Python sklearn数据分析中常用方法

一、数据处理

随机划分训练集和测试集：

from sklearn.model_selection import train_test_splitX_all = data_train.drop(['Survived', 'PassengerId'], axis=1) #只包含特征集，不包含预测目标y_all = data_train['Survived'] #只包含预测目标num_test = 0.20 # 测试集占据比例，，如果是整数的话就是样本的数量X_train, X_test, y_train, y_test = train_test_split(X_all, y_all, test_size=num_test, random_state=23)# random_state参数表示随机种子，如果为0或不填，每次随机产生的随机数组不同。

from sklearn.model_selection import StratifiedShuffleSplitsss = StratifiedShuffleSplit(n_splits=10, test_size=0.1, random_state=0)# sss对象用于划分数据集X = train[0::, 1::]# X为特征集y = train[0::, 0]# y为Label集for train_index, test_index in sss.split(X, y):    X_train, X_test = X[train_index], X[test_index]    y_train, y_test = y[train_index], y[test_index]

二、模型选择

# machine learningfrom sklearn.linear_model import LogisticRegressionfrom sklearn.svm import SVC, LinearSVCfrom sklearn.ensemble import RandomForestClassifierfrom sklearn.neighbors import KNeighborsClassifierfrom sklearn.naive_bayes import GaussianNBfrom sklearn.linear_model import Perceptronfrom sklearn.linear_model import SGDClassifierfrom sklearn.tree import DecisionTreeClassifier

逻辑回归：

logreg = LogisticRegression()logreg.fit(X_train, Y_train)Y_pred = logreg.predict(X_test)acc_log = round(logreg.score(X_train, Y_train) * 100, 2)acc_log

# 查看特征系数coeff_df = pd.DataFrame(train_df.columns.delete(0))coeff_df.columns = ['Feature']coeff_df["Correlation"] = pd.Series(logreg.coef_[0])coeff_df.sort_values(by='Correlation', ascending=False)

SVC支持向量机：

svc = SVC()svc.fit(X_train, Y_train)Y_pred = svc.predict(X_test)acc_svc = round(svc.score(X_train, Y_train) * 100, 2)

# # Linear SVC# linear_svc = LinearSVC()# linear_svc.fit(X_train, Y_train)# Y_pred = linear_svc.predict(X_test)# acc_linear_svc = round(linear_svc.score(X_train, Y_train) * 100, 2)# acc_linear_svc

K近邻学习KNN：

# knn = KNeighborsClassifier(n_neighbors = 3)# knn.fit(X_train, Y_train)# Y_pred = knn.predict(X_test)# acc_knn = round(knn.score(X_train, Y_train) * 100, 2)# acc_knn

朴素贝叶斯分类器：

# gaussian = GaussianNB()# gaussian.fit(X_train, Y_train)# Y_pred = gaussian.predict(X_test)# acc_gaussian = round(gaussian.score(X_train, Y_train) * 100, 2)# acc_gaussian

感知机：

# perceptron = Perceptron()# perceptron.fit(X_train, Y_train)# Y_pred = perceptron.predict(X_test)# acc_perceptron = round(perceptron.score(X_train, Y_train) * 100, 2)# acc_perceptron

随机梯度下降法：

# sgd = SGDClassifier()# sgd.fit(X_train, Y_train)# Y_pred = sgd.predict(X_test)# acc_sgd = round(sgd.score(X_train, Y_train) * 100, 2)# acc_sgd

决策树：

# # Decision Tree# decision_tree = DecisionTreeClassifier()# decision_tree.fit(X_train, Y_train)# Y_pred = decision_tree.predict(X_test)# acc_decision_tree = round(decision_tree.score(X_train, Y_train) * 100, 2)# acc_decision_tree

随机森林：

# # Random Forest# random_forest = RandomForestClassifier(n_estimators=100)# random_forest.fit(X_train, Y_train)# Y_pred = random_forest.predict(X_test)# random_forest.score(X_train, Y_train)# acc_random_forest = round(random_forest.score(X_train, Y_train) * 100, 2)# acc_random_forest

