmax)\n\u001b[1;32m--> 250\u001b[0m fit(X, y, sample_weight, solver_type, kernel, random_seed\u001b[38;5;241m=\u001b[39mseed)\n\u001b[0;32m 251\u001b[0m \u001b[38;5;66;03m# see comment on the other call to np.iinfo in this file\u001b[39;00m\n\u001b[0;32m 253\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mshape_fit_ \u001b[38;5;241m=\u001b[39m X\u001b[38;5;241m.\u001b[39mshape \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mhasattr\u001b[39m(X, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mshape\u001b[39m\u001b[38;5;124m\"\u001b[39m) \u001b[38;5;28;01melse\u001b[39;00m (n_samples,)\n", "File \u001b[1;32mD:\\anaconda\\Lib\\site-packages\\sklearn\\svm\\_base.py:328\u001b[0m, in \u001b[0;36mBaseLibSVM._dense_fit\u001b[1;34m(self, X, y, sample_weight, solver_type, kernel, random_seed)\u001b[0m\n\u001b[0;32m 314\u001b[0m libsvm\u001b[38;5;241m.\u001b[39mset_verbosity_wrap(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mverbose)\n\u001b[0;32m 316\u001b[0m \u001b[38;5;66;03m# we don't pass **self.get_params() to allow subclasses to\u001b[39;00m\n\u001b[0;32m 317\u001b[0m \u001b[38;5;66;03m# add other parameters to __init__\u001b[39;00m\n\u001b[0;32m 318\u001b[0m (\n\u001b[0;32m 319\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msupport_,\n\u001b[0;32m 320\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msupport_vectors_,\n\u001b[0;32m 321\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_n_support,\n\u001b[0;32m 322\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdual_coef_,\n\u001b[0;32m 323\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mintercept_,\n\u001b[0;32m 324\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_probA,\n\u001b[0;32m 325\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_probB,\n\u001b[0;32m 326\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfit_status_,\n\u001b[0;32m 327\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_num_iter,\n\u001b[1;32m--> 328\u001b[0m ) \u001b[38;5;241m=\u001b[39m libsvm\u001b[38;5;241m.\u001b[39mfit(\n\u001b[0;32m 329\u001b[0m X,\n\u001b[0;32m 330\u001b[0m y,\n\u001b[0;32m 331\u001b[0m svm_type\u001b[38;5;241m=\u001b[39msolver_type,\n\u001b[0;32m 332\u001b[0m sample_weight\u001b[38;5;241m=\u001b[39msample_weight,\n\u001b[0;32m 333\u001b[0m class_weight\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mgetattr\u001b[39m(\u001b[38;5;28mself\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mclass_weight_\u001b[39m\u001b[38;5;124m\"\u001b[39m, np\u001b[38;5;241m.\u001b[39mempty(\u001b[38;5;241m0\u001b[39m)),\n\u001b[0;32m 334\u001b[0m kernel\u001b[38;5;241m=\u001b[39mkernel,\n\u001b[0;32m 335\u001b[0m C\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mC,\n\u001b[0;32m 336\u001b[0m nu\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mnu,\n\u001b[0;32m 337\u001b[0m probability\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mprobability,\n\u001b[0;32m 338\u001b[0m degree\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdegree,\n\u001b[0;32m 339\u001b[0m shrinking\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mshrinking,\n\u001b[0;32m 340\u001b[0m tol\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtol,\n\u001b[0;32m 341\u001b[0m cache_size\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcache_size,\n\u001b[0;32m 342\u001b[0m coef0\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcoef0,\n\u001b[0;32m 343\u001b[0m gamma\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_gamma,\n\u001b[0;32m 344\u001b[0m epsilon\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mepsilon,\n\u001b[0;32m 345\u001b[0m max_iter\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmax_iter,\n\u001b[0;32m 346\u001b[0m random_seed\u001b[38;5;241m=\u001b[39mrandom_seed,\n\u001b[0;32m 347\u001b[0m )\n\u001b[0;32m 349\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_warn_from_fit_status()\n", "\u001b[1;31mKeyboardInterrupt\u001b[0m: " ] } ], "source": [ "# Create a model using the Support Vector Classifier / Machine algorithm\n", "svm = SVC()\n", "# Set the parameters to be tuned\n", "parameters = {\n", " 'kernel' : ['linear', 'rbf'],\n", " 'C' : [0.1, 1, 10]\n", "}\n", "# instantiate the grid search\n", "cv = GridSearchCV(svm, parameters, cv=5)\n", "# fit the training data to the model\n", "cv.fit(X_train, y_train.ravel())\n", "# display