Python编程从入门到实践：数据处理与可视化

'''
@File    :   mpl_squares.py
@Time    :   2019/04/06 16:45:51
@Author  :   leacoder
@Version :   1.0
@Contact :   leacock1991@gmail.com
@License :   
@Desc    :   绘制折线图
'''
# here put the import lib
# 导入了模块pyplot 

import matplotlib.pyplot as plt

input_values = [1, 2, 3, 4, 5] # X 轴数据

squares = [1, 4, 9, 16, 25] # Y 轴数据
'''
plot(*args[, scalex, scaley, data])
绘制 x y 坐标组成的线
'''
plt.plot(input_values, squares, linewidth=5)

# 设置图表标题， 并给坐标轴加上标签
plt.title( "Square Numbers", fontsize = 24 )
plt.xlabel( "Value", fontsize = 14 )
plt.ylabel( "Square of Value", fontsize = 14 )

# 设置刻度标记的大小
plt.tick_params( axis = 'both', labelsize = 14 , colors = 'r' ) # axis 将参数应用于哪个轴

plt.show()  
'''
打开matplotlib查看器， 并显示绘制的图形
'''

'''
@File    :   random_walk.py
@Time    :   2019/04/06 17:39:26
@Author  :   leacoder
@Version :   1.0
@Contact :   leacock1991@gmail.com
@License :   
@Desc    :   Python来生成随机漫步数据
'''

# here put the import lib
from random import choice

class RandomWalk():
    """一个生成随机漫步数据的类"""

    def __init__(self, num_points=5000):
        """初始化随机漫步的属性"""
        self.num_points = num_points
        # 所有随机漫步都始于(0, 0)
        self.x_values = [0]
        self.y_values = [0]

    def fill_walk(self):
        # 不断漫步， 直到列表达到指定的长度
        while len(self.x_values) < self.num_points:
            # 决定前进方向以及沿这个方向前进的距离
            x_direction = choice([1, -1])
            x_distance = choice([0, 1, 2, 3, 4])
            x_step = x_direction * x_distance

            y_direction = choice([1, -1])
            y_distance = choice([0, 1, 2, 3, 4])
            y_step = y_direction * y_distance

            # 拒绝原地踏步
            if x_step == 0 and y_step == 0:
                continue

            # 计算下一个点的x和y值
            next_x = self.x_values[-1] + x_step
            next_y = self.y_values[-1] + y_step
            self.x_values.append(next_x)
            self.y_values.append(next_y)

'''
@File    :   rw_visual.py
@Time    :   2019/04/07 00:56:52
@Author  :   leacoder
@Version :   1.0
@Contact :   leacock1991@gmail.com
@License :   
@Desc    :   循环生成随机漫步数据并显示
'''

# here put the import lib


import matplotlib.pyplot as plt
from random_walk import RandomWalk


# 只要程序处于活动状态， 就不断地模拟随机漫步
while True:
    rw = RandomWalk(50000)
    rw.fill_walk()

    '''
    figure([num, figsize, dpi, facecolor, ...])
        Create a new figure.
        figsize : (float, float), optional, default: None
            width, height in inches. If not provided, defaults to rcParams["figure.figsize"] = [6.4, 4.8].
        dpi : integer, optional, default: None
            resolution of the figure. If not provided, defaults to rcParams["figure.dpi"] = 100.
    '''
    # 设置绘图窗口的尺寸
    plt.figure(figsize=(10, 6),dpi=128)

    point_numbers = list(range(rw.num_points))
    plt.scatter(rw.x_values, rw.y_values, s=1, c=point_numbers,
                cmap=plt.cm.Blues, edgecolor='none')

    # 突出起点和终点
    plt.scatter(0, 0, c='green', edgecolors='none', s=100)
    plt.scatter(rw.x_values[-1], rw.y_values[-1],
                c='red', edgecolors='none', s=100)

