数据挖掘快速入门教程详解.pptx

王屯屯学习情况汇报;相关领域; 韩嘉炜：数据挖掘概念与技术 认识数据，数据预处理，分类，聚类（初高级），离群点检测，数据挖掘的研究问题和未来发展。其他还有数据立方体技术等。 刘 冰：网络数据挖掘 关联规则挖掘，监督学习，半监督学习，无监督学习。其他还有网络信息挖掘，网络爬虫等 林轩田：机器学习 三大监督学习 Martin： 神经网络 三大神经网络结构，性能曲面，性能优化。其他的还有有监督的Hebb学习等经典的学习方法 ;数据挖掘过程;数据的表现形式;挖掘功能;用到的技术;如何构建模型;如何将数据分类;如何将数据聚类;看论文与动手结合; import pandas import numpy as np from sklearn.linear_model import LinearRegression from sklearn.linear_model import LogisticRegression from sklearn.cross_validation import KFold from sklearn import cross_validation titanic = pandas.read_csv(../input/train.csv) titanic[Age] = titanic[Age].fillna(titanic[Age].median()) titanic.loc[titanic[Sex] == male, Sex] = 0 titanic.loc[titanic[Sex] == female, Sex] = 1 titanic[Embarked] = titanic[Embarked].fillna(S) titanic.loc[titanic[Embarked] == S, Embarked] = 0 titanic.loc[titanic[Embarked] == C, Embarked] = 1 titanic.loc[titanic[Embarked] == Q, Embarked] = 2; predictors = [Pclass, Sex, Age, SibSp, Parch, Fare, Embarked] alg = LinearRegression() kf = KFold(titanic.shape[0], n_folds = 3, random_state = 1) predictions = [] for train, test in kf: train_predictors = (titanic[predictors].iloc[train,:]) train_target = titanic[Survived].iloc[train] alg.fit(train_predictors, train_target) test_predictions = alg.predict(titanic[predictors].iloc[test,:]) predictions.append(test_predictions) predictions = np.concatenate(predictions,axis = 0) predictions[predictions .5] = 1 predictions[predictions = .5] = 0 accuracy = 1 - sum(abs(predictions - titanic[Survived])) / len(predictions) print (Accuracy of Linear Regression on the training set is + str(accuracy)) alg = LogisticRegression(random_state = 1) scores = cross_validation.cross_val_score(alg, titanic[predictors], titanic[Survived], cv = 3) print (Accuracy of Logistic Regression using cross-validation on the training set is + str(scores.mean())) ; # Read the test set csv file. titanic_test = pandas.read_csv(../input/test.csv) # ====================Preprocessing the data===================== titanic_test[