# -*- coding: utf-8 -*-
import csv
import inspect
import math
import numpy as np
from sklearn import preprocessing
import multiprocessing
import sys
def max_min_normalization(data_list):
"""
利用最大最小数将一组数据进行归一化输出
x_new = (x - min) / (max - min)
:param data_list:
:return:
"""
normalized_list = []
max_min_interval = max(data_list) - min(data_list)
for data in data_list:
data = float(data)
new_data = (data - min(data_list)) / max_min_interval
normalized_list.append(round(new_data, 3))
return normalized_list
def mean_normalization(data_list):
"""
利用平均数将一组数据进行标准化输出
标准化的结果不一定是在0,1之间
x_new = (x - mean) / (max - min)
:param data_list:
:return:
"""
normalized_list = []
mean = sum(data_list) / len(data_list)
max_min_interval = max(data_list) - min(data_list)
for data in data_list:
data = float(data)
new_data = (data - mean) / max_min_interval
normalized_list.append(round(new_data, 3))
return normalized_list
def zscores_normalization(data_list):
"""
利用z-scores方法针对数据进行标准化
:param data_list:
:return:
"""
normalized_list = []
mean = sum(data_list, 0.0) / len(data_list)
var_lst = []
for data in data_list:
var_lst.append((float(data) - mean) ** 2)
std_value = math.sqrt(sum(var_lst) / len(var_lst))
for data in data_list:
normalized_list.append(round((data - mean) / std_value, 3))
return normalized_list
def max_min_normalization_using_numpy(data_list):
"""
用数据处理包numpy归一化
:param data_list:
:return:
"""
normalized_list = []
max = np.max(data_list)
min = np.min(data_list)
for data in data_list:
new_data = (float(data) - min) / (max - min)
normalized_list.append(round(new_data, 3))
return normalized_list
def zscores_normalization_using_numpy(data_list):
"""
利用numpy中现有的方法计算标准差和平均数，然后用z-scores方法针对数据进行标准化
:param data_list:
:return:
"""
normalized_list = []
mean = np.mean(data_list)
std = np.std(data_list)
for data in data_list:
normalized_list.append(round((data - mean) / std, 3))
return normalized_list
def normalize_data_using_sk(data_list):
"""
利用sklearn学习库自带的归一方法实现
:param data_list:
:return:
"""
data_array = np.asarray(data_list, 'float').reshape(1, -1)
new_data = preprocessing.minmax_scale(data_array, axis=1)
return np.round(new_data, 3)[0, :]
def colunmn1(self):
print('colunmn1 as follow')
with open('Iris.csv', 'r') as csvfile:
reader = csv.DictReader(csvfile)
column1 = [row['SepalLengthCm'] for row in reader] ##
data_list1 = [float(x) for x in column1]
data1 = globals().copy()
for key1 in data1:
if inspect.isfunction(data1[key1]):
res1 = data1[key1](data_list1)
print('%s:\n%s' % (key1, res1))
colunmn1('a')
python3.7
问题就出在最后一个函数上，column1函数的目的是要读取表格数据，供其他函数调用处理，直接将表格数据做成列表不就行了，不必要通过globals()函数来遍历所有全局变量及其值。建议将最后一个函数修改，不要写成函数，将语句并入main主函数里，获取列表后，分别调用其他函数进行数据处理。
。。。你这明显要依托表格Iris.csv的吧，抛开数据单谈逻辑行不通啊哥们儿
def colunmn1(self): 这个方法参数self是干嘛的？ 看里面都没用到，还需要传参 么