# 基于准确率搜索最佳参数的随机森林from sklearn.ensemble import RandomForestClassifierfrom sklearn.metrics import make_scorer, accuracy_scorefrom sklearn.model_selection import GridSearchCV# Choose the type of classifier. clf = RandomForestClassifier()# Choose some parameter combinations to tryparameters = {'n_estimators': [4, 6, 9],               'max_features': ['log2', 'sqrt','auto'],               'criterion': ['entropy', 'gini'],              'max_depth': [2, 3, 5, 10],               'min_samples_split': [2, 3, 5],              'min_samples_leaf': [1,5,8]             }# Type of scoring used to compare parameter combinationsacc_scorer = make_scorer(accuracy_score)# Run the grid searchgrid_obj = GridSearchCV(clf, parameters, scoring=acc_scorer)grid_obj = grid_obj.fit(X_train, y_train)# Set the clf to the best combination of parametersclf = grid_obj.best_estimator_# Fit the best algorithm to the data. clf.fit(X_train, y_train)

遍历模型方法：

import matplotlib.pyplot as pltimport seaborn as snsfrom sklearn.model_selection import StratifiedShuffleSplitfrom sklearn.metrics import accuracy_score, log_lossfrom sklearn.neighbors import KNeighborsClassifierfrom sklearn.svm import SVCfrom sklearn.tree import DecisionTreeClassifierfrom sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier, GradientBoostingClassifierfrom sklearn.naive_bayes import GaussianNBfrom sklearn.discriminant_analysis import LinearDiscriminantAnalysis, QuadraticDiscriminantAnalysisfrom sklearn.linear_model import LogisticRegressionclassifiers = [    KNeighborsClassifier(3),    SVC(probability=True),    DecisionTreeClassifier(),    RandomForestClassifier(),    AdaBoostClassifier(),    GradientBoostingClassifier(),    GaussianNB(),    LinearDiscriminantAnalysis(),    QuadraticDiscriminantAnalysis(),    LogisticRegression()]log_cols = ["Classifier", "Accuracy"]log      = pd.DataFrame(columns=log_cols)sss = StratifiedShuffleSplit(n_splits=10, test_size=0.1, random_state=0)# sss对象用于划分数据集X = train[0::, 1::]# X为特征集y = train[0::, 0]# y为Label集acc_dict = {}for train_index, test_index in sss.split(X, y):    X_train, X_test = X[train_index], X[test_index]    y_train, y_test = y[train_index], y[test_index]    for clf in classifiers:        name = clf.__class__.__name__        clf.fit(X_train, y_train)        train_predictions = clf.predict(X_test)        acc = accuracy_score(y_test, train_predictions)        if name in acc_dict:            acc_dict[name] += acc        else:            acc_dict[name] = accfor clf in acc_dict:    acc_dict[clf] = acc_dict[clf] / 10.0    # 计算平均准确率    log_entry = pd.DataFrame([[clf, acc_dict[clf]]], columns=log_cols)    log = log.append(log_entry)plt.xlabel('Accuracy')plt.title('Classifier Accuracy')sns.set_color_codes("muted")sns.barplot(x='Accuracy', y='Classifier', data=log, color="b")# 画条形图分析

叠加多层（2）模型教程

三、模型评估

使用k折交叉验证法：

from sklearn.cross_validation import KFolddef run_kfold(clf):    kf = KFold(891, n_folds=10)    outcomes = []    fold = 0    for train_index, test_index in kf:        fold += 1        X_train, X_test = X_all.values[train_index], X_all.values[test_index]        y_train, y_test = y_all.values[train_index], y_all.values[test_index]        clf.fit(X_train, y_train)        predictions = clf.predict(X_test)        accuracy = accuracy_score(y_test, predictions)        outcomes.append(accuracy)        print("Fold {0} accuracy: {1}".format(fold, accuracy))         mean_outcome = np.mean(outcomes)    print("Mean Accuracy: {0}".format(mean_outcome)) run_kfold(clf)

四、其他

保存模型：

Pickle:>>> import pickle>>> s = pickle.dumps(clf)>>> clf2 = pickle.loads(s)>>> clf2.predict(X[0:1])joblib:>>> from sklearn.externals import joblib>>> joblib.dump(clf, 'filename.pkl') >>> clf = joblib.load('filename.pkl')