机器学习实战python代码总结

 

把之前的自己写的笔记云保存一下

pandas库	读数据	import pandas as pd pd.read_csv('breast-cancer-wisconsin.data')
numpy库	矩阵计算	import numpy as np X = np.array(df.drop(['class'], 1)) Y = np.array(df['class'])
knn	使用scikit-learn中k邻近算法 neighbors.KNeighborsClassifier()	from sklearn import cross_validation, neighbors X_trian,X_test,Y_train,Y_test = cross_validation.train_test_split(X, Y, test_size=0.2) clf = neighbors.KNeighborsClassifier() clf.fit(X_trian, Y_train)
math库	计算log	from math import log
decision tree 决策树分类	rom sklearn import tree tree.DecisionTreeClassifier()	>>> from sklearn import tree >>> X = [[0, 0], [1, 1]] >>> Y = [0, 1] >>> clf = tree.DecisionTreeClassifier() >>> clf = clf.fit(X, Y)
matplotlib库	画图	import matplotlib.pyplot as plt import numpy as np np.random.seed(19680801) data = np.random.randn(2, 100) fig, axs = plt.subplots(2, 2, figsize=(5, 5)) plt.show()
朴素bayes	from sklearn import datasets	>>> from sklearn import datasets >>> iris = datasets.load_iris() >>> from sklearn.naive_bayes import GaussianNB >>> gnb = GaussianNB() >>> y_pred = gnb.fit(iris.data,