Demo Project<\/p>\n\n\n\n
import pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\n\n# file from url as below\n# https:\/\/www.kaggle.com\/datasets\/erscodingzone\/user-datacsv\/\ndataset = pd.read_csv(\"User_Data.csv\")\n\n# input, \u6211\u5011\u4e3b\u8981\u662f\u770b\u5e74\u9f61 \u85aa\u8cc7 \u5c0d \u8cfc\u8cb7\u5546\u54c1\u7684 \u63a8\u7b97\nx = dataset.iloc[:, [2, 3]].values\n\n# output, \u8cb7: 1 \u6216\u662f\u4e0d\u8cb7: 0\ny = dataset.iloc[:, 4].values\n\n# Splitting The Dataset: Train and Test dataset, 75% for training, 25% testing data\nfrom sklearn.model_selection import train_test_split\n\nxtrain, xtest, ytrain, ytest = train_test_split(\n x, y, test_size=0.25, random_state=0)\n\nfrom sklearn.preprocessing import StandardScaler\n\nsc_x = StandardScaler()\nxtrain = sc_x.fit_transform(xtrain)\nxtest = sc_x.transform(xtest)\n# scale the age variable value because the salary vs age, the number is too different\nprint(xtrain[0:10, :])\n\nfrom sklearn.linear_model import LogisticRegression\n\n#Train The Model\nclassifier = LogisticRegression(random_state = 0)\nclassifier.fit(xtrain, ytrain)\n\n# After training the model, it is time to use it to do predictions on testing data.\ny_pred = classifier.predict(xtest)\n\n# Confusion Matrix\nfrom sklearn.metrics import confusion_matrix\n\ncm = confusion_matrix(ytest, y_pred)\nprint (\"Confusion Matrix : \\n\", cm)\n\nfrom sklearn.metrics import accuracy_score\n\nprint(\"Accuracy : \", accuracy_score(ytest, y_pred))\n\n# Visualizing the performance of our model.\nfrom matplotlib.colors import ListedColormap\n\nX_set, y_set = xtest, ytest\nX1, X2 = np.meshgrid(np.arange(start=X_set[:, 0].min() - 1,\n stop=X_set[:, 0].max() + 1, step=0.01),\n np.arange(start=X_set[:, 1].min() - 1,\n stop=X_set[:, 1].max() + 1, step=0.01))\n\n# \u586b\u6eff\u7684\u8272\u584a\nplt.contourf(X1, X2, classifier.predict(\n np.array([X1.ravel(), X2.ravel()]).T).reshape(\n X1.shape), alpha=0.75, cmap=ListedColormap(('red', 'green')))\n\nplt.xlim(X1.min(), X1.max())\nplt.ylim(X2.min(), X2.max())\n\n#paint dots\nfor i, j in enumerate(np.unique(y_set)):\n plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1],\n c=ListedColormap(('red', 'green'))(i), label=j)\n\nplt.title('Classifier (Test set)')\nplt.xlabel('Age')\nplt.ylabel('Estimated Salary')\nplt.legend()\nplt.show()\n<\/code><\/pre>\n\n\n\nUser_Data.csv, \u8acb\u5230\u9019\u908a\u4e0b\u8f09 DOWNLOAD<\/a><\/p>\n\n\n\n