    '''
    The Axes class The Axes contains most of the figure elements: Axis, Tick, Line2D, Text, Polygon, etc., and sets the coordinate system.
    '''
    # 隐藏坐标轴
    plt.axes().get_xaxis().set_visible(False)   # Return the XAxis instance.
    plt.axes().get_yaxis().set_visible(False)   # Return the YAxis instance.

    plt.show()
    keep_running = input("Make another walk? (y/n): ")
    if keep_running == 'n':
        break

'''
@File    :   scatter_squares.py
@Time    :   2019/04/06 17:08:01
@Author  :   leacoder
@Version :   1.0
@Contact :   leacock1991@gmail.com
@License :   
@Desc    :   绘制散点图
'''

# here put the import lib
import matplotlib.pyplot as plt

'''
scatter(x, y[, s, c, marker, cmap, norm, ...])
绘制x y 坐标的散点图，并设置不同的 标记 大小 或 颜色等。
'''

x_values = [1, 2, 3, 4, 5]
y_values = [1, 4, 9, 16, 25]
color = ['r', 'g', 'b']

# s 标记大小 以磅为单位**2  c 颜色，序列或颜色序列
plt.scatter(x_values, y_values, s=100, c=color)

# 设置图表标题并给坐标轴加上标签
plt.title("Square Numbers", fontsize=24)
plt.xlabel("Value", fontsize=14)
plt.ylabel("Square of Value", fontsize=14)
# 设置刻度标记的大小
plt.tick_params(axis='both', which='major', labelsize=14)

plt.show()


# 循环绘制1000个点

x_values = list(range(1, 1001))
y_values = [x**2 for x in x_values]


'''
c : color, sequence, or sequence of color, optional
    A single color format string.
    A sequence of color specifications of length n.
    A sequence of n numbers to be mapped to colors using cmap and norm.  #使用cmap和norm映射到颜色的n个数字序列
    A 2-D array in which the rows are RGB or RGBA.

cmap : Colormap, optional, default: None  # cmap 告诉pyplot 使用哪个颜色映射

edgecolors : color or sequence of color, optional, default: 'face' # 边框颜色

'''

plt.scatter(x_values, y_values, s=40, c=y_values, cmap=plt.cm.Blues, edgecolor='none')

# 设置图表标题并给坐标轴加上标签
plt.title("Square Numbers", fontsize=24)
plt.xlabel("Value", fontsize=14)
plt.ylabel("Square of Value", fontsize=14)
# 设置刻度标记的大小
plt.tick_params(axis='both', which='major', labelsize=14)

'''
axis(*v, **kwargs)
获取或设置某些轴属性的便捷方法
xmin, xmax, ymin, ymax = axis()
xmin, xmax, ymin, ymax = axis(xmin, xmax, ymin, ymax)
xmin, xmax, ymin, ymax = axis(option)
xmin, xmax, ymin, ymax = axis(**kwargs)
'''
# 设置每个坐标轴的取值范围
plt.axis([0, 1100, 0, 1100000])

plt.show()

'''
@File    :   die.py
@Time    :   2019/04/06 21:53:11
@Author  :   leacoder
@Version :   1.0
@Contact :   leacock1991@gmail.com
@License :   
@Desc    :   骰子类
'''

# here put the import lib

from random import randint


class Die():
    """表示一个骰子的类"""

    def __init__(self, num_sides=6):
        """骰子默认为6面"""
        self.num_sides = num_sides

    def roll(self):
        """"返回一个位于1和骰子面数之间的随机值"""
        return randint(1, self.num_sides)
        '''
        def randint(a, b)
            Return random integer in range [a, b], including both end points.
        '''

'''
@File    :   die_visual.py
@Time    :   2019/04/06 21:56:06
@Author  :   leacoder
@Version :   1.0
@Contact :   leacock1991@gmail.com
@License :   
@Desc    :   模拟掷骰子并柱状图显示点数出现次数
'''

