机器学习第二天

把sklearn今天学到的整理一下

#用datasets里面的数据，fit可以做训练
from __future__ import print_function
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.coef_)
print(model.intercept_)
print(model.get_params())
print(model.score(data_X, data_y)) # R^2 coefficient of determination

#注意训练集分割语句，可以用cross_val_score同时做fit和score??
from __future__ import print_function
from sklearn.datasets import load_iris
from sklearn.cross_validation import train_test_split
from sklearn.neighbors import KNeighborsClassifier

iris = load_iris()
X = iris.data
y = iris.target

# test train split #
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=4)
knn = KNeighborsClassifier(n_neighbors=5)
knn.fit(X_train, y_train)
y_pred = knn.predict(X_test)
print(knn.score(X_test, y_test))

# this is cross_val_score #
from sklearn.cross_validation import cross_val_score
knn = KNeighborsClassifier(n_neighbors=5)
scores = cross_val_score(knn, X, y, cv=5, scoring='accuracy')
print(scores)

# this is how to use cross_val_score to choose model and configs #
from sklearn.cross_validation import cross_val_score
import matplotlib.pyplot as plt
k_range = range(1, 31)
k_scores = []
for k in k_range:
    knn = KNeighborsClassifier(n_neighbors=k)
##    loss = -cross_val_score(knn, X, y, cv=10, scoring='mean_squared_error') # for regression
    scores = cross_val_score(knn, X, y, cv=10, scoring='accuracy') # for classification
    k_scores.append(scores.mean())

plt.plot(k_range, k_scores)
plt.xlabel('Value of K for KNN')
plt.ylabel('Cross-Validated Accuracy')
plt.show()

#标准化，缩小数据range提高准确率，向量机啥的还是不会需要看看
from __future__ import print_function
from sklearn import preprocessing
import numpy as np
from sklearn.model_selection 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.scale(X)    # normalization step
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.3)
clf = SVC()
clf.fit(X_train, y_train)
print(clf.score(X_test, y_test))