DEEPlearning

skl4

# -*- coding: utf-8 -*-
"""
Spyder Editor

This is a temporary script file.
"""

import numpy as np
from sklearn import datasets
from sklearn.cross_validation import train_test_split
from sklearn.neighbors import KNeighborsClassifier

iris = datasets.load_iris()
iris_X = iris.data
iris_y = iris.target

#print (iris_X[:2, :])
#print(iris_y)
X_train, X_test, y_train, y_test = train_test_split(
        iris_X, iris_y, test_size = 0.3)

#print(y_train)
#会打乱数据

knn = KNeighborsClassifier()
knn.fit(X_train, y_train)
#自动完成train,knn是已经预测好了的

print(knn.predict(X_test))
print(y_test)

y_pre = knn.predict(X_test)
print (np.sum(y_pre - y_test))

 skl5

使用数据

# -*- coding: utf-8 -*-
"""
Spyder Editor

This is a temporary script file.
"""

import numpy as np
from sklearn import datasets
from sklearn.linear_model import LinearRegression

loaded_data = datasets.load_boston()
data_X = loaded_data.data #属性
data_y = loaded_data.target

model = LinearRegression()
model.fit(data_X, data_y)

print (model.predict(data_X[:4,:]))
print (data_y[:4])

自己创建数据

import numpy as np
from sklearn import datasets
from sklearn.linear_model import LinearRegression
import matplotlib.pyplot as plt

X, y = datasets.make_regression(n_samples = 100,
                                n_features = 1,
                                n_targets = 1,
                                noise = 1)


plt.scatter(X,y)
plt.show()

skl6

属性

from sklearn import datasets
from sklearn.linear_model import LinearRegression


loaded_data = datasets.load_boston()
data_X = loaded_data.data
data_y = loaded_data.target

model = LinearRegression()
model.fit(data_X, data_y)

print(model.predict(data_X[:4,:]))
print(model.score(data_X, data_y))
#0.7406
#R^2 coeddicient of determination

skl7

normalization

from sklearn import preprocessing

X = preprocessing.scale(X)

from sklearn import preprocessing
import numpy as np
from sklearn.cross_validation import train_test_split
from sklearn.datasets.samples_generator import make_classification
from sklearn.svm import SVC
import matplotlib.pyplot as plt

a = np.array([[10, 2.7, 3.6],
             [-100, 5, -2],
             [120, 20, 40]], dtype = np.float64)
#print(a)
#print(preprocessing.scale(a))

X,y = make_classification(n_samples = 300, n_features = 2,
                          n_redundant = 0, n_informative = 2,
                          random_state = 22, n_clusters_per_class = 1, 
                          scale = 100)
#plt.scatter(X[:,0], X[:,1], c=y)
#plt.show()

#X = preprocessing.minmax_scale(X,feature_range = (0,1))
X = preprocessing.scale(X)
X_train, X_test,y_train,y_test = train_test_split(X, y,test_size = 0.3)
clf = SVC()
clf.fit(X_train, y_train)
print(clf.score(X_test, y_test))