# here put the import lib

from die import Die

import pygal

# 创建两个D6
die_1 = Die(8)
die_2 = Die(8)

# 掷几次骰子， 并将结果存储在一个列表中
results = []
for roll_num in range(50000):
    result = die_1.roll()+die_2.roll()
    results.append(result)


# 分析结果
frequencies = []
max_result = die_1.num_sides + die_2.num_sides
for value in range(2, max_result+1):
    frequency = results.count(value)
    frequencies.append(frequency)

# 对结果进行可视化
hist = pygal.Bar()  # Basic simple bar graph:

hist.title = "Results of rolling a D8 and a D8 50,000  times."
x_labels = set()
for i in range(1,die_1.num_sides+1):
    for j in range(1, die_2.num_sides+1):
        x_label = i + j
        x_labels.add(x_label)

print(x_labels)

hist.x_labels = list(x_labels)
hist.x_title = "Result"
hist.y_title = "Frequency of Result"
# 使用add() 将一系列值添加到图表中（向它传递要给添加的值指定的标签， 还有一个列表， 其中包含将出现在图表中的值） 。
hist.add('D8 + D8', frequencies)
hist.render_to_file('die_visual.svg')  # 最后， 我们将这个图表渲染为一个SVG文件

'''
@File    :   highs_lows.py
@Time    :   2019/04/06 22:32:59
@Author  :   leacoder
@Version :   1.0
@Contact :   leacock1991@gmail.com
@License :   
@Desc    :   处理CSV文件数据，matplotlib绘制最高温度最低温度折线图
'''

# here put the import lib

# c sv 模块包含在Python标准库中
import csv

from matplotlib import pyplot as plt
# 模块datetime 处理日期
from datetime import datetime

# 从文件中获取日期、 最高气温和最低气温
filename = 'death_valley_2014.csv'

with open(filename) as f:
        # 创建一个与该文件相关联的阅读器（reader ） 对象
    reader = csv.reader(f)
    # 模块csv 包含函数next() ， 调用它并将阅读器对象传递给它时， 它将返回文件中的下一行。 在前面的代码中， 我们只调用了next() 一次， 因此得到的是文件的第一行， 其中包含文件头
    header_row = next(reader)

    dates, highs, lows = [], [], []
    for row in reader:  # 遍历文件中余下的各行
        try: # 错误检查
            current_date = datetime.strptime(row[0], "%Y-%m-%d")  # '2014-7-1
            high = int(row[1])
            low = int(row[3])
        except ValueError:
            print(current_date, 'missing data')
        else:
            dates.append(current_date)
            highs.append(high) 
            lows.append(low)


# 根据数据绘制图形
fig = plt.figure(dpi=123, figsize=(10, 6))

'''
plot(*args[, scalex, scaley, data])
    Plot y versus x as lines and/or markers.
        alpha: float  Set the alpha value used for blending - not supported on all backends.
'''
plt.plot(dates, highs, c='red', alpha=0.5)  # 绘制最高温度
plt.plot(dates, lows, c='blue', alpha=0.5)  # 绘制最低温度

'''
fill_between(x, y1[, y2, where, ...])
    Fill the area between two horizontal curves.
'''
plt.fill_between(dates, highs, lows, facecolor='blue', alpha=0.1)

# 设置图形的格式
plt.title("Daily high temperatures - 2014", fontsize=24)
plt.xlabel('', fontsize=16)
'''
autofmt_xdate(self, bottom=0.2, rotation=30, ha='right', which=None)
    Date ticklabels often overlap, so it is useful to rotate them and right align them.
    bottom : scalar
        The bottom of the subplots for subplots_adjust().
    rotation : angle in degrees
        The rotation of the xtick labels.
    ha : string
        The horizontal alignment of the xticklabels.
    which : {None, 'major', 'minor', 'both'}
        Selects which ticklabels to rotate. Default is None which works the same as major.


