python基础代码

from heapq import *;
from collections import *;
import random as rd;
import operator as op;
import re;

data = [2,2,6,7,9,12,34,0,76,-12,45,79,102];
s = set();

for num in data:
    s.add(data.pop(0));
    if s.__len__() == 4:
        break;

heap = [];
for n in s:
    heappush(heap,n);

print(heap);


for num in data:
    if num > heap[0]:
        heapreplace(heap,num);

print(nlargest(4,heap))


def file2matrix(path,dimension):
    with open(path,'r+') as fr:
        lines = fr.readlines();
        num_lines = len(lines);
        return_mat = np.zeros((num_lines,dimension));
        classLabel = [];

    index = 0;
    for line in lines:
        contents = line.strip().split(' ');
        li = contents[:dimension];
        li = list(map(float,li));
        return_mat[index,:] = li;

        if(contents[-1] == 'small'):
            classLabel.append(0);
        elif(contents[-1] == 'middle'):
            classLabel.append(1)
        elif (contents[-1] == 'large'):
            classLabel.append(2)
        index += 1;

    return return_mat, classLabel;

#mat,label = file2matrix('G:\test.txt',3);

import collections;
print(dir(collections))

class MyObject:
    def __init__(self,score):
        self.score = score;

    def __repr__(self):
        return "MyObject(%s)" % self.score;

objs = [MyObject(i) for i in range(5)];
rd.shuffle(objs);
print(objs);

g = op.attrgetter("score");
scores = [g(i) for i in objs];
print("scores: ",scores);
print(sorted(objs,key = g));

l = [(i,i*-2) for i in range(4)]
print ("tuples: ", l)
g = op.itemgetter(1)
vals = [g(i) for i in l]
print ("values:", vals)
print ("sorted:", sorted(l, key=g))


class MyObj(object):
    def __init__(self, val):
        super(MyObj, self).__init__()
        self.val = val
        return

    def __str__(self):
        return "MyObj(%s)" % self.val

    def __lt__(self, other):
        return self.val < other.val

    def __add__(self, other):
        return MyObj(self.val + other.val)


a = MyObj(1)
b = MyObj(2)

print(op.lt(a, b))

print(op.add(a, b))



items = [('A', 1),('B', 2),('C', 3)]
regular_dict = dict(items);
order_dict = OrderedDict(items);
print(regular_dict);
print(order_dict);


# -*- coding: utf-8 -*-
import numpy as np
import matplotlib.pyplot as plt
from matplotlib.lines import Line2D

x = np.linspace(0, 10, 1000)
y = np.sin(x)
z = np.cos(x**2)

fig = plt.figure(figsize=(8,4),dpi=120)
plt.plot(x,y,label="$sin(x)$",color="red",linewidth=2)
plt.plot(x,z,"b--",label="$cos(x^2)$")
plt.xlabel("Time(s)")
plt.ylabel("Volt")
plt.title("PyPlot First Example")
plt.ylim(-1.2,1.2)
plt.legend()
#plt.show()


f = plt.gcf();
all_lines = plt.getp(f.axes[0],'lines');
print(all_lines[0])

fig = plt.figure()
line1 = Line2D([0,1],[0,1], transform=fig.transFigure, figure=fig, color="r")
line2 = Line2D([0,1],[1,0], transform=fig.transFigure, figure=fig, color="g")
fig.lines.extend([line1, line2])
fig.show()

def autonorm(dataSet):
    minVals = dataSet.min(0);
    maxVals = dataSet.max(0);
    ranges = maxVals - minVals;
    rows = dataSet.shape[0];
    ranges = np.tile(ranges,(rows,1));
    dataSet = dataSet - np.tile(minVals,(rows,1));
    normData = dataSet / ranges;
    return normData;


def classify(inX,path,k):
    #1.文件到矩阵的映射
    labels,dataSet = file2matrix(path);
    #2.矩阵归一化处理
    dataSet = autonorm(dataSet);
    #3.计算欧式距离
    distance = dataSet - inX;
    distance = np.square(distance);
    distance = distance.sum(axis=1);
    distance = np.sqrt(distance);
    print(distance);
    #4.对距离排序
    sortdisIndices = distance.argsort();
    #5.取前k个，加载到dict中，然后对dict排序，取首个值
    classCount = {};
    for index in range(k):
        label = labels[sortdisIndices[index]];
        print(label)
        classCount[label] = classCount.get(label,0) + 1;

    sortedDict = sorted(classCount.items(),key=op.itemgetter(1),reverse=True);
    return sortedDict[0][0];

def file2matrix(filepath):
    with open(filepath,'r+') as fr:
        lines = fr.readlines();
        num_lines = len(lines);
        classLabelVector = [];
        dimension = len(lines[0].strip().split(" "))-1;
        dataSet = np.zeros((num_lines,dimension));

    index = 0;
    for line in lines:
        contents = line.strip().split(" ");
        li = contents[:dimension];
        li = list(map(float,li));
        dataSet[index,:] = li;

        if contents[-1] == 'largeDoses':
            classLabelVector.append(3);
        elif contents[-1] == 'smallDoses':
            classLabelVector.append(2);
        elif contents[-1] == 'didntLike':
            classLabelVector.append(1);
        index += 1;

    return classLabelVector,dataSet;




def main():

    inX = np.array([1.2,1.0,0.8]);
    label = classify(inX,"E:\Python\datingTestSet.txt",3);
    print("class:",label);


if __name__ == '__main__':
    main();