python编程实用技巧

1. 定义二维数组

a = [[0] * 3 for i in range(3)]

2. 求两个集合的笛卡尔积

import itertools as it
a = [1,2,3]
b = [4,5,6]
for c in it.product(a,b):
    print(c)

 3.推导式

variable = [out_exp_res for out_exp in input_list if out_exp == 2]
  　　out_exp_res:　　列表生成元素表达式，可以是有返回值的函数。
  　　for out_exp in input_list：　　迭代input_list将out_exp传入out_exp_res表达式中。
  　　if out_exp == 2：　　根据条件过滤哪些值可以。

#example
def squared(x):
    return x*x
multiples = [squared(i) for i in range(30) if i % 3 is 0]
print multiples
# Output: [0, 9, 36, 81, 144, 225, 324, 441, 576, 729]

4.求两序列的相关系数

import pandas as pd
src = r'datafill.csv'
data = pd.read_csv(src, parse_dates=[0],index_col='TIME')
print(data[['zhexi_in','xiaoxi_out','zhexi_add','xinhua_add','lengshuijiang_add']].corr()['zhexi_in'])
#result
##zhexi_in             1.000000
##xiaoxi_out           0.806205
##zhexi_add            0.145267
##xinhua_add           0.165155
##lengshuijiang_add    0.117305
##Name: zhexi_in, dtype: float64

 5. 画3D图

from matplotlib import pyplot as plt
from matplotlib.pylab import rcParams
rcParams['figure.figsize'] = 15, 9
from mpl_toolkits.mplot3d import Axes3D

fig = plt.figure()
ax = fig.gca(projection='3d')
x = np.arange(1024)
y = np.arange(1024)
z = np.random.rand(1024)
ax.scatter(x,np.zeros(1024),z,color = '#00CED1' , alpha = 0.2 , label = 'DDDDD')
ax.plot(x,np.zeros(1024)+1,z,color = '#0567D1' , alpha = 0.2 , label = 'DDDDD')
ax.text(0,0,0,'DDDDDD',color='r',ha='center', va='bottom', fontsize=10)
ax.set_xlabel('x')
ax.set_ylabel('y')
ax.set_zlabel('z)')
plt.show()
plt.close()

6. 随机得到训练集和测试集

from sklearn.model_selection import train_test_split
train_x, test_x, train_y, test_y = train_test_split(x, y, test_size=0.1,random_state=self.get_random_state())
# random_state用于设置随机数种子，test_size为测试集的大小

7.求均方误差MSE

from sklearn.metrics import mean_squared_error
mse = mean_squared_error(predict,test_y)

8.一些可以解决回归问题的算法

from sklearn import linear_model as lm
import xgboost as xgb
from sklearn import ensemble
def set_models(self):
        self.models = { 'BayesianRidge':lm.BayesianRidge(),
                        'LinearRegression':lm.LinearRegression(),
                        'Ridge':lm.Ridge(),
                        'Lasso':lm.Lasso(),
                        'LassoLars':lm.LassoLars(),
                        'GradientBoostingRegressor':ensemble.GradientBoostingRegressor(),
                        'BaggingRegressor':ensemble.BaggingRegressor(),
                        'RandomForestRegressor':ensemble.RandomForestRegressor(criterion='mse'),
                        'ensemble.AdaBoostRegressor':ensemble.AdaBoostRegressor(),
                        'XGBRegressor':xgb.XGBRegressor(n_estimators=230, min_child_weight=2)
                      }

9.获取字符的assic码

ord('a')
#结果为97

10.在本地建文件夹

import os
if not os.path.exists(self.result_path + name +'/non_add_rain/'):
                    os.makedirs(self.result_path + name +'/non_add_rain/')

　listglob = glob.glob(r"/home/xxx/picture/*.png") #通配符，找到所有满足条件的文件

　file_name = os.path.basename(r"/home/xxx/picture/hello.png") #file_name = 'hello.png'
　prefix,suffix = os.path.splitext(file_name) #'hello'   'png'