scikit-learn的核心用法

pip install -U scikit-learn

conda install scikit-learn

conda update scikit-learn

conda remove scikit-learn

from sklearn import datasets
import matplotlib.pyplot as plt

# 鸢尾花数据演示
iris = datasets.load_iris()
features = iris.data
target = iris.target
print(features.shape,target.shape)
print(iris.feature_names)

# 手写数字图片演示
digits = datasets.load_digits()
print(digits.data.shape)
plt.gray()
plt.imshow(digits.images[2])
plt.show()

# 生成圆形数据
x, y = datasets.make_circles(n_samples=15000, shuffle=True, noise=0.03)
plt.scatter(x[:, 0], x[:, 1], c=y, s=7)
plt.show()

# 生成瑞士卷型数据
X, t = datasets.make_swiss_roll(n_samples=2000, noise=0.1)
fig = plt.figure()
ax = fig.add_subplot(111, projection='3d')
ax.scatter(X[:, 0], X[:, 1], X[:, 2], c=t, cmap=plt.cm.Spectral,edgecolors='black')
plt.show()

# 展示示例图片
img = datasets.load_sample_image('flower.jpg')
print(img.shape)
plt.imshow(img)
plt.show()

import numpy as np
from sklearn import preprocessing

#标准化：将数据转换为均值为0，方差为1的数据，即标注正态分布的数据
x = np.array([[1,-1,2],[2,0,0],[0,1,-1]])
x_scale = preprocessing.scale(x)
print(x_scale.mean(axis=0),x_scale.std(axis=0))

std_scale = preprocessing.StandardScaler().fit(x)
x_std = std_scale.transform(x)
print(x_std.mean(axis=0),x_std.std(axis=0))

#将数据缩放至给定范围（0-1）
mm_scale = preprocessing.MinMaxScaler()
x_mm = mm_scale.fit_transform(x)
print(x_mm.mean(axis=0),x_mm.std(axis=0))

#正则化
nor_scale = preprocessing.Normalizer()
x_nor = nor_scale.fit_transform(x)
print(x_nor.mean(axis=0),x_nor.std(axis=0))

# 将分类特征或数据标签转换位独热编码
ohe = preprocessing.OneHotEncoder()
x1 = ([["大象"],["猴子"],["老虎"],["老鼠"]])
x_ohe = ohe.fit(x1).transform([["老虎"]]).toarray()
print(x_ohe)

# 简单划分数据
from sklearn.model_selection import train_test_split
from sklearn import datasets
import pandas as pd
X,y = datasets.load_iris(return_X_y=True)
X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.3)
print(X_train.shape,X_test.shape,y_train.shape,y_test.shape)

# K折交叉验证
from sklearn.model_selection import KFold
import numpy as np
X = np.random.randint(1,10,20)
kf = KFold(n_splits=5)
for train,test in kf.split(X):
    print(train,'\n',test)
    
# 留一法划分数据    
from sklearn.model_selection import LeaveOneOut
import numpy as np
X = np.random.randint(1,10,5)
kf = LeaveOneOut()
for train,test in kf.split(X):
    print(train,'\n',test)    

# 使用逻辑回归训练鸢尾花数据集
from sklearn.datasets import load_iris
dataSet = load_iris()
data = dataSet['data'] # 数据
label = dataSet['target'] # 数据对应的标签
feature = dataSet['feature_names'] # 特征的名称
target = dataSet['target_names'] # 标签的名称
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import ShuffleSplit
from sklearn.metrics import classification_report
from sklearn.metrics import roc_auc_score
ss = ShuffleSplit(n_splits = 1,test_size= 0.2) # 按比例拆分数据，80%用作训练
for tr,te in ss.split(data,label):
    xr = data[tr] # 训练数据
    xe = data[te] # 测试数据
    yr = label[tr] 
    ye = label[te]
    clf = LogisticRegression(solver = 'lbfgs',multi_class = 'multinomial') 
    clf.fit(xr,yr)
    predict = clf.predict(xe)
    print(classification_report(ye, predict)) 

from sklearn.model_selection import GridSearchCV,KFold,train_test_split
from sklearn.metrics import make_scorer , accuracy_score
from sklearn.tree  import DecisionTreeClassifier
from sklearn.datasets import load_breast_cancer


# load  data
data = load_breast_cancer()
X,y = data['data'] , data['target']

X_train,X_test,y_train,y_test = train_test_split(
    X,y,train_size=0.8 , random_state=0
)

regressor = DecisionTreeClassifier(random_state=0) # 决策树模型
parameters = {'max_depth':range(1,6)} # 参数列表
scorin_fnc = make_scorer(accuracy_score) # 评估函数采用准确率
kflod = KFold(n_splits=10) # 交叉验证 10折

grid = GridSearchCV(regressor,parameters,scoring=scorin_fnc,cv=kflod)
grid = grid.fit(X_train,y_train)
reg = grid.best_estimator_
print('best score:%f'%grid.best_score_)
#print('best parameters:%d' %grid.best_params_)
print(grid.best_params_)
print('test score : %f'%reg.score(X_test,y_test))

import matplotlib.pyplot as plt

# Import datasets, classifiers and performance metrics
from sklearn import datasets, svm, metrics
from sklearn.model_selection import train_test_split

digits = datasets.load_digits()

_, axes = plt.subplots(nrows=1, ncols=4, figsize=(10, 3))
for ax, image, label in zip(axes, digits.images, digits.target):
    ax.set_axis_off()
    ax.imshow(image, interpolation="nearest")
    ax.set_title("Training: %i" % label)
    
# flatten the images
n_samples = len(digits.images)
data = digits.images.reshape((n_samples, -1))
print(type(digits.images[0]))
# Split data into 50% train and 50% test subsets
X_train, X_test, y_train, y_test = train_test_split(
    data, digits.target, test_size=0.5, shuffle=False
)

# Create a classifier: a support vector classifier
clf = svm.SVC(gamma=0.001)
# Learn the digits on the train subset
clf.fit(X_train, y_train)
# Predict the value of the digit on the test subset
predicted = clf.predict(X_test)

print(
    f"Classification report for classifier {clf}:\n"
    f"{metrics.classification_report(y_test, predicted)}\n"
)

disp = metrics.ConfusionMatrixDisplay.from_predictions(y_test, predicted)
disp.figure_.suptitle("Confusion Matrix")
print(f"Confusion matrix:\n{disp.confusion_matrix}")

plt.show()

from sklearn.datasets import load_iris
from sklearn import tree

x,y = load_iris(return_X_y=True)
clf = tree.DecisionTreeClassifier()
clf = clf.fit(x,y)
tree.plot_tree(clf)