'''
fig.autofmt_xdate()

title = "Daily high and low temperatures - 2014\nDeath Valley, CA"
plt.title(title, fontsize=24)

'''
tick_params([axis])
    Change the appearance of ticks, tick labels, and gridlines. 更改刻度，刻度标签和网格线的外观
    axis : {'x', 'y', 'both'}, optional
        Which axis to apply the parameters to.
    which : {'major', 'minor', 'both'}
        Default is 'major'; apply arguments to which ticks.
'''
plt.tick_params(axis='both', which='major', labelsize=16)

plt.show()

'''
@File    :   countries.py
@Time    :   2019/04/06 23:42:39
@Author  :   leacoder
@Version :   1.0
@Contact :   leacock1991@gmail.com
@License :   
@Desc    :   处理国家识别码
'''

# here put the import lib

# from pygal.i18n import COUNTRIES 模块已被遗弃 但是现在可以在 pygal_maps_world 插件中找到它  pip3 install pygal_maps_world

from pygal.maps.world import COUNTRIES


def get_country_code(country_name):
    """根据指定的国家， 返回Pygal使用的两个字母的国别码"""
    for country_code in sorted(COUNTRIES.keys()):
        for code, name in COUNTRIES.items():
            if name == country_name:
                return code

        # 如果没有找到指定的国家， 就返回None
        return None

'''
@File    :   world_population.py
@Time    :   2019/04/06 23:36:41
@Author  :   leacoder
@Version :   1.0
@Contact :   leacock1991@gmail.com
@License :   
@Desc    :   对json文件格式的数据处理，通过pygal绘制世界人口地图
'''

# here put the import lib

''' 导入画地图的模块 '''
import pygal.maps.world

''' 解析json文件 '''
import json

'''世界地图的样式'''
import pygal
from pygal.style import RotateStyle  # 十六进制颜色
from pygal.style import LightColorizedStyle # 加亮地图的颜色

from country_codes import get_country_code


# 将数据加载到一个列表中
filename = 'population_data.json'
with open(filename) as f:
    pop_data = json.load(f)

# 创建一个包含人口数量的字典
cc_populations = {}

for pop_dict in pop_data:
    if pop_dict['Year'] == '2010':
        country_name = pop_dict['Country Name']
        # population = int(pop_dict['Value']) # '1127437398.85751'  Python不能直接将包含小数点的字符串'1127437398.85751' 转换为整数
        # 先将字符串转换为浮点数， 再将浮点数转换为整数：
        population = int(float(pop_dict['Value']))

        code = get_country_code(country_name)
        if code:
            cc_populations[code] = population
        else:
            print('ERROR - ' + country_name)

# 根据人口数量将所有的国家分成三组
cc_pops_1, cc_pops_2, cc_pops_3 = {}, {}, {}
for cc, pop in cc_populations.items():

    if pop < 10000000:
        cc_pops_1[cc] = pop
    elif pop < 1000000000:
        cc_pops_2[cc] = pop
    else:
        cc_pops_3[cc] = pop

# 看看每组分别包含多少个国家
print(len(cc_pops_1), len(cc_pops_2), len(cc_pops_3))
    
'''
class pygal.style.RotateStyle(color, step=10, max_=None, base_style=None, **kwargs)
    Create a style by rotating the given color
'''
wm_style = RotateStyle('#336699', base_style=LightColorizedStyle) # 十六进制颜色码 
# wm = pygal.Worldmap()  # 已不可用 使用.maps.world.World()替代
wm = pygal.maps.world.World()  # 初始化一个地图对象
wm.style = wm_style # 设置地图的风格
wm.title = 'World Population in 2010, by Country'
#wm.add('2010', cc_populations)
wm.add('0-10m', cc_pops_1)
wm.add('10m-1bn', cc_pops_2)
wm.add('>1bn', cc_pops_3)
wm.render_to_file('world_population.svg')