the model evaluation with the different paramter combination values (C value and kernel)\n", "print_results(cv)" ] }, { "cell_type": "code", "execution_count": null, "id": "4bfb84c7", "metadata": {}, "outputs": [], "source": [ "# show the best paramters for classification (not a necesary step unless you are saving best parameter models to compare)\n", "cv.best_estimator_.get_params()" ] }, { "cell_type": "code", "execution_count": null, "id": "05d7456f", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "markdown", "id": "33f56a89-cf7c-4697-9629-c04199149a09", "metadata": {}, "source": [ "# Decision Tree" ] }, { "cell_type": "markdown", "id": "472032f5-928c-49ab-8c8d-b2454195ea2a", "metadata": {}, "source": [] }, { "cell_type": "code", "execution_count": 32, "id": "9be2e2e6-cc3e-46e1-8ece-1d74db056ff4", "metadata": {}, "outputs": [], "source": [ "from sklearn import tree" ] }, { "cell_type": "code", "execution_count": 46, "id": "34ca2eef-60bd-4684-a9b8-5e9b8f9c9d41", "metadata": {}, "outputs": [], "source": [ "clfdt = tree.DecisionTreeClassifier()" ] }, { "cell_type": "code", "execution_count": 47, "id": "ce928256-da0d-451d-92fc-4054922f6169", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'ccp_alpha': 0.0,\n", " 'class_weight': None,\n", " 'criterion': 'gini',\n", " 'max_depth': None,\n", " 'max_features': None,\n", " 'max_leaf_nodes': None,\n", " 'min_impurity_decrease': 0.0,\n", " 'min_samples_leaf': 1,\n", " 'min_samples_split': 2,\n", " 'min_weight_fraction_leaf': 0.0,\n", " 'monotonic_cst': None,\n", " 'random_state': None,\n", " 'splitter': 'best'}" ] }, "execution_count": 47, "metadata": {}, "output_type": "execute_result" } ], "source": [ "clfdt.get_params()" ] }, { "cell_type": "code", "execution_count": 48, "id": "9f885ef0-746c-4390-8ce4-e6a1751747f1", "metadata": {}, "outputs": [], "source": [ "dt_clf = clfdt.fit(X_train, y_train)" ] }, { "cell_type": "code", "execution_count": 49, "id": "ee42bad2-2a9a-4d56-8468-ddb164c67835", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([1, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 1, 1, 1, 0, 0, 0, 0, 1, 0, 1, 0,\n", " 0, 0, 0, 1, 0, 0, 0, 0, 1, 1, 1, 1, 0, 1, 1, 0, 0, 1, 0, 1, 1, 1,\n", " 0, 1, 1, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0,\n", " 0, 1, 0, 1, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 1, 1, 1, 1, 1,\n", " 1, 0, 0, 0, 0, 1, 0, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 0, 1, 0, 1,\n", " 0, 0, 0, 1, 0, 1, 1, 0, 0, 1, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1,\n", " 0, 0, 1, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0],\n", " dtype=int64)" ] }, "execution_count": 49, "metadata": {}, "output_type": "execute_result" } ], "source": [ "y_pred_dt=dt_clf.predict(X_test)\n", "# print predicted classifications\n", "y_pred_dt" ] }, { "cell_type": "code", "execution_count": 59, "id": "43f0421d-24c4-4d05-9894-43e7591d616d", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Accuracy: 0.7532467532467533\n" ] } ], "source": [ "from sklearn.metrics import accuracy_score\n", "accuracy_dt = accuracy_score(y_test, y_pred_dt)\n", "print(f\"Accuracy: {accuracy_dt}\")" ] }, { "cell_type": "code", "execution_count": 60, "id": "f6836788-0055-4a1c-86d6-4c1c95d4e2ac", "metadata": {}, "outputs": [], "source": [ "from sklearn.model_selection import GridSearchCV" ] }, { "cell_type": "code", "execution_count": 61, "id": "4d6b2a8c-e347-456e-8140-fd03540f44fe", "metadata": {}, "outputs": [], "source": [ "param_grid = {\n", " 'criterion': ['gini', 'entropy', 'log_loss'],\n", " 'max_depth': [None, 3, 5, 10],\n", " 'min_samples_split': [2, 5, 10],\n", " 'min_samples_leaf': [1, 2, 4]\n", "}" ] }, { "cell_type": "code", "execution_count": 62, "id": "c6bbd9a1-149e-41ea-8821-2f778da8936d", "metadata": {}, "outputs": [], "source": [ "clfdt = tree.DecisionTreeClassifier()" ] }, { "cell_type": "code", "execution_count": 63, "id": "92c36b6d-f91a-48fe-b953-6d6f25894fc1", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Best parameters: {'criterion': 'gini', 'max_depth': 3, 'min_samples_leaf': 1, 'min_samples_split': 2}\n", "Best accuracy: 0.759016393442623\n" ] } ], "source": [ "grid_search = GridSearchCV(clfdt, param_grid, cv=5, scoring='accuracy')\n", "grid_search.fit(X_train, y_train)\n", "\n", "# 最优参数和得分\n", "print(\"Best