sklearn 學習筆記1

import pickle
import os
import numpy as np
#
# # 引入數據集，sklearn包含衆多數據集
# from sklearn import datasets
# # 將數據分爲測試集和訓練集
# from sklearn.model_selection import train_test_split
# #SVM
# from sklearn import svm
# #森林迴歸
# from sklearn.ensemble import RandomForestClassifier
# # 利用鄰近點方式訓練數據
# from sklearn.neighbors import KNeighborsClassifier
#
# # 引入數據,本次導入鳶尾花數據，iris數據包含4個特徵變量
# iris = datasets.load_iris()
# # 特徵變量
# iris_X = iris.data
# # print(iris_X)
# print('特徵變量的長度', len(iris_X))
# # 目標值
# iris_y = iris.target
# print('鳶尾花的目標值', iris_y)
# # 利用train_test_split進行訓練集和測試機進行分開，test_size佔30%
# X_train, X_test, y_train, y_test = train_test_split(iris_X, iris_y, test_size=0.3)
# # 我們看到訓練數據的特徵值分爲3類
# # print(y_train)
# '''
# [1 1 0 2 0 0 0 2 2 2 1 0 2 0 2 1 0 1 0 2 0 1 0 0 2 1 2 0 0 1 0 0 1 0 0 0 0
#  2 2 2 1 1 1 2 0 2 0 1 1 1 1 2 2 1 2 2 2 0 2 2 2 0 1 0 1 0 0 1 2 2 2 1 1 1
#  2 0 0 1 0 2 1 2 0 1 2 2 2 1 2 1 0 0 1 0 0 1 1 1 0 2 1 1 0 2 2]
#  '''
# # 訓練數據
# # 引入訓練方法
# knn  = svm.SVC()
# # 進行填充測試數據進行訓練
# knn.fit(X_train, y_train)
#
# params = knn.get_params()
# print(params)
# '''
# {'algorithm': 'auto', 'leaf_size': 30, 'metric': 'minkowski',
#  'metric_params': None, 'n_jobs': None, 'n_neighbors': 5,
#  'p': 2, 'weights': 'uniform'}
#
# '''
#
# score = knn.score(X_test, y_test)
# print("預測得分爲：%s" % score)
# '''
# 預測得分爲：0.9555555555555556
# [1 2 1 1 2 2 1 0 0 0 0 1 2 0 1 0 2 0 0 0 2 2 0 2 2 2 2 1 2 2 2 1 2 2 1 2 0
#  2 1 2 1 1 0 2 1]
# [1 2 1 1 2 2 1 0 0 0 0 1 2 0 1 0 2 0 0 0 1 2 0 2 2 2 2 1 1 2 2 1 2 2 1 2 0
#  2 1 2 1 1 0 2 1]
# '''
#
# # 預測數據，預測特徵值
# print(knn.predict(X_test))
# '''
# [0 2 2 2 2 0 0 0 0 2 2 0 2 0 2 1 2 0 2 1 0 2 1 0 1 2 2 0 2 1 0 2 1 1 2 0 2
#  1 2 0 2 1 0 1 2]
# '''
# # 打印真實特徵值
# print(y_test)
# '''
# [1 2 2 2 2 1 1 1 1 2 1 1 1 1 2 1 1 0 2 1 1 1 0 2 0 2 0 0 2 0 2 0 2 0 2 2 0
#  2 2 0 1 0 2 0 0]
#
# '''
#
#
# # save model in path
# def save_model(path, model):
#     f = open(path, 'wb')
#     pickle.dump(model, f)
#     f.close()
#
# save_model(os.path.join('H:\wamp64\www\python', 'knn.pickle'), knn)










heat_f = open('H:\wamp64\www\python\knn.pickle', 'rb')
reg_tree_cer = pickle.load(heat_f)

# 做出預測
print('開始預測...')
X_heat = [ 5.1,           3.5,            1.4,           0.2]
# X_heat = [ 5.5,           3.2,            3,           0.8]
X_heat = [ 10,           2,            6,          2.8]
x_new = np.array(X_heat).reshape(1, -1)
result_heat = reg_tree_cer.predict(x_new)
print(result_heat)



from sklearn import datasets

import matplotlib.pyplot as plt

from sklearn import preprocessing
data = [[0, 0], [1, 0], [-1, 1], [1, 2]]

scalerstd = preprocessing.StandardScaler().fit(data)

print(scalerstd.mean_)
print(scalerstd.var_)