学习机器学习基础算法总结

from sklearn.naive_bayes import BernoulliNB from sklearn.naive_bayes import GaussianNB from sklearn.datasets import make_blobs from sklearn.model_selection import train_test_split from sklearn.preprocessing import LabelEncoder from sklearn.naive_bayes import MultinomialNB from sklearn.model_selection import learning_curve from sklearn.model_selection import ShuffleSplit import numpy as np import matplotlib.pyplot as plt import pandas as pd mushroom = pd.read_csv("../data/mushrooms.csv") print(mushroom.head()) print(mushroom.isnull().sum()) print(mushroom['class'].unique()) # 数据预处理 label_encoder = LabelEncoder() for col in mushroom.columns: mushroom[col] = label_encoder.fit_transform(mushroom[col]) print(mushroom.head()) # 训练模型 X = mushroom.iloc[:, 1:23] y = mushroom.iloc[:, 0] X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42) mnb = MultinomialNB() mnb.fit(X_train, y_train) print(mnb.score(X_train, y_train)) print(mnb.score(X_test, y_test)) # 查看样本数量对于样本的影响 def plot_learning_curve(estimator, title, X, y, ylim=None, cv=None, n_jobs=-1, train_sizes=np.linspace(.1, 1.0, 5)): plt.figure() plt.title(title) if ylim is not None: plt.ylim(* ylim) plt.xlabel('Training examples') plt.ylabel('Score') train_sizes, train_scores, test_scores = learning_curve(estimator, X, y, cv=cv, n_jobs=n_jobs, train_sizes=train_sizes) train_scores_mean = np.mean(train_scores, axis=1) test_scores_mean = np.mean(test_scores, axis=1) plt.grid() plt.plot(train_sizes, train_scores_mean, 'o-', color='r', label='Training score') plt.plot(train_sizes, test_scores_mean, 'o-', color='r', label='Cross-validation score') plt.legend(loc='lower right') return plt cv = ShuffleSplit(n_splits=30, test_size=0.3, random_state=28) estimators = [MultinomialNB(), GaussianNB()] for estimator in estimators: title = estimator plot_learning_curve(estimator, title, X, y, ylim=(0.5, 1.0), cv=cv, n_jobs=-1) plt.show()