parameters:\", grid_search.best_params_)\n", "print(\"Best accuracy:\", grid_search.best_score_)" ] }, { "cell_type": "markdown", "id": "b691d410-c1f7-419e-9c3f-24f0d55545db", "metadata": {}, "source": [ "# NaiveBayes " ] }, { "cell_type": "markdown", "id": "5cb737da-8ca9-43b7-8b39-c3f0b4f02d1b", "metadata": {}, "source": [] }, { "cell_type": "code", "execution_count": 38, "id": "6881fb78-9b6d-441c-88ba-91ad3a30c9b9", "metadata": {}, "outputs": [], "source": [ "from sklearn.naive_bayes import GaussianNB" ] }, { "cell_type": "code", "execution_count": 39, "id": "74a71c68-21c3-43d2-9bb7-35bf0a4e5b0b", "metadata": {}, "outputs": [], "source": [ "bys_clf = GaussianNB()" ] }, { "cell_type": "code", "execution_count": 68, "id": "818c1ddc-126e-4ee3-a79a-24a4846d7f09", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'priors': None, 'var_smoothing': 1e-09}" ] }, "execution_count": 68, "metadata": {}, "output_type": "execute_result" } ], "source": [ "bys_clf.get_params()" ] }, { "cell_type": "code", "execution_count": 40, "id": "4c00ba34-74a5-4df1-ba7d-fcc85b816cea", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
GaussianNB()
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" ], "text/plain": [ "GaussianNB()" ] }, "execution_count": 40, "metadata": {}, "output_type": "execute_result" } ], "source": [ "bys_clf.fit(X_train, y_train)" ] }, { "cell_type": "code", "execution_count": 41, "id": "26dc2f1d-cda6-4d18-99a5-667d8dfc0a22", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([0, 0, 0, 0, 1, 1, 0, 1, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0,\n", " 1, 0, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 0, 0, 0, 1,\n", " 0, 1, 1, 0, 0, 1, 0, 1, 1, 0, 0, 0, 1, 0, 0, 1, 1, 0, 1, 1, 0, 1,\n", " 0, 1, 0, 1, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 1, 0,\n", " 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 1, 0, 0, 1, 0, 1,\n", " 0, 0, 0, 1, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 1, 1, 1, 1, 1,\n", " 0, 1, 1, 0, 0, 1, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0],\n", " dtype=int64)" ] }, "execution_count": 41, "metadata": {}, "output_type": "execute_result" } ], "source": [ "y_pred_bys=bys_clf.predict(X_test)\n", "# print predicted classifications\n", "y_pred_bys" ] }, { "cell_type": "code", "execution_count": 71, "id": "d3f14cee-d304-48a4-86d9-5a9fa520de45", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Accuracy: 0.7662337662337663\n" ] } ], "source": [ "accuracy_bys = accuracy_score(y_test, y_pred_bys)\n", "print(f\"Accuracy: {accuracy_bys}\")" ] }, { "cell_type": "code", "execution_count": null, "id": "32df4358-ed74-4d29-addf-6ca08cfbf025", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": 64, "id": "c6f94c66-4ef2-48dc-b5de-3a5f8c496024", "metadata": {}, "outputs": [], "source": [ "param_grid_bys = {\n", " 'var_smoothing': [1e-11, 1e-10, 1e-9, 1e-8, 1e-7]\n", "}" ] }, { "cell_type": "code", "execution_count": 65, "id": "abc7a409-7533-4a9d-93fc-f8c1ca0794f0", "metadata": {}, "outputs": [], "source": [ "bys_clf = GaussianNB()" ] }, { "cell_type": "code", "execution_count": 72, "id": "f444fa9a-1b00-4d9c-981e-009e923c6bdf", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Best parameters: {'var_smoothing': 1e-11}\n", "Best accuracy: 0.752472344395575\n" ] } ], "source": [ "grid_search = GridSearchCV(bys_clf, param_grid_bys, cv=5, scoring='accuracy')\n", "grid_search.fit(X_train, y_train)\n", "\n", "# 最优参数和得分\n", "print(\"Best parameters:\", grid_search.best_params_)\n", "print(\"Best accuracy:\", grid_search.best_score_)" ] }, { "cell_type": "markdown", "id": "d105e676-f417-4b03-b21d-74d1b52d474b", "metadata": {}, "source": [ "# Summary and Conclusion" ] }, { "cell_type": "markdown", "id": "433777c4-445e-451c-b2de-bdc858dae981", "metadata": {}, "source": [ "By comparing the three classification algorithms, the classification accuracy is roughly the same. However, the naive Bayes classifier has too few adjustable parameters, which may result in an insignificant optimization effect." ] }, { "cell_type": "code", "execution_count": null, "id": "f1a9fe59-25f8-4528-93b1-bea00ffc9f52", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python [conda env:base] *", "language": "python", "name": "conda-base-py" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.12.7" } }, "nbformat": 4, "nbformat_minor": 5 }